edit

.gitignore

@@ -0,0 +1,61 @@
+# ---> Python
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+.DS_Store
+

LICENSE

@@ -0,0 +1,72 @@
+Apache License 
+Version 2.0, January 2004 
+http://www.apache.org/licenses/
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+"License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document.
+
+"Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License.
+
+"Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity.
+
+"You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License.
+
+"Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files.
+
+"Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
+
+"Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below).
+
+"Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof.
+
+"Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
+
+"Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
+
+(a) You must give any other recipients of the Work or Derivative Works a copy of this License; and
+
+(b) You must cause any modified files to carry prominent notices stating that You changed the files; and
+
+(c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and
+
+(d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License.
+
+You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+APPENDIX: How to apply the Apache License to your work.
+
+To apply the Apache License to your work, attach the following boilerplate notice, with the fields enclosed by brackets "[]" replaced with your own identifying information. (Don't include the brackets!) The text should be enclosed in the appropriate comment syntax for the file format. We also recommend that a file or class name and description of purpose be included on the same "printed page" as the copyright notice for easier identification within third-party archives.
+
+Copyright [yyyy] [name of copyright owner]
+
+Licensed under the Apache License, Version 2.0 (the "License"); 
+you may not use this file except in compliance with the License. 
+You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software 
+distributed under the License is distributed on an "AS IS" BASIS, 
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 
+See the License for the specific language governing permissions and 
+limitations under the License.

README.md

@@ -0,0 +1,81 @@
+# dever-manage 小型编排工具
+<pre>
+git clone http://git.shemic.com:3000/dever/dm.git
+cd dm
+chmod +x install
+./install
+</pre>
+
+无需关注是否安装了docker，本工具会自动安装docker
+
+基础指令：
+<pre>
+更新代码：dm up
+使用docker工具包(默认已经使用该工具包)：dm use docker
+使用哪个仓库为主(默认aliyun)：dm set private|aliyun|hub
+删除某一个软件：dm rm web-php
+</pre>
+
+<pre>
+当前使用的工具包为docker时，可以使用以下命令开启web：
+启动全部：dm run web
+启动某一个软件：dm run web-mysql
+删除全部：dm rm web
+删除某一个软件：dm rm web-php
+</pre>
+
+执行完之后，请用浏览器访问你的ip即可。修改nginx配置可到container/conf/web/nginx下。
+
+<pre>
+目录说明：
+1、container：容器内的文件
+2、data：生成的数据目录，可以用作备份
+3、src：源码
+</pre>
+
+<pre>
+指令传参说明：
+
+-h 查看帮助 
+-a or --action 方法名
+-n or --name 配置文件名或行为名
+-p or --param 执行参数，一般要根据name判断
+
+docker方法列表：
+1、show：显示当前启动的docker容器
+2、showi：显示当前的docker镜像
+3、rm：删除出现异常或者没有启动的docker容器
+4、rmi：删除过期的docker镜像
+5、package：显示可用的docker镜像(2017-07-25)
+
+方法列表（带有name参数）：
+1、run：运行容器
+2、stop：停止容器
+3、crate：创建容器
+4、call：运行容器，仅运行一次，用于执行一些特殊指令
+5、up：运行容器并更新docker镜像
+6、rm：删除正在运行的docker容器
+7、save：保存或备份正在运行的docker容器
+8、load：将保存或备份的docker容器恢复并重新运行
+9、show：显示当前启动的docker容器(2017-07-25)
+
+例子：
+1、dever -a run -n web-php：根据src/docker/conf/web.conf里的php配置，来持续运行php容器
+2、dever -a run -n tool-apidoc -p input=demo^out=output：根据src/docker/conf/tool.conf里的apidoc配置，来运行apidoc容器，这个配置里设置了run参数，指令中加入run，则apidoc容器将作为工具使用，无需持续运行apidoc容器，仅执行一次。input=demo将替换{$input}为demo，out=output将替换{$out}为output，冒号“:”为默认值
+容器的配置请修改src/docker/conf/*.conf
+
+也可以使用无参数名的方式来传入参数：
+1、dm run web-php
+2、dm call tool-apidoc input=demo^out=output
+
+2017-07-25更新：
+当使用dm run之后，会自动生成这个容器的基本指令，比如执行了上述的dm run web-php
+
+之后可以这样使用：
+1、web-php: 进入该容器的sh命令行
+2、web-php logs：查看该容器启动日志
+3、web-php inspect：查看该容器的基本信息
+4、web-php stop：停止该容器
+5、web-php rm：停止并删除该容器，等同于dever rm web php
+6、web-php show：显示该容器的状态
+</pre>

container/conf/db/influxdb/influxdb.conf

@@ -0,0 +1,126 @@
+reporting-disabled = false
+bind-address = "0.0.0.0:8088"
+
+[meta]
+  dir = "/var/lib/influxdb/meta"
+  retention-autocreate = true
+  logging-enabled = true
+
+[data]
+  dir = "/var/lib/influxdb/data"
+  index-version = "inmem"
+  wal-dir = "/var/lib/influxdb/wal"
+  wal-fsync-delay = "0s"
+  query-log-enabled = true
+  cache-max-memory-size = 1073741824
+  cache-snapshot-memory-size = 26214400
+  cache-snapshot-write-cold-duration = "10m0s"
+  compact-full-write-cold-duration = "4h0m0s"
+  max-series-per-database = 1000000
+  max-values-per-tag = 100000
+  max-concurrent-compactions = 0
+  trace-logging-enabled = false
+
+[coordinator]
+  write-timeout = "10s"
+  max-concurrent-queries = 0
+  query-timeout = "0s"
+  log-queries-after = "0s"
+  max-select-point = 0
+  max-select-series = 0
+  max-select-buckets = 0
+
+[retention]
+  enabled = true
+  check-interval = "30m0s"
+
+[shard-precreation]
+  enabled = true
+  check-interval = "10m0s"
+  advance-period = "30m0s"
+
+[monitor]
+  store-enabled = true
+  store-database = "_internal"
+  store-interval = "10s"
+
+[subscriber]
+  enabled = true
+  http-timeout = "30s"
+  insecure-skip-verify = false
+  ca-certs = ""
+  write-concurrency = 40
+  write-buffer-size = 1000
+
+[http]
+  enabled = true
+  bind-address = "0.0.0.0:8086"
+  auth-enabled = false
+  log-enabled = true
+  write-tracing = false
+  pprof-enabled = true
+  https-enabled = false
+  https-certificate = "/etc/ssl/influxdb.pem"
+  https-private-key = ""
+  max-row-limit = 0
+  max-connection-limit = 0
+  shared-secret = ""
+  realm = "InfluxDB"
+  unix-socket-enabled = false
+  bind-socket = "/var/run/influxdb.sock"
+
+[[graphite]]
+  enabled = false
+  bind-address = "0.0.0.0:2003"
+  database = "graphite"
+  retention-policy = ""
+  protocol = "tcp"
+  batch-size = 5000
+  batch-pending = 10
+  batch-timeout = "1s"
+  consistency-level = "one"
+  separator = "."
+  udp-read-buffer = 0
+
+[[collectd]]
+  enabled = false
+  bind-address = "0.0.0.0:25826"
+  database = "collectd"
+  retention-policy = ""
+  batch-size = 5000
+  batch-pending = 10
+  batch-timeout = "10s"
+  read-buffer = 0
+  typesdb = "/usr/share/collectd/types.db"
+  security-level = "none"
+  auth-file = "/etc/collectd/auth_file"
+
+[[opentsdb]]
+  enabled = false
+  bind-address = "0.0.0.0:4242"
+  database = "opentsdb"
+  retention-policy = ""
+  consistency-level = "one"
+  tls-enabled = false
+  certificate = "/etc/ssl/influxdb.pem"
+  batch-size = 1000
+  batch-pending = 5
+  batch-timeout = "1s"
+  log-point-errors = true
+
+[[udp]]
+  enabled = false
+  bind-address = "0.0.0.0:8089"
+  database = "udp"
+  retention-policy = ""
+  batch-size = 5000
+  batch-pending = 10
+  read-buffer = 0
+  batch-timeout = "1s"
+  precision = ""
+
+[continuous_queries]
+  log-enabled = true
+  enabled = true
+  run-interval = "1s"
+

container/conf/db/mysql/my.conf

@@ -0,0 +1,152 @@
+# Example MariaDB config file for medium systems.                             
+#                                                                             
+# This is for a system with little memory (32M - 64M) where MariaDB plays     
+# an important part, or systems up to 128M where MariaDB is used together with
+# other programs (such as a web server)                                    
+#                                                                          
+# MariaDB programs look for option files in a set of                       
+# locations which depend on the deployment platform.                       
+# You can copy this option file to one of those                            
+# locations. For information about these locations, do:                    
+# 'my_print_defaults --help' and see what is printed under                 
+# Default options are read from the following files in the given order:    
+# More information at: http://dev.mysql.com/doc/mysql/en/option-files.html 
+#                                                                          
+# In this file, you can use all long options that a program supports.      
+# If you want to know which options a program supports, run the program    
+# with the "--help" option.                                                
+                                                                           
+# The following options will be passed to all MariaDB clients              
+[client]                                                                   
+#password       = 123456                                            
+port            = 3306                                                     
+socket          = /run/mysqld/mysqld.sock                                  
+                                                                           
+# Here follows entries for some specific programs                          
+                                                                           
+# The MariaDB server                                                       
+[mysqld] 
+skip-name-resolve
+skip-host-cache
+user=root                 
+port            = 3306                                                     
+socket          = /run/mysqld/mysqld.sock                                  
+skip-external-locking                                                      
+key_buffer_size = 16M                                                      
+max_allowed_packet = 1M                                                    
+table_open_cache = 64                                                      
+sort_buffer_size = 512K                                                    
+net_buffer_length = 8K                                                     
+read_buffer_size = 256K                                                    
+read_rnd_buffer_size = 512K                                                
+myisam_sort_buffer_size = 8M                                               
+                                                                           
+# Point the following paths to different dedicated disks                   
+#tmpdir         = /tmp/                                                    
+                                                                           
+# Don't listen on a TCP/IP port at all. This can be a security enhancement,
+# if all processes that need to connect to mysqld run on the same host.    
+# All interaction with mysqld must be made via Unix sockets or named pipes.
+# Note that using this option without enabling named pipes on Windows      
+# (via the "enable-named-pipe" option) will render mysqld useless!         
+#                                                                          
+#skip-networking                                                           
+                                                                           
+# Replication Master Server (default)                                      
+# binary logging is required for replication                               
+#log-bin=mysql-bin                                                          
+                                                                           
+# binary logging format - mixed recommended                                
+#binlog_format=mixed                                                        
+                                                                           
+# required unique id between 1 and 2^32 - 1                                
+# defaults to 1 if master-host is not set                                  
+# but will not function as a master if omitted                             
+server-id       = 1                                                        
+                                                                           
+# Replication Slave (comment out master section to use this)               
+#                                                                          
+# To configure this host as a replication slave, you can choose between
+# two methods :                                                               
+#                                                                          
+# 1) Use the CHANGE MASTER TO command (fully described in our manual) -    
+#    the syntax is:                                                        
+#                                                                          
+#    CHANGE MASTER TO MASTER_HOST=<host>, MASTER_PORT=<port>,              
+#    MASTER_USER=<user>, MASTER_PASSWORD=<password> ;                      
+#                                                                          
+#    where you replace <host>, <user>, <password> by quoted strings and    
+#    <port> by the master's port number (3306 by default).                 
+#                                                                          
+#    Example:                                                              
+#                                                                          
+#    CHANGE MASTER TO MASTER_HOST='125.564.12.1', MASTER_PORT=3306,        
+#    MASTER_USER='joe', MASTER_PASSWORD='secret';                          
+#                                                                          
+# OR                                                                       
+#                                                                          
+# 2) Set the variables below. However, in case you choose this method, then
+#    start replication for the first time (even unsuccessfully, for example
+#    if you mistyped the password in master-password and the slave fails to
+#    connect), the slave will create a master.info file, and any later     
+#    change in this file to the variables' values below will be ignored and
+#    overridden by the content of the master.info file, unless you shutdown
+#    the slave server, delete master.info and restart the slaver server.   
+#    For that reason, you may want to leave the lines below untouched      
+#    (commented) and instead use CHANGE MASTER TO (see above)              
+#                                                                          
+# required unique id between 2 and 2^32 - 1                                
+# (and different from the master)                                          
+# defaults to 2 if master-host is set                                      
+# but will not function as a slave if omitted                              
+#server-id       = 2                                                       
+#                                                                          
+# The replication master for this slave - required                         
+#master-host     =   <hostname>                                            
+#                                                                          
+# The username the slave will use for authentication when connecting       
+# to the master - required                                                 
+#master-user     =   <username>                                            
+#                                                                          
+# The password the slave will authenticate with when connecting to         
+# the master - required                                                    
+#master-password =   <password>                                            
+#                                                                          
+# The port the master is listening on.                                     
+# optional - defaults to 3306                                              
+#master-port     =  <port>                                                 
+#                                                                          
+# binary logging - not required for slaves, but recommended                
+#log-bin=mysql-bin                                                         
+                                                                           
+# Uncomment the following if you are using InnoDB tables                   
+#innodb_data_home_dir = /var/lib/mysql                                     
+#innodb_data_file_path = ibdata1:10M:autoextend                            
+#innodb_log_group_home_dir = /var/lib/mysql                                
+# You can set .._buffer_pool_size up to 50 - 80 %                          
+# of RAM but beware of setting memory usage too high                       
+#innodb_buffer_pool_size = 16M                                             
+#innodb_additional_mem_pool_size = 2M                                      
+# Set .._log_file_size to 25 % of buffer pool size                         
+#innodb_log_file_size = 5M                                                 
+#innodb_log_buffer_size = 8M                                              
+#innodb_flush_log_at_trx_commit = 1                                        
+#innodb_lock_wait_timeout = 50                                             
+                                                                           
+[mysqldump]                                                                
+quick                                                                      
+max_allowed_packet = 16M                                                   
+                                                                           
+[mysql]                                                                    
+no-auto-rehash                                                             
+# Remove the next comment character if you are not familiar with SQL       
+#safe-updates                                                              
+                                                                           
+[myisamchk]                                                                
+key_buffer_size = 20M                                                      
+sort_buffer_size = 20M                                                     
+read_buffer = 2M                                                           
+write_buffer = 2M                                                          
+                                                                           
+[mysqlhotcopy]                                                             
+interactive-timeout

container/conf/elastic/elasticsearch/elasticsearch.yml

@@ -0,0 +1,91 @@
+# ======================== Elasticsearch Configuration =========================
+#
+# NOTE: Elasticsearch comes with reasonable defaults for most settings.
+#       Before you set out to tweak and tune the configuration, make sure you
+#       understand what are you trying to accomplish and the consequences.
+#
+# The primary way of configuring a node is via this file. This template lists
+# the most important settings you may want to configure for a production cluster.
+#
+# Please consult the documentation for further information on configuration options:
+# https://www.elastic.co/guide/en/elasticsearch/reference/index.html
+#
+# ---------------------------------- Cluster -----------------------------------
+#
+# Use a descriptive name for your cluster:
+#
+#cluster.name: my-application
+#
+# ------------------------------------ Node ------------------------------------
+#
+# Use a descriptive name for the node:
+#
+#node.name: node-1
+#
+# Add custom attributes to the node:
+#
+#node.attr.rack: r1
+#
+# ----------------------------------- Paths ------------------------------------
+#
+# Path to directory where to store the data (separate multiple locations by comma):
+#
+path.data: /elasticsearch/data
+#
+# Path to log files:
+#
+path.logs: /elasticsearch/logs
+#
+# ----------------------------------- Memory -----------------------------------
+#
+# Lock the memory on startup:
+#
+#bootstrap.memory_lock: true
+#
+# Make sure that the heap size is set to about half the memory available
+# on the system and that the owner of the process is allowed to use this
+# limit.
+#
+# Elasticsearch performs poorly when the system is swapping the memory.
+#
+# ---------------------------------- Network -----------------------------------
+#
+# Set the bind address to a specific IP (IPv4 or IPv6):
+#
+network.host: 0.0.0.0
+#
+# Set a custom port for HTTP:
+#
+http.port: 9200
+#
+# For more information, consult the network module documentation.
+#
+# --------------------------------- Discovery ----------------------------------
+#
+# Pass an initial list of hosts to perform discovery when new node is started:
+# The default list of hosts is ["127.0.0.1", "[::1]"]
+#
+#discovery.zen.ping.unicast.hosts: ["host1", "host2"]
+#
+# Prevent the "split brain" by configuring the majority of nodes (total number of master-eligible nodes / 2 + 1):
+#
+#discovery.zen.minimum_master_nodes: 3
+#
+# For more information, consult the zen discovery module documentation.
+#
+# ---------------------------------- Gateway -----------------------------------
+#
+# Block initial recovery after a full cluster restart until N nodes are started:
+#
+#gateway.recover_after_nodes: 3
+#
+# For more information, consult the gateway module documentation.
+#
+# ---------------------------------- Various -----------------------------------
+#
+# Require explicit names when deleting indices:
+#
+#action.destructive_requires_name: true
+
+### xpack in alpine
+xpack.ml.enabled: false

container/conf/elastic/elasticsearch/jvm.options

@@ -0,0 +1,111 @@
+## JVM configuration
+
+################################################################
+## IMPORTANT: JVM heap size
+################################################################
+##
+## You should always set the min and max JVM heap
+## size to the same value. For example, to set
+## the heap to 4 GB, set:
+##
+## -Xms4g
+## -Xmx4g
+##
+## See https://www.elastic.co/guide/en/elasticsearch/reference/current/heap-size.html
+## for more information
+##
+################################################################
+
+# Xms represents the initial size of total heap space
+# Xmx represents the maximum size of total heap space
+
+-Xms1g
+-Xmx1g
+
+################################################################
+## Expert settings
+################################################################
+##
+## All settings below this section are considered
+## expert settings. Don't tamper with them unless
+## you understand what you are doing
+##
+################################################################
+
+## GC configuration
+-XX:+UseConcMarkSweepGC
+-XX:CMSInitiatingOccupancyFraction=75
+-XX:+UseCMSInitiatingOccupancyOnly
+
+## optimizations
+
+# pre-touch memory pages used by the JVM during initialization
+-XX:+AlwaysPreTouch
+
+## basic
+
+# force the server VM (remove on 32-bit client JVMs)
+-server
+
+# explicitly set the stack size (reduce to 320k on 32-bit client JVMs)
+-Xss1m
+
+# set to headless, just in case
+-Djava.awt.headless=true
+
+# ensure UTF-8 encoding by default (e.g. filenames)
+-Dfile.encoding=UTF-8
+
+# use our provided JNA always versus the system one
+-Djna.nosys=true
+
+# use old-style file permissions on JDK9
+-Djdk.io.permissionsUseCanonicalPath=true
+
+# flags to configure Netty
+-Dio.netty.noUnsafe=true
+-Dio.netty.noKeySetOptimization=true
+-Dio.netty.recycler.maxCapacityPerThread=0
+
+# log4j 2
+-Dlog4j.shutdownHookEnabled=false
+-Dlog4j2.disable.jmx=true
+-Dlog4j.skipJansi=true
+
+## heap dumps
+
+# generate a heap dump when an allocation from the Java heap fails
+# heap dumps are created in the working directory of the JVM
+-XX:+HeapDumpOnOutOfMemoryError
+
+# specify an alternative path for heap dumps
+# ensure the directory exists and has sufficient space
+#-XX:HeapDumpPath=${heap.dump.path}
+
+## GC logging
+
+#-XX:+PrintGCDetails
+#-XX:+PrintGCTimeStamps
+#-XX:+PrintGCDateStamps
+#-XX:+PrintClassHistogram
+#-XX:+PrintTenuringDistribution
+#-XX:+PrintGCApplicationStoppedTime
+
+# log GC status to a file with time stamps
+# ensure the directory exists
+#-Xloggc:${loggc}
+
+# By default, the GC log file will not rotate.
+# By uncommenting the lines below, the GC log file
+# will be rotated every 128MB at most 32 times.
+#-XX:+UseGCLogFileRotation
+#-XX:NumberOfGCLogFiles=32
+#-XX:GCLogFileSize=128M
+
+# Elasticsearch 5.0.0 will throw an exception on unquoted field names in JSON.
+# If documents were already indexed with unquoted fields in a previous version
+# of Elasticsearch, some operations may throw errors.
+#
+# WARNING: This option will be removed in Elasticsearch 6.0.0 and is provided
+# only for migration purposes.
+#-Delasticsearch.json.allow_unquoted_field_names=true

container/conf/elastic/elasticsearch/log4j2.properties

@@ -0,0 +1,74 @@
+status = error
+
+# log action execution errors for easier debugging
+logger.action.name = org.elasticsearch.action
+logger.action.level = debug
+
+appender.console.type = Console
+appender.console.name = console
+appender.console.layout.type = PatternLayout
+appender.console.layout.pattern = [%d{ISO8601}][%-5p][%-25c{1.}] %marker%m%n
+
+appender.rolling.type = RollingFile
+appender.rolling.name = rolling
+appender.rolling.fileName = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}.log
+appender.rolling.layout.type = PatternLayout
+appender.rolling.layout.pattern = [%d{ISO8601}][%-5p][%-25c{1.}] %marker%.-10000m%n
+appender.rolling.filePattern = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}-%d{yyyy-MM-dd}.log
+appender.rolling.policies.type = Policies
+appender.rolling.policies.time.type = TimeBasedTriggeringPolicy
+appender.rolling.policies.time.interval = 1
+appender.rolling.policies.time.modulate = true
+
+rootLogger.level = info
+rootLogger.appenderRef.console.ref = console
+rootLogger.appenderRef.rolling.ref = rolling
+
+appender.deprecation_rolling.type = RollingFile
+appender.deprecation_rolling.name = deprecation_rolling
+appender.deprecation_rolling.fileName = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_deprecation.log
+appender.deprecation_rolling.layout.type = PatternLayout
+appender.deprecation_rolling.layout.pattern = [%d{ISO8601}][%-5p][%-25c{1.}] %marker%.-10000m%n
+appender.deprecation_rolling.filePattern = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_deprecation-%i.log.gz
+appender.deprecation_rolling.policies.type = Policies
+appender.deprecation_rolling.policies.size.type = SizeBasedTriggeringPolicy
+appender.deprecation_rolling.policies.size.size = 1GB
+appender.deprecation_rolling.strategy.type = DefaultRolloverStrategy
+appender.deprecation_rolling.strategy.max = 4
+
+logger.deprecation.name = org.elasticsearch.deprecation
+logger.deprecation.level = warn
+logger.deprecation.appenderRef.deprecation_rolling.ref = deprecation_rolling
+logger.deprecation.additivity = false
+
+appender.index_search_slowlog_rolling.type = RollingFile
+appender.index_search_slowlog_rolling.name = index_search_slowlog_rolling
+appender.index_search_slowlog_rolling.fileName = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_index_search_slowlog.log
+appender.index_search_slowlog_rolling.layout.type = PatternLayout
+appender.index_search_slowlog_rolling.layout.pattern = [%d{ISO8601}][%-5p][%-25c] %marker%.-10000m%n
+appender.index_search_slowlog_rolling.filePattern = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_index_search_slowlog-%d{yyyy-MM-dd}.log
+appender.index_search_slowlog_rolling.policies.type = Policies
+appender.index_search_slowlog_rolling.policies.time.type = TimeBasedTriggeringPolicy
+appender.index_search_slowlog_rolling.policies.time.interval = 1
+appender.index_search_slowlog_rolling.policies.time.modulate = true
+
+logger.index_search_slowlog_rolling.name = index.search.slowlog
+logger.index_search_slowlog_rolling.level = trace
+logger.index_search_slowlog_rolling.appenderRef.index_search_slowlog_rolling.ref = index_search_slowlog_rolling
+logger.index_search_slowlog_rolling.additivity = false
+
+appender.index_indexing_slowlog_rolling.type = RollingFile
+appender.index_indexing_slowlog_rolling.name = index_indexing_slowlog_rolling
+appender.index_indexing_slowlog_rolling.fileName = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_index_indexing_slowlog.log
+appender.index_indexing_slowlog_rolling.layout.type = PatternLayout
+appender.index_indexing_slowlog_rolling.layout.pattern = [%d{ISO8601}][%-5p][%-25c] %marker%.-10000m%n
+appender.index_indexing_slowlog_rolling.filePattern = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_index_indexing_slowlog-%d{yyyy-MM-dd}.log
+appender.index_indexing_slowlog_rolling.policies.type = Policies
+appender.index_indexing_slowlog_rolling.policies.time.type = TimeBasedTriggeringPolicy
+appender.index_indexing_slowlog_rolling.policies.time.interval = 1
+appender.index_indexing_slowlog_rolling.policies.time.modulate = true
+
+logger.index_indexing_slowlog.name = index.indexing.slowlog.index
+logger.index_indexing_slowlog.level = trace
+logger.index_indexing_slowlog.appenderRef.index_indexing_slowlog_rolling.ref = index_indexing_slowlog_rolling
+logger.index_indexing_slowlog.additivity = false

container/conf/elastic/elasticsearch/scripts/README.md

@@ -0,0 +1 @@
+readme

container/conf/elastic/elasticsearch/x-pack/log4j2.properties

@@ -0,0 +1,15 @@
+appender.audit_rolling.type = RollingFile
+appender.audit_rolling.name = audit_rolling
+appender.audit_rolling.fileName = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_access.log
+appender.audit_rolling.layout.type = PatternLayout
+appender.audit_rolling.layout.pattern = [%d{ISO8601}] %m%n
+appender.audit_rolling.filePattern = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}_access-%d{yyyy-MM-dd}.log
+appender.audit_rolling.policies.type = Policies
+appender.audit_rolling.policies.time.type = TimeBasedTriggeringPolicy
+appender.audit_rolling.policies.time.interval = 1
+appender.audit_rolling.policies.time.modulate = true
+
+logger.xpack_security_audit_logfile.name = org.elasticsearch.xpack.security.audit.logfile.LoggingAuditTrail
+logger.xpack_security_audit_logfile.level = info
+logger.xpack_security_audit_logfile.appenderRef.audit_rolling.ref = audit_rolling
+logger.xpack_security_audit_logfile.additivity = false

container/conf/elastic/elasticsearch/x-pack/role_mapping.yml

@@ -0,0 +1,14 @@
+# Role mapping configuration file which has elasticsearch roles as keys
+# that map to one or more user or group distinguished names
+
+#roleA:   this is an elasticsearch role
+#  - groupA-DN  this is a group distinguished name
+#  - groupB-DN
+#  - user1-DN   this is the full user distinguished name
+
+#power_user:
+#  - "cn=admins,dc=example,dc=com"
+#user:
+#  - "cn=users,dc=example,dc=com"
+#  - "cn=admins,dc=example,dc=com"
+#  - "cn=John Doe,cn=other users,dc=example,dc=com"

container/conf/elastic/elasticsearch/x-pack/roles.yml

@@ -0,0 +1,3 @@
+# The default roles file is empty as the preferred method of defining roles is
+# through the API/UI. File based roles are useful in error scenarios when the
+# API based roles may not be available.

container/conf/elastic/filebeat/filebeat.yml

@@ -0,0 +1,114 @@
+###################### Filebeat Configuration Example #########################
+
+# This file is an example configuration file highlighting only the most common
+# options. The filebeat.full.yml file from the same directory contains all the
+# supported options with more comments. You can use it as a reference.
+#
+# You can find the full configuration reference here:
+# https://www.elastic.co/guide/en/beats/filebeat/index.html
+
+#=========================== Filebeat prospectors =============================
+
+filebeat.prospectors:
+
+# Each - is a prospector. Most options can be set at the prospector level, so
+# you can use different prospectors for various configurations.
+# Below are the prospector specific configurations.
+
+- input_type: log
+
+  # Paths that should be crawled and fetched. Glob based paths.
+  paths:
+    - /root/filebeat/*.log
+    #- c:\programdata\elasticsearch\logs\*
+
+  # Exclude lines. A list of regular expressions to match. It drops the lines that are
+  # matching any regular expression from the list.
+  #exclude_lines: ["^DBG"]
+
+  # Include lines. A list of regular expressions to match. It exports the lines that are
+  # matching any regular expression from the list.
+  #include_lines: ["^ERR", "^WARN"]
+
+  # Exclude files. A list of regular expressions to match. Filebeat drops the files that
+  # are matching any regular expression from the list. By default, no files are dropped.
+  #exclude_files: [".gz$"]
+
+  # Optional additional fields. These field can be freely picked
+  # to add additional information to the crawled log files for filtering
+  #fields:
+  #  level: debug
+  #  review: 1
+
+  ### Multiline options
+
+  # Mutiline can be used for log messages spanning multiple lines. This is common
+  # for Java Stack Traces or C-Line Continuation
+
+  # The regexp Pattern that has to be matched. The example pattern matches all lines starting with [
+  #multiline.pattern: ^\[
+
+  # Defines if the pattern set under pattern should be negated or not. Default is false.
+  #multiline.negate: false
+
+  # Match can be set to "after" or "before". It is used to define if lines should be append to a pattern
+  # that was (not) matched before or after or as long as a pattern is not matched based on negate.
+  # Note: After is the equivalent to previous and before is the equivalent to to next in Logstash
+  #multiline.match: after
+
+
+#================================ General =====================================
+
+# The name of the shipper that publishes the network data. It can be used to group
+# all the transactions sent by a single shipper in the web interface.
+#name:
+
+# The tags of the shipper are included in their own field with each
+# transaction published.
+#tags: ["service-X", "web-tier"]
+
+# Optional fields that you can specify to add additional information to the
+# output.
+#fields:
+#  env: staging
+
+#================================ Outputs =====================================
+
+# Configure what outputs to use when sending the data collected by the beat.
+# Multiple outputs may be used.
+
+#-------------------------- Elasticsearch output ------------------------------
+output.elasticsearch:
+  # Array of hosts to connect to.
+  hosts: ["elk-es:9200"]
+
+  # Optional protocol and basic auth credentials.
+  #protocol: "https"
+  username: "elastic"
+  password: "changeme"
+
+#----------------------------- Logstash output --------------------------------
+#output.logstash:
+  # The Logstash hosts
+  #hosts: ["elk-logstash:5044"]
+
+  # Optional SSL. By default is off.
+  # List of root certificates for HTTPS server verifications
+  #ssl.certificate_authorities: ["/etc/pki/root/ca.pem"]
+
+  # Certificate for SSL client authentication
+  #ssl.certificate: "/etc/pki/client/cert.pem"
+
+  # Client Certificate Key
+  #ssl.key: "/etc/pki/client/cert.key"
+
+#================================ Logging =====================================
+
+# Sets log level. The default log level is info.
+# Available log levels are: critical, error, warning, info, debug
+#logging.level: debug
+
+# At debug level, you can selectively enable logging only for some components.
+# To enable all selectors use ["*"]. Examples of other selectors are "beat",
+# "publish", "service".
+#logging.selectors: ["*"]

container/conf/elastic/kibana/kibana.yml

@@ -0,0 +1,106 @@
+# Kibana is served by a back end server. This setting specifies the port to use.
+#server.port: 5601
+
+# Specifies the address to which the Kibana server will bind. IP addresses and host names are both valid values.
+# The default is 'localhost', which usually means remote machines will not be able to connect.
+# To allow connections from remote users, set this parameter to a non-loopback address.
+server.host: "0.0.0.0"
+
+# Enables you to specify a path to mount Kibana at if you are running behind a proxy. This only affects
+# the URLs generated by Kibana, your proxy is expected to remove the basePath value before forwarding requests
+# to Kibana. This setting cannot end in a slash.
+#server.basePath: ""
+
+# The maximum payload size in bytes for incoming server requests.
+#server.maxPayloadBytes: 1048576
+
+# The Kibana server's name.  This is used for display purposes.
+#server.name: "your-hostname"
+
+# The URL of the Elasticsearch instance to use for all your queries.
+elasticsearch.url: "http://elk-es:9200"
+elasticsearch.username: "elastic" 
+elasticsearch.password: "changeme"
+
+# When this setting's value is true Kibana uses the hostname specified in the server.host
+# setting. When the value of this setting is false, Kibana uses the hostname of the host
+# that connects to this Kibana instance.
+#elasticsearch.preserveHost: true
+
+# Kibana uses an index in Elasticsearch to store saved searches, visualizations and
+# dashboards. Kibana creates a new index if the index doesn't already exist.
+#kibana.index: ".kibana"
+
+# The default application to load.
+#kibana.defaultAppId: "discover"
+
+# If your Elasticsearch is protected with basic authentication, these settings provide
+# the username and password that the Kibana server uses to perform maintenance on the Kibana
+# index at startup. Your Kibana users still need to authenticate with Elasticsearch, which
+# is proxied through the Kibana server.
+#elasticsearch.username: "user"
+#elasticsearch.password: "pass"
+
+# Enables SSL and paths to the PEM-format SSL certificate and SSL key files, respectively.
+# These settings enable SSL for outgoing requests from the Kibana server to the browser.
+#server.ssl.enabled: false
+#server.ssl.certificate: /path/to/your/server.crt
+#server.ssl.key: /path/to/your/server.key
+
+# Optional settings that provide the paths to the PEM-format SSL certificate and key files.
+# These files validate that your Elasticsearch backend uses the same key files.
+#elasticsearch.ssl.certificate: /path/to/your/client.crt
+#elasticsearch.ssl.key: /path/to/your/client.key
+
+# Optional setting that enables you to specify a path to the PEM file for the certificate
+# authority for your Elasticsearch instance.
+#elasticsearch.ssl.certificateAuthorities: [ "/path/to/your/CA.pem" ]
+
+# To disregard the validity of SSL certificates, change this setting's value to 'none'.
+#elasticsearch.ssl.verificationMode: full
+
+# Time in milliseconds to wait for Elasticsearch to respond to pings. Defaults to the value of
+# the elasticsearch.requestTimeout setting.
+#elasticsearch.pingTimeout: 1500
+
+# Time in milliseconds to wait for responses from the back end or Elasticsearch. This value
+# must be a positive integer.
+#elasticsearch.requestTimeout: 30000
+
+# List of Kibana client-side headers to send to Elasticsearch. To send *no* client-side
+# headers, set this value to [] (an empty list).
+#elasticsearch.requestHeadersWhitelist: [ authorization ]
+
+# Header names and values that are sent to Elasticsearch. Any custom headers cannot be overwritten
+# by client-side headers, regardless of the elasticsearch.requestHeadersWhitelist configuration.
+#elasticsearch.customHeaders: {}
+
+# Time in milliseconds for Elasticsearch to wait for responses from shards. Set to 0 to disable.
+#elasticsearch.shardTimeout: 0
+
+# Time in milliseconds to wait for Elasticsearch at Kibana startup before retrying.
+#elasticsearch.startupTimeout: 5000
+
+# Specifies the path where Kibana creates the process ID file.
+#pid.file: /var/run/kibana.pid
+
+# Enables you specify a file where Kibana stores log output.
+#logging.dest: stdout
+
+# Set the value of this setting to true to suppress all logging output.
+#logging.silent: false
+
+# Set the value of this setting to true to suppress all logging output other than error messages.
+#logging.quiet: false
+
+# Set the value of this setting to true to log all events, including system usage information
+# and all requests.
+#logging.verbose: false
+
+# Set the interval in milliseconds to sample system and process performance
+# metrics. Minimum is 100ms. Defaults to 5000.
+#ops.interval: 5000
+
+# The default locale. This locale can be used in certain circumstances to substitute any missing
+# translations.
+#i18n.defaultLocale: "en"

container/conf/elastic/logstash/jvm.options

@@ -0,0 +1,77 @@
+## JVM configuration
+
+# Xms represents the initial size of total heap space
+# Xmx represents the maximum size of total heap space
+
+-Xms256m
+-Xmx1g
+
+################################################################
+## Expert settings
+################################################################
+##
+## All settings below this section are considered
+## expert settings. Don't tamper with them unless
+## you understand what you are doing
+##
+################################################################
+
+## GC configuration
+-XX:+UseParNewGC
+-XX:+UseConcMarkSweepGC
+-XX:CMSInitiatingOccupancyFraction=75
+-XX:+UseCMSInitiatingOccupancyOnly
+
+## optimizations
+
+# disable calls to System#gc
+-XX:+DisableExplicitGC
+
+## Locale
+# Set the locale language
+#-Duser.language=en
+
+# Set the locale country
+#-Duser.country=US
+
+# Set the locale variant, if any
+#-Duser.variant=
+
+## basic
+
+# set the I/O temp directory
+#-Djava.io.tmpdir=$HOME
+
+# set to headless, just in case
+-Djava.awt.headless=true
+
+# ensure UTF-8 encoding by default (e.g. filenames)
+-Dfile.encoding=UTF-8
+
+# use our provided JNA always versus the system one
+#-Djna.nosys=true
+
+## heap dumps
+
+# generate a heap dump when an allocation from the Java heap fails
+# heap dumps are created in the working directory of the JVM
+-XX:+HeapDumpOnOutOfMemoryError
+
+# specify an alternative path for heap dumps
+# ensure the directory exists and has sufficient space
+#-XX:HeapDumpPath=${LOGSTASH_HOME}/heapdump.hprof
+
+## GC logging
+#-XX:+PrintGCDetails
+#-XX:+PrintGCTimeStamps
+#-XX:+PrintGCDateStamps
+#-XX:+PrintClassHistogram
+#-XX:+PrintTenuringDistribution
+#-XX:+PrintGCApplicationStoppedTime
+
+# log GC status to a file with time stamps
+# ensure the directory exists
+#-Xloggc:${LS_GC_LOG_FILE}
+
+# Entropy source for randomness
+-Djava.security.egd=file:/dev/urandom

container/conf/elastic/logstash/log4j2.properties

@@ -0,0 +1,83 @@
+status = error
+name = LogstashPropertiesConfig
+
+appender.console.type = Console
+appender.console.name = plain_console
+appender.console.layout.type = PatternLayout
+appender.console.layout.pattern = [%d{ISO8601}][%-5p][%-25c] %m%n
+
+appender.json_console.type = Console
+appender.json_console.name = json_console
+appender.json_console.layout.type = JSONLayout
+appender.json_console.layout.compact = true
+appender.json_console.layout.eventEol = true
+
+appender.rolling.type = RollingFile
+appender.rolling.name = plain_rolling
+appender.rolling.fileName = ${sys:ls.logs}/logstash-${sys:ls.log.format}.log
+appender.rolling.filePattern = ${sys:ls.logs}/logstash-${sys:ls.log.format}-%d{yyyy-MM-dd}.log
+appender.rolling.policies.type = Policies
+appender.rolling.policies.time.type = TimeBasedTriggeringPolicy
+appender.rolling.policies.time.interval = 1
+appender.rolling.policies.time.modulate = true
+appender.rolling.layout.type = PatternLayout
+appender.rolling.layout.pattern = [%d{ISO8601}][%-5p][%-25c] %-.10000m%n
+
+appender.json_rolling.type = RollingFile
+appender.json_rolling.name = json_rolling
+appender.json_rolling.fileName = ${sys:ls.logs}/logstash-${sys:ls.log.format}.log
+appender.json_rolling.filePattern = ${sys:ls.logs}/logstash-${sys:ls.log.format}-%d{yyyy-MM-dd}.log
+appender.json_rolling.policies.type = Policies
+appender.json_rolling.policies.time.type = TimeBasedTriggeringPolicy
+appender.json_rolling.policies.time.interval = 1
+appender.json_rolling.policies.time.modulate = true
+appender.json_rolling.layout.type = JSONLayout
+appender.json_rolling.layout.compact = true
+appender.json_rolling.layout.eventEol = true
+
+
+rootLogger.level = ${sys:ls.log.level}
+rootLogger.appenderRef.console.ref = ${sys:ls.log.format}_console
+rootLogger.appenderRef.rolling.ref = ${sys:ls.log.format}_rolling
+
+# Slowlog
+
+appender.console_slowlog.type = Console
+appender.console_slowlog.name = plain_console_slowlog
+appender.console_slowlog.layout.type = PatternLayout
+appender.console_slowlog.layout.pattern = [%d{ISO8601}][%-5p][%-25c] %m%n
+
+appender.json_console_slowlog.type = Console
+appender.json_console_slowlog.name = json_console_slowlog
+appender.json_console_slowlog.layout.type = JSONLayout
+appender.json_console_slowlog.layout.compact = true
+appender.json_console_slowlog.layout.eventEol = true
+
+appender.rolling_slowlog.type = RollingFile
+appender.rolling_slowlog.name = plain_rolling_slowlog
+appender.rolling_slowlog.fileName = ${sys:ls.logs}/logstash-slowlog-${sys:ls.log.format}.log
+appender.rolling_slowlog.filePattern = ${sys:ls.logs}/logstash-slowlog-${sys:ls.log.format}-%d{yyyy-MM-dd}.log
+appender.rolling_slowlog.policies.type = Policies
+appender.rolling_slowlog.policies.time.type = TimeBasedTriggeringPolicy
+appender.rolling_slowlog.policies.time.interval = 1
+appender.rolling_slowlog.policies.time.modulate = true
+appender.rolling_slowlog.layout.type = PatternLayout
+appender.rolling_slowlog.layout.pattern = [%d{ISO8601}][%-5p][%-25c] %.10000m%n
+
+appender.json_rolling_slowlog.type = RollingFile
+appender.json_rolling_slowlog.name = json_rolling_slowlog
+appender.json_rolling_slowlog.fileName = ${sys:ls.logs}/logstash-slowlog-${sys:ls.log.format}.log
+appender.json_rolling_slowlog.filePattern = ${sys:ls.logs}/logstash-slowlog-${sys:ls.log.format}-%d{yyyy-MM-dd}.log
+appender.json_rolling_slowlog.policies.type = Policies
+appender.json_rolling_slowlog.policies.time.type = TimeBasedTriggeringPolicy
+appender.json_rolling_slowlog.policies.time.interval = 1
+appender.json_rolling_slowlog.policies.time.modulate = true
+appender.json_rolling_slowlog.layout.type = JSONLayout
+appender.json_rolling_slowlog.layout.compact = true
+appender.json_rolling_slowlog.layout.eventEol = true
+
+logger.slowlog.name = slowlog
+logger.slowlog.level = trace
+logger.slowlog.appenderRef.console_slowlog.ref = ${sys:ls.log.format}_console_slowlog
+logger.slowlog.appenderRef.rolling_slowlog.ref = ${sys:ls.log.format}_rolling_slowlog
+logger.slowlog.additivity = false

container/conf/elastic/logstash/logstash.conf

@@ -0,0 +1,33 @@
+input
+{
+	beats
+	{
+		port => 5044
+		type => "logs"
+	}
+}
+filter
+{
+	grok
+	{
+		match =>
+		{ 
+			"message" => "%{COMBINEDAPACHELOG}"
+		}
+	}
+}
+output
+{
+	elasticsearch
+	{
+		hosts => elk-es:9020
+		user => elastic
+		password => changeme
+		index => "%{[@metadata][beat]}-%{+YYYY.MM.dd}"
+    	document_type => "%{[@metadata][type]}"
+	}
+	stdout
+	{
+		codec => rubydebug
+	}
+}

container/conf/elastic/logstash/logstash.yml

@@ -0,0 +1,195 @@
+# Settings file in YAML
+#
+# Settings can be specified either in hierarchical form, e.g.:
+#
+#   pipeline:
+#     batch:
+#       size: 125
+#       delay: 5
+#
+# Or as flat keys:
+#
+#   pipeline.batch.size: 125
+#   pipeline.batch.delay: 5
+#
+# ------------  Node identity ------------
+#
+# Use a descriptive name for the node:
+#
+# node.name: test
+#
+# If omitted the node name will default to the machine's host name
+#
+# ------------ Data path ------------------
+#
+# Which directory should be used by logstash and its plugins
+# for any persistent needs. Defaults to LOGSTASH_HOME/data
+#
+# path.data:
+#
+# ------------ Pipeline Settings --------------
+#
+# Set the number of workers that will, in parallel, execute the filters+outputs
+# stage of the pipeline.
+#
+# This defaults to the number of the host's CPU cores.
+#
+# pipeline.workers: 2
+#
+# How many workers should be used per output plugin instance
+#
+# pipeline.output.workers: 1
+#
+# How many events to retrieve from inputs before sending to filters+workers
+#
+# pipeline.batch.size: 125
+#
+# How long to wait before dispatching an undersized batch to filters+workers
+# Value is in milliseconds.
+#
+# pipeline.batch.delay: 5
+#
+# Force Logstash to exit during shutdown even if there are still inflight
+# events in memory. By default, logstash will refuse to quit until all
+# received events have been pushed to the outputs.
+#
+# WARNING: enabling this can lead to data loss during shutdown
+#
+# pipeline.unsafe_shutdown: false
+#
+# ------------ Pipeline Configuration Settings --------------
+#
+# Where to fetch the pipeline configuration for the main pipeline
+#
+# path.config:
+#
+# Pipeline configuration string for the main pipeline
+#
+# config.string:
+#
+# At startup, test if the configuration is valid and exit (dry run)
+#
+# config.test_and_exit: false
+#
+# Periodically check if the configuration has changed and reload the pipeline
+# This can also be triggered manually through the SIGHUP signal
+#
+# config.reload.automatic: false
+#
+# How often to check if the pipeline configuration has changed (in seconds)
+#
+# config.reload.interval: 3
+#
+# Show fully compiled configuration as debug log message
+# NOTE: --log.level must be 'debug'
+#
+# config.debug: false
+#
+# ------------ Module Settings ---------------
+# Define modules here.  Modules definitions must be defined as an array.
+# The simple way to see this is to prepend each `name` with a `-`, and keep
+# all associated variables under the `name` they are associated with, and 
+# above the next, like this:
+#
+# modules:
+#   - name: MODULE_NAME
+#     var.PLUGINTYPE1.PLUGINNAME1.KEY1: VALUE
+#     var.PLUGINTYPE1.PLUGINNAME1.KEY2: VALUE
+#     var.PLUGINTYPE2.PLUGINNAME1.KEY1: VALUE
+#     var.PLUGINTYPE3.PLUGINNAME3.KEY1: VALUE
+#
+# Module variable names must be in the format of 
+#
+# var.PLUGIN_TYPE.PLUGIN_NAME.KEY
+#
+# modules:
+#
+# ------------ Queuing Settings --------------
+#
+# Internal queuing model, "memory" for legacy in-memory based queuing and
+# "persisted" for disk-based acked queueing. Defaults is memory
+#
+# queue.type: memory
+#
+# If using queue.type: persisted, the directory path where the data files will be stored.
+# Default is path.data/queue
+#
+# path.queue:
+#
+# If using queue.type: persisted, the page data files size. The queue data consists of
+# append-only data files separated into pages. Default is 250mb
+#
+# queue.page_capacity: 250mb
+#
+# If using queue.type: persisted, the maximum number of unread events in the queue.
+# Default is 0 (unlimited)
+#
+# queue.max_events: 0
+#
+# If using queue.type: persisted, the total capacity of the queue in number of bytes.
+# If you would like more unacked events to be buffered in Logstash, you can increase the
+# capacity using this setting. Please make sure your disk drive has capacity greater than
+# the size specified here. If both max_bytes and max_events are specified, Logstash will pick
+# whichever criteria is reached first
+# Default is 1024mb or 1gb
+#
+# queue.max_bytes: 1024mb
+#
+# If using queue.type: persisted, the maximum number of acked events before forcing a checkpoint
+# Default is 1024, 0 for unlimited
+#
+# queue.checkpoint.acks: 1024
+#
+# If using queue.type: persisted, the maximum number of written events before forcing a checkpoint
+# Default is 1024, 0 for unlimited
+#
+# queue.checkpoint.writes: 1024
+#
+# If using queue.type: persisted, the interval in milliseconds when a checkpoint is forced on the head page
+# Default is 1000, 0 for no periodic checkpoint.
+#
+# queue.checkpoint.interval: 1000
+#
+# ------------ Dead-Letter Queue Settings --------------
+# Flag to turn on dead-letter queue.
+#
+# dead_letter_queue.enable: false
+
+# If using dead_letter_queue.enable: true, the maximum size of each dead letter queue. Entries
+# will be dropped if they would increase the size of the dead letter queue beyond this setting.
+# Deafault is 1024mb
+# dead_letter_queue.max_bytes: 1024mb
+
+# If using dead_letter_queue.enable: true, the directory path where the data files will be stored.
+# Default is path.data/dead_letter_queue
+#
+# path.dead_letter_queue:
+#
+# ------------ Metrics Settings --------------
+#
+# Bind address for the metrics REST endpoint
+#
+# http.host: "127.0.0.1"
+#
+# Bind port for the metrics REST endpoint, this option also accept a range
+# (9600-9700) and logstash will pick up the first available ports.
+#
+# http.port: 9600-9700
+#
+# ------------ Debugging Settings --------------
+#
+# Options for log.level:
+#   * fatal
+#   * error
+#   * warn
+#   * info (default)
+#   * debug
+#   * trace
+#
+# log.level: info
+# path.logs:
+#
+# ------------ Other Settings --------------
+#
+# Where to find custom plugins
+# path.plugins: []

container/conf/elastic/logstash/startup.options

@@ -0,0 +1,53 @@
+################################################################################
+# These settings are ONLY used by $LS_HOME/bin/system-install to create a custom
+# startup script for Logstash and is not used by Logstash itself. It should
+# automagically use the init system (systemd, upstart, sysv, etc.) that your
+# Linux distribution uses.
+#
+# After changing anything here, you need to re-run $LS_HOME/bin/system-install
+# as root to push the changes to the init script.
+################################################################################
+
+# Override Java location
+#JAVACMD=/usr/bin/java
+
+# Set a home directory
+LS_HOME=/usr/share/logstash
+
+# logstash settings directory, the path which contains logstash.yml
+LS_SETTINGS_DIR="${LS_HOME}/config"
+
+# Arguments to pass to logstash
+LS_OPTS="--path.settings ${LS_SETTINGS_DIR}"
+
+# Arguments to pass to java
+LS_JAVA_OPTS=""
+
+# pidfiles aren't used the same way for upstart and systemd; this is for sysv users.
+LS_PIDFILE=/var/run/logstash.pid
+
+# user and group id to be invoked as
+LS_USER=logstash
+LS_GROUP=logstash
+
+# Enable GC logging by uncommenting the appropriate lines in the GC logging
+# section in jvm.options
+LS_GC_LOG_FILE=/var/log/logstash/gc.log
+
+# Open file limit
+LS_OPEN_FILES=16384
+
+# Nice level
+LS_NICE=19
+
+# Change these to have the init script named and described differently
+# This is useful when running multiple instances of Logstash on the same
+# physical box or vm
+SERVICE_NAME="logstash"
+SERVICE_DESCRIPTION="logstash"
+
+# If you need to run a command or script before launching Logstash, put it
+# between the lines beginning with `read` and `EOM`, and uncomment those lines.
+###
+## read -r -d '' PRESTART << EOM
+## EOM

container/conf/java/flume/flume-conf.properties

@@ -0,0 +1,46 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#  http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+
+# The configuration file needs to define the sources, 
+# the channels and the sinks.
+# Sources, channels and sinks are defined per agent, 
+# in this case called 'agent'
+
+agent.sources = seqGenSrc
+agent.channels = memoryChannel
+agent.sinks = loggerSink
+
+# For each one of the sources, the type is defined
+agent.sources.seqGenSrc.type = seq
+
+# The channel can be defined as follows.
+agent.sources.seqGenSrc.channels = memoryChannel
+
+# Each sink's type must be defined
+agent.sinks.loggerSink.type = logger
+
+#Specify the channel the sink should use
+agent.sinks.loggerSink.channel = memoryChannel
+
+# Each channel's type is defined.
+agent.channels.memoryChannel.type = memory
+
+# Other config values specific to each type of channel(sink or source)
+# can be defined as well
+# In this case, it specifies the capacity of the memory channel
+agent.channels.memoryChannel.capacity = 100

container/conf/java/flume/flume-env.ps1

@@ -0,0 +1,28 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+# Give Flume more memory and pre-allocate, enable remote monitoring via JMX
+$JAVA_OPTS="-Xms100m -Xmx200m -Dcom.sun.management.jmxremote"
+
+# Let Flume write raw event data and configuration information to its log files for debugging
+# purposes. Enabling these flags is not recommended in production,
+# as it may result in logging sensitive user information or encryption secrets.
+# $JAVA_OPTS="$JAVA_OPTS -Dorg.apache.flume.log.rawdata=true -Dorg.apache.flume.log.printconfig=true "
+
+# Foll. classpath will be included in Flume's classpath.
+# Note that the Flume conf directory is always included in the classpath.
+$FLUME_CLASSPATH=""   # Example:  "path1;path2;path3"

container/conf/java/flume/flume-env.sh

@@ -0,0 +1,34 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# If this file is placed at FLUME_CONF_DIR/flume-env.sh, it will be sourced
+# during Flume startup.
+
+# Enviroment variables can be set here.
+
+# export JAVA_HOME=/usr/lib/jvm/java-6-sun
+
+# Give Flume more memory and pre-allocate, enable remote monitoring via JMX
+# export JAVA_OPTS="-Xms100m -Xmx2000m -Dcom.sun.management.jmxremote"
+
+# Let Flume write raw event data and configuration information to its log files for debugging
+# purposes. Enabling these flags is not recommended in production,
+# as it may result in logging sensitive user information or encryption secrets.
+# export JAVA_OPTS="$JAVA_OPTS -Dorg.apache.flume.log.rawdata=true -Dorg.apache.flume.log.printconfig=true "
+
+# Note that the Flume conf directory is always included in the classpath.
+#FLUME_CLASSPATH=""
+

container/conf/java/flume/flume.conf

@@ -0,0 +1,73 @@
+# source, channel, sink definition  
+agent.channels = spooling tail
+agent.sources = spooling-source tail-source
+agent.sinks = hdfs kafka
+  
+# Channel  
+# Define a memory channel
+#agent.channels.spooling.type = memory
+#agent.channels.tail.type = memory
+# Define a file channel
+agent.channels.spooling.type = file
+agent.channels.spooling.checkpointDir = /root/flume/spooling/tmp
+agent.channels.spooling.dataDirs = /root/flume/spooling/data
+
+agent.channels.tail.type = file
+agent.channels.tail.checkpointDir = /root/flume/tail/tmp
+agent.channels.tail.dataDirs = /root/flume/tail/data
+
+  
+# Source
+agent.sources.spooling-source.type = spooldir
+agent.sources.spooling-source.spoolDir = /root/flume/input
+agent.sources.spooling-source.channels = spooling
+agent.sources.spooling-source.fileHeader = true
+agent.sources.spooling-source.fileHeaderKey=file
+agent.sources.spooling-source.basenameHeader=true  
+agent.sources.spooling-source.basenameHeaderKey=basename
+##日志发送完毕后，是否删除此源文件，  
+#“immediate”表示发送完毕后立即删除，可以节约磁盘空间  
+agent.sources.spooling-source.deletePolicy=never
+
+agent.sources.tail-source.type=TAILDIR  
+agent.sources.tail-source.channels=tail  
+##本人不想写flume的扩展代码，所以就为每个tail的文件指定一个group  
+agent.sources.tail-source.filegroups=www error  
+agent.sources.tail-source.filegroups.www=/data/logs/agent/www.log  
+agent.sources.tail-source.filegroups.error=/data/logs/agent/error.log  
+##对于taildir，需要间歇性的保存tail文件的位置，以便中断后可以继续  
+##json格式文件  
+agent.sources.tail-source.positionFile=/data/flume/.flume/ch-tail/taildir_position.json  
+##每个tail的文件，创建一个kafka topic  
+agent.sources.tail-source.headers.www.topic=agent-www  
+agent.sources.tail-source.headers.error.topic=agent-error  
+agent.sources.tail-source.skipToEnd=true  
+agent.sources.tail-source.interceptors=i1 i2  
+agent.sources.tail-source.interceptors.i1.type=timestamp  
+agent.sources.tail-source.interceptors.i2.type=host  
+agent.sources.tail-source.interceptors.i2.useIP=true  
+agent.sources.tail-source.interceptors.i2.hostHeader=host  
+
+
+# Sink
+agent.sinks.hdfs.channel = spooling
+agent.sinks.hdfs.type = hdfs
+agent.sinks.hdfs.hdfs.path = hdfs://data-hadoop:9000/flume
+agent.sinks.hdfs.hdfs.fileType = DataStream
+agent.sinks.hdfs.hdfs.writeFormat = TEXT
+agent.sinks.hdfs.hdfs.rollInterval = 4
+
+# tail实时数据  
+agent.sinks.kafka.channel=ch-tail  
+agent.sinks.kafka.type=org.apache.flume.sink.kafka.KafkaSink  
+# kafka集群地址，可以为其子集  
+agent.sinks.kafka.kafka.bootstrap.servers=data-kafka:9092,data-kafka1:9092,data-kafka2:9092
+# 注意，topic中不支持参数化  
+# 但是为了提高扩展性，我们把topic信息通过header方式控制  
+#agent.sinks.kafka.kafka.topic=agent-%{filename}  
+# default 100，值越大，网络效率越高，但是延迟越高，准实时  
+agent.sinks.kafka.flumeBatchSize=32  
+agent.sinks.kafka.kafka.producer.acks=1  
+#use Avro-event format,will contain flume-headers  
+#default : false  
+agent.sinks.kafka.useFlumeEventFormat=false  

container/conf/java/flume/log4j.properties

@@ -0,0 +1,68 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#  http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+#
+
+# Define some default values that can be overridden by system properties.
+#
+# For testing, it may also be convenient to specify
+# -Dflume.root.logger=DEBUG,console when launching flume.
+
+#flume.root.logger=DEBUG,console
+flume.root.logger=INFO,LOGFILE
+flume.log.dir=./logs
+flume.log.file=flume.log
+
+log4j.logger.org.apache.flume.lifecycle = INFO
+log4j.logger.org.jboss = WARN
+log4j.logger.org.mortbay = INFO
+log4j.logger.org.apache.avro.ipc.NettyTransceiver = WARN
+log4j.logger.org.apache.hadoop = INFO
+log4j.logger.org.apache.hadoop.hive = ERROR
+
+# Define the root logger to the system property "flume.root.logger".
+log4j.rootLogger=${flume.root.logger}
+
+
+# Stock log4j rolling file appender
+# Default log rotation configuration
+log4j.appender.LOGFILE=org.apache.log4j.RollingFileAppender
+log4j.appender.LOGFILE.MaxFileSize=100MB
+log4j.appender.LOGFILE.MaxBackupIndex=10
+log4j.appender.LOGFILE.File=${flume.log.dir}/${flume.log.file}
+log4j.appender.LOGFILE.layout=org.apache.log4j.PatternLayout
+log4j.appender.LOGFILE.layout.ConversionPattern=%d{dd MMM yyyy HH:mm:ss,SSS} %-5p [%t] (%C.%M:%L) %x - %m%n
+
+
+# Warning: If you enable the following appender it will fill up your disk if you don't have a cleanup job!
+# This uses the updated rolling file appender from log4j-extras that supports a reliable time-based rolling policy.
+# See http://logging.apache.org/log4j/companions/extras/apidocs/org/apache/log4j/rolling/TimeBasedRollingPolicy.html
+# Add "DAILY" to flume.root.logger above if you want to use this
+log4j.appender.DAILY=org.apache.log4j.rolling.RollingFileAppender
+log4j.appender.DAILY.rollingPolicy=org.apache.log4j.rolling.TimeBasedRollingPolicy
+log4j.appender.DAILY.rollingPolicy.ActiveFileName=${flume.log.dir}/${flume.log.file}
+log4j.appender.DAILY.rollingPolicy.FileNamePattern=${flume.log.dir}/${flume.log.file}.%d{yyyy-MM-dd}
+log4j.appender.DAILY.layout=org.apache.log4j.PatternLayout
+log4j.appender.DAILY.layout.ConversionPattern=%d{dd MMM yyyy HH:mm:ss,SSS} %-5p [%t] (%C.%M:%L) %x - %m%n
+
+
+# console
+# Add "console" to flume.root.logger above if you want to use this
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.err
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d (%t) [%p - %l] %m%n

container/conf/java/hadoop/capacity-scheduler.xml

@@ -0,0 +1,134 @@
+<!--
+  Licensed under the Apache License, Version 2.0 (the "License");
+  you may not use this file except in compliance with the License.
+  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+  Unless required by applicable law or agreed to in writing, software
+  distributed under the License is distributed on an "AS IS" BASIS,
+  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+  See the License for the specific language governing permissions and
+  limitations under the License. See accompanying LICENSE file.
+-->
+<configuration>
+
+  <property>
+    <name>yarn.scheduler.capacity.maximum-applications</name>
+    <value>10000</value>
+    <description>
+      Maximum number of applications that can be pending and running.
+    </description>
+  </property>
+
+  <property>
+    <name>yarn.scheduler.capacity.maximum-am-resource-percent</name>
+    <value>0.5</value>
+    <description>
+      Maximum percent of resources in the cluster which can be used to run 
+      application masters i.e. controls number of concurrent running
+      applications.5
+    </description>
+  </property>
+
+  <property>
+    <name>yarn.scheduler.capacity.resource-calculator</name>
+    <value>org.apache.hadoop.yarn.util.resource.DefaultResourceCalculator</value>
+    <description>
+      The ResourceCalculator implementation to be used to compare 
+      Resources in the scheduler.
+      The default i.e. DefaultResourceCalculator only uses Memory while
+      DominantResourceCalculator uses dominant-resource to compare 
+      multi-dimensional resources such as Memory, CPU etc.
+    </description>
+  </property>
+
+  <property>
+    <name>yarn.scheduler.capacity.root.queues</name>
+    <value>default</value>
+    <description>
+      The queues at the this level (root is the root queue).
+    </description>
+  </property>
+
+  <property>
+    <name>yarn.scheduler.capacity.root.default.capacity</name>
+    <value>100</value>
+    <description>Default queue target capacity.</description>
+  </property>
+
+  <property>
+    <name>yarn.scheduler.capacity.root.default.user-limit-factor</name>
+    <value>1</value>
+    <description>
+      Default queue user limit a percentage from 0.0 to 1.0.
+    </description>
+  </property>
+
+  <property>
+    <name>yarn.scheduler.capacity.root.default.maximum-capacity</name>
+    <value>100</value>
+    <description>
+      The maximum capacity of the default queue. 
+    </description>
+  </property>
+
+  <property>
+    <name>yarn.scheduler.capacity.root.default.state</name>
+    <value>RUNNING</value>
+    <description>
+      The state of the default queue. State can be one of RUNNING or STOPPED.
+    </description>
+  </property>
+
+  <property>
+    <name>yarn.scheduler.capacity.root.default.acl_submit_applications</name>
+    <value>*</value>
+    <description>
+      The ACL of who can submit jobs to the default queue.
+    </description>
+  </property>
+
+  <property>
+    <name>yarn.scheduler.capacity.root.default.acl_administer_queue</name>
+    <value>*</value>
+    <description>
+      The ACL of who can administer jobs on the default queue.
+    </description>
+  </property>
+
+  <property>
+    <name>yarn.scheduler.capacity.node-locality-delay</name>
+    <value>40</value>
+    <description>
+      Number of missed scheduling opportunities after which the CapacityScheduler 
+      attempts to schedule rack-local containers. 
+      Typically this should be set to number of nodes in the cluster, By default is setting 
+      approximately number of nodes in one rack which is 40.
+    </description>
+  </property>
+
+  <property>
+    <name>yarn.scheduler.capacity.queue-mappings</name>
+    <value></value>
+    <description>
+      A list of mappings that will be used to assign jobs to queues
+      The syntax for this list is [u|g]:[name]:[queue_name][,next mapping]*
+      Typically this list will be used to map users to queues,
+      for example, u:%user:%user maps all users to queues with the same name
+      as the user.
+    </description>
+  </property>
+
+  <property>
+    <name>yarn.scheduler.capacity.queue-mappings-override.enable</name>
+    <value>false</value>
+    <description>
+      If a queue mapping is present, will it override the value specified
+      by the user? This can be used by administrators to place jobs in queues
+      that are different than the one specified by the user.
+      The default is false.
+    </description>
+  </property>
+
+</configuration>

container/conf/java/hadoop/configuration.xsl

@@ -0,0 +1,40 @@
+<?xml version="1.0"?>
+<!--
+   Licensed to the Apache Software Foundation (ASF) under one or more
+   contributor license agreements.  See the NOTICE file distributed with
+   this work for additional information regarding copyright ownership.
+   The ASF licenses this file to You under the Apache License, Version 2.0
+   (the "License"); you may not use this file except in compliance with
+   the License.  You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+-->
+<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" version="1.0">
+<xsl:output method="html"/>
+<xsl:template match="configuration">
+<html>
+<body>
+<table border="1">
+<tr>
+ <td>name</td>
+ <td>value</td>
+ <td>description</td>
+</tr>
+<xsl:for-each select="property">
+<tr>
+  <td><a name="{name}"><xsl:value-of select="name"/></a></td>
+  <td><xsl:value-of select="value"/></td>
+  <td><xsl:value-of select="description"/></td>
+</tr>
+</xsl:for-each>
+</table>
+</body>
+</html>
+</xsl:template>
+</xsl:stylesheet>

container/conf/java/hadoop/container-executor.cfg

@@ -0,0 +1,4 @@
+yarn.nodemanager.linux-container-executor.group=#configured value of yarn.nodemanager.linux-container-executor.group
+banned.users=#comma separated list of users who can not run applications
+min.user.id=1000#Prevent other super-users
+allowed.system.users=##comma separated list of system users who CAN run applications

container/conf/java/hadoop/core-site.xml

@@ -0,0 +1,19 @@
+<?xml version="1.0"?>
+<configuration>
+    <property>
+        <name>fs.defaultFS</name>
+        <value>hdfs://data-hadoop:9000/</value>
+    </property>
+    <property>
+        <name>hadoop.tmp.dir</name>
+        <value>file:///root/hadoop/tmp</value>
+    </property>
+    <property>
+        <name>io.file.buffer.size</name>
+        <value>131702</value>
+    </property>
+    <property>
+        <name>ha.zookeeper.quorum</name>
+        <value>data-zookeeper,data-zookeeper1,data-zookeeper2</value>
+    </property>
+</configuration>

container/conf/java/hadoop/hadoop-env.cmd

@@ -0,0 +1,81 @@
+@echo off
+@rem Licensed to the Apache Software Foundation (ASF) under one or more
+@rem contributor license agreements.  See the NOTICE file distributed with
+@rem this work for additional information regarding copyright ownership.
+@rem The ASF licenses this file to You under the Apache License, Version 2.0
+@rem (the "License"); you may not use this file except in compliance with
+@rem the License.  You may obtain a copy of the License at
+@rem
+@rem     http://www.apache.org/licenses/LICENSE-2.0
+@rem
+@rem Unless required by applicable law or agreed to in writing, software
+@rem distributed under the License is distributed on an "AS IS" BASIS,
+@rem WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+@rem See the License for the specific language governing permissions and
+@rem limitations under the License.
+
+@rem Set Hadoop-specific environment variables here.
+
+@rem The only required environment variable is JAVA_HOME.  All others are
+@rem optional.  When running a distributed configuration it is best to
+@rem set JAVA_HOME in this file, so that it is correctly defined on
+@rem remote nodes.
+
+@rem The java implementation to use.  Required.
+set JAVA_HOME=%JAVA_HOME%
+
+@rem The jsvc implementation to use. Jsvc is required to run secure datanodes.
+@rem set JSVC_HOME=%JSVC_HOME%
+
+@rem set HADOOP_CONF_DIR=
+
+@rem Extra Java CLASSPATH elements.  Automatically insert capacity-scheduler.
+if exist %HADOOP_HOME%\contrib\capacity-scheduler (
+  if not defined HADOOP_CLASSPATH (
+    set HADOOP_CLASSPATH=%HADOOP_HOME%\contrib\capacity-scheduler\*.jar
+  ) else (
+    set HADOOP_CLASSPATH=%HADOOP_CLASSPATH%;%HADOOP_HOME%\contrib\capacity-scheduler\*.jar
+  )
+)
+
+@rem The maximum amount of heap to use, in MB. Default is 1000.
+@rem set HADOOP_HEAPSIZE=
+@rem set HADOOP_NAMENODE_INIT_HEAPSIZE=""
+
+@rem Extra Java runtime options.  Empty by default.
+@rem set HADOOP_OPTS=%HADOOP_OPTS% -Djava.net.preferIPv4Stack=true
+
+@rem Command specific options appended to HADOOP_OPTS when specified
+if not defined HADOOP_SECURITY_LOGGER (
+  set HADOOP_SECURITY_LOGGER=INFO,RFAS
+)
+if not defined HDFS_AUDIT_LOGGER (
+  set HDFS_AUDIT_LOGGER=INFO,NullAppender
+)
+
+set HADOOP_NAMENODE_OPTS=-Dhadoop.security.logger=%HADOOP_SECURITY_LOGGER% -Dhdfs.audit.logger=%HDFS_AUDIT_LOGGER% %HADOOP_NAMENODE_OPTS%
+set HADOOP_DATANODE_OPTS=-Dhadoop.security.logger=ERROR,RFAS %HADOOP_DATANODE_OPTS%
+set HADOOP_SECONDARYNAMENODE_OPTS=-Dhadoop.security.logger=%HADOOP_SECURITY_LOGGER% -Dhdfs.audit.logger=%HDFS_AUDIT_LOGGER% %HADOOP_SECONDARYNAMENODE_OPTS%
+
+@rem The following applies to multiple commands (fs, dfs, fsck, distcp etc)
+set HADOOP_CLIENT_OPTS=-Xmx512m %HADOOP_CLIENT_OPTS%
+@rem set HADOOP_JAVA_PLATFORM_OPTS="-XX:-UsePerfData %HADOOP_JAVA_PLATFORM_OPTS%"
+
+@rem On secure datanodes, user to run the datanode as after dropping privileges
+set HADOOP_SECURE_DN_USER=%HADOOP_SECURE_DN_USER%
+
+@rem Where log files are stored.  %HADOOP_HOME%/logs by default.
+@rem set HADOOP_LOG_DIR=%HADOOP_LOG_DIR%\%USERNAME%
+
+@rem Where log files are stored in the secure data environment.
+set HADOOP_SECURE_DN_LOG_DIR=%HADOOP_LOG_DIR%\%HADOOP_HDFS_USER%
+
+@rem The directory where pid files are stored. /tmp by default.
+@rem NOTE: this should be set to a directory that can only be written to by 
+@rem       the user that will run the hadoop daemons.  Otherwise there is the
+@rem       potential for a symlink attack.
+set HADOOP_PID_DIR=%HADOOP_PID_DIR%
+set HADOOP_SECURE_DN_PID_DIR=%HADOOP_PID_DIR%
+
+@rem A string representing this instance of hadoop. %USERNAME% by default.
+set HADOOP_IDENT_STRING=%USERNAME%

container/conf/java/hadoop/hadoop-env.sh

@@ -0,0 +1,104 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Set Hadoop-specific environment variables here.
+
+# The only required environment variable is JAVA_HOME.  All others are
+# optional.  When running a distributed configuration it is best to
+# set JAVA_HOME in this file, so that it is correctly defined on
+# remote nodes.
+
+# The java implementation to use.
+export JAVA_HOME=/share/lib/jdk
+
+# The jsvc implementation to use. Jsvc is required to run secure datanodes
+# that bind to privileged ports to provide authentication of data transfer
+# protocol.  Jsvc is not required if SASL is configured for authentication of
+# data transfer protocol using non-privileged ports.
+#export JSVC_HOME=${JSVC_HOME}
+
+#export HADOOP_HOME_WARN_SUPPRESS=1
+#export HADOOP_ROOT_LOGGER="WARN,DRFA"
+
+export HADOOP_CONF_DIR=${HADOOP_CONF_DIR:-"/etc/hadoop"}
+#export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native
+
+# Extra Java CLASSPATH elements.  Automatically insert capacity-scheduler.
+for f in $HADOOP_HOME/contrib/capacity-scheduler/*.jar; do
+  if [ "$HADOOP_CLASSPATH" ]; then
+    export HADOOP_CLASSPATH=$HADOOP_CLASSPATH:$f
+  else
+    export HADOOP_CLASSPATH=$f
+  fi
+done
+
+# The maximum amount of heap to use, in MB. Default is 1000.
+#export HADOOP_HEAPSIZE=
+#export HADOOP_NAMENODE_INIT_HEAPSIZE=""
+
+# Extra Java runtime options.  Empty by default.
+export HADOOP_OPTS="$HADOOP_OPTS -Djava.net.preferIPv4Stack=true"
+#export HADOOP_OPTS="-Djava.library.path=$HADOOP_PREFIX/lib"
+
+# Command specific options appended to HADOOP_OPTS when specified
+export HADOOP_NAMENODE_OPTS="-Dhadoop.security.logger=${HADOOP_SECURITY_LOGGER:-INFO,RFAS} -Dhdfs.audit.logger=${HDFS_AUDIT_LOGGER:-INFO,NullAppender} $HADOOP_NAMENODE_OPTS"
+export HADOOP_DATANODE_OPTS="-Dhadoop.security.logger=ERROR,RFAS $HADOOP_DATANODE_OPTS"
+
+export HADOOP_SECONDARYNAMENODE_OPTS="-Dhadoop.security.logger=${HADOOP_SECURITY_LOGGER:-INFO,RFAS} -Dhdfs.audit.logger=${HDFS_AUDIT_LOGGER:-INFO,NullAppender} $HADOOP_SECONDARYNAMENODE_OPTS"
+
+export HADOOP_NFS3_OPTS="$HADOOP_NFS3_OPTS"
+export HADOOP_PORTMAP_OPTS="-Xmx512m $HADOOP_PORTMAP_OPTS"
+
+# The following applies to multiple commands (fs, dfs, fsck, distcp etc)
+export HADOOP_CLIENT_OPTS="-Xmx512m $HADOOP_CLIENT_OPTS"
+#HADOOP_JAVA_PLATFORM_OPTS="-XX:-UsePerfData $HADOOP_JAVA_PLATFORM_OPTS"
+
+# On secure datanodes, user to run the datanode as after dropping privileges.
+# This **MUST** be uncommented to enable secure HDFS if using privileged ports
+# to provide authentication of data transfer protocol.  This **MUST NOT** be
+# defined if SASL is configured for authentication of data transfer protocol
+# using non-privileged ports.
+export HADOOP_SECURE_DN_USER=${HADOOP_SECURE_DN_USER}
+
+# Where log files are stored.  $HADOOP_HOME/logs by default.
+#export HADOOP_LOG_DIR=${HADOOP_LOG_DIR}/$USER
+export HADOOP_LOG_DIR=${HADOOP_LOG_DIR}
+
+# Where log files are stored in the secure data environment.
+export HADOOP_SECURE_DN_LOG_DIR=${HADOOP_LOG_DIR}/${HADOOP_HDFS_USER}
+
+###
+# HDFS Mover specific parameters
+###
+# Specify the JVM options to be used when starting the HDFS Mover.
+# These options will be appended to the options specified as HADOOP_OPTS
+# and therefore may override any similar flags set in HADOOP_OPTS
+#
+# export HADOOP_MOVER_OPTS=""
+
+###
+# Advanced Users Only!
+###
+
+# The directory where pid files are stored. /tmp by default.
+# NOTE: this should be set to a directory that can only be written to by 
+#       the user that will run the hadoop daemons.  Otherwise there is the
+#       potential for a symlink attack.
+export HADOOP_PID_DIR=${HADOOP_PID_DIR}
+export HADOOP_SECURE_DN_PID_DIR=${HADOOP_PID_DIR}
+
+# A string representing this instance of hadoop. $USER by default.
+export HADOOP_IDENT_STRING=$USER

container/conf/java/hadoop/hadoop-metrics.properties

@@ -0,0 +1,75 @@
+# Configuration of the "dfs" context for null
+dfs.class=org.apache.hadoop.metrics.spi.NullContext
+
+# Configuration of the "dfs" context for file
+#dfs.class=org.apache.hadoop.metrics.file.FileContext
+#dfs.period=10
+#dfs.fileName=/tmp/dfsmetrics.log
+
+# Configuration of the "dfs" context for ganglia
+# Pick one: Ganglia 3.0 (former) or Ganglia 3.1 (latter)
+# dfs.class=org.apache.hadoop.metrics.ganglia.GangliaContext
+# dfs.class=org.apache.hadoop.metrics.ganglia.GangliaContext31
+# dfs.period=10
+# dfs.servers=localhost:8649
+
+
+# Configuration of the "mapred" context for null
+mapred.class=org.apache.hadoop.metrics.spi.NullContext
+
+# Configuration of the "mapred" context for file
+#mapred.class=org.apache.hadoop.metrics.file.FileContext
+#mapred.period=10
+#mapred.fileName=/tmp/mrmetrics.log
+
+# Configuration of the "mapred" context for ganglia
+# Pick one: Ganglia 3.0 (former) or Ganglia 3.1 (latter)
+# mapred.class=org.apache.hadoop.metrics.ganglia.GangliaContext
+# mapred.class=org.apache.hadoop.metrics.ganglia.GangliaContext31
+# mapred.period=10
+# mapred.servers=localhost:8649
+
+
+# Configuration of the "jvm" context for null
+#jvm.class=org.apache.hadoop.metrics.spi.NullContext
+
+# Configuration of the "jvm" context for file
+#jvm.class=org.apache.hadoop.metrics.file.FileContext
+#jvm.period=10
+#jvm.fileName=/tmp/jvmmetrics.log
+
+# Configuration of the "jvm" context for ganglia
+# jvm.class=org.apache.hadoop.metrics.ganglia.GangliaContext
+# jvm.class=org.apache.hadoop.metrics.ganglia.GangliaContext31
+# jvm.period=10
+# jvm.servers=localhost:8649
+
+# Configuration of the "rpc" context for null
+rpc.class=org.apache.hadoop.metrics.spi.NullContext
+
+# Configuration of the "rpc" context for file
+#rpc.class=org.apache.hadoop.metrics.file.FileContext
+#rpc.period=10
+#rpc.fileName=/tmp/rpcmetrics.log
+
+# Configuration of the "rpc" context for ganglia
+# rpc.class=org.apache.hadoop.metrics.ganglia.GangliaContext
+# rpc.class=org.apache.hadoop.metrics.ganglia.GangliaContext31
+# rpc.period=10
+# rpc.servers=localhost:8649
+
+
+# Configuration of the "ugi" context for null
+ugi.class=org.apache.hadoop.metrics.spi.NullContext
+
+# Configuration of the "ugi" context for file
+#ugi.class=org.apache.hadoop.metrics.file.FileContext
+#ugi.period=10
+#ugi.fileName=/tmp/ugimetrics.log
+
+# Configuration of the "ugi" context for ganglia
+# ugi.class=org.apache.hadoop.metrics.ganglia.GangliaContext
+# ugi.class=org.apache.hadoop.metrics.ganglia.GangliaContext31
+# ugi.period=10
+# ugi.servers=localhost:8649
+

container/conf/java/hadoop/hadoop-metrics2.properties

@@ -0,0 +1,68 @@
+# syntax: [prefix].[source|sink].[instance].[options]
+# See javadoc of package-info.java for org.apache.hadoop.metrics2 for details
+
+*.sink.file.class=org.apache.hadoop.metrics2.sink.FileSink
+# default sampling period, in seconds
+*.period=10
+
+# The namenode-metrics.out will contain metrics from all context
+#namenode.sink.file.filename=namenode-metrics.out
+# Specifying a special sampling period for namenode:
+#namenode.sink.*.period=8
+
+#datanode.sink.file.filename=datanode-metrics.out
+
+#resourcemanager.sink.file.filename=resourcemanager-metrics.out
+
+#nodemanager.sink.file.filename=nodemanager-metrics.out
+
+#mrappmaster.sink.file.filename=mrappmaster-metrics.out
+
+#jobhistoryserver.sink.file.filename=jobhistoryserver-metrics.out
+
+# the following example split metrics of different
+# context to different sinks (in this case files)
+#nodemanager.sink.file_jvm.class=org.apache.hadoop.metrics2.sink.FileSink
+#nodemanager.sink.file_jvm.context=jvm
+#nodemanager.sink.file_jvm.filename=nodemanager-jvm-metrics.out
+#nodemanager.sink.file_mapred.class=org.apache.hadoop.metrics2.sink.FileSink
+#nodemanager.sink.file_mapred.context=mapred
+#nodemanager.sink.file_mapred.filename=nodemanager-mapred-metrics.out
+
+#
+# Below are for sending metrics to Ganglia
+#
+# for Ganglia 3.0 support
+# *.sink.ganglia.class=org.apache.hadoop.metrics2.sink.ganglia.GangliaSink30
+#
+# for Ganglia 3.1 support
+# *.sink.ganglia.class=org.apache.hadoop.metrics2.sink.ganglia.GangliaSink31
+
+# *.sink.ganglia.period=10
+
+# default for supportsparse is false
+# *.sink.ganglia.supportsparse=true
+
+#*.sink.ganglia.slope=jvm.metrics.gcCount=zero,jvm.metrics.memHeapUsedM=both
+#*.sink.ganglia.dmax=jvm.metrics.threadsBlocked=70,jvm.metrics.memHeapUsedM=40
+
+# Tag values to use for the ganglia prefix. If not defined no tags are used.
+# If '*' all tags are used. If specifiying multiple tags separate them with 
+# commas. Note that the last segment of the property name is the context name.
+#
+#*.sink.ganglia.tagsForPrefix.jvm=ProcesName
+#*.sink.ganglia.tagsForPrefix.dfs=
+#*.sink.ganglia.tagsForPrefix.rpc=
+#*.sink.ganglia.tagsForPrefix.mapred=
+
+#namenode.sink.ganglia.servers=yourgangliahost_1:8649,yourgangliahost_2:8649
+
+#datanode.sink.ganglia.servers=yourgangliahost_1:8649,yourgangliahost_2:8649
+
+#resourcemanager.sink.ganglia.servers=yourgangliahost_1:8649,yourgangliahost_2:8649
+
+#nodemanager.sink.ganglia.servers=yourgangliahost_1:8649,yourgangliahost_2:8649
+
+#mrappmaster.sink.ganglia.servers=yourgangliahost_1:8649,yourgangliahost_2:8649
+
+#jobhistoryserver.sink.ganglia.servers=yourgangliahost_1:8649,yourgangliahost_2:8649

container/conf/java/hadoop/hadoop-policy.xml

@@ -0,0 +1,226 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<!--
+ 
+ Licensed to the Apache Software Foundation (ASF) under one
+ or more contributor license agreements.  See the NOTICE file
+ distributed with this work for additional information
+ regarding copyright ownership.  The ASF licenses this file
+ to you under the Apache License, Version 2.0 (the
+ "License"); you may not use this file except in compliance
+ with the License.  You may obtain a copy of the License at
+
+     http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+
+-->
+
+<!-- Put site-specific property overrides in this file. -->
+
+<configuration>
+  <property>
+    <name>security.client.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for ClientProtocol, which is used by user code
+    via the DistributedFileSystem.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.client.datanode.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for ClientDatanodeProtocol, the client-to-datanode protocol
+    for block recovery.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.datanode.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for DatanodeProtocol, which is used by datanodes to
+    communicate with the namenode.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.inter.datanode.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for InterDatanodeProtocol, the inter-datanode protocol
+    for updating generation timestamp.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.namenode.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for NamenodeProtocol, the protocol used by the secondary
+    namenode to communicate with the namenode.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+ <property>
+    <name>security.admin.operations.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for AdminOperationsProtocol. Used for admin commands.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.refresh.user.mappings.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for RefreshUserMappingsProtocol. Used to refresh
+    users mappings. The ACL is a comma-separated list of user and
+    group names. The user and group list is separated by a blank. For
+    e.g. "alice,bob users,wheel".  A special value of "*" means all
+    users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.refresh.policy.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for RefreshAuthorizationPolicyProtocol, used by the
+    dfsadmin and mradmin commands to refresh the security policy in-effect.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.ha.service.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for HAService protocol used by HAAdmin to manage the
+      active and stand-by states of namenode.</description>
+  </property>
+
+  <property>
+    <name>security.zkfc.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for access to the ZK Failover Controller
+    </description>
+  </property>
+
+  <property>
+    <name>security.qjournal.service.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for QJournalProtocol, used by the NN to communicate with
+    JNs when using the QuorumJournalManager for edit logs.</description>
+  </property>
+
+  <property>
+    <name>security.mrhs.client.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for HSClientProtocol, used by job clients to
+    communciate with the MR History Server job status etc. 
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <!-- YARN Protocols -->
+
+  <property>
+    <name>security.resourcetracker.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for ResourceTrackerProtocol, used by the
+    ResourceManager and NodeManager to communicate with each other.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.resourcemanager-administration.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for ResourceManagerAdministrationProtocol, for admin commands. 
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.applicationclient.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for ApplicationClientProtocol, used by the ResourceManager 
+    and applications submission clients to communicate with each other.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.applicationmaster.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for ApplicationMasterProtocol, used by the ResourceManager 
+    and ApplicationMasters to communicate with each other.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.containermanagement.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for ContainerManagementProtocol protocol, used by the NodeManager 
+    and ApplicationMasters to communicate with each other.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.resourcelocalizer.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for ResourceLocalizer protocol, used by the NodeManager 
+    and ResourceLocalizer to communicate with each other.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.job.task.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for TaskUmbilicalProtocol, used by the map and reduce
+    tasks to communicate with the parent tasktracker.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.job.client.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for MRClientProtocol, used by job clients to
+    communciate with the MR ApplicationMaster to query job status etc. 
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.applicationhistory.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for ApplicationHistoryProtocol, used by the timeline
+    server and the generic history service client to communicate with each other.
+    The ACL is a comma-separated list of user and group names. The user and
+    group list is separated by a blank. For e.g. "alice,bob users,wheel".
+    A special value of "*" means all users are allowed.</description>
+  </property>
+</configuration>

container/conf/java/hadoop/hdfs-site.xml

@@ -0,0 +1,30 @@
+<?xml version="1.0"?>
+<configuration>
+    <property>
+        <name>dfs.http.address</name>
+        <value>0.0.0.0:50070</value>
+    </property>
+    <property>
+        <name>dfs.secondary.http.address</name>
+        <value>data-hadoop-slave:50090</value>
+    </property>
+    <property>
+        <name>dfs.namenode.name.dir</name>
+        <value>file:///root/hdfs/namenode</value>
+        <description>NameNode directory for namespace and transaction logs storage.</description>
+    </property>
+    <property>
+        <name>dfs.datanode.data.dir</name>
+        <value>file:///root/hdfs/datanode</value>
+        <description>DataNode directory</description>
+    </property>
+    <property>
+        <name>dfs.replication</name>
+        <value>2</value>
+    </property>
+    <property>  
+         <name>dfs.block.size</name>  
+         <value>134217728</value>  
+         <!--value>67108864</value-->  
+    </property>
+</configuration>

container/conf/java/hadoop/httpfs-env.sh

@@ -0,0 +1,53 @@
+#!/bin/bash
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License. See accompanying LICENSE file.
+#
+
+# Set httpfs specific environment variables here.
+
+# Settings for the Embedded Tomcat that runs HttpFS
+# Java System properties for HttpFS should be specified in this variable
+#
+# export CATALINA_OPTS=
+
+# HttpFS logs directory
+#
+# export HTTPFS_LOG=${HTTPFS_HOME}/logs
+
+# HttpFS temporary directory
+#
+# export HTTPFS_TEMP=${HTTPFS_HOME}/temp
+
+# The HTTP port used by HttpFS
+#
+# export HTTPFS_HTTP_PORT=14000
+
+# The Admin port used by HttpFS
+#
+# export HTTPFS_ADMIN_PORT=`expr ${HTTPFS_HTTP_PORT} + 1`
+
+# The hostname HttpFS server runs on
+#
+# export HTTPFS_HTTP_HOSTNAME=`hostname -f`
+
+# Indicates if HttpFS is using SSL
+#
+# export HTTPFS_SSL_ENABLED=false
+
+# The location of the SSL keystore if using SSL
+#
+# export HTTPFS_SSL_KEYSTORE_FILE=${HOME}/.keystore
+
+# The password of the SSL keystore if using SSL
+#
+# export HTTPFS_SSL_KEYSTORE_PASS=password

container/conf/java/hadoop/httpfs-log4j.properties

@@ -0,0 +1,35 @@
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License. See accompanying LICENSE file.
+#
+
+# If the Java System property 'httpfs.log.dir' is not defined at HttpFSServer start up time
+# Setup sets its value to '${httpfs.home}/logs'
+
+log4j.appender.httpfs=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.httpfs.DatePattern='.'yyyy-MM-dd
+log4j.appender.httpfs.File=${httpfs.log.dir}/httpfs.log
+log4j.appender.httpfs.Append=true
+log4j.appender.httpfs.layout=org.apache.log4j.PatternLayout
+log4j.appender.httpfs.layout.ConversionPattern=%d{ISO8601} %5p %c{1} [%X{hostname}][%X{user}:%X{doAs}] %X{op} %m%n
+
+log4j.appender.httpfsaudit=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.httpfsaudit.DatePattern='.'yyyy-MM-dd
+log4j.appender.httpfsaudit.File=${httpfs.log.dir}/httpfs-audit.log
+log4j.appender.httpfsaudit.Append=true
+log4j.appender.httpfsaudit.layout=org.apache.log4j.PatternLayout
+log4j.appender.httpfsaudit.layout.ConversionPattern=%d{ISO8601} %5p [%X{hostname}][%X{user}:%X{doAs}] %X{op} %m%n
+
+log4j.logger.httpfsaudit=INFO, httpfsaudit
+
+log4j.logger.org.apache.hadoop.fs.http.server=INFO, httpfs
+log4j.logger.org.apache.hadoop.lib=INFO, httpfs

container/conf/java/hadoop/httpfs-signature.secret

@@ -0,0 +1 @@
+hadoop httpfs secret

container/conf/java/hadoop/httpfs-site.xml

@@ -0,0 +1,17 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+  Licensed under the Apache License, Version 2.0 (the "License");
+  you may not use this file except in compliance with the License.
+  You may obtain a copy of the License at
+
+  http://www.apache.org/licenses/LICENSE-2.0
+
+  Unless required by applicable law or agreed to in writing, software
+  distributed under the License is distributed on an "AS IS" BASIS,
+  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+  See the License for the specific language governing permissions and
+  limitations under the License.
+-->
+<configuration>
+
+</configuration>

container/conf/java/hadoop/kms-acls.xml

@@ -0,0 +1,135 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+  Licensed under the Apache License, Version 2.0 (the "License");
+  you may not use this file except in compliance with the License.
+  You may obtain a copy of the License at
+
+  http://www.apache.org/licenses/LICENSE-2.0
+
+  Unless required by applicable law or agreed to in writing, software
+  distributed under the License is distributed on an "AS IS" BASIS,
+  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+  See the License for the specific language governing permissions and
+  limitations under the License.
+-->
+<configuration>
+
+  <!-- This file is hot-reloaded when it changes -->
+
+  <!-- KMS ACLs -->
+
+  <property>
+    <name>hadoop.kms.acl.CREATE</name>
+    <value>*</value>
+    <description>
+      ACL for create-key operations.
+      If the user is not in the GET ACL, the key material is not returned
+      as part of the response.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.acl.DELETE</name>
+    <value>*</value>
+    <description>
+      ACL for delete-key operations.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.acl.ROLLOVER</name>
+    <value>*</value>
+    <description>
+      ACL for rollover-key operations.
+      If the user is not in the GET ACL, the key material is not returned
+      as part of the response.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.acl.GET</name>
+    <value>*</value>
+    <description>
+      ACL for get-key-version and get-current-key operations.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.acl.GET_KEYS</name>
+    <value>*</value>
+    <description>
+      ACL for get-keys operations.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.acl.GET_METADATA</name>
+    <value>*</value>
+    <description>
+      ACL for get-key-metadata and get-keys-metadata operations.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.acl.SET_KEY_MATERIAL</name>
+    <value>*</value>
+    <description>
+      Complementary ACL for CREATE and ROLLOVER operations to allow the client
+      to provide the key material when creating or rolling a key.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.acl.GENERATE_EEK</name>
+    <value>*</value>
+    <description>
+      ACL for generateEncryptedKey CryptoExtension operations.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.acl.DECRYPT_EEK</name>
+    <value>*</value>
+    <description>
+      ACL for decryptEncryptedKey CryptoExtension operations.
+    </description>
+  </property>
+
+  <property>
+    <name>default.key.acl.MANAGEMENT</name>
+    <value>*</value>
+    <description>
+      default ACL for MANAGEMENT operations for all key acls that are not
+      explicitly defined.
+    </description>
+  </property>
+
+  <property>
+    <name>default.key.acl.GENERATE_EEK</name>
+    <value>*</value>
+    <description>
+      default ACL for GENERATE_EEK operations for all key acls that are not
+      explicitly defined.
+    </description>
+  </property>
+
+  <property>
+    <name>default.key.acl.DECRYPT_EEK</name>
+    <value>*</value>
+    <description>
+      default ACL for DECRYPT_EEK operations for all key acls that are not
+      explicitly defined.
+    </description>
+  </property>
+
+  <property>
+    <name>default.key.acl.READ</name>
+    <value>*</value>
+    <description>
+      default ACL for READ operations for all key acls that are not
+      explicitly defined.
+    </description>
+  </property>
+
+
+</configuration>

container/conf/java/hadoop/kms-env.sh

@@ -0,0 +1,55 @@
+#!/bin/bash
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License. See accompanying LICENSE file.
+#
+
+# Set kms specific environment variables here.
+
+# Settings for the Embedded Tomcat that runs KMS
+# Java System properties for KMS should be specified in this variable
+#
+# export CATALINA_OPTS=
+
+# KMS logs directory
+#
+# export KMS_LOG=${KMS_HOME}/logs
+
+# KMS temporary directory
+#
+# export KMS_TEMP=${KMS_HOME}/temp
+
+# The HTTP port used by KMS
+#
+# export KMS_HTTP_PORT=16000
+
+# The Admin port used by KMS
+#
+# export KMS_ADMIN_PORT=`expr ${KMS_HTTP_PORT} + 1`
+
+# The maximum number of Tomcat handler threads
+#
+# export KMS_MAX_THREADS=1000
+
+# The location of the SSL keystore if using SSL
+#
+# export KMS_SSL_KEYSTORE_FILE=${HOME}/.keystore
+
+# The password of the SSL keystore if using SSL
+#
+# export KMS_SSL_KEYSTORE_PASS=password
+
+# The full path to any native libraries that need to be loaded
+# (For eg. location of natively compiled tomcat Apache portable
+# runtime (APR) libraries
+#
+# export JAVA_LIBRARY_PATH=${HOME}/lib/native

container/conf/java/hadoop/kms-log4j.properties

@@ -0,0 +1,38 @@
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License. See accompanying LICENSE file.
+#
+
+# If the Java System property 'kms.log.dir' is not defined at KMS start up time
+# Setup sets its value to '${kms.home}/logs'
+
+log4j.appender.kms=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.kms.DatePattern='.'yyyy-MM-dd
+log4j.appender.kms.File=${kms.log.dir}/kms.log
+log4j.appender.kms.Append=true
+log4j.appender.kms.layout=org.apache.log4j.PatternLayout
+log4j.appender.kms.layout.ConversionPattern=%d{ISO8601} %-5p %c{1} - %m%n
+
+log4j.appender.kms-audit=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.kms-audit.DatePattern='.'yyyy-MM-dd
+log4j.appender.kms-audit.File=${kms.log.dir}/kms-audit.log
+log4j.appender.kms-audit.Append=true
+log4j.appender.kms-audit.layout=org.apache.log4j.PatternLayout
+log4j.appender.kms-audit.layout.ConversionPattern=%d{ISO8601} %m%n
+
+log4j.logger.kms-audit=INFO, kms-audit
+log4j.additivity.kms-audit=false
+
+log4j.rootLogger=ALL, kms
+log4j.logger.org.apache.hadoop.conf=ERROR
+log4j.logger.org.apache.hadoop=INFO
+log4j.logger.com.sun.jersey.server.wadl.generators.WadlGeneratorJAXBGrammarGenerator=OFF

container/conf/java/hadoop/kms-site.xml

@@ -0,0 +1,173 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!--
+  Licensed under the Apache License, Version 2.0 (the "License");
+  you may not use this file except in compliance with the License.
+  You may obtain a copy of the License at
+
+  http://www.apache.org/licenses/LICENSE-2.0
+
+  Unless required by applicable law or agreed to in writing, software
+  distributed under the License is distributed on an "AS IS" BASIS,
+  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+  See the License for the specific language governing permissions and
+  limitations under the License.
+-->
+<configuration>
+
+  <!-- KMS Backend KeyProvider -->
+
+  <property>
+    <name>hadoop.kms.key.provider.uri</name>
+    <value>jceks://file@/${user.home}/kms.keystore</value>
+    <description>
+      URI of the backing KeyProvider for the KMS.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.security.keystore.JavaKeyStoreProvider.password</name>
+    <value>none</value>
+    <description>
+      If using the JavaKeyStoreProvider, the password for the keystore file.
+    </description>
+  </property>
+
+  <!-- KMS Cache -->
+
+  <property>
+    <name>hadoop.kms.cache.enable</name>
+    <value>true</value>
+    <description>
+      Whether the KMS will act as a cache for the backing KeyProvider.
+      When the cache is enabled, operations like getKeyVersion, getMetadata,
+      and getCurrentKey will sometimes return cached data without consulting
+      the backing KeyProvider. Cached values are flushed when keys are deleted
+      or modified.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.cache.timeout.ms</name>
+    <value>600000</value>
+    <description>
+      Expiry time for the KMS key version and key metadata cache, in
+      milliseconds. This affects getKeyVersion and getMetadata.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.current.key.cache.timeout.ms</name>
+    <value>30000</value>
+    <description>
+      Expiry time for the KMS current key cache, in milliseconds. This
+      affects getCurrentKey operations.
+    </description>
+  </property>
+
+  <!-- KMS Audit -->
+
+  <property>
+    <name>hadoop.kms.audit.aggregation.window.ms</name>
+    <value>10000</value>
+    <description>
+      Duplicate audit log events within the aggregation window (specified in
+      ms) are quashed to reduce log traffic. A single message for aggregated
+      events is printed at the end of the window, along with a count of the
+      number of aggregated events.
+    </description>
+  </property>
+
+  <!-- KMS Security -->
+
+  <property>
+    <name>hadoop.kms.authentication.type</name>
+    <value>simple</value>
+    <description>
+      Authentication type for the KMS. Can be either &quot;simple&quot;
+      or &quot;kerberos&quot;.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.authentication.kerberos.keytab</name>
+    <value>${user.home}/kms.keytab</value>
+    <description>
+      Path to the keytab with credentials for the configured Kerberos principal.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.authentication.kerberos.principal</name>
+    <value>HTTP/localhost</value>
+    <description>
+      The Kerberos principal to use for the HTTP endpoint.
+      The principal must start with 'HTTP/' as per the Kerberos HTTP SPNEGO specification.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.authentication.kerberos.name.rules</name>
+    <value>DEFAULT</value>
+    <description>
+      Rules used to resolve Kerberos principal names.
+    </description>
+  </property>
+
+  <!-- Authentication cookie signature source -->
+
+  <property>
+    <name>hadoop.kms.authentication.signer.secret.provider</name>
+    <value>random</value>
+    <description>
+      Indicates how the secret to sign the authentication cookies will be
+      stored. Options are 'random' (default), 'string' and 'zookeeper'.
+      If using a setup with multiple KMS instances, 'zookeeper' should be used.
+    </description>
+  </property>
+
+  <!-- Configuration for 'zookeeper' authentication cookie signature source -->
+
+  <property>
+    <name>hadoop.kms.authentication.signer.secret.provider.zookeeper.path</name>
+    <value>/hadoop-kms/hadoop-auth-signature-secret</value>
+    <description>
+      The Zookeeper ZNode path where the KMS instances will store and retrieve
+      the secret from.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.authentication.signer.secret.provider.zookeeper.connection.string</name>
+    <value>#HOSTNAME#:#PORT#,...</value>
+    <description>
+      The Zookeeper connection string, a list of hostnames and port comma
+      separated.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.authentication.signer.secret.provider.zookeeper.auth.type</name>
+    <value>kerberos</value>
+    <description>
+      The Zookeeper authentication type, 'none' or 'sasl' (Kerberos).
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.authentication.signer.secret.provider.zookeeper.kerberos.keytab</name>
+    <value>/etc/hadoop/conf/kms.keytab</value>
+    <description>
+      The absolute path for the Kerberos keytab with the credentials to
+      connect to Zookeeper.
+    </description>
+  </property>
+
+  <property>
+    <name>hadoop.kms.authentication.signer.secret.provider.zookeeper.kerberos.principal</name>
+    <value>kms/#HOSTNAME#</value>
+    <description>
+      The Kerberos service principal used to connect to Zookeeper.
+    </description>
+  </property>
+
+</configuration>

container/conf/java/hadoop/log4j.properties

@@ -0,0 +1,268 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Define some default values that can be overridden by system properties
+hadoop.root.logger=INFO,console
+hadoop.log.dir=.
+hadoop.log.file=hadoop.log
+
+# Define the root logger to the system property "hadoop.root.logger".
+log4j.rootLogger=${hadoop.root.logger}, EventCounter
+
+# Logging Threshold
+log4j.threshold=ALL
+
+# Null Appender
+log4j.appender.NullAppender=org.apache.log4j.varia.NullAppender
+
+#
+# Rolling File Appender - cap space usage at 5gb.
+#
+hadoop.log.maxfilesize=256MB
+hadoop.log.maxbackupindex=20
+log4j.appender.RFA=org.apache.log4j.RollingFileAppender
+log4j.appender.RFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+log4j.appender.RFA.MaxFileSize=${hadoop.log.maxfilesize}
+log4j.appender.RFA.MaxBackupIndex=${hadoop.log.maxbackupindex}
+
+log4j.appender.RFA.layout=org.apache.log4j.PatternLayout
+
+# Pattern format: Date LogLevel LoggerName LogMessage
+log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+# Debugging Pattern format
+#log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+
+#
+# Daily Rolling File Appender
+#
+
+log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.DRFA.File=${hadoop.log.dir}/${hadoop.log.file}
+
+# Rollover at midnight
+log4j.appender.DRFA.DatePattern=.yyyy-MM-dd
+
+log4j.appender.DRFA.layout=org.apache.log4j.PatternLayout
+
+# Pattern format: Date LogLevel LoggerName LogMessage
+log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+# Debugging Pattern format
+#log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p %c{2} (%F:%M(%L)) - %m%n
+
+
+#
+# console
+# Add "console" to rootlogger above if you want to use this 
+#
+
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.err
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
+
+#
+# TaskLog Appender
+#
+
+#Default values
+hadoop.tasklog.taskid=null
+hadoop.tasklog.iscleanup=false
+hadoop.tasklog.noKeepSplits=4
+hadoop.tasklog.totalLogFileSize=100
+hadoop.tasklog.purgeLogSplits=true
+hadoop.tasklog.logsRetainHours=12
+
+log4j.appender.TLA=org.apache.hadoop.mapred.TaskLogAppender
+log4j.appender.TLA.taskId=${hadoop.tasklog.taskid}
+log4j.appender.TLA.isCleanup=${hadoop.tasklog.iscleanup}
+log4j.appender.TLA.totalLogFileSize=${hadoop.tasklog.totalLogFileSize}
+
+log4j.appender.TLA.layout=org.apache.log4j.PatternLayout
+log4j.appender.TLA.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+
+#
+# HDFS block state change log from block manager
+#
+# Uncomment the following to suppress normal block state change
+# messages from BlockManager in NameNode.
+#log4j.logger.BlockStateChange=WARN
+
+#
+#Security appender
+#
+hadoop.security.logger=INFO,NullAppender
+hadoop.security.log.maxfilesize=256MB
+hadoop.security.log.maxbackupindex=20
+log4j.category.SecurityLogger=${hadoop.security.logger}
+hadoop.security.log.file=SecurityAuth-${user.name}.audit
+log4j.appender.RFAS=org.apache.log4j.RollingFileAppender 
+log4j.appender.RFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}
+log4j.appender.RFAS.layout=org.apache.log4j.PatternLayout
+log4j.appender.RFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+log4j.appender.RFAS.MaxFileSize=${hadoop.security.log.maxfilesize}
+log4j.appender.RFAS.MaxBackupIndex=${hadoop.security.log.maxbackupindex}
+
+#
+# Daily Rolling Security appender
+#
+log4j.appender.DRFAS=org.apache.log4j.DailyRollingFileAppender 
+log4j.appender.DRFAS.File=${hadoop.log.dir}/${hadoop.security.log.file}
+log4j.appender.DRFAS.layout=org.apache.log4j.PatternLayout
+log4j.appender.DRFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+log4j.appender.DRFAS.DatePattern=.yyyy-MM-dd
+
+#
+# hadoop configuration logging
+#
+
+# Uncomment the following line to turn off configuration deprecation warnings.
+# log4j.logger.org.apache.hadoop.conf.Configuration.deprecation=WARN
+
+#
+# hdfs audit logging
+#
+hdfs.audit.logger=INFO,NullAppender
+hdfs.audit.log.maxfilesize=256MB
+hdfs.audit.log.maxbackupindex=20
+log4j.logger.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=${hdfs.audit.logger}
+log4j.additivity.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=false
+log4j.appender.RFAAUDIT=org.apache.log4j.RollingFileAppender
+log4j.appender.RFAAUDIT.File=${hadoop.log.dir}/hdfs-audit.log
+log4j.appender.RFAAUDIT.layout=org.apache.log4j.PatternLayout
+log4j.appender.RFAAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
+log4j.appender.RFAAUDIT.MaxFileSize=${hdfs.audit.log.maxfilesize}
+log4j.appender.RFAAUDIT.MaxBackupIndex=${hdfs.audit.log.maxbackupindex}
+
+#
+# mapred audit logging
+#
+mapred.audit.logger=INFO,NullAppender
+mapred.audit.log.maxfilesize=256MB
+mapred.audit.log.maxbackupindex=20
+log4j.logger.org.apache.hadoop.mapred.AuditLogger=${mapred.audit.logger}
+log4j.additivity.org.apache.hadoop.mapred.AuditLogger=false
+log4j.appender.MRAUDIT=org.apache.log4j.RollingFileAppender
+log4j.appender.MRAUDIT.File=${hadoop.log.dir}/mapred-audit.log
+log4j.appender.MRAUDIT.layout=org.apache.log4j.PatternLayout
+log4j.appender.MRAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
+log4j.appender.MRAUDIT.MaxFileSize=${mapred.audit.log.maxfilesize}
+log4j.appender.MRAUDIT.MaxBackupIndex=${mapred.audit.log.maxbackupindex}
+
+# Custom Logging levels
+
+#log4j.logger.org.apache.hadoop.mapred.JobTracker=DEBUG
+#log4j.logger.org.apache.hadoop.mapred.TaskTracker=DEBUG
+#log4j.logger.org.apache.hadoop.hdfs.server.namenode.FSNamesystem.audit=DEBUG
+
+# Jets3t library
+log4j.logger.org.jets3t.service.impl.rest.httpclient.RestS3Service=ERROR
+
+# AWS SDK & S3A FileSystem
+log4j.logger.com.amazonaws=ERROR
+log4j.logger.com.amazonaws.http.AmazonHttpClient=ERROR
+log4j.logger.org.apache.hadoop.fs.s3a.S3AFileSystem=WARN
+
+#
+# Event Counter Appender
+# Sends counts of logging messages at different severity levels to Hadoop Metrics.
+#
+log4j.appender.EventCounter=org.apache.hadoop.log.metrics.EventCounter
+
+#
+# Job Summary Appender 
+#
+# Use following logger to send summary to separate file defined by 
+# hadoop.mapreduce.jobsummary.log.file :
+# hadoop.mapreduce.jobsummary.logger=INFO,JSA
+# 
+hadoop.mapreduce.jobsummary.logger=${hadoop.root.logger}
+hadoop.mapreduce.jobsummary.log.file=hadoop-mapreduce.jobsummary.log
+hadoop.mapreduce.jobsummary.log.maxfilesize=256MB
+hadoop.mapreduce.jobsummary.log.maxbackupindex=20
+log4j.appender.JSA=org.apache.log4j.RollingFileAppender
+log4j.appender.JSA.File=${hadoop.log.dir}/${hadoop.mapreduce.jobsummary.log.file}
+log4j.appender.JSA.MaxFileSize=${hadoop.mapreduce.jobsummary.log.maxfilesize}
+log4j.appender.JSA.MaxBackupIndex=${hadoop.mapreduce.jobsummary.log.maxbackupindex}
+log4j.appender.JSA.layout=org.apache.log4j.PatternLayout
+log4j.appender.JSA.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{2}: %m%n
+log4j.logger.org.apache.hadoop.mapred.JobInProgress$JobSummary=${hadoop.mapreduce.jobsummary.logger}
+log4j.additivity.org.apache.hadoop.mapred.JobInProgress$JobSummary=false
+
+#
+# Yarn ResourceManager Application Summary Log 
+#
+# Set the ResourceManager summary log filename
+yarn.server.resourcemanager.appsummary.log.file=rm-appsummary.log
+# Set the ResourceManager summary log level and appender
+yarn.server.resourcemanager.appsummary.logger=${hadoop.root.logger}
+#yarn.server.resourcemanager.appsummary.logger=INFO,RMSUMMARY
+
+# To enable AppSummaryLogging for the RM, 
+# set yarn.server.resourcemanager.appsummary.logger to 
+# <LEVEL>,RMSUMMARY in hadoop-env.sh
+
+# Appender for ResourceManager Application Summary Log
+# Requires the following properties to be set
+#    - hadoop.log.dir (Hadoop Log directory)
+#    - yarn.server.resourcemanager.appsummary.log.file (resource manager app summary log filename)
+#    - yarn.server.resourcemanager.appsummary.logger (resource manager app summary log level and appender)
+
+log4j.logger.org.apache.hadoop.yarn.server.resourcemanager.RMAppManager$ApplicationSummary=${yarn.server.resourcemanager.appsummary.logger}
+log4j.additivity.org.apache.hadoop.yarn.server.resourcemanager.RMAppManager$ApplicationSummary=false
+log4j.appender.RMSUMMARY=org.apache.log4j.RollingFileAppender
+log4j.appender.RMSUMMARY.File=${hadoop.log.dir}/${yarn.server.resourcemanager.appsummary.log.file}
+log4j.appender.RMSUMMARY.MaxFileSize=256MB
+log4j.appender.RMSUMMARY.MaxBackupIndex=20
+log4j.appender.RMSUMMARY.layout=org.apache.log4j.PatternLayout
+log4j.appender.RMSUMMARY.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
+
+# HS audit log configs
+#mapreduce.hs.audit.logger=INFO,HSAUDIT
+#log4j.logger.org.apache.hadoop.mapreduce.v2.hs.HSAuditLogger=${mapreduce.hs.audit.logger}
+#log4j.additivity.org.apache.hadoop.mapreduce.v2.hs.HSAuditLogger=false
+#log4j.appender.HSAUDIT=org.apache.log4j.DailyRollingFileAppender
+#log4j.appender.HSAUDIT.File=${hadoop.log.dir}/hs-audit.log
+#log4j.appender.HSAUDIT.layout=org.apache.log4j.PatternLayout
+#log4j.appender.HSAUDIT.layout.ConversionPattern=%d{ISO8601} %p %c{2}: %m%n
+#log4j.appender.HSAUDIT.DatePattern=.yyyy-MM-dd
+
+# Http Server Request Logs
+#log4j.logger.http.requests.namenode=INFO,namenoderequestlog
+#log4j.appender.namenoderequestlog=org.apache.hadoop.http.HttpRequestLogAppender
+#log4j.appender.namenoderequestlog.Filename=${hadoop.log.dir}/jetty-namenode-yyyy_mm_dd.log
+#log4j.appender.namenoderequestlog.RetainDays=3
+
+#log4j.logger.http.requests.datanode=INFO,datanoderequestlog
+#log4j.appender.datanoderequestlog=org.apache.hadoop.http.HttpRequestLogAppender
+#log4j.appender.datanoderequestlog.Filename=${hadoop.log.dir}/jetty-datanode-yyyy_mm_dd.log
+#log4j.appender.datanoderequestlog.RetainDays=3
+
+#log4j.logger.http.requests.resourcemanager=INFO,resourcemanagerrequestlog
+#log4j.appender.resourcemanagerrequestlog=org.apache.hadoop.http.HttpRequestLogAppender
+#log4j.appender.resourcemanagerrequestlog.Filename=${hadoop.log.dir}/jetty-resourcemanager-yyyy_mm_dd.log
+#log4j.appender.resourcemanagerrequestlog.RetainDays=3
+
+#log4j.logger.http.requests.jobhistory=INFO,jobhistoryrequestlog
+#log4j.appender.jobhistoryrequestlog=org.apache.hadoop.http.HttpRequestLogAppender
+#log4j.appender.jobhistoryrequestlog.Filename=${hadoop.log.dir}/jetty-jobhistory-yyyy_mm_dd.log
+#log4j.appender.jobhistoryrequestlog.RetainDays=3
+
+#log4j.logger.http.requests.nodemanager=INFO,nodemanagerrequestlog
+#log4j.appender.nodemanagerrequestlog=org.apache.hadoop.http.HttpRequestLogAppender
+#log4j.appender.nodemanagerrequestlog.Filename=${hadoop.log.dir}/jetty-nodemanager-yyyy_mm_dd.log
+#log4j.appender.nodemanagerrequestlog.RetainDays=3

container/conf/java/hadoop/mapred-env.cmd

@@ -0,0 +1,20 @@
+@echo off
+@rem Licensed to the Apache Software Foundation (ASF) under one or more
+@rem contributor license agreements.  See the NOTICE file distributed with
+@rem this work for additional information regarding copyright ownership.
+@rem The ASF licenses this file to You under the Apache License, Version 2.0
+@rem (the "License"); you may not use this file except in compliance with
+@rem the License.  You may obtain a copy of the License at
+@rem
+@rem     http://www.apache.org/licenses/LICENSE-2.0
+@rem
+@rem Unless required by applicable law or agreed to in writing, software
+@rem distributed under the License is distributed on an "AS IS" BASIS,
+@rem WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+@rem See the License for the specific language governing permissions and
+@rem limitations under the License.
+
+set HADOOP_JOB_HISTORYSERVER_HEAPSIZE=1000
+
+set HADOOP_MAPRED_ROOT_LOGGER=%HADOOP_LOGLEVEL%,RFA
+

container/conf/java/hadoop/mapred-env.sh

@@ -0,0 +1,27 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# export JAVA_HOME=/home/y/libexec/jdk1.6.0/
+
+export HADOOP_JOB_HISTORYSERVER_HEAPSIZE=1000
+
+export HADOOP_MAPRED_ROOT_LOGGER=INFO,RFA
+
+#export HADOOP_JOB_HISTORYSERVER_OPTS=
+#export HADOOP_MAPRED_LOG_DIR="" # Where log files are stored.  $HADOOP_MAPRED_HOME/logs by default.
+#export HADOOP_JHS_LOGGER=INFO,RFA # Hadoop JobSummary logger.
+#export HADOOP_MAPRED_PID_DIR= # The pid files are stored. /tmp by default.
+#export HADOOP_MAPRED_IDENT_STRING= #A string representing this instance of hadoop. $USER by default
+#export HADOOP_MAPRED_NICENESS= #The scheduling priority for daemons. Defaults to 0.

container/conf/java/hadoop/mapred-queues.xml.template

@@ -0,0 +1,92 @@
+<?xml version="1.0"?>
+<!--
+   Licensed to the Apache Software Foundation (ASF) under one or more
+   contributor license agreements.  See the NOTICE file distributed with
+   this work for additional information regarding copyright ownership.
+   The ASF licenses this file to You under the Apache License, Version 2.0
+   (the "License"); you may not use this file except in compliance with
+   the License.  You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+-->
+<!-- This is the template for queue configuration. The format supports nesting of
+     queues within queues - a feature called hierarchical queues. All queues are
+     defined within the 'queues' tag which is the top level element for this
+     XML document. The queue acls configured here for different queues are
+     checked for authorization only if the configuration property
+     mapreduce.cluster.acls.enabled is set to true. -->
+<queues>
+
+  <!-- Configuration for a queue is specified by defining a 'queue' element. -->
+  <queue>
+
+    <!-- Name of a queue. Queue name cannot contain a ':'  -->
+    <name>default</name>
+
+    <!-- properties for a queue, typically used by schedulers,
+    can be defined here -->
+    <properties>
+    </properties>
+
+	<!-- State of the queue. If running, the queue will accept new jobs.
+         If stopped, the queue will not accept new jobs. -->
+    <state>running</state>
+
+    <!-- Specifies the ACLs to check for submitting jobs to this queue.
+         If set to '*', it allows all users to submit jobs to the queue.
+         If set to ' '(i.e. space), no user will be allowed to do this
+         operation. The default value for any queue acl is ' '.
+         For specifying a list of users and groups the format to use is
+         user1,user2 group1,group2
+
+         It is only used if authorization is enabled in Map/Reduce by setting
+         the configuration property mapreduce.cluster.acls.enabled to true.
+
+         Irrespective of this ACL configuration, the user who started the
+         cluster and cluster administrators configured via
+         mapreduce.cluster.administrators can do this operation. -->
+    <acl-submit-job> </acl-submit-job>
+
+    <!-- Specifies the ACLs to check for viewing and modifying jobs in this
+         queue. Modifications include killing jobs, tasks of jobs or changing
+         priorities.
+         If set to '*', it allows all users to view, modify jobs of the queue.
+         If set to ' '(i.e. space), no user will be allowed to do this
+         operation.
+         For specifying a list of users and groups the format to use is
+         user1,user2 group1,group2
+
+         It is only used if authorization is enabled in Map/Reduce by setting
+         the configuration property mapreduce.cluster.acls.enabled to true.
+
+         Irrespective of this ACL configuration, the user who started the
+         cluster  and cluster administrators configured via
+         mapreduce.cluster.administrators can do the above operations on all
+         the jobs in all the queues. The job owner can do all the above
+         operations on his/her job irrespective of this ACL configuration. -->
+    <acl-administer-jobs> </acl-administer-jobs>
+  </queue>
+
+  <!-- Here is a sample of a hierarchical queue configuration
+       where q2 is a child of q1. In this example, q2 is a leaf level
+       queue as it has no queues configured within it. Currently, ACLs
+       and state are only supported for the leaf level queues.
+       Note also the usage of properties for the queue q2.
+  <queue>
+    <name>q1</name>
+    <queue>
+      <name>q2</name>
+      <properties>
+        <property key="capacity" value="20"/>
+        <property key="user-limit" value="30"/>
+      </properties>
+    </queue>
+  </queue>
+ -->
+</queues>

container/conf/java/hadoop/mapred-site.xml

@@ -0,0 +1,25 @@
+<?xml version="1.0"?>
+<configuration>
+    <property>
+        <name>mapreduce.framework.name</name>
+        <value>yarn</value>
+    </property>
+    <property>
+	　　<name>mapreduce.map.memory.mb</name>
+	　　<value>640</value>
+		<description>每个Map任务的物理内存限制</description>
+	</property>
+	<property>
+	　　<name>mapreduce.reduce.memory.mb</name>
+	　　<value>1280</value>
+		<description>每个Reduce任务的物理内存限制</description>
+	</property>
+	<property>
+	　　<name>mapreduce.map.java.opts</name>
+	　　<value>-Xmx512M</value>
+	</property>
+	<property>
+	　　<name>mapreduce.reduce.java.opts</name>
+	　　<value>-Xmx1024M</value>
+	</property>
+</configuration>

container/conf/java/hadoop/mapred-site.xml.template

@@ -0,0 +1,21 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<!--
+  Licensed under the Apache License, Version 2.0 (the "License");
+  you may not use this file except in compliance with the License.
+  You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+  Unless required by applicable law or agreed to in writing, software
+  distributed under the License is distributed on an "AS IS" BASIS,
+  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+  See the License for the specific language governing permissions and
+  limitations under the License. See accompanying LICENSE file.
+-->
+
+<!-- Put site-specific property overrides in this file. -->
+
+<configuration>
+
+</configuration>

container/conf/java/hadoop/masters

@@ -0,0 +1 @@
+data-hadoop

container/conf/java/hadoop/slaves

@@ -0,0 +1,2 @@
+data-hadoop-slave
+data-hadoop-slave1

container/conf/java/hadoop/ssl-client.xml.example

@@ -0,0 +1,80 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<!--
+   Licensed to the Apache Software Foundation (ASF) under one or more
+   contributor license agreements.  See the NOTICE file distributed with
+   this work for additional information regarding copyright ownership.
+   The ASF licenses this file to You under the Apache License, Version 2.0
+   (the "License"); you may not use this file except in compliance with
+   the License.  You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+-->
+<configuration>
+
+<property>
+  <name>ssl.client.truststore.location</name>
+  <value></value>
+  <description>Truststore to be used by clients like distcp. Must be
+  specified.
+  </description>
+</property>
+
+<property>
+  <name>ssl.client.truststore.password</name>
+  <value></value>
+  <description>Optional. Default value is "".
+  </description>
+</property>
+
+<property>
+  <name>ssl.client.truststore.type</name>
+  <value>jks</value>
+  <description>Optional. The keystore file format, default value is "jks".
+  </description>
+</property>
+
+<property>
+  <name>ssl.client.truststore.reload.interval</name>
+  <value>10000</value>
+  <description>Truststore reload check interval, in milliseconds.
+  Default value is 10000 (10 seconds).
+  </description>
+</property>
+
+<property>
+  <name>ssl.client.keystore.location</name>
+  <value></value>
+  <description>Keystore to be used by clients like distcp. Must be
+  specified.
+  </description>
+</property>
+
+<property>
+  <name>ssl.client.keystore.password</name>
+  <value></value>
+  <description>Optional. Default value is "".
+  </description>
+</property>
+
+<property>
+  <name>ssl.client.keystore.keypassword</name>
+  <value></value>
+  <description>Optional. Default value is "".
+  </description>
+</property>
+
+<property>
+  <name>ssl.client.keystore.type</name>
+  <value>jks</value>
+  <description>Optional. The keystore file format, default value is "jks".
+  </description>
+</property>
+
+</configuration>

container/conf/java/hadoop/ssl-server.xml.example

@@ -0,0 +1,78 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<!--
+   Licensed to the Apache Software Foundation (ASF) under one or more
+   contributor license agreements.  See the NOTICE file distributed with
+   this work for additional information regarding copyright ownership.
+   The ASF licenses this file to You under the Apache License, Version 2.0
+   (the "License"); you may not use this file except in compliance with
+   the License.  You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+-->
+<configuration>
+
+<property>
+  <name>ssl.server.truststore.location</name>
+  <value></value>
+  <description>Truststore to be used by NN and DN. Must be specified.
+  </description>
+</property>
+
+<property>
+  <name>ssl.server.truststore.password</name>
+  <value></value>
+  <description>Optional. Default value is "".
+  </description>
+</property>
+
+<property>
+  <name>ssl.server.truststore.type</name>
+  <value>jks</value>
+  <description>Optional. The keystore file format, default value is "jks".
+  </description>
+</property>
+
+<property>
+  <name>ssl.server.truststore.reload.interval</name>
+  <value>10000</value>
+  <description>Truststore reload check interval, in milliseconds.
+  Default value is 10000 (10 seconds).
+  </description>
+</property>
+
+<property>
+  <name>ssl.server.keystore.location</name>
+  <value></value>
+  <description>Keystore to be used by NN and DN. Must be specified.
+  </description>
+</property>
+
+<property>
+  <name>ssl.server.keystore.password</name>
+  <value></value>
+  <description>Must be specified.
+  </description>
+</property>
+
+<property>
+  <name>ssl.server.keystore.keypassword</name>
+  <value></value>
+  <description>Must be specified.
+  </description>
+</property>
+
+<property>
+  <name>ssl.server.keystore.type</name>
+  <value>jks</value>
+  <description>Optional. The keystore file format, default value is "jks".
+  </description>
+</property>
+
+</configuration>

container/conf/java/hadoop/yarn-env.cmd

@@ -0,0 +1,60 @@
+@echo off
+@rem Licensed to the Apache Software Foundation (ASF) under one or more
+@rem contributor license agreements.  See the NOTICE file distributed with
+@rem this work for additional information regarding copyright ownership.
+@rem The ASF licenses this file to You under the Apache License, Version 2.0
+@rem (the "License"); you may not use this file except in compliance with
+@rem the License.  You may obtain a copy of the License at
+@rem
+@rem     http://www.apache.org/licenses/LICENSE-2.0
+@rem
+@rem Unless required by applicable law or agreed to in writing, software
+@rem distributed under the License is distributed on an "AS IS" BASIS,
+@rem WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+@rem See the License for the specific language governing permissions and
+@rem limitations under the License.
+
+@rem User for YARN daemons
+if not defined HADOOP_YARN_USER (
+  set HADOOP_YARN_USER=%yarn%
+)
+
+if not defined YARN_CONF_DIR (
+  set YARN_CONF_DIR=%HADOOP_YARN_HOME%\conf
+)
+
+if defined YARN_HEAPSIZE (
+  @rem echo run with Java heapsize %YARN_HEAPSIZE%
+  set JAVA_HEAP_MAX=-Xmx%YARN_HEAPSIZE%m
+)
+
+if not defined YARN_LOG_DIR (
+  set YARN_LOG_DIR=%HADOOP_YARN_HOME%\logs
+)
+
+if not defined YARN_LOGFILE (
+  set YARN_LOGFILE=yarn.log
+)
+
+@rem default policy file for service-level authorization
+if not defined YARN_POLICYFILE (
+  set YARN_POLICYFILE=hadoop-policy.xml
+)
+
+if not defined YARN_ROOT_LOGGER (
+  set YARN_ROOT_LOGGER=%HADOOP_LOGLEVEL%,console
+)
+
+set YARN_OPTS=%YARN_OPTS% -Dhadoop.log.dir=%YARN_LOG_DIR%
+set YARN_OPTS=%YARN_OPTS% -Dyarn.log.dir=%YARN_LOG_DIR%
+set YARN_OPTS=%YARN_OPTS% -Dhadoop.log.file=%YARN_LOGFILE%
+set YARN_OPTS=%YARN_OPTS% -Dyarn.log.file=%YARN_LOGFILE%
+set YARN_OPTS=%YARN_OPTS% -Dyarn.home.dir=%HADOOP_YARN_HOME%
+set YARN_OPTS=%YARN_OPTS% -Dyarn.id.str=%YARN_IDENT_STRING%
+set YARN_OPTS=%YARN_OPTS% -Dhadoop.home.dir=%HADOOP_YARN_HOME%
+set YARN_OPTS=%YARN_OPTS% -Dhadoop.root.logger=%YARN_ROOT_LOGGER%
+set YARN_OPTS=%YARN_OPTS% -Dyarn.root.logger=%YARN_ROOT_LOGGER%
+if defined JAVA_LIBRARY_PATH (
+  set YARN_OPTS=%YARN_OPTS% -Djava.library.path=%JAVA_LIBRARY_PATH%
+)
+set YARN_OPTS=%YARN_OPTS% -Dyarn.policy.file=%YARN_POLICYFILE%

container/conf/java/hadoop/yarn-env.sh

@@ -0,0 +1,121 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# User for YARN daemons
+export HADOOP_YARN_USER=${HADOOP_YARN_USER:-yarn}
+
+# resolve links - $0 may be a softlink
+export YARN_CONF_DIR="${YARN_CONF_DIR:-$HADOOP_YARN_HOME/conf}"
+
+# some Java parameters
+# export JAVA_HOME=/home/y/libexec/jdk1.6.0/
+if [ "$JAVA_HOME" != "" ]; then
+  #echo "run java in $JAVA_HOME"
+  JAVA_HOME=$JAVA_HOME
+fi
+  
+if [ "$JAVA_HOME" = "" ]; then
+  echo "Error: JAVA_HOME is not set."
+  exit 1
+fi
+
+JAVA=$JAVA_HOME/bin/java
+JAVA_HEAP_MAX=-Xmx1000m 
+
+# For setting YARN specific HEAP sizes please use this
+# Parameter and set appropriately
+# YARN_HEAPSIZE=1000
+
+# check envvars which might override default args
+if [ "$YARN_HEAPSIZE" != "" ]; then
+  JAVA_HEAP_MAX="-Xmx""$YARN_HEAPSIZE""m"
+fi
+
+# Resource Manager specific parameters
+
+# Specify the max Heapsize for the ResourceManager using a numerical value
+# in the scale of MB. For example, to specify an jvm option of -Xmx1000m, set
+# the value to 1000.
+# This value will be overridden by an Xmx setting specified in either YARN_OPTS
+# and/or YARN_RESOURCEMANAGER_OPTS.
+# If not specified, the default value will be picked from either YARN_HEAPMAX
+# or JAVA_HEAP_MAX with YARN_HEAPMAX as the preferred option of the two.
+#export YARN_RESOURCEMANAGER_HEAPSIZE=1000
+
+# Specify the max Heapsize for the timeline server using a numerical value
+# in the scale of MB. For example, to specify an jvm option of -Xmx1000m, set
+# the value to 1000.
+# This value will be overridden by an Xmx setting specified in either YARN_OPTS
+# and/or YARN_TIMELINESERVER_OPTS.
+# If not specified, the default value will be picked from either YARN_HEAPMAX
+# or JAVA_HEAP_MAX with YARN_HEAPMAX as the preferred option of the two.
+#export YARN_TIMELINESERVER_HEAPSIZE=1000
+
+# Specify the JVM options to be used when starting the ResourceManager.
+# These options will be appended to the options specified as YARN_OPTS
+# and therefore may override any similar flags set in YARN_OPTS
+#export YARN_RESOURCEMANAGER_OPTS=
+
+# Node Manager specific parameters
+
+# Specify the max Heapsize for the NodeManager using a numerical value
+# in the scale of MB. For example, to specify an jvm option of -Xmx1000m, set
+# the value to 1000.
+# This value will be overridden by an Xmx setting specified in either YARN_OPTS
+# and/or YARN_NODEMANAGER_OPTS.
+# If not specified, the default value will be picked from either YARN_HEAPMAX
+# or JAVA_HEAP_MAX with YARN_HEAPMAX as the preferred option of the two.
+#export YARN_NODEMANAGER_HEAPSIZE=1000
+
+# Specify the JVM options to be used when starting the NodeManager.
+# These options will be appended to the options specified as YARN_OPTS
+# and therefore may override any similar flags set in YARN_OPTS
+#export YARN_NODEMANAGER_OPTS=
+
+# so that filenames w/ spaces are handled correctly in loops below
+IFS=
+
+
+# default log directory & file
+if [ "$YARN_LOG_DIR" = "" ]; then
+  YARN_LOG_DIR="$HADOOP_YARN_HOME/logs"
+fi
+if [ "$YARN_LOGFILE" = "" ]; then
+  YARN_LOGFILE='yarn.log'
+fi
+
+# default policy file for service-level authorization
+if [ "$YARN_POLICYFILE" = "" ]; then
+  YARN_POLICYFILE="hadoop-policy.xml"
+fi
+
+# restore ordinary behaviour
+unset IFS
+
+
+YARN_OPTS="$YARN_OPTS -Dhadoop.log.dir=$YARN_LOG_DIR"
+YARN_OPTS="$YARN_OPTS -Dyarn.log.dir=$YARN_LOG_DIR"
+YARN_OPTS="$YARN_OPTS -Dhadoop.log.file=$YARN_LOGFILE"
+YARN_OPTS="$YARN_OPTS -Dyarn.log.file=$YARN_LOGFILE"
+YARN_OPTS="$YARN_OPTS -Dyarn.home.dir=$YARN_COMMON_HOME"
+YARN_OPTS="$YARN_OPTS -Dyarn.id.str=$YARN_IDENT_STRING"
+YARN_OPTS="$YARN_OPTS -Dhadoop.root.logger=${YARN_ROOT_LOGGER:-INFO,console}"
+YARN_OPTS="$YARN_OPTS -Dyarn.root.logger=${YARN_ROOT_LOGGER:-INFO,console}"
+if [ "x$JAVA_LIBRARY_PATH" != "x" ]; then
+  YARN_OPTS="$YARN_OPTS -Djava.library.path=$JAVA_LIBRARY_PATH"
+fi  
+YARN_OPTS="$YARN_OPTS -Dyarn.policy.file=$YARN_POLICYFILE"
+
+

container/conf/java/hadoop/yarn-site.xml

@@ -0,0 +1,104 @@
+<?xml version="1.0"?>
+<configuration>
+    <property>  
+       <name>yarn.resourcemanager.hostname</name>  
+       <value>data-hadoop</value>  
+       <description>The hostname of the RM.</description>  
+    </property> 
+    <property>
+        <name>yarn.nodemanager.resource.memory-mb</name>
+        <value>1536</value>
+        <discription>每个节点可用内存,单位MB</discription>
+    </property>
+    <property>
+        <name>yarn.scheduler.minimum-allocation-mb</name>
+        <value>640</value>
+        <discription>单个任务可申请最少内存，默认1024MB</discription>
+    </property>
+    <property>
+        <name>yarn.scheduler.maximum-allocation-mb</name>
+        <value>1536</value>
+        <discription>单个任务可申请最大内存，默认8192MB</discription>
+    </property>
+    <property>
+        <name>yarn.app.mapreduce.am.resource.mb</name>
+        <value>1536</value>
+        <discription>AM能够申请的最大内存，默认值为1536MB</discription>
+    </property>
+    <property>
+        <name>yarn.nodemanager.pmem-check-enabled</name>
+        <value>false</value>
+    </property>
+    <property>
+        <name>yarn.nodemanager.vmem-check-enabled</name>
+        <value>false</value>
+    </property>
+    <!--property>
+        <name>yarn.resourcemanager.scheduler.class</name>
+        <value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler</value>
+    </property>
+    <property>
+        <name>yarn.resourcemanager.address</name>
+        <value>8032</value>
+    </property>
+    <property>
+        <name>yarn.resourcemanager.scheduler.address</name>
+        <value>8030</value>
+    </property>
+    <property>
+        <name>yarn.resourcemanager.resource-tracker.address</name>
+        <value>8031</value>
+    </property>
+    <property>
+        <name>yarn.resourcemanager.admin.address</name>
+        <value>8033</value>
+    </property>
+    <property>
+        <name>yarn.resourcemanager.webapp.address</name>
+        <value>8088</value>
+    </property>
+    <property>
+        <name>yarn.nodemanager.localizer.address</name>
+        <value>8040</value>
+    </property>
+    <property>
+        <name>yarn.nodemanager.address</name>
+        <value>8041</value>
+    </property>
+    <property>
+        <name>yarn.nodemanager.webapp.address</name>
+        <value>8042</value>
+    </property>
+    <property>
+        <name>mapreduce.jobhistory.address</name>
+        <value>10020</value>
+    </property>
+    <property>
+        <name>mapreduce.jobhistory.webapp.address</name>
+        <value>19888</value>
+    </property>
+    <property>
+        <name>yarn.nodemanager.aux-services</name>
+        <value>mapreduce_shuffle</value>
+    </property>
+    <property>
+        <name>yarn.nodemanager.aux-services.mapreduce_shuffle.class</name>
+        <value>org.apache.hadoop.mapred.ShuffleHandler</value>
+    </property>
+    <property>
+        <name>yarn.resourcemanager.scheduler.class</name>
+        <value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler</value>
+    </property>
+    <property>
+        <name>yarn.scheduler.fair.preemption</name>
+        <value>true</value>
+    </property>
+    <property>
+        <name>yarn.scheduler.fair.preemption.cluster-utilization-threshold</name>
+        <value>1.0</value>
+    </property-->
+    <property>
+        <name>yarn.resourcemanager.am.max-attempts</name>
+        <value>10000</value>
+    </property>
+</configuration>

container/conf/java/hbase/hadoop-metrics2-hbase.properties

@@ -0,0 +1,44 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# syntax: [prefix].[source|sink].[instance].[options]
+# See javadoc of package-info.java for org.apache.hadoop.metrics2 for details
+
+*.sink.file*.class=org.apache.hadoop.metrics2.sink.FileSink
+# default sampling period
+*.period=10
+
+# Below are some examples of sinks that could be used
+# to monitor different hbase daemons.
+
+# hbase.sink.file-all.class=org.apache.hadoop.metrics2.sink.FileSink
+# hbase.sink.file-all.filename=all.metrics
+
+# hbase.sink.file0.class=org.apache.hadoop.metrics2.sink.FileSink
+# hbase.sink.file0.context=hmaster
+# hbase.sink.file0.filename=master.metrics
+
+# hbase.sink.file1.class=org.apache.hadoop.metrics2.sink.FileSink
+# hbase.sink.file1.context=thrift-one
+# hbase.sink.file1.filename=thrift-one.metrics
+
+# hbase.sink.file2.class=org.apache.hadoop.metrics2.sink.FileSink
+# hbase.sink.file2.context=thrift-two
+# hbase.sink.file2.filename=thrift-one.metrics
+
+# hbase.sink.file3.class=org.apache.hadoop.metrics2.sink.FileSink
+# hbase.sink.file3.context=rest
+# hbase.sink.file3.filename=rest.metrics

container/conf/java/hbase/hbase-env.cmd

@@ -0,0 +1,87 @@
+@rem/**
+@rem * Licensed to the Apache Software Foundation (ASF) under one
+@rem * or more contributor license agreements.  See the NOTICE file
+@rem * distributed with this work for additional information
+@rem * regarding copyright ownership.  The ASF licenses this file
+@rem * to you under the Apache License, Version 2.0 (the
+@rem * "License"); you may not use this file except in compliance
+@rem * with the License.  You may obtain a copy of the License at
+@rem *
+@rem *     http://www.apache.org/licenses/LICENSE-2.0
+@rem *
+@rem * Unless required by applicable law or agreed to in writing, software
+@rem * distributed under the License is distributed on an "AS IS" BASIS,
+@rem * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+@rem * See the License for the specific language governing permissions and
+@rem * limitations under the License.
+@rem */
+
+@rem Set environment variables here.
+
+@rem The java implementation to use.  Java 1.7+ required.
+@rem set JAVA_HOME=c:\apps\java
+
+@rem Extra Java CLASSPATH elements.  Optional.
+@rem set HBASE_CLASSPATH=
+
+@rem The maximum amount of heap to use. Default is left to JVM default.
+@rem set HBASE_HEAPSIZE=1000
+
+@rem Uncomment below if you intend to use off heap cache. For example, to allocate 8G of 
+@rem offheap, set the value to "8G".
+@rem set HBASE_OFFHEAPSIZE=1000
+
+@rem For example, to allocate 8G of offheap, to 8G:
+@rem etHBASE_OFFHEAPSIZE=8G
+
+@rem Extra Java runtime options.
+@rem Below are what we set by default.  May only work with SUN JVM.
+@rem For more on why as well as other possible settings,
+@rem see http://wiki.apache.org/hadoop/PerformanceTuning
+@rem JDK6 on Windows has a known bug for IPv6, use preferIPv4Stack unless JDK7.
+@rem @rem See TestIPv6NIOServerSocketChannel.
+set HBASE_OPTS="-XX:+UseConcMarkSweepGC" "-Djava.net.preferIPv4Stack=true"
+
+@rem Configure PermSize. Only needed in JDK7. You can safely remove it for JDK8+
+set HBASE_MASTER_OPTS=%HBASE_MASTER_OPTS% "-XX:PermSize=128m" "-XX:MaxPermSize=128m"
+set HBASE_REGIONSERVER_OPTS=%HBASE_REGIONSERVER_OPTS% "-XX:PermSize=128m" "-XX:MaxPermSize=128m"
+
+@rem Uncomment below to enable java garbage collection logging for the server-side processes
+@rem this enables basic gc logging for the server processes to the .out file
+@rem set SERVER_GC_OPTS="-verbose:gc" "-XX:+PrintGCDetails" "-XX:+PrintGCDateStamps" %HBASE_GC_OPTS%
+
+@rem this enables gc logging using automatic GC log rolling. Only applies to jdk 1.6.0_34+ and 1.7.0_2+. Either use this set of options or the one above
+@rem set SERVER_GC_OPTS="-verbose:gc" "-XX:+PrintGCDetails" "-XX:+PrintGCDateStamps" "-XX:+UseGCLogFileRotation" "-XX:NumberOfGCLogFiles=1" "-XX:GCLogFileSize=512M" %HBASE_GC_OPTS%
+
+@rem Uncomment below to enable java garbage collection logging for the client processes in the .out file.
+@rem set CLIENT_GC_OPTS="-verbose:gc" "-XX:+PrintGCDetails" "-XX:+PrintGCDateStamps" %HBASE_GC_OPTS%
+
+@rem Uncomment below (along with above GC logging) to put GC information in its own logfile (will set HBASE_GC_OPTS)
+@rem set HBASE_USE_GC_LOGFILE=true
+
+@rem Uncomment and adjust to enable JMX exporting
+@rem See jmxremote.password and jmxremote.access in $JRE_HOME/lib/management to configure remote password access.
+@rem More details at: http://java.sun.com/javase/6/docs/technotes/guides/management/agent.html
+@rem
+@rem set HBASE_JMX_BASE="-Dcom.sun.management.jmxremote.ssl=false" "-Dcom.sun.management.jmxremote.authenticate=false"
+@rem set HBASE_MASTER_OPTS=%HBASE_JMX_BASE% "-Dcom.sun.management.jmxremote.port=10101"
+@rem set HBASE_REGIONSERVER_OPTS=%HBASE_JMX_BASE% "-Dcom.sun.management.jmxremote.port=10102"
+@rem set HBASE_THRIFT_OPTS=%HBASE_JMX_BASE% "-Dcom.sun.management.jmxremote.port=10103"
+@rem set HBASE_ZOOKEEPER_OPTS=%HBASE_JMX_BASE% -Dcom.sun.management.jmxremote.port=10104"
+
+@rem File naming hosts on which HRegionServers will run.  $HBASE_HOME/conf/regionservers by default.
+@rem set HBASE_REGIONSERVERS=%HBASE_HOME%\conf\regionservers
+
+@rem Where log files are stored.  $HBASE_HOME/logs by default.
+@rem set HBASE_LOG_DIR=%HBASE_HOME%\logs
+
+@rem A string representing this instance of hbase. $USER by default.
+@rem set HBASE_IDENT_STRING=%USERNAME%
+
+@rem Seconds to sleep between slave commands.  Unset by default.  This
+@rem can be useful in large clusters, where, e.g., slave rsyncs can
+@rem otherwise arrive faster than the master can service them.
+@rem set HBASE_SLAVE_SLEEP=0.1
+
+@rem Tell HBase whether it should manage it's own instance of Zookeeper or not.
+@rem set HBASE_MANAGES_ZK=true

container/conf/java/hbase/hbase-env.sh

@@ -0,0 +1,137 @@
+#
+#/**
+# * Licensed to the Apache Software Foundation (ASF) under one
+# * or more contributor license agreements.  See the NOTICE file
+# * distributed with this work for additional information
+# * regarding copyright ownership.  The ASF licenses this file
+# * to you under the Apache License, Version 2.0 (the
+# * "License"); you may not use this file except in compliance
+# * with the License.  You may obtain a copy of the License at
+# *
+# *     http://www.apache.org/licenses/LICENSE-2.0
+# *
+# * Unless required by applicable law or agreed to in writing, software
+# * distributed under the License is distributed on an "AS IS" BASIS,
+# * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# * See the License for the specific language governing permissions and
+# * limitations under the License.
+# */
+
+# Set environment variables here.
+
+# This script sets variables multiple times over the course of starting an hbase process,
+# so try to keep things idempotent unless you want to take an even deeper look
+# into the startup scripts (bin/hbase, etc.)
+
+# The java implementation to use.  Java 1.7+ required.
+export JAVA_HOME=/share/lib/jdk
+
+# Extra Java CLASSPATH elements.  Optional.
+# export HBASE_CLASSPATH=
+
+# The maximum amount of heap to use. Default is left to JVM default.
+# export HBASE_HEAPSIZE=1G
+
+# Uncomment below if you intend to use off heap cache. For example, to allocate 8G of 
+# offheap, set the value to "8G".
+# export HBASE_OFFHEAPSIZE=1G
+
+# Extra Java runtime options.
+# Below are what we set by default.  May only work with SUN JVM.
+# For more on why as well as other possible settings,
+# see http://wiki.apache.org/hadoop/PerformanceTuning
+export HBASE_OPTS="-XX:+UseConcMarkSweepGC"
+
+# Configure PermSize. Only needed in JDK7. You can safely remove it for JDK8+
+#export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS -XX:PermSize=128m -XX:MaxPermSize=128m"
+#export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS -XX:PermSize=128m -XX:MaxPermSize=128m"
+
+# Uncomment one of the below three options to enable java garbage collection logging for the server-side processes.
+
+# This enables basic gc logging to the .out file.
+# export SERVER_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps"
+
+# This enables basic gc logging to its own file.
+# If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR .
+# export SERVER_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH>"
+
+# This enables basic GC logging to its own file with automatic log rolling. Only applies to jdk 1.6.0_34+ and 1.7.0_2+.
+# If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR .
+# export SERVER_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH> -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=1 -XX:GCLogFileSize=512M"
+
+# Uncomment one of the below three options to enable java garbage collection logging for the client processes.
+
+# This enables basic gc logging to the .out file.
+# export CLIENT_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps"
+
+# This enables basic gc logging to its own file.
+# If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR .
+# export CLIENT_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH>"
+
+# This enables basic GC logging to its own file with automatic log rolling. Only applies to jdk 1.6.0_34+ and 1.7.0_2+.
+# If FILE-PATH is not replaced, the log file(.gc) would still be generated in the HBASE_LOG_DIR .
+# export CLIENT_GC_OPTS="-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -Xloggc:<FILE-PATH> -XX:+UseGCLogFileRotation -XX:NumberOfGCLogFiles=1 -XX:GCLogFileSize=512M"
+
+# See the package documentation for org.apache.hadoop.hbase.io.hfile for other configurations
+# needed setting up off-heap block caching. 
+
+# Uncomment and adjust to enable JMX exporting
+# See jmxremote.password and jmxremote.access in $JRE_HOME/lib/management to configure remote password access.
+# More details at: http://java.sun.com/javase/6/docs/technotes/guides/management/agent.html
+# NOTE: HBase provides an alternative JMX implementation to fix the random ports issue, please see JMX
+# section in HBase Reference Guide for instructions.
+
+# export HBASE_JMX_BASE="-Dcom.sun.management.jmxremote.ssl=false -Dcom.sun.management.jmxremote.authenticate=false"
+# export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10101"
+# export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10102"
+# export HBASE_THRIFT_OPTS="$HBASE_THRIFT_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10103"
+# export HBASE_ZOOKEEPER_OPTS="$HBASE_ZOOKEEPER_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10104"
+# export HBASE_REST_OPTS="$HBASE_REST_OPTS $HBASE_JMX_BASE -Dcom.sun.management.jmxremote.port=10105"
+
+# File naming hosts on which HRegionServers will run.  $HBASE_HOME/conf/regionservers by default.
+# export HBASE_REGIONSERVERS=${HBASE_HOME}/conf/regionservers
+
+# Uncomment and adjust to keep all the Region Server pages mapped to be memory resident
+#HBASE_REGIONSERVER_MLOCK=true
+#HBASE_REGIONSERVER_UID="hbase"
+
+# File naming hosts on which backup HMaster will run.  $HBASE_HOME/conf/backup-masters by default.
+# export HBASE_BACKUP_MASTERS=${HBASE_HOME}/conf/backup-masters
+
+# Extra ssh options.  Empty by default.
+# export HBASE_SSH_OPTS="-o ConnectTimeout=1 -o SendEnv=HBASE_CONF_DIR"
+
+# Where log files are stored.  $HBASE_HOME/logs by default.
+# export HBASE_LOG_DIR=${HBASE_HOME}/logs
+
+# Enable remote JDWP debugging of major HBase processes. Meant for Core Developers 
+# export HBASE_MASTER_OPTS="$HBASE_MASTER_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8070"
+# export HBASE_REGIONSERVER_OPTS="$HBASE_REGIONSERVER_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8071"
+# export HBASE_THRIFT_OPTS="$HBASE_THRIFT_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8072"
+# export HBASE_ZOOKEEPER_OPTS="$HBASE_ZOOKEEPER_OPTS -Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=8073"
+
+# A string representing this instance of hbase. $USER by default.
+# export HBASE_IDENT_STRING=$USER
+
+# The scheduling priority for daemon processes.  See 'man nice'.
+# export HBASE_NICENESS=10
+
+# The directory where pid files are stored. /tmp by default.
+# export HBASE_PID_DIR=/var/hadoop/pids
+
+# Seconds to sleep between slave commands.  Unset by default.  This
+# can be useful in large clusters, where, e.g., slave rsyncs can
+# otherwise arrive faster than the master can service them.
+# export HBASE_SLAVE_SLEEP=0.1
+
+# Tell HBase whether it should manage it's own instance of Zookeeper or not.
+# export HBASE_MANAGES_ZK=true
+
+# The default log rolling policy is RFA, where the log file is rolled as per the size defined for the 
+# RFA appender. Please refer to the log4j.properties file to see more details on this appender.
+# In case one needs to do log rolling on a date change, one should set the environment property
+# HBASE_ROOT_LOGGER to "<DESIRED_LOG LEVEL>,DRFA".
+# For example:
+# HBASE_ROOT_LOGGER=INFO,DRFA
+# The reason for changing default to RFA is to avoid the boundary case of filling out disk space as 
+# DRFA doesn't put any cap on the log size. Please refer to HBase-5655 for more context.

container/conf/java/hbase/hbase-policy.xml

@@ -0,0 +1,53 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<!--
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+-->
+
+<configuration>
+  <property>
+    <name>security.client.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for ClientProtocol and AdminProtocol implementations (ie. 
+    clients talking to HRegionServers)
+    The ACL is a comma-separated list of user and group names. The user and 
+    group list is separated by a blank. For e.g. "alice,bob users,wheel". 
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.admin.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for HMasterInterface protocol implementation (ie. 
+    clients talking to HMaster for admin operations).
+    The ACL is a comma-separated list of user and group names. The user and 
+    group list is separated by a blank. For e.g. "alice,bob users,wheel". 
+    A special value of "*" means all users are allowed.</description>
+  </property>
+
+  <property>
+    <name>security.masterregion.protocol.acl</name>
+    <value>*</value>
+    <description>ACL for HMasterRegionInterface protocol implementations
+    (for HRegionServers communicating with HMaster)
+    The ACL is a comma-separated list of user and group names. The user and 
+    group list is separated by a blank. For e.g. "alice,bob users,wheel". 
+    A special value of "*" means all users are allowed.</description>
+  </property>
+</configuration>

container/conf/java/hbase/hbase-site.xml

@@ -0,0 +1,49 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
+<!--
+/**
+ *
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+-->
+<configuration>
+	<property>
+        <name>hbase.rootdir</name>
+        <value>hdfs://data-hadoop:9000/hbase</value>
+    </property>
+    <property>
+        <name>hbase.cluster.distributed</name>
+        <value>true</value>
+    </property>
+    <property>
+        <name>hbase.zookeeper.quorum</name>
+        <value>data-zookeeper,data-zookeeper1,data-zookeeper2</value>
+    </property>
+    <property>
+        <name>hbase.master.maxclockskew</name>
+        <value>180000</value>
+        <description>Time difference of regionserver from master</description>
+    </property>
+     <property>
+        <name>hbase.master.info.port</name>
+        <value>60010</value>
+    </property>
+    <property>
+        <name>hbase.regionserver.info.port</name>
+        <value>-1</value>
+    </property>
+</configuration>

container/conf/java/hbase/log4j.properties

@@ -0,0 +1,115 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Define some default values that can be overridden by system properties
+hbase.root.logger=INFO,console
+hbase.security.logger=INFO,console
+hbase.log.dir=.
+hbase.log.file=hbase.log
+
+# Define the root logger to the system property "hbase.root.logger".
+log4j.rootLogger=${hbase.root.logger}
+
+# Logging Threshold
+log4j.threshold=ALL
+
+#
+# Daily Rolling File Appender
+#
+log4j.appender.DRFA=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.DRFA.File=${hbase.log.dir}/${hbase.log.file}
+
+# Rollver at midnight
+log4j.appender.DRFA.DatePattern=.yyyy-MM-dd
+
+# 30-day backup
+#log4j.appender.DRFA.MaxBackupIndex=30
+log4j.appender.DRFA.layout=org.apache.log4j.PatternLayout
+
+# Pattern format: Date LogLevel LoggerName LogMessage
+log4j.appender.DRFA.layout.ConversionPattern=%d{ISO8601} %-5p [%t] %c{2}: %m%n
+
+# Rolling File Appender properties
+hbase.log.maxfilesize=256MB
+hbase.log.maxbackupindex=20
+
+# Rolling File Appender
+log4j.appender.RFA=org.apache.log4j.RollingFileAppender
+log4j.appender.RFA.File=${hbase.log.dir}/${hbase.log.file}
+
+log4j.appender.RFA.MaxFileSize=${hbase.log.maxfilesize}
+log4j.appender.RFA.MaxBackupIndex=${hbase.log.maxbackupindex}
+
+log4j.appender.RFA.layout=org.apache.log4j.PatternLayout
+log4j.appender.RFA.layout.ConversionPattern=%d{ISO8601} %-5p [%t] %c{2}: %m%n
+
+#
+# Security audit appender
+#
+hbase.security.log.file=SecurityAuth.audit
+hbase.security.log.maxfilesize=256MB
+hbase.security.log.maxbackupindex=20
+log4j.appender.RFAS=org.apache.log4j.RollingFileAppender
+log4j.appender.RFAS.File=${hbase.log.dir}/${hbase.security.log.file}
+log4j.appender.RFAS.MaxFileSize=${hbase.security.log.maxfilesize}
+log4j.appender.RFAS.MaxBackupIndex=${hbase.security.log.maxbackupindex}
+log4j.appender.RFAS.layout=org.apache.log4j.PatternLayout
+log4j.appender.RFAS.layout.ConversionPattern=%d{ISO8601} %p %c: %m%n
+log4j.category.SecurityLogger=${hbase.security.logger}
+log4j.additivity.SecurityLogger=false
+#log4j.logger.SecurityLogger.org.apache.hadoop.hbase.security.access.AccessController=TRACE
+#log4j.logger.SecurityLogger.org.apache.hadoop.hbase.security.visibility.VisibilityController=TRACE
+
+#
+# Null Appender
+#
+log4j.appender.NullAppender=org.apache.log4j.varia.NullAppender
+
+#
+# console
+# Add "console" to rootlogger above if you want to use this 
+#
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.err
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d{ISO8601} %-5p [%t] %c{2}: %m%n
+
+# Custom Logging levels
+
+log4j.logger.org.apache.zookeeper=INFO
+#log4j.logger.org.apache.hadoop.fs.FSNamesystem=DEBUG
+log4j.logger.org.apache.hadoop.hbase=INFO
+# Make these two classes INFO-level. Make them DEBUG to see more zk debug.
+log4j.logger.org.apache.hadoop.hbase.zookeeper.ZKUtil=INFO
+log4j.logger.org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher=INFO
+#log4j.logger.org.apache.hadoop.dfs=DEBUG
+# Set this class to log INFO only otherwise its OTT
+# Enable this to get detailed connection error/retry logging.
+# log4j.logger.org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation=TRACE
+
+
+# Uncomment this line to enable tracing on _every_ RPC call (this can be a lot of output)
+#log4j.logger.org.apache.hadoop.ipc.HBaseServer.trace=DEBUG
+
+# Uncomment the below if you want to remove logging of client region caching'
+# and scan of hbase:meta messages
+# log4j.logger.org.apache.hadoop.hbase.client.HConnectionManager$HConnectionImplementation=INFO
+# log4j.logger.org.apache.hadoop.hbase.client.MetaScanner=INFO
+
+# Prevent metrics subsystem start/stop messages (HBASE-17722)
+log4j.logger.org.apache.hadoop.metrics2.impl.MetricsConfig=WARN
+log4j.logger.org.apache.hadoop.metrics2.impl.MetricsSinkAdapter=WARN
+log4j.logger.org.apache.hadoop.metrics2.impl.MetricsSystemImpl=WARN

container/conf/java/hbase/regionservers

@@ -0,0 +1,2 @@
+data-hbase-slave
+data-hbase-slave1

container/conf/java/hbase/zoo.cfg

@@ -0,0 +1,31 @@
+# The number of milliseconds of each tick
+tickTime=2000
+# The number of ticks that the initial 
+# synchronization phase can take
+initLimit=10
+# The number of ticks that can pass between 
+# sending a request and getting an acknowledgement
+syncLimit=5
+# the directory where the snapshot is stored.
+# do not use /tmp for storage, /tmp here is just 
+# example sakes.
+dataDir=/root/zookeeper/tmp
+# the port at which the clients will connect
+clientPort=2181
+# the maximum number of client connections.
+# increase this if you need to handle more clients
+#maxClientCnxns=60
+#
+# Be sure to read the maintenance section of the 
+# administrator guide before turning on autopurge.
+#
+# http://zookeeper.apache.org/doc/current/zookeeperAdmin.html#sc_maintenance
+#
+# The number of snapshots to retain in dataDir
+#autopurge.snapRetainCount=3
+# Purge task interval in hours
+# Set to "0" to disable auto purge feature
+#autopurge.purgeInterval=1
+server.1=data-zookeeper:2888:3888:participant
+server.2=data-zookeeper1:2888:3888:participant
+server.3=data-zookeeper2:2888:3888:participant

container/conf/java/hive/beeline-log4j2.properties

@@ -0,0 +1,45 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+status = INFO
+name = BeelineLog4j2
+packages = org.apache.hadoop.hive.ql.log
+
+# list of properties
+property.hive.log.level = WARN
+property.hive.root.logger = console
+
+# list of all appenders
+appenders = console
+
+# console appender
+appender.console.type = Console
+appender.console.name = console
+appender.console.target = SYSTEM_ERR
+appender.console.layout.type = PatternLayout
+appender.console.layout.pattern = %d{yy/MM/dd HH:mm:ss} [%t]: %p %c{2}: %m%n
+
+# list of all loggers
+loggers = HiveConnection
+
+# HiveConnection logs useful info for dynamic service discovery
+logger.HiveConnection.name = org.apache.hive.jdbc.HiveConnection
+logger.HiveConnection.level = INFO
+
+# root logger
+rootLogger.level = ${sys:hive.log.level}
+rootLogger.appenderRefs = root
+rootLogger.appenderRef.root.ref = ${sys:hive.root.logger}

container/conf/java/hive/hive-default.xml

@@ -0,0 +1,5349 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?><!--
+   Licensed to the Apache Software Foundation (ASF) under one or more
+   contributor license agreements.  See the NOTICE file distributed with
+   this work for additional information regarding copyright ownership.
+   The ASF licenses this file to You under the Apache License, Version 2.0
+   (the "License"); you may not use this file except in compliance with
+   the License.  You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+--><configuration>
+  <!-- WARNING!!! This file is auto generated for documentation purposes ONLY! -->
+  <!-- WARNING!!! Any changes you make to this file will be ignored by Hive.   -->
+  <!-- WARNING!!! You must make your changes in hive-site.xml instead.         -->
+  <!-- Hive Execution Parameters -->
+  <property>
+    <name>hive.exec.script.wrapper</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.plan</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.stagingdir</name>
+    <value>.hive-staging</value>
+    <description>Directory name that will be created inside table locations in order to support HDFS encryption. This is replaces ${hive.exec.scratchdir} for query results with the exception of read-only tables. In all cases ${hive.exec.scratchdir} is still used for other temporary files, such as job plans.</description>
+  </property>
+  <property>
+    <name>hive.exec.scratchdir</name>
+    <value>/tmp/hive</value>
+    <description>HDFS root scratch dir for Hive jobs which gets created with write all (733) permission. For each connecting user, an HDFS scratch dir: ${hive.exec.scratchdir}/&lt;username&gt; is created, with ${hive.scratch.dir.permission}.</description>
+  </property>
+  <property>
+    <name>hive.exec.local.scratchdir</name>
+    <value>${system:java.io.tmpdir}/${system:user.name}</value>
+    <description>Local scratch space for Hive jobs</description>
+  </property>
+  <property>
+    <name>hive.downloaded.resources.dir</name>
+    <value>${system:java.io.tmpdir}/${hive.session.id}_resources</value>
+    <description>Temporary local directory for added resources in the remote file system.</description>
+  </property>
+  <property>
+    <name>hive.scratch.dir.permission</name>
+    <value>700</value>
+    <description>The permission for the user specific scratch directories that get created.</description>
+  </property>
+  <property>
+    <name>hive.exec.submitviachild</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.submit.local.task.via.child</name>
+    <value>true</value>
+    <description>
+      Determines whether local tasks (typically mapjoin hashtable generation phase) runs in 
+      separate JVM (true recommended) or not. 
+      Avoids the overhead of spawning new JVM, but can lead to out-of-memory issues.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.script.maxerrsize</name>
+    <value>100000</value>
+    <description>
+      Maximum number of bytes a script is allowed to emit to standard error (per map-reduce task). 
+      This prevents runaway scripts from filling logs partitions to capacity
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.script.allow.partial.consumption</name>
+    <value>false</value>
+    <description>
+      When enabled, this option allows a user script to exit successfully without consuming 
+      all the data from the standard input.
+    </description>
+  </property>
+  <property>
+    <name>stream.stderr.reporter.prefix</name>
+    <value>reporter:</value>
+    <description>Streaming jobs that log to standard error with this prefix can log counter or status information.</description>
+  </property>
+  <property>
+    <name>stream.stderr.reporter.enabled</name>
+    <value>true</value>
+    <description>Enable consumption of status and counter messages for streaming jobs.</description>
+  </property>
+  <property>
+    <name>hive.exec.compress.output</name>
+    <value>false</value>
+    <description>
+      This controls whether the final outputs of a query (to a local/HDFS file or a Hive table) is compressed. 
+      The compression codec and other options are determined from Hadoop config variables mapred.output.compress*
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.compress.intermediate</name>
+    <value>false</value>
+    <description>
+      This controls whether intermediate files produced by Hive between multiple map-reduce jobs are compressed. 
+      The compression codec and other options are determined from Hadoop config variables mapred.output.compress*
+    </description>
+  </property>
+  <property>
+    <name>hive.intermediate.compression.codec</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.intermediate.compression.type</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.reducers.bytes.per.reducer</name>
+    <value>256000000</value>
+    <description>size per reducer.The default is 256Mb, i.e if the input size is 1G, it will use 4 reducers.</description>
+  </property>
+  <property>
+    <name>hive.exec.reducers.max</name>
+    <value>1009</value>
+    <description>
+      max number of reducers will be used. If the one specified in the configuration parameter mapred.reduce.tasks is
+      negative, Hive will use this one as the max number of reducers when automatically determine number of reducers.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.pre.hooks</name>
+    <value/>
+    <description>
+      Comma-separated list of pre-execution hooks to be invoked for each statement. 
+      A pre-execution hook is specified as the name of a Java class which implements the 
+      org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext interface.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.post.hooks</name>
+    <value/>
+    <description>
+      Comma-separated list of post-execution hooks to be invoked for each statement. 
+      A post-execution hook is specified as the name of a Java class which implements the 
+      org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext interface.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.failure.hooks</name>
+    <value/>
+    <description>
+      Comma-separated list of on-failure hooks to be invoked for each statement. 
+      An on-failure hook is specified as the name of Java class which implements the 
+      org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext interface.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.query.redactor.hooks</name>
+    <value/>
+    <description>
+      Comma-separated list of hooks to be invoked for each query which can 
+      tranform the query before it's placed in the job.xml file. Must be a Java class which 
+      extends from the org.apache.hadoop.hive.ql.hooks.Redactor abstract class.
+    </description>
+  </property>
+  <property>
+    <name>hive.client.stats.publishers</name>
+    <value/>
+    <description>
+      Comma-separated list of statistics publishers to be invoked on counters on each job. 
+      A client stats publisher is specified as the name of a Java class which implements the 
+      org.apache.hadoop.hive.ql.stats.ClientStatsPublisher interface.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.parallel</name>
+    <value>false</value>
+    <description>Whether to execute jobs in parallel</description>
+  </property>
+  <property>
+    <name>hive.exec.parallel.thread.number</name>
+    <value>8</value>
+    <description>How many jobs at most can be executed in parallel</description>
+  </property>
+  <property>
+    <name>hive.mapred.reduce.tasks.speculative.execution</name>
+    <value>true</value>
+    <description>Whether speculative execution for reducers should be turned on. </description>
+  </property>
+  <property>
+    <name>hive.exec.counters.pull.interval</name>
+    <value>1000</value>
+    <description>
+      The interval with which to poll the JobTracker for the counters the running job. 
+      The smaller it is the more load there will be on the jobtracker, the higher it is the less granular the caught will be.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.dynamic.partition</name>
+    <value>true</value>
+    <description>Whether or not to allow dynamic partitions in DML/DDL.</description>
+  </property>
+  <property>
+    <name>hive.exec.dynamic.partition.mode</name>
+    <value>strict</value>
+    <description>
+      In strict mode, the user must specify at least one static partition
+      in case the user accidentally overwrites all partitions.
+      In nonstrict mode all partitions are allowed to be dynamic.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.max.dynamic.partitions</name>
+    <value>1000</value>
+    <description>Maximum number of dynamic partitions allowed to be created in total.</description>
+  </property>
+  <property>
+    <name>hive.exec.max.dynamic.partitions.pernode</name>
+    <value>100</value>
+    <description>Maximum number of dynamic partitions allowed to be created in each mapper/reducer node.</description>
+  </property>
+  <property>
+    <name>hive.exec.max.created.files</name>
+    <value>100000</value>
+    <description>Maximum number of HDFS files created by all mappers/reducers in a MapReduce job.</description>
+  </property>
+  <property>
+    <name>hive.exec.default.partition.name</name>
+    <value>__HIVE_DEFAULT_PARTITION__</value>
+    <description>
+      The default partition name in case the dynamic partition column value is null/empty string or any other values that cannot be escaped. 
+      This value must not contain any special character used in HDFS URI (e.g., ':', '%', '/' etc). 
+      The user has to be aware that the dynamic partition value should not contain this value to avoid confusions.
+    </description>
+  </property>
+  <property>
+    <name>hive.lockmgr.zookeeper.default.partition.name</name>
+    <value>__HIVE_DEFAULT_ZOOKEEPER_PARTITION__</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.show.job.failure.debug.info</name>
+    <value>true</value>
+    <description>
+      If a job fails, whether to provide a link in the CLI to the task with the
+      most failures, along with debugging hints if applicable.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.job.debug.capture.stacktraces</name>
+    <value>true</value>
+    <description>
+      Whether or not stack traces parsed from the task logs of a sampled failed task 
+      for each failed job should be stored in the SessionState
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.job.debug.timeout</name>
+    <value>30000</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.tasklog.debug.timeout</name>
+    <value>20000</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.output.file.extension</name>
+    <value/>
+    <description>
+      String used as a file extension for output files. 
+      If not set, defaults to the codec extension for text files (e.g. ".gz"), or no extension otherwise.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.mode.local.auto</name>
+    <value>false</value>
+    <description>Let Hive determine whether to run in local mode automatically</description>
+  </property>
+  <property>
+    <name>hive.exec.mode.local.auto.inputbytes.max</name>
+    <value>134217728</value>
+    <description>When hive.exec.mode.local.auto is true, input bytes should less than this for local mode.</description>
+  </property>
+  <property>
+    <name>hive.exec.mode.local.auto.input.files.max</name>
+    <value>4</value>
+    <description>When hive.exec.mode.local.auto is true, the number of tasks should less than this for local mode.</description>
+  </property>
+  <property>
+    <name>hive.exec.drop.ignorenonexistent</name>
+    <value>true</value>
+    <description>Do not report an error if DROP TABLE/VIEW/Index/Function specifies a non-existent table/view/index/function</description>
+  </property>
+  <property>
+    <name>hive.ignore.mapjoin.hint</name>
+    <value>true</value>
+    <description>Ignore the mapjoin hint</description>
+  </property>
+  <property>
+    <name>hive.file.max.footer</name>
+    <value>100</value>
+    <description>maximum number of lines for footer user can define for a table file</description>
+  </property>
+  <property>
+    <name>hive.resultset.use.unique.column.names</name>
+    <value>true</value>
+    <description>
+      Make column names unique in the result set by qualifying column names with table alias if needed.
+      Table alias will be added to column names for queries of type "select *" or 
+      if query explicitly uses table alias "select r1.x..".
+    </description>
+  </property>
+  <property>
+    <name>fs.har.impl</name>
+    <value>org.apache.hadoop.hive.shims.HiveHarFileSystem</value>
+    <description>The implementation for accessing Hadoop Archives. Note that this won't be applicable to Hadoop versions less than 0.20</description>
+  </property>
+  <property>
+    <name>hive.metastore.warehouse.dir</name>
+    <value>/user/hive/warehouse</value>
+    <description>location of default database for the warehouse</description>
+  </property>
+  <property>
+    <name>hive.metastore.uris</name>
+    <value/>
+    <description>Thrift URI for the remote metastore. Used by metastore client to connect to remote metastore.</description>
+  </property>
+  <property>
+    <name>hive.metastore.fastpath</name>
+    <value>false</value>
+    <description>Used to avoid all of the proxies and object copies in the metastore.  Note, if this is set, you MUST use a local metastore (hive.metastore.uris must be empty) otherwise undefined and most likely undesired behavior will result</description>
+  </property>
+  <property>
+    <name>hive.metastore.fshandler.threads</name>
+    <value>20</value>
+    <description>Number of threads to be allocated for metastore handler for fs operations.</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.catalog.cache.size</name>
+    <value>50000</value>
+    <description>Maximum number of objects we will place in the hbase metastore catalog cache.  The objects will be divided up by types that we need to cache.</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggregate.stats.cache.size</name>
+    <value>10000</value>
+    <description>Maximum number of aggregate stats nodes that we will place in the hbase metastore aggregate stats cache.</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggregate.stats.max.partitions</name>
+    <value>10000</value>
+    <description>Maximum number of partitions that are aggregated per cache node.</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggregate.stats.false.positive.probability</name>
+    <value>0.01</value>
+    <description>Maximum false positive probability for the Bloom Filter used in each aggregate stats cache node (default 1%).</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggregate.stats.max.variance</name>
+    <value>0.1</value>
+    <description>Maximum tolerable variance in number of partitions between a cached node and our request (default 10%).</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.cache.ttl</name>
+    <value>600s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds for a cached node to be active in the cache before they become stale.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.cache.max.writer.wait</name>
+    <value>5000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Number of milliseconds a writer will wait to acquire the writelock before giving up.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.cache.max.reader.wait</name>
+    <value>1000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Number of milliseconds a reader will wait to acquire the readlock before giving up.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.cache.max.full</name>
+    <value>0.9</value>
+    <description>Maximum cache full % after which the cache cleaner thread kicks in.</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.cache.clean.until</name>
+    <value>0.8</value>
+    <description>The cleaner thread cleans until cache reaches this % full size.</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.connection.class</name>
+    <value>org.apache.hadoop.hive.metastore.hbase.VanillaHBaseConnection</value>
+    <description>Class used to connection to HBase</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggr.stats.cache.entries</name>
+    <value>10000</value>
+    <description>How many in stats objects to cache in memory</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggr.stats.memory.ttl</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds stats objects live in memory after they are read from HBase.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggr.stats.invalidator.frequency</name>
+    <value>5s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      How often the stats cache scans its HBase entries and looks for expired entries
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggr.stats.hbase.ttl</name>
+    <value>604800s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds stats entries live in HBase cache after they are created.  They may be invalided by updates or partition drops before this.  Default is one week.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.file.metadata.threads</name>
+    <value>1</value>
+    <description>Number of threads to use to read file metadata in background to cache it.</description>
+  </property>
+  <property>
+    <name>hive.metastore.connect.retries</name>
+    <value>3</value>
+    <description>Number of retries while opening a connection to metastore</description>
+  </property>
+  <property>
+    <name>hive.metastore.failure.retries</name>
+    <value>1</value>
+    <description>Number of retries upon failure of Thrift metastore calls</description>
+  </property>
+  <property>
+    <name>hive.metastore.port</name>
+    <value>9083</value>
+    <description>Hive metastore listener port</description>
+  </property>
+  <property>
+    <name>hive.metastore.client.connect.retry.delay</name>
+    <value>1s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds for the client to wait between consecutive connection attempts
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.client.socket.timeout</name>
+    <value>600s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      MetaStore Client socket timeout in seconds
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.client.socket.lifetime</name>
+    <value>0s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      MetaStore Client socket lifetime in seconds. After this time is exceeded, client
+      reconnects on the next MetaStore operation. A value of 0s means the connection
+      has an infinite lifetime.
+    </description>
+  </property>
+  <property>
+    <name>javax.jdo.option.ConnectionPassword</name>
+    <value>mine</value>
+    <description>password to use against metastore database</description>
+  </property>
+  <property>
+    <name>hive.metastore.ds.connection.url.hook</name>
+    <value/>
+    <description>Name of the hook to use for retrieving the JDO connection URL. If empty, the value in javax.jdo.option.ConnectionURL is used</description>
+  </property>
+  <property>
+    <name>javax.jdo.option.Multithreaded</name>
+    <value>true</value>
+    <description>Set this to true if multiple threads access metastore through JDO concurrently.</description>
+  </property>
+  <property>
+    <name>javax.jdo.option.ConnectionURL</name>
+    <value>jdbc:derby:;databaseName=metastore_db;create=true</value>
+    <description>
+      JDBC connect string for a JDBC metastore.
+      To use SSL to encrypt/authenticate the connection, provide database-specific SSL flag in the connection URL.
+      For example, jdbc:postgresql://myhost/db?ssl=true for postgres database.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.dbaccess.ssl.properties</name>
+    <value/>
+    <description>
+      Comma-separated SSL properties for metastore to access database when JDO connection URL
+      enables SSL access. e.g. javax.net.ssl.trustStore=/tmp/truststore,javax.net.ssl.trustStorePassword=pwd.
+    </description>
+  </property>
+  <property>
+    <name>hive.hmshandler.retry.attempts</name>
+    <value>10</value>
+    <description>The number of times to retry a HMSHandler call if there were a connection error.</description>
+  </property>
+  <property>
+    <name>hive.hmshandler.retry.interval</name>
+    <value>2000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      The time between HMSHandler retry attempts on failure.
+    </description>
+  </property>
+  <property>
+    <name>hive.hmshandler.force.reload.conf</name>
+    <value>false</value>
+    <description>
+      Whether to force reloading of the HMSHandler configuration (including
+      the connection URL, before the next metastore query that accesses the
+      datastore. Once reloaded, this value is reset to false. Used for
+      testing only.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.server.max.message.size</name>
+    <value>104857600</value>
+    <description>Maximum message size in bytes a HMS will accept.</description>
+  </property>
+  <property>
+    <name>hive.metastore.server.min.threads</name>
+    <value>200</value>
+    <description>Minimum number of worker threads in the Thrift server's pool.</description>
+  </property>
+  <property>
+    <name>hive.metastore.server.max.threads</name>
+    <value>1000</value>
+    <description>Maximum number of worker threads in the Thrift server's pool.</description>
+  </property>
+  <property>
+    <name>hive.metastore.server.tcp.keepalive</name>
+    <value>true</value>
+    <description>Whether to enable TCP keepalive for the metastore server. Keepalive will prevent accumulation of half-open connections.</description>
+  </property>
+  <property>
+    <name>hive.metastore.archive.intermediate.original</name>
+    <value>_INTERMEDIATE_ORIGINAL</value>
+    <description>
+      Intermediate dir suffixes used for archiving. Not important what they
+      are, as long as collisions are avoided
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.archive.intermediate.archived</name>
+    <value>_INTERMEDIATE_ARCHIVED</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.metastore.archive.intermediate.extracted</name>
+    <value>_INTERMEDIATE_EXTRACTED</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.metastore.kerberos.keytab.file</name>
+    <value/>
+    <description>The path to the Kerberos Keytab file containing the metastore Thrift server's service principal.</description>
+  </property>
+  <property>
+    <name>hive.metastore.kerberos.principal</name>
+    <value>hive-metastore/_HOST@EXAMPLE.COM</value>
+    <description>
+      The service principal for the metastore Thrift server. 
+      The special string _HOST will be replaced automatically with the correct host name.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.sasl.enabled</name>
+    <value>false</value>
+    <description>If true, the metastore Thrift interface will be secured with SASL. Clients must authenticate with Kerberos.</description>
+  </property>
+  <property>
+    <name>hive.metastore.thrift.framed.transport.enabled</name>
+    <value>false</value>
+    <description>If true, the metastore Thrift interface will use TFramedTransport. When false (default) a standard TTransport is used.</description>
+  </property>
+  <property>
+    <name>hive.metastore.thrift.compact.protocol.enabled</name>
+    <value>false</value>
+    <description>
+      If true, the metastore Thrift interface will use TCompactProtocol. When false (default) TBinaryProtocol will be used.
+      Setting it to true will break compatibility with older clients running TBinaryProtocol.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.token.signature</name>
+    <value/>
+    <description>The delegation token service name to match when selecting a token from the current user's tokens.</description>
+  </property>
+  <property>
+    <name>hive.cluster.delegation.token.store.class</name>
+    <value>org.apache.hadoop.hive.thrift.MemoryTokenStore</value>
+    <description>The delegation token store implementation. Set to org.apache.hadoop.hive.thrift.ZooKeeperTokenStore for load-balanced cluster.</description>
+  </property>
+  <property>
+    <name>hive.cluster.delegation.token.store.zookeeper.connectString</name>
+    <value/>
+    <description>
+      The ZooKeeper token store connect string. You can re-use the configuration value
+      set in hive.zookeeper.quorum, by leaving this parameter unset.
+    </description>
+  </property>
+  <property>
+    <name>hive.cluster.delegation.token.store.zookeeper.znode</name>
+    <value>/hivedelegation</value>
+    <description>
+      The root path for token store data. Note that this is used by both HiveServer2 and
+      MetaStore to store delegation Token. One directory gets created for each of them.
+      The final directory names would have the servername appended to it (HIVESERVER2,
+      METASTORE).
+    </description>
+  </property>
+  <property>
+    <name>hive.cluster.delegation.token.store.zookeeper.acl</name>
+    <value/>
+    <description>
+      ACL for token store entries. Comma separated list of ACL entries. For example:
+      sasl:hive/host1@MY.DOMAIN:cdrwa,sasl:hive/host2@MY.DOMAIN:cdrwa
+      Defaults to all permissions for the hiveserver2/metastore process user.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.cache.pinobjtypes</name>
+    <value>Table,StorageDescriptor,SerDeInfo,Partition,Database,Type,FieldSchema,Order</value>
+    <description>List of comma separated metastore object types that should be pinned in the cache</description>
+  </property>
+  <property>
+    <name>datanucleus.connectionPoolingType</name>
+    <value>BONECP</value>
+    <description>Specify connection pool library for datanucleus</description>
+  </property>
+  <property>
+    <name>datanucleus.rdbms.initializeColumnInfo</name>
+    <value>NONE</value>
+    <description>initializeColumnInfo setting for DataNucleus; set to NONE at least on Postgres.</description>
+  </property>
+  <property>
+    <name>datanucleus.schema.validateTables</name>
+    <value>false</value>
+    <description>validates existing schema against code. turn this on if you want to verify existing schema</description>
+  </property>
+  <property>
+    <name>datanucleus.schema.validateColumns</name>
+    <value>false</value>
+    <description>validates existing schema against code. turn this on if you want to verify existing schema</description>
+  </property>
+  <property>
+    <name>datanucleus.schema.validateConstraints</name>
+    <value>false</value>
+    <description>validates existing schema against code. turn this on if you want to verify existing schema</description>
+  </property>
+  <property>
+    <name>datanucleus.storeManagerType</name>
+    <value>rdbms</value>
+    <description>metadata store type</description>
+  </property>
+  <property>
+    <name>datanucleus.schema.autoCreateAll</name>
+    <value>false</value>
+    <description>Auto creates necessary schema on a startup if one doesn't exist. Set this to false, after creating it once.To enable auto create also set hive.metastore.schema.verification=false. Auto creation is not recommended for production use cases, run schematool command instead.</description>
+  </property>
+  <property>
+    <name>hive.metastore.schema.verification</name>
+    <value>true</value>
+    <description>
+      Enforce metastore schema version consistency.
+      True: Verify that version information stored in is compatible with one from Hive jars.  Also disable automatic
+            schema migration attempt. Users are required to manually migrate schema after Hive upgrade which ensures
+            proper metastore schema migration. (Default)
+      False: Warn if the version information stored in metastore doesn't match with one from in Hive jars.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.schema.verification.record.version</name>
+    <value>false</value>
+    <description>
+      When true the current MS version is recorded in the VERSION table. If this is disabled and verification is
+       enabled the MS will be unusable.
+    </description>
+  </property>
+  <property>
+    <name>datanucleus.transactionIsolation</name>
+    <value>read-committed</value>
+    <description>Default transaction isolation level for identity generation.</description>
+  </property>
+  <property>
+    <name>datanucleus.cache.level2</name>
+    <value>false</value>
+    <description>Use a level 2 cache. Turn this off if metadata is changed independently of Hive metastore server</description>
+  </property>
+  <property>
+    <name>datanucleus.cache.level2.type</name>
+    <value>none</value>
+    <description/>
+  </property>
+  <property>
+    <name>datanucleus.identifierFactory</name>
+    <value>datanucleus1</value>
+    <description>
+      Name of the identifier factory to use when generating table/column names etc. 
+      'datanucleus1' is used for backward compatibility with DataNucleus v1
+    </description>
+  </property>
+  <property>
+    <name>datanucleus.rdbms.useLegacyNativeValueStrategy</name>
+    <value>true</value>
+    <description/>
+  </property>
+  <property>
+    <name>datanucleus.plugin.pluginRegistryBundleCheck</name>
+    <value>LOG</value>
+    <description>Defines what happens when plugin bundles are found and are duplicated [EXCEPTION|LOG|NONE]</description>
+  </property>
+  <property>
+    <name>hive.metastore.batch.retrieve.max</name>
+    <value>300</value>
+    <description>
+      Maximum number of objects (tables/partitions) can be retrieved from metastore in one batch. 
+      The higher the number, the less the number of round trips is needed to the Hive metastore server, 
+      but it may also cause higher memory requirement at the client side.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.batch.retrieve.table.partition.max</name>
+    <value>1000</value>
+    <description>Maximum number of objects that metastore internally retrieves in one batch.</description>
+  </property>
+  <property>
+    <name>hive.metastore.init.hooks</name>
+    <value/>
+    <description>
+      A comma separated list of hooks to be invoked at the beginning of HMSHandler initialization. 
+      An init hook is specified as the name of Java class which extends org.apache.hadoop.hive.metastore.MetaStoreInitListener.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.pre.event.listeners</name>
+    <value/>
+    <description>List of comma separated listeners for metastore events.</description>
+  </property>
+  <property>
+    <name>hive.metastore.event.listeners</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.metastore.event.db.listener.timetolive</name>
+    <value>86400s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      time after which events will be removed from the database listener queue
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.authorization.storage.checks</name>
+    <value>false</value>
+    <description>
+      Should the metastore do authorization checks against the underlying storage (usually hdfs) 
+      for operations like drop-partition (disallow the drop-partition if the user in
+      question doesn't have permissions to delete the corresponding directory
+      on the storage).
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.event.clean.freq</name>
+    <value>0s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Frequency at which timer task runs to purge expired events in metastore.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.event.expiry.duration</name>
+    <value>0s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Duration after which events expire from events table
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.execute.setugi</name>
+    <value>true</value>
+    <description>
+      In unsecure mode, setting this property to true will cause the metastore to execute DFS operations using 
+      the client's reported user and group permissions. Note that this property must be set on 
+      both the client and server sides. Further note that its best effort. 
+      If client sets its to true and server sets it to false, client setting will be ignored.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.partition.name.whitelist.pattern</name>
+    <value/>
+    <description>Partition names will be checked against this regex pattern and rejected if not matched.</description>
+  </property>
+  <property>
+    <name>hive.metastore.integral.jdo.pushdown</name>
+    <value>false</value>
+    <description>
+      Allow JDO query pushdown for integral partition columns in metastore. Off by default. This
+      improves metastore perf for integral columns, especially if there's a large number of partitions.
+      However, it doesn't work correctly with integral values that are not normalized (e.g. have
+      leading zeroes, like 0012). If metastore direct SQL is enabled and works, this optimization
+      is also irrelevant.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.try.direct.sql</name>
+    <value>true</value>
+    <description>
+      Whether the Hive metastore should try to use direct SQL queries instead of the
+      DataNucleus for certain read paths. This can improve metastore performance when
+      fetching many partitions or column statistics by orders of magnitude; however, it
+      is not guaranteed to work on all RDBMS-es and all versions. In case of SQL failures,
+      the metastore will fall back to the DataNucleus, so it's safe even if SQL doesn't
+      work for all queries on your datastore. If all SQL queries fail (for example, your
+      metastore is backed by MongoDB), you might want to disable this to save the
+      try-and-fall-back cost.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.direct.sql.batch.size</name>
+    <value>0</value>
+    <description>
+      Batch size for partition and other object retrieval from the underlying DB in direct
+      SQL. For some DBs like Oracle and MSSQL, there are hardcoded or perf-based limitations
+      that necessitate this. For DBs that can handle the queries, this isn't necessary and
+      may impede performance. -1 means no batching, 0 means automatic batching.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.try.direct.sql.ddl</name>
+    <value>true</value>
+    <description>
+      Same as hive.metastore.try.direct.sql, for read statements within a transaction that
+      modifies metastore data. Due to non-standard behavior in Postgres, if a direct SQL
+      select query has incorrect syntax or something similar inside a transaction, the
+      entire transaction will fail and fall-back to DataNucleus will not be possible. You
+      should disable the usage of direct SQL inside transactions if that happens in your case.
+    </description>
+  </property>
+  <property>
+    <name>hive.direct.sql.max.query.length</name>
+    <value>100</value>
+    <description>
+      The maximum
+       size of a query string (in KB).
+    </description>
+  </property>
+  <property>
+    <name>hive.direct.sql.max.elements.in.clause</name>
+    <value>1000</value>
+    <description>
+      The maximum number of values in a IN clause. Once exceeded, it will be broken into
+       multiple OR separated IN clauses.
+    </description>
+  </property>
+  <property>
+    <name>hive.direct.sql.max.elements.values.clause</name>
+    <value>1000</value>
+    <description>The maximum number of values in a VALUES clause for INSERT statement.</description>
+  </property>
+  <property>
+    <name>hive.metastore.orm.retrieveMapNullsAsEmptyStrings</name>
+    <value>false</value>
+    <description>Thrift does not support nulls in maps, so any nulls present in maps retrieved from ORM must either be pruned or converted to empty strings. Some backing dbs such as Oracle persist empty strings as nulls, so we should set this parameter if we wish to reverse that behaviour. For others, pruning is the correct behaviour</description>
+  </property>
+  <property>
+    <name>hive.metastore.disallow.incompatible.col.type.changes</name>
+    <value>true</value>
+    <description>
+      If true (default is false), ALTER TABLE operations which change the type of a
+      column (say STRING) to an incompatible type (say MAP) are disallowed.
+      RCFile default SerDe (ColumnarSerDe) serializes the values in such a way that the
+      datatypes can be converted from string to any type. The map is also serialized as
+      a string, which can be read as a string as well. However, with any binary
+      serialization, this is not true. Blocking the ALTER TABLE prevents ClassCastExceptions
+      when subsequently trying to access old partitions.
+      
+      Primitive types like INT, STRING, BIGINT, etc., are compatible with each other and are
+      not blocked.
+      
+      See HIVE-4409 for more details.
+    </description>
+  </property>
+  <property>
+    <name>hive.table.parameters.default</name>
+    <value/>
+    <description>Default property values for newly created tables</description>
+  </property>
+  <property>
+    <name>hive.ddl.createtablelike.properties.whitelist</name>
+    <value/>
+    <description>Table Properties to copy over when executing a Create Table Like.</description>
+  </property>
+  <property>
+    <name>hive.metastore.rawstore.impl</name>
+    <value>org.apache.hadoop.hive.metastore.ObjectStore</value>
+    <description>
+      Name of the class that implements org.apache.hadoop.hive.metastore.rawstore interface. 
+      This class is used to store and retrieval of raw metadata objects such as table, database
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.txn.store.impl</name>
+    <value>org.apache.hadoop.hive.metastore.txn.CompactionTxnHandler</value>
+    <description>Name of class that implements org.apache.hadoop.hive.metastore.txn.TxnStore.  This class is used to store and retrieve transactions and locks</description>
+  </property>
+  <property>
+    <name>javax.jdo.option.ConnectionDriverName</name>
+    <value>org.apache.derby.jdbc.EmbeddedDriver</value>
+    <description>Driver class name for a JDBC metastore</description>
+  </property>
+  <property>
+    <name>javax.jdo.PersistenceManagerFactoryClass</name>
+    <value>org.datanucleus.api.jdo.JDOPersistenceManagerFactory</value>
+    <description>class implementing the jdo persistence</description>
+  </property>
+  <property>
+    <name>hive.metastore.expression.proxy</name>
+    <value>org.apache.hadoop.hive.ql.optimizer.ppr.PartitionExpressionForMetastore</value>
+    <description/>
+  </property>
+  <property>
+    <name>javax.jdo.option.DetachAllOnCommit</name>
+    <value>true</value>
+    <description>Detaches all objects from session so that they can be used after transaction is committed</description>
+  </property>
+  <property>
+    <name>javax.jdo.option.NonTransactionalRead</name>
+    <value>true</value>
+    <description>Reads outside of transactions</description>
+  </property>
+  <property>
+    <name>javax.jdo.option.ConnectionUserName</name>
+    <value>APP</value>
+    <description>Username to use against metastore database</description>
+  </property>
+  <property>
+    <name>hive.metastore.end.function.listeners</name>
+    <value/>
+    <description>List of comma separated listeners for the end of metastore functions.</description>
+  </property>
+  <property>
+    <name>hive.metastore.partition.inherit.table.properties</name>
+    <value/>
+    <description>
+      List of comma separated keys occurring in table properties which will get inherited to newly created partitions. 
+      * implies all the keys will get inherited.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.filter.hook</name>
+    <value>org.apache.hadoop.hive.metastore.DefaultMetaStoreFilterHookImpl</value>
+    <description>Metastore hook class for filtering the metadata read results. If hive.security.authorization.manageris set to instance of HiveAuthorizerFactory, then this value is ignored.</description>
+  </property>
+  <property>
+    <name>hive.metastore.dml.events</name>
+    <value>false</value>
+    <description>If true, the metastore will be asked to fire events for DML operations</description>
+  </property>
+  <property>
+    <name>hive.metastore.client.drop.partitions.using.expressions</name>
+    <value>true</value>
+    <description>Choose whether dropping partitions with HCatClient pushes the partition-predicate to the metastore, or drops partitions iteratively</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.enabled</name>
+    <value>true</value>
+    <description>Whether aggregate stats caching is enabled or not.</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.size</name>
+    <value>10000</value>
+    <description>Maximum number of aggregate stats nodes that we will place in the metastore aggregate stats cache.</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.max.partitions</name>
+    <value>10000</value>
+    <description>Maximum number of partitions that are aggregated per cache node.</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.fpp</name>
+    <value>0.01</value>
+    <description>Maximum false positive probability for the Bloom Filter used in each aggregate stats cache node (default 1%).</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.max.variance</name>
+    <value>0.01</value>
+    <description>Maximum tolerable variance in number of partitions between a cached node and our request (default 1%).</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.ttl</name>
+    <value>600s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds for a cached node to be active in the cache before they become stale.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.max.writer.wait</name>
+    <value>5000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Number of milliseconds a writer will wait to acquire the writelock before giving up.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.max.reader.wait</name>
+    <value>1000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Number of milliseconds a reader will wait to acquire the readlock before giving up.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.max.full</name>
+    <value>0.9</value>
+    <description>Maximum cache full % after which the cache cleaner thread kicks in.</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.clean.until</name>
+    <value>0.8</value>
+    <description>The cleaner thread cleans until cache reaches this % full size.</description>
+  </property>
+  <property>
+    <name>hive.metastore.metrics.enabled</name>
+    <value>false</value>
+    <description>Enable metrics on the metastore.</description>
+  </property>
+  <property>
+    <name>hive.metastore.initial.metadata.count.enabled</name>
+    <value>true</value>
+    <description>Enable a metadata count at metastore startup for metrics.</description>
+  </property>
+  <property>
+    <name>hive.metadata.export.location</name>
+    <value/>
+    <description>
+      When used in conjunction with the org.apache.hadoop.hive.ql.parse.MetaDataExportListener pre event listener, 
+      it is the location to which the metadata will be exported. The default is an empty string, which results in the 
+      metadata being exported to the current user's home directory on HDFS.
+    </description>
+  </property>
+  <property>
+    <name>hive.metadata.move.exported.metadata.to.trash</name>
+    <value>true</value>
+    <description>
+      When used in conjunction with the org.apache.hadoop.hive.ql.parse.MetaDataExportListener pre event listener, 
+      this setting determines if the metadata that is exported will subsequently be moved to the user's trash directory 
+      alongside the dropped table data. This ensures that the metadata will be cleaned up along with the dropped table data.
+    </description>
+  </property>
+  <property>
+    <name>hive.cli.errors.ignore</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.cli.print.current.db</name>
+    <value>false</value>
+    <description>Whether to include the current database in the Hive prompt.</description>
+  </property>
+  <property>
+    <name>hive.cli.prompt</name>
+    <value>hive</value>
+    <description>
+      Command line prompt configuration value. Other hiveconf can be used in this configuration value. 
+      Variable substitution will only be invoked at the Hive CLI startup.
+    </description>
+  </property>
+  <property>
+    <name>hive.cli.pretty.output.num.cols</name>
+    <value>-1</value>
+    <description>
+      The number of columns to use when formatting output generated by the DESCRIBE PRETTY table_name command.
+      If the value of this property is -1, then Hive will use the auto-detected terminal width.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.fs.handler.class</name>
+    <value>org.apache.hadoop.hive.metastore.HiveMetaStoreFsImpl</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.session.id</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.session.silent</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.session.history.enabled</name>
+    <value>false</value>
+    <description>Whether to log Hive query, query plan, runtime statistics etc.</description>
+  </property>
+  <property>
+    <name>hive.query.string</name>
+    <value/>
+    <description>Query being executed (might be multiple per a session)</description>
+  </property>
+  <property>
+    <name>hive.query.id</name>
+    <value/>
+    <description>ID for query being executed (might be multiple per a session)</description>
+  </property>
+  <property>
+    <name>hive.jobname.length</name>
+    <value>50</value>
+    <description>max jobname length</description>
+  </property>
+  <property>
+    <name>hive.jar.path</name>
+    <value/>
+    <description>The location of hive_cli.jar that is used when submitting jobs in a separate jvm.</description>
+  </property>
+  <property>
+    <name>hive.aux.jars.path</name>
+    <value/>
+    <description>The location of the plugin jars that contain implementations of user defined functions and serdes.</description>
+  </property>
+  <property>
+    <name>hive.reloadable.aux.jars.path</name>
+    <value/>
+    <description>Jars can be renewed by executing reload command. And these jars can be used as the auxiliary classes like creating a UDF or SerDe.</description>
+  </property>
+  <property>
+    <name>hive.added.files.path</name>
+    <value/>
+    <description>This an internal parameter.</description>
+  </property>
+  <property>
+    <name>hive.added.jars.path</name>
+    <value/>
+    <description>This an internal parameter.</description>
+  </property>
+  <property>
+    <name>hive.added.archives.path</name>
+    <value/>
+    <description>This an internal parameter.</description>
+  </property>
+  <property>
+    <name>hive.auto.progress.timeout</name>
+    <value>0s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      How long to run autoprogressor for the script/UDTF operators.
+      Set to 0 for forever.
+    </description>
+  </property>
+  <property>
+    <name>hive.script.auto.progress</name>
+    <value>false</value>
+    <description>
+      Whether Hive Transform/Map/Reduce Clause should automatically send progress information to TaskTracker 
+      to avoid the task getting killed because of inactivity.  Hive sends progress information when the script is 
+      outputting to stderr.  This option removes the need of periodically producing stderr messages, 
+      but users should be cautious because this may prevent infinite loops in the scripts to be killed by TaskTracker.
+    </description>
+  </property>
+  <property>
+    <name>hive.script.operator.id.env.var</name>
+    <value>HIVE_SCRIPT_OPERATOR_ID</value>
+    <description>
+      Name of the environment variable that holds the unique script operator ID in the user's 
+      transform function (the custom mapper/reducer that the user has specified in the query)
+    </description>
+  </property>
+  <property>
+    <name>hive.script.operator.truncate.env</name>
+    <value>false</value>
+    <description>Truncate each environment variable for external script in scripts operator to 20KB (to fit system limits)</description>
+  </property>
+  <property>
+    <name>hive.script.operator.env.blacklist</name>
+    <value>hive.txn.valid.txns,hive.script.operator.env.blacklist</value>
+    <description>Comma separated list of keys from the configuration file not to convert to environment variables when envoking the script operator</description>
+  </property>
+  <property>
+    <name>hive.strict.checks.large.query</name>
+    <value>false</value>
+    <description>
+      Enabling strict large query checks disallows the following:
+        Orderby without limit.
+        No partition being picked up for a query against partitioned table.
+      Note that these checks currently do not consider data size, only the query pattern.
+    </description>
+  </property>
+  <property>
+    <name>hive.strict.checks.type.safety</name>
+    <value>true</value>
+    <description>
+      Enabling strict type safety checks disallows the following:
+        Comparing bigints and strings.
+        Comparing bigints and doubles.
+    </description>
+  </property>
+  <property>
+    <name>hive.strict.checks.cartesian.product</name>
+    <value>true</value>
+    <description>
+      Enabling strict large query checks disallows the following:
+        Cartesian product (cross join).
+    </description>
+  </property>
+  <property>
+    <name>hive.mapred.mode</name>
+    <value>nonstrict</value>
+    <description>Deprecated; use hive.strict.checks.* settings instead.</description>
+  </property>
+  <property>
+    <name>hive.alias</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.map.aggr</name>
+    <value>true</value>
+    <description>Whether to use map-side aggregation in Hive Group By queries</description>
+  </property>
+  <property>
+    <name>hive.groupby.skewindata</name>
+    <value>false</value>
+    <description>Whether there is skew in data to optimize group by queries</description>
+  </property>
+  <property>
+    <name>hive.join.emit.interval</name>
+    <value>1000</value>
+    <description>How many rows in the right-most join operand Hive should buffer before emitting the join result.</description>
+  </property>
+  <property>
+    <name>hive.join.cache.size</name>
+    <value>25000</value>
+    <description>How many rows in the joining tables (except the streaming table) should be cached in memory.</description>
+  </property>
+  <property>
+    <name>hive.cbo.enable</name>
+    <value>true</value>
+    <description>Flag to control enabling Cost Based Optimizations using Calcite framework.</description>
+  </property>
+  <property>
+    <name>hive.cbo.cnf.maxnodes</name>
+    <value>-1</value>
+    <description>When converting to conjunctive normal form (CNF), fail ifthe expression exceeds this threshold; the threshold is expressed in terms of number of nodes (leaves andinterior nodes). -1 to not set up a threshold.</description>
+  </property>
+  <property>
+    <name>hive.cbo.returnpath.hiveop</name>
+    <value>false</value>
+    <description>Flag to control calcite plan to hive operator conversion</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.extended</name>
+    <value>false</value>
+    <description>Flag to control enabling the extended cost model based onCPU, IO and cardinality. Otherwise, the cost model is based on cardinality.</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.cpu</name>
+    <value>0.000001</value>
+    <description>Default cost of a comparison</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.network</name>
+    <value>150.0</value>
+    <description>Default cost of a transfering a byte over network; expressed as multiple of CPU cost</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.local.fs.write</name>
+    <value>4.0</value>
+    <description>Default cost of writing a byte to local FS; expressed as multiple of NETWORK cost</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.local.fs.read</name>
+    <value>4.0</value>
+    <description>Default cost of reading a byte from local FS; expressed as multiple of NETWORK cost</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.hdfs.write</name>
+    <value>10.0</value>
+    <description>Default cost of writing a byte to HDFS; expressed as multiple of Local FS write cost</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.hdfs.read</name>
+    <value>1.5</value>
+    <description>Default cost of reading a byte from HDFS; expressed as multiple of Local FS read cost</description>
+  </property>
+  <property>
+    <name>hive.transpose.aggr.join</name>
+    <value>false</value>
+    <description>push aggregates through join</description>
+  </property>
+  <property>
+    <name>hive.order.columnalignment</name>
+    <value>true</value>
+    <description>Flag to control whether we want to try to aligncolumns in operators such as Aggregate or Join so that we try to reduce the number of shuffling stages</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.bucket.cache.size</name>
+    <value>100</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.mapjoin.optimized.hashtable</name>
+    <value>true</value>
+    <description>
+      Whether Hive should use memory-optimized hash table for MapJoin.
+      Only works on Tez and Spark, because memory-optimized hashtable cannot be serialized.
+    </description>
+  </property>
+  <property>
+    <name>hive.mapjoin.optimized.hashtable.probe.percent</name>
+    <value>0.5</value>
+    <description>Probing space percentage of the optimized hashtable</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.hybridgrace.hashtable</name>
+    <value>true</value>
+    <description>Whether to use hybridgrace hash join as the join method for mapjoin. Tez only.</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.hybridgrace.memcheckfrequency</name>
+    <value>1024</value>
+    <description>For hybrid grace hash join, how often (how many rows apart) we check if memory is full. This number should be power of 2.</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.hybridgrace.minwbsize</name>
+    <value>524288</value>
+    <description>For hybrid graceHash join, the minimum write buffer size used by optimized hashtable. Default is 512 KB.</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.hybridgrace.minnumpartitions</name>
+    <value>16</value>
+    <description>ForHybrid grace hash join, the minimum number of partitions to create.</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.optimized.hashtable.wbsize</name>
+    <value>8388608</value>
+    <description>
+      Optimized hashtable (see hive.mapjoin.optimized.hashtable) uses a chain of buffers to
+      store data. This is one buffer size. HT may be slightly faster if this is larger, but for small
+      joins unnecessary memory will be allocated and then trimmed.
+    </description>
+  </property>
+  <property>
+    <name>hive.mapjoin.hybridgrace.bloomfilter</name>
+    <value>true</value>
+    <description>Whether to use BloomFilter in Hybrid grace hash join to minimize unnecessary spilling.</description>
+  </property>
+  <property>
+    <name>hive.smbjoin.cache.rows</name>
+    <value>10000</value>
+    <description>How many rows with the same key value should be cached in memory per smb joined table.</description>
+  </property>
+  <property>
+    <name>hive.groupby.mapaggr.checkinterval</name>
+    <value>100000</value>
+    <description>Number of rows after which size of the grouping keys/aggregation classes is performed</description>
+  </property>
+  <property>
+    <name>hive.map.aggr.hash.percentmemory</name>
+    <value>0.5</value>
+    <description>Portion of total memory to be used by map-side group aggregation hash table</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.followby.map.aggr.hash.percentmemory</name>
+    <value>0.3</value>
+    <description>Portion of total memory to be used by map-side group aggregation hash table, when this group by is followed by map join</description>
+  </property>
+  <property>
+    <name>hive.map.aggr.hash.force.flush.memory.threshold</name>
+    <value>0.9</value>
+    <description>
+      The max memory to be used by map-side group aggregation hash table.
+      If the memory usage is higher than this number, force to flush data
+    </description>
+  </property>
+  <property>
+    <name>hive.map.aggr.hash.min.reduction</name>
+    <value>0.5</value>
+    <description>
+      Hash aggregation will be turned off if the ratio between hash  table size and input rows is bigger than this number. 
+      Set to 1 to make sure hash aggregation is never turned off.
+    </description>
+  </property>
+  <property>
+    <name>hive.multigroupby.singlereducer</name>
+    <value>true</value>
+    <description>
+      Whether to optimize multi group by query to generate single M/R  job plan. If the multi group by query has 
+      common group by keys, it will be optimized to generate single M/R job.
+    </description>
+  </property>
+  <property>
+    <name>hive.map.groupby.sorted</name>
+    <value>true</value>
+    <description>
+      If the bucketing/sorting properties of the table exactly match the grouping key, whether to perform 
+      the group by in the mapper by using BucketizedHiveInputFormat. The only downside to this
+      is that it limits the number of mappers to the number of files.
+    </description>
+  </property>
+  <property>
+    <name>hive.groupby.orderby.position.alias</name>
+    <value>false</value>
+    <description>Whether to enable using Column Position Alias in Group By or Order By</description>
+  </property>
+  <property>
+    <name>hive.new.job.grouping.set.cardinality</name>
+    <value>30</value>
+    <description>
+      Whether a new map-reduce job should be launched for grouping sets/rollups/cubes.
+      For a query like: select a, b, c, count(1) from T group by a, b, c with rollup;
+      4 rows are created per row: (a, b, c), (a, b, null), (a, null, null), (null, null, null).
+      This can lead to explosion across map-reduce boundary if the cardinality of T is very high,
+      and map-side aggregation does not do a very good job. 
+      
+      This parameter decides if Hive should add an additional map-reduce job. If the grouping set
+      cardinality (4 in the example above), is more than this value, a new MR job is added under the
+      assumption that the original group by will reduce the data size.
+    </description>
+  </property>
+  <property>
+    <name>hive.groupby.limit.extrastep</name>
+    <value>true</value>
+    <description>
+      This parameter decides if Hive should 
+      create new MR job for sorting final output
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.copyfile.maxsize</name>
+    <value>33554432</value>
+    <description>Maximum file size (in Mb) that Hive uses to do single HDFS copies between directories.Distributed copies (distcp) will be used instead for bigger files so that copies can be done faster.</description>
+  </property>
+  <property>
+    <name>hive.udtf.auto.progress</name>
+    <value>false</value>
+    <description>
+      Whether Hive should automatically send progress information to TaskTracker 
+      when using UDTF's to prevent the task getting killed because of inactivity.  Users should be cautious 
+      because this may prevent TaskTracker from killing tasks with infinite loops.
+    </description>
+  </property>
+  <property>
+    <name>hive.default.fileformat</name>
+    <value>TextFile</value>
+    <description>
+      Expects one of [textfile, sequencefile, rcfile, orc].
+      Default file format for CREATE TABLE statement. Users can explicitly override it by CREATE TABLE ... STORED AS [FORMAT]
+    </description>
+  </property>
+  <property>
+    <name>hive.default.fileformat.managed</name>
+    <value>none</value>
+    <description>
+      Expects one of [none, textfile, sequencefile, rcfile, orc].
+      Default file format for CREATE TABLE statement applied to managed tables only. External tables will be 
+      created with format specified by hive.default.fileformat. Leaving this null will result in using hive.default.fileformat 
+      for all tables.
+    </description>
+  </property>
+  <property>
+    <name>hive.query.result.fileformat</name>
+    <value>SequenceFile</value>
+    <description>
+      Expects one of [textfile, sequencefile, rcfile, llap].
+      Default file format for storing result of the query.
+    </description>
+  </property>
+  <property>
+    <name>hive.fileformat.check</name>
+    <value>true</value>
+    <description>Whether to check file format or not when loading data files</description>
+  </property>
+  <property>
+    <name>hive.default.rcfile.serde</name>
+    <value>org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe</value>
+    <description>The default SerDe Hive will use for the RCFile format</description>
+  </property>
+  <property>
+    <name>hive.default.serde</name>
+    <value>org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe</value>
+    <description>The default SerDe Hive will use for storage formats that do not specify a SerDe.</description>
+  </property>
+  <property>
+    <name>hive.serdes.using.metastore.for.schema</name>
+    <value>org.apache.hadoop.hive.ql.io.orc.OrcSerde,org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe,org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe,org.apache.hadoop.hive.serde2.dynamic_type.DynamicSerDe,org.apache.hadoop.hive.serde2.MetadataTypedColumnsetSerDe,org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe,org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe,org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe</value>
+    <description>SerDes retrieving schema from metastore. This is an internal parameter.</description>
+  </property>
+  <property>
+    <name>hive.querylog.location</name>
+    <value>${system:java.io.tmpdir}/${system:user.name}</value>
+    <description>Location of Hive run time structured log file</description>
+  </property>
+  <property>
+    <name>hive.querylog.enable.plan.progress</name>
+    <value>true</value>
+    <description>
+      Whether to log the plan's progress every time a job's progress is checked.
+      These logs are written to the location specified by hive.querylog.location
+    </description>
+  </property>
+  <property>
+    <name>hive.querylog.plan.progress.interval</name>
+    <value>60000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      The interval to wait between logging the plan's progress.
+      If there is a whole number percentage change in the progress of the mappers or the reducers,
+      the progress is logged regardless of this value.
+      The actual interval will be the ceiling of (this value divided by the value of
+      hive.exec.counters.pull.interval) multiplied by the value of hive.exec.counters.pull.interval
+      I.e. if it is not divide evenly by the value of hive.exec.counters.pull.interval it will be
+      logged less frequently than specified.
+      This only has an effect if hive.querylog.enable.plan.progress is set to true.
+    </description>
+  </property>
+  <property>
+    <name>hive.script.serde</name>
+    <value>org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe</value>
+    <description>The default SerDe for transmitting input data to and reading output data from the user scripts. </description>
+  </property>
+  <property>
+    <name>hive.script.recordreader</name>
+    <value>org.apache.hadoop.hive.ql.exec.TextRecordReader</value>
+    <description>The default record reader for reading data from the user scripts. </description>
+  </property>
+  <property>
+    <name>hive.script.recordwriter</name>
+    <value>org.apache.hadoop.hive.ql.exec.TextRecordWriter</value>
+    <description>The default record writer for writing data to the user scripts. </description>
+  </property>
+  <property>
+    <name>hive.transform.escape.input</name>
+    <value>false</value>
+    <description>
+      This adds an option to escape special chars (newlines, carriage returns and
+      tabs) when they are passed to the user script. This is useful if the Hive tables
+      can contain data that contains special characters.
+    </description>
+  </property>
+  <property>
+    <name>hive.binary.record.max.length</name>
+    <value>1000</value>
+    <description>
+      Read from a binary stream and treat each hive.binary.record.max.length bytes as a record. 
+      The last record before the end of stream can have less than hive.binary.record.max.length bytes
+    </description>
+  </property>
+  <property>
+    <name>hive.hwi.listen.host</name>
+    <value>0.0.0.0</value>
+    <description>This is the host address the Hive Web Interface will listen on</description>
+  </property>
+  <property>
+    <name>hive.hwi.listen.port</name>
+    <value>9999</value>
+    <description>This is the port the Hive Web Interface will listen on</description>
+  </property>
+  <property>
+    <name>hive.hwi.war.file</name>
+    <value>${env:HWI_WAR_FILE}</value>
+    <description>This sets the path to the HWI war file, relative to ${HIVE_HOME}. </description>
+  </property>
+  <property>
+    <name>hive.mapred.local.mem</name>
+    <value>0</value>
+    <description>mapper/reducer memory in local mode</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.smalltable.filesize</name>
+    <value>25000000</value>
+    <description>
+      The threshold for the input file size of the small tables; if the file size is smaller 
+      than this threshold, it will try to convert the common join into map join
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.schema.evolution</name>
+    <value>true</value>
+    <description>Use schema evolution to convert self-describing file format's data to the schema desired by the reader.</description>
+  </property>
+  <property>
+    <name>hive.sample.seednumber</name>
+    <value>0</value>
+    <description>A number used to percentage sampling. By changing this number, user will change the subsets of data sampled.</description>
+  </property>
+  <property>
+    <name>hive.test.mode</name>
+    <value>false</value>
+    <description>Whether Hive is running in test mode. If yes, it turns on sampling and prefixes the output tablename.</description>
+  </property>
+  <property>
+    <name>hive.test.mode.prefix</name>
+    <value>test_</value>
+    <description>In test mode, specfies prefixes for the output table</description>
+  </property>
+  <property>
+    <name>hive.test.mode.samplefreq</name>
+    <value>32</value>
+    <description>
+      In test mode, specfies sampling frequency for table, which is not bucketed,
+      For example, the following query:
+        INSERT OVERWRITE TABLE dest SELECT col1 from src
+      would be converted to
+        INSERT OVERWRITE TABLE test_dest
+        SELECT col1 from src TABLESAMPLE (BUCKET 1 out of 32 on rand(1))
+    </description>
+  </property>
+  <property>
+    <name>hive.test.mode.nosamplelist</name>
+    <value/>
+    <description>In test mode, specifies comma separated table names which would not apply sampling</description>
+  </property>
+  <property>
+    <name>hive.test.dummystats.aggregator</name>
+    <value/>
+    <description>internal variable for test</description>
+  </property>
+  <property>
+    <name>hive.test.dummystats.publisher</name>
+    <value/>
+    <description>internal variable for test</description>
+  </property>
+  <property>
+    <name>hive.test.currenttimestamp</name>
+    <value/>
+    <description>current timestamp for test</description>
+  </property>
+  <property>
+    <name>hive.test.rollbacktxn</name>
+    <value>false</value>
+    <description>For testing only.  Will mark every ACID transaction aborted</description>
+  </property>
+  <property>
+    <name>hive.test.fail.compaction</name>
+    <value>false</value>
+    <description>For testing only.  Will cause CompactorMR to fail.</description>
+  </property>
+  <property>
+    <name>hive.test.fail.heartbeater</name>
+    <value>false</value>
+    <description>For testing only.  Will cause Heartbeater to fail.</description>
+  </property>
+  <property>
+    <name>hive.merge.mapfiles</name>
+    <value>true</value>
+    <description>Merge small files at the end of a map-only job</description>
+  </property>
+  <property>
+    <name>hive.merge.mapredfiles</name>
+    <value>false</value>
+    <description>Merge small files at the end of a map-reduce job</description>
+  </property>
+  <property>
+    <name>hive.merge.tezfiles</name>
+    <value>false</value>
+    <description>Merge small files at the end of a Tez DAG</description>
+  </property>
+  <property>
+    <name>hive.merge.sparkfiles</name>
+    <value>false</value>
+    <description>Merge small files at the end of a Spark DAG Transformation</description>
+  </property>
+  <property>
+    <name>hive.merge.size.per.task</name>
+    <value>256000000</value>
+    <description>Size of merged files at the end of the job</description>
+  </property>
+  <property>
+    <name>hive.merge.smallfiles.avgsize</name>
+    <value>16000000</value>
+    <description>
+      When the average output file size of a job is less than this number, Hive will start an additional 
+      map-reduce job to merge the output files into bigger files. This is only done for map-only jobs 
+      if hive.merge.mapfiles is true, and for map-reduce jobs if hive.merge.mapredfiles is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.merge.rcfile.block.level</name>
+    <value>true</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.merge.orcfile.stripe.level</name>
+    <value>true</value>
+    <description>
+      When hive.merge.mapfiles, hive.merge.mapredfiles or hive.merge.tezfiles is enabled
+      while writing a table with ORC file format, enabling this config will do stripe-level
+      fast merge for small ORC files. Note that enabling this config will not honor the
+      padding tolerance config (hive.exec.orc.block.padding.tolerance).
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.rcfile.use.explicit.header</name>
+    <value>true</value>
+    <description>
+      If this is set the header for RCFiles will simply be RCF.  If this is not
+      set the header will be that borrowed from sequence files, e.g. SEQ- followed
+      by the input and output RCFile formats.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.rcfile.use.sync.cache</name>
+    <value>true</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.io.rcfile.record.interval</name>
+    <value>2147483647</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.io.rcfile.column.number.conf</name>
+    <value>0</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.io.rcfile.tolerate.corruptions</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.io.rcfile.record.buffer.size</name>
+    <value>4194304</value>
+    <description/>
+  </property>
+  <property>
+    <name>parquet.memory.pool.ratio</name>
+    <value>0.5</value>
+    <description>
+      Maximum fraction of heap that can be used by Parquet file writers in one task.
+      It is for avoiding OutOfMemory error in tasks. Work with Parquet 1.6.0 and above.
+      This config parameter is defined in Parquet, so that it does not start with 'hive.'.
+    </description>
+  </property>
+  <property>
+    <name>hive.parquet.timestamp.skip.conversion</name>
+    <value>true</value>
+    <description>Current Hive implementation of parquet stores timestamps to UTC, this flag allows skipping of the conversionon reading parquet files from other tools</description>
+  </property>
+  <property>
+    <name>hive.int.timestamp.conversion.in.seconds</name>
+    <value>false</value>
+    <description>
+      Boolean/tinyint/smallint/int/bigint value is interpreted as milliseconds during the timestamp conversion.
+      Set this flag to true to interpret the value as seconds to be consistent with float/double.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.memory.pool</name>
+    <value>0.5</value>
+    <description>Maximum fraction of heap that can be used by ORC file writers</description>
+  </property>
+  <property>
+    <name>hive.exec.orc.write.format</name>
+    <value/>
+    <description>
+      Define the version of the file to write. Possible values are 0.11 and 0.12.
+      If this parameter is not defined, ORC will use the run length encoding (RLE)
+      introduced in Hive 0.12. Any value other than 0.11 results in the 0.12 encoding.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.default.stripe.size</name>
+    <value>67108864</value>
+    <description>Define the default ORC stripe size, in bytes.</description>
+  </property>
+  <property>
+    <name>hive.exec.orc.default.block.size</name>
+    <value>268435456</value>
+    <description>Define the default file system block size for ORC files.</description>
+  </property>
+  <property>
+    <name>hive.exec.orc.dictionary.key.size.threshold</name>
+    <value>0.8</value>
+    <description>
+      If the number of keys in a dictionary is greater than this fraction of the total number of
+      non-null rows, turn off dictionary encoding.  Use 1 to always use dictionary encoding.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.default.row.index.stride</name>
+    <value>10000</value>
+    <description>
+      Define the default ORC index stride in number of rows. (Stride is the number of rows
+      an index entry represents.)
+    </description>
+  </property>
+  <property>
+    <name>hive.orc.row.index.stride.dictionary.check</name>
+    <value>true</value>
+    <description>
+      If enabled dictionary check will happen after first row index stride (default 10000 rows)
+      else dictionary check will happen before writing first stripe. In both cases, the decision
+      to use dictionary or not will be retained thereafter.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.default.buffer.size</name>
+    <value>262144</value>
+    <description>Define the default ORC buffer size, in bytes.</description>
+  </property>
+  <property>
+    <name>hive.exec.orc.base.delta.ratio</name>
+    <value>8</value>
+    <description>
+      The ratio of base writer and
+      delta writer in terms of STRIPE_SIZE and BUFFER_SIZE.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.default.block.padding</name>
+    <value>true</value>
+    <description>Define the default block padding, which pads stripes to the HDFS block boundaries.</description>
+  </property>
+  <property>
+    <name>hive.exec.orc.block.padding.tolerance</name>
+    <value>0.05</value>
+    <description>
+      Define the tolerance for block padding as a decimal fraction of stripe size (for
+      example, the default value 0.05 is 5% of the stripe size). For the defaults of 64Mb
+      ORC stripe and 256Mb HDFS blocks, the default block padding tolerance of 5% will
+      reserve a maximum of 3.2Mb for padding within the 256Mb block. In that case, if the
+      available size within the block is more than 3.2Mb, a new smaller stripe will be
+      inserted to fit within that space. This will make sure that no stripe written will
+      cross block boundaries and cause remote reads within a node local task.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.default.compress</name>
+    <value>ZLIB</value>
+    <description>Define the default compression codec for ORC file</description>
+  </property>
+  <property>
+    <name>hive.exec.orc.encoding.strategy</name>
+    <value>SPEED</value>
+    <description>
+      Expects one of [speed, compression].
+      Define the encoding strategy to use while writing data. Changing this will
+      only affect the light weight encoding for integers. This flag will not
+      change the compression level of higher level compression codec (like ZLIB).
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.compression.strategy</name>
+    <value>SPEED</value>
+    <description>
+      Expects one of [speed, compression].
+      Define the compression strategy to use while writing data. 
+      This changes the compression level of higher level compression codec (like ZLIB).
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.split.strategy</name>
+    <value>HYBRID</value>
+    <description>
+      Expects one of [hybrid, bi, etl].
+      This is not a user level config. BI strategy is used when the requirement is to spend less time in split generation as opposed to query execution (split generation does not read or cache file footers). ETL strategy is used when spending little more time in split generation is acceptable (split generation reads and caches file footers). HYBRID chooses between the above strategies based on heuristics.
+    </description>
+  </property>
+  <property>
+    <name>hive.orc.splits.ms.footer.cache.enabled</name>
+    <value>false</value>
+    <description>Whether to enable using file metadata cache in metastore for ORC file footers.</description>
+  </property>
+  <property>
+    <name>hive.orc.splits.ms.footer.cache.ppd.enabled</name>
+    <value>true</value>
+    <description>
+      Whether to enable file footer cache PPD (hive.orc.splits.ms.footer.cache.enabled
+      must also be set to true for this to work).
+    </description>
+  </property>
+  <property>
+    <name>hive.orc.splits.include.file.footer</name>
+    <value>false</value>
+    <description>
+      If turned on splits generated by orc will include metadata about the stripes in the file. This
+      data is read remotely (from the client or HS2 machine) and sent to all the tasks.
+    </description>
+  </property>
+  <property>
+    <name>hive.orc.splits.directory.batch.ms</name>
+    <value>0</value>
+    <description>
+      How long, in ms, to wait to batch input directories for processing during ORC split
+      generation. 0 means process directories individually. This can increase the number of
+      metastore calls if metastore metadata cache is used.
+    </description>
+  </property>
+  <property>
+    <name>hive.orc.splits.include.fileid</name>
+    <value>true</value>
+    <description>Include file ID in splits on file systems that support it.</description>
+  </property>
+  <property>
+    <name>hive.orc.splits.allow.synthetic.fileid</name>
+    <value>true</value>
+    <description>Allow synthetic file ID in splits on file systems that don't have a native one.</description>
+  </property>
+  <property>
+    <name>hive.orc.cache.stripe.details.size</name>
+    <value>10000</value>
+    <description>Max cache size for keeping meta info about orc splits cached in the client.</description>
+  </property>
+  <property>
+    <name>hive.orc.compute.splits.num.threads</name>
+    <value>10</value>
+    <description>How many threads orc should use to create splits in parallel.</description>
+  </property>
+  <property>
+    <name>hive.orc.cache.use.soft.references</name>
+    <value>false</value>
+    <description>
+      By default, the cache that ORC input format uses to store orc file footer use hard
+      references for the cached object. Setting this to true can help avoid out of memory
+      issues under memory pressure (in some cases) at the cost of slight unpredictability in
+      overall query performance.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.skip.corrupt.data</name>
+    <value>false</value>
+    <description>
+      If ORC reader encounters corrupt data, this value will be used to determine
+      whether to skip the corrupt data or throw exception. The default behavior is to throw exception.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.zerocopy</name>
+    <value>false</value>
+    <description>Use zerocopy reads with ORC. (This requires Hadoop 2.3 or later.)</description>
+  </property>
+  <property>
+    <name>hive.lazysimple.extended_boolean_literal</name>
+    <value>false</value>
+    <description>
+      LazySimpleSerde uses this property to determine if it treats 'T', 't', 'F', 'f',
+      '1', and '0' as extened, legal boolean literal, in addition to 'TRUE' and 'FALSE'.
+      The default is false, which means only 'TRUE' and 'FALSE' are treated as legal
+      boolean literal.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.skewjoin</name>
+    <value>false</value>
+    <description>
+      Whether to enable skew join optimization. 
+      The algorithm is as follows: At runtime, detect the keys with a large skew. Instead of
+      processing those keys, store them temporarily in an HDFS directory. In a follow-up map-reduce
+      job, process those skewed keys. The same key need not be skewed for all the tables, and so,
+      the follow-up map-reduce job (for the skewed keys) would be much faster, since it would be a
+      map-join.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.dynamic.partition.hashjoin</name>
+    <value>false</value>
+    <description>
+      Whether to enable dynamically partitioned hash join optimization. 
+      This setting is also dependent on enabling hive.auto.convert.join
+    </description>
+  </property>
+  <property>
+    <name>hive.auto.convert.join</name>
+    <value>true</value>
+    <description>Whether Hive enables the optimization about converting common join into mapjoin based on the input file size</description>
+  </property>
+  <property>
+    <name>hive.auto.convert.join.noconditionaltask</name>
+    <value>true</value>
+    <description>
+      Whether Hive enables the optimization about converting common join into mapjoin based on the input file size. 
+      If this parameter is on, and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than the
+      specified size, the join is directly converted to a mapjoin (there is no conditional task).
+    </description>
+  </property>
+  <property>
+    <name>hive.auto.convert.join.noconditionaltask.size</name>
+    <value>10000000</value>
+    <description>
+      If hive.auto.convert.join.noconditionaltask is off, this parameter does not take affect. 
+      However, if it is on, and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than this size, 
+      the join is directly converted to a mapjoin(there is no conditional task). The default is 10MB
+    </description>
+  </property>
+  <property>
+    <name>hive.auto.convert.join.use.nonstaged</name>
+    <value>false</value>
+    <description>
+      For conditional joins, if input stream from a small alias can be directly applied to join operator without 
+      filtering or projection, the alias need not to be pre-staged in distributed cache via mapred local task.
+      Currently, this is not working with vectorization or tez execution engine.
+    </description>
+  </property>
+  <property>
+    <name>hive.skewjoin.key</name>
+    <value>100000</value>
+    <description>
+      Determine if we get a skew key in join. If we see more than the specified number of rows with the same key in join operator,
+      we think the key as a skew join key. 
+    </description>
+  </property>
+  <property>
+    <name>hive.skewjoin.mapjoin.map.tasks</name>
+    <value>10000</value>
+    <description>
+      Determine the number of map task used in the follow up map join job for a skew join.
+      It should be used together with hive.skewjoin.mapjoin.min.split to perform a fine grained control.
+    </description>
+  </property>
+  <property>
+    <name>hive.skewjoin.mapjoin.min.split</name>
+    <value>33554432</value>
+    <description>
+      Determine the number of map task at most used in the follow up map join job for a skew join by specifying 
+      the minimum split size. It should be used together with hive.skewjoin.mapjoin.map.tasks to perform a fine grained control.
+    </description>
+  </property>
+  <property>
+    <name>hive.heartbeat.interval</name>
+    <value>1000</value>
+    <description>Send a heartbeat after this interval - used by mapjoin and filter operators</description>
+  </property>
+  <property>
+    <name>hive.limit.row.max.size</name>
+    <value>100000</value>
+    <description>When trying a smaller subset of data for simple LIMIT, how much size we need to guarantee each row to have at least.</description>
+  </property>
+  <property>
+    <name>hive.limit.optimize.limit.file</name>
+    <value>10</value>
+    <description>When trying a smaller subset of data for simple LIMIT, maximum number of files we can sample.</description>
+  </property>
+  <property>
+    <name>hive.limit.optimize.enable</name>
+    <value>false</value>
+    <description>Whether to enable to optimization to trying a smaller subset of data for simple LIMIT first.</description>
+  </property>
+  <property>
+    <name>hive.limit.optimize.fetch.max</name>
+    <value>50000</value>
+    <description>
+      Maximum number of rows allowed for a smaller subset of data for simple LIMIT, if it is a fetch query. 
+      Insert queries are not restricted by this limit.
+    </description>
+  </property>
+  <property>
+    <name>hive.limit.pushdown.memory.usage</name>
+    <value>0.1</value>
+    <description>
+      Expects value between 0.0f and 1.0f.
+      The fraction of available memory to be used for buffering rows in Reducesink operator for limit pushdown optimization.
+    </description>
+  </property>
+  <property>
+    <name>hive.limit.query.max.table.partition</name>
+    <value>-1</value>
+    <description>
+      This controls how many partitions can be scanned for each partitioned table.
+      The default value "-1" means no limit.
+    </description>
+  </property>
+  <property>
+    <name>hive.hashtable.key.count.adjustment</name>
+    <value>1.0</value>
+    <description>Adjustment to mapjoin hashtable size derived from table and column statistics; the estimate of the number of keys is divided by this value. If the value is 0, statistics are not usedand hive.hashtable.initialCapacity is used instead.</description>
+  </property>
+  <property>
+    <name>hive.hashtable.initialCapacity</name>
+    <value>100000</value>
+    <description>Initial capacity of mapjoin hashtable if statistics are absent, or if hive.hashtable.key.count.adjustment is set to 0</description>
+  </property>
+  <property>
+    <name>hive.hashtable.loadfactor</name>
+    <value>0.75</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.mapjoin.followby.gby.localtask.max.memory.usage</name>
+    <value>0.55</value>
+    <description>
+      This number means how much memory the local task can take to hold the key/value into an in-memory hash table 
+      when this map join is followed by a group by. If the local task's memory usage is more than this number, 
+      the local task will abort by itself. It means the data of the small table is too large to be held in memory.
+    </description>
+  </property>
+  <property>
+    <name>hive.mapjoin.localtask.max.memory.usage</name>
+    <value>0.9</value>
+    <description>
+      This number means how much memory the local task can take to hold the key/value into an in-memory hash table. 
+      If the local task's memory usage is more than this number, the local task will abort by itself. 
+      It means the data of the small table is too large to be held in memory.
+    </description>
+  </property>
+  <property>
+    <name>hive.mapjoin.check.memory.rows</name>
+    <value>100000</value>
+    <description>The number means after how many rows processed it needs to check the memory usage</description>
+  </property>
+  <property>
+    <name>hive.debug.localtask</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.input.format</name>
+    <value>org.apache.hadoop.hive.ql.io.CombineHiveInputFormat</value>
+    <description>The default input format. Set this to HiveInputFormat if you encounter problems with CombineHiveInputFormat.</description>
+  </property>
+  <property>
+    <name>hive.tez.input.format</name>
+    <value>org.apache.hadoop.hive.ql.io.HiveInputFormat</value>
+    <description>The default input format for tez. Tez groups splits in the AM.</description>
+  </property>
+  <property>
+    <name>hive.tez.container.size</name>
+    <value>-1</value>
+    <description>By default Tez will spawn containers of the size of a mapper. This can be used to overwrite.</description>
+  </property>
+  <property>
+    <name>hive.tez.cpu.vcores</name>
+    <value>-1</value>
+    <description>
+      By default Tez will ask for however many cpus map-reduce is configured to use per container.
+      This can be used to overwrite.
+    </description>
+  </property>
+  <property>
+    <name>hive.tez.java.opts</name>
+    <value/>
+    <description>By default Tez will use the Java options from map tasks. This can be used to overwrite.</description>
+  </property>
+  <property>
+    <name>hive.tez.log.level</name>
+    <value>INFO</value>
+    <description>
+      The log level to use for tasks executing as part of the DAG.
+      Used only if hive.tez.java.opts is used to configure Java options.
+    </description>
+  </property>
+  <property>
+    <name>hive.query.name</name>
+    <value/>
+    <description>
+      This named is used by Tez to set the dag name. This name in turn will appear on 
+      the Tez UI representing the work that was done.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.bucketingsorting</name>
+    <value>true</value>
+    <description>
+      Don't create a reducer for enforcing 
+      bucketing/sorting for queries of the form: 
+      insert overwrite table T2 select * from T1;
+      where T1 and T2 are bucketed/sorted by the same keys into the same number of buckets.
+    </description>
+  </property>
+  <property>
+    <name>hive.mapred.partitioner</name>
+    <value>org.apache.hadoop.hive.ql.io.DefaultHivePartitioner</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.enforce.sortmergebucketmapjoin</name>
+    <value>false</value>
+    <description>If the user asked for sort-merge bucketed map-side join, and it cannot be performed, should the query fail or not ?</description>
+  </property>
+  <property>
+    <name>hive.enforce.bucketmapjoin</name>
+    <value>false</value>
+    <description>
+      If the user asked for bucketed map-side join, and it cannot be performed, 
+      should the query fail or not ? For example, if the buckets in the tables being joined are
+      not a multiple of each other, bucketed map-side join cannot be performed, and the
+      query will fail if hive.enforce.bucketmapjoin is set to true.
+    </description>
+  </property>
+  <property>
+    <name>hive.auto.convert.sortmerge.join</name>
+    <value>false</value>
+    <description>Will the join be automatically converted to a sort-merge join, if the joined tables pass the criteria for sort-merge join.</description>
+  </property>
+  <property>
+    <name>hive.auto.convert.sortmerge.join.bigtable.selection.policy</name>
+    <value>org.apache.hadoop.hive.ql.optimizer.AvgPartitionSizeBasedBigTableSelectorForAutoSMJ</value>
+    <description>
+      The policy to choose the big table for automatic conversion to sort-merge join. 
+      By default, the table with the largest partitions is assigned the big table. All policies are:
+      . based on position of the table - the leftmost table is selected
+      org.apache.hadoop.hive.ql.optimizer.LeftmostBigTableSMJ.
+      . based on total size (all the partitions selected in the query) of the table 
+      org.apache.hadoop.hive.ql.optimizer.TableSizeBasedBigTableSelectorForAutoSMJ.
+      . based on average size (all the partitions selected in the query) of the table 
+      org.apache.hadoop.hive.ql.optimizer.AvgPartitionSizeBasedBigTableSelectorForAutoSMJ.
+      New policies can be added in future.
+    </description>
+  </property>
+  <property>
+    <name>hive.auto.convert.sortmerge.join.to.mapjoin</name>
+    <value>false</value>
+    <description>
+      If hive.auto.convert.sortmerge.join is set to true, and a join was converted to a sort-merge join, 
+      this parameter decides whether each table should be tried as a big table, and effectively a map-join should be
+      tried. That would create a conditional task with n+1 children for a n-way join (1 child for each table as the
+      big table), and the backup task will be the sort-merge join. In some cases, a map-join would be faster than a
+      sort-merge join, if there is no advantage of having the output bucketed and sorted. For example, if a very big sorted
+      and bucketed table with few files (say 10 files) are being joined with a very small sorter and bucketed table
+      with few files (10 files), the sort-merge join will only use 10 mappers, and a simple map-only join might be faster
+      if the complete small table can fit in memory, and a map-join can be performed.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.script.trust</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.rowoffset</name>
+    <value>false</value>
+    <description>Whether to provide the row offset virtual column</description>
+  </property>
+  <property>
+    <name>hive.optimize.index.filter</name>
+    <value>false</value>
+    <description>Whether to enable automatic use of indexes</description>
+  </property>
+  <property>
+    <name>hive.optimize.index.autoupdate</name>
+    <value>false</value>
+    <description>Whether to update stale indexes automatically</description>
+  </property>
+  <property>
+    <name>hive.optimize.ppd</name>
+    <value>true</value>
+    <description>Whether to enable predicate pushdown</description>
+  </property>
+  <property>
+    <name>hive.optimize.ppd.windowing</name>
+    <value>true</value>
+    <description>Whether to enable predicate pushdown through windowing</description>
+  </property>
+  <property>
+    <name>hive.ppd.recognizetransivity</name>
+    <value>true</value>
+    <description>Whether to transitively replicate predicate filters over equijoin conditions.</description>
+  </property>
+  <property>
+    <name>hive.ppd.remove.duplicatefilters</name>
+    <value>true</value>
+    <description>
+      During query optimization, filters may be pushed down in the operator tree. 
+      If this config is true only pushed down filters remain in the operator tree, 
+      and the original filter is removed. If this config is false, the original filter 
+      is also left in the operator tree at the original place.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.point.lookup</name>
+    <value>true</value>
+    <description>Whether to transform OR clauses in Filter operators into IN clauses</description>
+  </property>
+  <property>
+    <name>hive.optimize.point.lookup.min</name>
+    <value>31</value>
+    <description>Minimum number of OR clauses needed to transform into IN clauses</description>
+  </property>
+  <property>
+    <name>hive.optimize.partition.columns.separate</name>
+    <value>true</value>
+    <description>Extract partition columns from IN clauses</description>
+  </property>
+  <property>
+    <name>hive.optimize.constant.propagation</name>
+    <value>true</value>
+    <description>Whether to enable constant propagation optimizer</description>
+  </property>
+  <property>
+    <name>hive.optimize.remove.identity.project</name>
+    <value>true</value>
+    <description>Removes identity project from operator tree</description>
+  </property>
+  <property>
+    <name>hive.optimize.metadataonly</name>
+    <value>true</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.optimize.null.scan</name>
+    <value>true</value>
+    <description>Dont scan relations which are guaranteed to not generate any rows</description>
+  </property>
+  <property>
+    <name>hive.optimize.ppd.storage</name>
+    <value>true</value>
+    <description>Whether to push predicates down to storage handlers</description>
+  </property>
+  <property>
+    <name>hive.optimize.groupby</name>
+    <value>true</value>
+    <description>Whether to enable the bucketed group by from bucketed partitions/tables.</description>
+  </property>
+  <property>
+    <name>hive.optimize.bucketmapjoin</name>
+    <value>false</value>
+    <description>Whether to try bucket mapjoin</description>
+  </property>
+  <property>
+    <name>hive.optimize.bucketmapjoin.sortedmerge</name>
+    <value>false</value>
+    <description>Whether to try sorted bucket merge map join</description>
+  </property>
+  <property>
+    <name>hive.optimize.reducededuplication</name>
+    <value>true</value>
+    <description>
+      Remove extra map-reduce jobs if the data is already clustered by the same key which needs to be used again. 
+      This should always be set to true. Since it is a new feature, it has been made configurable.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.reducededuplication.min.reducer</name>
+    <value>4</value>
+    <description>
+      Reduce deduplication merges two RSs by moving key/parts/reducer-num of the child RS to parent RS. 
+      That means if reducer-num of the child RS is fixed (order by or forced bucketing) and small, it can make very slow, single MR.
+      The optimization will be automatically disabled if number of reducers would be less than specified value.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.sort.dynamic.partition</name>
+    <value>false</value>
+    <description>
+      When enabled dynamic partitioning column will be globally sorted.
+      This way we can keep only one record writer open for each partition value
+      in the reducer thereby reducing the memory pressure on reducers.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.sampling.orderby</name>
+    <value>false</value>
+    <description>Uses sampling on order-by clause for parallel execution.</description>
+  </property>
+  <property>
+    <name>hive.optimize.sampling.orderby.number</name>
+    <value>1000</value>
+    <description>Total number of samples to be obtained.</description>
+  </property>
+  <property>
+    <name>hive.optimize.sampling.orderby.percent</name>
+    <value>0.1</value>
+    <description>
+      Expects value between 0.0f and 1.0f.
+      Probability with which a row will be chosen.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.distinct.rewrite</name>
+    <value>true</value>
+    <description>When applicable this optimization rewrites distinct aggregates from a single stage to multi-stage aggregation. This may not be optimal in all cases. Ideally, whether to trigger it or not should be cost based decision. Until Hive formalizes cost model for this, this is config driven.</description>
+  </property>
+  <property>
+    <name>hive.optimize.union.remove</name>
+    <value>false</value>
+    <description>
+      Whether to remove the union and push the operators between union and the filesink above union. 
+      This avoids an extra scan of the output by union. This is independently useful for union
+      queries, and specially useful when hive.optimize.skewjoin.compiletime is set to true, since an
+      extra union is inserted.
+      
+      The merge is triggered if either of hive.merge.mapfiles or hive.merge.mapredfiles is set to true.
+      If the user has set hive.merge.mapfiles to true and hive.merge.mapredfiles to false, the idea was the
+      number of reducers are few, so the number of files anyway are small. However, with this optimization,
+      we are increasing the number of files possibly by a big margin. So, we merge aggressively.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.correlation</name>
+    <value>false</value>
+    <description>exploit intra-query correlations.</description>
+  </property>
+  <property>
+    <name>hive.optimize.limittranspose</name>
+    <value>false</value>
+    <description>
+      Whether to push a limit through left/right outer join or union. If the value is true and the size of the outer
+      input is reduced enough (as specified in hive.optimize.limittranspose.reduction), the limit is pushed
+      to the outer input or union; to remain semantically correct, the limit is kept on top of the join or the union too.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.limittranspose.reductionpercentage</name>
+    <value>1.0</value>
+    <description>
+      When hive.optimize.limittranspose is true, this variable specifies the minimal reduction of the
+      size of the outer input of the join or input of the union that we should get in order to apply the rule.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.limittranspose.reductiontuples</name>
+    <value>0</value>
+    <description>
+      When hive.optimize.limittranspose is true, this variable specifies the minimal reduction in the
+      number of tuples of the outer input of the join or the input of the union that you should get in order to apply the rule.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.filter.stats.reduction</name>
+    <value>false</value>
+    <description>
+      Whether to simplify comparison
+      expressions in filter operators using column stats
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.skewjoin.compiletime</name>
+    <value>false</value>
+    <description>
+      Whether to create a separate plan for skewed keys for the tables in the join.
+      This is based on the skewed keys stored in the metadata. At compile time, the plan is broken
+      into different joins: one for the skewed keys, and the other for the remaining keys. And then,
+      a union is performed for the 2 joins generated above. So unless the same skewed key is present
+      in both the joined tables, the join for the skewed key will be performed as a map-side join.
+      
+      The main difference between this parameter and hive.optimize.skewjoin is that this parameter
+      uses the skew information stored in the metastore to optimize the plan at compile time itself.
+      If there is no skew information in the metadata, this parameter will not have any affect.
+      Both hive.optimize.skewjoin.compiletime and hive.optimize.skewjoin should be set to true.
+      Ideally, hive.optimize.skewjoin should be renamed as hive.optimize.skewjoin.runtime, but not doing
+      so for backward compatibility.
+      
+      If the skew information is correctly stored in the metadata, hive.optimize.skewjoin.compiletime
+      would change the query plan to take care of it, and hive.optimize.skewjoin will be a no-op.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.cte.materialize.threshold</name>
+    <value>-1</value>
+    <description>
+      If the number of references to a CTE clause exceeds this threshold, Hive will materialize it
+      before executing the main query block. -1 will disable this feature.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.index.filter.compact.minsize</name>
+    <value>5368709120</value>
+    <description>Minimum size (in bytes) of the inputs on which a compact index is automatically used.</description>
+  </property>
+  <property>
+    <name>hive.optimize.index.filter.compact.maxsize</name>
+    <value>-1</value>
+    <description>Maximum size (in bytes) of the inputs on which a compact index is automatically used.  A negative number is equivalent to infinity.</description>
+  </property>
+  <property>
+    <name>hive.index.compact.query.max.entries</name>
+    <value>10000000</value>
+    <description>The maximum number of index entries to read during a query that uses the compact index. Negative value is equivalent to infinity.</description>
+  </property>
+  <property>
+    <name>hive.index.compact.query.max.size</name>
+    <value>10737418240</value>
+    <description>The maximum number of bytes that a query using the compact index can read. Negative value is equivalent to infinity.</description>
+  </property>
+  <property>
+    <name>hive.index.compact.binary.search</name>
+    <value>true</value>
+    <description>Whether or not to use a binary search to find the entries in an index table that match the filter, where possible</description>
+  </property>
+  <property>
+    <name>hive.stats.autogather</name>
+    <value>true</value>
+    <description>A flag to gather statistics (only basic) automatically during the INSERT OVERWRITE command.</description>
+  </property>
+  <property>
+    <name>hive.stats.column.autogather</name>
+    <value>false</value>
+    <description>A flag to gather column statistics automatically.</description>
+  </property>
+  <property>
+    <name>hive.stats.dbclass</name>
+    <value>fs</value>
+    <description>
+      Expects one of the pattern in [custom, fs].
+      The storage that stores temporary Hive statistics. In filesystem based statistics collection ('fs'), 
+      each task writes statistics it has collected in a file on the filesystem, which will be aggregated 
+      after the job has finished. Supported values are fs (filesystem) and custom as defined in StatsSetupConst.java.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.default.publisher</name>
+    <value/>
+    <description>The Java class (implementing the StatsPublisher interface) that is used by default if hive.stats.dbclass is custom type.</description>
+  </property>
+  <property>
+    <name>hive.stats.default.aggregator</name>
+    <value/>
+    <description>The Java class (implementing the StatsAggregator interface) that is used by default if hive.stats.dbclass is custom type.</description>
+  </property>
+  <property>
+    <name>hive.stats.atomic</name>
+    <value>false</value>
+    <description>whether to update metastore stats only if all stats are available</description>
+  </property>
+  <property>
+    <name>hive.client.stats.counters</name>
+    <value/>
+    <description>
+      Subset of counters that should be of interest for hive.client.stats.publishers (when one wants to limit their publishing). 
+      Non-display names should be used
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.reliable</name>
+    <value>false</value>
+    <description>
+      Whether queries will fail because stats cannot be collected completely accurately. 
+      If this is set to true, reading/writing from/into a partition may fail because the stats
+      could not be computed accurately.
+    </description>
+  </property>
+  <property>
+    <name>hive.analyze.stmt.collect.partlevel.stats</name>
+    <value>true</value>
+    <description>analyze table T compute statistics for columns. Queries like these should compute partitionlevel stats for partitioned table even when no part spec is specified.</description>
+  </property>
+  <property>
+    <name>hive.stats.gather.num.threads</name>
+    <value>10</value>
+    <description>
+      Number of threads used by partialscan/noscan analyze command for partitioned tables.
+      This is applicable only for file formats that implement StatsProvidingRecordReader (like ORC).
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.collect.tablekeys</name>
+    <value>false</value>
+    <description>
+      Whether join and group by keys on tables are derived and maintained in the QueryPlan.
+      This is useful to identify how tables are accessed and to determine if they should be bucketed.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.collect.scancols</name>
+    <value>false</value>
+    <description>
+      Whether column accesses are tracked in the QueryPlan.
+      This is useful to identify how tables are accessed and to determine if there are wasted columns that can be trimmed.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.ndv.error</name>
+    <value>20.0</value>
+    <description>
+      Standard error expressed in percentage. Provides a tradeoff between accuracy and compute cost. 
+      A lower value for error indicates higher accuracy and a higher compute cost.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.stats.ndv.densityfunction</name>
+    <value>false</value>
+    <description>Whether to use density function to estimate the NDV for the whole table based on the NDV of partitions</description>
+  </property>
+  <property>
+    <name>hive.stats.max.variable.length</name>
+    <value>100</value>
+    <description>
+      To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.),
+      average row size is multiplied with the total number of rows coming out of each operator.
+      Average row size is computed from average column size of all columns in the row. In the absence
+      of column statistics, for variable length columns (like string, bytes etc.), this value will be
+      used. For fixed length columns their corresponding Java equivalent sizes are used
+      (float - 4 bytes, double - 8 bytes etc.).
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.list.num.entries</name>
+    <value>10</value>
+    <description>
+      To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.),
+      average row size is multiplied with the total number of rows coming out of each operator.
+      Average row size is computed from average column size of all columns in the row. In the absence
+      of column statistics and for variable length complex columns like list, the average number of
+      entries/values can be specified using this config.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.map.num.entries</name>
+    <value>10</value>
+    <description>
+      To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.),
+      average row size is multiplied with the total number of rows coming out of each operator.
+      Average row size is computed from average column size of all columns in the row. In the absence
+      of column statistics and for variable length complex columns like map, the average number of
+      entries/values can be specified using this config.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.fetch.partition.stats</name>
+    <value>true</value>
+    <description>
+      Annotation of operator tree with statistics information requires partition level basic
+      statistics like number of rows, data size and file size. Partition statistics are fetched from
+      metastore. Fetching partition statistics for each needed partition can be expensive when the
+      number of partitions is high. This flag can be used to disable fetching of partition statistics
+      from metastore. When this flag is disabled, Hive will make calls to filesystem to get file sizes
+      and will estimate the number of rows from row schema.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.fetch.column.stats</name>
+    <value>false</value>
+    <description>
+      Annotation of operator tree with statistics information requires column statistics.
+      Column statistics are fetched from metastore. Fetching column statistics for each needed column
+      can be expensive when the number of columns is high. This flag can be used to disable fetching
+      of column statistics from metastore.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.join.factor</name>
+    <value>1.1</value>
+    <description>
+      Hive/Tez optimizer estimates the data size flowing through each of the operators. JOIN operator
+      uses column statistics to estimate the number of rows flowing out of it and hence the data size.
+      In the absence of column statistics, this factor determines the amount of rows that flows out
+      of JOIN operator.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.deserialization.factor</name>
+    <value>1.0</value>
+    <description>
+      Hive/Tez optimizer estimates the data size flowing through each of the operators. In the absence
+      of basic statistics like number of rows and data size, file size is used to estimate the number
+      of rows and data size. Since files in tables/partitions are serialized (and optionally
+      compressed) the estimates of number of rows and data size cannot be reliably determined.
+      This factor is multiplied with the file size to account for serialization and compression.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.filter.in.factor</name>
+    <value>1.0</value>
+    <description>
+      Currently column distribution is assumed to be uniform. This can lead to overestimation/underestimation
+      in the number of rows filtered by a certain operator, which in turn might lead to overprovision or
+      underprovision of resources. This factor is applied to the cardinality estimation of IN clauses in
+      filter operators.
+    </description>
+  </property>
+  <property>
+    <name>hive.support.concurrency</name>
+    <value>false</value>
+    <description>
+      Whether Hive supports concurrency control or not. 
+      A ZooKeeper instance must be up and running when using zookeeper Hive lock manager 
+    </description>
+  </property>
+  <property>
+    <name>hive.lock.manager</name>
+    <value>org.apache.hadoop.hive.ql.lockmgr.zookeeper.ZooKeeperHiveLockManager</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.lock.numretries</name>
+    <value>100</value>
+    <description>The number of times you want to try to get all the locks</description>
+  </property>
+  <property>
+    <name>hive.unlock.numretries</name>
+    <value>10</value>
+    <description>The number of times you want to retry to do one unlock</description>
+  </property>
+  <property>
+    <name>hive.lock.sleep.between.retries</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      The time should be in between 0 sec (exclusive) and 9223372036854775807 sec (exclusive).
+      The maximum sleep time between various retries
+    </description>
+  </property>
+  <property>
+    <name>hive.lock.mapred.only.operation</name>
+    <value>false</value>
+    <description>
+      This param is to control whether or not only do lock on queries
+      that need to execute at least one mapred job.
+    </description>
+  </property>
+  <property>
+    <name>hive.zookeeper.quorum</name>
+    <value/>
+    <description>
+      List of ZooKeeper servers to talk to. This is needed for: 
+      1. Read/write locks - when hive.lock.manager is set to 
+      org.apache.hadoop.hive.ql.lockmgr.zookeeper.ZooKeeperHiveLockManager, 
+      2. When HiveServer2 supports service discovery via Zookeeper.
+      3. For delegation token storage if zookeeper store is used, if
+      hive.cluster.delegation.token.store.zookeeper.connectString is not set
+      4. LLAP daemon registry service
+    </description>
+  </property>
+  <property>
+    <name>hive.zookeeper.client.port</name>
+    <value>2181</value>
+    <description>
+      The port of ZooKeeper servers to talk to.
+      If the list of Zookeeper servers specified in hive.zookeeper.quorum
+      does not contain port numbers, this value is used.
+    </description>
+  </property>
+  <property>
+    <name>hive.zookeeper.session.timeout</name>
+    <value>1200000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      ZooKeeper client's session timeout (in milliseconds). The client is disconnected, and as a result, all locks released, 
+      if a heartbeat is not sent in the timeout.
+    </description>
+  </property>
+  <property>
+    <name>hive.zookeeper.namespace</name>
+    <value>hive_zookeeper_namespace</value>
+    <description>The parent node under which all ZooKeeper nodes are created.</description>
+  </property>
+  <property>
+    <name>hive.zookeeper.clean.extra.nodes</name>
+    <value>false</value>
+    <description>Clean extra nodes at the end of the session.</description>
+  </property>
+  <property>
+    <name>hive.zookeeper.connection.max.retries</name>
+    <value>3</value>
+    <description>Max number of times to retry when connecting to the ZooKeeper server.</description>
+  </property>
+  <property>
+    <name>hive.zookeeper.connection.basesleeptime</name>
+    <value>1000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Initial amount of time (in milliseconds) to wait between retries
+      when connecting to the ZooKeeper server when using ExponentialBackoffRetry policy.
+    </description>
+  </property>
+  <property>
+    <name>hive.txn.manager</name>
+    <value>org.apache.hadoop.hive.ql.lockmgr.DummyTxnManager</value>
+    <description>
+      Set to org.apache.hadoop.hive.ql.lockmgr.DbTxnManager as part of turning on Hive
+      transactions, which also requires appropriate settings for hive.compactor.initiator.on,
+      hive.compactor.worker.threads, hive.support.concurrency (true), hive.enforce.bucketing
+      (true), and hive.exec.dynamic.partition.mode (nonstrict).
+      The default DummyTxnManager replicates pre-Hive-0.13 behavior and provides
+      no transactions.
+    </description>
+  </property>
+  <property>
+    <name>hive.txn.timeout</name>
+    <value>300s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      time after which transactions are declared aborted if the client has not sent a heartbeat.
+    </description>
+  </property>
+  <property>
+    <name>hive.txn.heartbeat.threadpool.size</name>
+    <value>5</value>
+    <description>The number of threads to use for heartbeating. For Hive CLI, 1 is enough. For HiveServer2, we need a few</description>
+  </property>
+  <property>
+    <name>hive.txn.manager.dump.lock.state.on.acquire.timeout</name>
+    <value>false</value>
+    <description>Set this to true so that when attempt to acquire a lock on resource times out, the current state of the lock manager is dumped to log file.  This is for debugging.  See also hive.lock.numretries and hive.lock.sleep.between.retries.</description>
+  </property>
+  <property>
+    <name>hive.max.open.txns</name>
+    <value>100000</value>
+    <description>
+      Maximum number of open transactions. If 
+      current open transactions reach this limit, future open transaction requests will be 
+      rejected, until this number goes below the limit.
+    </description>
+  </property>
+  <property>
+    <name>hive.count.open.txns.interval</name>
+    <value>1s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Time in seconds between checks to count open transactions.
+    </description>
+  </property>
+  <property>
+    <name>hive.txn.max.open.batch</name>
+    <value>1000</value>
+    <description>
+      Maximum number of transactions that can be fetched in one call to open_txns().
+      This controls how many transactions streaming agents such as Flume or Storm open
+      simultaneously. The streaming agent then writes that number of entries into a single
+      file (per Flume agent or Storm bolt). Thus increasing this value decreases the number
+      of delta files created by streaming agents. But it also increases the number of open
+      transactions that Hive has to track at any given time, which may negatively affect
+      read performance.
+    </description>
+  </property>
+  <property>
+    <name>hive.txn.retryable.sqlex.regex</name>
+    <value/>
+    <description>
+      Comma separated list
+      of regular expression patterns for SQL state, error code, and error message of
+      retryable SQLExceptions, that's suitable for the metastore DB.
+      For example: Can't serialize.*,40001$,^Deadlock,.*ORA-08176.*
+      The string that the regex will be matched against is of the following form, where ex is a SQLException:
+      ex.getMessage() + " (SQLState=" + ex.getSQLState() + ", ErrorCode=" + ex.getErrorCode() + ")"
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.initiator.on</name>
+    <value>false</value>
+    <description>
+      Whether to run the initiator and cleaner threads on this metastore instance or not.
+      Set this to true on one instance of the Thrift metastore service as part of turning
+      on Hive transactions. For a complete list of parameters required for turning on
+      transactions, see hive.txn.manager.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.worker.threads</name>
+    <value>0</value>
+    <description>
+      How many compactor worker threads to run on this metastore instance. Set this to a
+      positive number on one or more instances of the Thrift metastore service as part of
+      turning on Hive transactions. For a complete list of parameters required for turning
+      on transactions, see hive.txn.manager.
+      Worker threads spawn MapReduce jobs to do compactions. They do not do the compactions
+      themselves. Increasing the number of worker threads will decrease the time it takes
+      tables or partitions to be compacted once they are determined to need compaction.
+      It will also increase the background load on the Hadoop cluster as more MapReduce jobs
+      will be running in the background.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.worker.timeout</name>
+    <value>86400s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Time in seconds after which a compaction job will be declared failed and the
+      compaction re-queued.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.check.interval</name>
+    <value>300s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Time in seconds between checks to see if any tables or partitions need to be
+      compacted. This should be kept high because each check for compaction requires
+      many calls against the NameNode.
+      Decreasing this value will reduce the time it takes for compaction to be started
+      for a table or partition that requires compaction. However, checking if compaction
+      is needed requires several calls to the NameNode for each table or partition that
+      has had a transaction done on it since the last major compaction. So decreasing this
+      value will increase the load on the NameNode.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.delta.num.threshold</name>
+    <value>10</value>
+    <description>
+      Number of delta directories in a table or partition that will trigger a minor
+      compaction.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.delta.pct.threshold</name>
+    <value>0.1</value>
+    <description>
+      Percentage (fractional) size of the delta files relative to the base that will trigger
+      a major compaction. (1.0 = 100%, so the default 0.1 = 10%.)
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.max.num.delta</name>
+    <value>500</value>
+    <description>Maximum number of delta files that the compactor will attempt to handle in a single job.</description>
+  </property>
+  <property>
+    <name>hive.compactor.abortedtxn.threshold</name>
+    <value>1000</value>
+    <description>
+      Number of aborted transactions involving a given table or partition that will trigger
+      a major compaction.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.initiator.failed.compacts.threshold</name>
+    <value>2</value>
+    <description>
+      Expects value between 1 and 20.
+      Number of consecutive compaction failures (per table/partition) after which automatic compactions will not be scheduled any more.  Note that this must be less than hive.compactor.history.retention.failed.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.cleaner.run.interval</name>
+    <value>5000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Time between runs of the cleaner thread
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.job.queue</name>
+    <value/>
+    <description>
+      Used to specify name of Hadoop queue to which
+      Compaction jobs will be submitted.  Set to empty string to let Hadoop choose the queue.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.history.retention.succeeded</name>
+    <value>3</value>
+    <description>
+      Expects value between 0 and 100.
+      Determines how many successful compaction records will be retained in compaction history for a given table/partition.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.history.retention.failed</name>
+    <value>3</value>
+    <description>
+      Expects value between 0 and 100.
+      Determines how many failed compaction records will be retained in compaction history for a given table/partition.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.history.retention.attempted</name>
+    <value>2</value>
+    <description>
+      Expects value between 0 and 100.
+      Determines how many attempted compaction records will be retained in compaction history for a given table/partition.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.history.reaper.interval</name>
+    <value>2m</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Determines how often compaction history reaper runs
+    </description>
+  </property>
+  <property>
+    <name>hive.timedout.txn.reaper.start</name>
+    <value>100s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Time delay of 1st reaper run after metastore start
+    </description>
+  </property>
+  <property>
+    <name>hive.timedout.txn.reaper.interval</name>
+    <value>180s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Time interval describing how often the reaper runs
+    </description>
+  </property>
+  <property>
+    <name>hive.writeset.reaper.interval</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Frequency of WriteSet reaper runs
+    </description>
+  </property>
+  <property>
+    <name>hive.hbase.wal.enabled</name>
+    <value>true</value>
+    <description>
+      Whether writes to HBase should be forced to the write-ahead log. 
+      Disabling this improves HBase write performance at the risk of lost writes in case of a crash.
+    </description>
+  </property>
+  <property>
+    <name>hive.hbase.generatehfiles</name>
+    <value>false</value>
+    <description>True when HBaseStorageHandler should generate hfiles instead of operate against the online table.</description>
+  </property>
+  <property>
+    <name>hive.hbase.snapshot.name</name>
+    <value/>
+    <description>The HBase table snapshot name to use.</description>
+  </property>
+  <property>
+    <name>hive.hbase.snapshot.restoredir</name>
+    <value>/tmp</value>
+    <description>The directory in which to restore the HBase table snapshot.</description>
+  </property>
+  <property>
+    <name>hive.archive.enabled</name>
+    <value>false</value>
+    <description>Whether archiving operations are permitted</description>
+  </property>
+  <property>
+    <name>hive.optimize.index.groupby</name>
+    <value>false</value>
+    <description>Whether to enable optimization of group-by queries using Aggregate indexes.</description>
+  </property>
+  <property>
+    <name>hive.outerjoin.supports.filters</name>
+    <value>true</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.fetch.task.conversion</name>
+    <value>more</value>
+    <description>
+      Expects one of [none, minimal, more].
+      Some select queries can be converted to single FETCH task minimizing latency.
+      Currently the query should be single sourced not having any subquery and should not have
+      any aggregations or distincts (which incurs RS), lateral views and joins.
+      0. none : disable hive.fetch.task.conversion
+      1. minimal : SELECT STAR, FILTER on partition columns, LIMIT only
+      2. more    : SELECT, FILTER, LIMIT only (support TABLESAMPLE and virtual columns)
+    </description>
+  </property>
+  <property>
+    <name>hive.fetch.task.conversion.threshold</name>
+    <value>1073741824</value>
+    <description>
+      Input threshold for applying hive.fetch.task.conversion. If target table is native, input length
+      is calculated by summation of file lengths. If it's not native, storage handler for the table
+      can optionally implement org.apache.hadoop.hive.ql.metadata.InputEstimator interface.
+    </description>
+  </property>
+  <property>
+    <name>hive.fetch.task.aggr</name>
+    <value>false</value>
+    <description>
+      Aggregation queries with no group-by clause (for example, select count(*) from src) execute
+      final aggregations in single reduce task. If this is set true, Hive delegates final aggregation
+      stage to fetch task, possibly decreasing the query time.
+    </description>
+  </property>
+  <property>
+    <name>hive.compute.query.using.stats</name>
+    <value>false</value>
+    <description>
+      When set to true Hive will answer a few queries like count(1) purely using stats
+      stored in metastore. For basic stats collection turn on the config hive.stats.autogather to true.
+      For more advanced stats collection need to run analyze table queries.
+    </description>
+  </property>
+  <property>
+    <name>hive.fetch.output.serde</name>
+    <value>org.apache.hadoop.hive.serde2.DelimitedJSONSerDe</value>
+    <description>The SerDe used by FetchTask to serialize the fetch output.</description>
+  </property>
+  <property>
+    <name>hive.cache.expr.evaluation</name>
+    <value>true</value>
+    <description>
+      If true, the evaluation result of a deterministic expression referenced twice or more
+      will be cached.
+      For example, in a filter condition like '.. where key + 10 = 100 or key + 10 = 0'
+      the expression 'key + 10' will be evaluated/cached once and reused for the following
+      expression ('key + 10 = 0'). Currently, this is applied only to expressions in select
+      or filter operators.
+    </description>
+  </property>
+  <property>
+    <name>hive.variable.substitute</name>
+    <value>true</value>
+    <description>This enables substitution using syntax like ${var} ${system:var} and ${env:var}.</description>
+  </property>
+  <property>
+    <name>hive.variable.substitute.depth</name>
+    <value>40</value>
+    <description>The maximum replacements the substitution engine will do.</description>
+  </property>
+  <property>
+    <name>hive.conf.validation</name>
+    <value>true</value>
+    <description>Enables type checking for registered Hive configurations</description>
+  </property>
+  <property>
+    <name>hive.semantic.analyzer.hook</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.security.authorization.enabled</name>
+    <value>false</value>
+    <description>enable or disable the Hive client authorization</description>
+  </property>
+  <property>
+    <name>hive.security.authorization.manager</name>
+    <value>org.apache.hadoop.hive.ql.security.authorization.plugin.sqlstd.SQLStdHiveAuthorizerFactory</value>
+    <description>
+      The Hive client authorization manager class name. The user defined authorization class should implement 
+      interface org.apache.hadoop.hive.ql.security.authorization.HiveAuthorizationProvider.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authenticator.manager</name>
+    <value>org.apache.hadoop.hive.ql.security.HadoopDefaultAuthenticator</value>
+    <description>
+      hive client authenticator manager class name. The user defined authenticator should implement 
+      interface org.apache.hadoop.hive.ql.security.HiveAuthenticationProvider.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.metastore.authorization.manager</name>
+    <value>org.apache.hadoop.hive.ql.security.authorization.DefaultHiveMetastoreAuthorizationProvider</value>
+    <description>
+      Names of authorization manager classes (comma separated) to be used in the metastore
+      for authorization. The user defined authorization class should implement interface
+      org.apache.hadoop.hive.ql.security.authorization.HiveMetastoreAuthorizationProvider.
+      All authorization manager classes have to successfully authorize the metastore API
+      call for the command execution to be allowed.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.metastore.authorization.auth.reads</name>
+    <value>true</value>
+    <description>If this is true, metastore authorizer authorizes read actions on database, table</description>
+  </property>
+  <property>
+    <name>hive.security.metastore.authenticator.manager</name>
+    <value>org.apache.hadoop.hive.ql.security.HadoopDefaultMetastoreAuthenticator</value>
+    <description>
+      authenticator manager class name to be used in the metastore for authentication. 
+      The user defined authenticator should implement interface org.apache.hadoop.hive.ql.security.HiveAuthenticationProvider.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authorization.createtable.user.grants</name>
+    <value/>
+    <description>
+      the privileges automatically granted to some users whenever a table gets created.
+      An example like "userX,userY:select;userZ:create" will grant select privilege to userX and userY,
+      and grant create privilege to userZ whenever a new table created.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authorization.createtable.group.grants</name>
+    <value/>
+    <description>
+      the privileges automatically granted to some groups whenever a table gets created.
+      An example like "groupX,groupY:select;groupZ:create" will grant select privilege to groupX and groupY,
+      and grant create privilege to groupZ whenever a new table created.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authorization.createtable.role.grants</name>
+    <value/>
+    <description>
+      the privileges automatically granted to some roles whenever a table gets created.
+      An example like "roleX,roleY:select;roleZ:create" will grant select privilege to roleX and roleY,
+      and grant create privilege to roleZ whenever a new table created.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authorization.createtable.owner.grants</name>
+    <value/>
+    <description>
+      The privileges automatically granted to the owner whenever a table gets created.
+      An example like "select,drop" will grant select and drop privilege to the owner
+      of the table. Note that the default gives the creator of a table no access to the
+      table (but see HIVE-8067).
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authorization.task.factory</name>
+    <value>org.apache.hadoop.hive.ql.parse.authorization.HiveAuthorizationTaskFactoryImpl</value>
+    <description>Authorization DDL task factory implementation</description>
+  </property>
+  <property>
+    <name>hive.security.authorization.sqlstd.confwhitelist</name>
+    <value/>
+    <description>
+      List of comma separated Java regexes. Configurations parameters that match these
+      regexes can be modified by user when SQL standard authorization is enabled.
+      To get the default value, use the 'set &lt;param&gt;' command.
+      Note that the hive.conf.restricted.list checks are still enforced after the white list
+      check
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authorization.sqlstd.confwhitelist.append</name>
+    <value/>
+    <description>
+      List of comma separated Java regexes, to be appended to list set in
+      hive.security.authorization.sqlstd.confwhitelist. Using this list instead
+      of updating the original list means that you can append to the defaults
+      set by SQL standard authorization instead of replacing it entirely.
+    </description>
+  </property>
+  <property>
+    <name>hive.cli.print.header</name>
+    <value>false</value>
+    <description>Whether to print the names of the columns in query output.</description>
+  </property>
+  <property>
+    <name>hive.cli.tez.session.async</name>
+    <value>true</value>
+    <description>
+      Whether to start Tez
+      session in background when running CLI with Tez, allowing CLI to be available earlier.
+    </description>
+  </property>
+  <property>
+    <name>hive.error.on.empty.partition</name>
+    <value>false</value>
+    <description>Whether to throw an exception if dynamic partition insert generates empty results.</description>
+  </property>
+  <property>
+    <name>hive.index.compact.file</name>
+    <value/>
+    <description>internal variable</description>
+  </property>
+  <property>
+    <name>hive.index.blockfilter.file</name>
+    <value/>
+    <description>internal variable</description>
+  </property>
+  <property>
+    <name>hive.index.compact.file.ignore.hdfs</name>
+    <value>false</value>
+    <description>
+      When true the HDFS location stored in the index file will be ignored at runtime.
+      If the data got moved or the name of the cluster got changed, the index data should still be usable.
+    </description>
+  </property>
+  <property>
+    <name>hive.exim.uri.scheme.whitelist</name>
+    <value>hdfs,pfile</value>
+    <description>A comma separated list of acceptable URI schemes for import and export.</description>
+  </property>
+  <property>
+    <name>hive.exim.strict.repl.tables</name>
+    <value>true</value>
+    <description>
+      Parameter that determines if 'regular' (non-replication) export dumps can be
+      imported on to tables that are the target of replication. If this parameter is
+      set, regular imports will check if the destination table(if it exists) has a 'repl.last.id' set on it. If so, it will fail.
+    </description>
+  </property>
+  <property>
+    <name>hive.repl.task.factory</name>
+    <value>org.apache.hive.hcatalog.api.repl.exim.EximReplicationTaskFactory</value>
+    <description>
+      Parameter that can be used to override which ReplicationTaskFactory will be
+      used to instantiate ReplicationTask events. Override for third party repl plugins
+    </description>
+  </property>
+  <property>
+    <name>hive.mapper.cannot.span.multiple.partitions</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.rework.mapredwork</name>
+    <value>false</value>
+    <description>
+      should rework the mapred work or not.
+      This is first introduced by SymlinkTextInputFormat to replace symlink files with real paths at compile time.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.concatenate.check.index</name>
+    <value>true</value>
+    <description>
+      If this is set to true, Hive will throw error when doing
+      'alter table tbl_name [partSpec] concatenate' on a table/partition
+      that has indexes on it. The reason the user want to set this to true
+      is because it can help user to avoid handling all index drop, recreation,
+      rebuild work. This is very helpful for tables with thousands of partitions.
+    </description>
+  </property>
+  <property>
+    <name>hive.io.exception.handlers</name>
+    <value/>
+    <description>
+      A list of io exception handler class names. This is used
+      to construct a list exception handlers to handle exceptions thrown
+      by record readers
+    </description>
+  </property>
+  <property>
+    <name>hive.log4j.file</name>
+    <value/>
+    <description>
+      Hive log4j configuration file.
+      If the property is not set, then logging will be initialized using hive-log4j2.properties found on the classpath.
+      If the property is set, the value must be a valid URI (java.net.URI, e.g. "file:///tmp/my-logging.xml"), 
+      which you can then extract a URL from and pass to PropertyConfigurator.configure(URL).
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.log4j.file</name>
+    <value/>
+    <description>
+      Hive log4j configuration file for execution mode(sub command).
+      If the property is not set, then logging will be initialized using hive-exec-log4j2.properties found on the classpath.
+      If the property is set, the value must be a valid URI (java.net.URI, e.g. "file:///tmp/my-logging.xml"), 
+      which you can then extract a URL from and pass to PropertyConfigurator.configure(URL).
+    </description>
+  </property>
+  <property>
+    <name>hive.async.log.enabled</name>
+    <value>true</value>
+    <description>
+      Whether to enable Log4j2's asynchronous logging. Asynchronous logging can give
+       significant performance improvement as logging will be handled in separate thread
+       that uses LMAX disruptor queue for buffering log messages.
+       Refer https://logging.apache.org/log4j/2.x/manual/async.html for benefits and
+       drawbacks.
+    </description>
+  </property>
+  <property>
+    <name>hive.log.explain.output</name>
+    <value>false</value>
+    <description>
+      Whether to log explain output for every query.
+      When enabled, will log EXPLAIN EXTENDED output for the query at INFO log4j log level.
+    </description>
+  </property>
+  <property>
+    <name>hive.explain.user</name>
+    <value>true</value>
+    <description>
+      Whether to show explain result at user level.
+      When enabled, will log EXPLAIN output for the query at user level.
+    </description>
+  </property>
+  <property>
+    <name>hive.autogen.columnalias.prefix.label</name>
+    <value>_c</value>
+    <description>
+      String used as a prefix when auto generating column alias.
+      By default the prefix label will be appended with a column position number to form the column alias. 
+      Auto generation would happen if an aggregate function is used in a select clause without an explicit alias.
+    </description>
+  </property>
+  <property>
+    <name>hive.autogen.columnalias.prefix.includefuncname</name>
+    <value>false</value>
+    <description>Whether to include function name in the column alias auto generated by Hive.</description>
+  </property>
+  <property>
+    <name>hive.service.metrics.class</name>
+    <value>org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics</value>
+    <description>
+      Expects one of [org.apache.hadoop.hive.common.metrics.metrics2.codahalemetrics, org.apache.hadoop.hive.common.metrics.legacymetrics].
+      Hive metrics subsystem implementation class.
+    </description>
+  </property>
+  <property>
+    <name>hive.service.metrics.reporter</name>
+    <value>JSON_FILE, JMX</value>
+    <description>Reporter type for metric class org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics, comma separated list of JMX, CONSOLE, JSON_FILE, HADOOP2</description>
+  </property>
+  <property>
+    <name>hive.service.metrics.file.location</name>
+    <value>/tmp/report.json</value>
+    <description>For metric class org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics JSON_FILE reporter, the location of local JSON metrics file.  This file will get overwritten at every interval.</description>
+  </property>
+  <property>
+    <name>hive.service.metrics.file.frequency</name>
+    <value>5s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      For metric class org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics JSON_FILE reporter, the frequency of updating JSON metrics file.
+    </description>
+  </property>
+  <property>
+    <name>hive.service.metrics.hadoop2.frequency</name>
+    <value>30s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      For metric class org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics HADOOP2 reporter, the frequency of updating the HADOOP2 metrics system.
+    </description>
+  </property>
+  <property>
+    <name>hive.service.metrics.hadoop2.component</name>
+    <value>hive</value>
+    <description>Component name to provide to Hadoop2 Metrics system. Ideally 'hivemetastore' for the MetaStore  and and 'hiveserver2' for HiveServer2.</description>
+  </property>
+  <property>
+    <name>hive.exec.perf.logger</name>
+    <value>org.apache.hadoop.hive.ql.log.PerfLogger</value>
+    <description>
+      The class responsible for logging client side performance metrics. 
+      Must be a subclass of org.apache.hadoop.hive.ql.log.PerfLogger
+    </description>
+  </property>
+  <property>
+    <name>hive.start.cleanup.scratchdir</name>
+    <value>false</value>
+    <description>To cleanup the Hive scratchdir when starting the Hive Server</description>
+  </property>
+  <property>
+    <name>hive.scratchdir.lock</name>
+    <value>false</value>
+    <description>To hold a lock file in scratchdir to prevent to be removed by cleardanglingscratchdir</description>
+  </property>
+  <property>
+    <name>hive.insert.into.multilevel.dirs</name>
+    <value>false</value>
+    <description>
+      Where to insert into multilevel directories like
+      "insert directory '/HIVEFT25686/chinna/' from table"
+    </description>
+  </property>
+  <property>
+    <name>hive.warehouse.subdir.inherit.perms</name>
+    <value>true</value>
+    <description>
+      Set this to false if the table directories should be created
+      with the permissions derived from dfs umask instead of
+      inheriting the permission of the warehouse or database directory.
+    </description>
+  </property>
+  <property>
+    <name>hive.insert.into.external.tables</name>
+    <value>true</value>
+    <description>whether insert into external tables is allowed</description>
+  </property>
+  <property>
+    <name>hive.exec.temporary.table.storage</name>
+    <value>default</value>
+    <description>
+      Expects one of [memory, ssd, default].
+      Define the storage policy for temporary tables.Choices between memory, ssd and default
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.driver.run.hooks</name>
+    <value/>
+    <description>A comma separated list of hooks which implement HiveDriverRunHook. Will be run at the beginning and end of Driver.run, these will be run in the order specified.</description>
+  </property>
+  <property>
+    <name>hive.ddl.output.format</name>
+    <value/>
+    <description>
+      The data format to use for DDL output.  One of "text" (for human
+      readable text) or "json" (for a json object).
+    </description>
+  </property>
+  <property>
+    <name>hive.entity.separator</name>
+    <value>@</value>
+    <description>Separator used to construct names of tables and partitions. For example, dbname@tablename@partitionname</description>
+  </property>
+  <property>
+    <name>hive.entity.capture.transform</name>
+    <value>false</value>
+    <description>Compiler to capture transform URI referred in the query</description>
+  </property>
+  <property>
+    <name>hive.display.partition.cols.separately</name>
+    <value>true</value>
+    <description>
+      In older Hive version (0.10 and earlier) no distinction was made between
+      partition columns or non-partition columns while displaying columns in describe
+      table. From 0.12 onwards, they are displayed separately. This flag will let you
+      get old behavior, if desired. See, test-case in patch for HIVE-6689.
+    </description>
+  </property>
+  <property>
+    <name>hive.ssl.protocol.blacklist</name>
+    <value>SSLv2,SSLv3</value>
+    <description>SSL Versions to disable for all Hive Servers</description>
+  </property>
+  <property>
+    <name>hive.server2.max.start.attempts</name>
+    <value>30</value>
+    <description>
+      Expects value bigger than 0.
+      Number of times HiveServer2 will attempt to start before exiting, sleeping 60 seconds between retries. 
+       The default of 30 will keep trying for 30 minutes.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.support.dynamic.service.discovery</name>
+    <value>false</value>
+    <description>Whether HiveServer2 supports dynamic service discovery for its clients. To support this, each instance of HiveServer2 currently uses ZooKeeper to register itself, when it is brought up. JDBC/ODBC clients should use the ZooKeeper ensemble: hive.zookeeper.quorum in their connection string.</description>
+  </property>
+  <property>
+    <name>hive.server2.zookeeper.namespace</name>
+    <value>hiveserver2</value>
+    <description>The parent node in ZooKeeper used by HiveServer2 when supporting dynamic service discovery.</description>
+  </property>
+  <property>
+    <name>hive.server2.zookeeper.publish.configs</name>
+    <value>true</value>
+    <description>Whether we should publish HiveServer2's configs to ZooKeeper.</description>
+  </property>
+  <property>
+    <name>hive.server2.global.init.file.location</name>
+    <value>${env:HIVE_CONF_DIR}</value>
+    <description>
+      Either the location of a HS2 global init file or a directory containing a .hiverc file. If the 
+      property is set, the value must be a valid path to an init file or directory where the init file is located.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.transport.mode</name>
+    <value>binary</value>
+    <description>
+      Expects one of [binary, http].
+      Transport mode of HiveServer2.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.bind.host</name>
+    <value/>
+    <description>Bind host on which to run the HiveServer2 Thrift service.</description>
+  </property>
+  <property>
+    <name>hive.driver.parallel.compilation</name>
+    <value>false</value>
+    <description>
+      Whether to
+      enable parallel compilation between sessions on HiveServer2. The default is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.compile.lock.timeout</name>
+    <value>0s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds a request will wait to acquire the compile lock before giving up. Setting it to 0s disables the timeout.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.parallel.ops.in.session</name>
+    <value>true</value>
+    <description>Whether to allow several parallel operations (such as SQL statements) in one session.</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.host</name>
+    <value>0.0.0.0</value>
+    <description>The host address the HiveServer2 WebUI will listen on</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.port</name>
+    <value>10002</value>
+    <description>The port the HiveServer2 WebUI will listen on. This can beset to 0 or a negative integer to disable the web UI</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.max.threads</name>
+    <value>50</value>
+    <description>The max HiveServer2 WebUI threads</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.use.ssl</name>
+    <value>false</value>
+    <description>Set this to true for using SSL encryption for HiveServer2 WebUI.</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.keystore.path</name>
+    <value/>
+    <description>SSL certificate keystore location for HiveServer2 WebUI.</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.keystore.password</name>
+    <value/>
+    <description>SSL certificate keystore password for HiveServer2 WebUI.</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.use.spnego</name>
+    <value>false</value>
+    <description>If true, the HiveServer2 WebUI will be secured with SPNEGO. Clients must authenticate with Kerberos.</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.spnego.keytab</name>
+    <value/>
+    <description>The path to the Kerberos Keytab file containing the HiveServer2 WebUI SPNEGO service principal.</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.spnego.principal</name>
+    <value>HTTP/_HOST@EXAMPLE.COM</value>
+    <description>
+      The HiveServer2 WebUI SPNEGO service principal.
+      The special string _HOST will be replaced automatically with 
+      the value of hive.server2.webui.host or the correct host name.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.webui.max.historic.queries</name>
+    <value>25</value>
+    <description>The maximum number of past queries to show in HiverSever2 WebUI.</description>
+  </property>
+  <property>
+    <name>hive.server2.tez.default.queues</name>
+    <value/>
+    <description>
+      A list of comma separated values corresponding to YARN queues of the same name.
+      When HiveServer2 is launched in Tez mode, this configuration needs to be set
+      for multiple Tez sessions to run in parallel on the cluster.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.tez.sessions.per.default.queue</name>
+    <value>1</value>
+    <description>
+      A positive integer that determines the number of Tez sessions that should be
+      launched on each of the queues specified by "hive.server2.tez.default.queues".
+      Determines the parallelism on each queue.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.tez.initialize.default.sessions</name>
+    <value>false</value>
+    <description>
+      This flag is used in HiveServer2 to enable a user to use HiveServer2 without
+      turning on Tez for HiveServer2. The user could potentially want to run queries
+      over Tez without the pool of sessions.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.tez.session.lifetime</name>
+    <value>162h</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is hour if not specified.
+      The lifetime of the Tez sessions launched by HS2 when default sessions are enabled.
+      Set to 0 to disable session expiration.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.tez.session.lifetime.jitter</name>
+    <value>3h</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is hour if not specified.
+      The jitter for Tez session lifetime; prevents all the sessions from restarting at once.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.tez.sessions.init.threads</name>
+    <value>16</value>
+    <description>
+      If hive.server2.tez.initialize.default.sessions is enabled, the maximum number of
+      threads to use to initialize the default sessions.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.logging.operation.enabled</name>
+    <value>true</value>
+    <description>When true, HS2 will save operation logs and make them available for clients</description>
+  </property>
+  <property>
+    <name>hive.server2.logging.operation.log.location</name>
+    <value>${system:java.io.tmpdir}/${system:user.name}/operation_logs</value>
+    <description>Top level directory where operation logs are stored if logging functionality is enabled</description>
+  </property>
+  <property>
+    <name>hive.server2.logging.operation.level</name>
+    <value>EXECUTION</value>
+    <description>
+      Expects one of [none, execution, performance, verbose].
+      HS2 operation logging mode available to clients to be set at session level.
+      For this to work, hive.server2.logging.operation.enabled should be set to true.
+        NONE: Ignore any logging
+        EXECUTION: Log completion of tasks
+        PERFORMANCE: Execution + Performance logs 
+        VERBOSE: All logs
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.metrics.enabled</name>
+    <value>false</value>
+    <description>Enable metrics on the HiveServer2.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.port</name>
+    <value>10001</value>
+    <description>Port number of HiveServer2 Thrift interface when hive.server2.transport.mode is 'http'.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.path</name>
+    <value>cliservice</value>
+    <description>Path component of URL endpoint when in HTTP mode.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.max.message.size</name>
+    <value>104857600</value>
+    <description>Maximum message size in bytes a HS2 server will accept.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.max.idle.time</name>
+    <value>1800s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Maximum idle time for a connection on the server when in HTTP mode.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.worker.keepalive.time</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Keepalive time for an idle http worker thread. When the number of workers exceeds min workers, excessive threads are killed after this time interval.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.request.header.size</name>
+    <value>6144</value>
+    <description>Request header size in bytes, when using HTTP transport mode. Jetty defaults used.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.response.header.size</name>
+    <value>6144</value>
+    <description>Response header size in bytes, when using HTTP transport mode. Jetty defaults used.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.cookie.auth.enabled</name>
+    <value>true</value>
+    <description>When true, HiveServer2 in HTTP transport mode, will use cookie based authentication mechanism.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.cookie.max.age</name>
+    <value>86400s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Maximum age in seconds for server side cookie used by HS2 in HTTP mode.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.cookie.domain</name>
+    <value/>
+    <description>Domain for the HS2 generated cookies</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.cookie.path</name>
+    <value/>
+    <description>Path for the HS2 generated cookies</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.cookie.is.secure</name>
+    <value>true</value>
+    <description>Secure attribute of the HS2 generated cookie.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.cookie.is.httponly</name>
+    <value>true</value>
+    <description>HttpOnly attribute of the HS2 generated cookie.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.port</name>
+    <value>10000</value>
+    <description>Port number of HiveServer2 Thrift interface when hive.server2.transport.mode is 'binary'.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.sasl.qop</name>
+    <value>auth</value>
+    <description>
+      Expects one of [auth, auth-int, auth-conf].
+      Sasl QOP value; set it to one of following values to enable higher levels of
+      protection for HiveServer2 communication with clients.
+      Setting hadoop.rpc.protection to a higher level than HiveServer2 does not
+      make sense in most situations. HiveServer2 ignores hadoop.rpc.protection in favor
+      of hive.server2.thrift.sasl.qop.
+        "auth" - authentication only (default)
+        "auth-int" - authentication plus integrity protection
+        "auth-conf" - authentication plus integrity and confidentiality protection
+      This is applicable only if HiveServer2 is configured to use Kerberos authentication.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.min.worker.threads</name>
+    <value>5</value>
+    <description>Minimum number of Thrift worker threads</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.max.worker.threads</name>
+    <value>500</value>
+    <description>Maximum number of Thrift worker threads</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.exponential.backoff.slot.length</name>
+    <value>100ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Binary exponential backoff slot time for Thrift clients during login to HiveServer2,
+      for retries until hitting Thrift client timeout
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.login.timeout</name>
+    <value>20s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Timeout for Thrift clients during login to HiveServer2
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.worker.keepalive.time</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Keepalive time (in seconds) for an idle worker thread. When the number of workers exceeds min workers, excessive threads are killed after this time interval.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.async.exec.threads</name>
+    <value>100</value>
+    <description>Number of threads in the async thread pool for HiveServer2</description>
+  </property>
+  <property>
+    <name>hive.server2.async.exec.shutdown.timeout</name>
+    <value>10s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      How long HiveServer2 shutdown will wait for async threads to terminate.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.async.exec.wait.queue.size</name>
+    <value>100</value>
+    <description>
+      Size of the wait queue for async thread pool in HiveServer2.
+      After hitting this limit, the async thread pool will reject new requests.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.async.exec.keepalive.time</name>
+    <value>10s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Time that an idle HiveServer2 async thread (from the thread pool) will wait for a new task
+      to arrive before terminating
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.async.exec.async.compile</name>
+    <value>false</value>
+    <description>Whether to enable compiling async query asynchronously. If enabled, it is unknown if the query will have any resultset before compilation completed.</description>
+  </property>
+  <property>
+    <name>hive.server2.long.polling.timeout</name>
+    <value>5000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Time that HiveServer2 will wait before responding to asynchronous calls that use long polling
+    </description>
+  </property>
+  <property>
+    <name>hive.session.impl.classname</name>
+    <value/>
+    <description>Classname for custom implementation of hive session</description>
+  </property>
+  <property>
+    <name>hive.session.impl.withugi.classname</name>
+    <value/>
+    <description>Classname for custom implementation of hive session with UGI</description>
+  </property>
+  <property>
+    <name>hive.server2.authentication</name>
+    <value>NONE</value>
+    <description>
+      Expects one of [nosasl, none, ldap, kerberos, pam, custom].
+      Client authentication types.
+        NONE: no authentication check
+        LDAP: LDAP/AD based authentication
+        KERBEROS: Kerberos/GSSAPI authentication
+        CUSTOM: Custom authentication provider
+                (Use with property hive.server2.custom.authentication.class)
+        PAM: Pluggable authentication module
+        NOSASL:  Raw transport
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.allow.user.substitution</name>
+    <value>true</value>
+    <description>Allow alternate user to be specified as part of HiveServer2 open connection request.</description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.kerberos.keytab</name>
+    <value/>
+    <description>Kerberos keytab file for server principal</description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.kerberos.principal</name>
+    <value/>
+    <description>Kerberos server principal</description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.spnego.keytab</name>
+    <value/>
+    <description>
+      keytab file for SPNego principal, optional,
+      typical value would look like /etc/security/keytabs/spnego.service.keytab,
+      This keytab would be used by HiveServer2 when Kerberos security is enabled and 
+      HTTP transport mode is used.
+      This needs to be set only if SPNEGO is to be used in authentication.
+      SPNego authentication would be honored only if valid
+        hive.server2.authentication.spnego.principal
+      and
+        hive.server2.authentication.spnego.keytab
+      are specified.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.spnego.principal</name>
+    <value/>
+    <description>
+      SPNego service principal, optional,
+      typical value would look like HTTP/_HOST@EXAMPLE.COM
+      SPNego service principal would be used by HiveServer2 when Kerberos security is enabled
+      and HTTP transport mode is used.
+      This needs to be set only if SPNEGO is to be used in authentication.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.url</name>
+    <value/>
+    <description>
+      LDAP connection URL(s),
+      this value could contain URLs to mutiple LDAP servers instances for HA,
+      each LDAP URL is separated by a SPACE character. URLs are used in the 
+       order specified until a connection is successful.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.baseDN</name>
+    <value/>
+    <description>LDAP base DN</description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.Domain</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.groupDNPattern</name>
+    <value/>
+    <description>
+      COLON-separated list of patterns to use to find DNs for group entities in this directory.
+      Use %s where the actual group name is to be substituted for.
+      For example: CN=%s,CN=Groups,DC=subdomain,DC=domain,DC=com.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.groupFilter</name>
+    <value/>
+    <description>
+      COMMA-separated list of LDAP Group names (short name not full DNs).
+      For example: HiveAdmins,HadoopAdmins,Administrators
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.userDNPattern</name>
+    <value/>
+    <description>
+      COLON-separated list of patterns to use to find DNs for users in this directory.
+      Use %s where the actual group name is to be substituted for.
+      For example: CN=%s,CN=Users,DC=subdomain,DC=domain,DC=com.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.userFilter</name>
+    <value/>
+    <description>
+      COMMA-separated list of LDAP usernames (just short names, not full DNs).
+      For example: hiveuser,impalauser,hiveadmin,hadoopadmin
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.guidKey</name>
+    <value>uid</value>
+    <description>
+      LDAP attribute name whose values are unique in this LDAP server.
+      For example: uid or CN.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.groupMembershipKey</name>
+    <value>member</value>
+    <description>
+      LDAP attribute name on the user entry that references a group, the user belongs to.
+      For example: member, uniqueMember or memberUid
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.groupClassKey</name>
+    <value>groupOfNames</value>
+    <description>
+      LDAP attribute name on the group entry that is to be used in LDAP group searches.
+      For example: group, groupOfNames or groupOfUniqueNames.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.customLDAPQuery</name>
+    <value/>
+    <description>
+      A full LDAP query that LDAP Atn provider uses to execute against LDAP Server.
+      If this query returns a null resultset, the LDAP Provider fails the Authentication
+      request, succeeds if the user is part of the resultset.For example: (&amp;(objectClass=group)(objectClass=top)(instanceType=4)(cn=Domain*)) 
+      (&amp;(objectClass=person)(|(sAMAccountName=admin)(|(memberOf=CN=Domain Admins,CN=Users,DC=domain,DC=com)(memberOf=CN=Administrators,CN=Builtin,DC=domain,DC=com))))
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.custom.authentication.class</name>
+    <value/>
+    <description>
+      Custom authentication class. Used when property
+      'hive.server2.authentication' is set to 'CUSTOM'. Provided class
+      must be a proper implementation of the interface
+      org.apache.hive.service.auth.PasswdAuthenticationProvider. HiveServer2
+      will call its Authenticate(user, passed) method to authenticate requests.
+      The implementation may optionally implement Hadoop's
+      org.apache.hadoop.conf.Configurable class to grab Hive's Configuration object.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.pam.services</name>
+    <value/>
+    <description>
+      List of the underlying pam services that should be used when auth type is PAM
+      A file with the same name must exist in /etc/pam.d
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.enable.doAs</name>
+    <value>true</value>
+    <description>
+      Setting this property to true will have HiveServer2 execute
+      Hive operations as the user making the calls to it.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.table.type.mapping</name>
+    <value>CLASSIC</value>
+    <description>
+      Expects one of [classic, hive].
+      This setting reflects how HiveServer2 will report the table types for JDBC and other
+      client implementations that retrieve the available tables and supported table types
+        HIVE : Exposes Hive's native table types like MANAGED_TABLE, EXTERNAL_TABLE, VIRTUAL_VIEW
+        CLASSIC : More generic types like TABLE and VIEW
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.session.hook</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.server2.use.SSL</name>
+    <value>false</value>
+    <description>Set this to true for using SSL encryption in HiveServer2.</description>
+  </property>
+  <property>
+    <name>hive.server2.keystore.path</name>
+    <value/>
+    <description>SSL certificate keystore location.</description>
+  </property>
+  <property>
+    <name>hive.server2.keystore.password</name>
+    <value/>
+    <description>SSL certificate keystore password.</description>
+  </property>
+  <property>
+    <name>hive.server2.map.fair.scheduler.queue</name>
+    <value>true</value>
+    <description>
+      If the YARN fair scheduler is configured and HiveServer2 is running in non-impersonation mode,
+      this setting determines the user for fair scheduler queue mapping.
+      If set to true (default), the logged-in user determines the fair scheduler queue
+      for submitted jobs, so that map reduce resource usage can be tracked by user.
+      If set to false, all Hive jobs go to the 'hive' user's queue.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.builtin.udf.whitelist</name>
+    <value/>
+    <description>
+      Comma separated list of builtin udf names allowed in queries.
+      An empty whitelist allows all builtin udfs to be executed.  The udf black list takes precedence over udf white list
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.builtin.udf.blacklist</name>
+    <value/>
+    <description>Comma separated list of udfs names. These udfs will not be allowed in queries. The udf black list takes precedence over udf white list</description>
+  </property>
+  <property>
+    <name>hive.allow.udf.load.on.demand</name>
+    <value>false</value>
+    <description>
+      Whether enable loading UDFs from metastore on demand; this is mostly relevant for
+      HS2 and was the default behavior before Hive 1.2. Off by default.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.session.check.interval</name>
+    <value>6h</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      The time should be bigger than or equal to 3000 msec.
+      The check interval for session/operation timeout, which can be disabled by setting to zero or negative value.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.close.session.on.disconnect</name>
+    <value>true</value>
+    <description>Session will be closed when connection is closed. Set this to false to have session outlive its parent connection.</description>
+  </property>
+  <property>
+    <name>hive.server2.idle.session.timeout</name>
+    <value>7d</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Session will be closed when it's not accessed for this duration, which can be disabled by setting to zero or negative value.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.idle.operation.timeout</name>
+    <value>5d</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Operation will be closed when it's not accessed for this duration of time, which can be disabled by setting to zero value.
+        With positive value, it's checked for operations in terminal state only (FINISHED, CANCELED, CLOSED, ERROR).
+        With negative value, it's checked for all of the operations regardless of state.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.idle.session.check.operation</name>
+    <value>true</value>
+    <description>
+      Session will be considered to be idle only if there is no activity, and there is no pending operation.
+       This setting takes effect only if session idle timeout (hive.server2.idle.session.timeout) and checking
+      (hive.server2.session.check.interval) are enabled.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.client.retry.limit</name>
+    <value>1</value>
+    <description>Number of retries upon failure of Thrift HiveServer2 calls</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.client.connect.retry.limit</name>
+    <value>1</value>
+    <description>Number of retries while opening a connection to HiveServe2</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.client.retry.delay.seconds</name>
+    <value>1s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds for the HiveServer2 thrift client to wait between consecutive connection attempts. Also specifies the time to wait between retrying thrift calls upon failures
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.client.user</name>
+    <value>anonymous</value>
+    <description>Username to use against thrift client</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.client.password</name>
+    <value>anonymous</value>
+    <description>Password to use against thrift client</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.resultset.serialize.in.tasks</name>
+    <value>false</value>
+    <description>
+      Whether we should serialize the Thrift structures used in JDBC ResultSet RPC in task nodes.
+       We use SequenceFile and ThriftJDBCBinarySerDe to read and write the final results if this is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.resultset.max.fetch.size</name>
+    <value>1000</value>
+    <description>Max number of rows sent in one Fetch RPC call by the server to the client.</description>
+  </property>
+  <property>
+    <name>hive.server2.xsrf.filter.enabled</name>
+    <value>false</value>
+    <description>If enabled, HiveServer2 will block any requests made to it over http if an X-XSRF-HEADER header is not present</description>
+  </property>
+  <property>
+    <name>hive.security.command.whitelist</name>
+    <value>set,reset,dfs,add,list,delete,reload,compile</value>
+    <description>Comma separated list of non-SQL Hive commands users are authorized to execute</description>
+  </property>
+  <property>
+    <name>hive.mv.files.thread</name>
+    <value>15</value>
+    <description>
+      Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb).
+      The size should be in between 0Pb (inclusive) and 1Kb (inclusive).
+      Number of threads used to move files in move task. Set it to 0 to disable multi-threaded file moves. This parameter is also used by MSCK to check tables.
+    </description>
+  </property>
+  <property>
+    <name>hive.multi.insert.move.tasks.share.dependencies</name>
+    <value>false</value>
+    <description>
+      If this is set all move tasks for tables/partitions (not directories) at the end of a
+      multi-insert query will only begin once the dependencies for all these move tasks have been
+      met.
+      Advantages: If concurrency is enabled, the locks will only be released once the query has
+                  finished, so with this config enabled, the time when the table/partition is
+                  generated will be much closer to when the lock on it is released.
+      Disadvantages: If concurrency is not enabled, with this disabled, the tables/partitions which
+                     are produced by this query and finish earlier will be available for querying
+                     much earlier.  Since the locks are only released once the query finishes, this
+                     does not apply if concurrency is enabled.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.infer.bucket.sort</name>
+    <value>false</value>
+    <description>
+      If this is set, when writing partitions, the metadata will include the bucketing/sorting
+      properties with which the data was written if any (this will not overwrite the metadata
+      inherited from the table if the table is bucketed/sorted)
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.infer.bucket.sort.num.buckets.power.two</name>
+    <value>false</value>
+    <description>
+      If this is set, when setting the number of reducers for the map reduce task which writes the
+      final output files, it will choose a number which is a power of two, unless the user specifies
+      the number of reducers to use using mapred.reduce.tasks.  The number of reducers
+      may be set to a power of two, only to be followed by a merge task meaning preventing
+      anything from being inferred.
+      With hive.exec.infer.bucket.sort set to true:
+      Advantages:  If this is not set, the number of buckets for partitions will seem arbitrary,
+                   which means that the number of mappers used for optimized joins, for example, will
+                   be very low.  With this set, since the number of buckets used for any partition is
+                   a power of two, the number of mappers used for optimized joins will be the least
+                   number of buckets used by any partition being joined.
+      Disadvantages: This may mean a much larger or much smaller number of reducers being used in the
+                     final map reduce job, e.g. if a job was originally going to take 257 reducers,
+                     it will now take 512 reducers, similarly if the max number of reducers is 511,
+                     and a job was going to use this many, it will now use 256 reducers.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.listbucketing</name>
+    <value>false</value>
+    <description>Enable list bucketing optimizer. Default value is false so that we disable it by default.</description>
+  </property>
+  <property>
+    <name>hive.server.read.socket.timeout</name>
+    <value>10s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Timeout for the HiveServer to close the connection if no response from the client. By default, 10 seconds.
+    </description>
+  </property>
+  <property>
+    <name>hive.server.tcp.keepalive</name>
+    <value>true</value>
+    <description>Whether to enable TCP keepalive for the Hive Server. Keepalive will prevent accumulation of half-open connections.</description>
+  </property>
+  <property>
+    <name>hive.decode.partition.name</name>
+    <value>false</value>
+    <description>Whether to show the unquoted partition names in query results.</description>
+  </property>
+  <property>
+    <name>hive.execution.engine</name>
+    <value>mr</value>
+    <description>
+      Expects one of [mr, tez, spark].
+      Chooses execution engine. Options are: mr (Map reduce, default), tez, spark. While MR
+      remains the default engine for historical reasons, it is itself a historical engine
+      and is deprecated in Hive 2 line. It may be removed without further warning.
+    </description>
+  </property>
+  <property>
+    <name>hive.execution.mode</name>
+    <value>container</value>
+    <description>
+      Expects one of [container, llap].
+      Chooses whether query fragments will run in container or in llap
+    </description>
+  </property>
+  <property>
+    <name>hive.jar.directory</name>
+    <value/>
+    <description>
+      This is the location hive in tez mode will look for to find a site wide 
+      installed hive instance.
+    </description>
+  </property>
+  <property>
+    <name>hive.user.install.directory</name>
+    <value>/user/</value>
+    <description>
+      If hive (in tez mode only) cannot find a usable hive jar in "hive.jar.directory", 
+      it will upload the hive jar to "hive.user.install.directory/user.name"
+      and use it to run queries.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.enabled</name>
+    <value>false</value>
+    <description>
+      This flag should be set to true to enable vectorized mode of query execution.
+      The default value is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.reduce.enabled</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable vectorized mode of the reduce-side of query execution.
+      The default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.reduce.groupby.enabled</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable vectorized mode of the reduce-side GROUP BY query execution.
+      The default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.mapjoin.native.enabled</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable native (i.e. non-pass through) vectorization
+      of queries using MapJoin.
+      The default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.mapjoin.native.multikey.only.enabled</name>
+    <value>false</value>
+    <description>
+      This flag should be set to true to restrict use of native vector map join hash tables to
+      the MultiKey in queries using MapJoin.
+      The default value is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.mapjoin.minmax.enabled</name>
+    <value>false</value>
+    <description>
+      This flag should be set to true to enable vector map join hash tables to
+      use max / max filtering for integer join queries using MapJoin.
+      The default value is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.mapjoin.overflow.repeated.threshold</name>
+    <value>-1</value>
+    <description>
+      The number of small table rows for a match in vector map join hash tables
+      where we use the repeated field optimization in overflow vectorized row batch for join queries using MapJoin.
+      A value of -1 means do use the join result optimization.  Otherwise, threshold value can be 0 to maximum integer.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.mapjoin.native.fast.hashtable.enabled</name>
+    <value>false</value>
+    <description>
+      This flag should be set to true to enable use of native fast vector map join hash tables in
+      queries using MapJoin.
+      The default value is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.groupby.checkinterval</name>
+    <value>100000</value>
+    <description>Number of entries added to the group by aggregation hash before a recomputation of average entry size is performed.</description>
+  </property>
+  <property>
+    <name>hive.vectorized.groupby.maxentries</name>
+    <value>1000000</value>
+    <description>
+      Max number of entries in the vector group by aggregation hashtables. 
+      Exceeding this will trigger a flush irrelevant of memory pressure condition.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.groupby.flush.percent</name>
+    <value>0.1</value>
+    <description>Percent of entries in the group by aggregation hash flushed when the memory threshold is exceeded.</description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.reducesink.new.enabled</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable the new vectorization
+      of queries using ReduceSink.
+      iThe default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.use.vectorized.input.format</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable vectorizing with vectorized input file format capable SerDe.
+      The default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.use.vector.serde.deserialize</name>
+    <value>false</value>
+    <description>
+      This flag should be set to true to enable vectorizing rows using vector deserialize.
+      The default value is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.use.row.serde.deserialize</name>
+    <value>false</value>
+    <description>
+      This flag should be set to true to enable vectorizing using row deserialize.
+      The default value is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.typecheck.on.insert</name>
+    <value>true</value>
+    <description>This property has been extended to control whether to check, convert, and normalize partition value to conform to its column type in partition operations including but not limited to insert, such as alter, describe etc.</description>
+  </property>
+  <property>
+    <name>hive.hadoop.classpath</name>
+    <value/>
+    <description>
+      For Windows OS, we need to pass HIVE_HADOOP_CLASSPATH Java parameter while starting HiveServer2 
+      using "-hiveconf hive.hadoop.classpath=%HIVE_LIB%".
+    </description>
+  </property>
+  <property>
+    <name>hive.rpc.query.plan</name>
+    <value>false</value>
+    <description>Whether to send the query plan via local resource or RPC</description>
+  </property>
+  <property>
+    <name>hive.compute.splits.in.am</name>
+    <value>true</value>
+    <description>Whether to generate the splits locally or in the AM (tez only)</description>
+  </property>
+  <property>
+    <name>hive.tez.input.generate.consistent.splits</name>
+    <value>true</value>
+    <description>Whether to generate consistent split locations when generating splits in the AM</description>
+  </property>
+  <property>
+    <name>hive.prewarm.enabled</name>
+    <value>false</value>
+    <description>Enables container prewarm for Tez/Spark (Hadoop 2 only)</description>
+  </property>
+  <property>
+    <name>hive.prewarm.numcontainers</name>
+    <value>10</value>
+    <description>Controls the number of containers to prewarm for Tez/Spark (Hadoop 2 only)</description>
+  </property>
+  <property>
+    <name>hive.stageid.rearrange</name>
+    <value>none</value>
+    <description>
+      Expects one of [none, idonly, traverse, execution].
+    </description>
+  </property>
+  <property>
+    <name>hive.explain.dependency.append.tasktype</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.counters.group.name</name>
+    <value>HIVE</value>
+    <description>The name of counter group for internal Hive variables (CREATED_FILE, FATAL_ERROR, etc.)</description>
+  </property>
+  <property>
+    <name>hive.support.quoted.identifiers</name>
+    <value>column</value>
+    <description>
+      Expects one of [none, column].
+      Whether to use quoted identifier. 'none' or 'column' can be used. 
+        none: default(past) behavior. Implies only alphaNumeric and underscore are valid characters in identifiers.
+        column: implies column names can contain any character.
+    </description>
+  </property>
+  <property>
+    <name>hive.support.sql11.reserved.keywords</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable support for SQL2011 reserved keywords.
+      The default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.support.special.characters.tablename</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable support for special characters in table names.
+      When it is set to false, only [a-zA-Z_0-9]+ are supported.
+      The only supported special character right now is '/'. This flag applies only to quoted table names.
+      The default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.users.in.admin.role</name>
+    <value/>
+    <description>
+      Comma separated list of users who are in admin role for bootstrapping.
+      More users can be added in ADMIN role later.
+    </description>
+  </property>
+  <property>
+    <name>hive.compat</name>
+    <value>0.12</value>
+    <description>
+      Enable (configurable) deprecated behaviors by setting desired level of backward compatibility.
+      Setting to 0.12:
+        Maintains division behavior: int / int = double
+    </description>
+  </property>
+  <property>
+    <name>hive.convert.join.bucket.mapjoin.tez</name>
+    <value>false</value>
+    <description>
+      Whether joins can be automatically converted to bucket map joins in hive 
+      when tez is used as the execution engine.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.check.crossproducts</name>
+    <value>true</value>
+    <description>Check if a plan contains a Cross Product. If there is one, output a warning to the Session's console.</description>
+  </property>
+  <property>
+    <name>hive.localize.resource.wait.interval</name>
+    <value>5000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Time to wait for another thread to localize the same resource for hive-tez.
+    </description>
+  </property>
+  <property>
+    <name>hive.localize.resource.num.wait.attempts</name>
+    <value>5</value>
+    <description>The number of attempts waiting for localizing a resource in hive-tez.</description>
+  </property>
+  <property>
+    <name>hive.tez.auto.reducer.parallelism</name>
+    <value>false</value>
+    <description>
+      Turn on Tez' auto reducer parallelism feature. When enabled, Hive will still estimate data sizes
+      and set parallelism estimates. Tez will sample source vertices' output sizes and adjust the estimates at runtime as
+      necessary.
+    </description>
+  </property>
+  <property>
+    <name>hive.tez.max.partition.factor</name>
+    <value>2.0</value>
+    <description>When auto reducer parallelism is enabled this factor will be used to over-partition data in shuffle edges.</description>
+  </property>
+  <property>
+    <name>hive.tez.min.partition.factor</name>
+    <value>0.25</value>
+    <description>
+      When auto reducer parallelism is enabled this factor will be used to put a lower limit to the number
+      of reducers that tez specifies.
+    </description>
+  </property>
+  <property>
+    <name>hive.tez.bucket.pruning</name>
+    <value>false</value>
+    <description>
+      When pruning is enabled, filters on bucket columns will be processed by 
+      filtering the splits against a bitset of included buckets. This needs predicates 
+      produced by hive.optimize.ppd and hive.optimize.index.filters.
+    </description>
+  </property>
+  <property>
+    <name>hive.tez.bucket.pruning.compat</name>
+    <value>true</value>
+    <description>
+      When pruning is enabled, handle possibly broken inserts due to negative hashcodes.
+      This occasionally doubles the data scan cost, but is default enabled for safety
+    </description>
+  </property>
+  <property>
+    <name>hive.tez.dynamic.partition.pruning</name>
+    <value>true</value>
+    <description>
+      When dynamic pruning is enabled, joins on partition keys will be processed by sending
+      events from the processing vertices to the Tez application master. These events will be
+      used to prune unnecessary partitions.
+    </description>
+  </property>
+  <property>
+    <name>hive.tez.dynamic.partition.pruning.max.event.size</name>
+    <value>1048576</value>
+    <description>Maximum size of events sent by processors in dynamic pruning. If this size is crossed no pruning will take place.</description>
+  </property>
+  <property>
+    <name>hive.tez.dynamic.partition.pruning.max.data.size</name>
+    <value>104857600</value>
+    <description>Maximum total data size of events in dynamic pruning.</description>
+  </property>
+  <property>
+    <name>hive.tez.smb.number.waves</name>
+    <value>0.5</value>
+    <description>The number of waves in which to run the SMB join. Account for cluster being occupied. Ideally should be 1 wave.</description>
+  </property>
+  <property>
+    <name>hive.tez.exec.print.summary</name>
+    <value>false</value>
+    <description>Display breakdown of execution steps, for every query executed by the shell.</description>
+  </property>
+  <property>
+    <name>hive.tez.exec.inplace.progress</name>
+    <value>true</value>
+    <description>Updates tez job execution progress in-place in the terminal.</description>
+  </property>
+  <property>
+    <name>hive.tez.container.max.java.heap.fraction</name>
+    <value>0.8</value>
+    <description>This is to override the tez setting with the same name</description>
+  </property>
+  <property>
+    <name>hive.tez.task.scale.memory.reserve-fraction.min</name>
+    <value>0.3</value>
+    <description>This is to override the tez setting tez.task.scale.memory.reserve-fraction</description>
+  </property>
+  <property>
+    <name>hive.tez.task.scale.memory.reserve.fraction.max</name>
+    <value>0.5</value>
+    <description>The maximum fraction of JVM memory which Tez will reserve for the processor</description>
+  </property>
+  <property>
+    <name>hive.tez.task.scale.memory.reserve.fraction</name>
+    <value>-1.0</value>
+    <description>The customized fraction of JVM memory which Tez will reserve for the processor</description>
+  </property>
+  <property>
+    <name>hive.llap.io.enabled</name>
+    <value/>
+    <description>Whether the LLAP IO layer is enabled.</description>
+  </property>
+  <property>
+    <name>hive.llap.io.memory.mode</name>
+    <value>cache</value>
+    <description>
+      Expects one of [cache, none].
+      LLAP IO memory usage; 'cache' (the default) uses data and metadata cache with a
+      custom off-heap allocator, 'none' doesn't use either (this mode may result in
+      significant performance degradation)
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.allocator.alloc.min</name>
+    <value>16Kb</value>
+    <description>
+      Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb).
+      Minimum allocation possible from LLAP buddy allocator. Allocations below that are
+      padded to minimum allocation. For ORC, should generally be the same as the expected
+      compression buffer size, or next lowest power of 2. Must be a power of 2.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.allocator.alloc.max</name>
+    <value>16Mb</value>
+    <description>
+      Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb).
+      Maximum allocation possible from LLAP buddy allocator. For ORC, should be as large as
+      the largest expected ORC compression buffer size. Must be a power of 2.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.allocator.arena.count</name>
+    <value>8</value>
+    <description>
+      Arena count for LLAP low-level cache; cache will be allocated in the steps of
+      (size/arena_count) bytes. This size must be &lt;= 1Gb and &gt;= max allocation; if it is
+      not the case, an adjusted size will be used. Using powers of 2 is recommended.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.memory.size</name>
+    <value>1Gb</value>
+    <description>
+      Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb).
+      Maximum size for IO allocator or ORC low-level cache.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.allocator.direct</name>
+    <value>true</value>
+    <description>Whether ORC low-level cache should use direct allocation.</description>
+  </property>
+  <property>
+    <name>hive.llap.io.allocator.mmap</name>
+    <value>false</value>
+    <description>
+      Whether ORC low-level cache should use memory mapped allocation (direct I/O). 
+      This is recommended to be used along-side NVDIMM (DAX) or NVMe flash storage.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.allocator.mmap.path</name>
+    <value>/tmp</value>
+    <description>
+      Expects a writable directory on the local filesystem.
+      The directory location for mapping NVDIMM/NVMe flash storage into the ORC low-level cache.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.use.lrfu</name>
+    <value>true</value>
+    <description>Whether ORC low-level cache should use LRFU cache policy instead of default (FIFO).</description>
+  </property>
+  <property>
+    <name>hive.llap.io.lrfu.lambda</name>
+    <value>0.01</value>
+    <description>
+      Lambda for ORC low-level cache LRFU cache policy. Must be in [0, 1]. 0 makes LRFU
+      behave like LFU, 1 makes it behave like LRU, values in between balance accordingly.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.cache.allow.synthetic.fileid</name>
+    <value>false</value>
+    <description>
+      Whether LLAP cache should use synthetic file ID if real one is not available. Systems
+      like HDFS, Isilon, etc. provide a unique file/inode ID. On other FSes (e.g. local
+      FS), the cache would not work by default because LLAP is unable to uniquely track the
+      files; enabling this setting allows LLAP to generate file ID from the path, size and
+      modification time, which is almost certain to identify file uniquely. However, if you
+      use a FS without file IDs and rewrite files a lot (or are paranoid), you might want
+      to avoid this setting.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.orc.gap.cache</name>
+    <value>true</value>
+    <description>
+      Whether LLAP cache for ORC should remember gaps in ORC compression buffer read
+      estimates, to avoid re-reading the data that was read once and discarded because it
+      is unneeded. This is only necessary for ORC files written before HIVE-9660.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.use.fileid.path</name>
+    <value>true</value>
+    <description>
+      Whether LLAP should use fileId (inode)-based path to ensure better consistency for the
+      cases of file overwrites. This is supported on HDFS.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.orc.time.counters</name>
+    <value>true</value>
+    <description>Whether to enable time counters for LLAP IO layer (time spent in HDFS, etc.)</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.allow.uber</name>
+    <value>false</value>
+    <description>Whether or not to allow the planner to run vertices in the AM.</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.enforce.tree</name>
+    <value>true</value>
+    <description>Enforce that all parents are in llap, before considering vertex</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.enforce.vectorized</name>
+    <value>true</value>
+    <description>Enforce that inputs are vectorized, before considering vertex</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.enforce.stats</name>
+    <value>true</value>
+    <description>Enforce that col stats are available, before considering vertex</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.max.input.size</name>
+    <value>10737418240</value>
+    <description>Check input size, before considering vertex (-1 disables check)</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.max.output.size</name>
+    <value>1073741824</value>
+    <description>Check output size, before considering vertex (-1 disables check)</description>
+  </property>
+  <property>
+    <name>hive.llap.skip.compile.udf.check</name>
+    <value>false</value>
+    <description>
+      Whether to skip the compile-time check for non-built-in UDFs when deciding whether to
+      execute tasks in LLAP. Skipping the check allows executing UDFs from pre-localized
+      jars in LLAP; if the jars are not pre-localized, the UDFs will simply fail to load.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.allow.permanent.fns</name>
+    <value>true</value>
+    <description>Whether LLAP decider should allow permanent UDFs.</description>
+  </property>
+  <property>
+    <name>hive.llap.execution.mode</name>
+    <value>none</value>
+    <description>
+      Expects one of [auto, none, all, map].
+      Chooses whether query fragments will run in container or in llap
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.object.cache.enabled</name>
+    <value>true</value>
+    <description>Cache objects (plans, hashtables, etc) in llap</description>
+  </property>
+  <property>
+    <name>hive.llap.io.decoding.metrics.percentiles.intervals</name>
+    <value>30</value>
+    <description>
+      Comma-delimited set of integers denoting the desired rollover intervals (in seconds)
+      for percentile latency metrics on the LLAP daemon IO decoding time.
+      hive.llap.queue.metrics.percentiles.intervals
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.threadpool.size</name>
+    <value>10</value>
+    <description>Specify the number of threads to use for low-level IO thread pool.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.service.principal</name>
+    <value/>
+    <description>The name of the LLAP daemon's service principal.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.keytab.file</name>
+    <value/>
+    <description>The path to the Kerberos Keytab file containing the LLAP daemon's service principal.</description>
+  </property>
+  <property>
+    <name>hive.llap.zk.sm.principal</name>
+    <value/>
+    <description>The name of the principal to use to talk to ZooKeeper for ZooKeeper SecretManager.</description>
+  </property>
+  <property>
+    <name>hive.llap.zk.sm.keytab.file</name>
+    <value/>
+    <description>
+      The path to the Kerberos Keytab file containing the principal to use to talk to
+      ZooKeeper for ZooKeeper SecretManager.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.zk.sm.connectionString</name>
+    <value/>
+    <description>ZooKeeper connection string for ZooKeeper SecretManager.</description>
+  </property>
+  <property>
+    <name>hive.llap.zk.registry.user</name>
+    <value/>
+    <description>
+      In the LLAP ZooKeeper-based registry, specifies the username in the Zookeeper path.
+      This should be the hive user or whichever user is running the LLAP daemon.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.zk.registry.namespace</name>
+    <value/>
+    <description>
+      In the LLAP ZooKeeper-based registry, overrides the ZK path namespace. Note that
+      using this makes the path management (e.g. setting correct ACLs) your responsibility.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.acl</name>
+    <value>*</value>
+    <description>The ACL for LLAP daemon.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.acl.blocked</name>
+    <value/>
+    <description>The deny ACL for LLAP daemon.</description>
+  </property>
+  <property>
+    <name>hive.llap.management.acl</name>
+    <value>*</value>
+    <description>The ACL for LLAP daemon management.</description>
+  </property>
+  <property>
+    <name>hive.llap.management.acl.blocked</name>
+    <value/>
+    <description>The deny ACL for LLAP daemon management.</description>
+  </property>
+  <property>
+    <name>hive.llap.remote.token.requires.signing</name>
+    <value>true</value>
+    <description>
+      Expects one of [false, except_llap_owner, true].
+      Whether the token returned from LLAP management API should require fragment signing.
+      True by default; can be disabled to allow CLI to get tokens from LLAP in a secure
+      cluster by setting it to true or 'except_llap_owner' (the latter returns such tokens
+      to everyone except the user LLAP cluster is authenticating under).
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.delegation.token.lifetime</name>
+    <value>14d</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      LLAP delegation token lifetime, in seconds if specified without a unit.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.management.rpc.port</name>
+    <value>15004</value>
+    <description>RPC port for LLAP daemon management service.</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.auth</name>
+    <value>false</value>
+    <description>Whether or not to set Hadoop configs to enable auth in LLAP web app.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.rpc.num.handlers</name>
+    <value>5</value>
+    <description>Number of RPC handlers for LLAP daemon.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.work.dirs</name>
+    <value/>
+    <description>
+      Working directories for the daemon. Needs to be set for a secure cluster, since LLAP may
+      not have access to the default YARN working directories. yarn.nodemanager.local-dirs is
+      used if this is not set
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.yarn.shuffle.port</name>
+    <value>15551</value>
+    <description>YARN shuffle port for LLAP-daemon-hosted shuffle.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.yarn.container.mb</name>
+    <value>-1</value>
+    <description>llap server yarn container size in MB. Used in LlapServiceDriver and package.py</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.queue.name</name>
+    <value/>
+    <description>Queue name within which the llap slider application will run. Used in LlapServiceDriver and package.py</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.container.id</name>
+    <value/>
+    <description>ContainerId of a running LlapDaemon. Used to publish to the registry</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.shuffle.dir.watcher.enabled</name>
+    <value>false</value>
+    <description>TODO doc</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.am.liveness.heartbeat.interval.ms</name>
+    <value>10000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Tez AM-LLAP heartbeat interval (milliseconds). This needs to be below the task timeout
+      interval, but otherwise as high as possible to avoid unnecessary traffic.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.am.liveness.connection.timeout.ms</name>
+    <value>10000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Amount of time to wait on connection failures to the AM from an LLAP daemon before
+      considering the AM to be dead.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.am.liveness.connection.sleep.between.retries.ms</name>
+    <value>2000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Sleep duration while waiting to retry connection failures to the AM from the daemon for
+      the general keep-alive thread (milliseconds).
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.scheduler.timeout.seconds</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Amount of time to wait before failing the query when there are no llap daemons running
+      (alive) in the cluster.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.num.executors</name>
+    <value>4</value>
+    <description>
+      Number of executors to use in LLAP daemon; essentially, the number of tasks that can be
+      executed in parallel.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.rpc.port</name>
+    <value>15001</value>
+    <description>The LLAP daemon RPC port.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.memory.per.instance.mb</name>
+    <value>4096</value>
+    <description>The total amount of memory to use for the executors inside LLAP (in megabytes).</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.vcpus.per.instance</name>
+    <value>4</value>
+    <description>The total number of vcpus to use for the executors inside LLAP.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.num.file.cleaner.threads</name>
+    <value>1</value>
+    <description>Number of file cleaner threads in LLAP.</description>
+  </property>
+  <property>
+    <name>hive.llap.file.cleanup.delay.seconds</name>
+    <value>300s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      How long to delay before cleaning up query files in LLAP (in seconds, for debugging).
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.service.hosts</name>
+    <value/>
+    <description>
+      Explicitly specified hosts to use for LLAP scheduling. Useful for testing. By default,
+      YARN registry is used.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.service.refresh.interval.sec</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      LLAP YARN registry service list refresh delay, in seconds.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.communicator.num.threads</name>
+    <value>10</value>
+    <description>Number of threads to use in LLAP task communicator in Tez AM.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.download.permanent.fns</name>
+    <value>false</value>
+    <description>Whether LLAP daemon should localize the resources for permanent UDFs.</description>
+  </property>
+  <property>
+    <name>hive.llap.task.scheduler.node.reenable.min.timeout.ms</name>
+    <value>200ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Minimum time after which a previously disabled node will be re-enabled for scheduling,
+      in milliseconds. This may be modified by an exponential back-off if failures persist.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.scheduler.node.reenable.max.timeout.ms</name>
+    <value>10000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Maximum time after which a previously disabled node will be re-enabled for scheduling,
+      in milliseconds. This may be modified by an exponential back-off if failures persist.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.scheduler.node.disable.backoff.factor</name>
+    <value>1.5</value>
+    <description>
+      Backoff factor on successive blacklists of a node due to some failures. Blacklist times
+      start at the min timeout and go up to the max timeout based on this backoff factor.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.scheduler.num.schedulable.tasks.per.node</name>
+    <value>0</value>
+    <description>
+      The number of tasks the AM TaskScheduler will try allocating per node. 0 indicates that
+      this should be picked up from the Registry. -1 indicates unlimited capacity; positive
+      values indicate a specific bound.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.scheduler.locality.delay</name>
+    <value>0ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      The time should be in between -1 msec (inclusive) and 9223372036854775807 msec (inclusive).
+      Amount of time to wait before allocating a request which contains location information, to a location other than the ones requested. Set to -1 for an infinite delay, 0for no delay.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.task.preemption.metrics.intervals</name>
+    <value>30,60,300</value>
+    <description>
+      Comma-delimited set of integers denoting the desired rollover intervals (in seconds)
+       for percentile latency metrics. Used by LLAP daemon task scheduler metrics for
+       time taken to kill task (due to pre-emption) and useful time wasted by the task that
+       is about to be preempted.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.task.scheduler.wait.queue.size</name>
+    <value>10</value>
+    <description>LLAP scheduler maximum queue size.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.wait.queue.comparator.class.name</name>
+    <value>org.apache.hadoop.hive.llap.daemon.impl.comparator.ShortestJobFirstComparator</value>
+    <description>
+      The priority comparator to use for LLAP scheduler prioroty queue. The built-in options
+      are org.apache.hadoop.hive.llap.daemon.impl.comparator.ShortestJobFirstComparator and
+      .....FirstInFirstOutComparator
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.task.scheduler.enable.preemption</name>
+    <value>true</value>
+    <description>
+      Whether non-finishable running tasks (e.g. a reducer waiting for inputs) should be
+      preempted by finishable tasks inside LLAP scheduler.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.communicator.connection.timeout.ms</name>
+    <value>16000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Connection timeout (in milliseconds) before a failure to an LLAP daemon from Tez AM.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.communicator.connection.sleep.between.retries.ms</name>
+    <value>2000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Sleep duration (in milliseconds) to wait before retrying on error when obtaining a
+      connection to LLAP daemon from Tez AM.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.web.port</name>
+    <value>15002</value>
+    <description>LLAP daemon web UI port.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.web.ssl</name>
+    <value>false</value>
+    <description>Whether LLAP daemon web UI should use SSL.</description>
+  </property>
+  <property>
+    <name>hive.llap.client.consistent.splits</name>
+    <value>false</value>
+    <description>Whether to setup split locations to match nodes on which llap daemons are running, instead of using the locations provided by the split itself</description>
+  </property>
+  <property>
+    <name>hive.llap.validate.acls</name>
+    <value>true</value>
+    <description>
+      Whether LLAP should reject permissive ACLs in some cases (e.g. its own management
+      protocol or ZK paths), similar to how ssh refuses a key with bad access permissions.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.output.service.port</name>
+    <value>15003</value>
+    <description>LLAP daemon output service port</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.output.service.send.buffer.size</name>
+    <value>131072</value>
+    <description>Send buffer size to be used by LLAP daemon output service</description>
+  </property>
+  <property>
+    <name>hive.llap.enable.grace.join.in.llap</name>
+    <value>false</value>
+    <description>Override if grace join should be allowed to run in llap.</description>
+  </property>
+  <property>
+    <name>hive.spark.client.future.timeout</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Timeout for requests from Hive client to remote Spark driver.
+    </description>
+  </property>
+  <property>
+    <name>hive.spark.job.monitor.timeout</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Timeout for job monitor to get Spark job state.
+    </description>
+  </property>
+  <property>
+    <name>hive.spark.client.connect.timeout</name>
+    <value>1000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Timeout for remote Spark driver in connecting back to Hive client.
+    </description>
+  </property>
+  <property>
+    <name>hive.spark.client.server.connect.timeout</name>
+    <value>90000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Timeout for handshake between Hive client and remote Spark driver.  Checked by both processes.
+    </description>
+  </property>
+  <property>
+    <name>hive.spark.client.secret.bits</name>
+    <value>256</value>
+    <description>Number of bits of randomness in the generated secret for communication between Hive client and remote Spark driver. Rounded down to the nearest multiple of 8.</description>
+  </property>
+  <property>
+    <name>hive.spark.client.rpc.threads</name>
+    <value>8</value>
+    <description>Maximum number of threads for remote Spark driver's RPC event loop.</description>
+  </property>
+  <property>
+    <name>hive.spark.client.rpc.max.size</name>
+    <value>52428800</value>
+    <description>Maximum message size in bytes for communication between Hive client and remote Spark driver. Default is 50MB.</description>
+  </property>
+  <property>
+    <name>hive.spark.client.channel.log.level</name>
+    <value/>
+    <description>Channel logging level for remote Spark driver.  One of {DEBUG, ERROR, INFO, TRACE, WARN}.</description>
+  </property>
+  <property>
+    <name>hive.spark.client.rpc.sasl.mechanisms</name>
+    <value>DIGEST-MD5</value>
+    <description>Name of the SASL mechanism to use for authentication.</description>
+  </property>
+  <property>
+    <name>hive.spark.client.rpc.server.address</name>
+    <value/>
+    <description>The server address of HiverServer2 host to be used for communication between Hive client and remote Spark driver. Default is empty, which means the address will be determined in the same way as for hive.server2.thrift.bind.host.This is only necessary if the host has mutiple network addresses and if a different network address other than hive.server2.thrift.bind.host is to be used.</description>
+  </property>
+  <property>
+    <name>hive.spark.dynamic.partition.pruning</name>
+    <value>false</value>
+    <description>
+      When dynamic pruning is enabled, joins on partition keys will be processed by writing
+      to a temporary HDFS file, and read later for removing unnecessary partitions.
+    </description>
+  </property>
+  <property>
+    <name>hive.spark.dynamic.partition.pruning.max.data.size</name>
+    <value>104857600</value>
+    <description>Maximum total data size in dynamic pruning.</description>
+  </property>
+  <property>
+    <name>hive.reorder.nway.joins</name>
+    <value>true</value>
+    <description>Runs reordering of tables within single n-way join (i.e.: picks streamtable)</description>
+  </property>
+  <property>
+    <name>hive.log.every.n.records</name>
+    <value>0</value>
+    <description>
+      Expects value bigger than 0.
+      If value is greater than 0 logs in fixed intervals of size n rather than exponentially.
+    </description>
+  </property>
+  <property>
+    <name>hive.msck.path.validation</name>
+    <value>throw</value>
+    <description>
+      Expects one of [throw, skip, ignore].
+      The approach msck should take with HDFS directories that are partition-like but contain unsupported characters. 'throw' (an exception) is the default; 'skip' will skip the invalid directories and still repair the others; 'ignore' will skip the validation (legacy behavior, causes bugs in many cases)
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.llap.concurrent.queries</name>
+    <value>-1</value>
+    <description>The number of queries allowed in parallel via llap. Negative number implies 'infinite'.</description>
+  </property>
+  <property>
+    <name>hive.tez.enable.memory.manager</name>
+    <value>true</value>
+    <description>Enable memory manager for tez</description>
+  </property>
+  <property>
+    <name>hive.hash.table.inflation.factor</name>
+    <value>2.0</value>
+    <description>Expected inflation factor between disk/in memory representation of hash tables</description>
+  </property>
+  <property>
+    <name>hive.log.trace.id</name>
+    <value/>
+    <description>Log tracing id that can be used by upstream clients for tracking respective logs. Truncated to 64 characters. Defaults to use auto-generated session id.</description>
+  </property>
+  <property>
+    <name>hive.conf.restricted.list</name>
+    <value>hive.security.authenticator.manager,hive.security.authorization.manager,hive.users.in.admin.role,hive.server2.xsrf.filter.enabled</value>
+    <description>Comma separated list of configuration options which are immutable at runtime</description>
+  </property>
+  <property>
+    <name>hive.conf.hidden.list</name>
+    <value>javax.jdo.option.ConnectionPassword,hive.server2.keystore.password</value>
+    <description>Comma separated list of configuration options which should not be read by normal user like passwords</description>
+  </property>
+  <property>
+    <name>hive.conf.internal.variable.list</name>
+    <value>hive.added.files.path,hive.added.jars.path,hive.added.archives.path</value>
+    <description>Comma separated list of variables which are used internally and should not be configurable.</description>
+  </property>
+</configuration>

container/conf/java/hive/hive-env.sh

@@ -0,0 +1,54 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Set Hive and Hadoop environment variables here. These variables can be used
+# to control the execution of Hive. It should be used by admins to configure
+# the Hive installation (so that users do not have to set environment variables
+# or set command line parameters to get correct behavior).
+#
+# The hive service being invoked (CLI/HWI etc.) is available via the environment
+# variable SERVICE
+
+
+# Hive Client memory usage can be an issue if a large number of clients
+# are running at the same time. The flags below have been useful in 
+# reducing memory usage:
+#
+# if [ "$SERVICE" = "cli" ]; then
+#   if [ -z "$DEBUG" ]; then
+#     export HADOOP_OPTS="$HADOOP_OPTS -XX:NewRatio=12 -Xms10m -XX:MaxHeapFreeRatio=40 -XX:MinHeapFreeRatio=15 -XX:+UseParNewGC -XX:-UseGCOverheadLimit"
+#   else
+#     export HADOOP_OPTS="$HADOOP_OPTS -XX:NewRatio=12 -Xms10m -XX:MaxHeapFreeRatio=40 -XX:MinHeapFreeRatio=15 -XX:-UseGCOverheadLimit"
+#   fi
+# fi
+
+# The heap size of the jvm stared by hive shell script can be controlled via:
+#
+# export HADOOP_HEAPSIZE=1024
+#
+# Larger heap size may be required when running queries over large number of files or partitions. 
+# By default hive shell scripts use a heap size of 256 (MB).  Larger heap size would also be 
+# appropriate for hive server (hwi etc).
+
+
+# Set HADOOP_HOME to point to a specific hadoop install directory
+# HADOOP_HOME=${bin}/../../hadoop
+
+# Hive Configuration Directory can be controlled by:
+# export HIVE_CONF_DIR=
+
+# Folder containing extra ibraries required for hive compilation/execution can be controlled by:
+# export HIVE_AUX_JARS_PATH=

container/conf/java/hive/hive-exec-log4j2.properties

@@ -0,0 +1,66 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+status = INFO
+name = HiveExecLog4j2
+packages = org.apache.hadoop.hive.ql.log
+
+# list of properties
+property.hive.log.level = INFO
+property.hive.root.logger = FA
+property.hive.query.id = hadoop
+property.hive.log.dir = ${sys:java.io.tmpdir}/${sys:user.name}
+property.hive.log.file = ${sys:hive.query.id}.log
+
+# list of all appenders
+appenders = console, FA
+
+# console appender
+appender.console.type = Console
+appender.console.name = console
+appender.console.target = SYSTEM_ERR
+appender.console.layout.type = PatternLayout
+appender.console.layout.pattern = %d{ISO8601} %5p [%t] %c{2}: %m%n
+
+# simple file appender
+appender.FA.type = RandomAccessFile
+appender.FA.name = FA
+appender.FA.fileName = ${sys:hive.log.dir}/${sys:hive.log.file}
+appender.FA.layout.type = PatternLayout
+appender.FA.layout.pattern = %d{ISO8601} %5p [%t] %c{2}: %m%n
+
+# list of all loggers
+loggers = NIOServerCnxn, ClientCnxnSocketNIO, DataNucleus, Datastore, JPOX
+
+logger.NIOServerCnxn.name = org.apache.zookeeper.server.NIOServerCnxn
+logger.NIOServerCnxn.level = WARN
+
+logger.ClientCnxnSocketNIO.name = org.apache.zookeeper.ClientCnxnSocketNIO
+logger.ClientCnxnSocketNIO.level = WARN
+
+logger.DataNucleus.name = DataNucleus
+logger.DataNucleus.level = ERROR
+
+logger.Datastore.name = Datastore
+logger.Datastore.level = ERROR
+
+logger.JPOX.name = JPOX
+logger.JPOX.level = ERROR
+
+# root logger
+rootLogger.level = ${sys:hive.log.level}
+rootLogger.appenderRefs = root
+rootLogger.appenderRef.root.ref = ${sys:hive.root.logger}

container/conf/java/hive/hive-log4j2.properties

@@ -0,0 +1,77 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+status = INFO
+name = HiveLog4j2
+packages = org.apache.hadoop.hive.ql.log
+
+# list of properties
+property.hive.log.level = INFO
+property.hive.root.logger = DRFA
+property.hive.log.dir = ${sys:java.io.tmpdir}/${sys:user.name}
+property.hive.log.file = hive.log
+property.hive.perflogger.log.level = INFO
+
+# list of all appenders
+appenders = console, DRFA
+
+# console appender
+appender.console.type = Console
+appender.console.name = console
+appender.console.target = SYSTEM_ERR
+appender.console.layout.type = PatternLayout
+appender.console.layout.pattern = %d{ISO8601} %5p [%t] %c{2}: %m%n
+
+# daily rolling file appender
+appender.DRFA.type = RollingRandomAccessFile
+appender.DRFA.name = DRFA
+appender.DRFA.fileName = ${sys:hive.log.dir}/${sys:hive.log.file}
+# Use %pid in the filePattern to append <process-id>@<host-name> to the filename if you want separate log files for different CLI session
+appender.DRFA.filePattern = ${sys:hive.log.dir}/${sys:hive.log.file}.%d{yyyy-MM-dd}
+appender.DRFA.layout.type = PatternLayout
+appender.DRFA.layout.pattern = %d{ISO8601} %5p [%t] %c{2}: %m%n
+appender.DRFA.policies.type = Policies
+appender.DRFA.policies.time.type = TimeBasedTriggeringPolicy
+appender.DRFA.policies.time.interval = 1
+appender.DRFA.policies.time.modulate = true
+appender.DRFA.strategy.type = DefaultRolloverStrategy
+appender.DRFA.strategy.max = 30
+
+# list of all loggers
+loggers = NIOServerCnxn, ClientCnxnSocketNIO, DataNucleus, Datastore, JPOX, PerfLogger
+
+logger.NIOServerCnxn.name = org.apache.zookeeper.server.NIOServerCnxn
+logger.NIOServerCnxn.level = WARN
+
+logger.ClientCnxnSocketNIO.name = org.apache.zookeeper.ClientCnxnSocketNIO
+logger.ClientCnxnSocketNIO.level = WARN
+
+logger.DataNucleus.name = DataNucleus
+logger.DataNucleus.level = ERROR
+
+logger.Datastore.name = Datastore
+logger.Datastore.level = ERROR
+
+logger.JPOX.name = JPOX
+logger.JPOX.level = ERROR
+
+logger.PerfLogger.name = org.apache.hadoop.hive.ql.log.PerfLogger
+logger.PerfLogger.level = ${sys:hive.perflogger.log.level}
+
+# root logger
+rootLogger.level = ${sys:hive.log.level}
+rootLogger.appenderRefs = root
+rootLogger.appenderRef.root.ref = ${sys:hive.root.logger}

container/conf/java/hive/hive-site.xml

@@ -0,0 +1,5355 @@
+<?xml version="1.0" encoding="UTF-8" standalone="no"?>
+<?xml-stylesheet type="text/xsl" href="configuration.xsl"?><!--
+   Licensed to the Apache Software Foundation (ASF) under one or more
+   contributor license agreements.  See the NOTICE file distributed with
+   this work for additional information regarding copyright ownership.
+   The ASF licenses this file to You under the Apache License, Version 2.0
+   (the "License"); you may not use this file except in compliance with
+   the License.  You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+--><configuration>
+  <!-- WARNING!!! This file is auto generated for documentation purposes ONLY! -->
+  <!-- WARNING!!! Any changes you make to this file will be ignored by Hive.   -->
+  <!-- WARNING!!! You must make your changes in hive-site.xml instead.         -->
+  <!-- Hive Execution Parameters -->
+  <property>
+    <name>hive.exec.script.wrapper</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.plan</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.stagingdir</name>
+    <value>.hive-staging</value>
+    <description>Directory name that will be created inside table locations in order to support HDFS encryption. This is replaces ${hive.exec.scratchdir} for query results with the exception of read-only tables. In all cases ${hive.exec.scratchdir} is still used for other temporary files, such as job plans.</description>
+  </property>
+  <property>
+    <name>hive.exec.scratchdir</name>
+    <value>hdfs://data-hadoop:9000/hive/tmp</value>
+    <description>HDFS root scratch dir for Hive jobs which gets created with write all (733) permission. For each connecting user, an HDFS scratch dir: ${hive.exec.scratchdir}/&lt;username&gt; is created, with ${hive.scratch.dir.permission}.</description>
+  </property>
+  <property>
+    <name>hive.exec.local.scratchdir</name>
+    <value>/root/hive/tmp</value>
+    <description>Local scratch space for Hive jobs</description>
+  </property>
+  <property>
+    <name>hive.downloaded.resources.dir</name>
+    <value>/root/hive/tmp/${hive.session.id}_resources</value>
+    <description>Temporary local directory for added resources in the remote file system.</description>
+  </property>
+  <property>
+    <name>hive.scratch.dir.permission</name>
+    <value>700</value>
+    <description>The permission for the user specific scratch directories that get created.</description>
+  </property>
+  <property>
+    <name>hive.exec.submitviachild</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.submit.local.task.via.child</name>
+    <value>true</value>
+    <description>
+      Determines whether local tasks (typically mapjoin hashtable generation phase) runs in 
+      separate JVM (true recommended) or not. 
+      Avoids the overhead of spawning new JVM, but can lead to out-of-memory issues.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.script.maxerrsize</name>
+    <value>100000</value>
+    <description>
+      Maximum number of bytes a script is allowed to emit to standard error (per map-reduce task). 
+      This prevents runaway scripts from filling logs partitions to capacity
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.script.allow.partial.consumption</name>
+    <value>false</value>
+    <description>
+      When enabled, this option allows a user script to exit successfully without consuming 
+      all the data from the standard input.
+    </description>
+  </property>
+  <property>
+    <name>stream.stderr.reporter.prefix</name>
+    <value>reporter:</value>
+    <description>Streaming jobs that log to standard error with this prefix can log counter or status information.</description>
+  </property>
+  <property>
+    <name>stream.stderr.reporter.enabled</name>
+    <value>true</value>
+    <description>Enable consumption of status and counter messages for streaming jobs.</description>
+  </property>
+  <property>
+    <name>hive.exec.compress.output</name>
+    <value>false</value>
+    <description>
+      This controls whether the final outputs of a query (to a local/HDFS file or a Hive table) is compressed. 
+      The compression codec and other options are determined from Hadoop config variables mapred.output.compress*
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.compress.intermediate</name>
+    <value>false</value>
+    <description>
+      This controls whether intermediate files produced by Hive between multiple map-reduce jobs are compressed. 
+      The compression codec and other options are determined from Hadoop config variables mapred.output.compress*
+    </description>
+  </property>
+  <property>
+    <name>hive.intermediate.compression.codec</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.intermediate.compression.type</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.reducers.bytes.per.reducer</name>
+    <value>256000000</value>
+    <description>size per reducer.The default is 256Mb, i.e if the input size is 1G, it will use 4 reducers.</description>
+  </property>
+  <property>
+    <name>hive.exec.reducers.max</name>
+    <value>1009</value>
+    <description>
+      max number of reducers will be used. If the one specified in the configuration parameter mapred.reduce.tasks is
+      negative, Hive will use this one as the max number of reducers when automatically determine number of reducers.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.pre.hooks</name>
+    <value/>
+    <description>
+      Comma-separated list of pre-execution hooks to be invoked for each statement. 
+      A pre-execution hook is specified as the name of a Java class which implements the 
+      org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext interface.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.post.hooks</name>
+    <value/>
+    <description>
+      Comma-separated list of post-execution hooks to be invoked for each statement. 
+      A post-execution hook is specified as the name of a Java class which implements the 
+      org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext interface.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.failure.hooks</name>
+    <value/>
+    <description>
+      Comma-separated list of on-failure hooks to be invoked for each statement. 
+      An on-failure hook is specified as the name of Java class which implements the 
+      org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext interface.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.query.redactor.hooks</name>
+    <value/>
+    <description>
+      Comma-separated list of hooks to be invoked for each query which can 
+      tranform the query before it's placed in the job.xml file. Must be a Java class which 
+      extends from the org.apache.hadoop.hive.ql.hooks.Redactor abstract class.
+    </description>
+  </property>
+  <property>
+    <name>hive.client.stats.publishers</name>
+    <value/>
+    <description>
+      Comma-separated list of statistics publishers to be invoked on counters on each job. 
+      A client stats publisher is specified as the name of a Java class which implements the 
+      org.apache.hadoop.hive.ql.stats.ClientStatsPublisher interface.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.parallel</name>
+    <value>false</value>
+    <description>Whether to execute jobs in parallel</description>
+  </property>
+  <property>
+    <name>hive.exec.parallel.thread.number</name>
+    <value>8</value>
+    <description>How many jobs at most can be executed in parallel</description>
+  </property>
+  <property>
+    <name>hive.mapred.reduce.tasks.speculative.execution</name>
+    <value>true</value>
+    <description>Whether speculative execution for reducers should be turned on. </description>
+  </property>
+  <property>
+    <name>hive.exec.counters.pull.interval</name>
+    <value>1000</value>
+    <description>
+      The interval with which to poll the JobTracker for the counters the running job. 
+      The smaller it is the more load there will be on the jobtracker, the higher it is the less granular the caught will be.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.dynamic.partition</name>
+    <value>true</value>
+    <description>Whether or not to allow dynamic partitions in DML/DDL.</description>
+  </property>
+  <property>
+    <name>hive.exec.dynamic.partition.mode</name>
+    <value>strict</value>
+    <description>
+      In strict mode, the user must specify at least one static partition
+      in case the user accidentally overwrites all partitions.
+      In nonstrict mode all partitions are allowed to be dynamic.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.max.dynamic.partitions</name>
+    <value>1000</value>
+    <description>Maximum number of dynamic partitions allowed to be created in total.</description>
+  </property>
+  <property>
+    <name>hive.exec.max.dynamic.partitions.pernode</name>
+    <value>100</value>
+    <description>Maximum number of dynamic partitions allowed to be created in each mapper/reducer node.</description>
+  </property>
+  <property>
+    <name>hive.exec.max.created.files</name>
+    <value>100000</value>
+    <description>Maximum number of HDFS files created by all mappers/reducers in a MapReduce job.</description>
+  </property>
+  <property>
+    <name>hive.exec.default.partition.name</name>
+    <value>__HIVE_DEFAULT_PARTITION__</value>
+    <description>
+      The default partition name in case the dynamic partition column value is null/empty string or any other values that cannot be escaped. 
+      This value must not contain any special character used in HDFS URI (e.g., ':', '%', '/' etc). 
+      The user has to be aware that the dynamic partition value should not contain this value to avoid confusions.
+    </description>
+  </property>
+  <property>
+    <name>hive.lockmgr.zookeeper.default.partition.name</name>
+    <value>__HIVE_DEFAULT_ZOOKEEPER_PARTITION__</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.show.job.failure.debug.info</name>
+    <value>true</value>
+    <description>
+      If a job fails, whether to provide a link in the CLI to the task with the
+      most failures, along with debugging hints if applicable.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.job.debug.capture.stacktraces</name>
+    <value>true</value>
+    <description>
+      Whether or not stack traces parsed from the task logs of a sampled failed task 
+      for each failed job should be stored in the SessionState
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.job.debug.timeout</name>
+    <value>30000</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.tasklog.debug.timeout</name>
+    <value>20000</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.output.file.extension</name>
+    <value/>
+    <description>
+      String used as a file extension for output files. 
+      If not set, defaults to the codec extension for text files (e.g. ".gz"), or no extension otherwise.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.mode.local.auto</name>
+    <value>false</value>
+    <description>Let Hive determine whether to run in local mode automatically</description>
+  </property>
+  <property>
+    <name>hive.exec.mode.local.auto.inputbytes.max</name>
+    <value>134217728</value>
+    <description>When hive.exec.mode.local.auto is true, input bytes should less than this for local mode.</description>
+  </property>
+  <property>
+    <name>hive.exec.mode.local.auto.input.files.max</name>
+    <value>4</value>
+    <description>When hive.exec.mode.local.auto is true, the number of tasks should less than this for local mode.</description>
+  </property>
+  <property>
+    <name>hive.exec.drop.ignorenonexistent</name>
+    <value>true</value>
+    <description>Do not report an error if DROP TABLE/VIEW/Index/Function specifies a non-existent table/view/index/function</description>
+  </property>
+  <property>
+    <name>hive.ignore.mapjoin.hint</name>
+    <value>true</value>
+    <description>Ignore the mapjoin hint</description>
+  </property>
+  <property>
+    <name>hive.file.max.footer</name>
+    <value>100</value>
+    <description>maximum number of lines for footer user can define for a table file</description>
+  </property>
+  <property>
+    <name>hive.resultset.use.unique.column.names</name>
+    <value>true</value>
+    <description>
+      Make column names unique in the result set by qualifying column names with table alias if needed.
+      Table alias will be added to column names for queries of type "select *" or 
+      if query explicitly uses table alias "select r1.x..".
+    </description>
+  </property>
+  <property>
+    <name>fs.har.impl</name>
+    <value>org.apache.hadoop.hive.shims.HiveHarFileSystem</value>
+    <description>The implementation for accessing Hadoop Archives. Note that this won't be applicable to Hadoop versions less than 0.20</description>
+  </property>
+  <property>
+    <name>hive.metastore.warehouse.dir</name>
+    <value>hdfs://data-hadoop:9000/hive/warehouse</value>
+    <description>location of default database for the warehouse</description>
+  </property>
+  <property>
+    <name>hive.metastore.uris</name>
+    <value/>
+    <description>Thrift URI for the remote metastore. Used by metastore client to connect to remote metastore.</description>
+  </property>
+  <property>
+    <name>hive.metastore.fastpath</name>
+    <value>false</value>
+    <description>Used to avoid all of the proxies and object copies in the metastore.  Note, if this is set, you MUST use a local metastore (hive.metastore.uris must be empty) otherwise undefined and most likely undesired behavior will result</description>
+  </property>
+  <property>
+    <name>hive.metastore.fshandler.threads</name>
+    <value>20</value>
+    <description>Number of threads to be allocated for metastore handler for fs operations.</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.catalog.cache.size</name>
+    <value>50000</value>
+    <description>Maximum number of objects we will place in the hbase metastore catalog cache.  The objects will be divided up by types that we need to cache.</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggregate.stats.cache.size</name>
+    <value>10000</value>
+    <description>Maximum number of aggregate stats nodes that we will place in the hbase metastore aggregate stats cache.</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggregate.stats.max.partitions</name>
+    <value>10000</value>
+    <description>Maximum number of partitions that are aggregated per cache node.</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggregate.stats.false.positive.probability</name>
+    <value>0.01</value>
+    <description>Maximum false positive probability for the Bloom Filter used in each aggregate stats cache node (default 1%).</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggregate.stats.max.variance</name>
+    <value>0.1</value>
+    <description>Maximum tolerable variance in number of partitions between a cached node and our request (default 10%).</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.cache.ttl</name>
+    <value>600s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds for a cached node to be active in the cache before they become stale.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.cache.max.writer.wait</name>
+    <value>5000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Number of milliseconds a writer will wait to acquire the writelock before giving up.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.cache.max.reader.wait</name>
+    <value>1000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Number of milliseconds a reader will wait to acquire the readlock before giving up.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.cache.max.full</name>
+    <value>0.9</value>
+    <description>Maximum cache full % after which the cache cleaner thread kicks in.</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.cache.clean.until</name>
+    <value>0.8</value>
+    <description>The cleaner thread cleans until cache reaches this % full size.</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.connection.class</name>
+    <value>org.apache.hadoop.hive.metastore.hbase.VanillaHBaseConnection</value>
+    <description>Class used to connection to HBase</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggr.stats.cache.entries</name>
+    <value>10000</value>
+    <description>How many in stats objects to cache in memory</description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggr.stats.memory.ttl</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds stats objects live in memory after they are read from HBase.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggr.stats.invalidator.frequency</name>
+    <value>5s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      How often the stats cache scans its HBase entries and looks for expired entries
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.aggr.stats.hbase.ttl</name>
+    <value>604800s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds stats entries live in HBase cache after they are created.  They may be invalided by updates or partition drops before this.  Default is one week.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.hbase.file.metadata.threads</name>
+    <value>1</value>
+    <description>Number of threads to use to read file metadata in background to cache it.</description>
+  </property>
+  <property>
+    <name>hive.metastore.connect.retries</name>
+    <value>3</value>
+    <description>Number of retries while opening a connection to metastore</description>
+  </property>
+  <property>
+    <name>hive.metastore.failure.retries</name>
+    <value>1</value>
+    <description>Number of retries upon failure of Thrift metastore calls</description>
+  </property>
+  <property>
+    <name>hive.metastore.port</name>
+    <value>9083</value>
+    <description>Hive metastore listener port</description>
+  </property>
+  <property>
+    <name>hive.metastore.client.connect.retry.delay</name>
+    <value>1s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds for the client to wait between consecutive connection attempts
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.client.socket.timeout</name>
+    <value>600s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      MetaStore Client socket timeout in seconds
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.client.socket.lifetime</name>
+    <value>0s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      MetaStore Client socket lifetime in seconds. After this time is exceeded, client
+      reconnects on the next MetaStore operation. A value of 0s means the connection
+      has an infinite lifetime.
+    </description>
+  </property>
+  <property>
+    <name>javax.jdo.option.ConnectionPassword</name>
+    <!--value>mine</value-->
+    <value>123456</value>
+    <description>password to use against metastore database</description>
+  </property>
+  <property>
+    <name>hive.metastore.ds.connection.url.hook</name>
+    <value/>
+    <description>Name of the hook to use for retrieving the JDO connection URL. If empty, the value in javax.jdo.option.ConnectionURL is used</description>
+  </property>
+  <property>
+    <name>javax.jdo.option.Multithreaded</name>
+    <value>true</value>
+    <description>Set this to true if multiple threads access metastore through JDO concurrently.</description>
+  </property>
+  <property>
+    <name>javax.jdo.option.ConnectionURL</name>
+    <!--value>jdbc:derby:;databaseName=metastore_db;create=true</value-->
+    <value>jdbc:mysql://data-mysql:3306/hive?createDatabaseIfNotExist=true</value>
+    <description>
+      JDBC connect string for a JDBC metastore.
+      To use SSL to encrypt/authenticate the connection, provide database-specific SSL flag in the connection URL.
+      For example, jdbc:postgresql://myhost/db?ssl=true for postgres database.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.dbaccess.ssl.properties</name>
+    <value/>
+    <description>
+      Comma-separated SSL properties for metastore to access database when JDO connection URL
+      enables SSL access. e.g. javax.net.ssl.trustStore=/tmp/truststore,javax.net.ssl.trustStorePassword=pwd.
+    </description>
+  </property>
+  <property>
+    <name>hive.hmshandler.retry.attempts</name>
+    <value>10</value>
+    <description>The number of times to retry a HMSHandler call if there were a connection error.</description>
+  </property>
+  <property>
+    <name>hive.hmshandler.retry.interval</name>
+    <value>2000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      The time between HMSHandler retry attempts on failure.
+    </description>
+  </property>
+  <property>
+    <name>hive.hmshandler.force.reload.conf</name>
+    <value>false</value>
+    <description>
+      Whether to force reloading of the HMSHandler configuration (including
+      the connection URL, before the next metastore query that accesses the
+      datastore. Once reloaded, this value is reset to false. Used for
+      testing only.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.server.max.message.size</name>
+    <value>104857600</value>
+    <description>Maximum message size in bytes a HMS will accept.</description>
+  </property>
+  <property>
+    <name>hive.metastore.server.min.threads</name>
+    <value>200</value>
+    <description>Minimum number of worker threads in the Thrift server's pool.</description>
+  </property>
+  <property>
+    <name>hive.metastore.server.max.threads</name>
+    <value>1000</value>
+    <description>Maximum number of worker threads in the Thrift server's pool.</description>
+  </property>
+  <property>
+    <name>hive.metastore.server.tcp.keepalive</name>
+    <value>true</value>
+    <description>Whether to enable TCP keepalive for the metastore server. Keepalive will prevent accumulation of half-open connections.</description>
+  </property>
+  <property>
+    <name>hive.metastore.archive.intermediate.original</name>
+    <value>_INTERMEDIATE_ORIGINAL</value>
+    <description>
+      Intermediate dir suffixes used for archiving. Not important what they
+      are, as long as collisions are avoided
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.archive.intermediate.archived</name>
+    <value>_INTERMEDIATE_ARCHIVED</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.metastore.archive.intermediate.extracted</name>
+    <value>_INTERMEDIATE_EXTRACTED</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.metastore.kerberos.keytab.file</name>
+    <value/>
+    <description>The path to the Kerberos Keytab file containing the metastore Thrift server's service principal.</description>
+  </property>
+  <property>
+    <name>hive.metastore.kerberos.principal</name>
+    <value>hive-metastore/_HOST@EXAMPLE.COM</value>
+    <description>
+      The service principal for the metastore Thrift server. 
+      The special string _HOST will be replaced automatically with the correct host name.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.sasl.enabled</name>
+    <value>false</value>
+    <description>If true, the metastore Thrift interface will be secured with SASL. Clients must authenticate with Kerberos.</description>
+  </property>
+  <property>
+    <name>hive.metastore.thrift.framed.transport.enabled</name>
+    <value>false</value>
+    <description>If true, the metastore Thrift interface will use TFramedTransport. When false (default) a standard TTransport is used.</description>
+  </property>
+  <property>
+    <name>hive.metastore.thrift.compact.protocol.enabled</name>
+    <value>false</value>
+    <description>
+      If true, the metastore Thrift interface will use TCompactProtocol. When false (default) TBinaryProtocol will be used.
+      Setting it to true will break compatibility with older clients running TBinaryProtocol.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.token.signature</name>
+    <value/>
+    <description>The delegation token service name to match when selecting a token from the current user's tokens.</description>
+  </property>
+  <property>
+    <name>hive.cluster.delegation.token.store.class</name>
+    <value>org.apache.hadoop.hive.thrift.MemoryTokenStore</value>
+    <description>The delegation token store implementation. Set to org.apache.hadoop.hive.thrift.ZooKeeperTokenStore for load-balanced cluster.</description>
+  </property>
+  <property>
+    <name>hive.cluster.delegation.token.store.zookeeper.connectString</name>
+    <value/>
+    <description>
+      The ZooKeeper token store connect string. You can re-use the configuration value
+      set in hive.zookeeper.quorum, by leaving this parameter unset.
+    </description>
+  </property>
+  <property>
+    <name>hive.cluster.delegation.token.store.zookeeper.znode</name>
+    <value>/hivedelegation</value>
+    <description>
+      The root path for token store data. Note that this is used by both HiveServer2 and
+      MetaStore to store delegation Token. One directory gets created for each of them.
+      The final directory names would have the servername appended to it (HIVESERVER2,
+      METASTORE).
+    </description>
+  </property>
+  <property>
+    <name>hive.cluster.delegation.token.store.zookeeper.acl</name>
+    <value/>
+    <description>
+      ACL for token store entries. Comma separated list of ACL entries. For example:
+      sasl:hive/host1@MY.DOMAIN:cdrwa,sasl:hive/host2@MY.DOMAIN:cdrwa
+      Defaults to all permissions for the hiveserver2/metastore process user.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.cache.pinobjtypes</name>
+    <value>Table,StorageDescriptor,SerDeInfo,Partition,Database,Type,FieldSchema,Order</value>
+    <description>List of comma separated metastore object types that should be pinned in the cache</description>
+  </property>
+  <property>
+    <name>datanucleus.connectionPoolingType</name>
+    <value>BONECP</value>
+    <description>Specify connection pool library for datanucleus</description>
+  </property>
+  <property>
+    <name>datanucleus.rdbms.initializeColumnInfo</name>
+    <value>NONE</value>
+    <description>initializeColumnInfo setting for DataNucleus; set to NONE at least on Postgres.</description>
+  </property>
+  <property>
+    <name>datanucleus.schema.validateTables</name>
+    <value>false</value>
+    <description>validates existing schema against code. turn this on if you want to verify existing schema</description>
+  </property>
+  <property>
+    <name>datanucleus.schema.validateColumns</name>
+    <value>false</value>
+    <description>validates existing schema against code. turn this on if you want to verify existing schema</description>
+  </property>
+  <property>
+    <name>datanucleus.schema.validateConstraints</name>
+    <value>false</value>
+    <description>validates existing schema against code. turn this on if you want to verify existing schema</description>
+  </property>
+  <property>
+    <name>datanucleus.storeManagerType</name>
+    <value>rdbms</value>
+    <description>metadata store type</description>
+  </property>
+  <property>
+    <name>datanucleus.schema.autoCreateAll</name>
+    <value>true</value>
+    <description>Auto creates necessary schema on a startup if one doesn't exist. Set this to false, after creating it once.To enable auto create also set hive.metastore.schema.verification=false. Auto creation is not recommended for production use cases, run schematool command instead.</description>
+  </property>
+  <property>
+    <name>hive.metastore.schema.verification</name>
+    <value>true</value>
+    <description>
+      Enforce metastore schema version consistency.
+      True: Verify that version information stored in is compatible with one from Hive jars.  Also disable automatic
+            schema migration attempt. Users are required to manually migrate schema after Hive upgrade which ensures
+            proper metastore schema migration. (Default)
+      False: Warn if the version information stored in metastore doesn't match with one from in Hive jars.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.schema.verification.record.version</name>
+    <value>false</value>
+    <description>
+      When true the current MS version is recorded in the VERSION table. If this is disabled and verification is
+       enabled the MS will be unusable.
+    </description>
+  </property>
+  <property>
+    <name>datanucleus.transactionIsolation</name>
+    <value>read-committed</value>
+    <description>Default transaction isolation level for identity generation.</description>
+  </property>
+  <property>
+    <name>datanucleus.cache.level2</name>
+    <value>false</value>
+    <description>Use a level 2 cache. Turn this off if metadata is changed independently of Hive metastore server</description>
+  </property>
+  <property>
+    <name>datanucleus.cache.level2.type</name>
+    <value>none</value>
+    <description/>
+  </property>
+  <property>
+    <name>datanucleus.identifierFactory</name>
+    <value>datanucleus1</value>
+    <description>
+      Name of the identifier factory to use when generating table/column names etc. 
+      'datanucleus1' is used for backward compatibility with DataNucleus v1
+    </description>
+  </property>
+  <property>
+    <name>datanucleus.rdbms.useLegacyNativeValueStrategy</name>
+    <value>true</value>
+    <description/>
+  </property>
+  <property>
+    <name>datanucleus.plugin.pluginRegistryBundleCheck</name>
+    <value>LOG</value>
+    <description>Defines what happens when plugin bundles are found and are duplicated [EXCEPTION|LOG|NONE]</description>
+  </property>
+  <property>
+    <name>hive.metastore.batch.retrieve.max</name>
+    <value>300</value>
+    <description>
+      Maximum number of objects (tables/partitions) can be retrieved from metastore in one batch. 
+      The higher the number, the less the number of round trips is needed to the Hive metastore server, 
+      but it may also cause higher memory requirement at the client side.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.batch.retrieve.table.partition.max</name>
+    <value>1000</value>
+    <description>Maximum number of objects that metastore internally retrieves in one batch.</description>
+  </property>
+  <property>
+    <name>hive.metastore.init.hooks</name>
+    <value/>
+    <description>
+      A comma separated list of hooks to be invoked at the beginning of HMSHandler initialization. 
+      An init hook is specified as the name of Java class which extends org.apache.hadoop.hive.metastore.MetaStoreInitListener.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.pre.event.listeners</name>
+    <value/>
+    <description>List of comma separated listeners for metastore events.</description>
+  </property>
+  <property>
+    <name>hive.metastore.event.listeners</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.metastore.event.db.listener.timetolive</name>
+    <value>86400s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      time after which events will be removed from the database listener queue
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.authorization.storage.checks</name>
+    <value>false</value>
+    <description>
+      Should the metastore do authorization checks against the underlying storage (usually hdfs) 
+      for operations like drop-partition (disallow the drop-partition if the user in
+      question doesn't have permissions to delete the corresponding directory
+      on the storage).
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.event.clean.freq</name>
+    <value>0s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Frequency at which timer task runs to purge expired events in metastore.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.event.expiry.duration</name>
+    <value>0s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Duration after which events expire from events table
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.execute.setugi</name>
+    <value>true</value>
+    <description>
+      In unsecure mode, setting this property to true will cause the metastore to execute DFS operations using 
+      the client's reported user and group permissions. Note that this property must be set on 
+      both the client and server sides. Further note that its best effort. 
+      If client sets its to true and server sets it to false, client setting will be ignored.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.partition.name.whitelist.pattern</name>
+    <value/>
+    <description>Partition names will be checked against this regex pattern and rejected if not matched.</description>
+  </property>
+  <property>
+    <name>hive.metastore.integral.jdo.pushdown</name>
+    <value>false</value>
+    <description>
+      Allow JDO query pushdown for integral partition columns in metastore. Off by default. This
+      improves metastore perf for integral columns, especially if there's a large number of partitions.
+      However, it doesn't work correctly with integral values that are not normalized (e.g. have
+      leading zeroes, like 0012). If metastore direct SQL is enabled and works, this optimization
+      is also irrelevant.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.try.direct.sql</name>
+    <value>true</value>
+    <description>
+      Whether the Hive metastore should try to use direct SQL queries instead of the
+      DataNucleus for certain read paths. This can improve metastore performance when
+      fetching many partitions or column statistics by orders of magnitude; however, it
+      is not guaranteed to work on all RDBMS-es and all versions. In case of SQL failures,
+      the metastore will fall back to the DataNucleus, so it's safe even if SQL doesn't
+      work for all queries on your datastore. If all SQL queries fail (for example, your
+      metastore is backed by MongoDB), you might want to disable this to save the
+      try-and-fall-back cost.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.direct.sql.batch.size</name>
+    <value>0</value>
+    <description>
+      Batch size for partition and other object retrieval from the underlying DB in direct
+      SQL. For some DBs like Oracle and MSSQL, there are hardcoded or perf-based limitations
+      that necessitate this. For DBs that can handle the queries, this isn't necessary and
+      may impede performance. -1 means no batching, 0 means automatic batching.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.try.direct.sql.ddl</name>
+    <value>true</value>
+    <description>
+      Same as hive.metastore.try.direct.sql, for read statements within a transaction that
+      modifies metastore data. Due to non-standard behavior in Postgres, if a direct SQL
+      select query has incorrect syntax or something similar inside a transaction, the
+      entire transaction will fail and fall-back to DataNucleus will not be possible. You
+      should disable the usage of direct SQL inside transactions if that happens in your case.
+    </description>
+  </property>
+  <property>
+    <name>hive.direct.sql.max.query.length</name>
+    <value>100</value>
+    <description>
+      The maximum
+       size of a query string (in KB).
+    </description>
+  </property>
+  <property>
+    <name>hive.direct.sql.max.elements.in.clause</name>
+    <value>1000</value>
+    <description>
+      The maximum number of values in a IN clause. Once exceeded, it will be broken into
+       multiple OR separated IN clauses.
+    </description>
+  </property>
+  <property>
+    <name>hive.direct.sql.max.elements.values.clause</name>
+    <value>1000</value>
+    <description>The maximum number of values in a VALUES clause for INSERT statement.</description>
+  </property>
+  <property>
+    <name>hive.metastore.orm.retrieveMapNullsAsEmptyStrings</name>
+    <value>false</value>
+    <description>Thrift does not support nulls in maps, so any nulls present in maps retrieved from ORM must either be pruned or converted to empty strings. Some backing dbs such as Oracle persist empty strings as nulls, so we should set this parameter if we wish to reverse that behaviour. For others, pruning is the correct behaviour</description>
+  </property>
+  <property>
+    <name>hive.metastore.disallow.incompatible.col.type.changes</name>
+    <value>true</value>
+    <description>
+      If true (default is false), ALTER TABLE operations which change the type of a
+      column (say STRING) to an incompatible type (say MAP) are disallowed.
+      RCFile default SerDe (ColumnarSerDe) serializes the values in such a way that the
+      datatypes can be converted from string to any type. The map is also serialized as
+      a string, which can be read as a string as well. However, with any binary
+      serialization, this is not true. Blocking the ALTER TABLE prevents ClassCastExceptions
+      when subsequently trying to access old partitions.
+      
+      Primitive types like INT, STRING, BIGINT, etc., are compatible with each other and are
+      not blocked.
+      
+      See HIVE-4409 for more details.
+    </description>
+  </property>
+  <property>
+    <name>hive.table.parameters.default</name>
+    <value/>
+    <description>Default property values for newly created tables</description>
+  </property>
+  <property>
+    <name>hive.ddl.createtablelike.properties.whitelist</name>
+    <value/>
+    <description>Table Properties to copy over when executing a Create Table Like.</description>
+  </property>
+  <property>
+    <name>hive.metastore.rawstore.impl</name>
+    <value>org.apache.hadoop.hive.metastore.ObjectStore</value>
+    <description>
+      Name of the class that implements org.apache.hadoop.hive.metastore.rawstore interface. 
+      This class is used to store and retrieval of raw metadata objects such as table, database
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.txn.store.impl</name>
+    <value>org.apache.hadoop.hive.metastore.txn.CompactionTxnHandler</value>
+    <description>Name of class that implements org.apache.hadoop.hive.metastore.txn.TxnStore.  This class is used to store and retrieve transactions and locks</description>
+  </property>
+  <property>
+    <name>javax.jdo.option.ConnectionDriverName</name>
+    <!--value>org.apache.derby.jdbc.EmbeddedDriver</value-->
+    <!--value>com.mariadb.jdbc.Driver</value-->
+    <value>com.mysql.jdbc.Driver</value>
+    <description>Driver class name for a JDBC metastore</description>
+  </property>
+  <property>
+    <name>javax.jdo.PersistenceManagerFactoryClass</name>
+    <value>org.datanucleus.api.jdo.JDOPersistenceManagerFactory</value>
+    <description>class implementing the jdo persistence</description>
+  </property>
+  <property>
+    <name>hive.metastore.expression.proxy</name>
+    <value>org.apache.hadoop.hive.ql.optimizer.ppr.PartitionExpressionForMetastore</value>
+    <description/>
+  </property>
+  <property>
+    <name>javax.jdo.option.DetachAllOnCommit</name>
+    <value>true</value>
+    <description>Detaches all objects from session so that they can be used after transaction is committed</description>
+  </property>
+  <property>
+    <name>javax.jdo.option.NonTransactionalRead</name>
+    <value>true</value>
+    <description>Reads outside of transactions</description>
+  </property>
+  <property>
+    <name>javax.jdo.option.ConnectionUserName</name>
+    <!--value>APP</value-->
+    <value>root</value>
+    <description>Username to use against metastore database</description>
+  </property>
+  <property>
+    <name>hive.metastore.end.function.listeners</name>
+    <value/>
+    <description>List of comma separated listeners for the end of metastore functions.</description>
+  </property>
+  <property>
+    <name>hive.metastore.partition.inherit.table.properties</name>
+    <value/>
+    <description>
+      List of comma separated keys occurring in table properties which will get inherited to newly created partitions. 
+      * implies all the keys will get inherited.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.filter.hook</name>
+    <value>org.apache.hadoop.hive.metastore.DefaultMetaStoreFilterHookImpl</value>
+    <description>Metastore hook class for filtering the metadata read results. If hive.security.authorization.manageris set to instance of HiveAuthorizerFactory, then this value is ignored.</description>
+  </property>
+  <property>
+    <name>hive.metastore.dml.events</name>
+    <value>false</value>
+    <description>If true, the metastore will be asked to fire events for DML operations</description>
+  </property>
+  <property>
+    <name>hive.metastore.client.drop.partitions.using.expressions</name>
+    <value>true</value>
+    <description>Choose whether dropping partitions with HCatClient pushes the partition-predicate to the metastore, or drops partitions iteratively</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.enabled</name>
+    <value>true</value>
+    <description>Whether aggregate stats caching is enabled or not.</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.size</name>
+    <value>10000</value>
+    <description>Maximum number of aggregate stats nodes that we will place in the metastore aggregate stats cache.</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.max.partitions</name>
+    <value>10000</value>
+    <description>Maximum number of partitions that are aggregated per cache node.</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.fpp</name>
+    <value>0.01</value>
+    <description>Maximum false positive probability for the Bloom Filter used in each aggregate stats cache node (default 1%).</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.max.variance</name>
+    <value>0.01</value>
+    <description>Maximum tolerable variance in number of partitions between a cached node and our request (default 1%).</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.ttl</name>
+    <value>600s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds for a cached node to be active in the cache before they become stale.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.max.writer.wait</name>
+    <value>5000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Number of milliseconds a writer will wait to acquire the writelock before giving up.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.max.reader.wait</name>
+    <value>1000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Number of milliseconds a reader will wait to acquire the readlock before giving up.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.max.full</name>
+    <value>0.9</value>
+    <description>Maximum cache full % after which the cache cleaner thread kicks in.</description>
+  </property>
+  <property>
+    <name>hive.metastore.aggregate.stats.cache.clean.until</name>
+    <value>0.8</value>
+    <description>The cleaner thread cleans until cache reaches this % full size.</description>
+  </property>
+  <property>
+    <name>hive.metastore.metrics.enabled</name>
+    <value>false</value>
+    <description>Enable metrics on the metastore.</description>
+  </property>
+  <property>
+    <name>hive.metastore.initial.metadata.count.enabled</name>
+    <value>true</value>
+    <description>Enable a metadata count at metastore startup for metrics.</description>
+  </property>
+  <property>
+    <name>hive.metadata.export.location</name>
+    <value/>
+    <description>
+      When used in conjunction with the org.apache.hadoop.hive.ql.parse.MetaDataExportListener pre event listener, 
+      it is the location to which the metadata will be exported. The default is an empty string, which results in the 
+      metadata being exported to the current user's home directory on HDFS.
+    </description>
+  </property>
+  <property>
+    <name>hive.metadata.move.exported.metadata.to.trash</name>
+    <value>true</value>
+    <description>
+      When used in conjunction with the org.apache.hadoop.hive.ql.parse.MetaDataExportListener pre event listener, 
+      this setting determines if the metadata that is exported will subsequently be moved to the user's trash directory 
+      alongside the dropped table data. This ensures that the metadata will be cleaned up along with the dropped table data.
+    </description>
+  </property>
+  <property>
+    <name>hive.cli.errors.ignore</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.cli.print.current.db</name>
+    <!--value>false</value-->
+    <value>true</value>
+    <description>Whether to include the current database in the Hive prompt.</description>
+  </property>
+  <property>
+    <name>hive.cli.prompt</name>
+    <value>hive</value>
+    <description>
+      Command line prompt configuration value. Other hiveconf can be used in this configuration value. 
+      Variable substitution will only be invoked at the Hive CLI startup.
+    </description>
+  </property>
+  <property>
+    <name>hive.cli.pretty.output.num.cols</name>
+    <value>-1</value>
+    <description>
+      The number of columns to use when formatting output generated by the DESCRIBE PRETTY table_name command.
+      If the value of this property is -1, then Hive will use the auto-detected terminal width.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.fs.handler.class</name>
+    <value>org.apache.hadoop.hive.metastore.HiveMetaStoreFsImpl</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.session.id</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.session.silent</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.session.history.enabled</name>
+    <value>false</value>
+    <description>Whether to log Hive query, query plan, runtime statistics etc.</description>
+  </property>
+  <property>
+    <name>hive.query.string</name>
+    <value/>
+    <description>Query being executed (might be multiple per a session)</description>
+  </property>
+  <property>
+    <name>hive.query.id</name>
+    <value/>
+    <description>ID for query being executed (might be multiple per a session)</description>
+  </property>
+  <property>
+    <name>hive.jobname.length</name>
+    <value>50</value>
+    <description>max jobname length</description>
+  </property>
+  <property>
+    <name>hive.jar.path</name>
+    <value/>
+    <description>The location of hive_cli.jar that is used when submitting jobs in a separate jvm.</description>
+  </property>
+  <property>
+    <name>hive.aux.jars.path</name>
+    <value/>
+    <description>The location of the plugin jars that contain implementations of user defined functions and serdes.</description>
+  </property>
+  <property>
+    <name>hive.reloadable.aux.jars.path</name>
+    <value/>
+    <description>Jars can be renewed by executing reload command. And these jars can be used as the auxiliary classes like creating a UDF or SerDe.</description>
+  </property>
+  <property>
+    <name>hive.added.files.path</name>
+    <value/>
+    <description>This an internal parameter.</description>
+  </property>
+  <property>
+    <name>hive.added.jars.path</name>
+    <value/>
+    <description>This an internal parameter.</description>
+  </property>
+  <property>
+    <name>hive.added.archives.path</name>
+    <value/>
+    <description>This an internal parameter.</description>
+  </property>
+  <property>
+    <name>hive.auto.progress.timeout</name>
+    <value>0s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      How long to run autoprogressor for the script/UDTF operators.
+      Set to 0 for forever.
+    </description>
+  </property>
+  <property>
+    <name>hive.script.auto.progress</name>
+    <value>false</value>
+    <description>
+      Whether Hive Transform/Map/Reduce Clause should automatically send progress information to TaskTracker 
+      to avoid the task getting killed because of inactivity.  Hive sends progress information when the script is 
+      outputting to stderr.  This option removes the need of periodically producing stderr messages, 
+      but users should be cautious because this may prevent infinite loops in the scripts to be killed by TaskTracker.
+    </description>
+  </property>
+  <property>
+    <name>hive.script.operator.id.env.var</name>
+    <value>HIVE_SCRIPT_OPERATOR_ID</value>
+    <description>
+      Name of the environment variable that holds the unique script operator ID in the user's 
+      transform function (the custom mapper/reducer that the user has specified in the query)
+    </description>
+  </property>
+  <property>
+    <name>hive.script.operator.truncate.env</name>
+    <value>false</value>
+    <description>Truncate each environment variable for external script in scripts operator to 20KB (to fit system limits)</description>
+  </property>
+  <property>
+    <name>hive.script.operator.env.blacklist</name>
+    <value>hive.txn.valid.txns,hive.script.operator.env.blacklist</value>
+    <description>Comma separated list of keys from the configuration file not to convert to environment variables when envoking the script operator</description>
+  </property>
+  <property>
+    <name>hive.strict.checks.large.query</name>
+    <value>false</value>
+    <description>
+      Enabling strict large query checks disallows the following:
+        Orderby without limit.
+        No partition being picked up for a query against partitioned table.
+      Note that these checks currently do not consider data size, only the query pattern.
+    </description>
+  </property>
+  <property>
+    <name>hive.strict.checks.type.safety</name>
+    <value>true</value>
+    <description>
+      Enabling strict type safety checks disallows the following:
+        Comparing bigints and strings.
+        Comparing bigints and doubles.
+    </description>
+  </property>
+  <property>
+    <name>hive.strict.checks.cartesian.product</name>
+    <value>true</value>
+    <description>
+      Enabling strict large query checks disallows the following:
+        Cartesian product (cross join).
+    </description>
+  </property>
+  <property>
+    <name>hive.mapred.mode</name>
+    <value>nonstrict</value>
+    <description>Deprecated; use hive.strict.checks.* settings instead.</description>
+  </property>
+  <property>
+    <name>hive.alias</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.map.aggr</name>
+    <value>true</value>
+    <description>Whether to use map-side aggregation in Hive Group By queries</description>
+  </property>
+  <property>
+    <name>hive.groupby.skewindata</name>
+    <value>false</value>
+    <description>Whether there is skew in data to optimize group by queries</description>
+  </property>
+  <property>
+    <name>hive.join.emit.interval</name>
+    <value>1000</value>
+    <description>How many rows in the right-most join operand Hive should buffer before emitting the join result.</description>
+  </property>
+  <property>
+    <name>hive.join.cache.size</name>
+    <value>25000</value>
+    <description>How many rows in the joining tables (except the streaming table) should be cached in memory.</description>
+  </property>
+  <property>
+    <name>hive.cbo.enable</name>
+    <value>true</value>
+    <description>Flag to control enabling Cost Based Optimizations using Calcite framework.</description>
+  </property>
+  <property>
+    <name>hive.cbo.cnf.maxnodes</name>
+    <value>-1</value>
+    <description>When converting to conjunctive normal form (CNF), fail ifthe expression exceeds this threshold; the threshold is expressed in terms of number of nodes (leaves andinterior nodes). -1 to not set up a threshold.</description>
+  </property>
+  <property>
+    <name>hive.cbo.returnpath.hiveop</name>
+    <value>false</value>
+    <description>Flag to control calcite plan to hive operator conversion</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.extended</name>
+    <value>false</value>
+    <description>Flag to control enabling the extended cost model based onCPU, IO and cardinality. Otherwise, the cost model is based on cardinality.</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.cpu</name>
+    <value>0.000001</value>
+    <description>Default cost of a comparison</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.network</name>
+    <value>150.0</value>
+    <description>Default cost of a transfering a byte over network; expressed as multiple of CPU cost</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.local.fs.write</name>
+    <value>4.0</value>
+    <description>Default cost of writing a byte to local FS; expressed as multiple of NETWORK cost</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.local.fs.read</name>
+    <value>4.0</value>
+    <description>Default cost of reading a byte from local FS; expressed as multiple of NETWORK cost</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.hdfs.write</name>
+    <value>10.0</value>
+    <description>Default cost of writing a byte to HDFS; expressed as multiple of Local FS write cost</description>
+  </property>
+  <property>
+    <name>hive.cbo.costmodel.hdfs.read</name>
+    <value>1.5</value>
+    <description>Default cost of reading a byte from HDFS; expressed as multiple of Local FS read cost</description>
+  </property>
+  <property>
+    <name>hive.transpose.aggr.join</name>
+    <value>false</value>
+    <description>push aggregates through join</description>
+  </property>
+  <property>
+    <name>hive.order.columnalignment</name>
+    <value>true</value>
+    <description>Flag to control whether we want to try to aligncolumns in operators such as Aggregate or Join so that we try to reduce the number of shuffling stages</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.bucket.cache.size</name>
+    <value>100</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.mapjoin.optimized.hashtable</name>
+    <value>true</value>
+    <description>
+      Whether Hive should use memory-optimized hash table for MapJoin.
+      Only works on Tez and Spark, because memory-optimized hashtable cannot be serialized.
+    </description>
+  </property>
+  <property>
+    <name>hive.mapjoin.optimized.hashtable.probe.percent</name>
+    <value>0.5</value>
+    <description>Probing space percentage of the optimized hashtable</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.hybridgrace.hashtable</name>
+    <value>true</value>
+    <description>Whether to use hybridgrace hash join as the join method for mapjoin. Tez only.</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.hybridgrace.memcheckfrequency</name>
+    <value>1024</value>
+    <description>For hybrid grace hash join, how often (how many rows apart) we check if memory is full. This number should be power of 2.</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.hybridgrace.minwbsize</name>
+    <value>524288</value>
+    <description>For hybrid graceHash join, the minimum write buffer size used by optimized hashtable. Default is 512 KB.</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.hybridgrace.minnumpartitions</name>
+    <value>16</value>
+    <description>ForHybrid grace hash join, the minimum number of partitions to create.</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.optimized.hashtable.wbsize</name>
+    <value>8388608</value>
+    <description>
+      Optimized hashtable (see hive.mapjoin.optimized.hashtable) uses a chain of buffers to
+      store data. This is one buffer size. HT may be slightly faster if this is larger, but for small
+      joins unnecessary memory will be allocated and then trimmed.
+    </description>
+  </property>
+  <property>
+    <name>hive.mapjoin.hybridgrace.bloomfilter</name>
+    <value>true</value>
+    <description>Whether to use BloomFilter in Hybrid grace hash join to minimize unnecessary spilling.</description>
+  </property>
+  <property>
+    <name>hive.smbjoin.cache.rows</name>
+    <value>10000</value>
+    <description>How many rows with the same key value should be cached in memory per smb joined table.</description>
+  </property>
+  <property>
+    <name>hive.groupby.mapaggr.checkinterval</name>
+    <value>100000</value>
+    <description>Number of rows after which size of the grouping keys/aggregation classes is performed</description>
+  </property>
+  <property>
+    <name>hive.map.aggr.hash.percentmemory</name>
+    <value>0.5</value>
+    <description>Portion of total memory to be used by map-side group aggregation hash table</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.followby.map.aggr.hash.percentmemory</name>
+    <value>0.3</value>
+    <description>Portion of total memory to be used by map-side group aggregation hash table, when this group by is followed by map join</description>
+  </property>
+  <property>
+    <name>hive.map.aggr.hash.force.flush.memory.threshold</name>
+    <value>0.9</value>
+    <description>
+      The max memory to be used by map-side group aggregation hash table.
+      If the memory usage is higher than this number, force to flush data
+    </description>
+  </property>
+  <property>
+    <name>hive.map.aggr.hash.min.reduction</name>
+    <value>0.5</value>
+    <description>
+      Hash aggregation will be turned off if the ratio between hash  table size and input rows is bigger than this number. 
+      Set to 1 to make sure hash aggregation is never turned off.
+    </description>
+  </property>
+  <property>
+    <name>hive.multigroupby.singlereducer</name>
+    <value>true</value>
+    <description>
+      Whether to optimize multi group by query to generate single M/R  job plan. If the multi group by query has 
+      common group by keys, it will be optimized to generate single M/R job.
+    </description>
+  </property>
+  <property>
+    <name>hive.map.groupby.sorted</name>
+    <value>true</value>
+    <description>
+      If the bucketing/sorting properties of the table exactly match the grouping key, whether to perform 
+      the group by in the mapper by using BucketizedHiveInputFormat. The only downside to this
+      is that it limits the number of mappers to the number of files.
+    </description>
+  </property>
+  <property>
+    <name>hive.groupby.orderby.position.alias</name>
+    <value>false</value>
+    <description>Whether to enable using Column Position Alias in Group By or Order By</description>
+  </property>
+  <property>
+    <name>hive.new.job.grouping.set.cardinality</name>
+    <value>30</value>
+    <description>
+      Whether a new map-reduce job should be launched for grouping sets/rollups/cubes.
+      For a query like: select a, b, c, count(1) from T group by a, b, c with rollup;
+      4 rows are created per row: (a, b, c), (a, b, null), (a, null, null), (null, null, null).
+      This can lead to explosion across map-reduce boundary if the cardinality of T is very high,
+      and map-side aggregation does not do a very good job. 
+      
+      This parameter decides if Hive should add an additional map-reduce job. If the grouping set
+      cardinality (4 in the example above), is more than this value, a new MR job is added under the
+      assumption that the original group by will reduce the data size.
+    </description>
+  </property>
+  <property>
+    <name>hive.groupby.limit.extrastep</name>
+    <value>true</value>
+    <description>
+      This parameter decides if Hive should 
+      create new MR job for sorting final output
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.copyfile.maxsize</name>
+    <value>33554432</value>
+    <description>Maximum file size (in Mb) that Hive uses to do single HDFS copies between directories.Distributed copies (distcp) will be used instead for bigger files so that copies can be done faster.</description>
+  </property>
+  <property>
+    <name>hive.udtf.auto.progress</name>
+    <value>false</value>
+    <description>
+      Whether Hive should automatically send progress information to TaskTracker 
+      when using UDTF's to prevent the task getting killed because of inactivity.  Users should be cautious 
+      because this may prevent TaskTracker from killing tasks with infinite loops.
+    </description>
+  </property>
+  <property>
+    <name>hive.default.fileformat</name>
+    <value>TextFile</value>
+    <description>
+      Expects one of [textfile, sequencefile, rcfile, orc].
+      Default file format for CREATE TABLE statement. Users can explicitly override it by CREATE TABLE ... STORED AS [FORMAT]
+    </description>
+  </property>
+  <property>
+    <name>hive.default.fileformat.managed</name>
+    <value>none</value>
+    <description>
+      Expects one of [none, textfile, sequencefile, rcfile, orc].
+      Default file format for CREATE TABLE statement applied to managed tables only. External tables will be 
+      created with format specified by hive.default.fileformat. Leaving this null will result in using hive.default.fileformat 
+      for all tables.
+    </description>
+  </property>
+  <property>
+    <name>hive.query.result.fileformat</name>
+    <value>SequenceFile</value>
+    <description>
+      Expects one of [textfile, sequencefile, rcfile, llap].
+      Default file format for storing result of the query.
+    </description>
+  </property>
+  <property>
+    <name>hive.fileformat.check</name>
+    <value>true</value>
+    <description>Whether to check file format or not when loading data files</description>
+  </property>
+  <property>
+    <name>hive.default.rcfile.serde</name>
+    <value>org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe</value>
+    <description>The default SerDe Hive will use for the RCFile format</description>
+  </property>
+  <property>
+    <name>hive.default.serde</name>
+    <value>org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe</value>
+    <description>The default SerDe Hive will use for storage formats that do not specify a SerDe.</description>
+  </property>
+  <property>
+    <name>hive.serdes.using.metastore.for.schema</name>
+    <value>org.apache.hadoop.hive.ql.io.orc.OrcSerde,org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe,org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe,org.apache.hadoop.hive.serde2.dynamic_type.DynamicSerDe,org.apache.hadoop.hive.serde2.MetadataTypedColumnsetSerDe,org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe,org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe,org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe</value>
+    <description>SerDes retrieving schema from metastore. This is an internal parameter.</description>
+  </property>
+  <property>
+    <name>hive.querylog.location</name>
+    <value>/root/hive/logs</value>
+    <description>Location of Hive run time structured log file</description>
+  </property>
+  <property>
+    <name>hive.querylog.enable.plan.progress</name>
+    <value>true</value>
+    <description>
+      Whether to log the plan's progress every time a job's progress is checked.
+      These logs are written to the location specified by hive.querylog.location
+    </description>
+  </property>
+  <property>
+    <name>hive.querylog.plan.progress.interval</name>
+    <value>60000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      The interval to wait between logging the plan's progress.
+      If there is a whole number percentage change in the progress of the mappers or the reducers,
+      the progress is logged regardless of this value.
+      The actual interval will be the ceiling of (this value divided by the value of
+      hive.exec.counters.pull.interval) multiplied by the value of hive.exec.counters.pull.interval
+      I.e. if it is not divide evenly by the value of hive.exec.counters.pull.interval it will be
+      logged less frequently than specified.
+      This only has an effect if hive.querylog.enable.plan.progress is set to true.
+    </description>
+  </property>
+  <property>
+    <name>hive.script.serde</name>
+    <value>org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe</value>
+    <description>The default SerDe for transmitting input data to and reading output data from the user scripts. </description>
+  </property>
+  <property>
+    <name>hive.script.recordreader</name>
+    <value>org.apache.hadoop.hive.ql.exec.TextRecordReader</value>
+    <description>The default record reader for reading data from the user scripts. </description>
+  </property>
+  <property>
+    <name>hive.script.recordwriter</name>
+    <value>org.apache.hadoop.hive.ql.exec.TextRecordWriter</value>
+    <description>The default record writer for writing data to the user scripts. </description>
+  </property>
+  <property>
+    <name>hive.transform.escape.input</name>
+    <value>false</value>
+    <description>
+      This adds an option to escape special chars (newlines, carriage returns and
+      tabs) when they are passed to the user script. This is useful if the Hive tables
+      can contain data that contains special characters.
+    </description>
+  </property>
+  <property>
+    <name>hive.binary.record.max.length</name>
+    <value>1000</value>
+    <description>
+      Read from a binary stream and treat each hive.binary.record.max.length bytes as a record. 
+      The last record before the end of stream can have less than hive.binary.record.max.length bytes
+    </description>
+  </property>
+  <property>
+    <name>hive.hwi.listen.host</name>
+    <value>0.0.0.0</value>
+    <description>This is the host address the Hive Web Interface will listen on</description>
+  </property>
+  <property>
+    <name>hive.hwi.listen.port</name>
+    <value>9999</value>
+    <description>This is the port the Hive Web Interface will listen on</description>
+  </property>
+  <property>
+    <name>hive.hwi.war.file</name>
+    <value>${env:HWI_WAR_FILE}</value>
+    <description>This sets the path to the HWI war file, relative to ${HIVE_HOME}. </description>
+  </property>
+  <property>
+    <name>hive.mapred.local.mem</name>
+    <value>0</value>
+    <description>mapper/reducer memory in local mode</description>
+  </property>
+  <property>
+    <name>hive.mapjoin.smalltable.filesize</name>
+    <value>25000000</value>
+    <description>
+      The threshold for the input file size of the small tables; if the file size is smaller 
+      than this threshold, it will try to convert the common join into map join
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.schema.evolution</name>
+    <value>true</value>
+    <description>Use schema evolution to convert self-describing file format's data to the schema desired by the reader.</description>
+  </property>
+  <property>
+    <name>hive.sample.seednumber</name>
+    <value>0</value>
+    <description>A number used to percentage sampling. By changing this number, user will change the subsets of data sampled.</description>
+  </property>
+  <property>
+    <name>hive.test.mode</name>
+    <value>false</value>
+    <description>Whether Hive is running in test mode. If yes, it turns on sampling and prefixes the output tablename.</description>
+  </property>
+  <property>
+    <name>hive.test.mode.prefix</name>
+    <value>test_</value>
+    <description>In test mode, specfies prefixes for the output table</description>
+  </property>
+  <property>
+    <name>hive.test.mode.samplefreq</name>
+    <value>32</value>
+    <description>
+      In test mode, specfies sampling frequency for table, which is not bucketed,
+      For example, the following query:
+        INSERT OVERWRITE TABLE dest SELECT col1 from src
+      would be converted to
+        INSERT OVERWRITE TABLE test_dest
+        SELECT col1 from src TABLESAMPLE (BUCKET 1 out of 32 on rand(1))
+    </description>
+  </property>
+  <property>
+    <name>hive.test.mode.nosamplelist</name>
+    <value/>
+    <description>In test mode, specifies comma separated table names which would not apply sampling</description>
+  </property>
+  <property>
+    <name>hive.test.dummystats.aggregator</name>
+    <value/>
+    <description>internal variable for test</description>
+  </property>
+  <property>
+    <name>hive.test.dummystats.publisher</name>
+    <value/>
+    <description>internal variable for test</description>
+  </property>
+  <property>
+    <name>hive.test.currenttimestamp</name>
+    <value/>
+    <description>current timestamp for test</description>
+  </property>
+  <property>
+    <name>hive.test.rollbacktxn</name>
+    <value>false</value>
+    <description>For testing only.  Will mark every ACID transaction aborted</description>
+  </property>
+  <property>
+    <name>hive.test.fail.compaction</name>
+    <value>false</value>
+    <description>For testing only.  Will cause CompactorMR to fail.</description>
+  </property>
+  <property>
+    <name>hive.test.fail.heartbeater</name>
+    <value>false</value>
+    <description>For testing only.  Will cause Heartbeater to fail.</description>
+  </property>
+  <property>
+    <name>hive.merge.mapfiles</name>
+    <value>true</value>
+    <description>Merge small files at the end of a map-only job</description>
+  </property>
+  <property>
+    <name>hive.merge.mapredfiles</name>
+    <value>false</value>
+    <description>Merge small files at the end of a map-reduce job</description>
+  </property>
+  <property>
+    <name>hive.merge.tezfiles</name>
+    <value>false</value>
+    <description>Merge small files at the end of a Tez DAG</description>
+  </property>
+  <property>
+    <name>hive.merge.sparkfiles</name>
+    <value>false</value>
+    <description>Merge small files at the end of a Spark DAG Transformation</description>
+  </property>
+  <property>
+    <name>hive.merge.size.per.task</name>
+    <value>256000000</value>
+    <description>Size of merged files at the end of the job</description>
+  </property>
+  <property>
+    <name>hive.merge.smallfiles.avgsize</name>
+    <value>16000000</value>
+    <description>
+      When the average output file size of a job is less than this number, Hive will start an additional 
+      map-reduce job to merge the output files into bigger files. This is only done for map-only jobs 
+      if hive.merge.mapfiles is true, and for map-reduce jobs if hive.merge.mapredfiles is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.merge.rcfile.block.level</name>
+    <value>true</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.merge.orcfile.stripe.level</name>
+    <value>true</value>
+    <description>
+      When hive.merge.mapfiles, hive.merge.mapredfiles or hive.merge.tezfiles is enabled
+      while writing a table with ORC file format, enabling this config will do stripe-level
+      fast merge for small ORC files. Note that enabling this config will not honor the
+      padding tolerance config (hive.exec.orc.block.padding.tolerance).
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.rcfile.use.explicit.header</name>
+    <value>true</value>
+    <description>
+      If this is set the header for RCFiles will simply be RCF.  If this is not
+      set the header will be that borrowed from sequence files, e.g. SEQ- followed
+      by the input and output RCFile formats.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.rcfile.use.sync.cache</name>
+    <value>true</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.io.rcfile.record.interval</name>
+    <value>2147483647</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.io.rcfile.column.number.conf</name>
+    <value>0</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.io.rcfile.tolerate.corruptions</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.io.rcfile.record.buffer.size</name>
+    <value>4194304</value>
+    <description/>
+  </property>
+  <property>
+    <name>parquet.memory.pool.ratio</name>
+    <value>0.5</value>
+    <description>
+      Maximum fraction of heap that can be used by Parquet file writers in one task.
+      It is for avoiding OutOfMemory error in tasks. Work with Parquet 1.6.0 and above.
+      This config parameter is defined in Parquet, so that it does not start with 'hive.'.
+    </description>
+  </property>
+  <property>
+    <name>hive.parquet.timestamp.skip.conversion</name>
+    <value>true</value>
+    <description>Current Hive implementation of parquet stores timestamps to UTC, this flag allows skipping of the conversionon reading parquet files from other tools</description>
+  </property>
+  <property>
+    <name>hive.int.timestamp.conversion.in.seconds</name>
+    <value>false</value>
+    <description>
+      Boolean/tinyint/smallint/int/bigint value is interpreted as milliseconds during the timestamp conversion.
+      Set this flag to true to interpret the value as seconds to be consistent with float/double.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.memory.pool</name>
+    <value>0.5</value>
+    <description>Maximum fraction of heap that can be used by ORC file writers</description>
+  </property>
+  <property>
+    <name>hive.exec.orc.write.format</name>
+    <value/>
+    <description>
+      Define the version of the file to write. Possible values are 0.11 and 0.12.
+      If this parameter is not defined, ORC will use the run length encoding (RLE)
+      introduced in Hive 0.12. Any value other than 0.11 results in the 0.12 encoding.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.default.stripe.size</name>
+    <value>67108864</value>
+    <description>Define the default ORC stripe size, in bytes.</description>
+  </property>
+  <property>
+    <name>hive.exec.orc.default.block.size</name>
+    <value>268435456</value>
+    <description>Define the default file system block size for ORC files.</description>
+  </property>
+  <property>
+    <name>hive.exec.orc.dictionary.key.size.threshold</name>
+    <value>0.8</value>
+    <description>
+      If the number of keys in a dictionary is greater than this fraction of the total number of
+      non-null rows, turn off dictionary encoding.  Use 1 to always use dictionary encoding.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.default.row.index.stride</name>
+    <value>10000</value>
+    <description>
+      Define the default ORC index stride in number of rows. (Stride is the number of rows
+      an index entry represents.)
+    </description>
+  </property>
+  <property>
+    <name>hive.orc.row.index.stride.dictionary.check</name>
+    <value>true</value>
+    <description>
+      If enabled dictionary check will happen after first row index stride (default 10000 rows)
+      else dictionary check will happen before writing first stripe. In both cases, the decision
+      to use dictionary or not will be retained thereafter.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.default.buffer.size</name>
+    <value>262144</value>
+    <description>Define the default ORC buffer size, in bytes.</description>
+  </property>
+  <property>
+    <name>hive.exec.orc.base.delta.ratio</name>
+    <value>8</value>
+    <description>
+      The ratio of base writer and
+      delta writer in terms of STRIPE_SIZE and BUFFER_SIZE.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.default.block.padding</name>
+    <value>true</value>
+    <description>Define the default block padding, which pads stripes to the HDFS block boundaries.</description>
+  </property>
+  <property>
+    <name>hive.exec.orc.block.padding.tolerance</name>
+    <value>0.05</value>
+    <description>
+      Define the tolerance for block padding as a decimal fraction of stripe size (for
+      example, the default value 0.05 is 5% of the stripe size). For the defaults of 64Mb
+      ORC stripe and 256Mb HDFS blocks, the default block padding tolerance of 5% will
+      reserve a maximum of 3.2Mb for padding within the 256Mb block. In that case, if the
+      available size within the block is more than 3.2Mb, a new smaller stripe will be
+      inserted to fit within that space. This will make sure that no stripe written will
+      cross block boundaries and cause remote reads within a node local task.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.default.compress</name>
+    <value>ZLIB</value>
+    <description>Define the default compression codec for ORC file</description>
+  </property>
+  <property>
+    <name>hive.exec.orc.encoding.strategy</name>
+    <value>SPEED</value>
+    <description>
+      Expects one of [speed, compression].
+      Define the encoding strategy to use while writing data. Changing this will
+      only affect the light weight encoding for integers. This flag will not
+      change the compression level of higher level compression codec (like ZLIB).
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.compression.strategy</name>
+    <value>SPEED</value>
+    <description>
+      Expects one of [speed, compression].
+      Define the compression strategy to use while writing data. 
+      This changes the compression level of higher level compression codec (like ZLIB).
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.split.strategy</name>
+    <value>HYBRID</value>
+    <description>
+      Expects one of [hybrid, bi, etl].
+      This is not a user level config. BI strategy is used when the requirement is to spend less time in split generation as opposed to query execution (split generation does not read or cache file footers). ETL strategy is used when spending little more time in split generation is acceptable (split generation reads and caches file footers). HYBRID chooses between the above strategies based on heuristics.
+    </description>
+  </property>
+  <property>
+    <name>hive.orc.splits.ms.footer.cache.enabled</name>
+    <value>false</value>
+    <description>Whether to enable using file metadata cache in metastore for ORC file footers.</description>
+  </property>
+  <property>
+    <name>hive.orc.splits.ms.footer.cache.ppd.enabled</name>
+    <value>true</value>
+    <description>
+      Whether to enable file footer cache PPD (hive.orc.splits.ms.footer.cache.enabled
+      must also be set to true for this to work).
+    </description>
+  </property>
+  <property>
+    <name>hive.orc.splits.include.file.footer</name>
+    <value>false</value>
+    <description>
+      If turned on splits generated by orc will include metadata about the stripes in the file. This
+      data is read remotely (from the client or HS2 machine) and sent to all the tasks.
+    </description>
+  </property>
+  <property>
+    <name>hive.orc.splits.directory.batch.ms</name>
+    <value>0</value>
+    <description>
+      How long, in ms, to wait to batch input directories for processing during ORC split
+      generation. 0 means process directories individually. This can increase the number of
+      metastore calls if metastore metadata cache is used.
+    </description>
+  </property>
+  <property>
+    <name>hive.orc.splits.include.fileid</name>
+    <value>true</value>
+    <description>Include file ID in splits on file systems that support it.</description>
+  </property>
+  <property>
+    <name>hive.orc.splits.allow.synthetic.fileid</name>
+    <value>true</value>
+    <description>Allow synthetic file ID in splits on file systems that don't have a native one.</description>
+  </property>
+  <property>
+    <name>hive.orc.cache.stripe.details.size</name>
+    <value>10000</value>
+    <description>Max cache size for keeping meta info about orc splits cached in the client.</description>
+  </property>
+  <property>
+    <name>hive.orc.compute.splits.num.threads</name>
+    <value>10</value>
+    <description>How many threads orc should use to create splits in parallel.</description>
+  </property>
+  <property>
+    <name>hive.orc.cache.use.soft.references</name>
+    <value>false</value>
+    <description>
+      By default, the cache that ORC input format uses to store orc file footer use hard
+      references for the cached object. Setting this to true can help avoid out of memory
+      issues under memory pressure (in some cases) at the cost of slight unpredictability in
+      overall query performance.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.skip.corrupt.data</name>
+    <value>false</value>
+    <description>
+      If ORC reader encounters corrupt data, this value will be used to determine
+      whether to skip the corrupt data or throw exception. The default behavior is to throw exception.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.orc.zerocopy</name>
+    <value>false</value>
+    <description>Use zerocopy reads with ORC. (This requires Hadoop 2.3 or later.)</description>
+  </property>
+  <property>
+    <name>hive.lazysimple.extended_boolean_literal</name>
+    <value>false</value>
+    <description>
+      LazySimpleSerde uses this property to determine if it treats 'T', 't', 'F', 'f',
+      '1', and '0' as extened, legal boolean literal, in addition to 'TRUE' and 'FALSE'.
+      The default is false, which means only 'TRUE' and 'FALSE' are treated as legal
+      boolean literal.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.skewjoin</name>
+    <value>false</value>
+    <description>
+      Whether to enable skew join optimization. 
+      The algorithm is as follows: At runtime, detect the keys with a large skew. Instead of
+      processing those keys, store them temporarily in an HDFS directory. In a follow-up map-reduce
+      job, process those skewed keys. The same key need not be skewed for all the tables, and so,
+      the follow-up map-reduce job (for the skewed keys) would be much faster, since it would be a
+      map-join.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.dynamic.partition.hashjoin</name>
+    <value>false</value>
+    <description>
+      Whether to enable dynamically partitioned hash join optimization. 
+      This setting is also dependent on enabling hive.auto.convert.join
+    </description>
+  </property>
+  <property>
+    <name>hive.auto.convert.join</name>
+    <value>true</value>
+    <description>Whether Hive enables the optimization about converting common join into mapjoin based on the input file size</description>
+  </property>
+  <property>
+    <name>hive.auto.convert.join.noconditionaltask</name>
+    <value>true</value>
+    <description>
+      Whether Hive enables the optimization about converting common join into mapjoin based on the input file size. 
+      If this parameter is on, and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than the
+      specified size, the join is directly converted to a mapjoin (there is no conditional task).
+    </description>
+  </property>
+  <property>
+    <name>hive.auto.convert.join.noconditionaltask.size</name>
+    <value>10000000</value>
+    <description>
+      If hive.auto.convert.join.noconditionaltask is off, this parameter does not take affect. 
+      However, if it is on, and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than this size, 
+      the join is directly converted to a mapjoin(there is no conditional task). The default is 10MB
+    </description>
+  </property>
+  <property>
+    <name>hive.auto.convert.join.use.nonstaged</name>
+    <value>false</value>
+    <description>
+      For conditional joins, if input stream from a small alias can be directly applied to join operator without 
+      filtering or projection, the alias need not to be pre-staged in distributed cache via mapred local task.
+      Currently, this is not working with vectorization or tez execution engine.
+    </description>
+  </property>
+  <property>
+    <name>hive.skewjoin.key</name>
+    <value>100000</value>
+    <description>
+      Determine if we get a skew key in join. If we see more than the specified number of rows with the same key in join operator,
+      we think the key as a skew join key. 
+    </description>
+  </property>
+  <property>
+    <name>hive.skewjoin.mapjoin.map.tasks</name>
+    <value>10000</value>
+    <description>
+      Determine the number of map task used in the follow up map join job for a skew join.
+      It should be used together with hive.skewjoin.mapjoin.min.split to perform a fine grained control.
+    </description>
+  </property>
+  <property>
+    <name>hive.skewjoin.mapjoin.min.split</name>
+    <value>33554432</value>
+    <description>
+      Determine the number of map task at most used in the follow up map join job for a skew join by specifying 
+      the minimum split size. It should be used together with hive.skewjoin.mapjoin.map.tasks to perform a fine grained control.
+    </description>
+  </property>
+  <property>
+    <name>hive.heartbeat.interval</name>
+    <value>1000</value>
+    <description>Send a heartbeat after this interval - used by mapjoin and filter operators</description>
+  </property>
+  <property>
+    <name>hive.limit.row.max.size</name>
+    <value>100000</value>
+    <description>When trying a smaller subset of data for simple LIMIT, how much size we need to guarantee each row to have at least.</description>
+  </property>
+  <property>
+    <name>hive.limit.optimize.limit.file</name>
+    <value>10</value>
+    <description>When trying a smaller subset of data for simple LIMIT, maximum number of files we can sample.</description>
+  </property>
+  <property>
+    <name>hive.limit.optimize.enable</name>
+    <value>false</value>
+    <description>Whether to enable to optimization to trying a smaller subset of data for simple LIMIT first.</description>
+  </property>
+  <property>
+    <name>hive.limit.optimize.fetch.max</name>
+    <value>50000</value>
+    <description>
+      Maximum number of rows allowed for a smaller subset of data for simple LIMIT, if it is a fetch query. 
+      Insert queries are not restricted by this limit.
+    </description>
+  </property>
+  <property>
+    <name>hive.limit.pushdown.memory.usage</name>
+    <value>0.1</value>
+    <description>
+      Expects value between 0.0f and 1.0f.
+      The fraction of available memory to be used for buffering rows in Reducesink operator for limit pushdown optimization.
+    </description>
+  </property>
+  <property>
+    <name>hive.limit.query.max.table.partition</name>
+    <value>-1</value>
+    <description>
+      This controls how many partitions can be scanned for each partitioned table.
+      The default value "-1" means no limit.
+    </description>
+  </property>
+  <property>
+    <name>hive.hashtable.key.count.adjustment</name>
+    <value>1.0</value>
+    <description>Adjustment to mapjoin hashtable size derived from table and column statistics; the estimate of the number of keys is divided by this value. If the value is 0, statistics are not usedand hive.hashtable.initialCapacity is used instead.</description>
+  </property>
+  <property>
+    <name>hive.hashtable.initialCapacity</name>
+    <value>100000</value>
+    <description>Initial capacity of mapjoin hashtable if statistics are absent, or if hive.hashtable.key.count.adjustment is set to 0</description>
+  </property>
+  <property>
+    <name>hive.hashtable.loadfactor</name>
+    <value>0.75</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.mapjoin.followby.gby.localtask.max.memory.usage</name>
+    <value>0.55</value>
+    <description>
+      This number means how much memory the local task can take to hold the key/value into an in-memory hash table 
+      when this map join is followed by a group by. If the local task's memory usage is more than this number, 
+      the local task will abort by itself. It means the data of the small table is too large to be held in memory.
+    </description>
+  </property>
+  <property>
+    <name>hive.mapjoin.localtask.max.memory.usage</name>
+    <value>0.9</value>
+    <description>
+      This number means how much memory the local task can take to hold the key/value into an in-memory hash table. 
+      If the local task's memory usage is more than this number, the local task will abort by itself. 
+      It means the data of the small table is too large to be held in memory.
+    </description>
+  </property>
+  <property>
+    <name>hive.mapjoin.check.memory.rows</name>
+    <value>100000</value>
+    <description>The number means after how many rows processed it needs to check the memory usage</description>
+  </property>
+  <property>
+    <name>hive.debug.localtask</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.input.format</name>
+    <value>org.apache.hadoop.hive.ql.io.CombineHiveInputFormat</value>
+    <description>The default input format. Set this to HiveInputFormat if you encounter problems with CombineHiveInputFormat.</description>
+  </property>
+  <property>
+    <name>hive.tez.input.format</name>
+    <value>org.apache.hadoop.hive.ql.io.HiveInputFormat</value>
+    <description>The default input format for tez. Tez groups splits in the AM.</description>
+  </property>
+  <property>
+    <name>hive.tez.container.size</name>
+    <value>-1</value>
+    <description>By default Tez will spawn containers of the size of a mapper. This can be used to overwrite.</description>
+  </property>
+  <property>
+    <name>hive.tez.cpu.vcores</name>
+    <value>-1</value>
+    <description>
+      By default Tez will ask for however many cpus map-reduce is configured to use per container.
+      This can be used to overwrite.
+    </description>
+  </property>
+  <property>
+    <name>hive.tez.java.opts</name>
+    <value/>
+    <description>By default Tez will use the Java options from map tasks. This can be used to overwrite.</description>
+  </property>
+  <property>
+    <name>hive.tez.log.level</name>
+    <value>INFO</value>
+    <description>
+      The log level to use for tasks executing as part of the DAG.
+      Used only if hive.tez.java.opts is used to configure Java options.
+    </description>
+  </property>
+  <property>
+    <name>hive.query.name</name>
+    <value/>
+    <description>
+      This named is used by Tez to set the dag name. This name in turn will appear on 
+      the Tez UI representing the work that was done.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.bucketingsorting</name>
+    <value>true</value>
+    <description>
+      Don't create a reducer for enforcing 
+      bucketing/sorting for queries of the form: 
+      insert overwrite table T2 select * from T1;
+      where T1 and T2 are bucketed/sorted by the same keys into the same number of buckets.
+    </description>
+  </property>
+  <property>
+    <name>hive.mapred.partitioner</name>
+    <value>org.apache.hadoop.hive.ql.io.DefaultHivePartitioner</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.enforce.sortmergebucketmapjoin</name>
+    <value>false</value>
+    <description>If the user asked for sort-merge bucketed map-side join, and it cannot be performed, should the query fail or not ?</description>
+  </property>
+  <property>
+    <name>hive.enforce.bucketmapjoin</name>
+    <value>false</value>
+    <description>
+      If the user asked for bucketed map-side join, and it cannot be performed, 
+      should the query fail or not ? For example, if the buckets in the tables being joined are
+      not a multiple of each other, bucketed map-side join cannot be performed, and the
+      query will fail if hive.enforce.bucketmapjoin is set to true.
+    </description>
+  </property>
+  <property>
+    <name>hive.auto.convert.sortmerge.join</name>
+    <value>false</value>
+    <description>Will the join be automatically converted to a sort-merge join, if the joined tables pass the criteria for sort-merge join.</description>
+  </property>
+  <property>
+    <name>hive.auto.convert.sortmerge.join.bigtable.selection.policy</name>
+    <value>org.apache.hadoop.hive.ql.optimizer.AvgPartitionSizeBasedBigTableSelectorForAutoSMJ</value>
+    <description>
+      The policy to choose the big table for automatic conversion to sort-merge join. 
+      By default, the table with the largest partitions is assigned the big table. All policies are:
+      . based on position of the table - the leftmost table is selected
+      org.apache.hadoop.hive.ql.optimizer.LeftmostBigTableSMJ.
+      . based on total size (all the partitions selected in the query) of the table 
+      org.apache.hadoop.hive.ql.optimizer.TableSizeBasedBigTableSelectorForAutoSMJ.
+      . based on average size (all the partitions selected in the query) of the table 
+      org.apache.hadoop.hive.ql.optimizer.AvgPartitionSizeBasedBigTableSelectorForAutoSMJ.
+      New policies can be added in future.
+    </description>
+  </property>
+  <property>
+    <name>hive.auto.convert.sortmerge.join.to.mapjoin</name>
+    <value>false</value>
+    <description>
+      If hive.auto.convert.sortmerge.join is set to true, and a join was converted to a sort-merge join, 
+      this parameter decides whether each table should be tried as a big table, and effectively a map-join should be
+      tried. That would create a conditional task with n+1 children for a n-way join (1 child for each table as the
+      big table), and the backup task will be the sort-merge join. In some cases, a map-join would be faster than a
+      sort-merge join, if there is no advantage of having the output bucketed and sorted. For example, if a very big sorted
+      and bucketed table with few files (say 10 files) are being joined with a very small sorter and bucketed table
+      with few files (10 files), the sort-merge join will only use 10 mappers, and a simple map-only join might be faster
+      if the complete small table can fit in memory, and a map-join can be performed.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.script.trust</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.exec.rowoffset</name>
+    <value>false</value>
+    <description>Whether to provide the row offset virtual column</description>
+  </property>
+  <property>
+    <name>hive.optimize.index.filter</name>
+    <value>false</value>
+    <description>Whether to enable automatic use of indexes</description>
+  </property>
+  <property>
+    <name>hive.optimize.index.autoupdate</name>
+    <value>false</value>
+    <description>Whether to update stale indexes automatically</description>
+  </property>
+  <property>
+    <name>hive.optimize.ppd</name>
+    <value>true</value>
+    <description>Whether to enable predicate pushdown</description>
+  </property>
+  <property>
+    <name>hive.optimize.ppd.windowing</name>
+    <value>true</value>
+    <description>Whether to enable predicate pushdown through windowing</description>
+  </property>
+  <property>
+    <name>hive.ppd.recognizetransivity</name>
+    <value>true</value>
+    <description>Whether to transitively replicate predicate filters over equijoin conditions.</description>
+  </property>
+  <property>
+    <name>hive.ppd.remove.duplicatefilters</name>
+    <value>true</value>
+    <description>
+      During query optimization, filters may be pushed down in the operator tree. 
+      If this config is true only pushed down filters remain in the operator tree, 
+      and the original filter is removed. If this config is false, the original filter 
+      is also left in the operator tree at the original place.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.point.lookup</name>
+    <value>true</value>
+    <description>Whether to transform OR clauses in Filter operators into IN clauses</description>
+  </property>
+  <property>
+    <name>hive.optimize.point.lookup.min</name>
+    <value>31</value>
+    <description>Minimum number of OR clauses needed to transform into IN clauses</description>
+  </property>
+  <property>
+    <name>hive.optimize.partition.columns.separate</name>
+    <value>true</value>
+    <description>Extract partition columns from IN clauses</description>
+  </property>
+  <property>
+    <name>hive.optimize.constant.propagation</name>
+    <value>true</value>
+    <description>Whether to enable constant propagation optimizer</description>
+  </property>
+  <property>
+    <name>hive.optimize.remove.identity.project</name>
+    <value>true</value>
+    <description>Removes identity project from operator tree</description>
+  </property>
+  <property>
+    <name>hive.optimize.metadataonly</name>
+    <value>true</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.optimize.null.scan</name>
+    <value>true</value>
+    <description>Dont scan relations which are guaranteed to not generate any rows</description>
+  </property>
+  <property>
+    <name>hive.optimize.ppd.storage</name>
+    <value>true</value>
+    <description>Whether to push predicates down to storage handlers</description>
+  </property>
+  <property>
+    <name>hive.optimize.groupby</name>
+    <value>true</value>
+    <description>Whether to enable the bucketed group by from bucketed partitions/tables.</description>
+  </property>
+  <property>
+    <name>hive.optimize.bucketmapjoin</name>
+    <value>false</value>
+    <description>Whether to try bucket mapjoin</description>
+  </property>
+  <property>
+    <name>hive.optimize.bucketmapjoin.sortedmerge</name>
+    <value>false</value>
+    <description>Whether to try sorted bucket merge map join</description>
+  </property>
+  <property>
+    <name>hive.optimize.reducededuplication</name>
+    <value>true</value>
+    <description>
+      Remove extra map-reduce jobs if the data is already clustered by the same key which needs to be used again. 
+      This should always be set to true. Since it is a new feature, it has been made configurable.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.reducededuplication.min.reducer</name>
+    <value>4</value>
+    <description>
+      Reduce deduplication merges two RSs by moving key/parts/reducer-num of the child RS to parent RS. 
+      That means if reducer-num of the child RS is fixed (order by or forced bucketing) and small, it can make very slow, single MR.
+      The optimization will be automatically disabled if number of reducers would be less than specified value.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.sort.dynamic.partition</name>
+    <value>false</value>
+    <description>
+      When enabled dynamic partitioning column will be globally sorted.
+      This way we can keep only one record writer open for each partition value
+      in the reducer thereby reducing the memory pressure on reducers.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.sampling.orderby</name>
+    <value>false</value>
+    <description>Uses sampling on order-by clause for parallel execution.</description>
+  </property>
+  <property>
+    <name>hive.optimize.sampling.orderby.number</name>
+    <value>1000</value>
+    <description>Total number of samples to be obtained.</description>
+  </property>
+  <property>
+    <name>hive.optimize.sampling.orderby.percent</name>
+    <value>0.1</value>
+    <description>
+      Expects value between 0.0f and 1.0f.
+      Probability with which a row will be chosen.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.distinct.rewrite</name>
+    <value>true</value>
+    <description>When applicable this optimization rewrites distinct aggregates from a single stage to multi-stage aggregation. This may not be optimal in all cases. Ideally, whether to trigger it or not should be cost based decision. Until Hive formalizes cost model for this, this is config driven.</description>
+  </property>
+  <property>
+    <name>hive.optimize.union.remove</name>
+    <value>false</value>
+    <description>
+      Whether to remove the union and push the operators between union and the filesink above union. 
+      This avoids an extra scan of the output by union. This is independently useful for union
+      queries, and specially useful when hive.optimize.skewjoin.compiletime is set to true, since an
+      extra union is inserted.
+      
+      The merge is triggered if either of hive.merge.mapfiles or hive.merge.mapredfiles is set to true.
+      If the user has set hive.merge.mapfiles to true and hive.merge.mapredfiles to false, the idea was the
+      number of reducers are few, so the number of files anyway are small. However, with this optimization,
+      we are increasing the number of files possibly by a big margin. So, we merge aggressively.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.correlation</name>
+    <value>false</value>
+    <description>exploit intra-query correlations.</description>
+  </property>
+  <property>
+    <name>hive.optimize.limittranspose</name>
+    <value>false</value>
+    <description>
+      Whether to push a limit through left/right outer join or union. If the value is true and the size of the outer
+      input is reduced enough (as specified in hive.optimize.limittranspose.reduction), the limit is pushed
+      to the outer input or union; to remain semantically correct, the limit is kept on top of the join or the union too.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.limittranspose.reductionpercentage</name>
+    <value>1.0</value>
+    <description>
+      When hive.optimize.limittranspose is true, this variable specifies the minimal reduction of the
+      size of the outer input of the join or input of the union that we should get in order to apply the rule.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.limittranspose.reductiontuples</name>
+    <value>0</value>
+    <description>
+      When hive.optimize.limittranspose is true, this variable specifies the minimal reduction in the
+      number of tuples of the outer input of the join or the input of the union that you should get in order to apply the rule.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.filter.stats.reduction</name>
+    <value>false</value>
+    <description>
+      Whether to simplify comparison
+      expressions in filter operators using column stats
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.skewjoin.compiletime</name>
+    <value>false</value>
+    <description>
+      Whether to create a separate plan for skewed keys for the tables in the join.
+      This is based on the skewed keys stored in the metadata. At compile time, the plan is broken
+      into different joins: one for the skewed keys, and the other for the remaining keys. And then,
+      a union is performed for the 2 joins generated above. So unless the same skewed key is present
+      in both the joined tables, the join for the skewed key will be performed as a map-side join.
+      
+      The main difference between this parameter and hive.optimize.skewjoin is that this parameter
+      uses the skew information stored in the metastore to optimize the plan at compile time itself.
+      If there is no skew information in the metadata, this parameter will not have any affect.
+      Both hive.optimize.skewjoin.compiletime and hive.optimize.skewjoin should be set to true.
+      Ideally, hive.optimize.skewjoin should be renamed as hive.optimize.skewjoin.runtime, but not doing
+      so for backward compatibility.
+      
+      If the skew information is correctly stored in the metadata, hive.optimize.skewjoin.compiletime
+      would change the query plan to take care of it, and hive.optimize.skewjoin will be a no-op.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.cte.materialize.threshold</name>
+    <value>-1</value>
+    <description>
+      If the number of references to a CTE clause exceeds this threshold, Hive will materialize it
+      before executing the main query block. -1 will disable this feature.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.index.filter.compact.minsize</name>
+    <value>5368709120</value>
+    <description>Minimum size (in bytes) of the inputs on which a compact index is automatically used.</description>
+  </property>
+  <property>
+    <name>hive.optimize.index.filter.compact.maxsize</name>
+    <value>-1</value>
+    <description>Maximum size (in bytes) of the inputs on which a compact index is automatically used.  A negative number is equivalent to infinity.</description>
+  </property>
+  <property>
+    <name>hive.index.compact.query.max.entries</name>
+    <value>10000000</value>
+    <description>The maximum number of index entries to read during a query that uses the compact index. Negative value is equivalent to infinity.</description>
+  </property>
+  <property>
+    <name>hive.index.compact.query.max.size</name>
+    <value>10737418240</value>
+    <description>The maximum number of bytes that a query using the compact index can read. Negative value is equivalent to infinity.</description>
+  </property>
+  <property>
+    <name>hive.index.compact.binary.search</name>
+    <value>true</value>
+    <description>Whether or not to use a binary search to find the entries in an index table that match the filter, where possible</description>
+  </property>
+  <property>
+    <name>hive.stats.autogather</name>
+    <value>true</value>
+    <description>A flag to gather statistics (only basic) automatically during the INSERT OVERWRITE command.</description>
+  </property>
+  <property>
+    <name>hive.stats.column.autogather</name>
+    <value>false</value>
+    <description>A flag to gather column statistics automatically.</description>
+  </property>
+  <property>
+    <name>hive.stats.dbclass</name>
+    <value>fs</value>
+    <description>
+      Expects one of the pattern in [custom, fs].
+      The storage that stores temporary Hive statistics. In filesystem based statistics collection ('fs'), 
+      each task writes statistics it has collected in a file on the filesystem, which will be aggregated 
+      after the job has finished. Supported values are fs (filesystem) and custom as defined in StatsSetupConst.java.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.default.publisher</name>
+    <value/>
+    <description>The Java class (implementing the StatsPublisher interface) that is used by default if hive.stats.dbclass is custom type.</description>
+  </property>
+  <property>
+    <name>hive.stats.default.aggregator</name>
+    <value/>
+    <description>The Java class (implementing the StatsAggregator interface) that is used by default if hive.stats.dbclass is custom type.</description>
+  </property>
+  <property>
+    <name>hive.stats.atomic</name>
+    <value>false</value>
+    <description>whether to update metastore stats only if all stats are available</description>
+  </property>
+  <property>
+    <name>hive.client.stats.counters</name>
+    <value/>
+    <description>
+      Subset of counters that should be of interest for hive.client.stats.publishers (when one wants to limit their publishing). 
+      Non-display names should be used
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.reliable</name>
+    <value>false</value>
+    <description>
+      Whether queries will fail because stats cannot be collected completely accurately. 
+      If this is set to true, reading/writing from/into a partition may fail because the stats
+      could not be computed accurately.
+    </description>
+  </property>
+  <property>
+    <name>hive.analyze.stmt.collect.partlevel.stats</name>
+    <value>true</value>
+    <description>analyze table T compute statistics for columns. Queries like these should compute partitionlevel stats for partitioned table even when no part spec is specified.</description>
+  </property>
+  <property>
+    <name>hive.stats.gather.num.threads</name>
+    <value>10</value>
+    <description>
+      Number of threads used by partialscan/noscan analyze command for partitioned tables.
+      This is applicable only for file formats that implement StatsProvidingRecordReader (like ORC).
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.collect.tablekeys</name>
+    <value>false</value>
+    <description>
+      Whether join and group by keys on tables are derived and maintained in the QueryPlan.
+      This is useful to identify how tables are accessed and to determine if they should be bucketed.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.collect.scancols</name>
+    <value>false</value>
+    <description>
+      Whether column accesses are tracked in the QueryPlan.
+      This is useful to identify how tables are accessed and to determine if there are wasted columns that can be trimmed.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.ndv.error</name>
+    <value>20.0</value>
+    <description>
+      Standard error expressed in percentage. Provides a tradeoff between accuracy and compute cost. 
+      A lower value for error indicates higher accuracy and a higher compute cost.
+    </description>
+  </property>
+  <property>
+    <name>hive.metastore.stats.ndv.densityfunction</name>
+    <value>false</value>
+    <description>Whether to use density function to estimate the NDV for the whole table based on the NDV of partitions</description>
+  </property>
+  <property>
+    <name>hive.stats.max.variable.length</name>
+    <value>100</value>
+    <description>
+      To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.),
+      average row size is multiplied with the total number of rows coming out of each operator.
+      Average row size is computed from average column size of all columns in the row. In the absence
+      of column statistics, for variable length columns (like string, bytes etc.), this value will be
+      used. For fixed length columns their corresponding Java equivalent sizes are used
+      (float - 4 bytes, double - 8 bytes etc.).
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.list.num.entries</name>
+    <value>10</value>
+    <description>
+      To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.),
+      average row size is multiplied with the total number of rows coming out of each operator.
+      Average row size is computed from average column size of all columns in the row. In the absence
+      of column statistics and for variable length complex columns like list, the average number of
+      entries/values can be specified using this config.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.map.num.entries</name>
+    <value>10</value>
+    <description>
+      To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.),
+      average row size is multiplied with the total number of rows coming out of each operator.
+      Average row size is computed from average column size of all columns in the row. In the absence
+      of column statistics and for variable length complex columns like map, the average number of
+      entries/values can be specified using this config.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.fetch.partition.stats</name>
+    <value>true</value>
+    <description>
+      Annotation of operator tree with statistics information requires partition level basic
+      statistics like number of rows, data size and file size. Partition statistics are fetched from
+      metastore. Fetching partition statistics for each needed partition can be expensive when the
+      number of partitions is high. This flag can be used to disable fetching of partition statistics
+      from metastore. When this flag is disabled, Hive will make calls to filesystem to get file sizes
+      and will estimate the number of rows from row schema.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.fetch.column.stats</name>
+    <value>false</value>
+    <description>
+      Annotation of operator tree with statistics information requires column statistics.
+      Column statistics are fetched from metastore. Fetching column statistics for each needed column
+      can be expensive when the number of columns is high. This flag can be used to disable fetching
+      of column statistics from metastore.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.join.factor</name>
+    <value>1.1</value>
+    <description>
+      Hive/Tez optimizer estimates the data size flowing through each of the operators. JOIN operator
+      uses column statistics to estimate the number of rows flowing out of it and hence the data size.
+      In the absence of column statistics, this factor determines the amount of rows that flows out
+      of JOIN operator.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.deserialization.factor</name>
+    <value>1.0</value>
+    <description>
+      Hive/Tez optimizer estimates the data size flowing through each of the operators. In the absence
+      of basic statistics like number of rows and data size, file size is used to estimate the number
+      of rows and data size. Since files in tables/partitions are serialized (and optionally
+      compressed) the estimates of number of rows and data size cannot be reliably determined.
+      This factor is multiplied with the file size to account for serialization and compression.
+    </description>
+  </property>
+  <property>
+    <name>hive.stats.filter.in.factor</name>
+    <value>1.0</value>
+    <description>
+      Currently column distribution is assumed to be uniform. This can lead to overestimation/underestimation
+      in the number of rows filtered by a certain operator, which in turn might lead to overprovision or
+      underprovision of resources. This factor is applied to the cardinality estimation of IN clauses in
+      filter operators.
+    </description>
+  </property>
+  <property>
+    <name>hive.support.concurrency</name>
+    <value>false</value>
+    <description>
+      Whether Hive supports concurrency control or not. 
+      A ZooKeeper instance must be up and running when using zookeeper Hive lock manager 
+    </description>
+  </property>
+  <property>
+    <name>hive.lock.manager</name>
+    <value>org.apache.hadoop.hive.ql.lockmgr.zookeeper.ZooKeeperHiveLockManager</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.lock.numretries</name>
+    <value>100</value>
+    <description>The number of times you want to try to get all the locks</description>
+  </property>
+  <property>
+    <name>hive.unlock.numretries</name>
+    <value>10</value>
+    <description>The number of times you want to retry to do one unlock</description>
+  </property>
+  <property>
+    <name>hive.lock.sleep.between.retries</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      The time should be in between 0 sec (exclusive) and 9223372036854775807 sec (exclusive).
+      The maximum sleep time between various retries
+    </description>
+  </property>
+  <property>
+    <name>hive.lock.mapred.only.operation</name>
+    <value>false</value>
+    <description>
+      This param is to control whether or not only do lock on queries
+      that need to execute at least one mapred job.
+    </description>
+  </property>
+  <property>
+    <name>hive.zookeeper.quorum</name>
+    <value>data-zookeeper,data-zookeeper1,data-zookeeper2</value>
+    <description>
+      List of ZooKeeper servers to talk to. This is needed for: 
+      1. Read/write locks - when hive.lock.manager is set to 
+      org.apache.hadoop.hive.ql.lockmgr.zookeeper.ZooKeeperHiveLockManager, 
+      2. When HiveServer2 supports service discovery via Zookeeper.
+      3. For delegation token storage if zookeeper store is used, if
+      hive.cluster.delegation.token.store.zookeeper.connectString is not set
+      4. LLAP daemon registry service
+    </description>
+  </property>
+  <property>
+    <name>hive.zookeeper.client.port</name>
+    <value>2181</value>
+    <description>
+      The port of ZooKeeper servers to talk to.
+      If the list of Zookeeper servers specified in hive.zookeeper.quorum
+      does not contain port numbers, this value is used.
+    </description>
+  </property>
+  <property>
+    <name>hive.zookeeper.session.timeout</name>
+    <value>1200000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      ZooKeeper client's session timeout (in milliseconds). The client is disconnected, and as a result, all locks released, 
+      if a heartbeat is not sent in the timeout.
+    </description>
+  </property>
+  <property>
+    <name>hive.zookeeper.namespace</name>
+    <value>hive_zookeeper_namespace</value>
+    <description>The parent node under which all ZooKeeper nodes are created.</description>
+  </property>
+  <property>
+    <name>hive.zookeeper.clean.extra.nodes</name>
+    <value>false</value>
+    <description>Clean extra nodes at the end of the session.</description>
+  </property>
+  <property>
+    <name>hive.zookeeper.connection.max.retries</name>
+    <value>3</value>
+    <description>Max number of times to retry when connecting to the ZooKeeper server.</description>
+  </property>
+  <property>
+    <name>hive.zookeeper.connection.basesleeptime</name>
+    <value>1000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Initial amount of time (in milliseconds) to wait between retries
+      when connecting to the ZooKeeper server when using ExponentialBackoffRetry policy.
+    </description>
+  </property>
+  <property>
+    <name>hive.txn.manager</name>
+    <value>org.apache.hadoop.hive.ql.lockmgr.DummyTxnManager</value>
+    <description>
+      Set to org.apache.hadoop.hive.ql.lockmgr.DbTxnManager as part of turning on Hive
+      transactions, which also requires appropriate settings for hive.compactor.initiator.on,
+      hive.compactor.worker.threads, hive.support.concurrency (true), hive.enforce.bucketing
+      (true), and hive.exec.dynamic.partition.mode (nonstrict).
+      The default DummyTxnManager replicates pre-Hive-0.13 behavior and provides
+      no transactions.
+    </description>
+  </property>
+  <property>
+    <name>hive.txn.timeout</name>
+    <value>300s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      time after which transactions are declared aborted if the client has not sent a heartbeat.
+    </description>
+  </property>
+  <property>
+    <name>hive.txn.heartbeat.threadpool.size</name>
+    <value>5</value>
+    <description>The number of threads to use for heartbeating. For Hive CLI, 1 is enough. For HiveServer2, we need a few</description>
+  </property>
+  <property>
+    <name>hive.txn.manager.dump.lock.state.on.acquire.timeout</name>
+    <value>false</value>
+    <description>Set this to true so that when attempt to acquire a lock on resource times out, the current state of the lock manager is dumped to log file.  This is for debugging.  See also hive.lock.numretries and hive.lock.sleep.between.retries.</description>
+  </property>
+  <property>
+    <name>hive.max.open.txns</name>
+    <value>100000</value>
+    <description>
+      Maximum number of open transactions. If 
+      current open transactions reach this limit, future open transaction requests will be 
+      rejected, until this number goes below the limit.
+    </description>
+  </property>
+  <property>
+    <name>hive.count.open.txns.interval</name>
+    <value>1s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Time in seconds between checks to count open transactions.
+    </description>
+  </property>
+  <property>
+    <name>hive.txn.max.open.batch</name>
+    <value>1000</value>
+    <description>
+      Maximum number of transactions that can be fetched in one call to open_txns().
+      This controls how many transactions streaming agents such as Flume or Storm open
+      simultaneously. The streaming agent then writes that number of entries into a single
+      file (per Flume agent or Storm bolt). Thus increasing this value decreases the number
+      of delta files created by streaming agents. But it also increases the number of open
+      transactions that Hive has to track at any given time, which may negatively affect
+      read performance.
+    </description>
+  </property>
+  <property>
+    <name>hive.txn.retryable.sqlex.regex</name>
+    <value/>
+    <description>
+      Comma separated list
+      of regular expression patterns for SQL state, error code, and error message of
+      retryable SQLExceptions, that's suitable for the metastore DB.
+      For example: Can't serialize.*,40001$,^Deadlock,.*ORA-08176.*
+      The string that the regex will be matched against is of the following form, where ex is a SQLException:
+      ex.getMessage() + " (SQLState=" + ex.getSQLState() + ", ErrorCode=" + ex.getErrorCode() + ")"
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.initiator.on</name>
+    <value>false</value>
+    <description>
+      Whether to run the initiator and cleaner threads on this metastore instance or not.
+      Set this to true on one instance of the Thrift metastore service as part of turning
+      on Hive transactions. For a complete list of parameters required for turning on
+      transactions, see hive.txn.manager.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.worker.threads</name>
+    <value>0</value>
+    <description>
+      How many compactor worker threads to run on this metastore instance. Set this to a
+      positive number on one or more instances of the Thrift metastore service as part of
+      turning on Hive transactions. For a complete list of parameters required for turning
+      on transactions, see hive.txn.manager.
+      Worker threads spawn MapReduce jobs to do compactions. They do not do the compactions
+      themselves. Increasing the number of worker threads will decrease the time it takes
+      tables or partitions to be compacted once they are determined to need compaction.
+      It will also increase the background load on the Hadoop cluster as more MapReduce jobs
+      will be running in the background.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.worker.timeout</name>
+    <value>86400s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Time in seconds after which a compaction job will be declared failed and the
+      compaction re-queued.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.check.interval</name>
+    <value>300s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Time in seconds between checks to see if any tables or partitions need to be
+      compacted. This should be kept high because each check for compaction requires
+      many calls against the NameNode.
+      Decreasing this value will reduce the time it takes for compaction to be started
+      for a table or partition that requires compaction. However, checking if compaction
+      is needed requires several calls to the NameNode for each table or partition that
+      has had a transaction done on it since the last major compaction. So decreasing this
+      value will increase the load on the NameNode.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.delta.num.threshold</name>
+    <value>10</value>
+    <description>
+      Number of delta directories in a table or partition that will trigger a minor
+      compaction.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.delta.pct.threshold</name>
+    <value>0.1</value>
+    <description>
+      Percentage (fractional) size of the delta files relative to the base that will trigger
+      a major compaction. (1.0 = 100%, so the default 0.1 = 10%.)
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.max.num.delta</name>
+    <value>500</value>
+    <description>Maximum number of delta files that the compactor will attempt to handle in a single job.</description>
+  </property>
+  <property>
+    <name>hive.compactor.abortedtxn.threshold</name>
+    <value>1000</value>
+    <description>
+      Number of aborted transactions involving a given table or partition that will trigger
+      a major compaction.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.initiator.failed.compacts.threshold</name>
+    <value>2</value>
+    <description>
+      Expects value between 1 and 20.
+      Number of consecutive compaction failures (per table/partition) after which automatic compactions will not be scheduled any more.  Note that this must be less than hive.compactor.history.retention.failed.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.cleaner.run.interval</name>
+    <value>5000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Time between runs of the cleaner thread
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.job.queue</name>
+    <value/>
+    <description>
+      Used to specify name of Hadoop queue to which
+      Compaction jobs will be submitted.  Set to empty string to let Hadoop choose the queue.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.history.retention.succeeded</name>
+    <value>3</value>
+    <description>
+      Expects value between 0 and 100.
+      Determines how many successful compaction records will be retained in compaction history for a given table/partition.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.history.retention.failed</name>
+    <value>3</value>
+    <description>
+      Expects value between 0 and 100.
+      Determines how many failed compaction records will be retained in compaction history for a given table/partition.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.history.retention.attempted</name>
+    <value>2</value>
+    <description>
+      Expects value between 0 and 100.
+      Determines how many attempted compaction records will be retained in compaction history for a given table/partition.
+    </description>
+  </property>
+  <property>
+    <name>hive.compactor.history.reaper.interval</name>
+    <value>2m</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Determines how often compaction history reaper runs
+    </description>
+  </property>
+  <property>
+    <name>hive.timedout.txn.reaper.start</name>
+    <value>100s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Time delay of 1st reaper run after metastore start
+    </description>
+  </property>
+  <property>
+    <name>hive.timedout.txn.reaper.interval</name>
+    <value>180s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Time interval describing how often the reaper runs
+    </description>
+  </property>
+  <property>
+    <name>hive.writeset.reaper.interval</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Frequency of WriteSet reaper runs
+    </description>
+  </property>
+  <property>
+    <name>hive.hbase.wal.enabled</name>
+    <value>true</value>
+    <description>
+      Whether writes to HBase should be forced to the write-ahead log. 
+      Disabling this improves HBase write performance at the risk of lost writes in case of a crash.
+    </description>
+  </property>
+  <property>
+    <name>hive.hbase.generatehfiles</name>
+    <value>false</value>
+    <description>True when HBaseStorageHandler should generate hfiles instead of operate against the online table.</description>
+  </property>
+  <property>
+    <name>hive.hbase.snapshot.name</name>
+    <value/>
+    <description>The HBase table snapshot name to use.</description>
+  </property>
+  <property>
+    <name>hive.hbase.snapshot.restoredir</name>
+    <value>/tmp</value>
+    <description>The directory in which to restore the HBase table snapshot.</description>
+  </property>
+  <property>
+    <name>hive.archive.enabled</name>
+    <value>false</value>
+    <description>Whether archiving operations are permitted</description>
+  </property>
+  <property>
+    <name>hive.optimize.index.groupby</name>
+    <value>false</value>
+    <description>Whether to enable optimization of group-by queries using Aggregate indexes.</description>
+  </property>
+  <property>
+    <name>hive.outerjoin.supports.filters</name>
+    <value>true</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.fetch.task.conversion</name>
+    <value>more</value>
+    <description>
+      Expects one of [none, minimal, more].
+      Some select queries can be converted to single FETCH task minimizing latency.
+      Currently the query should be single sourced not having any subquery and should not have
+      any aggregations or distincts (which incurs RS), lateral views and joins.
+      0. none : disable hive.fetch.task.conversion
+      1. minimal : SELECT STAR, FILTER on partition columns, LIMIT only
+      2. more    : SELECT, FILTER, LIMIT only (support TABLESAMPLE and virtual columns)
+    </description>
+  </property>
+  <property>
+    <name>hive.fetch.task.conversion.threshold</name>
+    <value>1073741824</value>
+    <description>
+      Input threshold for applying hive.fetch.task.conversion. If target table is native, input length
+      is calculated by summation of file lengths. If it's not native, storage handler for the table
+      can optionally implement org.apache.hadoop.hive.ql.metadata.InputEstimator interface.
+    </description>
+  </property>
+  <property>
+    <name>hive.fetch.task.aggr</name>
+    <value>false</value>
+    <description>
+      Aggregation queries with no group-by clause (for example, select count(*) from src) execute
+      final aggregations in single reduce task. If this is set true, Hive delegates final aggregation
+      stage to fetch task, possibly decreasing the query time.
+    </description>
+  </property>
+  <property>
+    <name>hive.compute.query.using.stats</name>
+    <value>false</value>
+    <description>
+      When set to true Hive will answer a few queries like count(1) purely using stats
+      stored in metastore. For basic stats collection turn on the config hive.stats.autogather to true.
+      For more advanced stats collection need to run analyze table queries.
+    </description>
+  </property>
+  <property>
+    <name>hive.fetch.output.serde</name>
+    <value>org.apache.hadoop.hive.serde2.DelimitedJSONSerDe</value>
+    <description>The SerDe used by FetchTask to serialize the fetch output.</description>
+  </property>
+  <property>
+    <name>hive.cache.expr.evaluation</name>
+    <value>true</value>
+    <description>
+      If true, the evaluation result of a deterministic expression referenced twice or more
+      will be cached.
+      For example, in a filter condition like '.. where key + 10 = 100 or key + 10 = 0'
+      the expression 'key + 10' will be evaluated/cached once and reused for the following
+      expression ('key + 10 = 0'). Currently, this is applied only to expressions in select
+      or filter operators.
+    </description>
+  </property>
+  <property>
+    <name>hive.variable.substitute</name>
+    <value>true</value>
+    <description>This enables substitution using syntax like ${var} ${system:var} and ${env:var}.</description>
+  </property>
+  <property>
+    <name>hive.variable.substitute.depth</name>
+    <value>40</value>
+    <description>The maximum replacements the substitution engine will do.</description>
+  </property>
+  <property>
+    <name>hive.conf.validation</name>
+    <value>true</value>
+    <description>Enables type checking for registered Hive configurations</description>
+  </property>
+  <property>
+    <name>hive.semantic.analyzer.hook</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.security.authorization.enabled</name>
+    <value>false</value>
+    <description>enable or disable the Hive client authorization</description>
+  </property>
+  <property>
+    <name>hive.security.authorization.manager</name>
+    <value>org.apache.hadoop.hive.ql.security.authorization.plugin.sqlstd.SQLStdHiveAuthorizerFactory</value>
+    <description>
+      The Hive client authorization manager class name. The user defined authorization class should implement 
+      interface org.apache.hadoop.hive.ql.security.authorization.HiveAuthorizationProvider.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authenticator.manager</name>
+    <value>org.apache.hadoop.hive.ql.security.HadoopDefaultAuthenticator</value>
+    <description>
+      hive client authenticator manager class name. The user defined authenticator should implement 
+      interface org.apache.hadoop.hive.ql.security.HiveAuthenticationProvider.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.metastore.authorization.manager</name>
+    <value>org.apache.hadoop.hive.ql.security.authorization.DefaultHiveMetastoreAuthorizationProvider</value>
+    <description>
+      Names of authorization manager classes (comma separated) to be used in the metastore
+      for authorization. The user defined authorization class should implement interface
+      org.apache.hadoop.hive.ql.security.authorization.HiveMetastoreAuthorizationProvider.
+      All authorization manager classes have to successfully authorize the metastore API
+      call for the command execution to be allowed.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.metastore.authorization.auth.reads</name>
+    <value>true</value>
+    <description>If this is true, metastore authorizer authorizes read actions on database, table</description>
+  </property>
+  <property>
+    <name>hive.security.metastore.authenticator.manager</name>
+    <value>org.apache.hadoop.hive.ql.security.HadoopDefaultMetastoreAuthenticator</value>
+    <description>
+      authenticator manager class name to be used in the metastore for authentication. 
+      The user defined authenticator should implement interface org.apache.hadoop.hive.ql.security.HiveAuthenticationProvider.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authorization.createtable.user.grants</name>
+    <value/>
+    <description>
+      the privileges automatically granted to some users whenever a table gets created.
+      An example like "userX,userY:select;userZ:create" will grant select privilege to userX and userY,
+      and grant create privilege to userZ whenever a new table created.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authorization.createtable.group.grants</name>
+    <value/>
+    <description>
+      the privileges automatically granted to some groups whenever a table gets created.
+      An example like "groupX,groupY:select;groupZ:create" will grant select privilege to groupX and groupY,
+      and grant create privilege to groupZ whenever a new table created.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authorization.createtable.role.grants</name>
+    <value/>
+    <description>
+      the privileges automatically granted to some roles whenever a table gets created.
+      An example like "roleX,roleY:select;roleZ:create" will grant select privilege to roleX and roleY,
+      and grant create privilege to roleZ whenever a new table created.
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authorization.createtable.owner.grants</name>
+    <value/>
+    <description>
+      The privileges automatically granted to the owner whenever a table gets created.
+      An example like "select,drop" will grant select and drop privilege to the owner
+      of the table. Note that the default gives the creator of a table no access to the
+      table (but see HIVE-8067).
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authorization.task.factory</name>
+    <value>org.apache.hadoop.hive.ql.parse.authorization.HiveAuthorizationTaskFactoryImpl</value>
+    <description>Authorization DDL task factory implementation</description>
+  </property>
+  <property>
+    <name>hive.security.authorization.sqlstd.confwhitelist</name>
+    <value/>
+    <description>
+      List of comma separated Java regexes. Configurations parameters that match these
+      regexes can be modified by user when SQL standard authorization is enabled.
+      To get the default value, use the 'set &lt;param&gt;' command.
+      Note that the hive.conf.restricted.list checks are still enforced after the white list
+      check
+    </description>
+  </property>
+  <property>
+    <name>hive.security.authorization.sqlstd.confwhitelist.append</name>
+    <value/>
+    <description>
+      List of comma separated Java regexes, to be appended to list set in
+      hive.security.authorization.sqlstd.confwhitelist. Using this list instead
+      of updating the original list means that you can append to the defaults
+      set by SQL standard authorization instead of replacing it entirely.
+    </description>
+  </property>
+  <property>
+    <name>hive.cli.print.header</name>
+    <value>false</value>
+    <description>Whether to print the names of the columns in query output.</description>
+  </property>
+  <property>
+    <name>hive.cli.tez.session.async</name>
+    <value>true</value>
+    <description>
+      Whether to start Tez
+      session in background when running CLI with Tez, allowing CLI to be available earlier.
+    </description>
+  </property>
+  <property>
+    <name>hive.error.on.empty.partition</name>
+    <value>false</value>
+    <description>Whether to throw an exception if dynamic partition insert generates empty results.</description>
+  </property>
+  <property>
+    <name>hive.index.compact.file</name>
+    <value/>
+    <description>internal variable</description>
+  </property>
+  <property>
+    <name>hive.index.blockfilter.file</name>
+    <value/>
+    <description>internal variable</description>
+  </property>
+  <property>
+    <name>hive.index.compact.file.ignore.hdfs</name>
+    <value>false</value>
+    <description>
+      When true the HDFS location stored in the index file will be ignored at runtime.
+      If the data got moved or the name of the cluster got changed, the index data should still be usable.
+    </description>
+  </property>
+  <property>
+    <name>hive.exim.uri.scheme.whitelist</name>
+    <value>hdfs,pfile</value>
+    <description>A comma separated list of acceptable URI schemes for import and export.</description>
+  </property>
+  <property>
+    <name>hive.exim.strict.repl.tables</name>
+    <value>true</value>
+    <description>
+      Parameter that determines if 'regular' (non-replication) export dumps can be
+      imported on to tables that are the target of replication. If this parameter is
+      set, regular imports will check if the destination table(if it exists) has a 'repl.last.id' set on it. If so, it will fail.
+    </description>
+  </property>
+  <property>
+    <name>hive.repl.task.factory</name>
+    <value>org.apache.hive.hcatalog.api.repl.exim.EximReplicationTaskFactory</value>
+    <description>
+      Parameter that can be used to override which ReplicationTaskFactory will be
+      used to instantiate ReplicationTask events. Override for third party repl plugins
+    </description>
+  </property>
+  <property>
+    <name>hive.mapper.cannot.span.multiple.partitions</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.rework.mapredwork</name>
+    <value>false</value>
+    <description>
+      should rework the mapred work or not.
+      This is first introduced by SymlinkTextInputFormat to replace symlink files with real paths at compile time.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.concatenate.check.index</name>
+    <value>true</value>
+    <description>
+      If this is set to true, Hive will throw error when doing
+      'alter table tbl_name [partSpec] concatenate' on a table/partition
+      that has indexes on it. The reason the user want to set this to true
+      is because it can help user to avoid handling all index drop, recreation,
+      rebuild work. This is very helpful for tables with thousands of partitions.
+    </description>
+  </property>
+  <property>
+    <name>hive.io.exception.handlers</name>
+    <value/>
+    <description>
+      A list of io exception handler class names. This is used
+      to construct a list exception handlers to handle exceptions thrown
+      by record readers
+    </description>
+  </property>
+  <property>
+    <name>hive.log4j.file</name>
+    <value/>
+    <description>
+      Hive log4j configuration file.
+      If the property is not set, then logging will be initialized using hive-log4j2.properties found on the classpath.
+      If the property is set, the value must be a valid URI (java.net.URI, e.g. "file:///tmp/my-logging.xml"), 
+      which you can then extract a URL from and pass to PropertyConfigurator.configure(URL).
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.log4j.file</name>
+    <value/>
+    <description>
+      Hive log4j configuration file for execution mode(sub command).
+      If the property is not set, then logging will be initialized using hive-exec-log4j2.properties found on the classpath.
+      If the property is set, the value must be a valid URI (java.net.URI, e.g. "file:///tmp/my-logging.xml"), 
+      which you can then extract a URL from and pass to PropertyConfigurator.configure(URL).
+    </description>
+  </property>
+  <property>
+    <name>hive.async.log.enabled</name>
+    <value>true</value>
+    <description>
+      Whether to enable Log4j2's asynchronous logging. Asynchronous logging can give
+       significant performance improvement as logging will be handled in separate thread
+       that uses LMAX disruptor queue for buffering log messages.
+       Refer https://logging.apache.org/log4j/2.x/manual/async.html for benefits and
+       drawbacks.
+    </description>
+  </property>
+  <property>
+    <name>hive.log.explain.output</name>
+    <value>false</value>
+    <description>
+      Whether to log explain output for every query.
+      When enabled, will log EXPLAIN EXTENDED output for the query at INFO log4j log level.
+    </description>
+  </property>
+  <property>
+    <name>hive.explain.user</name>
+    <value>true</value>
+    <description>
+      Whether to show explain result at user level.
+      When enabled, will log EXPLAIN output for the query at user level.
+    </description>
+  </property>
+  <property>
+    <name>hive.autogen.columnalias.prefix.label</name>
+    <value>_c</value>
+    <description>
+      String used as a prefix when auto generating column alias.
+      By default the prefix label will be appended with a column position number to form the column alias. 
+      Auto generation would happen if an aggregate function is used in a select clause without an explicit alias.
+    </description>
+  </property>
+  <property>
+    <name>hive.autogen.columnalias.prefix.includefuncname</name>
+    <value>false</value>
+    <description>Whether to include function name in the column alias auto generated by Hive.</description>
+  </property>
+  <property>
+    <name>hive.service.metrics.class</name>
+    <value>org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics</value>
+    <description>
+      Expects one of [org.apache.hadoop.hive.common.metrics.metrics2.codahalemetrics, org.apache.hadoop.hive.common.metrics.legacymetrics].
+      Hive metrics subsystem implementation class.
+    </description>
+  </property>
+  <property>
+    <name>hive.service.metrics.reporter</name>
+    <value>JSON_FILE, JMX</value>
+    <description>Reporter type for metric class org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics, comma separated list of JMX, CONSOLE, JSON_FILE, HADOOP2</description>
+  </property>
+  <property>
+    <name>hive.service.metrics.file.location</name>
+    <value>/tmp/report.json</value>
+    <description>For metric class org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics JSON_FILE reporter, the location of local JSON metrics file.  This file will get overwritten at every interval.</description>
+  </property>
+  <property>
+    <name>hive.service.metrics.file.frequency</name>
+    <value>5s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      For metric class org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics JSON_FILE reporter, the frequency of updating JSON metrics file.
+    </description>
+  </property>
+  <property>
+    <name>hive.service.metrics.hadoop2.frequency</name>
+    <value>30s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      For metric class org.apache.hadoop.hive.common.metrics.metrics2.CodahaleMetrics HADOOP2 reporter, the frequency of updating the HADOOP2 metrics system.
+    </description>
+  </property>
+  <property>
+    <name>hive.service.metrics.hadoop2.component</name>
+    <value>hive</value>
+    <description>Component name to provide to Hadoop2 Metrics system. Ideally 'hivemetastore' for the MetaStore  and and 'hiveserver2' for HiveServer2.</description>
+  </property>
+  <property>
+    <name>hive.exec.perf.logger</name>
+    <value>org.apache.hadoop.hive.ql.log.PerfLogger</value>
+    <description>
+      The class responsible for logging client side performance metrics. 
+      Must be a subclass of org.apache.hadoop.hive.ql.log.PerfLogger
+    </description>
+  </property>
+  <property>
+    <name>hive.start.cleanup.scratchdir</name>
+    <value>false</value>
+    <description>To cleanup the Hive scratchdir when starting the Hive Server</description>
+  </property>
+  <property>
+    <name>hive.scratchdir.lock</name>
+    <value>false</value>
+    <description>To hold a lock file in scratchdir to prevent to be removed by cleardanglingscratchdir</description>
+  </property>
+  <property>
+    <name>hive.insert.into.multilevel.dirs</name>
+    <value>false</value>
+    <description>
+      Where to insert into multilevel directories like
+      "insert directory '/HIVEFT25686/chinna/' from table"
+    </description>
+  </property>
+  <property>
+    <name>hive.warehouse.subdir.inherit.perms</name>
+    <value>true</value>
+    <description>
+      Set this to false if the table directories should be created
+      with the permissions derived from dfs umask instead of
+      inheriting the permission of the warehouse or database directory.
+    </description>
+  </property>
+  <property>
+    <name>hive.insert.into.external.tables</name>
+    <value>true</value>
+    <description>whether insert into external tables is allowed</description>
+  </property>
+  <property>
+    <name>hive.exec.temporary.table.storage</name>
+    <value>default</value>
+    <description>
+      Expects one of [memory, ssd, default].
+      Define the storage policy for temporary tables.Choices between memory, ssd and default
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.driver.run.hooks</name>
+    <value/>
+    <description>A comma separated list of hooks which implement HiveDriverRunHook. Will be run at the beginning and end of Driver.run, these will be run in the order specified.</description>
+  </property>
+  <property>
+    <name>hive.ddl.output.format</name>
+    <value/>
+    <description>
+      The data format to use for DDL output.  One of "text" (for human
+      readable text) or "json" (for a json object).
+    </description>
+  </property>
+  <property>
+    <name>hive.entity.separator</name>
+    <value>@</value>
+    <description>Separator used to construct names of tables and partitions. For example, dbname@tablename@partitionname</description>
+  </property>
+  <property>
+    <name>hive.entity.capture.transform</name>
+    <value>false</value>
+    <description>Compiler to capture transform URI referred in the query</description>
+  </property>
+  <property>
+    <name>hive.display.partition.cols.separately</name>
+    <value>true</value>
+    <description>
+      In older Hive version (0.10 and earlier) no distinction was made between
+      partition columns or non-partition columns while displaying columns in describe
+      table. From 0.12 onwards, they are displayed separately. This flag will let you
+      get old behavior, if desired. See, test-case in patch for HIVE-6689.
+    </description>
+  </property>
+  <property>
+    <name>hive.ssl.protocol.blacklist</name>
+    <value>SSLv2,SSLv3</value>
+    <description>SSL Versions to disable for all Hive Servers</description>
+  </property>
+  <property>
+    <name>hive.server2.max.start.attempts</name>
+    <value>30</value>
+    <description>
+      Expects value bigger than 0.
+      Number of times HiveServer2 will attempt to start before exiting, sleeping 60 seconds between retries. 
+       The default of 30 will keep trying for 30 minutes.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.support.dynamic.service.discovery</name>
+    <value>false</value>
+    <description>Whether HiveServer2 supports dynamic service discovery for its clients. To support this, each instance of HiveServer2 currently uses ZooKeeper to register itself, when it is brought up. JDBC/ODBC clients should use the ZooKeeper ensemble: hive.zookeeper.quorum in their connection string.</description>
+  </property>
+  <property>
+    <name>hive.server2.zookeeper.namespace</name>
+    <value>hiveserver2</value>
+    <description>The parent node in ZooKeeper used by HiveServer2 when supporting dynamic service discovery.</description>
+  </property>
+  <property>
+    <name>hive.server2.zookeeper.publish.configs</name>
+    <value>true</value>
+    <description>Whether we should publish HiveServer2's configs to ZooKeeper.</description>
+  </property>
+  <property>
+    <name>hive.server2.global.init.file.location</name>
+    <value>${env:HIVE_CONF_DIR}</value>
+    <description>
+      Either the location of a HS2 global init file or a directory containing a .hiverc file. If the 
+      property is set, the value must be a valid path to an init file or directory where the init file is located.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.transport.mode</name>
+    <value>binary</value>
+    <description>
+      Expects one of [binary, http].
+      Transport mode of HiveServer2.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.bind.host</name>
+    <value/>
+    <description>Bind host on which to run the HiveServer2 Thrift service.</description>
+  </property>
+  <property>
+    <name>hive.driver.parallel.compilation</name>
+    <value>false</value>
+    <description>
+      Whether to
+      enable parallel compilation between sessions on HiveServer2. The default is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.compile.lock.timeout</name>
+    <value>0s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds a request will wait to acquire the compile lock before giving up. Setting it to 0s disables the timeout.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.parallel.ops.in.session</name>
+    <value>true</value>
+    <description>Whether to allow several parallel operations (such as SQL statements) in one session.</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.host</name>
+    <value>0.0.0.0</value>
+    <description>The host address the HiveServer2 WebUI will listen on</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.port</name>
+    <value>10002</value>
+    <description>The port the HiveServer2 WebUI will listen on. This can beset to 0 or a negative integer to disable the web UI</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.max.threads</name>
+    <value>50</value>
+    <description>The max HiveServer2 WebUI threads</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.use.ssl</name>
+    <value>false</value>
+    <description>Set this to true for using SSL encryption for HiveServer2 WebUI.</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.keystore.path</name>
+    <value/>
+    <description>SSL certificate keystore location for HiveServer2 WebUI.</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.keystore.password</name>
+    <value/>
+    <description>SSL certificate keystore password for HiveServer2 WebUI.</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.use.spnego</name>
+    <value>false</value>
+    <description>If true, the HiveServer2 WebUI will be secured with SPNEGO. Clients must authenticate with Kerberos.</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.spnego.keytab</name>
+    <value/>
+    <description>The path to the Kerberos Keytab file containing the HiveServer2 WebUI SPNEGO service principal.</description>
+  </property>
+  <property>
+    <name>hive.server2.webui.spnego.principal</name>
+    <value>HTTP/_HOST@EXAMPLE.COM</value>
+    <description>
+      The HiveServer2 WebUI SPNEGO service principal.
+      The special string _HOST will be replaced automatically with 
+      the value of hive.server2.webui.host or the correct host name.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.webui.max.historic.queries</name>
+    <value>25</value>
+    <description>The maximum number of past queries to show in HiverSever2 WebUI.</description>
+  </property>
+  <property>
+    <name>hive.server2.tez.default.queues</name>
+    <value/>
+    <description>
+      A list of comma separated values corresponding to YARN queues of the same name.
+      When HiveServer2 is launched in Tez mode, this configuration needs to be set
+      for multiple Tez sessions to run in parallel on the cluster.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.tez.sessions.per.default.queue</name>
+    <value>1</value>
+    <description>
+      A positive integer that determines the number of Tez sessions that should be
+      launched on each of the queues specified by "hive.server2.tez.default.queues".
+      Determines the parallelism on each queue.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.tez.initialize.default.sessions</name>
+    <value>false</value>
+    <description>
+      This flag is used in HiveServer2 to enable a user to use HiveServer2 without
+      turning on Tez for HiveServer2. The user could potentially want to run queries
+      over Tez without the pool of sessions.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.tez.session.lifetime</name>
+    <value>162h</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is hour if not specified.
+      The lifetime of the Tez sessions launched by HS2 when default sessions are enabled.
+      Set to 0 to disable session expiration.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.tez.session.lifetime.jitter</name>
+    <value>3h</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is hour if not specified.
+      The jitter for Tez session lifetime; prevents all the sessions from restarting at once.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.tez.sessions.init.threads</name>
+    <value>16</value>
+    <description>
+      If hive.server2.tez.initialize.default.sessions is enabled, the maximum number of
+      threads to use to initialize the default sessions.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.logging.operation.enabled</name>
+    <value>true</value>
+    <description>When true, HS2 will save operation logs and make them available for clients</description>
+  </property>
+  <property>
+    <name>hive.server2.logging.operation.log.location</name>
+    <value>/root/hive/logs/operation_logs</value>
+    <description>Top level directory where operation logs are stored if logging functionality is enabled</description>
+  </property>
+  <property>
+    <name>hive.server2.logging.operation.level</name>
+    <value>EXECUTION</value>
+    <description>
+      Expects one of [none, execution, performance, verbose].
+      HS2 operation logging mode available to clients to be set at session level.
+      For this to work, hive.server2.logging.operation.enabled should be set to true.
+        NONE: Ignore any logging
+        EXECUTION: Log completion of tasks
+        PERFORMANCE: Execution + Performance logs 
+        VERBOSE: All logs
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.metrics.enabled</name>
+    <value>false</value>
+    <description>Enable metrics on the HiveServer2.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.port</name>
+    <value>10001</value>
+    <description>Port number of HiveServer2 Thrift interface when hive.server2.transport.mode is 'http'.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.path</name>
+    <value>cliservice</value>
+    <description>Path component of URL endpoint when in HTTP mode.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.max.message.size</name>
+    <value>104857600</value>
+    <description>Maximum message size in bytes a HS2 server will accept.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.max.idle.time</name>
+    <value>1800s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Maximum idle time for a connection on the server when in HTTP mode.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.worker.keepalive.time</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Keepalive time for an idle http worker thread. When the number of workers exceeds min workers, excessive threads are killed after this time interval.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.request.header.size</name>
+    <value>6144</value>
+    <description>Request header size in bytes, when using HTTP transport mode. Jetty defaults used.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.response.header.size</name>
+    <value>6144</value>
+    <description>Response header size in bytes, when using HTTP transport mode. Jetty defaults used.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.cookie.auth.enabled</name>
+    <value>true</value>
+    <description>When true, HiveServer2 in HTTP transport mode, will use cookie based authentication mechanism.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.cookie.max.age</name>
+    <value>86400s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Maximum age in seconds for server side cookie used by HS2 in HTTP mode.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.cookie.domain</name>
+    <value/>
+    <description>Domain for the HS2 generated cookies</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.cookie.path</name>
+    <value/>
+    <description>Path for the HS2 generated cookies</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.cookie.is.secure</name>
+    <value>true</value>
+    <description>Secure attribute of the HS2 generated cookie.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.http.cookie.is.httponly</name>
+    <value>true</value>
+    <description>HttpOnly attribute of the HS2 generated cookie.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.port</name>
+    <value>10000</value>
+    <description>Port number of HiveServer2 Thrift interface when hive.server2.transport.mode is 'binary'.</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.sasl.qop</name>
+    <value>auth</value>
+    <description>
+      Expects one of [auth, auth-int, auth-conf].
+      Sasl QOP value; set it to one of following values to enable higher levels of
+      protection for HiveServer2 communication with clients.
+      Setting hadoop.rpc.protection to a higher level than HiveServer2 does not
+      make sense in most situations. HiveServer2 ignores hadoop.rpc.protection in favor
+      of hive.server2.thrift.sasl.qop.
+        "auth" - authentication only (default)
+        "auth-int" - authentication plus integrity protection
+        "auth-conf" - authentication plus integrity and confidentiality protection
+      This is applicable only if HiveServer2 is configured to use Kerberos authentication.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.min.worker.threads</name>
+    <value>5</value>
+    <description>Minimum number of Thrift worker threads</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.max.worker.threads</name>
+    <value>500</value>
+    <description>Maximum number of Thrift worker threads</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.exponential.backoff.slot.length</name>
+    <value>100ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Binary exponential backoff slot time for Thrift clients during login to HiveServer2,
+      for retries until hitting Thrift client timeout
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.login.timeout</name>
+    <value>20s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Timeout for Thrift clients during login to HiveServer2
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.worker.keepalive.time</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Keepalive time (in seconds) for an idle worker thread. When the number of workers exceeds min workers, excessive threads are killed after this time interval.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.async.exec.threads</name>
+    <value>100</value>
+    <description>Number of threads in the async thread pool for HiveServer2</description>
+  </property>
+  <property>
+    <name>hive.server2.async.exec.shutdown.timeout</name>
+    <value>10s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      How long HiveServer2 shutdown will wait for async threads to terminate.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.async.exec.wait.queue.size</name>
+    <value>100</value>
+    <description>
+      Size of the wait queue for async thread pool in HiveServer2.
+      After hitting this limit, the async thread pool will reject new requests.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.async.exec.keepalive.time</name>
+    <value>10s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Time that an idle HiveServer2 async thread (from the thread pool) will wait for a new task
+      to arrive before terminating
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.async.exec.async.compile</name>
+    <value>false</value>
+    <description>Whether to enable compiling async query asynchronously. If enabled, it is unknown if the query will have any resultset before compilation completed.</description>
+  </property>
+  <property>
+    <name>hive.server2.long.polling.timeout</name>
+    <value>5000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Time that HiveServer2 will wait before responding to asynchronous calls that use long polling
+    </description>
+  </property>
+  <property>
+    <name>hive.session.impl.classname</name>
+    <value/>
+    <description>Classname for custom implementation of hive session</description>
+  </property>
+  <property>
+    <name>hive.session.impl.withugi.classname</name>
+    <value/>
+    <description>Classname for custom implementation of hive session with UGI</description>
+  </property>
+  <property>
+    <name>hive.server2.authentication</name>
+    <value>NONE</value>
+    <description>
+      Expects one of [nosasl, none, ldap, kerberos, pam, custom].
+      Client authentication types.
+        NONE: no authentication check
+        LDAP: LDAP/AD based authentication
+        KERBEROS: Kerberos/GSSAPI authentication
+        CUSTOM: Custom authentication provider
+                (Use with property hive.server2.custom.authentication.class)
+        PAM: Pluggable authentication module
+        NOSASL:  Raw transport
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.allow.user.substitution</name>
+    <value>true</value>
+    <description>Allow alternate user to be specified as part of HiveServer2 open connection request.</description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.kerberos.keytab</name>
+    <value/>
+    <description>Kerberos keytab file for server principal</description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.kerberos.principal</name>
+    <value/>
+    <description>Kerberos server principal</description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.spnego.keytab</name>
+    <value/>
+    <description>
+      keytab file for SPNego principal, optional,
+      typical value would look like /etc/security/keytabs/spnego.service.keytab,
+      This keytab would be used by HiveServer2 when Kerberos security is enabled and 
+      HTTP transport mode is used.
+      This needs to be set only if SPNEGO is to be used in authentication.
+      SPNego authentication would be honored only if valid
+        hive.server2.authentication.spnego.principal
+      and
+        hive.server2.authentication.spnego.keytab
+      are specified.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.spnego.principal</name>
+    <value/>
+    <description>
+      SPNego service principal, optional,
+      typical value would look like HTTP/_HOST@EXAMPLE.COM
+      SPNego service principal would be used by HiveServer2 when Kerberos security is enabled
+      and HTTP transport mode is used.
+      This needs to be set only if SPNEGO is to be used in authentication.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.url</name>
+    <value/>
+    <description>
+      LDAP connection URL(s),
+      this value could contain URLs to mutiple LDAP servers instances for HA,
+      each LDAP URL is separated by a SPACE character. URLs are used in the 
+       order specified until a connection is successful.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.baseDN</name>
+    <value/>
+    <description>LDAP base DN</description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.Domain</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.groupDNPattern</name>
+    <value/>
+    <description>
+      COLON-separated list of patterns to use to find DNs for group entities in this directory.
+      Use %s where the actual group name is to be substituted for.
+      For example: CN=%s,CN=Groups,DC=subdomain,DC=domain,DC=com.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.groupFilter</name>
+    <value/>
+    <description>
+      COMMA-separated list of LDAP Group names (short name not full DNs).
+      For example: HiveAdmins,HadoopAdmins,Administrators
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.userDNPattern</name>
+    <value/>
+    <description>
+      COLON-separated list of patterns to use to find DNs for users in this directory.
+      Use %s where the actual group name is to be substituted for.
+      For example: CN=%s,CN=Users,DC=subdomain,DC=domain,DC=com.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.userFilter</name>
+    <value/>
+    <description>
+      COMMA-separated list of LDAP usernames (just short names, not full DNs).
+      For example: hiveuser,impalauser,hiveadmin,hadoopadmin
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.guidKey</name>
+    <value>uid</value>
+    <description>
+      LDAP attribute name whose values are unique in this LDAP server.
+      For example: uid or CN.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.groupMembershipKey</name>
+    <value>member</value>
+    <description>
+      LDAP attribute name on the user entry that references a group, the user belongs to.
+      For example: member, uniqueMember or memberUid
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.groupClassKey</name>
+    <value>groupOfNames</value>
+    <description>
+      LDAP attribute name on the group entry that is to be used in LDAP group searches.
+      For example: group, groupOfNames or groupOfUniqueNames.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.ldap.customLDAPQuery</name>
+    <value/>
+    <description>
+      A full LDAP query that LDAP Atn provider uses to execute against LDAP Server.
+      If this query returns a null resultset, the LDAP Provider fails the Authentication
+      request, succeeds if the user is part of the resultset.For example: (&amp;(objectClass=group)(objectClass=top)(instanceType=4)(cn=Domain*)) 
+      (&amp;(objectClass=person)(|(sAMAccountName=admin)(|(memberOf=CN=Domain Admins,CN=Users,DC=domain,DC=com)(memberOf=CN=Administrators,CN=Builtin,DC=domain,DC=com))))
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.custom.authentication.class</name>
+    <value/>
+    <description>
+      Custom authentication class. Used when property
+      'hive.server2.authentication' is set to 'CUSTOM'. Provided class
+      must be a proper implementation of the interface
+      org.apache.hive.service.auth.PasswdAuthenticationProvider. HiveServer2
+      will call its Authenticate(user, passed) method to authenticate requests.
+      The implementation may optionally implement Hadoop's
+      org.apache.hadoop.conf.Configurable class to grab Hive's Configuration object.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.authentication.pam.services</name>
+    <value/>
+    <description>
+      List of the underlying pam services that should be used when auth type is PAM
+      A file with the same name must exist in /etc/pam.d
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.enable.doAs</name>
+    <value>true</value>
+    <description>
+      Setting this property to true will have HiveServer2 execute
+      Hive operations as the user making the calls to it.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.table.type.mapping</name>
+    <value>CLASSIC</value>
+    <description>
+      Expects one of [classic, hive].
+      This setting reflects how HiveServer2 will report the table types for JDBC and other
+      client implementations that retrieve the available tables and supported table types
+        HIVE : Exposes Hive's native table types like MANAGED_TABLE, EXTERNAL_TABLE, VIRTUAL_VIEW
+        CLASSIC : More generic types like TABLE and VIEW
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.session.hook</name>
+    <value/>
+    <description/>
+  </property>
+  <property>
+    <name>hive.server2.use.SSL</name>
+    <value>false</value>
+    <description>Set this to true for using SSL encryption in HiveServer2.</description>
+  </property>
+  <property>
+    <name>hive.server2.keystore.path</name>
+    <value/>
+    <description>SSL certificate keystore location.</description>
+  </property>
+  <property>
+    <name>hive.server2.keystore.password</name>
+    <value/>
+    <description>SSL certificate keystore password.</description>
+  </property>
+  <property>
+    <name>hive.server2.map.fair.scheduler.queue</name>
+    <value>true</value>
+    <description>
+      If the YARN fair scheduler is configured and HiveServer2 is running in non-impersonation mode,
+      this setting determines the user for fair scheduler queue mapping.
+      If set to true (default), the logged-in user determines the fair scheduler queue
+      for submitted jobs, so that map reduce resource usage can be tracked by user.
+      If set to false, all Hive jobs go to the 'hive' user's queue.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.builtin.udf.whitelist</name>
+    <value/>
+    <description>
+      Comma separated list of builtin udf names allowed in queries.
+      An empty whitelist allows all builtin udfs to be executed.  The udf black list takes precedence over udf white list
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.builtin.udf.blacklist</name>
+    <value/>
+    <description>Comma separated list of udfs names. These udfs will not be allowed in queries. The udf black list takes precedence over udf white list</description>
+  </property>
+  <property>
+    <name>hive.allow.udf.load.on.demand</name>
+    <value>false</value>
+    <description>
+      Whether enable loading UDFs from metastore on demand; this is mostly relevant for
+      HS2 and was the default behavior before Hive 1.2. Off by default.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.session.check.interval</name>
+    <value>6h</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      The time should be bigger than or equal to 3000 msec.
+      The check interval for session/operation timeout, which can be disabled by setting to zero or negative value.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.close.session.on.disconnect</name>
+    <value>true</value>
+    <description>Session will be closed when connection is closed. Set this to false to have session outlive its parent connection.</description>
+  </property>
+  <property>
+    <name>hive.server2.idle.session.timeout</name>
+    <value>7d</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Session will be closed when it's not accessed for this duration, which can be disabled by setting to zero or negative value.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.idle.operation.timeout</name>
+    <value>5d</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Operation will be closed when it's not accessed for this duration of time, which can be disabled by setting to zero value.
+        With positive value, it's checked for operations in terminal state only (FINISHED, CANCELED, CLOSED, ERROR).
+        With negative value, it's checked for all of the operations regardless of state.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.idle.session.check.operation</name>
+    <value>true</value>
+    <description>
+      Session will be considered to be idle only if there is no activity, and there is no pending operation.
+       This setting takes effect only if session idle timeout (hive.server2.idle.session.timeout) and checking
+      (hive.server2.session.check.interval) are enabled.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.client.retry.limit</name>
+    <value>1</value>
+    <description>Number of retries upon failure of Thrift HiveServer2 calls</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.client.connect.retry.limit</name>
+    <value>1</value>
+    <description>Number of retries while opening a connection to HiveServe2</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.client.retry.delay.seconds</name>
+    <value>1s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Number of seconds for the HiveServer2 thrift client to wait between consecutive connection attempts. Also specifies the time to wait between retrying thrift calls upon failures
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.client.user</name>
+    <value>anonymous</value>
+    <description>Username to use against thrift client</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.client.password</name>
+    <value>anonymous</value>
+    <description>Password to use against thrift client</description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.resultset.serialize.in.tasks</name>
+    <value>false</value>
+    <description>
+      Whether we should serialize the Thrift structures used in JDBC ResultSet RPC in task nodes.
+       We use SequenceFile and ThriftJDBCBinarySerDe to read and write the final results if this is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.thrift.resultset.max.fetch.size</name>
+    <value>1000</value>
+    <description>Max number of rows sent in one Fetch RPC call by the server to the client.</description>
+  </property>
+  <property>
+    <name>hive.server2.xsrf.filter.enabled</name>
+    <value>false</value>
+    <description>If enabled, HiveServer2 will block any requests made to it over http if an X-XSRF-HEADER header is not present</description>
+  </property>
+  <property>
+    <name>hive.security.command.whitelist</name>
+    <value>set,reset,dfs,add,list,delete,reload,compile</value>
+    <description>Comma separated list of non-SQL Hive commands users are authorized to execute</description>
+  </property>
+  <property>
+    <name>hive.mv.files.thread</name>
+    <value>15</value>
+    <description>
+      Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb).
+      The size should be in between 0Pb (inclusive) and 1Kb (inclusive).
+      Number of threads used to move files in move task. Set it to 0 to disable multi-threaded file moves. This parameter is also used by MSCK to check tables.
+    </description>
+  </property>
+  <property>
+    <name>hive.multi.insert.move.tasks.share.dependencies</name>
+    <value>false</value>
+    <description>
+      If this is set all move tasks for tables/partitions (not directories) at the end of a
+      multi-insert query will only begin once the dependencies for all these move tasks have been
+      met.
+      Advantages: If concurrency is enabled, the locks will only be released once the query has
+                  finished, so with this config enabled, the time when the table/partition is
+                  generated will be much closer to when the lock on it is released.
+      Disadvantages: If concurrency is not enabled, with this disabled, the tables/partitions which
+                     are produced by this query and finish earlier will be available for querying
+                     much earlier.  Since the locks are only released once the query finishes, this
+                     does not apply if concurrency is enabled.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.infer.bucket.sort</name>
+    <value>false</value>
+    <description>
+      If this is set, when writing partitions, the metadata will include the bucketing/sorting
+      properties with which the data was written if any (this will not overwrite the metadata
+      inherited from the table if the table is bucketed/sorted)
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.infer.bucket.sort.num.buckets.power.two</name>
+    <value>false</value>
+    <description>
+      If this is set, when setting the number of reducers for the map reduce task which writes the
+      final output files, it will choose a number which is a power of two, unless the user specifies
+      the number of reducers to use using mapred.reduce.tasks.  The number of reducers
+      may be set to a power of two, only to be followed by a merge task meaning preventing
+      anything from being inferred.
+      With hive.exec.infer.bucket.sort set to true:
+      Advantages:  If this is not set, the number of buckets for partitions will seem arbitrary,
+                   which means that the number of mappers used for optimized joins, for example, will
+                   be very low.  With this set, since the number of buckets used for any partition is
+                   a power of two, the number of mappers used for optimized joins will be the least
+                   number of buckets used by any partition being joined.
+      Disadvantages: This may mean a much larger or much smaller number of reducers being used in the
+                     final map reduce job, e.g. if a job was originally going to take 257 reducers,
+                     it will now take 512 reducers, similarly if the max number of reducers is 511,
+                     and a job was going to use this many, it will now use 256 reducers.
+    </description>
+  </property>
+  <property>
+    <name>hive.optimize.listbucketing</name>
+    <value>false</value>
+    <description>Enable list bucketing optimizer. Default value is false so that we disable it by default.</description>
+  </property>
+  <property>
+    <name>hive.server.read.socket.timeout</name>
+    <value>10s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Timeout for the HiveServer to close the connection if no response from the client. By default, 10 seconds.
+    </description>
+  </property>
+  <property>
+    <name>hive.server.tcp.keepalive</name>
+    <value>true</value>
+    <description>Whether to enable TCP keepalive for the Hive Server. Keepalive will prevent accumulation of half-open connections.</description>
+  </property>
+  <property>
+    <name>hive.decode.partition.name</name>
+    <value>false</value>
+    <description>Whether to show the unquoted partition names in query results.</description>
+  </property>
+  <property>
+    <name>hive.execution.engine</name>
+    <value>mr</value>
+    <description>
+      Expects one of [mr, tez, spark].
+      Chooses execution engine. Options are: mr (Map reduce, default), tez, spark. While MR
+      remains the default engine for historical reasons, it is itself a historical engine
+      and is deprecated in Hive 2 line. It may be removed without further warning.
+    </description>
+  </property>
+  <property>
+    <name>hive.execution.mode</name>
+    <value>container</value>
+    <description>
+      Expects one of [container, llap].
+      Chooses whether query fragments will run in container or in llap
+    </description>
+  </property>
+  <property>
+    <name>hive.jar.directory</name>
+    <value/>
+    <description>
+      This is the location hive in tez mode will look for to find a site wide 
+      installed hive instance.
+    </description>
+  </property>
+  <property>
+    <name>hive.user.install.directory</name>
+    <value>/user/</value>
+    <description>
+      If hive (in tez mode only) cannot find a usable hive jar in "hive.jar.directory", 
+      it will upload the hive jar to "hive.user.install.directory/user.name"
+      and use it to run queries.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.enabled</name>
+    <value>false</value>
+    <description>
+      This flag should be set to true to enable vectorized mode of query execution.
+      The default value is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.reduce.enabled</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable vectorized mode of the reduce-side of query execution.
+      The default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.reduce.groupby.enabled</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable vectorized mode of the reduce-side GROUP BY query execution.
+      The default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.mapjoin.native.enabled</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable native (i.e. non-pass through) vectorization
+      of queries using MapJoin.
+      The default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.mapjoin.native.multikey.only.enabled</name>
+    <value>false</value>
+    <description>
+      This flag should be set to true to restrict use of native vector map join hash tables to
+      the MultiKey in queries using MapJoin.
+      The default value is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.mapjoin.minmax.enabled</name>
+    <value>false</value>
+    <description>
+      This flag should be set to true to enable vector map join hash tables to
+      use max / max filtering for integer join queries using MapJoin.
+      The default value is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.mapjoin.overflow.repeated.threshold</name>
+    <value>-1</value>
+    <description>
+      The number of small table rows for a match in vector map join hash tables
+      where we use the repeated field optimization in overflow vectorized row batch for join queries using MapJoin.
+      A value of -1 means do use the join result optimization.  Otherwise, threshold value can be 0 to maximum integer.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.mapjoin.native.fast.hashtable.enabled</name>
+    <value>false</value>
+    <description>
+      This flag should be set to true to enable use of native fast vector map join hash tables in
+      queries using MapJoin.
+      The default value is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.groupby.checkinterval</name>
+    <value>100000</value>
+    <description>Number of entries added to the group by aggregation hash before a recomputation of average entry size is performed.</description>
+  </property>
+  <property>
+    <name>hive.vectorized.groupby.maxentries</name>
+    <value>1000000</value>
+    <description>
+      Max number of entries in the vector group by aggregation hashtables. 
+      Exceeding this will trigger a flush irrelevant of memory pressure condition.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.groupby.flush.percent</name>
+    <value>0.1</value>
+    <description>Percent of entries in the group by aggregation hash flushed when the memory threshold is exceeded.</description>
+  </property>
+  <property>
+    <name>hive.vectorized.execution.reducesink.new.enabled</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable the new vectorization
+      of queries using ReduceSink.
+      iThe default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.use.vectorized.input.format</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable vectorizing with vectorized input file format capable SerDe.
+      The default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.use.vector.serde.deserialize</name>
+    <value>false</value>
+    <description>
+      This flag should be set to true to enable vectorizing rows using vector deserialize.
+      The default value is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.vectorized.use.row.serde.deserialize</name>
+    <value>false</value>
+    <description>
+      This flag should be set to true to enable vectorizing using row deserialize.
+      The default value is false.
+    </description>
+  </property>
+  <property>
+    <name>hive.typecheck.on.insert</name>
+    <value>true</value>
+    <description>This property has been extended to control whether to check, convert, and normalize partition value to conform to its column type in partition operations including but not limited to insert, such as alter, describe etc.</description>
+  </property>
+  <property>
+    <name>hive.hadoop.classpath</name>
+    <value/>
+    <description>
+      For Windows OS, we need to pass HIVE_HADOOP_CLASSPATH Java parameter while starting HiveServer2 
+      using "-hiveconf hive.hadoop.classpath=%HIVE_LIB%".
+    </description>
+  </property>
+  <property>
+    <name>hive.rpc.query.plan</name>
+    <value>false</value>
+    <description>Whether to send the query plan via local resource or RPC</description>
+  </property>
+  <property>
+    <name>hive.compute.splits.in.am</name>
+    <value>true</value>
+    <description>Whether to generate the splits locally or in the AM (tez only)</description>
+  </property>
+  <property>
+    <name>hive.tez.input.generate.consistent.splits</name>
+    <value>true</value>
+    <description>Whether to generate consistent split locations when generating splits in the AM</description>
+  </property>
+  <property>
+    <name>hive.prewarm.enabled</name>
+    <value>false</value>
+    <description>Enables container prewarm for Tez/Spark (Hadoop 2 only)</description>
+  </property>
+  <property>
+    <name>hive.prewarm.numcontainers</name>
+    <value>10</value>
+    <description>Controls the number of containers to prewarm for Tez/Spark (Hadoop 2 only)</description>
+  </property>
+  <property>
+    <name>hive.stageid.rearrange</name>
+    <value>none</value>
+    <description>
+      Expects one of [none, idonly, traverse, execution].
+    </description>
+  </property>
+  <property>
+    <name>hive.explain.dependency.append.tasktype</name>
+    <value>false</value>
+    <description/>
+  </property>
+  <property>
+    <name>hive.counters.group.name</name>
+    <value>HIVE</value>
+    <description>The name of counter group for internal Hive variables (CREATED_FILE, FATAL_ERROR, etc.)</description>
+  </property>
+  <property>
+    <name>hive.support.quoted.identifiers</name>
+    <value>column</value>
+    <description>
+      Expects one of [none, column].
+      Whether to use quoted identifier. 'none' or 'column' can be used. 
+        none: default(past) behavior. Implies only alphaNumeric and underscore are valid characters in identifiers.
+        column: implies column names can contain any character.
+    </description>
+  </property>
+  <property>
+    <name>hive.support.sql11.reserved.keywords</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable support for SQL2011 reserved keywords.
+      The default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.support.special.characters.tablename</name>
+    <value>true</value>
+    <description>
+      This flag should be set to true to enable support for special characters in table names.
+      When it is set to false, only [a-zA-Z_0-9]+ are supported.
+      The only supported special character right now is '/'. This flag applies only to quoted table names.
+      The default value is true.
+    </description>
+  </property>
+  <property>
+    <name>hive.users.in.admin.role</name>
+    <value/>
+    <description>
+      Comma separated list of users who are in admin role for bootstrapping.
+      More users can be added in ADMIN role later.
+    </description>
+  </property>
+  <property>
+    <name>hive.compat</name>
+    <value>0.12</value>
+    <description>
+      Enable (configurable) deprecated behaviors by setting desired level of backward compatibility.
+      Setting to 0.12:
+        Maintains division behavior: int / int = double
+    </description>
+  </property>
+  <property>
+    <name>hive.convert.join.bucket.mapjoin.tez</name>
+    <value>false</value>
+    <description>
+      Whether joins can be automatically converted to bucket map joins in hive 
+      when tez is used as the execution engine.
+    </description>
+  </property>
+  <property>
+    <name>hive.exec.check.crossproducts</name>
+    <value>true</value>
+    <description>Check if a plan contains a Cross Product. If there is one, output a warning to the Session's console.</description>
+  </property>
+  <property>
+    <name>hive.localize.resource.wait.interval</name>
+    <value>5000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Time to wait for another thread to localize the same resource for hive-tez.
+    </description>
+  </property>
+  <property>
+    <name>hive.localize.resource.num.wait.attempts</name>
+    <value>5</value>
+    <description>The number of attempts waiting for localizing a resource in hive-tez.</description>
+  </property>
+  <property>
+    <name>hive.tez.auto.reducer.parallelism</name>
+    <value>false</value>
+    <description>
+      Turn on Tez' auto reducer parallelism feature. When enabled, Hive will still estimate data sizes
+      and set parallelism estimates. Tez will sample source vertices' output sizes and adjust the estimates at runtime as
+      necessary.
+    </description>
+  </property>
+  <property>
+    <name>hive.tez.max.partition.factor</name>
+    <value>2.0</value>
+    <description>When auto reducer parallelism is enabled this factor will be used to over-partition data in shuffle edges.</description>
+  </property>
+  <property>
+    <name>hive.tez.min.partition.factor</name>
+    <value>0.25</value>
+    <description>
+      When auto reducer parallelism is enabled this factor will be used to put a lower limit to the number
+      of reducers that tez specifies.
+    </description>
+  </property>
+  <property>
+    <name>hive.tez.bucket.pruning</name>
+    <value>false</value>
+    <description>
+      When pruning is enabled, filters on bucket columns will be processed by 
+      filtering the splits against a bitset of included buckets. This needs predicates 
+      produced by hive.optimize.ppd and hive.optimize.index.filters.
+    </description>
+  </property>
+  <property>
+    <name>hive.tez.bucket.pruning.compat</name>
+    <value>true</value>
+    <description>
+      When pruning is enabled, handle possibly broken inserts due to negative hashcodes.
+      This occasionally doubles the data scan cost, but is default enabled for safety
+    </description>
+  </property>
+  <property>
+    <name>hive.tez.dynamic.partition.pruning</name>
+    <value>true</value>
+    <description>
+      When dynamic pruning is enabled, joins on partition keys will be processed by sending
+      events from the processing vertices to the Tez application master. These events will be
+      used to prune unnecessary partitions.
+    </description>
+  </property>
+  <property>
+    <name>hive.tez.dynamic.partition.pruning.max.event.size</name>
+    <value>1048576</value>
+    <description>Maximum size of events sent by processors in dynamic pruning. If this size is crossed no pruning will take place.</description>
+  </property>
+  <property>
+    <name>hive.tez.dynamic.partition.pruning.max.data.size</name>
+    <value>104857600</value>
+    <description>Maximum total data size of events in dynamic pruning.</description>
+  </property>
+  <property>
+    <name>hive.tez.smb.number.waves</name>
+    <value>0.5</value>
+    <description>The number of waves in which to run the SMB join. Account for cluster being occupied. Ideally should be 1 wave.</description>
+  </property>
+  <property>
+    <name>hive.tez.exec.print.summary</name>
+    <value>false</value>
+    <description>Display breakdown of execution steps, for every query executed by the shell.</description>
+  </property>
+  <property>
+    <name>hive.tez.exec.inplace.progress</name>
+    <value>true</value>
+    <description>Updates tez job execution progress in-place in the terminal.</description>
+  </property>
+  <property>
+    <name>hive.tez.container.max.java.heap.fraction</name>
+    <value>0.8</value>
+    <description>This is to override the tez setting with the same name</description>
+  </property>
+  <property>
+    <name>hive.tez.task.scale.memory.reserve-fraction.min</name>
+    <value>0.3</value>
+    <description>This is to override the tez setting tez.task.scale.memory.reserve-fraction</description>
+  </property>
+  <property>
+    <name>hive.tez.task.scale.memory.reserve.fraction.max</name>
+    <value>0.5</value>
+    <description>The maximum fraction of JVM memory which Tez will reserve for the processor</description>
+  </property>
+  <property>
+    <name>hive.tez.task.scale.memory.reserve.fraction</name>
+    <value>-1.0</value>
+    <description>The customized fraction of JVM memory which Tez will reserve for the processor</description>
+  </property>
+  <property>
+    <name>hive.llap.io.enabled</name>
+    <value/>
+    <description>Whether the LLAP IO layer is enabled.</description>
+  </property>
+  <property>
+    <name>hive.llap.io.memory.mode</name>
+    <value>cache</value>
+    <description>
+      Expects one of [cache, none].
+      LLAP IO memory usage; 'cache' (the default) uses data and metadata cache with a
+      custom off-heap allocator, 'none' doesn't use either (this mode may result in
+      significant performance degradation)
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.allocator.alloc.min</name>
+    <value>16Kb</value>
+    <description>
+      Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb).
+      Minimum allocation possible from LLAP buddy allocator. Allocations below that are
+      padded to minimum allocation. For ORC, should generally be the same as the expected
+      compression buffer size, or next lowest power of 2. Must be a power of 2.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.allocator.alloc.max</name>
+    <value>16Mb</value>
+    <description>
+      Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb).
+      Maximum allocation possible from LLAP buddy allocator. For ORC, should be as large as
+      the largest expected ORC compression buffer size. Must be a power of 2.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.allocator.arena.count</name>
+    <value>8</value>
+    <description>
+      Arena count for LLAP low-level cache; cache will be allocated in the steps of
+      (size/arena_count) bytes. This size must be &lt;= 1Gb and &gt;= max allocation; if it is
+      not the case, an adjusted size will be used. Using powers of 2 is recommended.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.memory.size</name>
+    <value>1Gb</value>
+    <description>
+      Expects a byte size value with unit (blank for bytes, kb, mb, gb, tb, pb).
+      Maximum size for IO allocator or ORC low-level cache.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.allocator.direct</name>
+    <value>true</value>
+    <description>Whether ORC low-level cache should use direct allocation.</description>
+  </property>
+  <property>
+    <name>hive.llap.io.allocator.mmap</name>
+    <value>false</value>
+    <description>
+      Whether ORC low-level cache should use memory mapped allocation (direct I/O). 
+      This is recommended to be used along-side NVDIMM (DAX) or NVMe flash storage.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.allocator.mmap.path</name>
+    <value>/tmp</value>
+    <description>
+      Expects a writable directory on the local filesystem.
+      The directory location for mapping NVDIMM/NVMe flash storage into the ORC low-level cache.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.use.lrfu</name>
+    <value>true</value>
+    <description>Whether ORC low-level cache should use LRFU cache policy instead of default (FIFO).</description>
+  </property>
+  <property>
+    <name>hive.llap.io.lrfu.lambda</name>
+    <value>0.01</value>
+    <description>
+      Lambda for ORC low-level cache LRFU cache policy. Must be in [0, 1]. 0 makes LRFU
+      behave like LFU, 1 makes it behave like LRU, values in between balance accordingly.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.cache.allow.synthetic.fileid</name>
+    <value>false</value>
+    <description>
+      Whether LLAP cache should use synthetic file ID if real one is not available. Systems
+      like HDFS, Isilon, etc. provide a unique file/inode ID. On other FSes (e.g. local
+      FS), the cache would not work by default because LLAP is unable to uniquely track the
+      files; enabling this setting allows LLAP to generate file ID from the path, size and
+      modification time, which is almost certain to identify file uniquely. However, if you
+      use a FS without file IDs and rewrite files a lot (or are paranoid), you might want
+      to avoid this setting.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.orc.gap.cache</name>
+    <value>true</value>
+    <description>
+      Whether LLAP cache for ORC should remember gaps in ORC compression buffer read
+      estimates, to avoid re-reading the data that was read once and discarded because it
+      is unneeded. This is only necessary for ORC files written before HIVE-9660.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.use.fileid.path</name>
+    <value>true</value>
+    <description>
+      Whether LLAP should use fileId (inode)-based path to ensure better consistency for the
+      cases of file overwrites. This is supported on HDFS.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.orc.time.counters</name>
+    <value>true</value>
+    <description>Whether to enable time counters for LLAP IO layer (time spent in HDFS, etc.)</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.allow.uber</name>
+    <value>false</value>
+    <description>Whether or not to allow the planner to run vertices in the AM.</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.enforce.tree</name>
+    <value>true</value>
+    <description>Enforce that all parents are in llap, before considering vertex</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.enforce.vectorized</name>
+    <value>true</value>
+    <description>Enforce that inputs are vectorized, before considering vertex</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.enforce.stats</name>
+    <value>true</value>
+    <description>Enforce that col stats are available, before considering vertex</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.max.input.size</name>
+    <value>10737418240</value>
+    <description>Check input size, before considering vertex (-1 disables check)</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.max.output.size</name>
+    <value>1073741824</value>
+    <description>Check output size, before considering vertex (-1 disables check)</description>
+  </property>
+  <property>
+    <name>hive.llap.skip.compile.udf.check</name>
+    <value>false</value>
+    <description>
+      Whether to skip the compile-time check for non-built-in UDFs when deciding whether to
+      execute tasks in LLAP. Skipping the check allows executing UDFs from pre-localized
+      jars in LLAP; if the jars are not pre-localized, the UDFs will simply fail to load.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.allow.permanent.fns</name>
+    <value>true</value>
+    <description>Whether LLAP decider should allow permanent UDFs.</description>
+  </property>
+  <property>
+    <name>hive.llap.execution.mode</name>
+    <value>none</value>
+    <description>
+      Expects one of [auto, none, all, map].
+      Chooses whether query fragments will run in container or in llap
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.object.cache.enabled</name>
+    <value>true</value>
+    <description>Cache objects (plans, hashtables, etc) in llap</description>
+  </property>
+  <property>
+    <name>hive.llap.io.decoding.metrics.percentiles.intervals</name>
+    <value>30</value>
+    <description>
+      Comma-delimited set of integers denoting the desired rollover intervals (in seconds)
+      for percentile latency metrics on the LLAP daemon IO decoding time.
+      hive.llap.queue.metrics.percentiles.intervals
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.io.threadpool.size</name>
+    <value>10</value>
+    <description>Specify the number of threads to use for low-level IO thread pool.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.service.principal</name>
+    <value/>
+    <description>The name of the LLAP daemon's service principal.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.keytab.file</name>
+    <value/>
+    <description>The path to the Kerberos Keytab file containing the LLAP daemon's service principal.</description>
+  </property>
+  <property>
+    <name>hive.llap.zk.sm.principal</name>
+    <value/>
+    <description>The name of the principal to use to talk to ZooKeeper for ZooKeeper SecretManager.</description>
+  </property>
+  <property>
+    <name>hive.llap.zk.sm.keytab.file</name>
+    <value/>
+    <description>
+      The path to the Kerberos Keytab file containing the principal to use to talk to
+      ZooKeeper for ZooKeeper SecretManager.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.zk.sm.connectionString</name>
+    <value/>
+    <description>ZooKeeper connection string for ZooKeeper SecretManager.</description>
+  </property>
+  <property>
+    <name>hive.llap.zk.registry.user</name>
+    <value/>
+    <description>
+      In the LLAP ZooKeeper-based registry, specifies the username in the Zookeeper path.
+      This should be the hive user or whichever user is running the LLAP daemon.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.zk.registry.namespace</name>
+    <value/>
+    <description>
+      In the LLAP ZooKeeper-based registry, overrides the ZK path namespace. Note that
+      using this makes the path management (e.g. setting correct ACLs) your responsibility.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.acl</name>
+    <value>*</value>
+    <description>The ACL for LLAP daemon.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.acl.blocked</name>
+    <value/>
+    <description>The deny ACL for LLAP daemon.</description>
+  </property>
+  <property>
+    <name>hive.llap.management.acl</name>
+    <value>*</value>
+    <description>The ACL for LLAP daemon management.</description>
+  </property>
+  <property>
+    <name>hive.llap.management.acl.blocked</name>
+    <value/>
+    <description>The deny ACL for LLAP daemon management.</description>
+  </property>
+  <property>
+    <name>hive.llap.remote.token.requires.signing</name>
+    <value>true</value>
+    <description>
+      Expects one of [false, except_llap_owner, true].
+      Whether the token returned from LLAP management API should require fragment signing.
+      True by default; can be disabled to allow CLI to get tokens from LLAP in a secure
+      cluster by setting it to true or 'except_llap_owner' (the latter returns such tokens
+      to everyone except the user LLAP cluster is authenticating under).
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.delegation.token.lifetime</name>
+    <value>14d</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      LLAP delegation token lifetime, in seconds if specified without a unit.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.management.rpc.port</name>
+    <value>15004</value>
+    <description>RPC port for LLAP daemon management service.</description>
+  </property>
+  <property>
+    <name>hive.llap.auto.auth</name>
+    <value>false</value>
+    <description>Whether or not to set Hadoop configs to enable auth in LLAP web app.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.rpc.num.handlers</name>
+    <value>5</value>
+    <description>Number of RPC handlers for LLAP daemon.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.work.dirs</name>
+    <value/>
+    <description>
+      Working directories for the daemon. Needs to be set for a secure cluster, since LLAP may
+      not have access to the default YARN working directories. yarn.nodemanager.local-dirs is
+      used if this is not set
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.yarn.shuffle.port</name>
+    <value>15551</value>
+    <description>YARN shuffle port for LLAP-daemon-hosted shuffle.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.yarn.container.mb</name>
+    <value>-1</value>
+    <description>llap server yarn container size in MB. Used in LlapServiceDriver and package.py</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.queue.name</name>
+    <value/>
+    <description>Queue name within which the llap slider application will run. Used in LlapServiceDriver and package.py</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.container.id</name>
+    <value/>
+    <description>ContainerId of a running LlapDaemon. Used to publish to the registry</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.shuffle.dir.watcher.enabled</name>
+    <value>false</value>
+    <description>TODO doc</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.am.liveness.heartbeat.interval.ms</name>
+    <value>10000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Tez AM-LLAP heartbeat interval (milliseconds). This needs to be below the task timeout
+      interval, but otherwise as high as possible to avoid unnecessary traffic.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.am.liveness.connection.timeout.ms</name>
+    <value>10000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Amount of time to wait on connection failures to the AM from an LLAP daemon before
+      considering the AM to be dead.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.am.liveness.connection.sleep.between.retries.ms</name>
+    <value>2000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Sleep duration while waiting to retry connection failures to the AM from the daemon for
+      the general keep-alive thread (milliseconds).
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.scheduler.timeout.seconds</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Amount of time to wait before failing the query when there are no llap daemons running
+      (alive) in the cluster.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.num.executors</name>
+    <value>4</value>
+    <description>
+      Number of executors to use in LLAP daemon; essentially, the number of tasks that can be
+      executed in parallel.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.rpc.port</name>
+    <value>15001</value>
+    <description>The LLAP daemon RPC port.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.memory.per.instance.mb</name>
+    <value>4096</value>
+    <description>The total amount of memory to use for the executors inside LLAP (in megabytes).</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.vcpus.per.instance</name>
+    <value>4</value>
+    <description>The total number of vcpus to use for the executors inside LLAP.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.num.file.cleaner.threads</name>
+    <value>1</value>
+    <description>Number of file cleaner threads in LLAP.</description>
+  </property>
+  <property>
+    <name>hive.llap.file.cleanup.delay.seconds</name>
+    <value>300s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      How long to delay before cleaning up query files in LLAP (in seconds, for debugging).
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.service.hosts</name>
+    <value/>
+    <description>
+      Explicitly specified hosts to use for LLAP scheduling. Useful for testing. By default,
+      YARN registry is used.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.service.refresh.interval.sec</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      LLAP YARN registry service list refresh delay, in seconds.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.communicator.num.threads</name>
+    <value>10</value>
+    <description>Number of threads to use in LLAP task communicator in Tez AM.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.download.permanent.fns</name>
+    <value>false</value>
+    <description>Whether LLAP daemon should localize the resources for permanent UDFs.</description>
+  </property>
+  <property>
+    <name>hive.llap.task.scheduler.node.reenable.min.timeout.ms</name>
+    <value>200ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Minimum time after which a previously disabled node will be re-enabled for scheduling,
+      in milliseconds. This may be modified by an exponential back-off if failures persist.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.scheduler.node.reenable.max.timeout.ms</name>
+    <value>10000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Maximum time after which a previously disabled node will be re-enabled for scheduling,
+      in milliseconds. This may be modified by an exponential back-off if failures persist.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.scheduler.node.disable.backoff.factor</name>
+    <value>1.5</value>
+    <description>
+      Backoff factor on successive blacklists of a node due to some failures. Blacklist times
+      start at the min timeout and go up to the max timeout based on this backoff factor.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.scheduler.num.schedulable.tasks.per.node</name>
+    <value>0</value>
+    <description>
+      The number of tasks the AM TaskScheduler will try allocating per node. 0 indicates that
+      this should be picked up from the Registry. -1 indicates unlimited capacity; positive
+      values indicate a specific bound.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.scheduler.locality.delay</name>
+    <value>0ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      The time should be in between -1 msec (inclusive) and 9223372036854775807 msec (inclusive).
+      Amount of time to wait before allocating a request which contains location information, to a location other than the ones requested. Set to -1 for an infinite delay, 0for no delay.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.task.preemption.metrics.intervals</name>
+    <value>30,60,300</value>
+    <description>
+      Comma-delimited set of integers denoting the desired rollover intervals (in seconds)
+       for percentile latency metrics. Used by LLAP daemon task scheduler metrics for
+       time taken to kill task (due to pre-emption) and useful time wasted by the task that
+       is about to be preempted.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.task.scheduler.wait.queue.size</name>
+    <value>10</value>
+    <description>LLAP scheduler maximum queue size.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.wait.queue.comparator.class.name</name>
+    <value>org.apache.hadoop.hive.llap.daemon.impl.comparator.ShortestJobFirstComparator</value>
+    <description>
+      The priority comparator to use for LLAP scheduler prioroty queue. The built-in options
+      are org.apache.hadoop.hive.llap.daemon.impl.comparator.ShortestJobFirstComparator and
+      .....FirstInFirstOutComparator
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.task.scheduler.enable.preemption</name>
+    <value>true</value>
+    <description>
+      Whether non-finishable running tasks (e.g. a reducer waiting for inputs) should be
+      preempted by finishable tasks inside LLAP scheduler.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.communicator.connection.timeout.ms</name>
+    <value>16000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Connection timeout (in milliseconds) before a failure to an LLAP daemon from Tez AM.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.task.communicator.connection.sleep.between.retries.ms</name>
+    <value>2000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Sleep duration (in milliseconds) to wait before retrying on error when obtaining a
+      connection to LLAP daemon from Tez AM.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.web.port</name>
+    <value>15002</value>
+    <description>LLAP daemon web UI port.</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.web.ssl</name>
+    <value>false</value>
+    <description>Whether LLAP daemon web UI should use SSL.</description>
+  </property>
+  <property>
+    <name>hive.llap.client.consistent.splits</name>
+    <value>false</value>
+    <description>Whether to setup split locations to match nodes on which llap daemons are running, instead of using the locations provided by the split itself</description>
+  </property>
+  <property>
+    <name>hive.llap.validate.acls</name>
+    <value>true</value>
+    <description>
+      Whether LLAP should reject permissive ACLs in some cases (e.g. its own management
+      protocol or ZK paths), similar to how ssh refuses a key with bad access permissions.
+    </description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.output.service.port</name>
+    <value>15003</value>
+    <description>LLAP daemon output service port</description>
+  </property>
+  <property>
+    <name>hive.llap.daemon.output.service.send.buffer.size</name>
+    <value>131072</value>
+    <description>Send buffer size to be used by LLAP daemon output service</description>
+  </property>
+  <property>
+    <name>hive.llap.enable.grace.join.in.llap</name>
+    <value>false</value>
+    <description>Override if grace join should be allowed to run in llap.</description>
+  </property>
+  <property>
+    <name>hive.spark.client.future.timeout</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Timeout for requests from Hive client to remote Spark driver.
+    </description>
+  </property>
+  <property>
+    <name>hive.spark.job.monitor.timeout</name>
+    <value>60s</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified.
+      Timeout for job monitor to get Spark job state.
+    </description>
+  </property>
+  <property>
+    <name>hive.spark.client.connect.timeout</name>
+    <value>1000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Timeout for remote Spark driver in connecting back to Hive client.
+    </description>
+  </property>
+  <property>
+    <name>hive.spark.client.server.connect.timeout</name>
+    <value>90000ms</value>
+    <description>
+      Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified.
+      Timeout for handshake between Hive client and remote Spark driver.  Checked by both processes.
+    </description>
+  </property>
+  <property>
+    <name>hive.spark.client.secret.bits</name>
+    <value>256</value>
+    <description>Number of bits of randomness in the generated secret for communication between Hive client and remote Spark driver. Rounded down to the nearest multiple of 8.</description>
+  </property>
+  <property>
+    <name>hive.spark.client.rpc.threads</name>
+    <value>8</value>
+    <description>Maximum number of threads for remote Spark driver's RPC event loop.</description>
+  </property>
+  <property>
+    <name>hive.spark.client.rpc.max.size</name>
+    <value>52428800</value>
+    <description>Maximum message size in bytes for communication between Hive client and remote Spark driver. Default is 50MB.</description>
+  </property>
+  <property>
+    <name>hive.spark.client.channel.log.level</name>
+    <value/>
+    <description>Channel logging level for remote Spark driver.  One of {DEBUG, ERROR, INFO, TRACE, WARN}.</description>
+  </property>
+  <property>
+    <name>hive.spark.client.rpc.sasl.mechanisms</name>
+    <value>DIGEST-MD5</value>
+    <description>Name of the SASL mechanism to use for authentication.</description>
+  </property>
+  <property>
+    <name>hive.spark.client.rpc.server.address</name>
+    <value/>
+    <description>The server address of HiverServer2 host to be used for communication between Hive client and remote Spark driver. Default is empty, which means the address will be determined in the same way as for hive.server2.thrift.bind.host.This is only necessary if the host has mutiple network addresses and if a different network address other than hive.server2.thrift.bind.host is to be used.</description>
+  </property>
+  <property>
+    <name>hive.spark.dynamic.partition.pruning</name>
+    <value>false</value>
+    <description>
+      When dynamic pruning is enabled, joins on partition keys will be processed by writing
+      to a temporary HDFS file, and read later for removing unnecessary partitions.
+    </description>
+  </property>
+  <property>
+    <name>hive.spark.dynamic.partition.pruning.max.data.size</name>
+    <value>104857600</value>
+    <description>Maximum total data size in dynamic pruning.</description>
+  </property>
+  <property>
+    <name>hive.reorder.nway.joins</name>
+    <value>true</value>
+    <description>Runs reordering of tables within single n-way join (i.e.: picks streamtable)</description>
+  </property>
+  <property>
+    <name>hive.log.every.n.records</name>
+    <value>0</value>
+    <description>
+      Expects value bigger than 0.
+      If value is greater than 0 logs in fixed intervals of size n rather than exponentially.
+    </description>
+  </property>
+  <property>
+    <name>hive.msck.path.validation</name>
+    <value>throw</value>
+    <description>
+      Expects one of [throw, skip, ignore].
+      The approach msck should take with HDFS directories that are partition-like but contain unsupported characters. 'throw' (an exception) is the default; 'skip' will skip the invalid directories and still repair the others; 'ignore' will skip the validation (legacy behavior, causes bugs in many cases)
+    </description>
+  </property>
+  <property>
+    <name>hive.server2.llap.concurrent.queries</name>
+    <value>-1</value>
+    <description>The number of queries allowed in parallel via llap. Negative number implies 'infinite'.</description>
+  </property>
+  <property>
+    <name>hive.tez.enable.memory.manager</name>
+    <value>true</value>
+    <description>Enable memory manager for tez</description>
+  </property>
+  <property>
+    <name>hive.hash.table.inflation.factor</name>
+    <value>2.0</value>
+    <description>Expected inflation factor between disk/in memory representation of hash tables</description>
+  </property>
+  <property>
+    <name>hive.log.trace.id</name>
+    <value/>
+    <description>Log tracing id that can be used by upstream clients for tracking respective logs. Truncated to 64 characters. Defaults to use auto-generated session id.</description>
+  </property>
+  <property>
+    <name>hive.conf.restricted.list</name>
+    <value>hive.security.authenticator.manager,hive.security.authorization.manager,hive.users.in.admin.role,hive.server2.xsrf.filter.enabled</value>
+    <description>Comma separated list of configuration options which are immutable at runtime</description>
+  </property>
+  <property>
+    <name>hive.conf.hidden.list</name>
+    <value>javax.jdo.option.ConnectionPassword,hive.server2.keystore.password</value>
+    <description>Comma separated list of configuration options which should not be read by normal user like passwords</description>
+  </property>
+  <property>
+    <name>hive.conf.internal.variable.list</name>
+    <value>hive.added.files.path,hive.added.jars.path,hive.added.archives.path</value>
+    <description>Comma separated list of variables which are used internally and should not be configurable.</description>
+  </property>
+</configuration>

container/conf/java/hive/ivysettings.xml

@@ -0,0 +1,45 @@
+<!--
+   Licensed to the Apache Software Foundation (ASF) under one or more
+   contributor license agreements.  See the NOTICE file distributed with
+   this work for additional information regarding copyright ownership.
+   The ASF licenses this file to You under the Apache License, Version 2.0
+   (the "License"); you may not use this file except in compliance with
+   the License.  You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+   -->
+
+<!--This file is used by grapes to download dependencies from a maven repository.
+    This is just a template and can be edited to add more repositories.
+-->
+
+<ivysettings>
+  <!--name of the defaultResolver should always be 'downloadGrapes'. -->
+  <settings defaultResolver="downloadGrapes"/>
+  <!-- Only set maven.local.repository if not already set -->
+  <property name="maven.local.repository" value="${user.home}/.m2/repository" override="false" />
+  <property name="m2-pattern"
+            value="file:${maven.local.repository}/[organisation]/[module]/[revision]/[module]-[revision](-[classifier]).[ext]"
+            override="false"/>
+  <resolvers>
+    <!-- more resolvers can be added here -->
+    <chain name="downloadGrapes">
+      <!-- This resolver uses ibiblio to find artifacts, compatible with maven2 repository -->
+      <ibiblio name="central" m2compatible="true"/>
+      <url name="local-maven2" m2compatible="true">
+        <artifact pattern="${m2-pattern}"/>
+      </url>
+      <!-- File resolver to add jars from the local system. -->
+      <filesystem name="test" checkmodified="true">
+        <artifact pattern="${test.tmp.dir}/[module]-[revision](-[classifier]).jar"/>
+      </filesystem>
+
+    </chain>
+  </resolvers>
+</ivysettings>

container/conf/java/hive/llap-cli-log4j2.properties

@@ -0,0 +1,74 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+status = WARN
+name = LlapCliLog4j2
+packages = org.apache.hadoop.hive.ql.log
+
+# list of properties
+property.hive.log.level = INFO
+property.hive.root.logger = console
+property.hive.log.dir = ${sys:java.io.tmpdir}/${sys:user.name}
+property.hive.log.file = llap-cli.log
+
+# list of all appenders
+appenders = console, DRFA
+
+# console appender
+appender.console.type = Console
+appender.console.name = console
+appender.console.target = SYSTEM_ERR
+appender.console.layout.type = PatternLayout
+appender.console.layout.pattern = %p %c{2}: %m%n
+
+# daily rolling file appender
+appender.DRFA.type = RollingRandomAccessFile
+appender.DRFA.name = DRFA
+appender.DRFA.fileName = ${sys:hive.log.dir}/${sys:hive.log.file}
+# Use %pid in the filePattern to append <process-id>@<host-name> to the filename if you want separate log files for different CLI session
+appender.DRFA.filePattern = ${sys:hive.log.dir}/${sys:hive.log.file}.%d{yyyy-MM-dd}
+appender.DRFA.layout.type = PatternLayout
+appender.DRFA.layout.pattern = %d{ISO8601} %5p [%t] %c{2}: %m%n
+appender.DRFA.policies.type = Policies
+appender.DRFA.policies.time.type = TimeBasedTriggeringPolicy
+appender.DRFA.policies.time.interval = 1
+appender.DRFA.policies.time.modulate = true
+appender.DRFA.strategy.type = DefaultRolloverStrategy
+appender.DRFA.strategy.max = 30
+
+# list of all loggers
+loggers = ZooKeeper, DataNucleus, Datastore, JPOX, HadoopConf
+
+logger.ZooKeeper.name = org.apache.zookeeper
+logger.ZooKeeper.level = WARN
+
+logger.DataNucleus.name = DataNucleus
+logger.DataNucleus.level = ERROR
+
+logger.Datastore.name = Datastore
+logger.Datastore.level = ERROR
+
+logger.JPOX.name = JPOX
+logger.JPOX.level = ERROR
+
+logger.HadoopConf.name = org.apache.hadoop.conf.Configuration
+logger.HadoopConf.level = ERROR
+
+# root logger
+rootLogger.level = ${sys:hive.log.level}
+rootLogger.appenderRefs = root, DRFA
+rootLogger.appenderRef.root.ref = ${sys:hive.root.logger}
+rootLogger.appenderRef.DRFA.ref = DRFA

container/conf/java/hive/llap-daemon-log4j2.properties

@@ -0,0 +1,108 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+status = INFO
+name = LlapDaemonLog4j2
+packages = org.apache.hadoop.hive.ql.log
+
+# list of properties
+property.llap.daemon.log.level = INFO
+property.llap.daemon.root.logger = console
+property.llap.daemon.log.dir = .
+property.llap.daemon.log.file = llapdaemon.log
+property.llap.daemon.historylog.file = llapdaemon_history.log
+property.llap.daemon.log.maxfilesize = 256MB
+property.llap.daemon.log.maxbackupindex = 20
+
+# list of all appenders
+appenders = console, RFA, HISTORYAPPENDER
+
+# console appender
+appender.console.type = Console
+appender.console.name = console
+appender.console.target = SYSTEM_ERR
+appender.console.layout.type = PatternLayout
+appender.console.layout.pattern = %d{ISO8601} %5p [%t%x] %c{2}: %m%n
+
+# rolling file appender
+appender.RFA.type = RollingRandomAccessFile
+appender.RFA.name = RFA
+appender.RFA.fileName = ${sys:llap.daemon.log.dir}/${sys:llap.daemon.log.file}
+appender.RFA.filePattern = ${sys:llap.daemon.log.dir}/${sys:llap.daemon.log.file}_%i
+appender.RFA.layout.type = PatternLayout
+appender.RFA.layout.pattern = %d{ISO8601} %5p [%t%x] %c{2}: %m%n
+appender.RFA.policies.type = Policies
+appender.RFA.policies.size.type = SizeBasedTriggeringPolicy
+appender.RFA.policies.size.size = ${sys:llap.daemon.log.maxfilesize}
+appender.RFA.strategy.type = DefaultRolloverStrategy
+appender.RFA.strategy.max = ${sys:llap.daemon.log.maxbackupindex}
+
+# history file appender
+appender.HISTORYAPPENDER.type = RollingRandomAccessFile
+appender.HISTORYAPPENDER.name = HISTORYAPPENDER
+appender.HISTORYAPPENDER.fileName = ${sys:llap.daemon.log.dir}/${sys:llap.daemon.historylog.file}
+appender.HISTORYAPPENDER.filePattern = ${sys:llap.daemon.log.dir}/${sys:llap.daemon.historylog.file}_%i
+appender.HISTORYAPPENDER.layout.type = PatternLayout
+appender.HISTORYAPPENDER.layout.pattern = %m%n
+appender.HISTORYAPPENDER.policies.type = Policies
+appender.HISTORYAPPENDER.policies.size.type = SizeBasedTriggeringPolicy
+appender.HISTORYAPPENDER.policies.size.size = ${sys:llap.daemon.log.maxfilesize}
+appender.HISTORYAPPENDER.strategy.type = DefaultRolloverStrategy
+appender.HISTORYAPPENDER.strategy.max = ${sys:llap.daemon.log.maxbackupindex}
+
+# list of all loggers
+loggers = EncodedReader, NIOServerCnxn, ClientCnxnSocketNIO, DataNucleus, Datastore, JPOX, HistoryLogger, LlapIoImpl, LlapIoOrc, LlapIoCache, LlapIoLocking
+
+logger.EncodedReader.name = org.apache.hadoop.hive.ql.io.orc.encoded.EncodedReaderImpl
+logger.EncodedReader.level = INFO
+
+logger.LlapIoImpl.name = LlapIoImpl
+logger.LlapIoImpl.level = INFO
+
+logger.LlapIoOrc.name = LlapIoOrc
+logger.LlapIoOrc.level = WARN
+
+logger.LlapIoCache.name = LlapIoCache
+logger.LlapIoCache.level = WARN
+
+logger.LlapIoLocking.name = LlapIoLocking
+logger.LlapIoLocking.level = WARN
+
+logger.NIOServerCnxn.name = org.apache.zookeeper.server.NIOServerCnxn
+logger.NIOServerCnxn.level = WARN
+
+logger.ClientCnxnSocketNIO.name = org.apache.zookeeper.ClientCnxnSocketNIO
+logger.ClientCnxnSocketNIO.level = WARN
+
+logger.DataNucleus.name = DataNucleus
+logger.DataNucleus.level = ERROR
+
+logger.Datastore.name = Datastore
+logger.Datastore.level = ERROR
+
+logger.JPOX.name = JPOX
+logger.JPOX.level = ERROR
+
+logger.HistoryLogger.name = org.apache.hadoop.hive.llap.daemon.HistoryLogger
+logger.HistoryLogger.level = INFO
+logger.HistoryLogger.additivity = false
+logger.HistoryLogger.appenderRefs = HistoryAppender
+logger.HistoryLogger.appenderRef.HistoryAppender.ref = HISTORYAPPENDER
+
+# root logger
+rootLogger.level = ${sys:llap.daemon.log.level}
+rootLogger.appenderRefs = root
+rootLogger.appenderRef.root.ref = ${sys:llap.daemon.root.logger}

container/conf/java/hive/parquet-logging.properties

@@ -0,0 +1,70 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# Properties file which configures the operation of the JDK
+# logging facility.
+
+# The system will look for this config file, first using
+# a System property specified at startup:
+#
+# >java -Djava.util.logging.config.file=myLoggingConfigFilePath
+#
+# If this property is not specified, then the config file is
+# retrieved from its default location at:
+#
+# JDK_HOME/jre/lib/logging.properties
+
+# Global logging properties.
+# ------------------------------------------
+# The set of handlers to be loaded upon startup.
+# Comma-separated list of class names.
+# (? LogManager docs say no comma here, but JDK example has comma.)
+# handlers=java.util.logging.ConsoleHandler
+org.apache.parquet.handlers= java.util.logging.FileHandler
+
+# Default global logging level.
+# Loggers and Handlers may override this level
+.level=INFO
+
+# Handlers
+# -----------------------------------------
+
+# --- ConsoleHandler ---
+# Override of global logging level
+java.util.logging.ConsoleHandler.level=INFO
+java.util.logging.ConsoleHandler.formatter=java.util.logging.SimpleFormatter
+java.util.logging.SimpleFormatter.format=[%1$tc] %4$s: %2$s - %5$s %6$s%n
+
+# --- FileHandler ---
+# Override of global logging level
+java.util.logging.FileHandler.level=ALL
+
+# Naming style for the output file:
+# (The output file is placed in the system temporary directory.
+# %u is used to provide unique identifier for the file.
+# For more information refer
+# https://docs.oracle.com/javase/7/docs/api/java/util/logging/FileHandler.html)
+java.util.logging.FileHandler.pattern=%t/parquet-%u.log
+
+# Limiting size of output file in bytes:
+java.util.logging.FileHandler.limit=50000000
+
+# Number of output files to cycle through, by appending an
+# integer to the base file name:
+java.util.logging.FileHandler.count=1
+
+# Style of output (Simple or XML):
+java.util.logging.FileHandler.formatter=java.util.logging.SimpleFormatter

container/conf/java/jupyter/jupyter_notebook_config.py

@@ -0,0 +1,605 @@
+# Configuration file for jupyter-notebook.
+
+#------------------------------------------------------------------------------
+# Application(SingletonConfigurable) configuration
+#------------------------------------------------------------------------------
+
+## This is an application.
+
+## The date format used by logging formatters for %(asctime)s
+#c.Application.log_datefmt = '%Y-%m-%d %H:%M:%S'
+
+## The Logging format template
+#c.Application.log_format = '[%(name)s]%(highlevel)s %(message)s'
+
+## Set the log level by value or name.
+#c.Application.log_level = 30
+
+#------------------------------------------------------------------------------
+# JupyterApp(Application) configuration
+#------------------------------------------------------------------------------
+
+## Base class for Jupyter applications
+
+## Answer yes to any prompts.
+#c.JupyterApp.answer_yes = False
+
+## Full path of a config file.
+#c.JupyterApp.config_file = u''
+
+## Specify a config file to load.
+#c.JupyterApp.config_file_name = u''
+
+## Generate default config file.
+#c.JupyterApp.generate_config = False
+
+#------------------------------------------------------------------------------
+# NotebookApp(JupyterApp) configuration
+#------------------------------------------------------------------------------
+
+## Set the Access-Control-Allow-Credentials: true header
+#c.NotebookApp.allow_credentials = False
+
+## Set the Access-Control-Allow-Origin header
+#  
+#  Use '*' to allow any origin to access your server.
+#  
+#  Takes precedence over allow_origin_pat.
+#c.NotebookApp.allow_origin = ''
+
+## Use a regular expression for the Access-Control-Allow-Origin header
+#  
+#  Requests from an origin matching the expression will get replies with:
+#  
+#      Access-Control-Allow-Origin: origin
+#  
+#  where `origin` is the origin of the request.
+#  
+#  Ignored if allow_origin is set.
+#c.NotebookApp.allow_origin_pat = ''
+
+## Whether to allow the user to run the notebook as root.
+#c.NotebookApp.allow_root = False
+
+## DEPRECATED use base_url
+#c.NotebookApp.base_project_url = '/'
+
+## The base URL for the notebook server.
+#  
+#  Leading and trailing slashes can be omitted, and will automatically be added.
+#c.NotebookApp.base_url = '/'
+
+## Specify what command to use to invoke a web browser when opening the notebook.
+#  If not specified, the default browser will be determined by the `webbrowser`
+#  standard library module, which allows setting of the BROWSER environment
+#  variable to override it.
+#c.NotebookApp.browser = u''
+
+## The full path to an SSL/TLS certificate file.
+#c.NotebookApp.certfile = u''
+
+## The full path to a certificate authority certificate for SSL/TLS client
+#  authentication.
+#c.NotebookApp.client_ca = u''
+
+## The config manager class to use
+#c.NotebookApp.config_manager_class = 'notebook.services.config.manager.ConfigManager'
+
+## The notebook manager class to use.
+#c.NotebookApp.contents_manager_class = 'notebook.services.contents.largefilemanager.LargeFileManager'
+
+## Extra keyword arguments to pass to `set_secure_cookie`. See tornado's
+#  set_secure_cookie docs for details.
+#c.NotebookApp.cookie_options = {}
+
+## The random bytes used to secure cookies. By default this is a new random
+#  number every time you start the Notebook. Set it to a value in a config file
+#  to enable logins to persist across server sessions.
+#  
+#  Note: Cookie secrets should be kept private, do not share config files with
+#  cookie_secret stored in plaintext (you can read the value from a file).
+#c.NotebookApp.cookie_secret = ''
+
+## The file where the cookie secret is stored.
+#c.NotebookApp.cookie_secret_file = u''
+
+## The default URL to redirect to from `/`
+#c.NotebookApp.default_url = '/tree'
+
+## Disable cross-site-request-forgery protection
+#  
+#  Jupyter notebook 4.3.1 introduces protection from cross-site request
+#  forgeries, requiring API requests to either:
+#  
+#  - originate from pages served by this server (validated with XSRF cookie and
+#  token), or - authenticate with a token
+#  
+#  Some anonymous compute resources still desire the ability to run code,
+#  completely without authentication. These services can disable all
+#  authentication and security checks, with the full knowledge of what that
+#  implies.
+#c.NotebookApp.disable_check_xsrf = False
+
+## Whether to enable MathJax for typesetting math/TeX
+#  
+#  MathJax is the javascript library Jupyter uses to render math/LaTeX. It is
+#  very large, so you may want to disable it if you have a slow internet
+#  connection, or for offline use of the notebook.
+#  
+#  When disabled, equations etc. will appear as their untransformed TeX source.
+#c.NotebookApp.enable_mathjax = True
+
+## extra paths to look for Javascript notebook extensions
+#c.NotebookApp.extra_nbextensions_path = []
+
+## Extra paths to search for serving static files.
+#  
+#  This allows adding javascript/css to be available from the notebook server
+#  machine, or overriding individual files in the IPython
+#c.NotebookApp.extra_static_paths = []
+
+## Extra paths to search for serving jinja templates.
+#  
+#  Can be used to override templates from notebook.templates.
+#c.NotebookApp.extra_template_paths = []
+
+## 
+#c.NotebookApp.file_to_run = ''
+
+## Deprecated: Use minified JS file or not, mainly use during dev to avoid JS
+#  recompilation
+#c.NotebookApp.ignore_minified_js = False
+
+## (bytes/sec) Maximum rate at which messages can be sent on iopub before they
+#  are limited.
+#c.NotebookApp.iopub_data_rate_limit = 1000000
+
+## (msgs/sec) Maximum rate at which messages can be sent on iopub before they are
+#  limited.
+#c.NotebookApp.iopub_msg_rate_limit = 1000
+
+## The IP address the notebook server will listen on.
+c.NotebookApp.ip = '*'
+
+## Supply extra arguments that will be passed to Jinja environment.
+#c.NotebookApp.jinja_environment_options = {}
+
+## Extra variables to supply to jinja templates when rendering.
+#c.NotebookApp.jinja_template_vars = {}
+
+## The kernel manager class to use.
+#c.NotebookApp.kernel_manager_class = 'notebook.services.kernels.kernelmanager.MappingKernelManager'
+
+## The kernel spec manager class to use. Should be a subclass of
+#  `jupyter_client.kernelspec.KernelSpecManager`.
+#  
+#  The Api of KernelSpecManager is provisional and might change without warning
+#  between this version of Jupyter and the next stable one.
+#c.NotebookApp.kernel_spec_manager_class = 'jupyter_client.kernelspec.KernelSpecManager'
+
+## The full path to a private key file for usage with SSL/TLS.
+#c.NotebookApp.keyfile = u''
+
+## The login handler class to use.
+#c.NotebookApp.login_handler_class = 'notebook.auth.login.LoginHandler'
+
+## The logout handler class to use.
+#c.NotebookApp.logout_handler_class = 'notebook.auth.logout.LogoutHandler'
+
+## The MathJax.js configuration file that is to be used.
+#c.NotebookApp.mathjax_config = 'TeX-AMS-MML_HTMLorMML-full,Safe'
+
+## A custom url for MathJax.js. Should be in the form of a case-sensitive url to
+#  MathJax, for example:  /static/components/MathJax/MathJax.js
+#c.NotebookApp.mathjax_url = ''
+
+## Dict of Python modules to load as notebook server extensions.Entry values can
+#  be used to enable and disable the loading ofthe extensions. The extensions
+#  will be loaded in alphabetical order.
+#c.NotebookApp.nbserver_extensions = {}
+
+## The directory to use for notebooks and kernels.
+#c.NotebookApp.notebook_dir = u''
+
+## Whether to open in a browser after starting. The specific browser used is
+#  platform dependent and determined by the python standard library `webbrowser`
+#  module, unless it is overridden using the --browser (NotebookApp.browser)
+#  configuration option.
+c.NotebookApp.open_browser = False
+
+## Hashed password to use for web authentication.
+#  
+#  To generate, type in a python/IPython shell:
+#  
+#    from notebook.auth import passwd; passwd()
+#  
+#  The string should be of the form type:salt:hashed-password.
+c.NotebookApp.password = u'sha1:541752f910ba:24d697c59553365469ca804b54127458aa35b755'
+
+## Forces users to use a password for the Notebook server. This is useful in a
+#  multi user environment, for instance when everybody in the LAN can access each
+#  other's machine though ssh.
+#  
+#  In such a case, server the notebook server on localhost is not secure since
+#  any user can connect to the notebook server via ssh.
+#c.NotebookApp.password_required = False
+
+## The port the notebook server will listen on.
+c.NotebookApp.port = 8888
+
+## The number of additional ports to try if the specified port is not available.
+#c.NotebookApp.port_retries = 50
+
+## DISABLED: use %pylab or %matplotlib in the notebook to enable matplotlib.
+c.NotebookApp.pylab = 'inline'
+
+## (sec) Time window used to  check the message and data rate limits.
+#c.NotebookApp.rate_limit_window = 3
+
+## Reraise exceptions encountered loading server extensions?
+#c.NotebookApp.reraise_server_extension_failures = False
+
+## DEPRECATED use the nbserver_extensions dict instead
+#c.NotebookApp.server_extensions = []
+
+## The session manager class to use.
+#c.NotebookApp.session_manager_class = 'notebook.services.sessions.sessionmanager.SessionManager'
+
+## Supply SSL options for the tornado HTTPServer. See the tornado docs for
+#  details.
+#c.NotebookApp.ssl_options = {}
+
+## Supply overrides for terminado. Currently only supports "shell_command".
+#c.NotebookApp.terminado_settings = {}
+
+## Token used for authenticating first-time connections to the server.
+#  
+#  When no password is enabled, the default is to generate a new, random token.
+#  
+#  Setting to an empty string disables authentication altogether, which is NOT
+#  RECOMMENDED.
+#c.NotebookApp.token = '<generated>'
+
+## Supply overrides for the tornado.web.Application that the Jupyter notebook
+#  uses.
+#c.NotebookApp.tornado_settings = {}
+
+## Whether to trust or not X-Scheme/X-Forwarded-Proto and X-Real-Ip/X-Forwarded-
+#  For headerssent by the upstream reverse proxy. Necessary if the proxy handles
+#  SSL
+#c.NotebookApp.trust_xheaders = False
+
+## DEPRECATED, use tornado_settings
+#c.NotebookApp.webapp_settings = {}
+
+## The base URL for websockets, if it differs from the HTTP server (hint: it
+#  almost certainly doesn't).
+#  
+#  Should be in the form of an HTTP origin: ws[s]://hostname[:port]
+#c.NotebookApp.websocket_url = ''
+
+#------------------------------------------------------------------------------
+# ConnectionFileMixin(LoggingConfigurable) configuration
+#------------------------------------------------------------------------------
+
+## Mixin for configurable classes that work with connection files
+
+## JSON file in which to store connection info [default: kernel-<pid>.json]
+#  
+#  This file will contain the IP, ports, and authentication key needed to connect
+#  clients to this kernel. By default, this file will be created in the security
+#  dir of the current profile, but can be specified by absolute path.
+#c.ConnectionFileMixin.connection_file = ''
+
+## set the control (ROUTER) port [default: random]
+#c.ConnectionFileMixin.control_port = 0
+
+## set the heartbeat port [default: random]
+#c.ConnectionFileMixin.hb_port = 0
+
+## set the iopub (PUB) port [default: random]
+#c.ConnectionFileMixin.iopub_port = 0
+
+## Set the kernel's IP address [default localhost]. If the IP address is
+#  something other than localhost, then Consoles on other machines will be able
+#  to connect to the Kernel, so be careful!
+#c.ConnectionFileMixin.ip = u''
+
+## set the shell (ROUTER) port [default: random]
+#c.ConnectionFileMixin.shell_port = 0
+
+## set the stdin (ROUTER) port [default: random]
+#c.ConnectionFileMixin.stdin_port = 0
+
+## 
+#c.ConnectionFileMixin.transport = 'tcp'
+
+#------------------------------------------------------------------------------
+# KernelManager(ConnectionFileMixin) configuration
+#------------------------------------------------------------------------------
+
+## Manages a single kernel in a subprocess on this host.
+#  
+#  This version starts kernels with Popen.
+
+## Should we autorestart the kernel if it dies.
+#c.KernelManager.autorestart = True
+
+## DEPRECATED: Use kernel_name instead.
+#  
+#  The Popen Command to launch the kernel. Override this if you have a custom
+#  kernel. If kernel_cmd is specified in a configuration file, Jupyter does not
+#  pass any arguments to the kernel, because it cannot make any assumptions about
+#  the arguments that the kernel understands. In particular, this means that the
+#  kernel does not receive the option --debug if it given on the Jupyter command
+#  line.
+#c.KernelManager.kernel_cmd = []
+
+## Time to wait for a kernel to terminate before killing it, in seconds.
+#c.KernelManager.shutdown_wait_time = 5.0
+
+#------------------------------------------------------------------------------
+# Session(Configurable) configuration
+#------------------------------------------------------------------------------
+
+## Object for handling serialization and sending of messages.
+#  
+#  The Session object handles building messages and sending them with ZMQ sockets
+#  or ZMQStream objects.  Objects can communicate with each other over the
+#  network via Session objects, and only need to work with the dict-based IPython
+#  message spec. The Session will handle serialization/deserialization, security,
+#  and metadata.
+#  
+#  Sessions support configurable serialization via packer/unpacker traits, and
+#  signing with HMAC digests via the key/keyfile traits.
+#  
+#  Parameters ----------
+#  
+#  debug : bool
+#      whether to trigger extra debugging statements
+#  packer/unpacker : str : 'json', 'pickle' or import_string
+#      importstrings for methods to serialize message parts.  If just
+#      'json' or 'pickle', predefined JSON and pickle packers will be used.
+#      Otherwise, the entire importstring must be used.
+#  
+#      The functions must accept at least valid JSON input, and output *bytes*.
+#  
+#      For example, to use msgpack:
+#      packer = 'msgpack.packb', unpacker='msgpack.unpackb'
+#  pack/unpack : callables
+#      You can also set the pack/unpack callables for serialization directly.
+#  session : bytes
+#      the ID of this Session object.  The default is to generate a new UUID.
+#  username : unicode
+#      username added to message headers.  The default is to ask the OS.
+#  key : bytes
+#      The key used to initialize an HMAC signature.  If unset, messages
+#      will not be signed or checked.
+#  keyfile : filepath
+#      The file containing a key.  If this is set, `key` will be initialized
+#      to the contents of the file.
+
+## Threshold (in bytes) beyond which an object's buffer should be extracted to
+#  avoid pickling.
+#c.Session.buffer_threshold = 1024
+
+## Whether to check PID to protect against calls after fork.
+#  
+#  This check can be disabled if fork-safety is handled elsewhere.
+#c.Session.check_pid = True
+
+## Threshold (in bytes) beyond which a buffer should be sent without copying.
+#c.Session.copy_threshold = 65536
+
+## Debug output in the Session
+#c.Session.debug = False
+
+## The maximum number of digests to remember.
+#  
+#  The digest history will be culled when it exceeds this value.
+#c.Session.digest_history_size = 65536
+
+## The maximum number of items for a container to be introspected for custom
+#  serialization. Containers larger than this are pickled outright.
+#c.Session.item_threshold = 64
+
+## execution key, for signing messages.
+#c.Session.key = ''
+
+## path to file containing execution key.
+#c.Session.keyfile = ''
+
+## Metadata dictionary, which serves as the default top-level metadata dict for
+#  each message.
+#c.Session.metadata = {}
+
+## The name of the packer for serializing messages. Should be one of 'json',
+#  'pickle', or an import name for a custom callable serializer.
+#c.Session.packer = 'json'
+
+## The UUID identifying this session.
+#c.Session.session = u''
+
+## The digest scheme used to construct the message signatures. Must have the form
+#  'hmac-HASH'.
+#c.Session.signature_scheme = 'hmac-sha256'
+
+## The name of the unpacker for unserializing messages. Only used with custom
+#  functions for `packer`.
+#c.Session.unpacker = 'json'
+
+## Username for the Session. Default is your system username.
+#c.Session.username = u'username'
+
+#------------------------------------------------------------------------------
+# MultiKernelManager(LoggingConfigurable) configuration
+#------------------------------------------------------------------------------
+
+## A class for managing multiple kernels.
+
+## The name of the default kernel to start
+#c.MultiKernelManager.default_kernel_name = 'python2'
+
+## The kernel manager class.  This is configurable to allow subclassing of the
+#  KernelManager for customized behavior.
+#c.MultiKernelManager.kernel_manager_class = 'jupyter_client.ioloop.IOLoopKernelManager'
+
+#------------------------------------------------------------------------------
+# MappingKernelManager(MultiKernelManager) configuration
+#------------------------------------------------------------------------------
+
+## A KernelManager that handles notebook mapping and HTTP error handling
+
+## 
+#c.MappingKernelManager.root_dir = u''
+
+#------------------------------------------------------------------------------
+# ContentsManager(LoggingConfigurable) configuration
+#------------------------------------------------------------------------------
+
+## Base class for serving files and directories.
+#  
+#  This serves any text or binary file, as well as directories, with special
+#  handling for JSON notebook documents.
+#  
+#  Most APIs take a path argument, which is always an API-style unicode path, and
+#  always refers to a directory.
+#  
+#  - unicode, not url-escaped
+#  - '/'-separated
+#  - leading and trailing '/' will be stripped
+#  - if unspecified, path defaults to '',
+#    indicating the root path.
+
+## 
+#c.ContentsManager.checkpoints = None
+
+## 
+#c.ContentsManager.checkpoints_class = 'notebook.services.contents.checkpoints.Checkpoints'
+
+## 
+#c.ContentsManager.checkpoints_kwargs = {}
+
+## Glob patterns to hide in file and directory listings.
+#c.ContentsManager.hide_globs = [u'__pycache__', '*.pyc', '*.pyo', '.DS_Store', '*.so', '*.dylib', '*~']
+
+## Python callable or importstring thereof
+#  
+#  To be called on a contents model prior to save.
+#  
+#  This can be used to process the structure, such as removing notebook outputs
+#  or other side effects that should not be saved.
+#  
+#  It will be called as (all arguments passed by keyword)::
+#  
+#      hook(path=path, model=model, contents_manager=self)
+#  
+#  - model: the model to be saved. Includes file contents.
+#    Modifying this dict will affect the file that is stored.
+#  - path: the API path of the save destination
+#  - contents_manager: this ContentsManager instance
+#c.ContentsManager.pre_save_hook = None
+
+## 
+#c.ContentsManager.root_dir = '/'
+
+## The base name used when creating untitled directories.
+#c.ContentsManager.untitled_directory = 'Untitled Folder'
+
+## The base name used when creating untitled files.
+#c.ContentsManager.untitled_file = 'untitled'
+
+## The base name used when creating untitled notebooks.
+#c.ContentsManager.untitled_notebook = 'Untitled'
+
+#------------------------------------------------------------------------------
+# FileManagerMixin(Configurable) configuration
+#------------------------------------------------------------------------------
+
+## Mixin for ContentsAPI classes that interact with the filesystem.
+#  
+#  Provides facilities for reading, writing, and copying both notebooks and
+#  generic files.
+#  
+#  Shared by FileContentsManager and FileCheckpoints.
+#  
+#  Note ---- Classes using this mixin must provide the following attributes:
+#  
+#  root_dir : unicode
+#      A directory against against which API-style paths are to be resolved.
+#  
+#  log : logging.Logger
+
+## By default notebooks are saved on disk on a temporary file and then if
+#  succefully written, it replaces the old ones. This procedure, namely
+#  'atomic_writing', causes some bugs on file system whitout operation order
+#  enforcement (like some networked fs). If set to False, the new notebook is
+#  written directly on the old one which could fail (eg: full filesystem or quota
+#  )
+#c.FileManagerMixin.use_atomic_writing = True
+
+#------------------------------------------------------------------------------
+# FileContentsManager(FileManagerMixin,ContentsManager) configuration
+#------------------------------------------------------------------------------
+
+## Python callable or importstring thereof
+#  
+#  to be called on the path of a file just saved.
+#  
+#  This can be used to process the file on disk, such as converting the notebook
+#  to a script or HTML via nbconvert.
+#  
+#  It will be called as (all arguments passed by keyword)::
+#  
+#      hook(os_path=os_path, model=model, contents_manager=instance)
+#  
+#  - path: the filesystem path to the file just written - model: the model
+#  representing the file - contents_manager: this ContentsManager instance
+#c.FileContentsManager.post_save_hook = None
+
+## 
+#c.FileContentsManager.root_dir = u''
+
+## DEPRECATED, use post_save_hook. Will be removed in Notebook 5.0
+#c.FileContentsManager.save_script = False
+
+#------------------------------------------------------------------------------
+# NotebookNotary(LoggingConfigurable) configuration
+#------------------------------------------------------------------------------
+
+## A class for computing and verifying notebook signatures.
+
+## The hashing algorithm used to sign notebooks.
+#c.NotebookNotary.algorithm = 'sha256'
+
+## The sqlite file in which to store notebook signatures. By default, this will
+#  be in your Jupyter data directory. You can set it to ':memory:' to disable
+#  sqlite writing to the filesystem.
+#c.NotebookNotary.db_file = u''
+
+## The secret key with which notebooks are signed.
+#c.NotebookNotary.secret = ''
+
+## The file where the secret key is stored.
+#c.NotebookNotary.secret_file = u''
+
+## A callable returning the storage backend for notebook signatures. The default
+#  uses an SQLite database.
+#c.NotebookNotary.store_factory = traitlets.Undefined
+
+#------------------------------------------------------------------------------
+# KernelSpecManager(LoggingConfigurable) configuration
+#------------------------------------------------------------------------------
+
+## If there is no Python kernelspec registered and the IPython kernel is
+#  available, ensure it is added to the spec list.
+#c.KernelSpecManager.ensure_native_kernel = True
+
+## The kernel spec class.  This is configurable to allow subclassing of the
+#  KernelSpecManager for customized behavior.
+#c.KernelSpecManager.kernel_spec_class = 'jupyter_client.kernelspec.KernelSpec'
+
+## Whitelist of allowed kernel names.
+#  
+#  By default, all installed kernels are allowed.
+#c.KernelSpecManager.whitelist = set([])

container/conf/java/kafka/connect-console-sink.properties

@@ -0,0 +1,19 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+name=local-console-sink
+connector.class=org.apache.kafka.connect.file.FileStreamSinkConnector
+tasks.max=1
+topics=connect-test

container/conf/java/kafka/connect-console-source.properties

@@ -0,0 +1,19 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+name=local-console-source
+connector.class=org.apache.kafka.connect.file.FileStreamSourceConnector
+tasks.max=1
+topic=connect-test

container/conf/java/kafka/connect-distributed.properties

@@ -0,0 +1,42 @@
+##
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+##
+
+# These are defaults. This file just demonstrates how to override some settings.
+bootstrap.servers=localhost:9092
+
+group.id=connect-cluster
+
+# The converters specify the format of data in Kafka and how to translate it into Connect data. Every Connect user will
+# need to configure these based on the format they want their data in when loaded from or stored into Kafka
+key.converter=org.apache.kafka.connect.json.JsonConverter
+value.converter=org.apache.kafka.connect.json.JsonConverter
+# Converter-specific settings can be passed in by prefixing the Converter's setting with the converter we want to apply
+# it to
+key.converter.schemas.enable=true
+value.converter.schemas.enable=true
+
+# The internal converter used for offsets and config data is configurable and must be specified, but most users will
+# always want to use the built-in default. Offset and config data is never visible outside of Copcyat in this format.
+internal.key.converter=org.apache.kafka.connect.json.JsonConverter
+internal.value.converter=org.apache.kafka.connect.json.JsonConverter
+internal.key.converter.schemas.enable=false
+internal.value.converter.schemas.enable=false
+
+offset.storage.topic=connect-offsets
+# Flush much faster than normal, which is useful for testing/debugging
+offset.flush.interval.ms=10000
+config.storage.topic=connect-configs

container/conf/java/kafka/connect-file-sink.properties

@@ -0,0 +1,20 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+name=local-file-sink
+connector.class=org.apache.kafka.connect.file.FileStreamSinkConnector
+tasks.max=1
+file=test.sink.txt
+topics=connect-test

container/conf/java/kafka/connect-file-source.properties

@@ -0,0 +1,20 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+name=local-file-source
+connector.class=org.apache.kafka.connect.file.FileStreamSourceConnector
+tasks.max=1
+file=test.txt
+topic=connect-test

container/conf/java/kafka/connect-log4j.properties

@@ -0,0 +1,23 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+log4j.rootLogger=INFO, stdout
+
+log4j.appender.stdout=org.apache.log4j.ConsoleAppender
+log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
+log4j.appender.stdout.layout.ConversionPattern=[%d] %p %m (%c:%L)%n
+
+log4j.logger.org.apache.zookeeper=ERROR
+log4j.logger.org.I0Itec.zkclient=ERROR

container/conf/java/kafka/connect-standalone.properties

@@ -0,0 +1,37 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# These are defaults. This file just demonstrates how to override some settings.
+bootstrap.servers=localhost:9092
+
+# The converters specify the format of data in Kafka and how to translate it into Connect data. Every Connect user will
+# need to configure these based on the format they want their data in when loaded from or stored into Kafka
+key.converter=org.apache.kafka.connect.json.JsonConverter
+value.converter=org.apache.kafka.connect.json.JsonConverter
+# Converter-specific settings can be passed in by prefixing the Converter's setting with the converter we want to apply
+# it to
+key.converter.schemas.enable=true
+value.converter.schemas.enable=true
+
+# The internal converter used for offsets and config data is configurable and must be specified, but most users will
+# always want to use the built-in default. Offset and config data is never visible outside of Copcyat in this format.
+internal.key.converter=org.apache.kafka.connect.json.JsonConverter
+internal.value.converter=org.apache.kafka.connect.json.JsonConverter
+internal.key.converter.schemas.enable=false
+internal.value.converter.schemas.enable=false
+
+offset.storage.file.filename=/tmp/connect.offsets
+# Flush much faster than normal, which is useful for testing/debugging
+offset.flush.interval.ms=10000

container/conf/java/kafka/consumer.properties

@@ -0,0 +1,29 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+# 
+#    http://www.apache.org/licenses/LICENSE-2.0
+# 
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# see kafka.consumer.ConsumerConfig for more details
+
+# Zookeeper connection string
+# comma separated host:port pairs, each corresponding to a zk
+# server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002"
+zookeeper.connect=127.0.0.1:2181
+
+# timeout in ms for connecting to zookeeper
+zookeeper.connection.timeout.ms=6000
+
+#consumer group id
+group.id=test-consumer-group
+
+#consumer timeout
+#consumer.timeout.ms=5000

container/conf/java/kafka/log4j.properties

@@ -0,0 +1,87 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+log4j.rootLogger=INFO, stdout 
+
+log4j.appender.stdout=org.apache.log4j.ConsoleAppender
+log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
+log4j.appender.stdout.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.kafkaAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.kafkaAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.kafkaAppender.File=${kafka.logs.dir}/server.log
+log4j.appender.kafkaAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.kafkaAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.stateChangeAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.stateChangeAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.stateChangeAppender.File=${kafka.logs.dir}/state-change.log
+log4j.appender.stateChangeAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.stateChangeAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.requestAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.requestAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.requestAppender.File=${kafka.logs.dir}/kafka-request.log
+log4j.appender.requestAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.requestAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.cleanerAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.cleanerAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.cleanerAppender.File=${kafka.logs.dir}/log-cleaner.log
+log4j.appender.cleanerAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.cleanerAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.controllerAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.controllerAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.controllerAppender.File=${kafka.logs.dir}/controller.log
+log4j.appender.controllerAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.controllerAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.authorizerAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.authorizerAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.authorizerAppender.File=${kafka.logs.dir}/kafka-authorizer.log
+log4j.appender.authorizerAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.authorizerAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+# Turn on all our debugging info
+#log4j.logger.kafka.producer.async.DefaultEventHandler=DEBUG, kafkaAppender
+#log4j.logger.kafka.client.ClientUtils=DEBUG, kafkaAppender
+#log4j.logger.kafka.perf=DEBUG, kafkaAppender
+#log4j.logger.kafka.perf.ProducerPerformance$ProducerThread=DEBUG, kafkaAppender
+#log4j.logger.org.I0Itec.zkclient.ZkClient=DEBUG
+log4j.logger.kafka=INFO, kafkaAppender
+
+log4j.logger.kafka.network.RequestChannel$=WARN, requestAppender
+log4j.additivity.kafka.network.RequestChannel$=false
+
+#log4j.logger.kafka.network.Processor=TRACE, requestAppender
+#log4j.logger.kafka.server.KafkaApis=TRACE, requestAppender
+#log4j.additivity.kafka.server.KafkaApis=false
+log4j.logger.kafka.request.logger=WARN, requestAppender
+log4j.additivity.kafka.request.logger=false
+
+log4j.logger.kafka.controller=TRACE, controllerAppender
+log4j.additivity.kafka.controller=false
+
+log4j.logger.kafka.log.LogCleaner=INFO, cleanerAppender
+log4j.additivity.kafka.log.LogCleaner=false
+
+log4j.logger.state.change.logger=TRACE, stateChangeAppender
+log4j.additivity.state.change.logger=false
+
+#Change this to debug to get the actual audit log for authorizer.
+log4j.logger.kafka.authorizer.logger=WARN, authorizerAppender
+log4j.additivity.kafka.authorizer.logger=false
+

container/conf/java/kafka/producer.properties

@@ -0,0 +1,53 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# see kafka.producer.ProducerConfig for more details
+
+############################# Producer Basics #############################
+
+# list of brokers used for bootstrapping knowledge about the rest of the cluster
+# format: host1:port1,host2:port2 ...
+metadata.broker.list=localhost:9092
+
+# name of the partitioner class for partitioning events; default partition spreads data randomly
+#partitioner.class=
+
+# specifies whether the messages are sent asynchronously (async) or synchronously (sync)
+producer.type=sync
+
+# specify the compression codec for all data generated: none, gzip, snappy, lz4.
+# the old config values work as well: 0, 1, 2, 3 for none, gzip, snappy, lz4, respectively
+compression.codec=none
+
+# message encoder
+serializer.class=kafka.serializer.DefaultEncoder
+
+# allow topic level compression
+#compressed.topics=
+
+############################# Async Producer #############################
+# maximum time, in milliseconds, for buffering data on the producer queue 
+#queue.buffering.max.ms=
+
+# the maximum size of the blocking queue for buffering on the producer 
+#queue.buffering.max.messages=
+
+# Timeout for event enqueue:
+# 0: events will be enqueued immediately or dropped if the queue is full
+# -ve: enqueue will block indefinitely if the queue is full
+# +ve: enqueue will block up to this many milliseconds if the queue is full
+#queue.enqueue.timeout.ms=
+
+# the number of messages batched at the producer 
+#batch.num.messages=

container/conf/java/kafka/server.properties

@@ -0,0 +1,123 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# see kafka.server.KafkaConfig for additional details and defaults
+
+############################# Server Basics #############################
+
+# The id of the broker. This must be set to a unique integer for each broker.
+broker.id=1
+
+############################# Socket Server Settings #############################
+
+listeners=PLAINTEXT://:9092
+
+# The port the socket server listens on
+port=9092
+
+# Hostname the broker will bind to. If not set, the server will bind to all interfaces
+#host.name=localhost
+
+# Hostname the broker will advertise to producers and consumers. If not set, it uses the
+# value for "host.name" if configured.  Otherwise, it will use the value returned from
+# java.net.InetAddress.getCanonicalHostName().
+#advertised.host.name=<hostname routable by clients>
+
+# The port to publish to ZooKeeper for clients to use. If this is not set,
+# it will publish the same port that the broker binds to.
+#advertised.port=<port accessible by clients>
+
+# The number of threads handling network requests
+num.network.threads=3
+
+# The number of threads doing disk I/O
+num.io.threads=8
+
+# The send buffer (SO_SNDBUF) used by the socket server
+socket.send.buffer.bytes=102400
+
+# The receive buffer (SO_RCVBUF) used by the socket server
+socket.receive.buffer.bytes=102400
+
+# The maximum size of a request that the socket server will accept (protection against OOM)
+socket.request.max.bytes=104857600
+
+
+############################# Log Basics #############################
+
+# A comma seperated list of directories under which to store log files
+log.dirs=/root/kafka/logs
+
+# The default number of log partitions per topic. More partitions allow greater
+# parallelism for consumption, but this will also result in more files across
+# the brokers.
+num.partitions=1
+
+# The number of threads per data directory to be used for log recovery at startup and flushing at shutdown.
+# This value is recommended to be increased for installations with data dirs located in RAID array.
+num.recovery.threads.per.data.dir=1
+
+############################# Log Flush Policy #############################
+
+# Messages are immediately written to the filesystem but by default we only fsync() to sync
+# the OS cache lazily. The following configurations control the flush of data to disk.
+# There are a few important trade-offs here:
+#    1. Durability: Unflushed data may be lost if you are not using replication.
+#    2. Latency: Very large flush intervals may lead to latency spikes when the flush does occur as there will be a lot of data to flush.
+#    3. Throughput: The flush is generally the most expensive operation, and a small flush interval may lead to exceessive seeks.
+# The settings below allow one to configure the flush policy to flush data after a period of time or
+# every N messages (or both). This can be done globally and overridden on a per-topic basis.
+
+# The number of messages to accept before forcing a flush of data to disk
+#log.flush.interval.messages=10000
+
+# The maximum amount of time a message can sit in a log before we force a flush
+#log.flush.interval.ms=1000
+
+############################# Log Retention Policy #############################
+
+# The following configurations control the disposal of log segments. The policy can
+# be set to delete segments after a period of time, or after a given size has accumulated.
+# A segment will be deleted whenever *either* of these criteria are met. Deletion always happens
+# from the end of the log.
+
+# The minimum age of a log file to be eligible for deletion
+log.retention.hours=168
+
+# A size-based retention policy for logs. Segments are pruned from the log as long as the remaining
+# segments don't drop below log.retention.bytes.
+#log.retention.bytes=1073741824
+
+# The maximum size of a log segment file. When this size is reached a new log segment will be created.
+log.segment.bytes=1073741824
+
+# The interval at which log segments are checked to see if they can be deleted according
+# to the retention policies
+log.retention.check.interval.ms=300000
+
+############################# Zookeeper #############################
+
+# Zookeeper connection string (see zookeeper docs for details).
+# This is a comma separated host:port pairs, each corresponding to a zk
+# server. e.g. "127.0.0.1:3000,127.0.0.1:3001,127.0.0.1:3002".
+# You can also append an optional chroot string to the urls to specify the
+# root directory for all kafka znodes.
+zookeeper.connect=data-zookeeper:2181,data-zookeeper1:2181,data-zookeeper2:2181/kafka
+
+# Timeout in ms for connecting to zookeeper
+zookeeper.connection.timeout.ms=6000
+
+delete.topic.enable=true  
+min.insync.replicas=1  
+zookeeper.session.timeout.ms=6000  

container/conf/java/kafka/test-log4j.properties

@@ -0,0 +1,66 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+log4j.rootLogger=INFO, stdout
+
+log4j.appender.stdout=org.apache.log4j.ConsoleAppender
+log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
+log4j.appender.stdout.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.kafkaAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.kafkaAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.kafkaAppender.File=logs/server.log
+log4j.appender.kafkaAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.kafkaAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.stateChangeAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.stateChangeAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.stateChangeAppender.File=logs/state-change.log
+log4j.appender.stateChangeAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.stateChangeAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.requestAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.requestAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.requestAppender.File=logs/kafka-request.log
+log4j.appender.requestAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.requestAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+log4j.appender.controllerAppender=org.apache.log4j.DailyRollingFileAppender
+log4j.appender.controllerAppender.DatePattern='.'yyyy-MM-dd-HH
+log4j.appender.controllerAppender.File=logs/controller.log
+log4j.appender.controllerAppender.layout=org.apache.log4j.PatternLayout
+log4j.appender.controllerAppender.layout.ConversionPattern=[%d] %p %m (%c)%n
+
+# Turn on all our debugging info
+#log4j.logger.kafka.producer.async.DefaultEventHandler=DEBUG, kafkaAppender
+#log4j.logger.kafka.client.ClientUtils=DEBUG, kafkaAppender
+log4j.logger.kafka.tools=DEBUG, kafkaAppender
+log4j.logger.kafka.tools.ProducerPerformance$ProducerThread=DEBUG, kafkaAppender
+#log4j.logger.org.I0Itec.zkclient.ZkClient=DEBUG
+log4j.logger.kafka=INFO, kafkaAppender
+
+log4j.logger.kafka.network.RequestChannel$=TRACE, requestAppender
+log4j.additivity.kafka.network.RequestChannel$=false
+
+#log4j.logger.kafka.network.Processor=TRACE, requestAppender
+#log4j.logger.kafka.server.KafkaApis=TRACE, requestAppender
+#log4j.additivity.kafka.server.KafkaApis=false
+log4j.logger.kafka.request.logger=TRACE, requestAppender
+log4j.additivity.kafka.request.logger=false
+
+log4j.logger.kafka.controller=TRACE, controllerAppender
+log4j.additivity.kafka.controller=false
+
+log4j.logger.state.change.logger=TRACE, stateChangeAppender
+log4j.additivity.state.change.logger=false

container/conf/java/kafka/tools-log4j.properties

@@ -0,0 +1,21 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+log4j.rootLogger=WARN, stderr
+
+log4j.appender.stderr=org.apache.log4j.ConsoleAppender
+log4j.appender.stderr.layout=org.apache.log4j.PatternLayout
+log4j.appender.stderr.layout.ConversionPattern=[%d] %p %m (%c)%n
+log4j.appender.stderr.Target=System.err

container/conf/java/kafka/zookeeper.properties

@@ -0,0 +1,20 @@
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+# 
+#    http://www.apache.org/licenses/LICENSE-2.0
+# 
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# the directory where the snapshot is stored.
+dataDir=/tmp/zookeeper
+# the port at which the clients will connect
+clientPort=2181
+# disable the per-ip limit on the number of connections since this is a non-production config
+maxClientCnxns=0

container/conf/java/sbt/sbtconfig.txt

@@ -0,0 +1,13 @@
+# Set the java args to high
+
+-Xmx512M
+
+-XX:MaxPermSize=256m
+
+-XX:ReservedCodeCacheSize=128m
+
+
+
+# Set the extra SBT options
+
+-Dsbt.log.format=true

container/conf/java/sbt/sbtopts

@@ -0,0 +1,49 @@
+# ------------------------------------------------ #
+#  The SBT Configuration file.                     #
+# ------------------------------------------------ #
+
+
+# Disable ANSI color codes
+#
+#-no-colors
+
+# Starts sbt even if the current directory contains no sbt project.
+#
+-sbt-create
+
+# Path to global settings/plugins directory (default: ~/.sbt)
+#
+#-sbt-dir  /etc/sbt
+
+# Path to shared boot directory (default: ~/.sbt/boot in 0.11 series)
+#
+#-sbt-boot ~/.sbt/boot  
+
+# Path to local Ivy repository (default: ~/.ivy2)
+#
+#-ivy ~/.ivy2
+
+# set memory options
+#
+#-mem   <integer>  
+
+# Use local caches for projects, no sharing.
+#
+#-no-share
+
+# Put SBT in offline mode.
+#
+#-offline
+
+# Sets the SBT version to use.
+#-sbt-version  0.11.3
+
+# Scala version (default: latest release)
+#
+#-scala-home <path>        
+#-scala-version <version>
+
+# java version (default: java from PATH, currently $(java -version |& grep version))
+#
+#-java-home <path>
+

container/conf/java/spark/docker.properties

@@ -0,0 +1,20 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+spark.mesos.executor.docker.image: <image built from `../docker/spark-mesos/Dockerfile`>
+spark.mesos.executor.docker.volumes: /usr/local/lib:/host/usr/local/lib:ro
+spark.mesos.executor.home: /opt/spark

container/conf/java/spark/fairscheduler.xml

@@ -0,0 +1,31 @@
+<?xml version="1.0"?>
+
+<!--
+   Licensed to the Apache Software Foundation (ASF) under one or more
+   contributor license agreements.  See the NOTICE file distributed with
+   this work for additional information regarding copyright ownership.
+   The ASF licenses this file to You under the Apache License, Version 2.0
+   (the "License"); you may not use this file except in compliance with
+   the License.  You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+-->
+
+<allocations>
+  <pool name="production">
+    <schedulingMode>FAIR</schedulingMode>
+    <weight>1</weight>
+    <minShare>2</minShare>
+  </pool>
+  <pool name="test">
+    <schedulingMode>FIFO</schedulingMode>
+    <weight>2</weight>
+    <minShare>3</minShare>
+  </pool>
+</allocations>

container/conf/java/spark/log4j.properties

@@ -0,0 +1,40 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# Set everything to be logged to the console
+log4j.rootCategory=INFO, console
+log4j.appender.console=org.apache.log4j.ConsoleAppender
+log4j.appender.console.target=System.err
+log4j.appender.console.layout=org.apache.log4j.PatternLayout
+log4j.appender.console.layout.ConversionPattern=%d{yy/MM/dd HH:mm:ss} %p %c{1}: %m%n
+
+# Set the default spark-shell log level to WARN. When running the spark-shell, the
+# log level for this class is used to overwrite the root logger's log level, so that
+# the user can have different defaults for the shell and regular Spark apps.
+log4j.logger.org.apache.spark.repl.Main=WARN
+
+# Settings to quiet third party logs that are too verbose
+log4j.logger.org.spark_project.jetty=WARN
+log4j.logger.org.spark_project.jetty.util.component.AbstractLifeCycle=ERROR
+log4j.logger.org.apache.spark.repl.SparkIMain$exprTyper=INFO
+log4j.logger.org.apache.spark.repl.SparkILoop$SparkILoopInterpreter=INFO
+log4j.logger.org.apache.parquet=ERROR
+log4j.logger.parquet=ERROR
+
+# SPARK-9183: Settings to avoid annoying messages when looking up nonexistent UDFs in SparkSQL with Hive support
+log4j.logger.org.apache.hadoop.hive.metastore.RetryingHMSHandler=FATAL
+log4j.logger.org.apache.hadoop.hive.ql.exec.FunctionRegistry=ERROR

container/conf/java/spark/metrics.properties

@@ -0,0 +1,170 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+#  syntax: [instance].sink|source.[name].[options]=[value]
+
+#  This file configures Spark's internal metrics system. The metrics system is
+#  divided into instances which correspond to internal components.
+#  Each instance can be configured to report its metrics to one or more sinks.
+#  Accepted values for [instance] are "master", "worker", "executor", "driver",
+#  and "applications". A wildcard "*" can be used as an instance name, in
+#  which case all instances will inherit the supplied property.
+#
+#  Within an instance, a "source" specifies a particular set of grouped metrics.
+#  there are two kinds of sources:
+#    1. Spark internal sources, like MasterSource, WorkerSource, etc, which will
+#    collect a Spark component's internal state. Each instance is paired with a
+#    Spark source that is added automatically.
+#    2. Common sources, like JvmSource, which will collect low level state.
+#    These can be added through configuration options and are then loaded
+#    using reflection.
+#
+#  A "sink" specifies where metrics are delivered to. Each instance can be
+#  assigned one or more sinks.
+#
+#  The sink|source field specifies whether the property relates to a sink or
+#  source.
+#
+#  The [name] field specifies the name of source or sink.
+#
+#  The [options] field is the specific property of this source or sink. The
+#  source or sink is responsible for parsing this property.
+#
+#  Notes:
+#    1. To add a new sink, set the "class" option to a fully qualified class
+#    name (see examples below).
+#    2. Some sinks involve a polling period. The minimum allowed polling period
+#    is 1 second.
+#    3. Wildcard properties can be overridden by more specific properties.
+#    For example, master.sink.console.period takes precedence over
+#    *.sink.console.period.
+#    4. A metrics specific configuration
+#    "spark.metrics.conf=${SPARK_HOME}/conf/metrics.properties" should be
+#    added to Java properties using -Dspark.metrics.conf=xxx if you want to
+#    customize metrics system. You can also put the file in ${SPARK_HOME}/conf
+#    and it will be loaded automatically.
+#    5. The MetricsServlet sink is added by default as a sink in the master,
+#    worker and driver, and you can send HTTP requests to the "/metrics/json"
+#    endpoint to get a snapshot of all the registered metrics in JSON format.
+#    For master, requests to the "/metrics/master/json" and
+#    "/metrics/applications/json" endpoints can be sent separately to get
+#    metrics snapshots of the master instance and applications. This
+#    MetricsServlet does not have to be configured.
+
+## List of available common sources and their properties.
+
+# org.apache.spark.metrics.source.JvmSource
+#   Note: Currently, JvmSource is the only available common source.
+#         It can be added to an instance by setting the "class" option to its
+#         fully qualified class name (see examples below).
+
+## List of available sinks and their properties.
+
+# org.apache.spark.metrics.sink.ConsoleSink
+#   Name:   Default:   Description:
+#   period  10         Poll period
+#   unit    seconds    Unit of the poll period
+
+# org.apache.spark.metrics.sink.CSVSink
+#   Name:     Default:   Description:
+#   period    10         Poll period
+#   unit      seconds    Unit of the poll period
+#   directory /tmp       Where to store CSV files
+
+# org.apache.spark.metrics.sink.GangliaSink
+#   Name:     Default:   Description:
+#   host      NONE       Hostname or multicast group of the Ganglia server,
+#                        must be set
+#   port      NONE       Port of the Ganglia server(s), must be set
+#   period    10         Poll period
+#   unit      seconds    Unit of the poll period
+#   ttl       1          TTL of messages sent by Ganglia
+#   dmax      0          Lifetime in seconds of metrics (0 never expired)
+#   mode      multicast  Ganglia network mode ('unicast' or 'multicast')
+
+# org.apache.spark.metrics.sink.JmxSink
+
+# org.apache.spark.metrics.sink.MetricsServlet
+#   Name:     Default:   Description:
+#   path      VARIES*    Path prefix from the web server root
+#   sample    false      Whether to show entire set of samples for histograms
+#                        ('false' or 'true')
+#
+# * Default path is /metrics/json for all instances except the master. The
+#   master has two paths:
+#     /metrics/applications/json # App information
+#     /metrics/master/json       # Master information
+
+# org.apache.spark.metrics.sink.GraphiteSink
+#   Name:     Default:      Description:
+#   host      NONE          Hostname of the Graphite server, must be set
+#   port      NONE          Port of the Graphite server, must be set
+#   period    10            Poll period
+#   unit      seconds       Unit of the poll period
+#   prefix    EMPTY STRING  Prefix to prepend to every metric's name
+#   protocol  tcp           Protocol ("tcp" or "udp") to use
+
+## Examples
+# Enable JmxSink for all instances by class name
+#*.sink.jmx.class=org.apache.spark.metrics.sink.JmxSink
+
+# Enable ConsoleSink for all instances by class name
+#*.sink.console.class=org.apache.spark.metrics.sink.ConsoleSink
+
+# Polling period for the ConsoleSink
+#*.sink.console.period=10
+# Unit of the polling period for the ConsoleSink
+#*.sink.console.unit=seconds
+
+# Polling period for the ConsoleSink specific for the master instance
+#master.sink.console.period=15
+# Unit of the polling period for the ConsoleSink specific for the master
+# instance
+#master.sink.console.unit=seconds
+
+# Enable CsvSink for all instances by class name
+#*.sink.csv.class=org.apache.spark.metrics.sink.CsvSink
+
+# Polling period for the CsvSink
+#*.sink.csv.period=1
+# Unit of the polling period for the CsvSink
+#*.sink.csv.unit=minutes
+
+# Polling directory for CsvSink
+#*.sink.csv.directory=/tmp/
+
+# Polling period for the CsvSink specific for the worker instance
+#worker.sink.csv.period=10
+# Unit of the polling period for the CsvSink specific for the worker instance
+#worker.sink.csv.unit=minutes
+
+# Enable Slf4jSink for all instances by class name
+#*.sink.slf4j.class=org.apache.spark.metrics.sink.Slf4jSink
+
+# Polling period for the Slf4JSink
+#*.sink.slf4j.period=1
+# Unit of the polling period for the Slf4jSink
+#*.sink.slf4j.unit=minutes
+
+# Enable JvmSource for instance master, worker, driver and executor
+#master.source.jvm.class=org.apache.spark.metrics.source.JvmSource
+
+#worker.source.jvm.class=org.apache.spark.metrics.source.JvmSource
+
+#driver.source.jvm.class=org.apache.spark.metrics.source.JvmSource
+
+#executor.source.jvm.class=org.apache.spark.metrics.source.JvmSource

container/conf/java/spark/slaves

@@ -0,0 +1,2 @@
+data-spark-slave
+data-spark-slave1

container/conf/java/spark/spark-defaults.conf

@@ -0,0 +1,32 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# Default system properties included when running spark-submit.
+# This is useful for setting default environmental settings.
+
+# Example:
+# spark.master                     spark://master:7077
+# spark.eventLog.enabled           true
+# spark.eventLog.dir               hdfs://namenode:8021/directory
+# spark.serializer                 org.apache.spark.serializer.KryoSerializer
+# spark.executor.extraJavaOptions  -XX:+PrintGCDetails -Dkey=value -Dnumbers="one two three"
+spark.driver.memory              1g
+spark.eventLog.enabled           false
+#spark.eventLog.dir               hdfs://data-hadoop:9000/spark/log
+spark.yarn.jars					 hdfs://data-hadoop:9000/spark/jars/*.jar
+#spark.eventLog.dir               /root/spark/logs
+#spark.yarn.jars					 /usr/local/spark/jars/*.jar

container/conf/java/spark/spark-env.sh

@@ -0,0 +1,76 @@
+#!/usr/bin/env bash
+
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# This file is sourced when running various Spark programs.
+# Copy it as spark-env.sh and edit that to configure Spark for your site.
+
+# Options read when launching programs locally with
+# ./bin/run-example or ./bin/spark-submit
+# - HADOOP_CONF_DIR, to point Spark towards Hadoop configuration files
+# - SPARK_LOCAL_IP, to set the IP address Spark binds to on this node
+# - SPARK_PUBLIC_DNS, to set the public dns name of the driver program
+# - SPARK_CLASSPATH, default classpath entries to append
+
+# Options read by executors and drivers running inside the cluster
+# - SPARK_LOCAL_IP, to set the IP address Spark binds to on this node
+# - SPARK_PUBLIC_DNS, to set the public DNS name of the driver program
+# - SPARK_CLASSPATH, default classpath entries to append
+# - SPARK_LOCAL_DIRS, storage directories to use on this node for shuffle and RDD data
+# - MESOS_NATIVE_JAVA_LIBRARY, to point to your libmesos.so if you use Mesos
+
+# Options read in YARN client mode
+# - HADOOP_CONF_DIR, to point Spark towards Hadoop configuration files
+# - SPARK_EXECUTOR_INSTANCES, Number of executors to start (Default: 2)
+# - SPARK_EXECUTOR_CORES, Number of cores for the executors (Default: 1).
+# - SPARK_EXECUTOR_MEMORY, Memory per Executor (e.g. 1000M, 2G) (Default: 1G)
+# - SPARK_DRIVER_MEMORY, Memory for Driver (e.g. 1000M, 2G) (Default: 1G)
+
+# Options for the daemons used in the standalone deploy mode
+# - SPARK_MASTER_HOST, to bind the master to a different IP address or hostname
+# - SPARK_MASTER_PORT / SPARK_MASTER_WEBUI_PORT, to use non-default ports for the master
+# - SPARK_MASTER_OPTS, to set config properties only for the master (e.g. "-Dx=y")
+# - SPARK_WORKER_CORES, to set the number of cores to use on this machine
+# - SPARK_WORKER_MEMORY, to set how much total memory workers have to give executors (e.g. 1000m, 2g)
+# - SPARK_WORKER_PORT / SPARK_WORKER_WEBUI_PORT, to use non-default ports for the worker
+# - SPARK_WORKER_INSTANCES, to set the number of worker processes per node
+# - SPARK_WORKER_DIR, to set the working directory of worker processes
+# - SPARK_WORKER_OPTS, to set config properties only for the worker (e.g. "-Dx=y")
+# - SPARK_DAEMON_MEMORY, to allocate to the master, worker and history server themselves (default: 1g).
+# - SPARK_HISTORY_OPTS, to set config properties only for the history server (e.g. "-Dx=y")
+# - SPARK_SHUFFLE_OPTS, to set config properties only for the external shuffle service (e.g. "-Dx=y")
+# - SPARK_DAEMON_JAVA_OPTS, to set config properties for all daemons (e.g. "-Dx=y")
+# - SPARK_PUBLIC_DNS, to set the public dns name of the master or workers
+
+# Generic options for the daemons used in the standalone deploy mode
+# - SPARK_CONF_DIR      Alternate conf dir. (Default: ${SPARK_HOME}/conf)
+# - SPARK_LOG_DIR       Where log files are stored.  (Default: ${SPARK_HOME}/logs)
+# - SPARK_PID_DIR       Where the pid file is stored. (Default: /tmp)
+# - SPARK_IDENT_STRING  A string representing this instance of spark. (Default: $USER)
+# - SPARK_NICENESS      The scheduling priority for daemons. (Default: 0)
+# - SPARK_NO_DAEMONIZE  Run the proposed command in the foreground. It will not output a PID file.
+
+export SPARK_MASTER_HOST=data-spark
+export SPARK_MASTER_PORT=7077
+export SPARK_MASTER_WEBUI_PORT=8080
+export SPARK_MASTER_OPTS="-Dspark.driver.port=7001 -Dspark.fileserver.port=7002 -Dspark.broadcast.port=7003 -Dspark.replClassServer.port=7004 -Dspark.blockManager.port=7005 -Dspark.executor.port=7006 -Dspark.ui.port=4040 -Dspark.broadcast.factory=org.apache.spark.broadcast.HttpBroadcastFactory"
+export SPARK_WORKER_OPTS="-Dspark.driver.port=7001 -Dspark.fileserver.port=7002 -Dspark.broadcast.port=7003 -Dspark.replClassServer.port=7004 -Dspark.blockManager.port=7005 -Dspark.executor.port=7006 -Dspark.ui.port=4040 -Dspark.broadcast.factory=org.apache.spark.broadcast.HttpBroadcastFactory"
+export SPARK_WORKER_PORT=8888
+export SPARK_WORKER_WEBUI_PORT=8081
+export SPARK_WORKER_MEMORY=1g
+export SPARK_PID_DIR=/root/spark/tmp

container/conf/java/thrift/sbtconfig.txt

@@ -0,0 +1,13 @@
+# Set the java args to high
+
+-Xmx512M
+
+-XX:MaxPermSize=256m
+
+-XX:ReservedCodeCacheSize=128m
+
+
+
+# Set the extra SBT options
+
+-Dsbt.log.format=true