<?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.
-->
<!-- Do not modify this file directly. Instead, copy entries that you -->
<!-- wish to modify from this file into mapred-site.xml and change them -->
<!-- there. If mapred-site.xml does not already exist, create it. -->
<configuration>
<property>
<name>mapreduce.job.hdfs-servers</name>
<value>${fs.defaultFS}</value>
</property>
<property>
<name>mapreduce.job.committer.setup.cleanup.needed</name>
<value>true</value>
<description> true, if job needs job-setup and job-cleanup.
false, otherwise
</description>
</property>
<!-- i/o properties -->
<property>
<name>mapreduce.task.io.sort.factor</name>
<value>10</value>
<description>The number of streams to merge at once while sorting
files. This determines the number of open file handles.</description>
</property>
<property>
<name>mapreduce.task.io.sort.mb</name>
<value>100</value>
<description>The total amount of buffer memory to use while sorting
files, in megabytes. By default, gives each merge stream 1MB, which
should minimize seeks.</description>
</property>
<property>
<name>mapreduce.map.sort.spill.percent</name>
<value>0.80</value>
<description>The soft limit in the serialization buffer. Once reached, a
thread will begin to spill the contents to disk in the background. Note that
collection will not block if this threshold is exceeded while a spill is
already in progress, so spills may be larger than this threshold when it is
set to less than .5</description>
</property>
<property>
<name>mapreduce.job.local-fs.single-disk-limit.bytes</name>
<value>-1</value>
<description>Enable an in task monitor thread to watch for single disk
consumption by jobs. By setting this to x nr of bytes, the task will fast
fail in case it is reached. This is a per disk configuration.</description>
</property>
<property>
<name>mapreduce.job.local-fs.single-disk-limit.check.interval-ms</name>
<value>5000</value>
<description>Interval of disk limit check to run in ms.</description>
</property>
<property>
<name>mapreduce.job.local-fs.single-disk-limit.check.kill-limit-exceed</name>
<value>true</value>
<description>If mapreduce.job.local-fs.single-disk-limit.bytes is triggered
should the task be killed or logged. If false the intent to kill the task
is only logged in the container logs.</description>
</property>
<property>
<name>mapreduce.job.maps</name>
<value>2</value>
<description>The default number of map tasks per job.
Ignored when mapreduce.framework.name is "local".
</description>
</property>
<property>
<name>mapreduce.job.reduces</name>
<value>1</value>
<description>The default number of reduce tasks per job. Typically set to 99%
of the cluster's reduce capacity, so that if a node fails the reduces can
still be executed in a single wave.
Ignored when mapreduce.framework.name is "local".
</description>
</property>
<property>
<name>mapreduce.job.running.map.limit</name>
<value>0</value>
<description>The maximum number of simultaneous map tasks per job.
There is no limit if this value is 0 or negative.
</description>
</property>
<property>
<name>mapreduce.job.running.reduce.limit</name>
<value>0</value>
<description>The maximum number of simultaneous reduce tasks per job.
There is no limit if this value is 0 or negative.
</description>
</property>
<property>
<name>mapreduce.job.max.map</name>
<value>-1</value>
<description>Limit on the number of map tasks allowed per job.
There is no limit if this value is negative.
</description>
</property>
<property>
<name>mapreduce.job.reducer.preempt.delay.sec</name>
<value>0</value>
<description>The threshold (in seconds) after which an unsatisfied
mapper request triggers reducer preemption when there is no anticipated
headroom. If set to 0 or a negative value, the reducer is preempted as
soon as lack of headroom is detected. Default is 0.
</description>
</property>
<property>
<name>mapreduce.job.reducer.unconditional-preempt.delay.sec</name>
<value>300</value>
<description>The threshold (in seconds) after which an unsatisfied
mapper request triggers a forced reducer preemption irrespective of the
anticipated headroom. By default, it is set to 5 mins. Setting it to 0
leads to immediate reducer preemption. Setting to -1 disables this
preemption altogether.
</description>
</property>
<property>
<name>mapreduce.job.max.split.locations</name>
<value>15</value>
<description>The max number of block locations to store for each split for
locality calculation.
</description>
</property>
<property>
<name>mapreduce.job.split.metainfo.maxsize</name>
<value>10000000</value>
<description>The maximum permissible size of the split metainfo file.
The MapReduce ApplicationMaster won't attempt to read submitted split metainfo
files bigger than this configured value.
No limits if set to -1.
</description>
</property>
<property>
<name>mapreduce.map.maxattempts</name>
<value>4</value>
<description>Expert: The maximum number of attempts per map task.
In other words, framework will try to execute a map task these many number
of times before giving up on it.
</description>
</property>
<property>
<name>mapreduce.reduce.maxattempts</name>
<value>4</value>
<description>Expert: The maximum number of attempts per reduce task.
In other words, framework will try to execute a reduce task these many number
of times before giving up on it.
</description>
</property>
<property>
<name>mapreduce.reduce.shuffle.fetch.retry.enabled</name>
<value>${yarn.nodemanager.recovery.enabled}</value>
<description>Set to enable fetch retry during host restart.</description>
</property>
<property>
<name>mapreduce.reduce.shuffle.fetch.retry.interval-ms</name>
<value>1000</value>
<description>Time of interval that fetcher retry to fetch again when some
non-fatal failure happens because of some events like NM restart.
</description>
</property>
<property>
<name>mapreduce.reduce.shuffle.fetch.retry.timeout-ms</name>
<value>30000</value>
<description>Timeout value for fetcher to retry to fetch again when some
non-fatal failure happens because of some events like NM restart.</description>
</property>
<property>
<name>mapreduce.reduce.shuffle.retry-delay.max.ms</name>
<value>60000</value>
<description>The maximum number of ms the reducer will delay before retrying
to download map data.
</description>
</property>
<property>
<name>mapreduce.reduce.shuffle.parallelcopies</name>
<value>5</value>
<description>The default number of parallel transfers run by reduce
during the copy(shuffle) phase.
</description>
</property>
<property>
<name>mapreduce.reduce.shuffle.connect.timeout</name>
<value>180000</value>
<description>Expert: The maximum amount of time (in milli seconds) reduce
task spends in trying to connect to a remote node for getting map output.
</description>
</property>
<property>
<name>mapreduce.reduce.shuffle.read.timeout</name>
<value>180000</value>
<description>Expert: The maximum amount of time (in milli seconds) reduce
task waits for map output data to be available for reading after obtaining
connection.
</description>
</property>
<property>
<name>mapreduce.shuffle.listen.queue.size</name>
<value>128</value>
<description>The length of the shuffle server listen queue.</description>
</property>
<property>
<name>mapreduce.shuffle.connection-keep-alive.enable</name>
<value>false</value>
<description>set to true to support keep-alive connections.</description>
</property>
<property>
<name>mapreduce.shuffle.connection-keep-alive.timeout</name>
<value>5</value>
<description>The number of seconds a shuffle client attempts to retain
http connection. Refer "Keep-Alive: timeout=" header in
Http specification
</description>
</property>
<property>
<name>mapreduce.task.timeout</name>
<value>600000</value>
<description>The number of milliseconds before a task will be
terminated if it neither reads an input, writes an output, nor
updates its status string. A value of 0 disables the timeout.
</description>
</property>
<property>
<name>mapreduce.map.memory.mb</name>
<value>-1</value>
<description>The amount of memory to request from the scheduler for each
map task. If this is not specified or is non-positive, it is inferred from
mapreduce.map.java.opts and mapreduce.job.heap.memory-mb.ratio.
If java-opts are also not specified, we set it to 1024.
</description>
</property>
<property>
<name>mapreduce.map.cpu.vcores</name>
<value>1</value>
<description>The number of virtual cores to request from the scheduler for
each map task.
</description>
</property>
<property>
<name>mapreduce.reduce.memory.mb</name>
<value>-1</value>
<description>The amount of memory to request from the scheduler for each
reduce task. If this is not specified or is non-positive, it is inferred
from mapreduce.reduce.java.opts and mapreduce.job.heap.memory-mb.ratio.
If java-opts are also not specified, we set it to 1024.
</description>
</property>
<property>
<name>mapreduce.reduce.cpu.vcores</name>
<value>1</value>
<description>The number of virtual cores to request from the scheduler for
each reduce task.
</description>
</property>
<property>
<name>mapred.child.java.opts</name>
<value></value>
<description>Java opts for the task processes.
The following symbol, if present, will be interpolated: @taskid@ is replaced
by current TaskID. Any other occurrences of '@' will go unchanged.
For example, to enable verbose gc logging to a file named for the taskid in
/tmp and to set the heap maximum to be a gigabyte, pass a 'value' of:
-Xmx1024m -verbose:gc -Xloggc:/tmp/@taskid@.gc
Usage of -Djava.library.path can cause programs to no longer function if
hadoop native libraries are used. These values should instead be set as part
of LD_LIBRARY_PATH in the map / reduce JVM env using the mapreduce.map.env and
mapreduce.reduce.env config settings.
If -Xmx is not set, it is inferred from mapreduce.{map|reduce}.memory.mb and
mapreduce.job.heap.memory-mb.ratio.
</description>
</property>
<!-- This is commented out so that it won't override mapred.child.java.opts.
<property>
<name>mapreduce.map.java.opts</name>
<value></value>
<description>Java opts only for the child processes that are maps. If set,
this will be used instead of mapred.child.java.opts. If -Xmx is not set,
it is inferred from mapreduce.map.memory.mb and
mapreduce.job.heap.memory-mb.ratio.
</description>
</property>
-->
<!-- This is commented out so that it won't override mapred.child.java.opts.
<property>
<name>mapreduce.reduce.java.opts</name>
<value></value>
<description>Java opts only for the child processes that are reduces. If set,
this will be used instead of mapred.child.java.opts. If -Xmx is not set,
it is inferred from mapreduce.reduce.memory.mb and
mapreduce.job.heap.memory-mb.ratio.
</description>
</property>
-->
<property>
<name>mapred.child.env</name>
<value></value>
<description>User added environment variables for the task processes.
Example :
1) A=foo This will set the env variable A to foo
2) B=$B:c This is inherit nodemanager's B env variable on Unix.
3) B=%B%;c This is inherit nodemanager's B env variable on Windows.
</description>
</property>
<!-- This is commented out so that it won't override mapred.child.env.
<property>
<name>mapreduce.map.env</name>
<value></value>
<description>User added environment variables for the map task processes.
</description>
</property>
-->
<!-- This is commented out so that it won't override mapred.child.env.
<property>
<name>mapreduce.reduce.env</name>
<value></value>
<description>User added environment variables for the reduce task processes.
</description>
</property>
-->
<property>
<name>mapreduce.admin.user.env</name>
<value></value>
<description>
Expert: Additional execution environment entries for
map and reduce task processes. This is not an additive property.
You must preserve the original value if you want your map and
reduce tasks to have access to native libraries (compression, etc).
When this value is empty, the command to set execution
envrionment will be OS dependent:
For linux, use LD_LIBRARY_PATH=$HADOOP_COMMON_HOME/lib/native.
For windows, use PATH = %PATH%;%HADOOP_COMMON_HOME%\\bin.
</description>
</property>
<property>
<name>yarn.app.mapreduce.am.log.level</name>
<value>INFO</value>
<description>The logging level for the MR ApplicationMaster. The allowed
levels are: OFF, FATAL, ERROR, WARN, INFO, DEBUG, TRACE and ALL.
The setting here could be overriden if "mapreduce.job.log4j-properties-file"
is set.
</description>
</property>
<property>
<name>mapreduce.map.log.level</name>
<value>INFO</value>
<description>The logging level for the map task. The allowed levels are:
OFF, FATAL, ERROR, WARN, INFO, DEBUG, TRACE and ALL.
The setting here could be overridden if "mapreduce.job.log4j-properties-file"
is set.
</description>
</property>
<property>
<name>mapreduce.reduce.log.level</name>
<value>INFO</value>
<description>The logging level for the reduce task. The allowed levels are:
OFF, FATAL, ERROR, WARN, INFO, DEBUG, TRACE and ALL.
The setting here could be overridden if "mapreduce.job.log4j-properties-file"
is set.
</description>
</property>
<property>
<name>mapreduce.reduce.merge.inmem.threshold</name>
<value>1000</value>
<description>The threshold, in terms of the number of files
for the in-memory merge process. When we accumulate threshold number of files
we initiate the in-memory merge and spill to disk. A value of 0 or less than
0 indicates we want to DON'T have any threshold and instead depend only on
the ramfs's memory consumption to trigger the merge.
</description>
</property>
<property>
<name>mapreduce.reduce.shuffle.merge.percent</name>
<value>0.66</value>
<description>The usage threshold at which an in-memory merge will be
initiated, expressed as a percentage of the total memory allocated to
storing in-memory map outputs, as defined by
mapreduce.reduce.shuffle.input.buffer.percent.
</description>
</property>
<property>
<name>mapreduce.reduce.shuffle.input.buffer.percent</name>
<value>0.70</value>
<description>The percentage of memory to be allocated from the maximum heap
size to storing map outputs during the shuffle.
</description>
</property>
<property>
<name>mapreduce.reduce.input.buffer.percent</name>
<value>0.0</value>
<description>The percentage of memory- relative to the maximum heap size- to
retain map outputs during the reduce. When the shuffle is concluded, any
remaining map outputs in memory must consume less than this threshold before
the reduce can begin.
</description>
</property>
<property>
<name>mapreduce.reduce.shuffle.memory.limit.percent</name>
<value>0.25</value>
<description>Expert: Maximum percentage of the in-memory limit that a
single shuffle can consume. Range of valid values is [0.0, 1.0]. If the value
is 0.0 map outputs are shuffled directly to disk.</description>
</property>
<property>
<name>mapreduce.shuffle.ssl.enabled</name>
<value>false</value>
<description>
Whether to use SSL for for the Shuffle HTTP endpoints.
</description>
</property>
<property>
<name>mapreduce.shuffle.ssl.file.buffer.size</name>
<value>65536</value>
<description>Buffer size for reading spills from file when using SSL.
</description>
</property>
<property>
<name>mapreduce.shuffle.max.connections</name>
<value>0</value>
<description>Max allowed connections for the shuffle. Set to 0 (zero)
to indicate no limit on the number of connections.
</description>
</property>
<property>
<name>mapreduce.shuffle.max.threads</name>
<value>0</value>
<description>Max allowed threads for serving shuffle connections. Set to zero
to indicate the default of 2 times the number of available
processors (as reported by Runtime.availableProcessors()). Netty is used to
serve requests, so a thread is not needed for each connection.
</description>
</property>
<property>
<name>mapreduce.shuffle.transferTo.allowed</name>
<value></value>
<description>This option can enable/disable using nio transferTo method in
the shuffle phase. NIO transferTo does not perform well on windows in the
shuffle phase. Thus, with this configuration property it is possible to
disable it, in which case custom transfer method will be used. Recommended
value is false when running Hadoop on Windows. For Linux, it is recommended
to set it to true. If nothing is set then the default value is false for
Windows, and true for Linux.
</description>
</property>
<property>
<name>mapreduce.shuffle.transfer.buffer.size</name>
<value>131072</value>
<description>This property is used only if
mapreduce.shuffle.transferTo.allowed is set to false. In that case,
this property defines the size of the buffer used in the buffer copy code
for the shuffle phase. The size of this buffer determines the size of the IO
requests.
</description>
</property>
<property>
<name>mapreduce.reduce.markreset.buffer.percent</name>
<value>0.0</value>
<description>The percentage of memory -relative to the maximum heap size- to
be used for caching values when using the mark-reset functionality.
</description>
</property>
<property>
<name>mapreduce.map.speculative</name>
<value>true</value>
<description>If true, then multiple instances of some map tasks
may be executed in parallel.</description>
</property>
<property>
<name>mapreduce.reduce.speculative</name>
<value>true</value>
<description>If true, then multiple instances of some reduce tasks
may be executed in parallel.</description>
</property>
<property>
<name>mapreduce.job.speculative.speculative-cap-running-tasks</name>
<value>0.1</value>
<description>The max percent (0-1) of running tasks that
can be speculatively re-executed at any time.</description>
</property>
<property>
<name>mapreduce.job.speculative.speculative-cap-total-tasks</name>
<value>0.01</value>
<description>The max percent (0-1) of all tasks that
can be speculatively re-executed at any time.</description>
</property>
<property>
<name>mapreduce.job.speculative.minimum-allowed-tasks</name>
<value>10</value>
<description>The minimum allowed tasks that
can be speculatively re-executed at any time.</description>
</property>
<property>
<name>mapreduce.job.speculative.retry-after-no-speculate</name>
<value>1000</value>
<description>The waiting time(ms) to do next round of speculation
if there is no task speculated in this round.</description>
</property>
<property>
<name>mapreduce.job.speculative.retry-after-speculate</name>
<value>15000</value>
<description>The waiting time(ms) to do next round of speculation
if there are tasks speculated in this round.</description>
</property>
<property>
<name>mapreduce.job.map.output.collector.class</name>
<value>org.apache.hadoop.mapred.MapTask$MapOutputBuffer</value>
<description>
The MapOutputCollector implementation(s) to use. This may be a comma-separated
list of class names, in which case the map task will try to initialize each
of the collectors in turn. The first to successfully initialize will be used.
</description>
</property>
<property>
<name>mapreduce.job.speculative.slowtaskthreshold</name>
<value>1.0</value>
<description>The number of standard deviations by which a task's
ave progress-rates must be lower than the average of all running tasks'
for the task to be considered too slow.
</description>
</property>
<property>
<name>mapreduce.job.ubertask.enable</name>
<value>false</value>
<description>Whether to enable the small-jobs "ubertask" optimization,
which runs "sufficiently small" jobs sequentially within a single JVM.
"Small" is defined by the following maxmaps, maxreduces, and maxbytes
settings. Note that configurations for application masters also affect
the "Small" definition - yarn.app.mapreduce.am.resource.mb must be
larger than both mapreduce.map.memory.mb and mapreduce.reduce.memory.mb,
and yarn.app.mapreduce.am.resource.cpu-vcores must be larger than
both mapreduce.map.cpu.vcores and mapreduce.reduce.cpu.vcores to enable
ubertask. Users may override this value.
</description>
</property>
<property>
<name>mapreduce.job.ubertask.maxmaps</name>
<value>9</value>
<description>Threshold for number of maps, beyond which job is considered
too big for the ubertasking optimization. Users may override this value,
but only downward.
</description>
</property>
<property>
<name>mapreduce.job.ubertask.maxreduces</name>
<value>1</value>
<description>Threshold for number of reduces, beyond which job is considered
too big for the ubertasking optimization. CURRENTLY THE CODE CANNOT SUPPORT
MORE THAN ONE REDUCE and will ignore larger values. (Zero is a valid max,
however.) Users may override this value, but only downward.
</description>
</property>
<property>
<name>mapreduce.job.ubertask.maxbytes</name>
<value></value>
<description>Threshold for number of input bytes, beyond which job is
considered too big for the ubertasking optimization. If no value is
specified, dfs.block.size is used as a default. Be sure to specify a
default value in mapred-site.xml if the underlying filesystem is not HDFS.
Users may override this value, but only downward.
</description>
</property>
<property>
<name>mapreduce.job.emit-timeline-data</name>
<value>false</value>
<description>Specifies if the Application Master should emit timeline data
to the timeline server. Individual jobs can override this value.
</description>
</property>
<property>
<name>mapreduce.job.sharedcache.mode</name>
<value>disabled</value>
<description>
A comma delimited list of resource categories to submit to the shared cache.
The valid categories are: jobjar, libjars, files, archives.
If "disabled" is specified then the job submission code will not use
the shared cache.
</description>
</property>
<property>
<name>mapreduce.input.fileinputformat.split.minsize</name>
<value>0</value>
<description>The minimum size chunk that map input should be split
into. Note that some file formats may have minimum split sizes that
take priority over this setting.</description>
</property>
<property>
<name>mapreduce.input.fileinputformat.list-status.num-threads</name>
<value>1</value>
<description>The number of threads to use to list and fetch block locations
for the specified input paths. Note: multiple threads should not be used
if a custom non thread-safe path filter is used.
</description>
</property>
<property>
<name>mapreduce.input.lineinputformat.linespermap</name>
<value>1</value>
<description>When using NLineInputFormat, the number of lines of input data
to include in each split.</description>
</property>
<property>
<name>mapreduce.client.submit.file.replication</name>
<value>10</value>
<description>The replication level for submitted job files. This
should be around the square root of the number of nodes.
</description>
</property>
<property>
<name>mapreduce.task.files.preserve.failedtasks</name>
<value>false</value>
<description>Should the files for failed tasks be kept. This should only be
used on jobs that are failing, because the storage is never
reclaimed. It also prevents the map outputs from being erased
from the reduce directory as they are consumed.</description>
</property>
<!--
<property>
<name>mapreduce.task.files.preserve.filepattern</name>
<value>.*_m_123456_0</value>
<description>Keep all files from tasks whose task names match the given
regular expression. Defaults to none.</description>
</property>
-->
<property>
<name>mapreduce.output.fileoutputformat.compress</name>
<value>false</value>
<description>Should the job outputs be compressed?
</description>
</property>
<property>
<name>mapreduce.output.fileoutputformat.compress.type</name>
<value>RECORD</value>
<description>If the job outputs are to compressed as SequenceFiles, how should
they be compressed? Should be one of NONE, RECORD or BLOCK.
</description>
</property>
<property>
<name>mapreduce.output.fileoutputformat.compress.codec</name>
<value>org.apache.hadoop.io.compress.DefaultCodec</value>
<description>If the job outputs are compressed, how should they be compressed?
</description>
</property>
<property>
<name>mapreduce.map.output.compress</name>
<value>false</value>
<description>Should the outputs of the maps be compressed before being
sent across the network. Uses SequenceFile compression.
</description>
</property>
<property>
<name>mapreduce.map.output.compress.codec</name>
<value>org.apache.hadoop.io.compress.DefaultCodec</value>
<description>If the map outputs are compressed, how should they be
compressed?
</description>
</property>
<property>
<name>map.sort.class</name>
<value>org.apache.hadoop.util.QuickSort</value>
<description>The default sort class for sorting keys.
</description>
</property>
<property>
<name>mapreduce.task.userlog.limit.kb</name>
<value>0</value>
<description>The maximum size of user-logs of each task in KB. 0 disables the cap.
</description>
</property>
<property>
<name>yarn.app.mapreduce.am.container.log.limit.kb</name>
<value>0</value>
<description>The maximum size of the MRAppMaster attempt container logs in KB.
0 disables the cap.
</description>
</property>
<property>
<name>yarn.app.mapreduce.task.container.log.backups</name>
<value>0</value>
<description>Number of backup files for task logs when using
ContainerRollingLogAppender (CRLA). See
org.apache.log4j.RollingFileAppender.maxBackupIndex. By default,
ContainerLogAppender (CLA) is used, and container logs are not rolled. CRLA
is enabled for tasks when both mapreduce.task.userlog.limit.kb and
yarn.app.mapreduce.task.container.log.backups are greater than zero.
</description>
</property>
<property>
<name>yarn.app.mapreduce.am.container.log.backups</name>
<value>0</value>
<description>Number of backup files for the ApplicationMaster logs when using
ContainerRollingLogAppender (CRLA). See
org.apache.log4j.RollingFileAppender.maxBackupIndex. By default,
ContainerLogAppender (CLA) is used, and container logs are not rolled. CRLA
is enabled for the ApplicationMaster when both
yarn.app.mapreduce.am.container.log.limit.kb and
yarn.app.mapreduce.am.container.log.backups are greater than zero.
</description>
</property>
<property>
<name>yarn.app.mapreduce.shuffle.log.separate</name>
<value>true</value>
<description>If enabled ('true') logging generated by the client-side shuffle
classes in a reducer will be written in a dedicated log file
'syslog.shuffle' instead of 'syslog'.
</description>
</property>
<property>
<name>yarn.app.mapreduce.shuffle.log.limit.kb</name>
<value>0</value>
<description>Maximum size of the syslog.shuffle file in kilobytes
(0 for no limit).
</description>
</property>
<property>
<name>yarn.app.mapreduce.shuffle.log.backups</name>
<value>0</value>
<description>If yarn.app.mapreduce.shuffle.log.limit.kb and
yarn.app.mapreduce.shuffle.log.backups are greater than zero
then a ContainerRollngLogAppender is used instead of ContainerLogAppender
for syslog.shuffle. See
org.apache.log4j.RollingFileAppender.maxBackupIndex
</description>
</property>
<property>
<name>mapreduce.job.maxtaskfailures.per.tracker</name>
<value>3</value>
<description>The number of task-failures on a node manager of a given job
after which new tasks of that job aren't assigned to it. It
MUST be less than mapreduce.map.maxattempts and
mapreduce.reduce.maxattempts otherwise the failed task will
never be tried on a different node.
</description>
</property>
<property>
<name>mapreduce.client.output.filter</name>
<value>FAILED</value>
<description>The filter for controlling the output of the task's userlogs sent
to the console of the JobClient.
The permissible options are: NONE, KILLED, FAILED, SUCCEEDED and
ALL.
</description>
</property>
<property>
<name>mapreduce.client.completion.pollinterval</name>
<value>5000</value>
<description>The interval (in milliseconds) between which the JobClient
polls the MapReduce ApplicationMaster for updates about job status. You may want to
set this to a lower value to make tests run faster on a single node system. Adjusting
this value in production may lead to unwanted client-server traffic.
</description>
</property>
<property>
<name>mapreduce.client.progressmonitor.pollinterval</name>
<value>1000</value>
<description>The interval (in milliseconds) between which the JobClient
reports status to the console and checks for job completion. You may want to set this
to a lower value to make tests run faster on a single node system. Adjusting
this value in production may lead to unwanted client-server traffic.
</description>
</property>
<property>
<name>mapreduce.client.libjars.wildcard</name>
<value>true</value>
<description>
Whether the libjars cache files should be localized using
a wildcarded directory instead of naming each archive independently.
Using wildcards reduces the space needed for storing the job
information in the case of a highly available resource manager
configuration.
This propery should only be set to false for specific
jobs which are highly sensitive to the details of the archive
localization. Having this property set to true will cause the archives
to all be localized to the same local cache location. If false, each
archive will be localized to its own local cache location. In both
cases a symbolic link will be created to every archive from the job's
working directory.
</description>
</property>
<property>
<name>mapreduce.task.profile</name>
<value>false</value>
<description>To set whether the system should collect profiler
information for some of the tasks in this job? The information is stored
in the user log directory. The value is "true" if task profiling
is enabled.</description>
</property>
<property>
<name>mapreduce.task.profile.maps</name>
<value>0-2</value>
<description> To set the ranges of map tasks to profile.
mapreduce.task.profile has to be set to true for the value to be accounted.
</description>
</property>
<property>
<name>mapreduce.task.profile.reduces</name>
<value>0-2</value>
<description> To set the ranges of reduce tasks to profile.
mapreduce.task.profile has to be set to true for the value to be accounted.
</description>
</property>
<property>
<name>mapreduce.task.profile.params</name>
<value>-agentlib:hprof=cpu=samples,heap=sites,force=n,thread=y,verbose=n,file=%s</value>
<description>JVM profiler parameters used to profile map and reduce task
attempts. This string may contain a single format specifier %s that will
be replaced by the path to profile.out in the task attempt log directory.
To specify different profiling options for map tasks and reduce tasks,
more specific parameters mapreduce.task.profile.map.params and
mapreduce.task.profile.reduce.params should be used.</description>
</property>
<property>
<name>mapreduce.task.profile.map.params</name>
<value>${mapreduce.task.profile.params}</value>
<description>Map-task-specific JVM profiler parameters. See
mapreduce.task.profile.params</description>
</property>
<property>
<name>mapreduce.task.profile.reduce.params</name>
<value>${mapreduce.task.profile.params}</value>
<description>Reduce-task-specific JVM profiler parameters. See
mapreduce.task.profile.params</description>
</property>
<property>
<name>mapreduce.task.skip.start.attempts</name>
<value>2</value>
<description> The number of Task attempts AFTER which skip mode
will be kicked off. When skip mode is kicked off, the
tasks reports the range of records which it will process
next, to the MR ApplicationMaster. So that on failures, the MR AM
knows which ones are possibly the bad records. On further executions,
those are skipped.
</description>
</property>
<property>
<name>mapreduce.job.skip.outdir</name>
<value></value>
<description> If no value is specified here, the skipped records are
written to the output directory at _logs/skip.
User can stop writing skipped records by giving the value "none".
</description>
</property>
<property>
<name>mapreduce.map.skip.maxrecords</name>
<value>0</value>
<description> The number of acceptable skip records surrounding the bad
record PER bad record in mapper. The number includes the bad record as well.
To turn the feature of detection/skipping of bad records off, set the
value to 0.
The framework tries to narrow down the skipped range by retrying
until this threshold is met OR all attempts get exhausted for this task.
Set the value to Long.MAX_VALUE to indicate that framework need not try to
narrow down. Whatever records(depends on application) get skipped are
acceptable.
</description>
</property>
<property>
<name>mapreduce.map.skip.proc-count.auto-incr</name>
<value>true</value>
<description>The flag which if set to true,
SkipBadRecords.COUNTER_MAP_PROCESSED_RECORDS is incremented by
MapRunner after invoking the map function. This value must be set
to false for applications which process the records asynchronously
or buffer the input records. For example streaming. In such cases
applications should increment this counter on their own.
</description>
</property>
<property>
<name>mapreduce.reduce.skip.maxgroups</name>
<value>0</value>
<description> The number of acceptable skip groups surrounding the bad
group PER bad group in reducer. The number includes the bad group as well.
To turn the feature of detection/skipping of bad groups off, set the
value to 0.
The framework tries to narrow down the skipped range by retrying
until this threshold is met OR all attempts get exhausted for this task.
Set the value to Long.MAX_VALUE to indicate that framework need not try to
narrow down. Whatever groups(depends on application) get skipped are
acceptable.
</description>
</property>
<property>
<name>mapreduce.reduce.skip.proc-count.auto-incr</name>
<value>true</value>
<description>The flag which if set to true.
SkipBadRecords.COUNTER_REDUCE_PROCESSED_GROUPS is incremented by framework
after invoking the reduce function. This value must be set to false for
applications which process the records asynchronously or buffer the input
records. For example streaming. In such cases applications should increment
this counter on their own.
</description>
</property>
<property>
<name>mapreduce.ifile.readahead</name>
<value>true</value>
<description>Configuration key to enable/disable IFile readahead.
</description>
</property>
<property>
<name>mapreduce.ifile.readahead.bytes</name>
<value>4194304</value>
<description>Configuration key to set the IFile readahead length in bytes.
</description>
</property>
<property>
<name>mapreduce.job.queuename</name>
<value>default</value>
<description> Queue to which a job is submitted. This must match one of the
queues defined in mapred-queues.xml for the system. Also, the ACL setup
for the queue must allow the current user to submit a job to the queue.
Before specifying a queue, ensure that the system is configured with
the queue, and access is allowed for submitting jobs to the queue.
</description>
</property>
<property>
<name>mapreduce.job.tags</name>
<value></value>
<description> Tags for the job that will be passed to YARN at submission
time. Queries to YARN for applications can filter on these tags.
If these tags are intended to be used with The YARN Timeline Service v.2,
prefix them with the appropriate tag names for flow name, flow version and
flow run id. Example:
timeline_flow_name_tag:foo,
timeline_flow_version_tag:3df8b0d6100530080d2e0decf9e528e57c42a90a,
timeline_flow_run_id_tag:1465246348599
</description>
</property>
<property>
<name>mapreduce.cluster.local.dir</name>
<value>${hadoop.tmp.dir}/mapred/local</value>
<description>
The local directory where MapReduce stores intermediate
data files. May be a comma-separated list of
directories on different devices in order to spread disk i/o.
Directories that do not exist are ignored.
</description>
</property>
<property>
<name>mapreduce.cluster.acls.enabled</name>
<value>false</value>
<description> Specifies whether ACLs should be checked
for authorization of users for doing various queue and job level operations.
ACLs are disabled by default. If enabled, access control checks are made by
MapReduce ApplicationMaster when requests are made by users for queue
operations like submit job to a queue and kill a job in the queue and job
operations like viewing the job-details (See mapreduce.job.acl-view-job)
or for modifying the job (See mapreduce.job.acl-modify-job) using
Map/Reduce APIs, RPCs or via the console and web user interfaces.
For enabling this flag, set to true in mapred-site.xml file of all
MapReduce clients (MR job submitting nodes).
</description>
</property>
<property>
<name>mapreduce.job.acl-modify-job</name>
<value> </value>
<description> Job specific access-control list for 'modifying' the job. It
is only used if authorization is enabled in Map/Reduce by setting the
configuration property mapreduce.cluster.acls.enabled to true.
This specifies the list of users and/or groups who can do modification
operations on the job. For specifying a list of users and groups the
format to use is "user1,user2 group1,group". If set to '*', it allows all
users/groups to modify this job. If set to ' '(i.e. space), it allows
none. This configuration is used to guard all the modifications with respect
to this job and takes care of all the following operations:
o killing this job
o killing a task of this job, failing a task of this job
o setting the priority of this job
Each of these operations are also protected by the per-queue level ACL
"acl-administer-jobs" configured via mapred-queues.xml. So a caller should
have the authorization to satisfy either the queue-level ACL or the
job-level ACL.
Irrespective of this ACL configuration, (a) job-owner, (b) the user who
started the cluster, (c) members of an admin configured supergroup
configured via mapreduce.cluster.permissions.supergroup and (d) queue
administrators of the queue to which this job was submitted to configured
via acl-administer-jobs for the specific queue in mapred-queues.xml can
do all the modification operations on a job.
By default, nobody else besides job-owner, the user who started the cluster,
members of supergroup and queue administrators can perform modification
operations on a job.
</description>
</property>
<property>
<name>mapreduce.job.acl-view-job</name>
<value> </value>
<description> Job specific access-control list for 'viewing' the job. It is
only used if authorization is enabled in Map/Reduce by setting the
configuration property mapreduce.cluster.acls.enabled to true.
This specifies the list of users and/or groups who can view private details
about the job. For specifying a list of users and groups the
format to use is "user1,user2 group1,group". If set to '*', it allows all
users/groups to modify this job. If set to ' '(i.e. space), it allows
none. This configuration is used to guard some of the job-views and at
present only protects APIs that can return possibly sensitive information
of the job-owner like
o job-level counters
o task-level counters
o tasks' diagnostic information
o task-logs displayed on the HistoryServer's web-UI and
o job.xml showed by the HistoryServer's web-UI
Every other piece of information of jobs is still accessible by any other
user, for e.g., JobStatus, JobProfile, list of jobs in the queue, etc.
Irrespective of this ACL configuration, (a) job-owner, (b) the user who
started the cluster, (c) members of an admin configured supergroup
configured via mapreduce.cluster.permissions.supergroup and (d) queue
administrators of the queue to which this job was submitted to configured
via acl-administer-jobs for the specific queue in mapred-queues.xml can
do all the view operations on a job.
By default, nobody else besides job-owner, the user who started the
cluster, memebers of supergroup and queue administrators can perform
view operations on a job.
</description>
</property>
<property>
<name>mapreduce.job.finish-when-all-reducers-done</name>
<value>true</value>
<description>Specifies whether the job should complete once all reducers
have finished, regardless of whether there are still running mappers.
</description>
</property>
<property>
<name>mapreduce.job.token.tracking.ids.enabled</name>
<value>false</value>
<description>Whether to write tracking ids of tokens to
job-conf. When true, the configuration property
"mapreduce.job.token.tracking.ids" is set to the token-tracking-ids of
the job</description>
</property>
<property>
<name>mapreduce.job.token.tracking.ids</name>
<value></value>
<description>When mapreduce.job.token.tracking.ids.enabled is
set to true, this is set by the framework to the
token-tracking-ids used by the job.</description>
</property>
<property>
<name>mapreduce.task.merge.progress.records</name>
<value>10000</value>
<description> The number of records to process during merge before
sending a progress notification to the MR ApplicationMaster.
</description>
</property>
<property>
<name>mapreduce.task.combine.progress.records</name>
<value>10000</value>
<description> The number of records to process during combine output collection
before sending a progress notification.
</description>
</property>
<property>
<name>mapreduce.job.reduce.slowstart.completedmaps</name>
<value>0.05</value>
<description>Fraction of the number of maps in the job which should be
complete before reduces are scheduled for the job.
</description>
</property>
<property>
<name>mapreduce.job.complete.cancel.delegation.tokens</name>
<value>true</value>
<description> if false - do not unregister/cancel delegation tokens from
renewal, because same tokens may be used by spawned jobs
</description>
</property>
<property>
<name>mapreduce.shuffle.port</name>
<value>13562</value>
<description>Default port that the ShuffleHandler will run on. ShuffleHandler
is a service run at the NodeManager to facilitate transfers of intermediate
Map outputs to requesting Reducers.
</description>
</property>
<property>
<name>mapreduce.job.reduce.shuffle.consumer.plugin.class</name>
<value>org.apache.hadoop.mapreduce.task.reduce.Shuffle</value>
<description>
Name of the class whose instance will be used
to send shuffle requests by reducetasks of this job.
The class must be an instance of org.apache.hadoop.mapred.ShuffleConsumerPlugin.
</description>
</property>
<!-- MR YARN Application properties -->
<property>
<name>mapreduce.job.node-label-expression</name>
<description>All the containers of the Map Reduce job will be run with this
node label expression. If the node-label-expression for job is not set, then
it will use queue's default-node-label-expression for all job's containers.
</description>
</property>
<property>
<name>mapreduce.job.am.node-label-expression</name>
<description>This is node-label configuration for Map Reduce Application Master
container. If not configured it will make use of
mapreduce.job.node-label-expression and if job's node-label expression is not
configured then it will use queue's default-node-label-expression.
</description>
</property>
<property>
<name>mapreduce.map.node-label-expression</name>
<description>This is node-label configuration for Map task containers. If not
configured it will use mapreduce.job.node-label-expression and if job's
node-label expression is not configured then it will use queue's
default-node-label-expression.
</description>
</property>
<property>
<name>mapreduce.reduce.node-label-expression</name>
<description>This is node-label configuration for Reduce task containers. If
not configured it will use mapreduce.job.node-label-expression and if job's
node-label expression is not configured then it will use queue's
default-node-label-expression.
</description>
</property>
<property>
<name>mapreduce.job.counters.limit</name>
<value>120</value>
<description>Limit on the number of user counters allowed per job.
</description>
</property>
<property>
<name>mapreduce.framework.name</name>
<value>local</value>
<description>The runtime framework for executing MapReduce jobs.
Can be one of local, classic or yarn.
</description>
</property>
<property>
<name>yarn.app.mapreduce.am.staging-dir</name>
<value>/tmp/hadoop-yarn/staging</value>
<description>The staging dir used while submitting jobs.
</description>
</property>
<property>
<name>yarn.app.mapreduce.am.staging-dir.erasurecoding.enabled</name>
<value>false</value>
<description>Whether Erasure Coding should be enabled for
files that are copied to the MR staging area. This is a job-level
setting.
</description>
</property>
<property>
<name>mapreduce.am.max-attempts</name>
<value>2</value>
<description>The maximum number of application attempts. It is a
application-specific setting. It should not be larger than the global number
set by resourcemanager. Otherwise, it will be override. The default number is
set to 2, to allow at least one retry for AM.</description>
</property>
<!-- Job Notification Configuration -->
<property>
<name>mapreduce.job.end-notification.url</name>
<!--<value>http://localhost:8080/jobstatus.php?jobId=$jobId&jobStatus=$jobStatus</value>-->
<description>Indicates url which will be called on completion of job to inform
end status of job.
User can give at most 2 variables with URI : $jobId and $jobStatus.
If they are present in URI, then they will be replaced by their
respective values.
</description>
</property>
<property>
<name>mapreduce.job.end-notification.retry.attempts</name>
<value>0</value>
<description>The number of times the submitter of the job wants to retry job
end notification if it fails. This is capped by
mapreduce.job.end-notification.max.attempts</description>
</property>
<property>
<name>mapreduce.job.end-notification.retry.interval</name>
<value>1000</value>
<description>The number of milliseconds the submitter of the job wants to
wait before job end notification is retried if it fails. This is capped by
mapreduce.job.end-notification.max.retry.interval</description>
</property>
<property>
<name>mapreduce.job.end-notification.max.attempts</name>
<value>5</value>
<final>true</final>
<description>The maximum number of times a URL will be read for providing job
end notification. Cluster administrators can set this to limit how long
after end of a job, the Application Master waits before exiting. Must be
marked as final to prevent users from overriding this.
</description>
</property>
<property>
<name>mapreduce.job.log4j-properties-file</name>
<value></value>
<description>Used to override the default settings of log4j in container-log4j.properties
for NodeManager. Like container-log4j.properties, it requires certain
framework appenders properly defined in this overriden file. The file on the
path will be added to distributed cache and classpath. If no-scheme is given
in the path, it defaults to point to a log4j file on the local FS.
</description>
</property>
<property>
<name>mapreduce.job.end-notification.max.retry.interval</name>
<value>5000</value>
<final>true</final>
<description>The maximum amount of time (in milliseconds) to wait before
retrying job end notification. Cluster administrators can set this to
limit how long the Application Master waits before exiting. Must be marked
as final to prevent users from overriding this.</description>
</property>
<property>
<name>yarn.app.mapreduce.am.env</name>
<value></value>
<description>User added environment variables for the MR App Master
processes. Example :
1) A=foo This will set the env variable A to foo
2) B=$B:c This is inherit tasktracker's B env variable.
</description>
</property>
<property>
<name>yarn.app.mapreduce.am.admin.user.env</name>
<value></value>
<description> Environment variables for the MR App Master
processes for admin purposes. These values are set first and can be
overridden by the user env (yarn.app.mapreduce.am.env) Example :
1) A=foo This will set the env variable A to foo
2) B=$B:c This is inherit app master's B env variable.
</description>
</property>
<property>
<name>yarn.app.mapreduce.am.command-opts</name>
<value>-Xmx1024m</value>
<description>Java opts for the MR App Master processes.
The following symbol, if present, will be interpolated: @taskid@ is replaced
by current TaskID. Any other occurrences of '@' will go unchanged.
For example, to enable verbose gc logging to a file named for the taskid in
/tmp and to set the heap maximum to be a gigabyte, pass a 'value' of:
-Xmx1024m -verbose:gc -Xloggc:/tmp/@taskid@.gc
Usage of -Djava.library.path can cause programs to no longer function if
hadoop native libraries are used. These values should instead be set as part
of LD_LIBRARY_PATH in the map / reduce JVM env using the mapreduce.map.env and
mapreduce.reduce.env config settings.
</description>
</property>
<property>
<name>yarn.app.mapreduce.am.admin-command-opts</name>
<value></value>
<description>Java opts for the MR App Master processes for admin purposes.
It will appears before the opts set by yarn.app.mapreduce.am.command-opts and
thus its options can be overridden user.
Usage of -Djava.library.path can cause programs to no longer function if
hadoop native libraries are used. These values should instead be set as part
of LD_LIBRARY_PATH in the map / reduce JVM env using the mapreduce.map.env and
mapreduce.reduce.env config settings.
</description>
</property>
<property>
<name>yarn.app.mapreduce.am.job.task.listener.thread-count</name>
<value>30</value>
<description>The number of threads used to handle RPC calls in the
MR AppMaster from remote tasks</description>
</property>
<property>
<name>yarn.app.mapreduce.am.job.client.port-range</name>
<value></value>
<description>Range of ports that the MapReduce AM can use when binding.
Leave blank if you want all possible ports.
For example 50000-50050,50100-50200</description>
</property>
<property>
<name>yarn.app.mapreduce.am.webapp.port-range</name>
<value></value>
<description>Range of ports that the MapReduce AM can use for its webapp when binding.
Leave blank if you want all possible ports.
For example 50000-50050,50100-50200</description>
</property>
<property>
<name>yarn.app.mapreduce.am.job.committer.cancel-timeout</name>
<value>60000</value>
<description>The amount of time in milliseconds to wait for the output
committer to cancel an operation if the job is killed</description>
</property>
<property>
<name>yarn.app.mapreduce.am.job.committer.commit-window</name>
<value>10000</value>
<description>Defines a time window in milliseconds for output commit
operations. If contact with the RM has occurred within this window then
commits are allowed, otherwise the AM will not allow output commits until
contact with the RM has been re-established.</description>
</property>
<property>
<name>mapreduce.fileoutputcommitter.algorithm.version</name>
<value>2</value>
<description>The file output committer algorithm version
valid algorithm version number: 1 or 2
default to 2, which is the original algorithm
In algorithm version 1,
1. commitTask will rename directory
$joboutput/_temporary/$appAttemptID/_temporary/$taskAttemptID/
to
$joboutput/_temporary/$appAttemptID/$taskID/
2. recoverTask will also do a rename
$joboutput/_temporary/$appAttemptID/$taskID/
to
$joboutput/_temporary/($appAttemptID + 1)/$taskID/
3. commitJob will merge every task output file in
$joboutput/_temporary/$appAttemptID/$taskID/
to
$joboutput/, then it will delete $joboutput/_temporary/
and write $joboutput/_SUCCESS
It has a performance regression, which is discussed in MAPREDUCE-4815.
If a job generates many files to commit then the commitJob
method call at the end of the job can take minutes.
the commit is single-threaded and waits until all
tasks have completed before commencing.
algorithm version 2 will change the behavior of commitTask,
recoverTask, and commitJob.
1. commitTask will rename all files in
$joboutput/_temporary/$appAttemptID/_temporary/$taskAttemptID/
to $joboutput/
2. recoverTask actually doesn't require to do anything, but for
upgrade from version 1 to version 2 case, it will check if there
are any files in
$joboutput/_temporary/($appAttemptID - 1)/$taskID/
and rename them to $joboutput/
3. commitJob can simply delete $joboutput/_temporary and write
$joboutput/_SUCCESS
This algorithm will reduce the output commit time for
large jobs by having the tasks commit directly to the final
output directory as they were completing and commitJob had
very little to do.
</description>
</property>
<property>
<name>mapreduce.fileoutputcommitter.task.cleanup.enabled</name>
<value>false</value>
<description>Whether tasks should delete their task temporary directories. This is purely an
optimization for filesystems without O(1) recursive delete, as commitJob will recursively delete
the entire job temporary directory. HDFS has O(1) recursive delete, so this parameter is left
false by default. Users of object stores, for example, may want to set this to true.
Note: this is only used if mapreduce.fileoutputcommitter.algorithm.version=2</description>
</property>
<property>
<name>yarn.app.mapreduce.am.scheduler.heartbeat.interval-ms</name>
<value>1000</value>
<description>The interval in ms at which the MR AppMaster should send
heartbeats to the ResourceManager</description>
</property>
<property>
<name>yarn.app.mapreduce.client-am.ipc.max-retries</name>
<value>3</value>
<description>The number of client retries to the AM - before reconnecting
to the RM to fetch Application Status.</description>
</property>
<property>
<name>yarn.app.mapreduce.client-am.ipc.max-retries-on-timeouts</name>
<value>3</value>
<description>The number of client retries on socket timeouts to the AM - before
reconnecting to the RM to fetch Application Status.</description>
</property>
<property>
<name>yarn.app.mapreduce.client.max-retries</name>
<value>3</value>
<description>The number of client retries to the RM/HS before
throwing exception. This is a layer above the ipc.</description>
</property>
<property>
<name>yarn.app.mapreduce.am.resource.mb</name>
<value>1536</value>
<description>The amount of memory the MR AppMaster needs.</description>
</property>
<property>
<name>yarn.app.mapreduce.am.resource.cpu-vcores</name>
<value>1</value>
<description>
The number of virtual CPU cores the MR AppMaster needs.
</description>
</property>
<property>
<name>yarn.app.mapreduce.am.hard-kill-timeout-ms</name>
<value>10000</value>
<description>
Number of milliseconds to wait before the job client kills the application.
</description>
</property>
<property>
<name>yarn.app.mapreduce.client.job.max-retries</name>
<value>3</value>
<description>The number of retries the client will make for getJob and
dependent calls.
This is needed for non-HDFS DFS where additional, high level
retries are required to avoid spurious failures during the getJob call.
30 is a good value for WASB</description>
</property>
<property>
<name>yarn.app.mapreduce.client.job.retry-interval</name>
<value>2000</value>
<description>The delay between getJob retries in ms for retries configured
with yarn.app.mapreduce.client.job.max-retries.</description>
</property>
<property>
<description>CLASSPATH for MR applications. A comma-separated list
of CLASSPATH entries. If mapreduce.application.framework is set then this
must specify the appropriate classpath for that archive, and the name of
the archive must be present in the classpath.
If mapreduce.app-submission.cross-platform is false, platform-specific
environment vairable expansion syntax would be used to construct the default
CLASSPATH entries.
For Linux:
$HADOOP_MAPRED_HOME/share/hadoop/mapreduce/*,
$HADOOP_MAPRED_HOME/share/hadoop/mapreduce/lib/*.
For Windows:
%HADOOP_MAPRED_HOME%/share/hadoop/mapreduce/*,
%HADOOP_MAPRED_HOME%/share/hadoop/mapreduce/lib/*.
If mapreduce.app-submission.cross-platform is true, platform-agnostic default
CLASSPATH for MR applications would be used:
{{HADOOP_MAPRED_HOME}}/share/hadoop/mapreduce/*,
{{HADOOP_MAPRED_HOME}}/share/hadoop/mapreduce/lib/*
Parameter expansion marker will be replaced by NodeManager on container
launch based on the underlying OS accordingly.
</description>
<name>mapreduce.application.classpath</name>
<value></value>
</property>
<property>
<description>If enabled, user can submit an application cross-platform
i.e. submit an application from a Windows client to a Linux/Unix server or
vice versa.
</description>
<name>mapreduce.app-submission.cross-platform</name>
<value>false</value>
</property>
<property>
<description>Path to the MapReduce framework archive. If set, the framework
archive will automatically be distributed along with the job, and this
path would normally reside in a public location in an HDFS filesystem. As
with distributed cache files, this can be a URL with a fragment specifying
the alias to use for the archive name. For example,
hdfs:/mapred/framework/hadoop-mapreduce-2.1.1.tar.gz#mrframework would
alias the localized archive as "mrframework".
Note that mapreduce.application.classpath must include the appropriate
classpath for the specified framework. The base name of the archive, or
alias of the archive if an alias is used, must appear in the specified
classpath.
</description>
<name>mapreduce.application.framework.path</name>
<value></value>
</property>
<property>
<name>mapreduce.job.classloader</name>
<value>false</value>
<description>Whether to use a separate (isolated) classloader for
user classes in the task JVM.</description>
</property>
<property>
<name>mapreduce.job.classloader.system.classes</name>
<value></value>
<description>Used to override the default definition of the system classes for
the job classloader. The system classes are a comma-separated list of
patterns that indicate whether to load a class from the system classpath,
instead from the user-supplied JARs, when mapreduce.job.classloader is
enabled.
A positive pattern is defined as:
1. A single class name 'C' that matches 'C' and transitively all nested
classes 'C$*' defined in C;
2. A package name ending with a '.' (e.g., "com.example.") that matches
all classes from that package.
A negative pattern is defined by a '-' in front of a positive pattern
(e.g., "-com.example.").
A class is considered a system class if and only if it matches one of the
positive patterns and none of the negative ones. More formally:
A class is a member of the inclusion set I if it matches one of the positive
patterns. A class is a member of the exclusion set E if it matches one of
the negative patterns. The set of system classes S = I \ E.
</description>
</property>
<property>
<name>mapreduce.jvm.system-properties-to-log</name>
<value>os.name,os.version,java.home,java.runtime.version,java.vendor,java.version,java.vm.name,java.class.path,java.io.tmpdir,user.dir,user.name</value>
<description>Comma-delimited list of system properties to log on mapreduce JVM start</description>
</property>
<!-- jobhistory properties -->
<property>
<name>mapreduce.jobhistory.address</name>
<value>0.0.0.0:10020</value>
<description>MapReduce JobHistory Server IPC host:port</description>
</property>
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>0.0.0.0:19888</value>
<description>MapReduce JobHistory Server Web UI host:port</description>
</property>
<property>
<name>mapreduce.jobhistory.webapp.https.address</name>
<value>0.0.0.0:19890</value>
<description>
The https address the MapReduce JobHistory Server WebApp is on.
</description>
</property>
<property>
<name>mapreduce.jobhistory.keytab</name>
<description>
Location of the kerberos keytab file for the MapReduce
JobHistory Server.
</description>
<value>/etc/security/keytab/jhs.service.keytab</value>
</property>
<property>
<name>mapreduce.jobhistory.principal</name>
<description>
Kerberos principal name for the MapReduce JobHistory Server.
</description>
<value>jhs/_HOST@REALM.TLD</value>
</property>
<property>
<name>mapreduce.jobhistory.intermediate-done-dir</name>
<value>${yarn.app.mapreduce.am.staging-dir}/history/done_intermediate</value>
<description></description>
</property>
<property>
<name>mapreduce.jobhistory.intermediate-user-done-dir.permissions</name>
<value>770</value>
<description>The permissions of the user directories in
${mapreduce.jobhistory.intermediate-done-dir}. The user and the group
permission must be 7, this is enforced.
</description>
</property>
<property>
<name>mapreduce.jobhistory.always-scan-user-dir</name>
<value>false</value>
<description>Some Cloud FileSystems do not currently update the
modification time of directories. To support these filesystems, this
configuration value should be set to 'true'.
</description>
</property>
<property>
<name>mapreduce.jobhistory.done-dir</name>
<value>${yarn.app.mapreduce.am.staging-dir}/history/done</value>
<description></description>
</property>
<property>
<name>mapreduce.jobhistory.cleaner.enable</name>
<value>true</value>
<description></description>
</property>
<property>
<name>mapreduce.jobhistory.cleaner.interval-ms</name>
<value>86400000</value>
<description> How often the job history cleaner checks for files to delete,
in milliseconds. Defaults to 86400000 (one day). Files are only deleted if
they are older than mapreduce.jobhistory.max-age-ms.
</description>
</property>
<property>
<name>mapreduce.jobhistory.max-age-ms</name>
<value>604800000</value>
<description> Job history files older than this many milliseconds will
be deleted when the history cleaner runs. Defaults to 604800000 (1 week).
</description>
</property>
<property>
<name>mapreduce.jobhistory.client.thread-count</name>
<value>10</value>
<description>The number of threads to handle client API requests</description>
</property>
<property>
<name>mapreduce.jobhistory.datestring.cache.size</name>
<value>200000</value>
<description>Size of the date string cache. Effects the number of directories
which will be scanned to find a job.</description>
</property>
<property>
<name>mapreduce.jobhistory.joblist.cache.size</name>
<value>20000</value>
<description>Size of the job list cache</description>
</property>
<property>
<name>mapreduce.jobhistory.loadedjobs.cache.size</name>
<value>5</value>
<description>Size of the loaded job cache. This property is ignored if
the property mapreduce.jobhistory.loadedtasks.cache.size is set to a
positive value.
</description>
</property>
<property>
<name>mapreduce.jobhistory.loadedtasks.cache.size</name>
<value></value>
<description>Change the job history cache limit to be set in terms
of total task count. If the total number of tasks loaded exceeds
this value, then the job cache will be shrunk down until it is
under this limit (minimum 1 job in cache). If this value is empty
or nonpositive then the cache reverts to using the property
mapreduce.jobhistory.loadedjobs.cache.size as a job cache size.
Two recommendations for the mapreduce.jobhistory.loadedtasks.cache.size
property:
1) For every 100k of cache size, set the heap size of the Job History
Server to 1.2GB. For example,
mapreduce.jobhistory.loadedtasks.cache.size=500000, heap size=6GB.
2) Make sure that the cache size is larger than the number of tasks
required for the largest job run on the cluster. It might be a good
idea to set the value slightly higher (say, 20%) in order to allow
for job size growth.
</description>
</property>
<property>
<name>mapreduce.jobhistory.move.interval-ms</name>
<value>180000</value>
<description>Scan for history files to more from intermediate done dir to done
dir at this frequency.
</description>
</property>
<property>
<name>mapreduce.jobhistory.move.thread-count</name>
<value>3</value>
<description>The number of threads used to move files.</description>
</property>
<property>
<name>mapreduce.jobhistory.store.class</name>
<value></value>
<description>The HistoryStorage class to use to cache history data.</description>
</property>
<property>
<name>mapreduce.jobhistory.minicluster.fixed.ports</name>
<value>false</value>
<description>Whether to use fixed ports with the minicluster</description>
</property>
<property>
<name>mapreduce.jobhistory.admin.address</name>
<value>0.0.0.0:10033</value>
<description>The address of the History server admin interface.</description>
</property>
<property>
<name>mapreduce.jobhistory.admin.acl</name>
<value>*</value>
<description>ACL of who can be admin of the History server.</description>
</property>
<property>
<name>mapreduce.jobhistory.recovery.enable</name>
<value>false</value>
<description>Enable the history server to store server state and recover
server state upon startup. If enabled then
mapreduce.jobhistory.recovery.store.class must be specified.</description>
</property>
<property>
<name>mapreduce.jobhistory.recovery.store.class</name>
<value>org.apache.hadoop.mapreduce.v2.hs.HistoryServerFileSystemStateStoreService</value>
<description>The HistoryServerStateStoreService class to store history server
state for recovery.</description>
</property>
<property>
<name>mapreduce.jobhistory.recovery.store.fs.uri</name>
<value>${hadoop.tmp.dir}/mapred/history/recoverystore</value>
<!--value>hdfs://localhost:9000/mapred/history/recoverystore</value-->
<description>The URI where history server state will be stored if
HistoryServerFileSystemStateStoreService is configured as the recovery
storage class.</description>
</property>
<property>
<name>mapreduce.jobhistory.recovery.store.leveldb.path</name>
<value>${hadoop.tmp.dir}/mapred/history/recoverystore</value>
<description>The URI where history server state will be stored if
HistoryServerLeveldbSystemStateStoreService is configured as the recovery
storage class.</description>
</property>
<property>
<name>mapreduce.jobhistory.http.policy</name>
<value>HTTP_ONLY</value>
<description>
This configures the HTTP endpoint for JobHistoryServer web UI.
The following values are supported:
- HTTP_ONLY : Service is provided only on http
- HTTPS_ONLY : Service is provided only on https
</description>
</property>
<property>
<name>mapreduce.jobhistory.jobname.limit</name>
<value>50</value>
<description>
Number of characters allowed for job name in Job History Server web page.
</description>
</property>
<property>
<description>
File format the AM will use when generating the .jhist file. Valid
values are "json" for text output and "binary" for faster parsing.
</description>
<name>mapreduce.jobhistory.jhist.format</name>
<value>binary</value>
</property>
<property>
<name>mapreduce.job.heap.memory-mb.ratio</name>
<value>0.8</value>
<description>The ratio of heap-size to container-size. If no -Xmx is
specified, it is calculated as
(mapreduce.{map|reduce}.memory.mb * mapreduce.heap.memory-mb.ratio).
If -Xmx is specified but not mapreduce.{map|reduce}.memory.mb, it is
calculated as (heapSize / mapreduce.heap.memory-mb.ratio).
</description>
</property>
<property>
<name>yarn.app.mapreduce.am.containerlauncher.threadpool-initial-size</name>
<value>10</value>
<description>The initial size of thread pool to launch containers in the
app master.
</description>
</property>
<property>
<name>mapreduce.task.exit.timeout</name>
<value>60000</value>
<description>The number of milliseconds before a task will be
terminated if it stays in finishing state for too long.
After a task attempt completes from TaskUmbilicalProtocol's point of view,
it will be transitioned to finishing state. That will give a chance for the
task to exit by itself.
</description>
</property>
<property>
<name>mapreduce.task.exit.timeout.check-interval-ms</name>
<value>20000</value>
<description>The interval in milliseconds between which the MR framework
checks if task attempts stay in finishing state for too long.
</description>
</property>
<property>
<name>mapreduce.job.encrypted-intermediate-data</name>
<value>false</value>
<description>Encrypt intermediate MapReduce spill files or not
default is false</description>
</property>
<property>
<name>mapreduce.job.encrypted-intermediate-data-key-size-bits</name>
<value>128</value>
<description>Mapreduce encrypt data key size default is 128</description>
</property>
<property>
<name>mapreduce.job.encrypted-intermediate-data.buffer.kb</name>
<value>128</value>
<description>Buffer size for intermediate encrypt data in kb
default is 128</description>
</property>
<property>
<name>mapreduce.task.local-fs.write-limit.bytes</name>
<value>-1</value>
<description>Limit on the byte written to the local file system by each task.
This limit only applies to writes that go through the Hadoop filesystem APIs
within the task process (i.e.: writes that will update the local filesystem's
BYTES_WRITTEN counter). It does not cover other writes such as logging,
sideband writes from subprocesses (e.g.: streaming jobs), etc.
Negative values disable the limit.
default is -1</description>
</property>
<property>
<description>
Enable the CSRF filter for the job history web app
</description>
<name>mapreduce.jobhistory.webapp.rest-csrf.enabled</name>
<value>false</value>
</property>
<property>
<description>
Optional parameter that indicates the custom header name to use for CSRF
protection.
</description>
<name>mapreduce.jobhistory.webapp.rest-csrf.custom-header</name>
<value>X-XSRF-Header</value>
</property>
<property>
<description>
Optional parameter that indicates the list of HTTP methods that do not
require CSRF protection
</description>
<name>mapreduce.jobhistory.webapp.rest-csrf.methods-to-ignore</name>
<value>GET,OPTIONS,HEAD</value>
</property>
<property>
<name>mapreduce.job.cache.limit.max-resources</name>
<value>0</value>
<description>The maximum number of resources a map reduce job is allowed to
submit for localization via files, libjars, archives, and jobjar command
line arguments and through the distributed cache. If set to 0 the limit is
ignored.
</description>
</property>
<property>
<name>mapreduce.job.cache.limit.max-resources-mb</name>
<value>0</value>
<description>The maximum size (in MB) a map reduce job is allowed to submit
for localization via files, libjars, archives, and jobjar command line
arguments and through the distributed cache. If set to 0 the limit is
ignored.
</description>
</property>
<property>
<name>mapreduce.job.cache.limit.max-single-resource-mb</name>
<value>0</value>
<description>The maximum size (in MB) of a single resource a map reduce job
is allow to submit for localization via files, libjars, archives, and
jobjar command line arguments and through the distributed cache. If set to
0 the limit is ignored.
</description>
</property>
<property>
<description>
Value of the xframe-options
</description>
<name>mapreduce.jobhistory.webapp.xfs-filter.xframe-options</name>
<value>SAMEORIGIN</value>
</property>
<property>
<description>
The maximum number of tasks that a job can have so that the Job History
Server will fully parse its associated job history file and load it into
memory. A value of -1 (default) will allow all jobs to be loaded.
</description>
<name>mapreduce.jobhistory.loadedjob.tasks.max</name>
<value>-1</value>
</property>
<property>
<description>
The list of job configuration properties whose value will be redacted.
</description>
<name>mapreduce.job.redacted-properties</name>
<value></value>
</property>
<property>
<description>
This configuration is a regex expression. The list of configurations that
match the regex expression will be sent to RM. RM will use these
configurations for renewing tokens.
This configuration is added for below scenario: User needs to run distcp
jobs across two clusters, but the RM does not have necessary hdfs
configurations to connect to the remote hdfs cluster. Hence, user relies on
this config to send the configurations to RM and RM uses these
configurations to renew tokens.
For example the following regex expression indicates the minimum required
configs for RM to connect to a remote hdfs cluster:
dfs.nameservices|^dfs.namenode.rpc-address.*$|^dfs.ha.namenodes.*$|^dfs.client.failover.proxy.provider.*$|dfs.namenode.kerberos.principal
</description>
<name>mapreduce.job.send-token-conf</name>
<value></value>
</property>
<property>
<description>
The name of an output committer factory for MRv2 FileOutputFormat to use
for committing work. If set, overrides any per-filesystem committer
defined for the destination filesystem.
</description>
<name>mapreduce.outputcommitter.factory.class</name>
<value></value>
</property>
<property>
<name>mapreduce.outputcommitter.factory.scheme.s3a</name>
<value>org.apache.hadoop.fs.s3a.commit.S3ACommitterFactory</value>
<description>
The committer factory to use when writing data to S3A filesystems.
If mapreduce.outputcommitter.factory.class is set, it will
override this property.
</description>
</property>
</configuration>
03-20
1万+
1万+
06-28
1183
1183
09-13
6306
6306
07-03
4404
4404
05-24
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
