|
|
@@ -22,101 +22,93 @@
|
|
|
|
|
|
<configuration xmlns:xi="http://www.w3.org/2001/XInclude">
|
|
|
|
|
|
-<!-- i/o properties -->
|
|
|
+ <!-- i/o properties -->
|
|
|
|
|
|
<property>
|
|
|
<name>mapreduce.task.io.sort.mb</name>
|
|
|
<value>100</value>
|
|
|
- <description>No description</description>
|
|
|
+ <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>0.1</value>
|
|
|
- <description>No description</description>
|
|
|
+ <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.task.io.sort.factor</name>
|
|
|
<value>100</value>
|
|
|
- <description>No description</description>
|
|
|
- </property>
|
|
|
-
|
|
|
-<!-- map/reduce properties -->
|
|
|
-
|
|
|
- <property>
|
|
|
- <name>mapreduce.jobtracker.system.dir</name>
|
|
|
- <value></value>
|
|
|
- <description>No description</description>
|
|
|
- <final>true</final>
|
|
|
- </property>
|
|
|
-
|
|
|
- <property>
|
|
|
- <!-- cluster specific -->
|
|
|
- <name>mapreduce.cluster.local.dir</name>
|
|
|
- <value></value>
|
|
|
- <description>No description</description>
|
|
|
- <final>true</final>
|
|
|
+ <description>
|
|
|
+ The number of streams to merge at once while sorting files.
|
|
|
+ This determines the number of open file handles.
|
|
|
+ </description>
|
|
|
</property>
|
|
|
|
|
|
+ <!-- map/reduce properties -->
|
|
|
<property>
|
|
|
<name>mapreduce.reduce.shuffle.parallelcopies</name>
|
|
|
<value>30</value>
|
|
|
- <description>No description</description>
|
|
|
- </property>
|
|
|
-
|
|
|
- <property>
|
|
|
- <name>mapreduce.tasktracker.map.tasks.maximum</name>
|
|
|
- <value></value>
|
|
|
- <description>No description</description>
|
|
|
+ <description>
|
|
|
+ The default number of parallel transfers run by reduce during
|
|
|
+ the copy(shuffle) phase.
|
|
|
+ </description>
|
|
|
</property>
|
|
|
|
|
|
<property>
|
|
|
<name>mapreduce.map.speculative</name>
|
|
|
<value>false</value>
|
|
|
- <description>If true, then multiple instances of some map tasks
|
|
|
- may be executed in parallel.</description>
|
|
|
+ <description>
|
|
|
+ If true, then multiple instances of some map tasks
|
|
|
+ may be executed in parallel.
|
|
|
+ </description>
|
|
|
</property>
|
|
|
|
|
|
<property>
|
|
|
<name>mapreduce.reduce.speculative</name>
|
|
|
<value>false</value>
|
|
|
- <description>If true, then multiple instances of some reduce tasks
|
|
|
- may be executed in parallel.</description>
|
|
|
+ <description>
|
|
|
+ If true, then multiple instances of some reduce tasks may be
|
|
|
+ executed in parallel.
|
|
|
+ </description>
|
|
|
</property>
|
|
|
|
|
|
<property>
|
|
|
<name>mapreduce.job.reduce.slowstart.completedmaps</name>
|
|
|
<value>0.05</value>
|
|
|
- </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>
|
|
|
+ <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.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>
|
|
|
+ <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>0.7</value>
|
|
|
- <description>The percentage of memory to be allocated from the maximum heap
|
|
|
- size to storing map outputs during the shuffle.
|
|
|
- </description>
|
|
|
+ <description>
|
|
|
+ The percentage of memory to be allocated from the maximum heap
|
|
|
+ size to storing map outputs during the shuffle.
|
|
|
+ </description>
|
|
|
</property>
|
|
|
|
|
|
<property>
|
|
|
@@ -127,144 +119,254 @@
|
|
|
</description>
|
|
|
</property>
|
|
|
|
|
|
-<property>
|
|
|
- <name>mapreduce.output.fileoutputformat.compress.type</name>
|
|
|
- <value>BLOCK</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.type</name>
|
|
|
+ <value>BLOCK</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.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>
|
|
|
+ <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.input.limit</name>
|
|
|
- <value>10737418240</value>
|
|
|
- <description>The limit on the input size of the reduce. (This value
|
|
|
- is 10 Gb.) If the estimated input size of the reduce is greater than
|
|
|
- this value, job is failed. A value of -1 means that there is no limit
|
|
|
- set. </description>
|
|
|
-</property>
|
|
|
-
|
|
|
-
|
|
|
<!-- copied from kryptonite configuration -->
|
|
|
<property>
|
|
|
<name>mapreduce.map.output.compress</name>
|
|
|
<value></value>
|
|
|
</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.
|
|
|
- </description>
|
|
|
+ <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.
|
|
|
+ </description>
|
|
|
</property>
|
|
|
|
|
|
<property>
|
|
|
- <name>mapred.child.java.opts</name>
|
|
|
- <value>-Xmx512m</value>
|
|
|
- <description>No description</description>
|
|
|
+ <name>mapreduce.map.memory.mb</name>
|
|
|
+ <value>1536</value>
|
|
|
</property>
|
|
|
|
|
|
<property>
|
|
|
- <name>mapreduce.cluster.reducememory.mb</name>
|
|
|
- <value>2048</value>
|
|
|
+ <name>mapreduce.reduce.memory.mb</name>
|
|
|
+ <value>1024</value>
|
|
|
</property>
|
|
|
|
|
|
<property>
|
|
|
- <name>mapreduce.map.memory.mb</name>
|
|
|
- <value>1536</value>
|
|
|
+ <name>mapreduce.tasktracker.keytab.file</name>
|
|
|
+ <value></value>
|
|
|
+ <description>The filename of the keytab for the task tracker</description>
|
|
|
</property>
|
|
|
|
|
|
<property>
|
|
|
- <name>mapreduce.reduce.memory.mb</name>
|
|
|
+ <name>mapreduce.jobhistory.keytab.file</name>
|
|
|
+ <!-- cluster variant -->
|
|
|
+ <value></value>
|
|
|
+ <description>The keytab for the job history server principal.</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.jobhistory.intermediate-done-dir</name>
|
|
|
+ <value>/mr-history/tmp</value>
|
|
|
+ <description>
|
|
|
+ Directory where history files are written by MapReduce jobs.
|
|
|
+ </description>
|
|
|
+ </property>
|
|
|
+
|
|
|
+ <property>
|
|
|
+ <name>mapreduce.jobhistory.done-dir</name>
|
|
|
+ <value>/mr-history/done</value>
|
|
|
+ <description>
|
|
|
+ Directory where history files are managed by the MR JobHistory Server.
|
|
|
+ </description>
|
|
|
+ </property>
|
|
|
+
|
|
|
+ <property>
|
|
|
+ <name>mapreduce.jobhistory.address</name>
|
|
|
+ <value>localhost:10020</value>
|
|
|
+ <description>Enter your JobHistoryServer hostname.</description>
|
|
|
+ </property>
|
|
|
+
|
|
|
+ <property>
|
|
|
+ <name>mapreduce.jobhistory.webapp.address</name>
|
|
|
+ <value>localhost:19888</value>
|
|
|
+ <description>Enter your JobHistoryServer hostname.</description>
|
|
|
+ </property>
|
|
|
+
|
|
|
+ <property>
|
|
|
+ <name>mapreduce.framework.name</name>
|
|
|
+ <value>yarn</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>/user</value>
|
|
|
+ <description>
|
|
|
+ The staging dir used while submitting jobs.
|
|
|
+ </description>
|
|
|
+ </property>
|
|
|
+
|
|
|
+ <property>
|
|
|
+ <name>yarn.app.mapreduce.am.resource.mb</name>
|
|
|
<value>1024</value>
|
|
|
+ <description>The amount of memory the MR AppMaster needs.</description>
|
|
|
</property>
|
|
|
|
|
|
<property>
|
|
|
- <name>mapreduce.jobtracker.tasktracker.maxblacklists</name>
|
|
|
- <value>16</value>
|
|
|
+ <name>yarn.app.mapreduce.am.command-opts</name>
|
|
|
+ <value>-Xmx756m</value>
|
|
|
<description>
|
|
|
- if node is reported blacklisted by 16 successful jobs within timeout-window, it will be graylisted
|
|
|
+ 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>mapreduce.tasktracker.healthchecker.script.path</name>
|
|
|
- <value></value>
|
|
|
+ <name>yarn.app.mapreduce.am.admin-command-opts</name>
|
|
|
+ <value>-Djava.net.preferIPv4Stack=true -Dhadoop.metrics.log.level=WARN</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>mapreduce.tasktracker.healthchecker.script.timeout</name>
|
|
|
- <value>60000</value>
|
|
|
+ <name>yarn.app.mapreduce.am.log.level</name>
|
|
|
+ <value>INFO</value>
|
|
|
+ <description>MR App Master process log level.</description>
|
|
|
</property>
|
|
|
|
|
|
<property>
|
|
|
- <name>mapreduce.tasktracker.keytab.file</name>
|
|
|
+ <name>yarn.app.mapreduce.am.env</name>
|
|
|
<value></value>
|
|
|
- <description>The filename of the keytab for the task tracker</description>
|
|
|
+ <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>mapreduce.jobhistory.keytab.file</name>
|
|
|
- <!-- cluster variant -->
|
|
|
- <value></value>
|
|
|
- <description>The keytab for the job history server principal.</description>
|
|
|
- </property>
|
|
|
-
|
|
|
-<property>
|
|
|
- <name>mapreduce.shuffle.port</name>
|
|
|
- <value>8081</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.jobhistory.intermediate-done-dir</name>
|
|
|
- <value>/mr-history/tmp</value>
|
|
|
- <description>Directory where history files are written by MapReduce jobs.</description>
|
|
|
-</property>
|
|
|
-
|
|
|
-<property>
|
|
|
- <name>mapreduce.jobhistory.done-dir</name>
|
|
|
- <value>/mr-history/done</value>
|
|
|
- <description>Directory where history files are managed by the MR JobHistory Server.</description>
|
|
|
-</property>
|
|
|
-
|
|
|
-<property>
|
|
|
- <name>mapreduce.jobhistory.address</name>
|
|
|
- <value>localhost:10020</value>
|
|
|
- <description>Enter your JobHistoryServer hostname.</description>
|
|
|
-</property>
|
|
|
-
|
|
|
-<property>
|
|
|
- <name>mapreduce.jobhistory.webapp.address</name>
|
|
|
- <value>localhost:19888</value>
|
|
|
- <description>Enter your JobHistoryServer hostname.</description>
|
|
|
-</property>
|
|
|
-
|
|
|
-<property>
|
|
|
- <name>mapreduce.framework.name</name>
|
|
|
- <value>yarn</value>
|
|
|
- <description>No description</description>
|
|
|
-</property>
|
|
|
-
|
|
|
-<property>
|
|
|
- <name>yarn.app.mapreduce.am.staging-dir</name>
|
|
|
- <value>/user</value>
|
|
|
- <description>
|
|
|
- The staging dir used while submitting jobs.
|
|
|
- </description>
|
|
|
-</property>
|
|
|
+ <property>
|
|
|
+ <name>mapreduce.admin.map.child.java.opts</name>
|
|
|
+ <value>-Djava.net.preferIPv4Stack=true -Dhadoop.metrics.log.level=WARN</value>
|
|
|
+ </property>
|
|
|
+
|
|
|
+ <property>
|
|
|
+ <name>mapreduce.admin.reduce.child.java.opts</name>
|
|
|
+ <value>-Djava.net.preferIPv4Stack=true -Dhadoop.metrics.log.level=WARN</value>
|
|
|
+ </property>
|
|
|
+
|
|
|
+ <property>
|
|
|
+ <name>mapreduce.application.classpath</name>
|
|
|
+ <value>$HADOOP_MAPRED_HOME/share/hadoop/mapreduce/*,$HADOOP_MAPRED_HOME/share/hadoop/mapreduce/lib/*</value>
|
|
|
+ <description>
|
|
|
+ CLASSPATH for MR applications. A comma-separated list of CLASSPATH
|
|
|
+ entries.
|
|
|
+ </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>
|
|
|
+
|
|
|
+ <property>
|
|
|
+ <name>mapreduce.map.memory.mb</name>
|
|
|
+ <value>512</value>
|
|
|
+ <description>
|
|
|
+ Larger resource limit for maps.
|
|
|
+ </description>
|
|
|
+ </property>
|
|
|
+
|
|
|
+ <property>
|
|
|
+ <name>mapreduce.map.java.opts</name>
|
|
|
+ <value>-Xmx320m</value>
|
|
|
+ <description>
|
|
|
+ Larger heap-size for child jvms of maps.
|
|
|
+ </description>
|
|
|
+ </property>
|
|
|
+
|
|
|
+ <property>
|
|
|
+ <name>mapreduce.reduce.memory.mb</name>
|
|
|
+ <value>1024</value>
|
|
|
+ <description>
|
|
|
+ Larger resource limit for reduces.
|
|
|
+ </description>
|
|
|
+ </property>
|
|
|
+
|
|
|
+ <property>
|
|
|
+ <name>mapreduce.reduce.java.opts</name>
|
|
|
+ <value>-Xmx756m</value>
|
|
|
+ <description>
|
|
|
+ Larger heap-size for child jvms of reduces.
|
|
|
+ </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.
|
|
|
+ </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.
|
|
|
+ </description>
|
|
|
+ </property>
|
|
|
|
|
|
</configuration>
|
Siddharth Wagle