blob: b450396ce7b7bc98b7657e4f5d020acc23e68d03 [file] [log] [blame]
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!-- Put site-specific property overrides in this file. -->
<configuration>
<property>
<name>mapred.tasktracker.tasks.sleeptime-before-sigkill</name>
<value>250</value>
<description>Normally, this is the amount of time before killing
processes, and the recommended-default is 5.000 seconds - a value of
5000 here. In this case, we are using it solely to blast tasks before
killing them, and killing them very quickly (1/4 second) to guarantee
that we do not leave VMs around for later jobs.
</description>
</property>
<property>
<name>mapred.system.dir</name>
<value>/mapred/mapredsystem</value>
<final>true</final>
</property>
<property>
<name>mapred.job.tracker</name>
<value>${HADOOP_JT_HOST}:9000</value>
<final>true</final>
</property>
<property>
<name>mapred.job.tracker.http.address</name>
<value>${HADOOP_JT_HOST}:50030</value>
<final>true</final>
</property>
<property>
<name>mapred.local.dir</name>
<value>${HADOOP_MAPRED_DIR}</value>
<final>true</final>
</property>
<property>
<name>mapreduce.cluster.administrators</name>
<value>${HADOOP_MR_USER}</value>
</property>
<property>
<name>mapred.map.tasks.speculative.execution</name>
<value>false</value>
<description>If true, then multiple instances of some map tasks
may be executed in parallel.</description>
</property>
<property>
<name>mapred.reduce.tasks.speculative.execution</name>
<value>false</value>
<description>If true, then multiple instances of some reduce tasks
may be executed in parallel.</description>
</property>
<property>
<name>mapred.output.compression.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>jetty.connector</name>
<value>org.mortbay.jetty.nio.SelectChannelConnector</value>
</property>
<property>
<name>mapred.task.tracker.task-controller</name>
<value>${TASK_CONTROLLER}</value>
</property>
<property>
<name>mapred.child.root.logger</name>
<value>INFO,TLA</value>
</property>
<property>
<name>mapred.child.java.opts</name>
<value>-server -Xmx640m -Djava.net.preferIPv4Stack=true</value>
</property>
<property>
<name>mapred.child.ulimit</name>
<value>8388608</value>
</property>
<property>
<name>mapred.job.tracker.persist.jobstatus.active</name>
<value>true</value>
<description>Indicates if persistency of job status information is
active or not.
</description>
</property>
<property>
<name>mapred.job.tracker.persist.jobstatus.dir</name>
<value>file:///${HADOOP_LOG_DIR}/${HADOOP_MR_USER}/jobstatus</value>
<description>The directory where the job status information is persisted
in a file system to be available after it drops of the memory queue and
between jobtracker restarts.
</description>
</property>
<property>
<name>mapred.job.tracker.history.completed.location</name>
<value>/mapred/history/done</value>
</property>
<property>
<name>mapred.heartbeats.in.second</name>
<value>200</value>
<description>to enable HADOOP:5784</description>
</property>
<property>
<name>mapreduce.tasktracker.outofband.heartbeat</name>
<value>true</value>
<description>to enable MAPREDUCE:270</description>
</property>
<property>
<name>mapred.jobtracker.maxtasks.per.job</name>
<value>200000</value>
<final>true</final>
<description>The maximum number of tasks for a single job.
A value of -1 indicates that there is no maximum.
</description>
</property>
<property>
<name>mapreduce.jobtracker.kerberos.principal</name>
<value>jt/_HOST@${local.realm}</value>
<description>
JT principal
</description>
</property>
<property>
<name>mapreduce.tasktracker.kerberos.principal</name>
<value>tt/_HOST@${local.realm}</value>
<description>
TT principal.
</description>
</property>
<property>
<name>hadoop.job.history.user.location</name>
<value>none</value>
</property>
<property>
<name>mapreduce.jobtracker.keytab.file</name>
<value>/etc/security/keytabs/jt.service.keytab</value>
<description>
The keytab for the jobtracker principal.
</description>
</property>
<property>
<name>mapreduce.tasktracker.keytab.file</name>
<value>/etc/security/keytabs/tt.service.keytab</value>
<description>The filename of the keytab for the task tracker</description>
</property>
<property>
<name>mapreduce.jobtracker.staging.root.dir</name>
<value>/user</value>
<description>The Path prefix for where the staging directories should be
placed. The next level is always the user's
name. It is a path in the default file system.
</description>
</property>
<property>
<name>mapreduce.job.acl-modify-job</name>
<value></value>
</property>
<property>
<name>mapreduce.job.acl-view-job</name>
<value>Dr.Who</value>
</property>
<property>
<name>mapreduce.tasktracker.group</name>
<value>${HADOOP_GROUP}</value>
<description>The group that the task controller uses for accessing the
task controller. The mapred user must be a member and users should *not*
be members.
</description>
</property>
<property>
<name>mapred.acls.enabled</name>
<value>true</value>
</property>
<property>
<name>mapred.jobtracker.taskScheduler</name>
<value>org.apache.hadoop.mapred.CapacityTaskScheduler</value>
</property>
<property>
<name>mapred.queue.names</name>
<value>default</value>
</property>
<!-- settings for the history server -->
<property>
<name>mapreduce.history.server.embedded</name>
<value>false</value>
</property>
<property>
<name>mapreduce.history.server.http.address</name>
<value>${HADOOP_JT_HOST}:51111</value>
</property>
<property>
<name>mapreduce.jobhistory.kerberos.principal</name>
<value>jt/_HOST@${local.realm}</value>
<description>history server principal</description>
</property>
<property>
<name>mapreduce.jobhistory.keytab.file</name>
<value>/etc/security/keytabs/jt.service.keytab</value>
<description>
The keytab for the jobtracker principal.
</description>
</property>
<property>
<name>mapred.hosts</name>
<value>${HADOOP_CONF_DIR}/mapred.include</value>
<description>Names a file that contains the list of nodes that may
connect to the jobtracker. If the value is empty, all hosts are
permitted.</description>
</property>
<property>
<name>mapred.hosts.exclude</name>
<value>${HADOOP_CONF_DIR}/mapred.exclude</value>
<description>Names a file that contains the list of hosts that
should be excluded by the jobtracker. If the value is empty, no
hosts are excluded.</description>
</property>
<property>
<name>mapred.jobtracker.retirejob.check</name>
<value>10000</value>
</property>
<property>
<name>mapred.jobtracker.retirejob.interval</name>
<value>0</value>
</property>
<property>
<name>mapred.cluster.map.memory.mb</name>
<value>${MAPRED_CLUSTER_MAP_MEMORY_MB}</value>
<description>The size, in terms of virtual memory, of a single map slot
in the Map-Reduce framework, used by the scheduler.
A job can ask for multiple slots for a single map task via
mapred.job.map.memory.mb, upto the limit specified by
mapred.cluster.max.map.memory.mb, if the scheduler supports the feature.
The value of -1 indicates that this feature is turned off.
</description>
</property>
<property>
<name>mapred.cluster.reduce.memory.mb</name>
<value>${MAPRED_CLUSTER_REDUCE_MEMORY_MB}</value>
<description>The size, in terms of virtual memory, of a single reduce slot
in the Map-Reduce framework, used by the scheduler.
A job can ask for multiple slots for a single reduce task via
mapred.job.reduce.memory.mb, upto the limit specified by
mapred.cluster.max.reduce.memory.mb, if the scheduler supports the feature.
The value of -1 indicates that this feature is turned off.
</description>
</property>
<property>
<name>mapred.cluster.max.map.memory.mb</name>
<value>${MAPRED_CLUSTER_MAX_MAP_MEMORY_MB}</value>
<description>The maximum size, in terms of virtual memory, of a single map
task launched by the Map-Reduce framework, used by the scheduler.
A job can ask for multiple slots for a single map task via
mapred.job.map.memory.mb, upto the limit specified by
mapred.cluster.max.map.memory.mb, if the scheduler supports the feature.
The value of -1 indicates that this feature is turned off.
</description>
</property>
<property>
<name>mapred.cluster.max.reduce.memory.mb</name>
<value>${MAPRED_CLUSTER_MAX_REDUCE_MEMORY_MB}</value>
<description>The maximum size, in terms of virtual memory, of a single reduce
task launched by the Map-Reduce framework, used by the scheduler.
A job can ask for multiple slots for a single reduce task via
mapred.job.reduce.memory.mb, upto the limit specified by
mapred.cluster.max.reduce.memory.mb, if the scheduler supports the feature.
The value of -1 indicates that this feature is turned off.
</description>
</property>
<property>
<name>mapred.job.map.memory.mb</name>
<value>${MAPRED_JOB_MAP_MEMORY_MB}</value>
<description>The size, in terms of virtual memory, of a single map task
for the job.
A job can ask for multiple slots for a single map task, rounded up to the
next multiple of mapred.cluster.map.memory.mb and upto the limit
specified by mapred.cluster.max.map.memory.mb, if the scheduler supports
the feature.
The value of -1 indicates that this feature is turned off iff
mapred.cluster.map.memory.mb is also turned off (-1).
</description>
</property>
<property>
<name>mapred.job.reduce.memory.mb</name>
<value>${MAPRED_JOB_REDUCE_MEMORY_MB}</value>
<description>The size, in terms of virtual memory, of a single reduce task
for the job.
A job can ask for multiple slots for a single map task, rounded up to the
next multiple of mapred.cluster.reduce.memory.mb and upto the limit
specified by mapred.cluster.max.reduce.memory.mb, if the scheduler supports
the feature.
The value of -1 indicates that this feature is turned off iff
mapred.cluster.reduce.memory.mb is also turned off (-1).
</description>
</property>
</configuration>