mapred-site.xml

<configuration>
<property>
  <name>mapreduce.map.output.compress</name>
  <value>true</value>
</property>
<property>
   <name>mapred.map.output.compress.codec</name>
   <value>org.apache.hadoop.io.compress.SnappyCodec</value>
</property>
<property>
  <name>mapreduce.framework.name</name>
  <value>yarn</value>
</property>
<property>
   <name>mapreduce.jobhistory.address</name>
   <value>ihub-an-l1:10020</value>
</property>
<property>
    <name>mapreduce.jobhistory.webapp.address</name>
    <value>ihub-an-l1:19888</value>
</property>
<property>
  <name>yarn.app.mapreduce.am.resource.mb</name>
  <value>1000</value>
  <description>The amount of memory the MR AppMaster needs.</description>
</property>
<property>
  <name>mapreduce.job.jvm.numtasks</name>
  <value>10</value>
  <description>How many tasks to run per jvm. If set to -1, there is
  no limit.
  </description>
</property>
<property>
  <name>mapreduce.map.speculative</name>
  <value>false</value>
  <final>true</final>
  <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>
  <final>true</final>
  <description>If true, then multiple instances of some reduce tasks
               may be executed in parallel.</description>
<property>
  <name>mapred.child.java.opts</name>
  <value>-Xmx300m</value>
  <description>Java opts for the task tracker child 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/@[email protected]
  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.map.tasks.maximum</name>
  <value>1</value>
  <description>The maximum number of map tasks that will be run
  simultaneously by a task tracker.
  </description>
</property>
<property>
  <name>mapreduce.tasktracker.reduce.tasks.maximum</name>
  <value>1</value>
  <description>The maximum number of reduce tasks that will be run
  simultaneously by a task tracker.
  </description>
</property>
<property>
  <name>mapreduce.jobtracker.restart.recover</name>
  <value>false</value>
  <description>"true" to enable (job) recovery upon restart,
               "false" to start afresh
  </description>
</property>
</configuration>