build/conf/kylin_job_conf_inmem.xml

<!--
  Licensed to the Apache Software Foundation (ASF) under one or more
  contributor license agreements.  See the NOTICE file distributed with
  this work for additional information regarding copyright ownership.
  The ASF licenses this file to You under the Apache License, Version 2.0
  (the "License"); you may not use this file except in compliance with
  the License.  You may obtain a copy of the License at

      http://www.apache.org/licenses/LICENSE-2.0

  Unless required by applicable law or agreed to in writing, software
  distributed under the License is distributed on an "AS IS" BASIS,
  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  See the License for the specific language governing permissions and
  limitations under the License.
-->
<configuration>
    <property>
        <name>mapreduce.job.is-mem-hungry</name>
        <value>true</value>
    </property>

    <property>
        <name>mapreduce.job.split.metainfo.maxsize</name>
        <value>-1</value>
        <description>The maximum permissible size of the split metainfo file.
            The JobTracker won't attempt to read split metainfo files bigger than
            the configured value. No limits if set to -1.
        </description>
    </property>

    <property>
        <name>mapreduce.map.output.compress</name>
        <value>true</value>
        <description>Compress map outputs</description>
    </property>

    <!--
    The default map outputs compress codec is org.apache.hadoop.io.compress.DefaultCodec,
    if SnappyCodec is supported, org.apache.hadoop.io.compress.SnappyCodec could be used.
    -->
    <!--
    <property>
        <name>mapreduce.map.output.compress.codec</name>
        <value>org.apache.hadoop.io.compress.SnappyCodec</value>
        <description>The compression codec to use for map outputs
        </description>
    </property>
    -->
    <property>
        <name>mapreduce.output.fileoutputformat.compress</name>
        <value>true</value>
        <description>Compress the output of a MapReduce job</description>
    </property>
    <!--
    The default job outputs compress codec is org.apache.hadoop.io.compress.DefaultCodec,
    if SnappyCodec is supported, org.apache.hadoop.io.compress.SnappyCodec could be used.
    -->
    <!--
    <property>
        <name>mapreduce.output.fileoutputformat.compress.codec</name>
        <value>org.apache.hadoop.io.compress.SnappyCodec</value>
        <description>The compression codec to use for job outputs
        </description>
    </property>
    -->
    <property>
        <name>mapreduce.output.fileoutputformat.compress.type</name>
        <value>BLOCK</value>
        <description>The compression type to use for job outputs</description>
    </property>


    <property>
        <name>mapreduce.job.max.split.locations</name>
        <value>2000</value>
        <description>No description</description>
    </property>

    <property>
        <name>dfs.replication</name>
        <value>2</value>
        <description>Block replication</description>
    </property>

    <property>
        <name>mapreduce.task.timeout</name>
        <value>7200000</value>
        <description>Set task timeout to 1 hour</description>
    </property>

    <!--Additional config for in-mem cubing, giving mapper more memory -->
    <property>
        <name>mapreduce.map.memory.mb</name>
        <value>3072</value>
        <description></description>
    </property>

    <property>
        <name>mapreduce.map.java.opts</name>
        <value>-Xmx2700m -XX:OnOutOfMemoryError='kill -9 %p'</value>
        <description></description>
    </property>

    <property>
        <name>mapreduce.task.io.sort.mb</name>
        <value>200</value>
        <description></description>
    </property>

</configuration>