hive configs

hive-site.xml

<configuration>
  <!-- Metastore configs -->
  <property>
    <name>hive.metastore.warehouse.dir</name>
    <value>/apps/hive/warehouse</value>
  </property>
  <property>
    <name>hive.metastore.cache.pinobjtypes</name>
    <value>Table,Database,Type,FieldSchema,Order</value>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionDriverName</name>
    <value>com.mysql.jdbc.Driver</value>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionUserName</name>
    <value>hive</value>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionPassword</name>
    <value>INSERT_PASSWORD_HERE</value>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionURL</name>
    <value>jdbc:mysql://localhost/metastore2?createDatabaseIfNotExist=true</value>
  </property>
  <property>
    <name>hive.metastore.uris</name>
    <value></value>
  </property>
  <property>
    <name>hive.metastore.client.socket.timeout</name>
    <value>60</value>
  </property>

  <!-- Filesystem configs -->
  <property>
    <name>hadoop.clientside.fs.operations</name>
    <value>true</value>
  </property>
  <property>
    <name>fs.hdfs.impl.disable.cache</name>
    <value>true</value>
  </property>
  <property>
    <name>fs.file.impl.disable.cache</name>
    <value>true</value>
  </property>

  <!-- stats gathering -->
  <property>
    <name>hive.stats.dbclass</name>
    <value>jdbc:mysql</value>
  </property>
  <property>
    <name>hive.stats.jdbcdriver</name>
    <value>com.mysql.jdbc.Driver</value>
  </property>
  <property>
    <name>hive.stats.dbconnectionstring</name>
    <value>jdbc:mysql://localhost/metastore2?createDatabaseIfNotExist=true&amp;useUnicode=true&amp;characterEncoding=UTF-8&amp;user=hive&amp;password=hive</value>
  </property>
  <property>
    <name>hive.stats.autogather</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.stats.jdbc.timeout</name>
    <value>60</value>
  </property>
  <property>
    <name>hive.stats.fetch.column.stats</name>
    <value>true</value>
  </property>

  <!-- dynamic partitions, bucketing, sorting config -->
  <property>
    <name>hive.exec.dynamic.partition</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.exec.dynamic.partition.mode</name>
    <value>nonstrict</value>
  </property>
  <property>
    <name>hive.exec.max.dynamic.partitions</name>
    <value>10000</value>
  </property>
  <property>
    <name>hive.exec.max.dynamic.partitions.pernode</name>
    <value>1000</value>
  </property>
  <property>
    <name>hive.enforce.bucketing</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.enforce.sorting</name>
    <value>true</value>
  </property>
  
  <!-- file merge configs -->
  <property>
    <name>hive.merge.tezfiles</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.merge.mapfiles</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.merge.mapredfiles</name>
    <value>true</value>
  </property>

  <!-- optimization configs -->
  <property>
    <name>hive.auto.convert.join</name>
    <value>true</value>
  </property>
    <property>
    <name>hive.auto.convert.sortmerge.join</name>
    <value>true</value>
  </property>
    <property>
    <name>hive.optimize.bucketmapjoin</name>
    <value>true</value>
  </property>
    <property>
    <name>hive.optimize.bucketmapjoin.sortedmerge</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.auto.convert.join.noconditionaltask.size</name>
    <value>1000000000</value>
  </property>
  <property>
    <name>hive.auto.convert.join.noconditionaltask</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.mapjoin.bucket.cache.size</name>
    <value>10000</value>
  </property>
  <property>
    <name>hive.optimize.reducededuplication.min.reducer</name>
    <value>4</value>
  </property>
  <property>
    <name>hive.map.aggr</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.optimize.reducededuplication</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.optimize.index.filter</name>
    <value>true</value>
  </property>

  <!-- vectorization config -->
  <property>
    <name>hive.vectorized.execution.enabled</name>
    <value>true</value>
  </property>
  <property>
    <name>hive.vectorized.groupby.maxentries</name>
    <value>10000</value>
  </property>
  <property>
    <name>hive.vectorized.groupby.checkinterval</name>
    <value>10000</value>
  </property>

  <!-- execution engine configs -->
  <property>
    <name>hive.execution.engine</name>
    <value>tez</value>
  </property>
  <property>
    <name>hive.mapred.reduce.tasks.speculative.execution</name>
    <value>false</value>
  </property>
  <property>
    <name>tez.am.node-blacklisting.enabled</name>
    <value>false</value>
  </property>
  <property>
    <name>hive.prewarm.numcontainers</name>
    <value>2</value>
    <description>
      Controls the number of containers to prewarm for tez (hadoop 2 only)
    </description>
  </property>
  <property>
    <name>mapred.tez.java.opts</name>
    <value>-Xmx2048m</value>
  </property>
  <property>
    <name>hive.tez.container.size</name>
    <value>2048</value>
    <description></description>
  </property>

  <!-- mr engine config -->
  <property>
    <name>mapred.child.java.opts</name>
    <value>-Djava.awt.headless=true -Xmx8096M</value>
  </property>
  <property>
    <name>mapred.map.max.attempts</name>
    <value>1</value>
  </property>

  <!-- hive input format -->
  <property>
    <name>hive.input.format</name>
    <value>org.apache.hadoop.hive.ql.io.HiveInputFormat</value>
  </property>
</configuration>