ambari-server/src/main/resources/stacks/HDP/2.1/services/HIVE/configuration/hive-site.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
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>ambari.hive.db.schema.name</name>
    <value>hive</value>
    <description>Database name used as the Hive Metastore</description>
  </property>

  <property>
    <name>javax.jdo.option.ConnectionURL</name>
    <value>jdbc</value>
    <description>JDBC connect string for a JDBC metastore</description>
  </property>

  <property>
    <name>javax.jdo.option.ConnectionDriverName</name>
    <value>com.mysql.jdbc.Driver</value>
    <description>Driver class name for a JDBC metastore</description>
  </property>

  <property>
    <name>javax.jdo.option.ConnectionUserName</name>
    <value>hive</value>
    <description>username to use against metastore database</description>
  </property>

  <property>
    <name>javax.jdo.option.ConnectionPassword</name>
    <value> </value>
    <description>password to use against metastore database</description>
  </property>

  <property>
    <name>hive.metastore.warehouse.dir</name>
    <value>/apps/hive/warehouse</value>
    <description>location of default database for the warehouse</description>
  </property>

  <property>
    <name>hive.metastore.sasl.enabled</name>
    <value></value>
    <description>If true, the metastore thrift interface will be secured with SASL.
     Clients must authenticate with Kerberos.</description>
  </property>

  <property>
    <name>hive.metastore.kerberos.keytab.file</name>
    <value></value>
    <description>The path to the Kerberos Keytab file containing the metastore
     thrift server's service principal.</description>
  </property>

  <property>
    <name>hive.metastore.kerberos.principal</name>
    <value></value>
    <description>The service principal for the metastore thrift server. The special
    string _HOST will be replaced automatically with the correct host name.</description>
  </property>

  <property>
    <name>hive.metastore.cache.pinobjtypes</name>
    <value>Table,Database,Type,FieldSchema,Order</value>
    <description>List of comma separated metastore object types that should be pinned in the cache</description>
  </property>

  <property>
    <name>hive.metastore.uris</name>
    <value>thrift://localhost:9083</value>
    <description>URI for client to contact metastore server</description>
  </property>

  <property>
    <name>hive.semantic.analyzer.factory.impl</name>
    <value>org.apache.hivealog.cli.HCatSemanticAnalyzerFactory</value>
    <description>controls which SemanticAnalyzerFactory implementation class is used by CLI</description>
  </property>

  <property>
    <name>hive.metastore.client.socket.timeout</name>
    <value>60</value>
    <description>MetaStore Client socket timeout in seconds</description>
  </property>

  <property>
    <name>hive.metastore.execute.setugi</name>
    <value>true</value>
    <description>In unsecure mode, setting this property to true will cause the metastore to execute DFS operations using the client's reported user and group permissions. Note that this property must be set on both the client and     server sides. Further note that its best effort. If client sets its to true and server sets it to false, client setting will be ignored.</description>
  </property>

  <property>
    <name>hive.security.authorization.enabled</name>
    <value>true</value>
    <description>enable or disable the hive client authorization</description>
  </property>

  <property>
    <name>hive.security.authorization.manager</name>
    <value>org.apache.hadoop.hive.ql.security.authorization.StorageBasedAuthorizationProvider</value>
    <description>the hive client authorization manager class name.
    The user defined authorization class should implement interface org.apache.hadoop.hive.ql.security.authorization.HiveAuthorizationProvider.  </description>
  </property>

  <property>
    <name>hive.security.metastore.authorization.manager</name>
    <value>org.apache.hadoop.hive.ql.security.authorization.StorageBasedAuthorizationProvider</value>
    <description>The authorization manager class name to be used in the metastore for authorization. The user-defined authorization class should implement interface org.apache.hadoop.hive.ql.security.authorization.HiveMetastoreAuthorizationProvider.  </description>
  </property>

  <property>
    <name>hive.security.authenticator.manager</name>
    <value>org.apache.hadoop.hive.ql.security.ProxyUserAuthenticator</value>
    <description>Hive client authenticator manager class name. The user-defined authenticator class should implement interface org.apache.hadoop.hive.ql.security.HiveAuthenticationProvider.  </description>
  </property>

  <property>
    <name>hive.server2.enable.doAs</name>
    <value>false</value>
    <description>Impersonate the connected user. By default HiveServer2 performs the query processing as the user who
      submitted the query. But if the parameter is set to false, the query will run as the user that the hiveserver2
      process runs as.
    </description>
  </property>

  <property>
    <name>fs.hdfs.impl.disable.cache</name>
    <value>true</value>
    <description>Disable HDFS filesystem cache.</description>
  </property>

  <property>
    <name>fs.file.impl.disable.cache</name>
    <value>true</value>
    <description>Disable local filesystem cache.</description>
  </property>

  <property>
    <name>hive.enforce.bucketing</name>
    <value>true</value>
    <description>Whether bucketing is enforced. If true, while inserting into the table, bucketing is enforced.</description>
  </property>

  <property>
    <name>hive.enforce.sorting</name>
    <value>true</value>
    <description>Whether sorting is enforced. If true, while inserting into the table, sorting is enforced.</description>
  </property>

  <property>
    <name>hive.enforce.sortmergebucketmapjoin</name>
    <value>true</value>
    <description>If the user asked for sort-merge bucketed map-side join, and it cannot be performed, should the query fail or not</description>
  </property>

  <property>
    <name>hive.map.aggr</name>
    <value>true</value>
    <description>Whether to use map-side aggregation in Hive Group By queries.</description>
  </property>

  <property>
    <name>hive.optimize.bucketmapjoin</name>
    <value>true</value>
    <description>If the tables being joined are bucketized on the join columns, and the number of buckets in one table
      is a multiple of the number of buckets in the other table, the buckets can be joined with each other by setting
      this parameter as true.
    </description>
  </property>

  <property>
    <name>hive.optimize.bucketmapjoin.sortedmerge</name>
    <value>false</value>
    <description> If the tables being joined are sorted and bucketized on the join columns, and they have the same number
    of buckets, a sort-merge join can be performed by setting this parameter as true.
    </description>
  </property>

  <property>
    <name>hive.mapred.reduce.tasks.speculative.execution</name>
    <value>false</value>
    <description>Whether speculative execution for reducers should be turned on.</description>
  </property>

  <property>
    <name>hive.auto.convert.join</name>
    <value>true</value>
    <description>Whether Hive enable the optimization about converting common
      join into mapjoin based on the input file size.</description>
  </property>

  <property>
    <name>hive.auto.convert.sortmerge.join</name>
    <value>true</value>
    <description>Will the join be automatically converted to a sort-merge join, if the joined tables pass
      the criteria for sort-merge join.
    </description>
  </property>

  <property>
    <name>hive.auto.convert.sortmerge.join.noconditionaltask</name>
    <value>true</value>
    <description>Required to Enable the conversion of an SMB (Sort-Merge-Bucket) to a map-join SMB.</description>
  </property>

  <property>
    <name>hive.auto.convert.join.noconditionaltask</name>
    <value>true</value>
    <description>Whether Hive enable the optimization about converting common join into mapjoin based on the input file
      size. If this paramater is on, and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than the
      specified size, the join is directly converted to a mapjoin (there is no conditional task).
    </description>
  </property>

  <property>
    <name>hive.auto.convert.join.noconditionaltask.size</name>
    <value>1000000000</value>
    <description>If hive.auto.convert.join.noconditionaltask is off, this parameter does not take affect. However, if it
      is on, and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than this size, the join is directly
      converted to a mapjoin(there is no conditional task). The default is 10MB.
    </description>
  </property>

  <property>
    <name>hive.optimize.reducededuplication.min.reducer</name>
    <value>4</value>
    <description>Reduce deduplication merges two RSs by moving key/parts/reducer-num of the child RS to parent RS.
      That means if reducer-num of the child RS is fixed (order by or forced bucketing) and small, it can make very slow, single MR.
      The optimization will be disabled if number of reducers is less than specified value.
    </description>
  </property>

  <property>
    <name>hive.optimize.mapjoin.mapreduce</name>
    <value>true</value>
    <description>If hive.auto.convert.join is off, this parameter does not take
      affect. If it is on, and if there are map-join jobs followed by a map-reduce
      job (for e.g a group by), each map-only job is merged with the following
      map-reduce job.
    </description>
  </property>

  <property>
    <name>hive.mapjoin.bucket.cache.size</name>
    <value>10000</value>
    <description>
      Size per reducer.The default is 1G, i.e if the input size is 10G, it
      will use 10 reducers.
    </description>
  </property>

  <property>
    <name>hive.vectorized.execution.enabled</name>
    <value>true</value>
    <description>This flag controls the vectorized mode of query execution as documented in HIVE-4160 (as of Hive 0.13.0)
    </description>
  </property>

  <property>
    <name>hive.optimize.reducededuplication</name>
    <value>true</value>
    <description>Remove extra map-reduce jobs if the data is already clustered by the same key which needs to be used again.
    </description>
  </property>

  <property>
    <name>hive.optimize.index.filter</name>
    <value>true</value>
    <description>
    Whether to enable automatic use of indexes
    </description>
  </property>

  <property>
    <name>hive.execution.engine</name>
    <value>mr</value>
    <description>Whether to use MR or Tez</description>
  </property>

  <property>
    <name>hive.exec.post.hooks</name>
    <value>org.apache.hadoop.hive.ql.hooks.ATSHook</value>
    <description>Comma-separated list of post-execution hooks to be invoked for each statement.</description>
  </property>

  <property>
    <name>hive.exec.pre.hooks</name>
    <value>org.apache.hadoop.hive.ql.hooks.ATSHook</value>
    <description>Comma-separated list of pre-execution hooks to be invoked for each statement.</description>
  </property>

  <property>
    <name>hive.exec.failure.hooks</name>
    <value>org.apache.hadoop.hive.ql.hooks.ATSHook</value>
    <description>Comma-separated list of on-failure hooks to be invoked for each statement.</description>
  </property>

  <property>
    <name>hive.vectorized.groupby.maxentries</name>
    <value>1024</value>
    <description>Max number of entries in the vector group by aggregation hashtables.
      Exceeding this will trigger a flush irrelevant of memory pressure condition.
    </description>
  </property>

  <property>
    <name>hive.vectorized.groupby.checkinterval</name>
    <value>1024</value>
    <description>Number of entries added to the group by aggregation hash before a reocmputation of average entry size is performed.</description>
  </property>

  <property>
    <name>hive.vectorized.groupby.flush.percent</name>
    <value>1.0</value>
    <description>Percent of entries in the group by aggregation hash flushed when the memory treshold is exceeded.</description>
  </property>

  <property>
    <name>hive.stats.autogather</name>
    <value>true</value>
    <description>A flag to gather statistics automatically during the INSERT OVERWRITE command.</description>
  </property>

  <property>
    <name>hive.tez.container.size</name>
    <value>3000000000</value>
    <description></description>
  </property>

  <property>
    <name>hive.tez.input.format</name>
    <value>org.apache.hadoop.hive.ql.io.HiveInputFormat</value>
    <description></description>
  </property>

  <property>
    <name>hive.tez.java.opts</name>
    <value>-server -Xmx1024m -Djava.net.preferIPv4Stack=true -XX:NewRatio=8 -XX:+UseNUMA -XX:+UseParallelGC</value>
    <description></description>
  </property>

  <property>
    <name>hive.compute.query.using.stats</name>
    <value>true</value>
    <description>
      When set to true Hive will answer a few queries like count(1) purely using stats
      stored in metastore. For basic stats collection turn on the config hive.stats.autogather to true.
      For more advanced stats collection need to run analyze table queries.
    </description>
  </property>

  <property>
    <name>hive.orc.splits.include.file.footer</name>
    <value>false</value>
    <description>
      If turned on splits generated by orc will include metadata about the stripes in the file. This
      data is read remotely (from the client or HS2 machine) and sent to all the tasks.
    </description>
  </property>

  <property>
    <name>hive.limit.pushdown.memory.usage</name>
    <value>0.04</value>
    <description>The max memory to be used for hash in RS operator for top K selection.</description>
  </property>

  <property>
    <name>hive.server2.tez.default.queues</name>
    <value>default</value>
    <description></description>
  </property>

  <property>
    <name>hive.server2.tez.sessions.per.default.queue</name>
    <value>1</value>
    <description></description>
  </property>

  <property>
    <name>hive.server2.tez.initialize.default.sessions</name>
    <value>false</value>
    <description></description>
  </property>

  <property>
    <name>hive.txn.manager</name>
    <value>org.apache.hadoop.hive.ql.lockmgr.DummyTxnManager</value>
    <description>Select the class to do transaction management. The default DummyTxnManager does no transactions and retains the legacy behavior.</description>
  </property>

  <property>
    <name>hive.txn.driver</name>
    <value></value>
    <description>Gives the jdbc driver to use to connect to the metastore</description>
  </property>

  <property>
    <name>hive.txn.connection.string</name>
    <value></value>
    <description>Gives the connection string to pass the jdbc driver</description>
  </property>

  <property>
    <name>hive.txn.timeout</name>
    <value>300</value>
    <description>Time after which transactions are declared aborted if the client has not sent a heartbeat, in seconds.</description>
  </property>

  <property>
    <name>hive.txn.max.open.batch</name>
    <value>1000</value>
    <description>Maximum number of transactions that can be fetched in one call to open_txns(). Increasing this will decrease the number of delta files created when streaming data into Hive. But it will also increase the number of open transactions at any given time, possibly impacting read performance.</description>
  </property>

  <property>
    <name>hive.compactor.initiator.on</name>
    <value>false</value>
    <description>Whether to run the compactor's initiator thread in this metastore instance or not. If there is more than one instance of the thrift metastore this should only be set to true for one of them.</description>
  </property>

  <property>
    <name>hive.compactor.worker.threads</name>
    <value>0</value>
    <description>Number of compactor worker threads to run on this metastore instance. Can be different values on different metastore instances.</description>
  </property>

  <property>
    <name>hive.compactor.worker.timeout</name>
    <value>86400L</value>
    <description>Time, in seconds, before a given compaction in working state is declared a failure and returned to the initiated state.</description>
  </property>

  <property>
    <name>hive.compactor.check.interval</name>
    <value>300L</value>
    <description>Time in seconds between checks to see if any partitions need compacted. This should be kept high because each check for compaction requires many calls against the NameNode.</description>
  </property>

  <property>
    <name>hive.compactor.delta.num.threshold</name>
    <value>10</value>
    <description>Number of delta files that must exist in a directory before the compactor will attempt a minor compaction.</description>
  </property>

  <property>
    <name>hive.compactor.delta.pct.threshold</name>
    <value>0.1f</value>
    <description>Percentage (by size) of base that deltas can be before major compaction is initiated.</description>
  </property>

  <property>
    <name>hive.compactor.abortedtxn.threshold</name>
    <value>1000</value>
    <description>Number of aborted transactions involving a particular table or partition before major compaction is initiated.</description>
  </property>

  <property>
    <name>hive.users.in.admin.role</name>
    <value></value>
    <description>If user is specified as value of this config, that user has superuser privileges in DB</description>
  </property>

</configuration>