<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
<name>hive.exec.scratchdir</name>
<value>/data/cloud/hive/scratchdir</value>
<description>HDFS root scratch dir for Hive jobs which gets created with write all (733) permission. For each connecting user, an HDFS scratch dir: ${hive.exec.scratchdir}/<username> is created, with ${hive.scratch.dir.permission}.</description>
</property>
<property>
<name>hive.exec.local.scratchdir</name>
<value>/data/cloud/hive/scratchdir</value>
<description>Local scratch space for Hive jobs</description>
</property>
<property>
<name>hive.downloaded.resources.dir</name>
<value>/data/cloud/hive/${hive.session.id}_resources</value>
<description>Temporary local directory for added resources in the remote file system.</description>
</property>
<property>
<name>hive.exec.compress.output</name>
<value>true</value>
<description>
This controls whether the final outputs of a query (to a local/HDFS file or a Hive table) is compressed.
The compression codec and other options are determined from Hadoop config variables mapred.output.compress*
</description>
</property>
<property>
<name>hive.exec.compress.intermediate</name>
<value>true</value>
<description>
This controls whether intermediate files produced by Hive between multiple map-reduce jobs are compressed.
The compression codec and other options are determined from Hadoop config variables mapred.output.compress*
</description>
</property>
<property>
<name>hive.intermediate.compression.codec</name>
<value>org.apache.hadoop.io.compress.Lz4Codec</value>
<description/>
</property>
<property>
<name>hive.intermediate.compression.type</name>
<value>BLOCK</value>
<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.metastore.warehouse.dir</name>
<value>/data/cloud/hive/warehouse</value>
<description>location of default database for the warehouse</description>
</property>
<property>
<name>javax.jdo.option.ConnectionURL</name>
<value>jdbc:mysql://xx:3306/hive?createDatabaseIfNotExist=true&characterEncoding=UTF-8&useSSL=false</value>
<description>
JDBC connect string for a JDBC metastore.
To use SSL to encrypt/authenticate the connection, provide database-specific SSL flag in the connection URL.
For example, jdbc:postgresql://myhost/db?ssl=true for postgres database.
</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>xx</value>
<description>Username to use against metastore database</description>
</property>
<property>
<name>javax.jdo.option.ConnectionPassword</name>
<value>xx</value>
<description>password to use against metastore database</description>
</property>
<property>
<name>hive.querylog.location</name>
<value>/data/cloud/hive/location</value>
<description>Location of Hive run time structured log file</description>
</property>
<property>
<name>hive.auto.convert.join</name>
<value>false</value>
<description>Whether Hive enables the optimization about converting common join into mapjoin based on the input file size</description>
</property>
<property>
<name>hive.zookeeper.quorum</name>
<value>dmcloud17,dmcloud18,dmcloud19</value>
<description>
List of ZooKeeper servers to talk to. This is needed for:
1. Read/write locks - when hive.lock.manager is set to
org.apache.hadoop.hive.ql.lockmgr.zookeeper.ZooKeeperHiveLockManager,
2. When HiveServer2 supports service discovery via Zookeeper.
3. For delegation token storage if zookeeper store is used, if
hive.cluster.delegation.token.store.zookeeper.connectString is not set
4. LLAP daemon registry service
</description>
</property>
<property>
<name>hive.async.log.enabled</name>
<value>false</value>
<description>
Whether to enable Log4j2's asynchronous logging. Asynchronous logging can give
significant performance improvement as logging will be handled in separate thread
that uses LMAX disruptor queue for buffering log messages.
Refer https://logging.apache.org/log4j/2.x/manual/async.html for benefits and
drawbacks.
</description>
</property>
<property>
<name>hive.server2.logging.operation.log.location</name>
<value>/data/cloud/hive/operation_logs</value>
<description>Top level directory where operation logs are stored if logging functionality is enabled</description>
</property>
<property>
<name>hive.server2.enable.doAs</name>
<value>false</value>
<description>
Setting this property to true will have HiveServer2 execute
Hive operations as the user making the calls to it.
</description>
</property>
<property>
<name>spark.yarn.jars</name>
<value>/data/app/spark/jars/*</value>
</property>
<property>
<name>hive.execution.engine</name>
<value>spark</value>
</property>
<property>
<name>hbase.zookeeper.quorum</name>
<value>dmcloud17,dmcloud18,dmcloud19</value>
</property>
<property>
<name>hive.metastore.event.db.notification.api.auth</name>
<value>false</value>
</property>
<property>
<name>hive.cli.print.current.db</name>
<value>true</value>
<description>Whether to include the current database in the Hive prompt.</description>
</property>
<property>
<name>hive.exec.mode.local.auto</name>
<value>true</value>
<description>Let Hive determine whether to run in local mode automatically</description>
</property>
<property>
<name>hive.vectorized.execution.enabled</name>
<value>true</value>
</property>
<property>
<name>hive.vectorized.execution.reduce.enabled</name>
<value>true</value>
</property>
<property>
<name>hive.compute.query.using.stats</name>
<value>true</value>
</property>
<property>
<name>hive.stats.fetch.column.stats</name>
<value>true</value>
</property>
<property>
<name>hive.stats.fetch.partition.stats</name>
<value>true</value>
</property>
<property>
<name>hive.exec.mode.local.auto</name>
<value>true</value>
</property>
<property>
<name>hive.exec.mode.local.auto.inputbytes.max</name>
<value>50000000</value>
</property>
<property>
<name>hive.exec.mode.local.auto.input.files.max</name>
<value>4</value>
</property>
<property>
<name>hive.exec.parallel</name>
<value>true</value>
</property>
<property>
<name>hive.exec.parallel.thread.number</name>
<value>16</value>
</property>
<property>
<name>mapreduce.map.speculative</name>
<value>true</value>
</property>
<property>
<name>mapreduce.reduce.speculative</name>
<value>true</value>
</property>
<property>
<name>hive.mapred.reduce.tasks.speculative.execution</name>
<value>true</value>
</property>
<property>
<name>hive.input.format</name>
<value>org.apache.hadoop.hive.ql.io.CombineHiveInputFormat</value>
</property>
<property>
<name>hive.merge.mapfiles</name>
<value>true</value>
</property>
<property>
<name>hive.merge.mapredfiles</name>
<value>true</value>
</property>
<property>
<name>hive.merge.size.per.task</name>
<value>268435456</value>
</property>
<property>
<name>hive.merge.smallfiles.avgsize</name>
<value>16777216</value>
</property>
<property>
<name>hive.fetch.task.conversion</name>
<value>more</value>
</property>
<property>
<name>hive.map.aggr</name>
<value>true</value>
</property>
<property>
<name>hive.groupby.mapaggr.checkinterval</name>
<value>100000</value>
</property>
<property>
<name>mapreduce.job.jvm.numtasks</name>
<value>10</value>
<description>
How many tasks to run per jvm. If set to -1, there isno limit.
</description>
</property>
</configuration>