知行天下

<property>
<name>hive.execution.engine</name>
<value>spark</value>
</property>
<property>
<name>hive.enable.spark.execution.engine</name>
<value>true</value>
</property>
<property>
<name>spark.home</name>
<value>/data/service/spark</value>
</property>
<property>
<name>spark.master</name>
<value>yarn</value>
</property>
<property>
<name>spark.submit.deployMode</name>
<value>cluster</value>
</property>
<property>
<name>spark.eventLog.enabled</name>
<value>true</value>
</property>
<property>
<name>spark.eventLog.compress</name>
<value>true</value>
</property>
<property>
<name>spark.eventLog.dir</name>
<value>viewfs://jssz-bigdata-cluster/tmp/sparklog</value>
</property>

<property>
<name>spark.serializer</name>
<value>org.apache.spark.serializer.KryoSerializer</value>
</property>

<property>
<name>spark.yarn.historyServer.address</name>
<value>http://10.69.1.34:18080</value>
</property>
<property>
<name>spark.driver.cores</name>
<value>1</value>
</property>

<property>
<name>spark.driver.memeory</name>
<value>4g</value>
</property>

<property>
<name>spark.driver.extraJavaOptions</name>
<value>-Dspark.driver.log.level=INFO -XX:+UseG1GC</value>
</property>

<property>
<name>spark.executor.memeory</name>
<value>15g</value>
</property>
<property>
<name>spark.executor.cores</name>
<value>1</value>
</property>

<property>
<name>spark.executor.extraJavaOptions</name>
<value>-verbose:gc -XX:+PrintGCDetails -XX:+PrintGCDateStamps -XX:+UseG1GC</value>
</property>

<property>
<name>spark.shuffle.service.enabled</name>
<value>true</value>
</property>
<property>
<name>spark.dynamicAllocation.enabled</name>
<value>true</value>
</property>
<property>
<name>spark.dynamicAllocation.minExecutors</name>
<value>1</value>
</property>
<property>
<name>spark.dynamicAllocation.maxExecutors</name>
<value>50</value>
</property>
<property>
<name>spark.dynamicAllocation.schedulerBacklogTimeout</name>
<value>10s</value>
</property>
<property>
<name>hive.spark.client.rpc.max.size</name>
<value>268435456</value>
</property>
<property>
<name>spark.rpc.message.maxSize</name>
<value>256</value>
</property>
<property>
<name>spark.scheduler.mode</name>
<value>FAIR</value>
</property>
<property>
<name>spark.blacklist.enabled</name>
<value>true</value>
</property>
<property>
<name>spark.speculation</name>
<value>true</value>
</property>
<property>
<name>spark.task.maxFailures</name>
<value>10</value>
</property>
<property>
<name>spark.rdd.compress</name>
<value>true</value>
</property>
<property>
<name>spark.executor.heartbeatInterval</name>
<value>20s</value>
</property>
<property>
<name>spark.network.timeout</name>
<value>120s</value>
</property>

<!-- 解决shuffle 的问题 -->
<property>
<name>spark.sql.tungsten.enabled</name>
<value>true</value>
</property>
<!-- 解决UDF的问题 -->
<property>
<name>spark.jars</name>
<value>/data/service/hive/lib/com.bilibili.hiveudf.jar</value>
</property>

</div>
<div>SparkSubmit --properties-file /tmp/spark-submit.3467179554612125337.properties --class org.apache.hive.spark.client.RemoteDriver /data/src/hive/apache-hive-2.3.4-bin/lib/hive
-exec-2.3.4.jar --remote-host jssz-bigdata-hive-04 --remote-port 16317 --conf hive.spark.client.connect.timeout=1000 --conf hive.spark.client.server.connect.timeout=90000 --conf hive.spark.client.channel.
log.level=null --conf hive.spark.client.rpc.max.size=1195725856 --conf hive.spark.client.rpc.threads=8 --conf hive.spark.client.secret.bits=256 --conf hive.spark.client.rpc.server.address=null</div>
<div>