118.Hive与Spark的集成

• Hive与Spark的版本兼容性：
  
• 测试Spark服务是否正常

spark-submit --class org.apache.spark.examples.SparkPi\
  --master yarn-client --num-executors 4 --driver-memory 2g\
  --driver-cores 1 --executor-memory 2g --executor-cores 1\
  /opt/cloudera/parcels/CDH/lib/spark/lib/spark-examples.jar 10

• spark-assembly.jar包软连至${HIVE2_HOME}/lib目录

[root@ip-xxx-xx-x-xx lib]# pwd
/opt/cloudera/HIVE2/lib
[root@ip-xxx-xx-x-xx lib]# ln -s /opt/cloudera/parcels/CDH/lib/spark/lib/spark-assembly.jar spark-assembly.jar 
[root@ip-xxx-xx-x-xx lib]# ll spark-assembly.jar

• spark-assembly.jar包上传至HDFS的/spark-jars目录

[root@ip-xxx-xx-x-xx lib]# pwd
/opt/cloudera/HIVE2/lib
[root@ip-xxx-xx-x-xx lib]# ln -s /opt/cloudera/parcels/CDH/lib/spark/lib/spark-assembly.jar spark-assembly.jar 
[root@ip-xxx-xx-x-xx lib]# ll spark-assembly.jar

• hive-site.xml配置修改

<property>
    <name>spark.master</name>
    <value>yarn-cluster</value>
</property>
<property>
    <name>hive.merge.sparkfiles</name>
    <value>true</value>
</property>
<property>
    <name>spark.executor.memory</name>
    <value>1g</value>
</property>
<property>
    <name>spark.driver.memory</name>
    <value>1g</value>
</property>
<property>
    <name>spark.executor.cores</name>
    <value>1</value>
</property>
<property>
    <name>spark.yarn.driver.memoryOverhead</name>
    <value>102</value>
</property>
<property>
    <name>spark.yarn.executor.memoryOverhead</name>
    <value>326</value>
</property>
<property>
    <name>spark.dynamicAllocation.enabled</name>
    <value>true</value>
</property>
<property>
    <name>spark.dynamicAllocation.initialExecutors</name>
    <value>1</value>
</property>
<property>
    <name>spark.dynamicAllocation.minExecutors</name>
    <value>1</value>
</property>
<property>
    <name>spark.dynamicAllocation.maxExecutors</name>
    <value>2147483647</value>
</property>
<property>
    <name>hive.spark.dynamic.partition.pruning.map.join.only</name>
    <value>false</value>
</property>
<property>
    <name>spark.shuffle.service.enabled</name>
    <value>true</value>
</property>
<property>
    <name>spark.eventLog.enabled</name>
    <value>true</value>
</property>
<property>
    <name>spark.eventLog.dir</name>
    <value>hdfs://ip-xxx-xx-x-xx.ap-southeast-1.compute.internal:8020/user/spark/applicationHistory</value>
</property>
<property>
    <name>spark.yarn.jar</name>
    <value>hdfs://ip-xxx-xx-x-xx.ap-southeast-1.compute.internal:8020/spark-jars/spark-assembly.jar</value>
</property>

• 重启HIveMetastore和HiveServer2

[root@ip-xxx-xx-x-xx ~]# hive2
[root@ip-xxx-xx-x-xx ~]# hive2-server
[root@ip-xxx-xx-x-xx ~]# ps -ef |grep -i hivemetastore
[root@ip-xxx-xx-x-xx ~]# ps -ef |grep -i hiveserver2

alias hive2="nohup /opt/cloudera/HIVE2/bin/hive --service metastore > /opt/cloudera/HIVE2/logs/hive-metastore.log 2>&1 &"
alias hive2-server="nohup /opt/cloudera/HIVE2/bin/hive --service hiveserver2 > /opt/cloudera/HIVE2/logs/hive-server2.log 2>&1 &"
alias beeline2="/opt/cloudera/HIVE2/bin/beeline"

• HiveCLI 验证

[root@ip-xxx-xx-x-xx bin]# sudo -u hive ./hive
hive> use test;
hive> set hive.execution.engine=spark;
hive> select id,count(*) from test_table group by id ;

• 测试beeline连接

[root@ip-xxx-xx-x-xx ~]# beeline2
beeline> !connect jdbc:hive2://localhost:10000 hive hive
0: jdbc:hive2://localhost:10000> use test;
0: jdbc:hive2://localhost:10000> set hive.execution.engine=spark;
0: jdbc:hive2://localhost:10000> select id,count(*) from test_table group by id;

大数据视频推荐：
CSDN
大数据语音推荐：
ELK7 stack开发运维
企业级大数据技术应用
大数据机器学习案例之推荐系统
自然语言处理
大数据基础
人工智能：深度学习入门到精通