hive安装

版本：2.3.9

下载地址：https://dlcdn.apache.org/hive/hive-2.3.9/apache-hive-2.3.9-bin.tar.gz

安装目录/opt

启动用户：hadoop

mysql安装略

解压hive

tar -zxvf apache-hive-2.3.9-bin.tar.gz
mv apache-hive-2.3.9-bin hive-2.3.9

修改配置文件

touch hive-site.xml
mv hive-env.sh.template hive-env.sh
mv hive-log4j2.properties.template hive-log4j2.properties

vi hive-site.xml

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
  <property>
    <name>javax.jdo.option.ConnectionURL</name>
    <value>jdbc:mysql://vm01:3306/hive2?createDatabaseIfNotExist=true</value>
  </property>
   <property>
    <name>javax.jdo.option.ConnectionDriverName</name>
    <value>com.mysql.jdbc.Driver</value>
  </property>
   <property>
    <name>javax.jdo.option.ConnectionUserName</name>
    <value>root</value>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionPassword</name>
    <value>123456</value>
  </property>
    <property>
    <name>hive.metastore.warehouse.dir</name>
    <value>/warehouse</value>
  </property>
  <property>
    <name>hive.zookeeper.quorum</name>
    <value>vm01:2181,vm02:2181,vm03:2181</value>
  </property>
  <property>
    <name>mapreduce.input.fileinputformat.split.maxsize</name>
    <value>512000000</value>
  </property>
  <property>
    <name>mapreduce.input.fileinputformat.split.minsize.per.node</name>
    <value>512000000</value>
  </property>
  <property>
    <name>mapreduce.input.fileinputformat.split.minsize.per.rack</name>
    <value>512000000</value>
  </property>
  <property>
    <name>hive.groupby.skewindata</name>
    <value>true</value>
  </property>
  <property>
    <name>mapreduce.map.memory.mb</name>
    <value>4096</value>
  </property>
  <property>
    <name>mapreduce.reduce.memory.mb</name>
    <value>8192</value>
  </property>
  <property>
    <name>mapreduce.map.java.opts</name>
    <value>-Xmx4000m</value>
  </property>
  <property>
    <name>mapreduce.reduce.java.opts</name>
    <value>-Xmx8000m</value>
  </property>
  <property>
    <name>mapreduce.job.reduce.slowstart.completedmaps</name>
    <value>0.9</value>
  </property>
  <property>
    <name>mapreduce.reduce.shuffle.memory.limit.percent</name>
    <value>0.2</value>
  </property>
  <property>
    <name>mapreduce.task.io.sort.mb</name>
    <value>512</value>
  </property>
  <property>
    <name>mapreduce.tasktracker.map.tasks.maximum</name>
    <value>1</value>
  </property>
  <property>
    <name>mapreduce.tasktracker.reduce.tasks.maximum</name>
    <value>2</value>
  </property>
  <property>
    <name>mapreduce.job.jvm.numtasks</name>
    <value>10</value>
  </property>
  <property>
    <name>yarn.scheduler.maximum-allocation-vcores</name>
    <value>8</value>
  </property>
  <property>
    <name>hive.metastore.schema.verification</name>
    <value>false</value>
  </property>
  <property>
    <name>datanucleus.schema.autoCreateAll</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>
  <property>
    <name>hive.merge.size.per.task</name>
    <value>512000000</value>
  </property>
  <property>
    <name>zhive.merge.smallfiles.avgsize</name>
    <value>512000000</value>
  </property>
  <property>
    <name>hive.metastore.uris</name>
    <value>thrift://vm01:9083</value>
  </property>
  <property>
    <name>hive.server2.thrift.port</name>
    <value>50000</value>
  </property>
<!--TEZ START
<property>
  <name>hive.execution.engine</name>
  <value>tez</value>
</property>
TEZ END-->
  <property>
    <name>hive.cli.print.header</name>
    <value>true</value>
  </property>

  <property>
    <name>hive.cli.print.current.db</name>
    <value>true</value>
  </property>
</configuration>

vi hive-log4j2.properties

property.hive.log.dir = /opt/hive-2.3.9/logs

 mkdir /opt/hive-2.3.9/logs

启动

nohup bin/hive --service metastore -p 9083 &
nohup bin/hive --service hiveserver2 --hiveconf hive.server2.thrift.port 50000 &