参考:
Apache hive 3.1.2从单机到高可用部署 HiveServer2高可用 Metastore高可用 hive on spark hiveserver2 web UI 高可用集群启动脚本_薛定谔的猫不吃猫粮的博客-CSDN博客
没用里头的hive on spark,测试后发现版本冲突
一、Hive 集群规划(蓝色部分)
| ck1 | ck2 | ck3 |
| SecondaryNameNode | NameNode | |
| DataNode | DataNode | DataNode |
| ResourceManager | ||
| yarn historyserver | ||
| NodeManager | NodeManager | NodeManager |
| MySQL | ||
| hiveServer2 | hiveServer2 | |
| hiveMetastore | hiveMetastore | |
| Spark | ||
| Spark JobHistoryServer |
二、配置文件
记得向hive的lib导入mysql6以上的安装包，否则：
[hive]报错:Caused by: java.lang.ClassNotFoundException: com.mysql.cj.jdbc.Driver_胖胖学编程的博客-CSDN博客
1、ck3和ck2相同的
1)hive-env.sh 末尾添加3行：
# Set HADOOP_HOME to point to a specific hadoop install directory
HADOOP_HOME=/home/data_warehouse/module/hadoop-3.1.3
# Hive Configuration Directory can be controlled by:
export HIVE_CONF_DIR=/home/data_warehouse/module/hive-3.1.2/conf
# Folder containing extra libraries required for hive compilation/execution can be controlled by:
export HIVE_AUX_JARS_PATH=/home/data_warehouse/module/hive-3.1.2/lib
2)环境变量
#HIVE_HOME
export HIVE_HOME=/home/data_warehouse/module/hive-3.1.2
export PATH=$PATH:$HIVE_HOME/bin2、ck3和ck2不同的
ck3
hive-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<!-- jdbc 连接的 URL -->
<property>
<name>javax.jdo.option.ConnectionURL</name>
<value>jdbc:mysql://ck3:3306/metastore?useSSL=false</value>
</property>
<!-- jdbc 连接的 Driver-->
<property>
<name>javax.jdo.option.ConnectionDriverName</name>
<value>com.mysql.cj.jdbc.Driver</value>
</property>
<!-- jdbc 连接的 username-->
<property>
<name>javax.jdo.option.ConnectionUserName</name>
<value>root</value>
</property>
<!-- jdbc 连接的 password -->
<property>
<name>javax.jdo.option.ConnectionPassword</name>
<value>123456</value>
</property>
<!-- Hive 元数据存储版本的验证 -->
<property>
<name>hive.metastore.schema.verification</name>
<value>false</value>
</property>
<!--元数据存储授权-->
<property>
<name>hive.metastore.event.db.notification.api.auth</name>
<value>false</value>
</property>
<!-- 指定存储元数据要连接的地址
<property>
<name>hive.metastore.uris</name>
<value>thrift://ck3:9083</value>
</property> -->
<!-- Hive 默认在 HDFS 的工作目录 -->
<property>
<name>hive.metastore.warehouse.dir</name>
<value>/user/hive/warehouse</value>
</property>
<property>
<name>hive.cli.print.current.db</name>
<value>true</value>
</property>
<property>
<name>hive.cli.print.header</name>
<value>true</value>
</property>
<property>
<name>hive.server2.session.check.interval</name>
<value>60000</value>
</property>
<property>
<name>hive.aux.jars.path</name>
<value>/home/data_warehouse/module/hive-3.1.2/lib</value>
</property>
<property>
<name>hive.execution.engine</name>
<value>mr</value>
</property>
<!--hive metastore高可用-->
<property>
<name>hive.metastore.uris</name>
<value>thrift://ck2:9083,thrift://ck3:9083</value>
</property>
<!--hiveserver2高可用-->
<property>
<name>hive.server2.support.dynamic.service.discovery</name>
<value>true</value>
</property>
<!-- <property>
<name>hive.server2.active.passive.ha.enable</name>
<value>true</value>
</property> -->
<property>
<name>hive.server2.zookeeper.namespace</name>
<value>hiveserver2_zk</value>
</property>
<property>
<name>hive.zookeeper.quorum</name>
<value>ck1:2181,ck2:2181,ck3:2181</value>
</property>
<property>
<name>hive.zookeeper.client.port</name>
<value>2181</value>
</property>
<!--填写节点, 如ck2,ck3 注意要填写本机的hostname-->
<property>
<name>hive.server2.thrift.bind.host</name>
<value>ck3</value>
</property>
<property>
<name>hive.server2.thrift.port</name>
<value>10000</value>
</property>
<!--hiveserver2 webui-->
<property>
<name>hive.server2.webui.host</name>
<value>ck3</value>
</property>
<property>
<name>hive.server2.webui.port</name>
<value>10002</value>
</property>
<!-- <property>
<name>hive.server2.idle.session.timeout</name>
<value>3600000</value>
</property> -->
</configuration>
ck2
hive-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<!-- jdbc 连接的 URL -->
<property>
<name>javax.jdo.option.ConnectionURL</name>
<value>jdbc:mysql://ck3:3306/metastore?useSSL=false</value>
</property>
<!-- jdbc 连接的 Driver-->
<property>
<name>javax.jdo.option.ConnectionDriverName</name>
<value>com.mysql.cj.jdbc.Driver</value>
</property>
<!-- jdbc 连接的 username-->
<property>
<name>javax.jdo.option.ConnectionUserName</name>
<value>root</value>
</property>
<!-- jdbc 连接的 password -->
<property>
<name>javax.jdo.option.ConnectionPassword</name>
<value>123456</value>
</property>
<!-- Hive 元数据存储版本的验证 -->
<property>
<name>hive.metastore.schema.verification</name>
<value>false</value>
</property>
<!--元数据存储授权-->
<property>
<name>hive.metastore.event.db.notification.api.auth</name>
<value>false</value>
</property>
<!-- 指定存储元数据要连接的地址
<property>
<name>hive.metastore.uris</name>
<value>thrift://ck3:9083</value>
</property> -->
<!-- Hive 默认在 HDFS 的工作目录 -->
<property>
<name>hive.metastore.warehouse.dir</name>
<value>/user/hive/warehouse</value>
</property>
<property>
<name>hive.cli.print.current.db</name>
<value>true</value>
</property>
<property>
<name>hive.cli.print.header</name>
<value>true</value>
</property>
<property>
<name>hive.server2.session.check.interval</name>
<value>60000</value>
</property>
<property>
<name>hive.aux.jars.path</name>
<value>/home/data_warehouse/module/hive-3.1.2/lib</value>
</property>
<property>
<name>hive.execution.engine</name>
<value>mr</value>
</property>
<!--hive metastore高可用-->
<property>
<name>hive.metastore.uris</name>
<value>thrift://ck2:9083,thrift://ck3:9083</value>
</property>
<!--hiveserver2高可用-->
<property>
<name>hive.server2.support.dynamic.service.discovery</name>
<value>true</value>
</property>
<!-- <property>
<name>hive.server2.active.passive.ha.enable</name>
<value>true</value>
</property> -->
<property>
<name>hive.server2.zookeeper.namespace</name>
<value>hiveserver2_zk</value>
</property>
<property>
<name>hive.zookeeper.quorum</name>
<value>ck1:2181,ck2:2181,ck3:2181</value>
</property>
<property>
<name>hive.zookeeper.client.port</name>
<value>2181</value>
</property>
<!--填写节点, 如ck2,ck3 注意要填写本机的hostname-->
<property>
<name>hive.server2.thrift.bind.host</name>
<value>ck2</value>
</property>
<property>
<name>hive.server2.thrift.port</name>
<value>10000</value>
</property>
<!--hiveserver2 webui-->
<property>
<name>hive.server2.webui.host</name>
<value>ck2</value>
</property>
<property>
<name>hive.server2.webui.port</name>
<value>10002</value>
</property>
<!-- <property>
<name>hive.server2.idle.session.timeout</name>
<value>3600000</value>
</property> -->
</configuration>
三、运行hiveserver2和hive metastore服务的脚本（ck2，ck3相同,下面缺一不可)
将这两个脚本放在/home/data_warehouse/module/hive-3.1.2/bin下，并chmod 777
1、hiveservices.sh
#!/bin/bash
HIVE_LOG_DIR=$HIVE_HOME/logs
mkdir -p $HIVE_LOG_DIR
#检查进程是否运行正常，参数1为进程名，参数2为进程端口
function check_process()
{
pid=$(ps -ef 2>/dev/null | grep -v grep | grep -i $1 | awk '{print $2}')
ppid=$(netstat -nltp 2>/dev/null | grep $2 | awk '{print $7}' | cut -d '/' -f 1)
echo $pid
[[ "$pid" =~ "$ppid" ]] && [ "$ppid" ] && return 0 || return 1
}
function hive_start()
{
metapid=$(check_process HiveMetastore 9083)
cmd="nohup hive --service metastore >$HIVE_LOG_DIR/metastore.log 2>&1 &"
cmd=$cmd" sleep 4; hdfs dfsadmin -safemode wait >/dev/null 2>&1"
[ -z "$metapid" ] && eval $cmd || echo "Metastroe服务已启动"
server2pid=$(check_process HiveServer2 10000)
cmd="nohup hive --service hiveserver2 >$HIVE_LOG_DIR/hiveServer2.log 2>&1 &"
[ -z "$server2pid" ] && eval $cmd || echo "HiveServer2服务已启动"
}
function hive_stop()
{
metapid=$(check_process HiveMetastore 9083)
[ "$metapid" ] && kill $metapid || echo "Metastore服务未启动"
server2pid=$(check_process HiveServer2 10000)
[ "$server2pid" ] && kill $server2pid || echo "HiveServer2服务未启动"
}
case $1 in
"start")
hive_start
;;
"stop")
hive_stop
;;
"restart")
hive_stop
sleep 2
hive_start
;;
"status")
check_process HiveMetastore 9083 >/dev/null && echo "Metastore服务运行正常" || echo "Metastore服务运行异常"
check_process HiveServer2 10000 >/dev/null && echo "HiveServer2服务运行正常" || echo "HiveServer2服务运行异常"
;;
*)
echo Invalid Args!
echo 'Usage: '$(basename $0)' start|stop|restart|status'
;;
esac
2、hive2server.sh
#!/bin/bash
if [ $# -lt 1 ]
then
echo "No Args Input..."
exit ;
fi
case $1 in
"start")
echo " =================== ck3 启动 HiveServer2和Metastore服务 ==================="
ssh ck3 "/home/data_warehouse/module/hive-3.1.2/bin/hiveservices.sh start"
echo " =================== ck2 启动 HiveServer2和Metastore服务 ==================="
ssh ck2 "/home/data_warehouse/module/hive-3.1.2/bin/hiveservices.sh start"
;;
"stop")
echo " =================== ck3 停止 HiveServer2和Metastore服务 ==================="
ssh ck3 "/home/data_warehouse/module/hive-3.1.2/bin/hiveservices.sh stop"
echo " =================== ck2 停止 HiveServer2和Metastore服务 ==================="
ssh ck2 "/home/data_warehouse/module/hive-3.1.2/bin/hiveservices.sh stop"
;;
"status")
echo " =================== ck3 查看 HiveServer2和Metastore服务 ==================="
ssh ck3 "/home/data_warehouse/module/hive-3.1.2/bin/hiveservices.sh status"
echo " =================== ck2 查看 HiveServer2和Metastore服务 ==================="
ssh ck2 "/home/data_warehouse/module/hive-3.1.2/bin/hiveservices.sh status"
;;
*)
echo "Input Args Error...start|stop|status"
;;
esac
四、启动hiveserver2和metastire服务
1、启动 :在ck3或ck2上:hive2server.sh start
2、查看状态 :在ck3或ck2上:hive2server.sh status
3、关闭 :在ck3或ck2上:hive2server.sh stop
五、使用
依次输入下面两个命令
beeline
!connect jdbc:hive2://ck1,ck2,ck3/;password=123456;serviceDiscoveryMode=zooKeeper;zooKeeperNamespace=hiveserver2_zk root
