在 WSL2 Ubuntu 20.04 上安装 Hive

下载

HIVE 3.1.3 下载下来解压

sudo tar -zxvf apache-hive-3.1.3-bin.tar.gz -C ~

配置

在 ./bashrc 里添加 Hive 环境：

## Hive env
export HIVE_HOME=~/apps/hive-3.1.3
export PATH=$PATH:$HIVE_HOME/bin

将 mysql-connector-java-8.0.28.jar 放在 $HIVE_HOME/lib 下,

在 MySQL 中配置 Hive 元数据库

mysql -u root -p
mysql> create database hive;
mysql> CREATE USER hive@localhost IDENTIFIED BY 'hive';
mysql> GRANT ALL PRIVILEGES ON *.* TO hive@localhost WITH GRANT OPTION;
mysql> FLUSH PRIVILEGES;

在 $HIVE_HOME/conf 下新建 hive-default.xml

cp hive-default.xml.template hive-default.xml

新建 hive-site.xml, 并添加以下内容：

<?xml version="1.0" encoding="utf-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<configuration> 
  <property> 
    <name>javax.jdo.option.ConnectionURL</name>  
    <value>jdbc:mysql://localhost:3306/hive?createDatabaseIfNotExist=true</value>  
    <description>JDBC connect string for a JDBC metastore</description> 
  </property>  
  <property> 
    <name>javax.jdo.option.ConnectionDriverName</name>  
    <value>com.mysql.cj.jdbc.Driver</value>  
    <description>Driver class name for a JDBC metastore</description> 
  </property>  
  <property> 
    <name>javax.jdo.option.ConnectionUserName</name>  
    <value>hive</value>  
    <description>username to use against metastore database</description> 
  </property>  
  <property> 
    <name>javax.jdo.option.ConnectionPassword</name>  
    <value>hive</value>  
    <description>password to use against metastore database</description> 
  </property>  
  <property> 
    <name>hive.server2.thrift.client.user</name>  
    <value>herman</value>  
    <description>Username to use against thrift client</description> 
  </property>  
  <property> 
    <name>hive.server2.thrift.client.password</name>  
    <value>[password]</value>  
    <description>Password to use against thrift client</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>hive.metastore.uris</name>  
    <value>thrift://localhost:9083</value> 
  </property>
  <property> 
    <name>hive.metastore.event.db.notification.api.auth</name>  
    <value>false</value> 
  </property> 
</configuration>

在 $HADOOP_HOME/etc/hadoop/core-site.xml 中添加下面内容：

<property> 
  <name>hadoop.proxyuser.hadoop.hosts</name>  
  <value>*</value> 
</property>  
<property> 
  <name>hadoop.proxyuser.hadoop.groups</name>  
  <value>*</value> 
</property>

启动 Hive CLI

启动 HADOOP 集群 start-dfs.sh, Hive 第一次启动要格式化 Hive Shema:

$HIVE_HOME/bin/schematool -dbType mysql -initSchema

启动 hive 验证是否安装成功:

hive>
hive>exit;

启动 Beeline

先启动 metastore 和 hiveserver2 服务：

nohup hive --service metastore 1>/dev/null 2>&1 &
nohup hive --service hiveserver2 1>/dev/null 2>&1 &

启动 Beeline 并连接 Hive:

beeline
beeline> !connect jdbc:hive2://localhost:10000
Connected to: Apache Hive (version 3.1.3)
Driver: Hive JDBC (version 2.3.9)
Transaction isolation: TRANSACTION_REPEATABLE_READ
0: jdbc:hive2://localhost:10000>

Hive 启动脚本

sudo vim $HIVE_HOME/bin/hive.sh

#!/bin/bash

mkdir -p $HIVE_HOME/log

status(){
    ps -ef | grep -v grep | grep -E 'HiveMetaStore|HiveServer2'
}

start(){
    status &>/dev/null && { echo "Stop HiveMetaStore or HiveServer2 first!";exit 1; }
    nohup $HIVE_HOME/bin/hive --service metastore &> $HIVE_HOME/log/metastore.log &
    nohup $HIVE_HOME/bin/hive --service hiveserver2 &> $HIVE_HOME/log/metastore.log &
    sleep 1 && echo "HiveMetaStore & HiveServer2 started!"

    ip addr | grep "eth0" | grep "inet" | cut -d " " -f 6 | cut -d / -f 1
}

stop(){
    if status &>/dev/null
    then
        status | awk '{print $2}' | xargs kill -9
        echo "HiveMetaStore & HiveServer2 stopped!"
    else
        echo "HiveMetaStore & HiveServer2 not found!"
    fi
}

restart(){
    stop && start
}

case $1 in
    status) status ;;
    start) start;;
    stop) stop;;
    restart) restart;;
    *) echo "Usage: $0 <start|stop|status|restart>";;
esac

sudo vim $HIVE_HOME/bin/hive.sh

#!/bin/bash
ssh_flag=$(echo 1 | sudo -S service ssh status | grep "Active" | awk '{print $2}')
mysql_flag=$(echo 1 | sudo -S service mysql status | grep "Active" | awk '{print $2}')
dfs_flag=$(jps | grep -v grep | awk '{print $2}' | grep -E 'DataNode|NameNode|SecondaryNameNode' | sort | xargs)
yarn_flag=$(jps | grep -v grep | awk '{print $2}' | grep -E 'ResourceManager|NodeManager' | sort | xargs)


if [ $ssh_flag == "inactive" ]; then
        echo 1 | sudo -S service ssh start
        echo "ssh service start successfully"
fi

if [ $mysql_flag == 'inactive' ]; then
        echo 1 | sudo -S service mysql start
        echo "mysql service start successfully"
fi

if [ "$dfs_flag" != "DataNode NameNode SecondaryNameNode" ]; then
        start-dfs.sh
fi

if [ "$yarn_flag" != "NodeManager ResourceManager" ]; then
        start-yarn.sh
fi

hive.sh start

故障排错

cat $HIVE_HOME/log