Linux下安装Hive集群

1.安装Hadoop

2.安装MySQL

3.安装HAProxy

3.下载并解压Hive

cd /usr/local
wget http://mirror.bit.edu.cn/apache/hive/hive-1.2.2/apache-hive-1.2.2-bin.tar.gz
tar -zxvf apache-hive-1.2.2-bin.tar.gz
#重命名
mv apache-hive-1.2.2-bin hive
#在Hadoop上创建Hive路径地址
hdfs dfs -mkdir -p /usr/local/hive/warehouse
hdfs dfs -mkdir -p /usr/local/hive/tmp
hdfs dfs -chmod 777 /usr/local/hive/warehouse
hdfs dfs -chmod 777 /usr/local/hive/tmp
#配置环境变量
export HIVE_HOME=/usr/local/hive
export PATH=$PATH:$HIVE_HOME/bin
#配置HADOOP_HOME
cp /usr/local/hive/conf/hive-env.sh.template /usr/local/hive/conf/hive-env.sh
HADOOP_HOME=/usr/local/hadoop-2.7.1
#配置日志信息
mkdir /usr/local/hive/log
cp /usr/local/hive/conf/hive-log4j.properties.template /usr/local/hive/conf/hive-log4j.properties
vi $HIVE_HOME/conf/hive-log4j.properties
hive.log.dir=/usr/local/hive/log
hive.log.file=hive.log
#配置hive-site.xml文件
cp /usr/local/hive/conf/hive-default.xml.template /usr/local/hive/conf/hive-site.xml

修改hive-site.xml配置文件（找到对应的name修改value）

  <property>
    <name>hive.exec.scratchdir</name>
    <value>/usr/local/hive/tmp</value>
    <description>HDFS root scratch dir for Hive jobs which gets created with write all (733) permission. For each connecting user, an HDFS scratch dir: ${hive.exec.scratchdir}/&lt;username&gt; is created, with ${hive.scratch.dir.permission}.</description>
  </property>
    <property>
    <name>hive.metastore.warehouse.dir</name>
    <value>/usr/local/hive/warehouse</value>
    <description>location of default database for the warehouse</description>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionPassword</name>
    <value>root</value>
    <description>password to use against metastore database</description>
  </property>
 <property>
    <name>javax.jdo.option.ConnectionURL</name>
    <value>jdbc:mysql://dn1:3306/hive?createDataseIfNotExist=true&amp;characterEncoding=UTF-8&amp;useSSL=false</value>
    <description>JDBC connect string for a JDBC metastore</description>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionDriverName</name>
    <value>com.mysql.jdbc.Driver</value>
    <description>Driver class name for a JDBC metastore</description>
  </property>
  <property>
    <name>javax.jdo.option.ConnectionUserName</name>
    <value>root</value>
    <description>Username to use against metastore database</description>
  </property>
    <property>
    <name>hive.exec.local.scratchdir</name>
    <value>/usr/local/hive/log</value>
    <description>Local scratch space for Hive jobs</description>
  </property>
  <property>
    <name>hive.downloaded.resources.dir</name>
    <value>/usr/local/hive/tmp</value>
    <description>Temporary local directory for added resources in the remote file system.</description>
  </property>

#下载mysql-connector-java-5.1.46.jar到/usr/local/hive/lib中
cd /usr/local/hive/lib
wget http://central.maven.org/maven2/mysql/mysql-connector-java/5.1.46/mysql-connector-java-5.1.46.jar
#将元数据信息初始化到Mysql数据库中
schematool -initSchema -dbType mysql

如果出现下列错误，则需要自己先创建好hive数据库

#直接运行Hive SQL脚本，测试Hive是否可用（显示ok则成功）
hive -e "show tables"
#将/etc/profile和hive文件夹发给dn2和dn3两个节点
scp /etc/profile hadoop@dn2:/etc
scp /etc/profile hadoop@dn3:/etc
scp /usr/local/hive hadoop@dn2:/usr/local
scp /usr/local/hive hadoop@dn3:/usr/local
#分别在dn2和dn3两个节点下启动hiveserver2服务
source /etc/profile
hive --service hiveserver2 &
#在dn1节点启动haproxy服务
cd /usr/local/haproxy
haproxy -f config.cfg