HIVE的搭建

HIVE的安装

参考：Hive安装 - Hive教程™ (yiibai.com)

安装包下载：Index of /infosystems/apache/hive/hive-1.2.2 (kddi-research.jp)

# 解压程序包到指定目录下/usr/local
tar -axvf apache-hive-3.1.2-bin.tar.gz -C /usr/local

# 切换到指定目录下
cd /usr/local

# 更改目录名
mv apache-hive-3.1.2-bin.tar.gz hive

# 配置HIVE中的环境配置：HADOOP_HOME=/usr/local/hadoop-2.7.3
[root@master conf]# cp hive-env.sh.template hive-env.sh
[root@master conf]# 
[root@master conf]# pwd
/usr/local/hive/conf
[root@master conf]# vim hive-env.sh # 配置HADOOP_HOME变量
[root@master conf]# 


# 设置环境变量
echo 'export HIVE_HOME=/usr/local/hive
export PATH=$PATH:$HIVE_HOME/bin
export CLASSPATH=$CLASSPATH:/usr/local/hadoop-2.7.3/lib/*:.
export CLASSPATH=$CLASSPATH:/usr/local/hive/lib/*:.' >> /etc/profile

# 使环境配置立即生效
source /etc/profile

安装 Derby数据库

 wget http://archive.apache.org/dist/db/derby/db-derby-10.4.2.0/db-derby-10.4.2.0-bin.tar.gz
 mkdir /usr/local/derby
 tar -zxvf db-derby-10.4.2.0-bin.tar.gz -C /usr/local/derby
 
echo 'export DERBY_HOME=/usr/local/derby
export PATH=$PATH:$DERBY_HOME/bin
export CLASSPATH=$CLASSPATH:$DERBY_HOME/lib/derby.jar:$DERBY_HOME/lib/derbytools.jar' >> /etc/profile

source /etc/profile

# 创建一个名为data目录在$DERBY_HOME目录中，用于存储Metastore数据。
mkdir $DERBY_HOME/data

配置Hive的Metastore

通过编辑hive-site.xml 文件来指定Hive的数据库存储。

cp hive-default.xml.template hive-default.xml
# 编辑hive-site.xml并在<configuration>和</configuration>标记之间追加以下行：
  <property>
     <name>javax.jdo.option.ConnectionURL</name>
     <value>jdbc:derby://localhost:1527/metastore_db;create=true </value>
     <description>JDBC connect string for a JDBC metastore </description>
  </property>

# 创建一个文件名为 jpox.properties 并添加以下行：
javax.jdo.PersistenceManagerFactoryClass = org.jpox.PersistenceManagerFactoryImpl
org.jpox.autoCreateSchema = false
org.jpox.validateTables = false
org.jpox.validateColumns = false
org.jpox.validateConstraints = false
org.jpox.storeManagerType = rdbms
org.jpox.autoCreateSchema = true
org.jpox.autoStartMechanismMode = checked
org.jpox.transactionIsolation = read_committed
javax.jdo.option.DetachAllOnCommit = true
javax.jdo.option.NontransactionalRead = true
javax.jdo.option.ConnectionDriverName = org.apache.derby.jdbc.ClientDriver
javax.jdo.option.ConnectionURL = jdbc:derby://hadoop1:1527/metastore_db;create = true
javax.jdo.option.ConnectionUserName = APP
javax.jdo.option.ConnectionPassword = mine

# 运行Hive之前，需要创建在HDFS独立的Hive文件夹/tmp。在这里使用/user/hive/warehouse文件夹。
# 需要给这些新创建的文件夹写权限
hdfs dfs -mkdir /tmp 
hdfs dfs -mkdir -p /user/hive/warehouse
hdfs dfs -chmod g+w /tmp 
hdfs dfs -chmod g+w /user/hive/warehouse

# 进入hive命令行
[root@master conf]# 
[root@master conf]# hive
Logging initialized using configuration in jar:file:/usr/local/hive/lib/hive-common-1.2.2.jar!/hive-log4j.properties
hive> show tables;
OK
Time taken: 0.979 seconds
hive> 

使用beeline连接HIVE

# 先启动 metastore 服务
nohup hive --service metastore > /dev/null 2>&1 &

# 再启动 hiveserver2 服务
nohup hiveserver2 > /dev/null 2>&1 &

# 第一种连接方式
beeline -u jdbc:hive2://master:10000 -n root

# 配置alias
alias beeline='beeline -u jdbc:hive2://master:10000 -n root'

# 第二种连接方式
[root@master derby]# beeline             # 进入beeline
Beeline version 1.2.2 by Apache Hive
beeline> !connect jdbc:hive2://master:10000  # 连接hive
Connecting to jdbc:hive2://master:10000
Enter username for jdbc:hive2://master:10000: root # 设置用户
Enter password for jdbc:hive2://master:10000: **** # 设置密码
Connected to: Apache Hive (version 1.2.2)
Driver: Hive JDBC (version 1.2.2)
Transaction isolation: TRANSACTION_REPEATABLE_READ
0: jdbc:hive2://master:10000> show tables; # 查看所有
+-----------+--+
| tab_name  |
+-----------+--+
| cx_stu01  |
| cx_stu02  |
+-----------+--+
2 rows selected (0.277 seconds)
0: jdbc:hive2://master:10000>