Hive 0.13.1 설치 (Ubuntu 14.04)

Download (hadoop user)

• hadoop#> wget http://apache.mirror.cdnetworks.com/hive/hive-0.13.1/apache-hive-0.13.1-bin.tar.gz
• hadoop#> sudo tar zxvf apache-hive-0.13.1-bin.tar.gz -C /usr/local
• hadoop#> sudo mv /usr/local/apache-hive-0.13.1-bin /usr/local/hive
• hadoop#> vi ~/.bashrc
• • export HIVE_HOME=/usr/local/hive
  • export PATH=$PATH:$HIVE_HOME/bin
• hadoop#> source ~/.bashrc

Make Hive Directory

• hadoop#> hadoop fs -mkdir /tmp
• hadoop#> hadoop fs -chmod g+w /tmp
• hadoop#> hadoop fs -mkdir -p /user/hive/warehouse
• hadoop#> hadoop fs -chmod g+w /user/hive/warehouse
• hadoop#> hive
• • hive> show databases;
  • hive> exit;

Install MySQL

• hadoop#> sudo apt-get install mysql-server
• hadoop#> sudo service mysql restart

Create User and Database

• hadoop#> mysql -u root -p
• • mysql> grant all privileges on *.* to hive@localhost identified by 'hive' with grant option;
  • mysql> exit;
• hadoop#> mysql -u hive -p
• • mysql> create database hive;
  • mysql> use hive;
  • mysql> exit;

Download MySQL Connector

• hadoop#> wget http://dev.mysql.com/get/Downloads/Connector-J/mysql-connector-java-5.1.31.tar.gz
• hadoop#> tar zxvf mysql-connector-java-5.1.31.tar.gz
• hadoop#> sudo mv mysql-connector-java-5.1.31/mysql-connector-java-5.1.31-bin.jar $HIVE_HOME/lib

Connect MySQL into Hive

• hadoop#> sudo vi $HIVE_HOME/conf/hive-site.xml

<configuration>
<property>
    <name>hive.metastore.local</name>
    <value>true</value>
</property>
<property>
    <name>javax.jdo.option.ConnectionURL</name>
    <value>jdbc:mysql://localhost:3306/hive?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>hive</value>
</property>
<property>
    <name>javax.jdo.option.ConnectionPassword</name>
    <value>hive</value>
</property>
</configuration>  

Test

• hadoop#> vi /tmp/sample.csv

1,aaaa,10
2,bbbb,20
3,cccc,30
4,dddd,40
5,ffff,50

• hadoop#> hive
• • hive> CREATE TABLE custom(id INT, name STRING, score INT) ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' LINES TERMINATED BY '\n';
  • hive> LOAD DATA LOCAL INPATH '/tmp/sample.csv' OVERWRITE INTO TABLE custom;
  • hive> select * from custom;
  • hive> select count(*), avg(score) from custom where id in (1, 3, 4);
  • hive> exit;
• hadoop#> hadoop fs -ls /user/hive/warehouse/custom
• hadoop#> mysql -u hive -p
• • mysql> show databases;
  • mysql> use hive;
  • mysql> show tables;
  • mysql> SELECT * FROM hive.TBLS;