Hive的安装

Hive只在一个节点上安装即可

1.上传tar包

2.解压
     tar -zxvf hive-0.9.0.tar.gz -C /cloud/
3.配置mysql metastore（切换到root用户）
     配置HIVE_HOME环境变量
     rpm -qa | grep mysql
     rpm -e mysql-libs-5.1.66-2.el6_3.i686 --nodeps
     rpm -ivh MySQL-server-5.1.73-1.glibc23.i386.rpm
     rpm -ivh MySQL-client-5.1.73-1.glibc23.i386.rpm
     修改mysql的密码
     /usr/bin/mysql_secure_installation
     （注意：删除匿名用户，允许用户远程连接）
     登陆mysql
     mysql -u root -p

4.配置hive
     cp hive-default.xml.template hive-site.xml
     修改hive-site.xml（删除所有内容，只留一个<property></property>）
     添加如下内容：
     <property>
       <name>javax.jdo.option.ConnectionURL</name>
       <value>jdbc:mysql://hadoop00:3306/hive?createDatabaseIfNotExist=true</value>
       <description>JDBC connect string for a JDBC metastore</description>
     </property>

     <property>
       <name>javax.jdo.option.ConnectionDriverName</name>
       <value>com.mysql.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>javax.jdo.option.ConnectionPassword</name>
       <value>123</value>
       <description>password to use against metastore database</description>
     </property>
    
5.安装hive和mysq完成后，将mysql的连接jar包拷贝到$HIVE_HOME/lib目录下
     如果出现没有权限的问题，在mysql授权(在安装mysql的机器上执行)
     mysql -uroot -p
     #(执行下面的语句  *.*:所有库下的所有表   %：任何IP地址或主机都可以连接)
     GRANT ALL PRIVILEGES ON *.* TO 'root'@'%' IDENTIFIED BY '123' WITH GRANT OPTION;
     FLUSH PRIVILEGES;

【.hiverc配置】

set hive.cli.print.current.db=true;

set hive.exec.parallel=true;

set hive.auto.convert.join=true;

set hive.exec.dynamic.partition.mode=nonstrict;

set hive.cli.print.header=true;

set hive.exec.max.dynamic.partitions=10000000;

set hive.exec.max.dynamic.partitions.pernode=10000000;

set hive.exec.mode.local.auto=true;

set mapred.max.split.size=100000000;

set mapred.min.split.size.per.node=100000000;

set mapred.min.split.size.per.rack=100000000;

set hive.input.format=org.apache.hadoop.hive.ql.io.CombineHiveInputFormat;

add jar /home/app/java/hive/java.jar

6.建表(默认是内部表)
     create table trade_detail(id bigint, account string, income double, expenses double, time string) row format delimited fields terminated by '\t';
     建分区表
     create table td_part(id bigint, account string, income double, expenses double, time string) partitioned by (logdate string) row format delimited fields terminated by '\t';
     建外部表
     create external table td_ext(id bigint, account string, income double, expenses double, time string) row format delimited fields terminated by '\t' location '/td_ext';

7.创建分区表
     普通表和分区表区别：有大量数据增加的需要建分区表
     create table book (id bigint, name string) partitioned by (pubdate string) row format delimited fields terminated by '\t';

     分区表加载数据
     load data local inpath './book.txt' overwrite into table book partition (pubdate='2010-08-22');
    
     load data local inpath '/root/data.am' into table beauty partition (nation="USA");

    
     select nation, avg(size) from beauties group by nation order by avg(size);