第7天hive

1 sqoop  hadoop01  192.168.8.110 

   hive   hadoop03    192.168.8.113 
   mysql  hadoop04  192.168.8.114  密码：mysql  -uroot -p123456
 2 tar -zxvf apache-hive-0.13.0-bin.tar.gz -C /itcast/
 3 chown -R root:root 
 4 C:\Windows\System32\drivers\etc-->hosts

 5 ctrl+v  D d

============================================

hive是基于Hadoop的一个数据仓库工具，可以将结构化的数据文件映射为一张数据库表，并提供简单的sql查询功能，可以将sql语句转换为MapReduce任务进行运行。 其优点是学习成本低，可以通过类SQL语句快速实现简单的MapReduce统计，不必开发专门的MapReduce应用，十分适合数据仓库的统计分析。

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>
==============================
<property>
 <name>javax.jdo.option.ConnectionURL</name>
 <value>jdbc:mysql://hadoop04:3306/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>123456</value>
 <description>password to use against metastore database</description>
</property>
========================================
scp /itcast/hadoop-2.2.0/etc/hadoop/{ core-site.xml, hdfs-site.xml} 


192.168.8.113:/itcast/apache-hive-0.13.0-bin/lib
=========================
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;
===========
GRANT ALL PRIVILEGES ON *.* TO 'root'@'%' IDENTIFIED BY '123456' WITH GRANT OPTION;
FLUSH PRIVILEGES;
==================
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);




=======================================================
1 元数据库 
mysql  作为metastore
安装mysql
=====================================
rpm -qa | grep mysql   //过滤mysql 获取冲突的包并删除
rpm -e mysql-libs-5.1.66-2.el6_3.i686 --nodeps  //删除冲突的包
安装mysql：
rpm -ivh MySQL-server-5.1.73-1.glibc23.i386.rpm //安装mysql 服务端
rpm -ivh MySQL-client-5.1.73-1.glibc23.i386.rpm //安装mysql 客户端
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
=============
hadoop fs -rmr /user/hive  //删除以前的数据
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://hadoop03:3306/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>123456</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;