安裝Hive(獨立模式 使用mysql鏈接)

安裝Hive(獨立模式 使用mysql鏈接)

1.默認安裝了java+hadoop
2.下載對應hadoop版本的安裝包
3.解壓安裝包
	tar zxvf apache-hive-1.2.1-bin.tar.gz
4.安裝mysql
	yum -y install mysql-server mysql mysqldev  //須要以root身份運行   另外可能須要配置yum源
	mysql經常使用命令:
		service mysqld start/stop
		chkconfig mysqld on //加入開機啓動 以系統root用戶操做
5.受權mysql(以系統hadoop身份 數據庫root身份進行操做)
	mysqladmin -u root password "root" //修改root密碼爲root
	mysql -uroot -p密碼  (初始密碼爲空)
	
	create user 'hive' identified by 'hive'; //建立用於鏈接的hive用戶 密碼爲hive
	grant all privileges on *.* to 'hive'@'%' identified by "hive" with grant option;
	flush privileges; //刷新權限
	
	grant all privileges on *.* to 'hive'@'localhost' identified by "hive" with grant option;
	flush privileges; //刷新權限
	
	grant all privileges on *.* to 'hive'@'hadoop.master' identified by "hive" with grant option;
	flush privileges; //刷新權限
	
	set global binlog_format='MIXED'; //設置格式  必須執行。否則報錯
	
	exit;
	service mysqld restart   //重啓服務
6.測試鏈接
	mysql -hhadoop.master -uhive -phive  //能進去則表示設置成功
	create database hive; //建立鏈接數據庫hive
	alter database hive character set latin1;
	
7.配置環境變量(/etc/profile)
	#hive
	export HIVE_HOME=/opt/hive-1.2.1
	export HIVE_AUX_JARS_PATH=/opt/hive-1.2.1/lib
	export HIVE_CONF_DIR=/opt/hive-1.2.1/conf
	export PATH=$PATH:$HIVE_HOME/bin
	export CLASSPATH=$CLASSPATH:$HIVE_HOME/lib
	保存退出
	source /etc/profile	
8.修改配置文件
	1.根據模版複製配置文件
		cp hive-default.xml.template hive-site.xml
		cp hive-env.sh.template hive-env.sh
		cp hive-log4j.properties.template hive-log4j.properties
	2.修改配置文件
		####hive-site.xml####
		//添加項目   --0.11 版本之後可不用添加此項
		<property>
		<name>hive.metastore.local</name>
		<value>false</value>
		</property>
		
		//修改項目
		<property>
		<name>javax.jdo.option.ConnectionURL</name>
		<value>jdbc:mysql://hadoop.master:3306/hive</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>hive</value>
		<description>Username to use against metastore database</description>
	    </property>
		
		<property>
		<name>javax.jdo.option.ConnectionPassword</name>
		<value>hive</value>
		<description>password to use against metastore database</description>
		</property>
		
		<property>
		<name>hive.exec.local.scratchdir</name>
		<value>/opt/hive-1.2.1/tmp</value>        //須要建立此目錄
		<description>Local scratch space for Hive jobs</description>
		</property>
		
		<property>
		<name>hive.downloaded.resources.dir</name>
		<value>/opt/hive-1.2.1/tmp</value>
		<description>Temporary local directory for added resources in the remote file system.</description>
		</property>
		
		
		<property>
		<name>hive.hwi.war.file</name>
		<value>/opt/hive-1.2.1/lib/hive-hwi-1.2.1.jar</value>
		<description>This sets the path to the HWI war file, relative to ${HIVE_HOME}. </description>
	    </property>
		
		####hive-env.sh####
		HADOOP_HOME=/opt/hadoop-2.5.2
		
		####hive-log4j.properties####
		hive.log.threshold=ALL
		hive.root.logger=INFO,DRFA
		hive.log.dir=/opt/hive-1.2.1/logs  //需建立相應目錄
		hive.log.file=hive.log
9.其餘配置項
	1.hdfs上建立相應文件夾並修改權限
		hadoop fs -mkdir -p /tmp/hive
		hadoop fs -chmod 777 /tmp/hive
		hadoop fs -mkdir -p /user/hive
		hadoop fs -chmod 777 /user/hive
	2.修改hadoop hadoop-env.sh配置文件
		export HADOOP_CLASSPATH=$HADOOP_CLASSPATH:$CLASSPATH
	3.將mysql jdbc jar包拷貝到lib目錄下
		cp mysql-connector-java-5.1.21.jar /opt/hive-1.2.1/lib
	4.將lib目錄下的jline-2.12.jar 拷貝到/opt/hadoop-2.5.2/share/hadoop/yarn/lib下,並將相應包重屬名
		cp /opt/hive-1.2.1/lib/jline-2.12.jar /opt/hadoop-2.5.2/share/hadoop/yarn/lib
		mv /opt/hadoop-2.5.2/share/hadoop/yarn/lib/jline-0.9.94.jar /opt/hadoop-2.5.2/share/hadoop/yarn/lib/jline-0.9.94.jar.bak
9.使用驗證
    hive --service metastore & //開機首次執行
	hive -e	"show databases;" //運行完不報錯即安裝成功
	也能夠使用hive命令行進去執行
10.經常使用命令
	1.顯示
		show tables;
		show databases;
	2.定義
	  //添加外部分區表  推薦之後就是用這種表
		create external table access_info(ip string,access_date string,url string)
		partitioned by(logdate string) row format delimited fields terminated by '\t'
		
		desc access_info;
	3.添加數據
		alter table access_info add partition(logdate='2016-01-15') location '/access'; --加載文件hdfs實際路徑  access爲文件夾名稱
		load data local inpath '/home/hadoop/huangzhijian/access.txt' into table access_info_local_file;  --加載本地文件
	3.查詢
		select * from access_info;
	4.刪除
		drop table access_info;  //外部表不會刪除本來數據  內部表就會刪除原數據
	
	//注意不能update
	
	5.其餘
	    1.hive –f test.sql
		  ####test.sql####
		  select * from t1;
		  select count(*) from t1;
	    2.hive -e 'hql語句'
		3.hive -S -e 'select * from t1'(用法與第一種方式的靜音模式同樣，不會顯示mapreduce的操做過程)
		4.hive -e 'select * from t1'  > test.txt  （將結果輸出到本地文件中）