CDH配置（Zookeeper，HADOOP，Hive）

1. 第一步：ZOOKEEPER（多台机器，时间同步）

   1. 在/opt下创建chd目录：sudo mkdir cdh-5.3.6
   2. 更改所属用户与用户组：sudo chown beifeng:beifeng /opt/*
      
   3. 上传文件到/opt/software目录下：zookeeper-3.4.5-cdh5.3.6.tar，hadoop-2.5.0-cdh5.3.6.tar，hive-0.13.1-cdh5.3.6.tar，sqoop-1.4.5-cdh5.3.6.tar

   4. 解压：

      tar -zxf hadoop-2.5.0-cdh5.3.6.tar.gz -C /opt/cdh-5.3.6/
      tar -zxf hive-0.13.1-cdh5.3.6.tar.gz -C /opt/cdh-5.3.6/
      tar -zxf zookeeper-3.4.5-cdh5.3.6.tar.gz -C /opt/cdh-5.3.6/

      
      

   5. 配置伪分布式zookeeper
      之前配置分布式的步骤博客：
      http://blog.csdn.net/haoyuexihuai/article/details/53080133
   6. conf目录下 zoo.cfg 配置数据路径：dataDir=/opt/cdh-5.3.6/zookeeper-3.4.5-cdh5.3.6/datas
   7. 启动并查看zookeeper
      

2. 第二步：HADOOP
   

   1. HDFS

      1. hadoop-env.sh
         配置export JAVA_HOME=/opt/modules/jdk1.7.0_67

      2. core-site.xml

         
         <property> 
             <name>fs.defaultFSname> 
             <value>hdfs://hadoop-senior01.ibeifeng.com:8020value> 
         property>
         
         <property> 
             <name>hadoop.tmp.dirname> 
             <value>/opt/cdh-5.3.6/hadoop-2.5.0-cdh5.3.6/datavalue> 
         property>

      3. hdfs-site.xml

         
         <property> 
             <name>dfs.replicationname> 
             <value>1value> 
         property>
         
         <property>
             <name>dfs.permissions.enabledname>
             <value>falsevalue>
         property>

      4. 配置完之后格式化： bin/hdfs namenode –format

      5. 启动进程

         sbin/hadoop-daemon.sh start namenode
         sbin/hadoop-daemon.sh start datanode

      6. 打开页面：http://hadoop-senior01.ibeifeng.com:50070/

      7. HDFS操作，创建数据仓库

         1. 创建两个目录/tmp 与 /user/hive/warehouse
            bin/hdfs dfs -mkdir -p /user/hive/warehouse
         2. 赋予权限

         bin/hdfs dfs -chmod g+w /tmp
         bin/hdfs dfs -chmod g+w /user/hive/warehouse
         

      8. 配置native
         

   2. YARN

      1. yarn-env.sh
         配置export JAVA_HOME=/opt/modules/jdk1.7.0_67

      2. yarn-site.xml

         
         <property>
             <name>yarn.resourcemanager.hostnamename>
             <value>hadoop-senior01.ibeifeng.comvalue>
         property>
         
         <property>
             <name>yarn.nodemanager.aux-servicesname>
             <value>mapreduce_shufflevalue>
         property>
         
         <property>
             <name>yarn.log-aggregation-enablename>
             <value>truevalue>
         property>
         
         <property>
             <name>yarn.log-aggregation.retain-secondsname>
             <value>106800value>
         property>
         

      3. 启动进程

         sbin/yarn-daemon.sh start resourcemanager
         sbin/yarn-daemon.sh start nodemanager
         

      4. 打开页面：http://hadoop-senior01.ibeifeng.com:8088

   3. MAPREDUCE

      1. mapred-env.sh
         配置：export JAVA_HOME=/opt/modules/jdk1.7.0_67

      2. mapred-site.xml.template -》 mapred -site.xml

         
         <property>
             <name>mapreduce.framework.namename>
             <value>yarnvalue>
         property>
         
         <property> 
             <name>mapreduce.jobhistory.addressname> 
             <value>hadoop-senior01.ibeifeng.com:10020value> 
         property> 
         <property> 
             <name>mapreduce.jobhistory.webapp.addressname> 
             <value>hadoop-senior01.ibeifeng.com:19888value> 
         property>
         

      3. 启动进程：sbin/mr-jobhistory-daemon.sh start historyserver

3. 第三步：HIVE配置
   博客：http://blog.csdn.net/haoyuexihuai/article/details/53290274

   1. hive-env.sh.template，将template去掉

      HADOOP_HOME=/opt/cdh-5.3.6/hadoop-2.5.0-cdh5.3.6
      export HIVE_CONF_DIR=/opt/cdh-5.3.6/hive-0.13.1-cdh5.3.6/conf

   2. hive-site.xml

      
         <property>
           <name>javax.jdo.option.ConnectionURLname>
           <value>jdbc:mysql://hadoop-senior01.ibeifeng.com:3306/cdhmetastore?createDatabaseIfNotExist=truevalue>
         property>
         
         <property>
           <name>javax.jdo.option.ConnectionDriverNamename>
           <value>com.mysql.jdbc.Drivervalue>
         property>
         
         <property>
           <name>javax.jdo.option.ConnectionUserNamename>
           <value>rootvalue>
         property>
         <property>
           <name>javax.jdo.option.ConnectionPasswordname>
           <value>123456value>
         property>
       
      <property> 
          <name>hive.cli.print.headername> 
          <value>truevalue> 
      property> 
      <property> 
          <name>hive.cli.print.current.dbname> 
          <value>truevalue> 
      property>
       
      <property>
        <name>hive.server2.thrift.portname>
        <value>10000value>
      property>
      <property>
        <name>hive.server2.thrift.bind.hostname>
        <value>hadoop-senior01.ibeifeng.comvalue>
      property>

   3. 复制mysql的驱动到hive下

      cp -r mysql-connector-java-5.1.27-bin.jar /opt/cdh-5.3.6/hive-0.13.1-cdh5.3.6/lib/

   4. 配置hive-log4j.properties 日志目录
      在hive下先创建logs目录

      hive.root.logger=INFO,DRFA
      hive.log.dir=/opt/cdh-5.3.6/hive-0.13.1-cdh5.3.6/logs