hadoop的五个配置文件，安装时候用

//core-site.xml
<configuration>
    <!--namenode的地址-->
     <property>
          <name>fs.defaultFS</name>
          <value>hdfs://master:9000</value>
     </property>
     <property>
          <name>io.file.buffer.size</name>
          <value>131072</value>
     </property>
    <!--存放临时文件的地址-->
     <property>
          <name>hadoop.tmp.dir</name>
          <value>file:/home/hadoop/hadoop-2.7.1/tmp</value>
          <description>Abasefor other temporary directories.</description>
     </property>
</configuration>

//hdfs-site.xml
<configuration>
    <!--配置secondnamenode的地址-->
     <property>
          <name>dfs.namenode.secondary.http-address</name>
          <value>master:9001</value>
     </property>
    <property>
          <name>dfs.namenode.rcp-address</name>
          <value>master:9000</value>
     </property>
      <property>
           <name>dfs.namenode.name.dir</name>
           <value>file:/home/hadoop/hadoop-2.7.1/dfs/name</value>
     </property>
     <property>
          <name>dfs.datanode.data.dir</name>
          <value>file:/home/hadoop/hadoop-2.7.1/dfs/data</value>
    </property>

     <property>
          <name>dfs.replication</name>
          <value>3</value>
     </property>
     <property>
          <name>dfs.webhdfs.enabled</name>
          <value>true</value>
     </property>
    <!--dfs 权限检查false -->
     <property>
          <name>dfs.permissions</name>
          <value>false</value>
     </property>
</configuration>

//yarn-site.xml
<configuration>
      <property>
           <name>yarn.nodemanager.aux-services</name>
           <value>mapreduce_shuffle</value>
      </property>
      <property>
           <name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
           <value>org.apache.hadoop.mapred.ShuffleHandler</value>
      </property>
      <!-- 开启日志 -->
         <property>
           <name>yarn.log-aggregation-enable</name>
           <value>true</value>
      </property>
       <!-- 指定日志保留的时间 -->
         <property>
           <name>yarn.log-aggregation.retain-seconds</name>
           <value>604800</value>
      </property>
     <!-- 日志放在dfs上的位置 -->
         <property>
           <name>yarn.nodemanager.remote-app-log-dir</name>
           <value>/logs</value>
      </property>
    <!--  指定resourcemanager的地址即yarn管理资源调度的地址-->
     <property>
           <name>yarn.resourcemanager.address</name>
           <value>master:8032</value>
      </property>
      <property>
           <name>yarn.resourcemanager.scheduler.address</name>
           <value>master:8030</value>
      </property>
      <property>
           <name>yarn.resourcemanager.resource-tracker.address</name>
           <value>master:8035</value>
      </property>
      <property>
           <name>yarn.resourcemanager.admin.address</name>
           <value>master:8033</value>
      </property>
    <!-- yarn(resoursemanager的地址 -->
      <property>
           <name>yarn.resourcemanager.webapp.address</name>
           <value>master:8088</value>
      </property>
      <!-- web安全任务代理的地址 -->
      <property>
           <name>yarn.web-proxy.address</name>
           <value>master:8888</value>
      </property>
    
</configuration>

//mapred-site.xml
<configuration>
    <!-- 指定用yarn进行资源调度 -->
      <property>
           <name>mapreduce.framework.name</name>
           <value>yarn</value>
     </property>

    <!-- 指定jobhistory进程的地址 *****（三大进程之一）-->
     <property>
          <name>mapreduce.jobhistory.address</name>
          <value>master:10020</value>
     </property>
     <property>
          <name>mapreduce.jobhistory.webapp.address</name>
          <value>master:19888</value>
     </property>

    <!-- 启动uber优化 -->
    <property>
        <name>mapreduce.job.ubertask.enable</name>
                <value>true</value> 
    </property>
    <property>
             <name>mapreduce.job.ubertask.maxmaps</name>
             <value>9</value>
    </property>

    <property>
             <name>mapreduce.job.ubertask.maxreduces</name>
             <value>1</value>
    </property>
</configuration>


//hadoop-env.sh
export JAVA_HOME=/home/hadoop/jdk1.7.0_80
//slaves指定datannode运行的节点
slave1
slave2


//********************重点配置讲解********//


//mapred-site.xml 设置jobhistory
    <property>
          <name>mapreduce.jobhistory.address</name>
          <value>master:10020</value>
     </property>
<!-- jobhistory 和yarn通信的端口 -->
     <property>
          <name>mapreduce.jobhistory.webapp.address</name>
          <value>master:19888</value>
     </property>

//maped-site.xml启动uber模式，适用于小作业，变完后好快
    <property>
        <name>mapreduce.job.ubertask.enable</name>
                <value>true</value> 
    </property>
    <property>
             <name>mapreduce.job.ubertask.maxmaps</name>
             <value>9</value>
    </property>

    <property>
             <name>mapreduce.job.ubertask.maxreduces</name>
             <value>1</value>
    </property>

//yarn-site.xml 启动日志，日志会放到dfs上
    <property>
                   <name>yarn.log-aggregation-enable</name>
                   <value>true</value>
          </property>

         <property>
                   <name>yarn.log-aggregation.retain-seconds</name>
                   <value>604800</value>
          </property>

         <property>
                   <name>yarn.nodemanager.remote-app-log-dir</name>
                   <value>/logs</value>
          </property>
    //设置second-namenode的地址
     <property>
          <name>dfs.namenode.secondary.http-address</name>
          <value>master:9001</value>
     </property>
    //namenode的webui的端口，文件系统监控界面
     <property>
          <name>dfs.namenode.http-address</name>
          <value>master:50070</value>
     </property>


    //yarn-site.xml 设置yarn-daemon.sh代理
     <property>
          <name>yarn.web-proxy.address</name>
          <value>master:8888</value>
     </property>