mapreduce on yarn搭建

节点分布

在HA的基础上进行以下修改

1.拷贝mapred-site.xml.template为mapred-site.xml文件，并进行修改

<configuration>    
    <property>
            <name>mapreduce.framework.name</name>
            <value>yarn</value>
    </property>
</configuration>

2.修改yarn-site.xml文件

<configuration>
    <property>
            <name>yarn.nodemanager.aux-services</name>
            <value>mapreduce_shuffle</value>
    </property>
    <!-- 启用ResourceManager的高可用-->
    <property>
            <name>yarn.resourcemanager.ha.enabled</name>
            <value>true</value>
    </property>
    <!--—指代ResourceManager HA的两台RM的逻辑名称 -->
    <property>
            <name>yarn.resourcemanager.cluster-id</name>
            <value>rmhacluster1</value>
    </property>
    <!--—指定该高可用ResourceManager下的两台ResourceManager的逻辑名称-->
    <property>
            <name>yarn.resourcemanager.ha.rm-ids</name>
            <value>rm1,rm2</value>
    </property>
    <!--—指定第一台ResourceManager服务器所在的主机名称 -->
    <property>
            <name>yarn.resourcemanager.hostname.rm1</name>
            <value>node3</value>
    </property>
    <property>
            <name>yarn.resourcemanager.hostname.rm2</name>
            <value>node4</value>
    </property>
    <!--—指定resourcemanager的web服务器的主机名和端口号-->
    <property>
            <name>yarn.resourcemanager.webapp.address.rm1</name>
            <value>node3:8088</value>
    </property>
    <property>
            <name>yarn.resourcemanager.webapp.address.rm2</name>
            <value>node4:8088</value>
    </property>
    <!--—做ResourceManager HA故障切换用到的zookeeper集群地址 -->
    <property>
            <name>yarn.resourcemanager.zk-address</name>
            <value>node2:2181,node3:2181,node4:2181</value>
    </property>
</configuration>

******将以上修改拷贝到其他三台机器上******

4.在两台ResourceManager中其中一台启动ResourceManager

start-yarn.sh

5.在另外一台ResourceManager上启动resourcemanager

yarn --daemon start resourcemanager