Yarn_HA

1.YARN-HA工作机制

 

2.YARN-HA配置

 

 配置yarn-site.xml

<configuration>

<!-- Site specific YARN configuration properties -->

<!--reduce数据的获取方式-->
<property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
</property>

<!--开启resourcemanager HA功能-->
<property>
    <name>yarn.resourcemanager.ha.enabled</name>
    <value>true</value>
</property>

<!--声明两台resourcemanager的地址-->
<property>
  <name>yarn.resourcemanager.cluster-id</name>
  <value>cluster-yarn1</value>
</property>

<!--集群中resourcemanager的ID列表，后面的配置将引用该ID-->
<property>
  <name>yarn.resourcemanager.ha.rm-ids</name>
  <value>rm1,rm2</value>
</property>

<!--resourcemanager1所在的节点主机名-->
<property>
  <name>yarn.resourcemanager.hostname.rm1</name>
  <value>hadoop102</value>
</property>

<!--resourcemanager2所在的节点主机名-->
<property>
  <name>yarn.resourcemanager.hostname.rm2</name>
  <value>hadoop103</value>
</property>


<!-- 指定zookeeper集群地址 -->
<property>
    <name>yarn.resourcemanager.zk-address</name>
    <value>hadoop102:2181,hadoop103:2181,hadoop104:2181</value>
</property>


<!--开启自动恢复功能-->
<property>
    <name>yarn.resourcemanager.recovery.enabled</name>
    <value>true</value>
</property>


<!--指定resourcemanager的状态信息存储在zookeeper集群-->
<property>
        <name>yarn.resourcemanager.store.class</name>
        <value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
</property>

</configuration>

 

(1)启动zookeeper
cd /opt/module/zookeeper-3.4.10/
bin/zkServer.sh start
bin/zkServer.sh status

(2)启动集群
sbin/start-dfs.sh
(3)启动yarn
sbin/start-yarn.sh
(4)手动启动第二个yarn
sbin/yarn-daemon.sh start resourcemanager
(5)查看是否启动成功
hadoop102:8088
bin/yarn rmadmin -getServiceState rm1
bin/yarn rmadmin -getServiceState rm2