1.停止yarn
$>stop-yarn.sh
2.配置 yarn-site.xml
<!-- 启用rm高可用 -->
<property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>
<!-- 集群ID -->
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>rmcluster</value>
</property>
<!-- 节点名称 -->
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<!-- 每个名称对应的机器节点hostname -->
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>s101</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>s106</value>
</property>
<!-- 每个名称对应的webui地址 -->
<property>
<name>yarn.resourcemanager.webapp.address.rm1</name>
<value>s101:8088</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm2</name>
<value>s106:8088</value>
</property>
<!-- zk服务器 -->
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>s102:2181,s103:2181,s104:2181</value>
</property>
3.启动yarn
$>start-yarn.sh
4.手动启动第二个RM
$>ssh s106 yarn-daemon.sh start resourcemanager
5.webui查看状态
s101:8088
s106:8088
6.查看zk中RM信息
登录zk客户端,查看元数据信息
zkCli.sh -server s102
7.手动容灾
$ yarn rmadmin -getServiceState rm1 active
$ yarn rmadmin -getServiceState rm2 standby
$ yarn rmadmin -transitionToStandby rm1