### --- YARN-HA工作机制

~~~     官方文档：https://hadoop.apache.org/docs/stable/hadoop-yarn/hadoop-yarnsite/ResourceManagerHA.html

### --- 环境准备

~~~     修改IP
~~~     修改主机名及主机名和IP地址的映射
~~~     关闭防火墙
~~~     ssh免密登录
~~~     安装JDK，配置环境变量等
~~~     配置Zookeeper集群

### --- yarn-site.xml3

[root@linux121 ~]# vim /opt/yanqi/servers/ha/hadoop-2.9.2/etc/hadoop/yarn-site.xml

<property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
</property>

<!--启用resourcemanager ha-->
<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-yarn</value>
</property>
<property>
        <name>yarn.resourcemanager.ha.rm-ids</name>
        <value>rm1,rm2</value>
</property>
<property>
        <name>yarn.resourcemanager.hostname.rm1</name>
        <value>linux122</value>
</property>
<property>
        <name>yarn.resourcemanager.hostname.rm2</name>
        <value>linux123</value>
</property>

<!--指定zookeeper集群的地址-->
<property>
        <name>yarn.resourcemanager.zk-address</name>
        <value>linux121:2181,linux122:2181,linux123:2181</value>
</property>

<!--启用自动恢复-->
<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>

### --- 同步更新其他节点的配置信息

[root@linux121 ~]# rsync-script /opt/yanqi/servers/ha/hadoop-2.9.2/etc/hadoop/yarn-site.xml

### --- 在linux123上启动yarn的主节点

[root@linux123 ~]# /opt/yanqi/servers/ha/hadoop-2.9.2/sbin/start-yarn.sh 
starting resourcemanager, logging to /opt/yanqi/servers/ha/hadoop-2.9.2/logs/yarn-root-resourcemanager-linux123.out
linux122: starting nodemanager, logging to /opt/yanqi/servers/ha/hadoop-2.9.2/logs/yarn-root-nodemanager-linux122.out
linux121: starting nodemanager, logging to /opt/yanqi/servers/ha/hadoop-2.9.2/logs/yarn-root-nodemanager-linux121.out
linux123: starting nodemanager, logging to /opt/yanqi/servers/ha/hadoop-2.9.2/logs/yarn-root-nodemanager-linux123.out

### --- 在linux122启动yarn的备用节点
~~~     访问：http://linux122:8088/cluster它会自动跳转到http://linux123:8088/cluster

[root@linux122 ~]# /opt/yanqi/servers/ha/hadoop-2.9.2/sbin/yarn-daemon.sh start resourcemanager
[root@linux122 ~]# jps
10480 ResourceManager

### --- 把linux123上的yarn杀死，验证http://linux122:8088/cluster是否可以访问
~~~     杀死linux123上yarn的resourcemanager进程
~~~     验证http://linux123:8088/cluster访问不通

[root@linux123 ~]# jps
11978 ResourceManager
[root@linux123 ~]# kill -9 11978

### --- linux121

[root@linux121 ~]# jps
11136 QuorumPeerMain
11360 JournalNode
11491 NameNode
12387 NodeManager
11806 DataNode
12095 DFSZKFailoverController
12559 Jps

### --- linux122

[root@linux122 ~]# jps
10480 ResourceManager
9905 DFSZKFailoverController
9747 DataNode
10838 Jps
10087 NameNode
9544 JournalNode
9342 QuorumPeerMain
10318 NodeManager

### --- linux123

[root@linux123 ~]# jps
11522 QuorumPeerMain
12517 Jps
11798 DataNode
12454 ResourceManager
12074 NodeManager
11711 JournalNode