接下来在node1上执行：

xxxxxxxxxx
[root@node1 ~]# hdfs zkfc -formatZK
2021-10-15 13:30:20,048 INFO ha.ActiveStandbyElector: Successfully created /hadoop-ha/mycluster in ZK.

然后在node4上接着执行：

xxxxxxxxxx
[zk: localhost:2181(CONNECTED) 1] ls /
[zookeeper, hadoop-ha]
[zk: localhost:2181(CONNECTED) 2] ls /hadoop-ha
[mycluster]
[z: localhost:2181(CONNECTED) 3] ls /hadoop-ha/mycluster
[]

执行到此处，还没有启动3个DataNode和2个ZKFC进程。

f) 启动hadoop集群，在node1执行

xxxxxxxxxx
[root@node1 ~]# start-dfs.sh
#出现如下错误提示
ERROR: Attempting to operate on hdfs journalnode as root
ERROR: but there is no HDFS_JOURNALNODE_USER defined. Aborting operation.
Starting ZK Failover Controllers on NN hosts [node1 node2]
ERROR: Attempting to operate on hdfs zkfc as root
ERROR: but there is no HDFS_ZKFC_USER defined. Aborting operation.
#解决办法：修改start-dfs.sh文件
[root@node1 ~]# vim /opt/hadoop-3.1.3/sbin/start-dfs.sh
#添加
HDFS_JOURNALNODE_USER=root
HDFS_ZKFC_USER=root

#为了防止关闭时出现类似的错误提示，修改stop-dfs.sh
[root@node1 ~]# vim /opt/hadoop-3.1.3/sbin/stop-dfs.sh
#添加
HDFS_JOURNALNODE_USER=root
HDFS_ZKFC_USER=root
#再次启动
[root@node1 hadoop]# start-dfs.sh 

在启动zkCli.sh的节点node4上观察：

xxxxxxxxxx
[zk: localhost:2181(CONNECTED) 5] ls /hadoop-ha/mycluster
[ActiveBreadCrumb, ActiveStandbyElectorLock]
[zk: localhost:2181(CONNECTED) 6] get -s /hadoop-ha/mycluster/ActiveStandbyElectorLock
    myclusternn1node1 �L(�>
cZxid = 0x600000008
ctime = Fri Oct 15 13:40:10 CST 2021
mZxid = 0x600000008
mtime = Fri Oct 15 13:40:10 CST 2021
pZxid = 0x600000008
cversion = 0
dataVersion = 0
aclVersion = 0
ephemeralOwner = 0x300006fd40a0002
dataLength = 29
numChildren = 0

node1占用着锁，它的状态是active的。浏览器访问：http://node1:9870

node2为standby，浏览器地址栏输入：http://node2:9870

将Active NameNode对应节点node1上NameNode进程kill掉：

xxxxxxxxxx
[root@node1 hadoop]# jps
10337 Jps
7347 JournalNode
9701 DFSZKFailoverController
7689 NameNode
[root@node1 hadoop]# kill -9 7689
#或者
[root@node1 hadoop]# hdfs --daemon stop namenode
[root@node1 hadoop]# jps
7347 JournalNode
9701 DFSZKFailoverController
10381 Jps

node4上继续查看：

xxxxxxxxxx
[zk: localhost:2181(CONNECTED) 12] get -s /hadoop-ha/mycluster/ActiveStandbyElectorLock
    myclusternn2node2 �L(�>
cZxid = 0x60000006c
......

但是通过浏览器访问发现Active NameNode不能自动进行切换。这是因为缺少一个rpm包：psmisc。接下来在四台节点上安装psmisc包。

xxxxxxxxxx
yum install -y psmisc

node1访问不了，node2 从Standby变为了Active。

node1上再次启动namenode:

xxxxxxxxxx
[root@node1 hadoop]# hdfs --daemon start namenode

node1变为standby，变为备机。