4.1 問題
本案例要求：
初始化集羣
驗證集羣
4.2 步驟
實現此案例需要按照如下步驟進行。
步驟一：驗證hadoop的高可用
1）初始化ZK集羣
[root@nn01 ~]# /usr/local/hadoop/bin/hdfs zkfc -formatZK
...
18/09/11 15:43:35 INFO ha.ActiveStandbyElector: Successfully created /hadoop-ha/nsdcluster in ZK //出現Successfully即爲成功
...
2）在node1，node2，node3上面啓動journalnode服務（以node1爲例子）
[root@node1 ~]# /usr/local/hadoop/sbin/hadoop-daemon.sh start journalnode
starting journalnode, logging to /usr/local/hadoop/logs/hadoop-root-journalnode-node1.out
[root@node1 ~]# jps
29262 JournalNode
26895 QuorumPeerMain
29311 Jps
3）格式化，先在node1，node2，node3上面啓動journalnode才能格式化
[root@nn01 ~]# /usr/local/hadoop//bin/hdfs namenode -format
//出現Successfully即爲成功
[root@nn01 hadoop]# ls /var/hadoop/
dfs
4）nn02數據同步到本地 /var/hadoop/dfs
[root@nn02 ~]# cd /var/hadoop/
[root@nn02 hadoop]# ls
[root@nn02 hadoop]# rsync -aSH nn01:/var/hadoop/ /var/hadoop/
[root@nn02 hadoop]# ls
dfs
5）初始化 JNS
[root@nn01 hadoop]# /usr/local/hadoop/bin/hdfs namenode -initializeSharedEdits
18/09/11 16:26:15 INFO client.QuorumJournalManager: Successfully started new epoch 1 //出現Successfully，成功開啓一個節點
6）停止 journalnode 服務（node1，node2，node3）
[root@node1 hadoop]# /usr/local/hadoop/sbin/hadoop-daemon.sh stop journalnode
stopping journalnode
[root@node1 hadoop]# jps
29346 Jps
26895 QuorumPeerMain
步驟二：啓動集羣
1）nn01上面操作
[root@nn01 hadoop]# /usr/local/hadoop/sbin/start-all.sh //啓動所有集羣
This script is Deprecated. Instead use start-dfs.sh and start-yarn.sh
Starting namenodes on [nn01 nn02]
nn01: starting namenode, logging to /usr/local/hadoop/logs/hadoop-root-namenode-nn01.out
nn02: starting namenode, logging to /usr/local/hadoop/logs/hadoop-root-namenode-nn02.out
node2: starting datanode, logging to /usr/local/hadoop/logs/hadoop-root-datanode-node2.out
node3: starting datanode, logging to /usr/local/hadoop/logs/hadoop-root-datanode-node3.out
node1: starting datanode, logging to /usr/local/hadoop/logs/hadoop-root-datanode-node1.out
Starting journal nodes [node1 node2 node3]
node1: starting journalnode, logging to /usr/local/hadoop/logs/hadoop-root-journalnode-node1.out
node3: starting journalnode, logging to /usr/local/hadoop/logs/hadoop-root-journalnode-node3.out
node2: starting journalnode, logging to /usr/local/hadoop/logs/hadoop-root-journalnode-node2.out
Starting ZK Failover Controllers on NN hosts [nn01 nn02]
nn01: starting zkfc, logging to /usr/local/hadoop/logs/hadoop-root-zkfc-nn01.out
nn02: starting zkfc, logging to /usr/local/hadoop/logs/hadoop-root-zkfc-nn02.out
starting yarn daemons
starting resourcemanager, logging to /usr/local/hadoop/logs/yarn-root-resourcemanager-nn01.out
node2: starting nodemanager, logging to /usr/local/hadoop/logs/yarn-root-nodemanager-node2.out
node1: starting nodemanager, logging to /usr/local/hadoop/logs/yarn-root-nodemanager-node1.out
node3: starting nodemanager, logging to /usr/local/hadoop/logs/yarn-root-nodemanager-node3.out
2）nn02上面操作
[root@nn02 hadoop]# /usr/local/hadoop/sbin/yarn-daemon.sh start resourcemanager
starting resourcemanager, logging to /usr/local/hadoop/logs/yarn-root-resourcemanager-nn02.out
3）查看集羣狀態
[root@nn01 hadoop]# /usr/local/hadoop/bin/hdfs haadmin -getServiceState nn1
active
[root@nn01 hadoop]# /usr/local/hadoop/bin/hdfs haadmin -getServiceState nn2
standby
[root@nn01 hadoop]# /usr/local/hadoop/bin/yarn rmadmin -getServiceState rm1
active
[root@nn01 hadoop]# /usr/local/hadoop/bin/yarn rmadmin -getServiceState rm2
standby
4）查看節點是否加入
[root@nn01 hadoop]# /usr/local/hadoop/bin/hdfs dfsadmin -report
...
Live datanodes (3): //會有三個節點
...
[root@nn01 hadoop]# /usr/local/hadoop/bin/yarn node -list
Total Nodes:3
Node-Id Node-State Node-Http-Address Number-of-Running-Containers
node2:43307 RUNNING node2:8042 0
node1:34606 RUNNING node1:8042 0
node3:36749 RUNNING node3:8042 0
步驟三：訪問集羣
1）查看並創建
[root@nn01 hadoop]# /usr/local/hadoop/bin/hadoop fs -ls /
[root@nn01 hadoop]# /usr/local/hadoop/bin/hadoop fs -mkdir /aa //創建aa
[root@nn01 hadoop]# /usr/local/hadoop/bin/hadoop fs -ls / //再次查看
Found 1 items
drwxr-xr-x - root supergroup 0 2018-09-11 16:54 /aa
[root@nn01 hadoop]# /usr/local/hadoop/bin/hadoop fs -put *.txt /aa
[root@nn01 hadoop]# /usr/local/hadoop/bin/hadoop fs -ls hdfs://nsdcluster/aa
//也可以這樣查看
Found 3 items
-rw-r--r-- 2 root supergroup 86424 2018-09-11 17:00 hdfs://nsdcluster/aa/LICENSE.txt
-rw-r--r-- 2 root supergroup 14978 2018-09-11 17:00 hdfs://nsdcluster/aa/NOTICE.txt
-rw-r--r-- 2 root supergroup 1366 2018-09-11 17:00 hdfs://nsdcluster/aa/README.txt
2）驗證高可用，關閉 active namenode
[root@nn01 hadoop]# /usr/local/hadoop/bin/hdfs haadmin -getServiceState nn1
active
[root@nn01 hadoop]# /usr/local/hadoop/sbin/hadoop-daemon.sh stop namenode
stopping namenode
[root@nn01 hadoop]# /usr/local/hadoop/bin/hdfs haadmin -getServiceState nn1
//再次查看會報錯
[root@nn01 hadoop]# /usr/local/hadoop/bin/hdfs haadmin -getServiceState nn2
//nn02由之前的standby變爲active
active
[root@nn01 hadoop]# /usr/local/hadoop/bin/yarn rmadmin -getServiceState rm1
active
[root@nn01 hadoop]# /usr/local/hadoop/sbin/yarn-daemon.sh stop resourcemanager
//停止resourcemanager
[root@nn01 hadoop]# /usr/local/hadoop/bin/yarn rmadmin -getServiceState rm2
active
3） 恢復節點
[root@nn01 hadoop]# /usr/local/hadoop/sbin/hadoop-daemon.sh start namenode
//啓動namenode
[root@nn01 hadoop]# /usr/local/hadoop/sbin/yarn-daemon.sh start resourcemanager
//啓動resourcemanager
[root@nn01 hadoop]# /usr/local/hadoop/bin/hdfs haadmin -getServiceState nn1
//查看
[root@nn01 hadoop]# /usr/local/hadoop/bin/yarn rmadmin -getServiceState rm1
//查看