2021.11.4高可用集群搭建

2021.11.4高可用集群搭建

文件配置

修改三个文件的JAVA_HOME
[root@linux02 hadoop]# vi ./hadoop-env.sh 
 25 export JAVA_HOME=/opt/soft/jdk180
[root@linux02 hadoop]# vi ./yarn-env.sh
 23  export JAVA_HOME=/opt/soft/jdk180
[root@linux02 hadoop]# vi ./mapred-env.sh
 16 export JAVA_HOME=/opt/soft/jdk180


[root@linux02 hadoop]# vi ./core-site.xml

     20   
     21   
     22    fs.defaultFS
     23    hdfs://mycluster/
     24   
     25   
     26   
     27   
     28     hadoop.tmp.dir
     29     /opt/soft/hadoop260/hadooptmp/
     30   
     31 
     32   
     33   
     34     ha.zookeeper.quorum
     35     linux03:2181,linux04:2181,linux05:2181
     36   
     37 
     38   
     39   
     40     hadoop.proxyuser.bigdata.hosts
     41     *
     42   
     43 
     44   
     45     hadoop.proxyuser.bigdata.groups
     46     *
     47   
     48 


--------------------------------------------------
[root@linux02 hadoop]# vi ./hdfs-site.xml

 
          
     28     dfs.nameservices
     29     mycluster
     30   
     31 
     32   
     33   
     34     dfs.ha.namenodes.mycluster
     35     nn1,nn2
     36   
     37 
     38   
     39   
     40     dfs.namenode.rpc-address.mycluster.nn1
     41     linux02:9000
     42   
     43   
     44   
     45   
     46     dfs.namenode.http-address.mycluster.nn1
     47     linux02:50070
     48   
     49 
     50 
     51   
     52   
     53     dfs.namenode.rpc-address.mycluster.nn2
     54     linux03:9000
     55   
     56 
     57   
     58   
     59     dfs.namenode.http-address.mycluster.nn2
     60     linux03:50070
     61   
     62 
     63   
     64   
     65     dfs.journalnode.edits.dir
     66     /opt/soft/hadoop260/journaldata
     67   
     68 
     69   
     70   
     71     dfs.namenode.shared.edits.dir
     72     qjournal://linux02:8485;linux03:8485;linux04:8485/mycluster
     73   
     74 
     75   
     76   
     77     dfs.ha.automatic-failover.enabled
     78     true
     79   
     80 
     81   
     82   
     83     dfs.client.failover.proxy.provider.mycluster
     84     org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider
     85   
     86 
     87   
     88   
     89     dfs.ha.fencing.methods
     90     
     91       sshfence
     92       shell(/bin/true)
     93     
     94   
     95 
     96   
     97   
     98     dfs.ha.fencing.ssh.private-key-files
     99     /root/.ssh/id_rsa
    100   
    101 
    102   
    103   
    104      dfs.ha.fencing.ssh.connect-timeout
    105      30000
    106   
    107 
    108   
    109     dfs.webhdfs.enabled
    110     true
    111   
    112 

-----------------------------------------
[root@linux02 hadoop]# cp mapred-site.xml.template mapred-site.xml
[root@linux02 hadoop]# vi ./mapred-site.xml


     20   
     21   
     22     mapreduce.framework.name
     23     yarn
     24   
     25 
     26   
     27   
     28     mapreduce.jobhistory.address
     29     linux05:10020
     30   
     31 
     32   
     33   
     34     mapreduce.jobhistory.webapp.address
     35     linux05:19888
     36   
 
 
 
 
 ----------------------------------------------
 [root@linux02 hadoop]# vi ./yarn-site.xml
 
  
  
    yarn.resourcemanager.ha.enabled
    true
  

  
  
    yarn.resourcemanager.cluster-id
    yrc
  

  
  
    yarn.resourcemanager.ha.rm-ids
    rm1,rm2
  


  
  
    yarn.resourcemanager.hostname.rm1
    linux02
  

  
  
    yarn.resourcemanager.hostname.rm2
    linux03
  

  
  
    yarn.resourcemanager.zk-address
    linux03:2181,linux04:2181,linux05:2181
  

  
  
    yarn.nodemanager.aux-services
    mapreduce_shuffle
  

  
  
    yarn.log-aggregation-enable
    true
  

  
  
    yarn.log-aggregation.retain-seconds
    86400
  

  
  
    yarn.resourcemanager.recovery.enabled
    true
  


  
  
    yarn.resourcemanager.store.class
    org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore
  


-----------------------------------------
[root@linux02 hadoop]# vi ./slaves 

linux02
linux03
linux04
linux05

----------------------------------
[root@linux02 hadoop]# xsync ./hadoop260/
-----------------
[root@linux02 hadoop]# vi /etc/profile
[root@linux03 hadoop]# vi /etc/profile
[root@linux04 hadoop]# vi /etc/profile
[root@linux05 hadoop]# vi /etc/profile

export HADOOP_HOME=/opt/soft/hadoop260
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export YARN_HOME=$HADOOP_HOME
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native
export HADOOP_OPTS="-Djava.library.path=$HADOOP_HOME/lib"
export PATH=$PATH:$HADOOP_HOME/sbin:$HADOOP_HOME/bin

[root@linux02hadoop]# xsync /etc/profile

 启动集群服务

第一次启动集群服务

1. 先将zookeeper集群启动
[root@linux02 hadoop]# zkop status
--------linux03 zookeeper status -----------
JMX enabled by default
Using config: /opt/soft/zookeeper345/bin/../conf/zoo.cfg
Mode: follower
--------linux04 zookeeper status -----------
JMX enabled by default
Using config: /opt/soft/zookeeper345/bin/../conf/zoo.cfg
Mode: leader
--------linux05 zookeeper status -----------
JMX enabled by default
Using config: /opt/soft/zookeeper345/bin/../conf/zoo.cfg
Mode: follower
[root@linux02 hadoop]# 
2. 启动journalnode 
[root@linux02 hadoop]# hadoop-daemon.sh start journalnode
starting journalnode, logging to /opt/soft/hadoop260/logs/hadoop-root-journalnode-linux02.out
[root@linux02 hadoop]# ssh linux03 "source /etc/profile; hadoop-daemon.sh start journalnode"
starting journalnode, logging to /opt/soft/hadoop260/logs/hadoop-root-journalnode-linux03.out
[root@linux02 hadoop]# ssh linux04 "source /etc/profile; hadoop-daemon.sh start journalnode"
starting journalnode, logging to /opt/soft/hadoop260/logs/hadoop-root-journalnode-linux04.out
[root@linux02 hadoop]# jqop jps
-------------linux02指令信息-----------
jps
9489 Jps
9048 JournalNode
-------------linux03指令信息-----------
jps
12081 Jps
1764 QuorumPeerMain
12006 JournalNode
-------------linux04指令信息-----------
jps
2595 JournalNode
1752 QuorumPeerMain
2654 Jps
-------------linux05指令信息-----------
jps
2440 Jps
1758 QuorumPeerMain
3.格式化
[root@linux02 soft]# hadoop namenode -format
将linux02格式化后的hadooptmp文件同步到linux03
[root@linux02 hadoop260]# scp -r ./hadooptmp/ root@linux03:/opt/soft/hadoop260/
VERSION                                                                                       100%  207    43.3KB/s   00:00    
seen_txid                                                                                     100%    2     0.4KB/s   00:00    
fsimage_0000000000000000000.md5                                                               100%   62    23.9KB/s   00:00    
fsimage_0000000000000000000                                                                   100%  321   120.3KB/s   00:00 

4.初始化zookeeper
[root@linux02 hadoop260]# hdfs zkfc -formatZK
5.启动HDFS
[root@linux02 hadoop260]# start-dfs.sh
21/11/04 23:24:40 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Starting namenodes on [linux02 linux03]
linux03: starting namenode, logging to /opt/soft/hadoop260/logs/hadoop-root-namenode-linux03.out
linux02: starting namenode, logging to /opt/soft/hadoop260/logs/hadoop-root-namenode-linux02.out
linux05: starting datanode, logging to /opt/soft/hadoop260/logs/hadoop-root-datanode-linux05.out
linux04: starting datanode, logging to /opt/soft/hadoop260/logs/hadoop-root-datanode-linux04.out
linux02: starting datanode, logging to /opt/soft/hadoop260/logs/hadoop-root-datanode-linux02.out
linux03: starting datanode, logging to /opt/soft/hadoop260/logs/hadoop-root-datanode-linux03.out
21/11/04 23:25:02 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Starting ZK Failover Controllers on NN hosts [linux02 linux03]
linux02: starting zkfc, logging to /opt/soft/hadoop260/logs/hadoop-root-zkfc-linux02.out
linux03: starting zkfc, logging to /opt/soft/hadoop260/logs/hadoop-root-zkfc-linux03.out
[root@linux02 hadoop260]# jqop jps
-------------linux02指令信息-----------
jps
10852 DFSZKFailoverController
9048 JournalNode
10970 Jps
10507 NameNode
10603 DataNode
-------------linux03指令信息-----------
jps
1764 QuorumPeerMain
12006 JournalNode
13319 Jps
13082 DataNode
13019 NameNode
13211 DFSZKFailoverController
-------------linux04指令信息-----------
jps
2688 DataNode
2595 JournalNode
1752 QuorumPeerMain
2776 Jps
-------------linux05指令信息-----------
jps
2562 Jps
2473 DataNode
1758 QuorumPeerMain
6.启动yarn
[root@linux02 hadoop260]# start-yarn.sh
starting yarn daemons
starting resourcemanager, logging to /opt/soft/hadoop260/logs/yarn-root-resourcemanager-linux02.out
linux05: starting nodemanager, logging to /opt/soft/hadoop260/logs/yarn-root-nodemanager-linux05.out
linux04: starting nodemanager, logging to /opt/soft/hadoop260/logs/yarn-root-nodemanager-linux04.out
linux03: starting nodemanager, logging to /opt/soft/hadoop260/logs/yarn-root-nodemanager-linux03.out
linux02: starting nodemanager, logging to /opt/soft/hadoop260/logs/yarn-root-nodemanager-linux02.out
[root@linux02 hadoop260]# jqop jps
-------------linux02指令信息-----------
jps
10852 DFSZKFailoverController
11252 NodeManager
9048 JournalNode
11160 ResourceManager
11321 Jps
10507 NameNode
10603 DataNode
-------------linux03指令信息-----------
jps
13634 Jps
1764 QuorumPeerMain
12006 JournalNode
13082 DataNode
13019 NameNode
13211 DFSZKFailoverController
13501 NodeManager
-------------linux04指令信息-----------
jps
2688 DataNode
2595 JournalNode
2933 Jps
1752 QuorumPeerMain
2809 NodeManager
-------------linux05指令信息-----------
jps
2720 Jps
2596 NodeManager
2473 DataNode
1758 QuorumPeerMain
[root@linux02 hadoop260]# jqop jps
-------------linux02指令信息-----------
jps
10852 DFSZKFailoverController
11252 NodeManager
9048 JournalNode
11160 ResourceManager
10507 NameNode
10603 DataNode
11837 Jps
-------------linux03指令信息-----------
jps
13953 Jps
1764 QuorumPeerMain
13861 ResourceManager
12006 JournalNode
13082 DataNode
13019 NameNode
13211 DFSZKFailoverController
13501 NodeManager
-------------linux04指令信息-----------
jps
2688 DataNode
2960 Jps
2595 JournalNode
1752 QuorumPeerMain
2809 NodeManager
-------------linux05指令信息-----------
jps
2596 NodeManager
2473 DataNode
2747 Jps
1758 QuorumPeerMain
[root@linux02 hadoop260]# ssh linux05 "source /etc/profile; mr-jobhistory-daemon.sh start historyserver
> "
starting historyserver, logging to /opt/soft/hadoop260/logs/mapred-root-historyserver-linux05.out
[root@linux02 hadoop260]# jqop jps
-------------linux02指令信息-----------
jps
12177 Jps
10852 DFSZKFailoverController
11252 NodeManager
9048 JournalNode
11160 ResourceManager
10507 NameNode
10603 DataNode
-------------linux03指令信息-----------
jps
1764 QuorumPeerMain
13861 ResourceManager
12006 JournalNode
13082 DataNode
13019 NameNode
13211 DFSZKFailoverController
13501 NodeManager
14287 Jps
-------------linux04指令信息-----------
jps
2688 DataNode
2595 JournalNode
1752 QuorumPeerMain
2809 NodeManager
2988 Jps
-------------linux05指令信息-----------
jps
2596 NodeManager
2871 Jps
2473 DataNode
2794 JobHistoryServer
1758 QuorumPeerMain

查看日志 

[root@linux05 ~]# cd /opt/soft/hadoop260/logs
[root@linux05 logs]# vi ./mapred-root-historyserver-linux05.log
[root@linux05 logs]# cat mapred-root-historyserver-linux05.log

所需脚本链接：https://blog.csdn.net/liuyongsheng666/article/details/121122238?spm=1001.2014.3001.5501