HA集群安装

拼搏现实的明天。 2022-02-22 14:38 289阅读 0赞

### HA集群安装 ###

*  硬件准备
 *  安装jdk
 *  安装zookeerper
 *  安装hadoop
 *   *  上传、解压
     *  修改core-site.xml文件
     *  修改mapred-site.xml
     *  修改yarn-site.xml
     *  修改hdfs-site.xml
     *  修改slaves
     *  配置hadoop\_home
     *  分发到其他虚拟机中
 *  启动
 *   *  启动zookeeper集群
     *  启动journalnode
     *  格式化HDFS
     *  格式化ZKFC
     *  启动HDFS
     *  启动YARN
 *  测试

# 硬件准备 #

> 七台虚拟机、配置好hosts、免密登录等。

hadoop1  192.168.56.101 jdk、hadoop 			NameNode、DFSZKFailoverController(zkfc)
    hadoop2  192.168.56.102 jdk、hadoop 			NameNode、DFSZKFailoverController(zkfc)
    hadoop3  192.168.56.103 jdk、hadoop 			ResourceManager
    hadoop4  192.168.56.104 jdk、hadoop 			ResourceManager
    hadoop5  192.168.56.105 jdk、hadoop、zookeeper  DataNode、NodeManager、JournalNode、QuorumPeerMain
    hadoop6  192.168.56.106 jdk、hadoop、zookeeper  DataNode、NodeManager、JournalNode、QuorumPeerMain
    hadoop7  192.168.56.107 jdk、hadoop、zookeeper  DataNode、NodeManager、JournalNode、QuorumPeerMain

# 安装jdk #

> jdk安装过程不再介绍

# 安装zookeerper #

请看 [zookeerper安装][zookeerper]

# 安装hadoop #

## 上传、解压 ##

## 修改core-site.xml文件 ##

<configuration>
    
    <property>
    <name>fs.defaultFS</name>
    <value>hdfs://bi/</value>
    </property>
    
    <property>
    <name>hadoop.tmp.dir</name>
    <value>/home/hadoop/data/hdpdata/</value>
    </property>
    
    
    <property>
    <name>ha.zookeeper.quorum</name>
    <value>hadoop5:2181,hadoop6:2181,hadoop7:2181</value>
    </property>
    </configuration>

## 修改mapred-site.xml ##

<configuration>
    
    <property>
    <name>mapreduce.framework.name</name>
    <value>yarn</value>
    </property>
    </configuration>

## 修改yarn-site.xml ##

<configuration>
    
    <property>
    <name>yarn.resourcemanager.ha.enabled</name>
    <value>true</value>
    </property>
    
    <property>
    <name>yarn.resourcemanager.cluster-id</name>
    <value>yrc</value>
    </property>
    
    <property>
    <name>yarn.resourcemanager.ha.rm-ids</name>
    <value>rm1,rm2</value>
    </property>
    
    <property>
    <name>yarn.resourcemanager.hostname.rm1</name>
    <value>hadoop3</value>
    </property>
    <property>
    <name>yarn.resourcemanager.hostname.rm2</name>
    <value>hadoop4</value>
    </property>
    
    <property>
    <name>yarn.resourcemanager.zk-address</name>
    <value>hadoop5:2181,hadoop6:2181,hadoop7:2181</value>
    </property>
    <property>
    <name>yarn.nodemanager.aux-services</name>
    <value>mapreduce_shuffle</value>
    </property>
    </configuration>

## 修改hdfs-site.xml ##

<configuration>
    
    <property>
    <name>dfs.nameservices</name>
    <value>bi</value>
    </property>
    
    <property>
    <name>dfs.ha.namenodes.bi</name>
    <value>nn1,nn2</value>
    </property>
    
    <property>
    <name>dfs.namenode.rpc-address.bi.nn1</name>
    <value>hadoop1:9000</value>
    </property>
    
    <property>
    <name>dfs.namenode.http-address.bi.nn1</name>
    <value>hadoop1:50070</value>
    </property>
    
    <property>
    <name>dfs.namenode.rpc-address.bi.nn2</name>
    <value>hadoop2:9000</value>
    </property>
    
    <property>
    <name>dfs.namenode.http-address.bi.nn2</name>
    <value>hadoop2:50070</value>
    </property>
    
    <property>
    <name>dfs.namenode.shared.edits.dir</name>
    <value>qjournal://hadoop5:8485;hadoop6:8485;hadoop7:8485/bi</value>
    </property>
    
    <property>
    <name>dfs.journalnode.edits.dir</name>
    <value>/home/hadoop/journaldata</value>
    </property>
    
    <property>
    <name>dfs.ha.automatic-failover.enabled</name>
    <value>true</value>
    </property>
    
    <property>
    <name>dfs.client.failover.proxy.provider.bi</name>
    <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
    </property>
    
    <property>
    <name>dfs.ha.fencing.methods</name>
    <value>
    sshfence
    shell(/bin/true)
    </value>
    </property>
    
    <property>
    <name>dfs.ha.fencing.ssh.private-key-files</name>
    <value>/home/hadoop/.ssh/id_rsa</value>
    </property>
    
    <property>
    <name>dfs.ha.fencing.ssh.connect-timeout</name>
    <value>30000</value>
    </property>
    </configuration>

## 修改slaves ##

> (slaves是指定子节点的位置，因为要在hadoop1上启动HDFS、在hadoop3启动yarn，  
> 所以hadoop1上的slaves文件指定的是datanode的位置，  
> hadoop3上的slaves文件指定的是nodemanager的位置)

hadoop5
    	hadoop6
    	hadoop7

## 配置hadoop\_home ##

export HADOOP=/home/hadoop/app/hadoop-2.6.4
    export PATH=$PATH:$HADOOP/bin:$HADOOP/sbin

## 分发到其他虚拟机中 ##

# 启动 #

## 启动zookeeper集群 ##

启动zookeeper集群（分别在hadoop5、hadoop6、hadoop7上启动zk）
    cd /hadoop/zookeeper/bin/
    ./zkServer.sh start
    #查看状态：一个leader，两个follower
    ./zkServer.sh status

## 启动journalnode ##

启动journalnode（分别在在hadoop5、hadoop6、hadoop7上执行）
    cd /home/hadoop/app/hadoop-2.6.4
    sbin/hadoop-daemon.sh start journalnode
    #运行jps命令检验，hadoop5、hadoop6、hadoop7上多了JournalNode进程

## 格式化HDFS ##

#在hadoop1上执行命令:
    	hdfs namenode -format
    	#格式化后会在根据core-site.xml中的hadoop.tmp.dir配置生成个文件，这里我配置的是/home/hadoop/data，
    	然后将/home/hadoop/data拷贝到hadoop2的/home/hadoop/data下。
    	
    	##也可以这样，建议hdfs namenode -bootstrapStandby

## 格式化ZKFC ##

格式化ZKFC(在mini1上执行一次即可)
    	hdfs zkfc -formatZK
    
    [zk: localhost:2181(CONNECTED) 0] ls /
    [zookeeper, hadoop-ha]
    [zk: localhost:2181(CONNECTED) 1] ls /hadoop-ha
    [bi]
    [zk: localhost:2181(CONNECTED) 2] ls /hadoop-ha/bi
    []
    [zk: localhost:2181(CONNECTED) 3] get /hadoop-ha/bi
    
    cZxid = 0x100000003
    ctime = Tue Apr 09 19:35:28 CST 2019
    mZxid = 0x100000003
    mtime = Tue Apr 09 19:35:28 CST 2019
    pZxid = 0x100000003
    cversion = 0
    dataVersion = 0
    aclVersion = 0
    ephemeralOwner = 0x0
    dataLength = 0
    numChildren = 0

## 启动HDFS ##

启动HDFS(在hadoop1上执行)
    	sbin/start-dfs.sh
    	
    	在hadoop上执行hadoop-daemon.sh start namenode

## 启动YARN ##

启动YARN(#####注意#####：是在hadoop3上执行start-yarn.sh，把namenode和resourcemanager分开是因为性能问题，
    因为他们都要占用大量资源，所以把他们分开了，他们分开了就要分别在不同的机器上启动)
    	sbin/start-yarn.sh
    
    在hadoop4上执行  ./yarn-daemon.sh start resourcemanager
    
    [zk: localhost:2181(CONNECTED) 7] ls /
    [zookeeper, yarn-leader-election, hadoop-ha]
    [zk: localhost:2181(CONNECTED) 8] ls /yarn-leader-election
    [yrc]
    [zk: localhost:2181(CONNECTED) 9] ls /yarn-leader-election/yrc
    [ActiveBreadCrumb, ActiveStandbyElectorLock]
    
    [zk: localhost:2181(CONNECTED) 10] get /yarn-leader-election/yrc/ActiveBreadCrumb
    
    yrcrm1
    cZxid = 0x10000000f
    ctime = Tue Apr 09 19:42:58 CST 2019
    mZxid = 0x10000000f
    mtime = Tue Apr 09 19:42:58 CST 2019
    pZxid = 0x10000000f
    cversion = 0
    dataVersion = 0
    aclVersion = 0
    ephemeralOwner = 0x0
    dataLength = 10
    numChildren = 0
    [zk: localhost:2181(CONNECTED) 11] get /yarn-leader-election/yrc/ActiveStandbyElectorLock
    
    yrcrm1
    cZxid = 0x10000000e
    ctime = Tue Apr 09 19:42:58 CST 2019
    mZxid = 0x10000000e
    mtime = Tue Apr 09 19:42:58 CST 2019
    pZxid = 0x10000000e
    cversion = 0
    dataVersion = 0
    aclVersion = 0
    ephemeralOwner = 0x16a017c7a3e0001
    dataLength = 10
    numChildren = 0

# 测试 #

访问hadoop1:50070  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2pqa2FuZ18_size_16_color_FFFFFF_t_70]  
访问hadoop2:50070  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2pqa2FuZ18_size_16_color_FFFFFF_t_70 1]

[zookeerper]: https://blog.csdn.net/jjkang_/article/details/89136455
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2pqa2FuZ18_size_16_color_FFFFFF_t_70]: /images/20220222/adf02c9c1c924af4a6b858bb3caa7ad8.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2pqa2FuZ18_size_16_color_FFFFFF_t_70 1]: /images/20220222/091e532c369f42fba0e2aed622757c60.png