hadoop 集群安装（二） HA部署

怼烎@ 2022-06-03 07:38 277阅读 0赞

继上篇博客《[Hadoop安装（一）zookeeper集群安装][Hadoop_zookeeper][》][Hadoop_zookeeper]后，我们已经搭建了hadoop所需要的免密码通信环境，以及高可用zookeeper集群，下面进入hadoop的高可用安装部署：

1. 下载解压hadoop文件 ：

tar -zxvf hadoop-2.7.4.tar.gz

2. 配置hadoop-2.7.4/etc/hadoop/core-site.xml

<configuration>
      <property>
            <name>fs.defaultFS</name>
    	
            <value>hdfs://mycluster</value> 
      </property>
      <property>
    	
            <name>hadoop.tmp.dir</name>
            <value>/srv/hadoop-2.7.4/tmp</value>
      </property>
     <property>
    	
       <name>ha.zookeeper.quorum</name>
       <value>h1:2181,h2:2181,h3:2181</value>
     </property>
    
    </configuration>

3. 配置hdfs-site.xml

<configuration>
    
    <property>
      <name>dfs.nameservices</name>
      <value>mycluster</value>
    </property>
    <property>
    
      <name>dfs.ha.namenodes.mycluster</name>
      <value>nn1,nn2</value>
    </property>
    <property>
    
      <name>dfs.namenode.rpc-address.mycluster.nn1</name>
      <value>h1:9000</value>
    </property>
    <property>
      <name>dfs.namenode.rpc-address.mycluster.nn2</name>
      <value>h2:9000</value>
    </property>
    <property>
    
      <name>dfs.namenode.http-address.mycluster.nn1</name>
      <value>h1:50070</value>
    </property>
    <property>
      <name>dfs.namenode.http-address.mycluster.nn2</name>
      <value>h2:50070</value>
    </property>
    <property>
    
      <name>dfs.namenode.shared.edits.dir</name>
      <value>qjournal://h2:8485;h3:8485;h4:8485/mycluster</value>
    </property>
    <property>
    
      <name>dfs.journalnode.edits.dir</name>
      <value>/srv/hadoop-2.7.4/journal</value>
    </property>
    
    <property>
      <name>dfs.ha.fencing.methods</name>
      <value>sshfence</value>
    </property>
    
    <property>
      <name>dfs.ha.fencing.ssh.private-key-files</name>
      <value>/root/.ssh/id_dsa</value>
    </property>
    
    <property>
       <name>dfs.ha.automatic-failover.enabled</name>
       <value>true</value>
     </property>
    
    <property>
      <name>dfs.client.failover.proxy.provider.mycluster</name> <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
    </property>
    <property>
        <name>dfs.webhdfs.enabled</name>
        <value>true</value>
    </property>
    
    <property>
    <name>dfs.permissions.enabled</name>
    <value>true</value>
    </property>
    <property>
    <name>dfs.namenode.acls.enabled</name>
    <value>false</value>
    </property>
    
    <property>
      <name>dfs.permissions.superusergroup</name>
      <value>hdfs</value>
    </property>
    <property>
      <name>dfs.block.access.token.enable</name>
      <value>true</value>
    </property>
    
        <property>
            <name>dfs.replication</name>
            <value>3</value>
        </property>
    <property>
    <name>dfs.datanode.data.dir</name>
    <value>/srv/hadoop-2.7.4/tmp/datanode</value>
    </property>
    
    <property>
    <name>dfs.namenode.name.dir</name>
    <value>/srv/hadoop-2.7.4/tmp/namenode</value>
    </property>

4. 配置mapred-site.xml 文件

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

5. 配置 yarn-site.xml文件

<configuration>  <property> <name>yarn.nodemanager.aux-services</name> <value>mapreduce_shuffle</value> </property> <property> <name>yarn.resourcemanager.hostname</name> <value>h1</value> </property> <property> <name>yarn.resourcemanager.ha.enabled</name> <value>true</value> </property>  <property> <name>yarn.resourcemanager.ha.rm-ids</name> <value>rm1,rm2</value> </property>  <property> <name>yarn.resourcemanager.hostname.rm1</name> <value>h1</value> </property> <property> <name>yarn.resourcemanager.hostname.rm2</name> <value>h2</value> </property>  <property> <name>yarn.resourcemanager.recovery.enabled</name> <value>true</value> </property>  <property> <name>yarn.resourcemanager.store.class</name> <value> org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore </value> </property>  <property> <name>yarn.resourcemanager.zk-address</name> <value>h1:2181,h2:2181,h3:2181</value> <description>For multiple zk services, separate them with comma</description> </property>  <property> <name>yarn.resourcemanager.cluster-id</name> <value>yarn-ha</value> </property> </configuration>

6.   配置slaves文件

h2  
        h3  
        h4

7.  配置hadoop的环境变量vim /etc/profile

export HADOOP\_HOME=/srv/hadoop-2.7.4  
        export PATH=$PATH:$HADOOP\_HOME/bin:$HADOOP\_HOME/sbin

8. 每台机器执行source /etc/profile

首次启动命令

1、首先启动各个节点的Zookeeper，在各个节点上执行以下命令：

bin/zkServer.sh start1

2、在某一个namenode节点执行如下命令，创建命名空间

hdfs zkfc -formatZK1

3、在每个journalnode节点用如下命令启动journalnode

sbin/hadoop-daemon.sh start journalnode1