HA配置

1.复制hadoop文件到目录ha

cp -r zookeeper-3.4.10/ ha

2.修改配置文件：core-site.xml

<configuration>
   <!--把两个Namenode地址组装成一个集群mycluster-->
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://mycluster</value>
    </property>
        <!--指定hadoop运行时产生文件的存储目录-->
    <property>
        <name>hadoop.tmp.dir</name>
        <value>/opt/module/ha/hadoop-2.7.6/data/tmp</value>
    </property>
</configuration>

 

3.修改配置文件：core-site.xml

<configuration>
    <!--完全分布式集群名称-->
    <property>
       <name>dfs.nameservices</name>
       <value>mycluster</value>
    </property>
    
    <!--集群中nameNode节点有哪些-->
    <property>
        <name>dfs.ha.namenodes.mycluster</name>
        <value>nn1,nn2</value>
    </property>
    
    <!--nn1,nn2的RPC通讯地址-->
    <property>
       <name>dfs.namenode.rpc-address.mycluster.nn1</name>
       <value>hadoop102:9000</value>
    </property>
    <property>
       <name>dfs.namenode.rpc-address.mycluster.nn2</name>
       <value>hadoop103:9000</value>
    </property>
    
    
    <!--nn1,nn2的HTTP通讯地址-->
    <property>
       <name>dfs.namenode.http-address.mycluster.nn1</name>
       <value>hadoop102:50070</value>
    </property>
    <property>
      <name>dfs.namenode.http-address.mycluster.nn2</name>
      <value>hadoop103:50070</value>
    </property>
    
    <!--指定namenode元数据在journalnode上的存放位置-->
    <property>
       <name>dfs.namenode.shared.edits.dir</name>
       <value>qjournal://hadoop102:8485;hadoop103:8485;hadoop104:8485/mycluster</value>
    </property>
    
    <!-- 配置隔离机制为ssh，即同一时刻只能有一台服务器对外响应 -->
    <property>
       <name>dfs.ha.fencing.methods</name>
       <value>sshfence</value>
    </property>
    
    <!-- 使用隔离机制时需要ssh无密钥登录 -->
    <property>
        <name>dfs.ha.fencing.ssh.private-key-files</name>
        <value>/home/atguigu/.ssh/id_rsa</value>
    </property>
    
    <!-- 使用journalnode服务器存储目录 -->
    <property>
        <name>dfs.journalnode.edits.dir</name>
        <value>/opt/module/ha/hadoop-2.7.6/data/jn</value>
    </property>
    
    <!-- 关闭权限检查 -->
    <property>
        <name>dfs.permissions.enable</name>
        <value>false</value>
    </property>
    
    <!-- 访问代理类：client,mycluster,active配置失败自动切换实现方式 -->
    <property>
        <name>dfs.client.failover.proxy.provider.mycluster</name>
        <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
    </property>
    
</configuration>

3.启动集群

hadoop102:
(1)启动journalnode
/opt/module/ha/hadoop-2.7.6
sbin/hadoop-daemons.sh start journalnode
(2)格式化namenode
bin/hdfs namenode -format
(3)启动namenode
sbin/hadoop-daemon.sh start namenode
(4)启动datanode
sbin/hadoop-daemon.sh start datanode

hadoop103:
(1)从hadoop102 namenode拉取数据
bin/hdfs namenode -bootstrapStandby
(2)启动namenode
sbin/hadoop-daemon.sh start namenode
(3)启动datanode
sbin/hadoop-daemon.sh start datanode

hadoop104:
(1)启动datanode
sbin/hadoop-daemon.sh start datanode

4.手动将hadoop102上的nn1变成active模式

bin/hdfs haadmin -transitionToActive nn1

5.自动设置hadoop102上的nn1变成active模式

5.1 停止HDFS服务

sbin/dfs-stop.sh

5.2 增加配置信息

//配置core-site.xml文件
<!-- 指定zookeeper地址，配置HA时需要 -->
<property>
<name>ha.zookeeper.quorum</name>
<value>hadoop102:2181,hadoop103:2181,hadoop104:2181</value>
</property>
//配置hdfs-site.xml文件
<!-- 开启自动切换功能 -->
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>

5.3 删除hadoop2,hadoop3，hadoop4的data和log目录

rm -r data logs

5.4 启动集群

(1)启动journalnode
/opt/module/ha/hadoop-2.7.6
sbin/hadoop-daemons.sh start journalnode
(2)格式化namenode
bin/hdfs namenode -format
(3)启动zookeeper集群
bin/zkServer.sh start
(4)初始化HA在Zookeeper中状态
bin/hdfs zkfc -formatZK
(5)启动HDFS事务
sbin/start-dfs.sh
(6)从hadoop102 namenode拉取数据
bin/hdfs namenode -bootstrapStandby
(7)启动namenode
sbin/hadoop-daemon.sh start namenode