hadoop高可用HA的配置

zk3
zk4
zk5

配置hadoop的HA大概可以分为以下几步:

• 配置zookpeer(namenode之间的通信要靠zk来实现)
• 配置hadoop的
  • hadoop-env.sh
  • hdfs-site.xml
  • core-site.xml
  • slave

* hadoop-env.sh

export JAVA_HOME=/opt/module/jdk1..0_144 

* hdfs-site.xml

<configuration>
    <!-- 指定数据冗余份数 -->
    <property>
        <name>dfs.replication</name>
        <value></value>
    </property>

    <!-- 完全分布式集群名称 -->
    <property>
        <name>dfs.nameservices</name>
        <value>mycluster</value>
    </property>

    <!-- 集群中NameNode节点都有哪些 -->
    <property>
        <name>dfs.ha.namenodes.mycluster</name>
        <value>nn1,nn2</value>
    </property>

    <!-- nn1的RPC通信地址 -->
    <property>
        <name>dfs.namenode.rpc-address.mycluster.nn1</name>
        <value>z04:</value>
    </property>

    <!-- nn2的RPC通信地址 -->
    <property>
        <name>dfs.namenode.rpc-address.mycluster.nn2</name>
        <value>z05:</value>
    </property>

    <!-- nn1的http通信地址 -->
    <property>
        <name>dfs.namenode.http-address.mycluster.nn1</name>
        <value>z04:</value>
    </property>

    <!-- nn2的http通信地址 -->
    <property>
        <name>dfs.namenode.http-address.mycluster.nn2</name>
        <value>z05:</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://z04:8485;z05:8485;z06:8485/mycluster</value>
    </property>

    <!-- 配置隔离机制，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无秘钥登录-->
    <property>
        <name>dfs.ha.fencing.ssh.private-key-files</name>
        <value>/home/z/.ssh/id_rsa</value>
    </property>

    <!-- 声明journalnode服务器存储目录-->
    <property>
        <name>dfs.journalnode.edits.dir</name>
        <value>/opt/modules/cdh/hadoop-2.5.-cdh5.3.6/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>

* core-site.xml

<configuration>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://mycluster</value>
    </property>

    <property>
        <name>hadoop.tmp.dir</name>
        <value>/opt/modules/cdh/hadoop-2.5.-cdh5.3.6/data</value>
    </property>
</configuration>

* slaves

zk04
zk05
zk06