高可用hadoop—安装Zookeeper

高可用hadoop—安装Zookeeper

配置修改

1. 备用namenode生成公钥并分发

   ssh-keygen -t dsa
   cd .ssh
   # 追加到自己的authorized_keys
   cat id_dsa.pub >> authorized_keys
   # 分发到主namenode
   scp id_dsa.pub node01:`pwd`/node07.pub
   

2. 修改配置文件

   # hdfs.xml应该有以下配置
   <property>
   	  <name>dfs.replication</name>
   	  <value>2</value>
       </property>
   
       <property>
   	  <name>dfs.nameservices</name>
   	  <value>mycluster</value>
       </property>
   
       <property>
             <name>dfs.ha.automatic-failover.enabled</name>
             <value>true</value>
      </property>
       <property>
   	  <name>dfs.ha.namenodes.mycluster</name>
   	  <value>nn1,nn2</value>
       </property>
   
       <property>
             <name>dfs.namenode.rpc-address.mycluster.nn1</name>
             <value>node01:9820</value>
       </property>
       <property>
             <name>dfs.namenode.rpc-address.mycluster.nn2</name>
             <value>node02:9820</value>
       </property>
   
       <property>
             <name>dfs.ha.namenode.http-address.mycluster.nn1</name>
             <value>node01:9870</value>
       </property>
       <property>
             <name>dfs.ha.namenode.http-address.mycluster.nn2</name>
             <value>node02:9870</value>
       </property>
   
       <property>
   	  <name>dfs.namenode.shared.edits.dir</name>
   	  <value>qjournal://node01:8485;node02:8485;node03:8485/mycluster</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.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.journalnode.edits.dir</name>
   	  <value>/var/ihep/hadoop/ha/journalnode</value>
       </property>
   
      <property>
      	 <name>dfs.ha.fencing.ssh.connect-timeout</name>
      	 <value>30000</value>
      </property>
   
   </configuration>
   
   # core.xml应该有以下配置
   <configuration>
   	<property>
   		<name>fs.defaultFS</name>
   		<value>hdfs://mycluster</value>
   	</property>
   	<property>
   		<name>hadoop.tmp.dir</name>
   		<value>/var/ihep/hadoop/ha</value>
   	</property>
   	<property>
   		<name>ha.zookeeper.quorum</name>
   		<value>node02:2181,node03:2181,node04:2181</value>
   	</property>
   </configuration>
   

3. 分发配置文件

   scp core-site.xml hdfs-site.xml node04:`pwd`
   scp core-site.xml hdfs-site.xml node03:`pwd`
   scp core-site.xml hdfs-site.xml node02:`pwd`
   

自动故障转移——安装Zookeeper

1. 安装Zookeeper，在第二个节点

   # 注意安装包用bin版本
   tar xf apache-zookeeper-3.5.5-bin.tar -C /opt/yourpath
   # 进入Zookeeper目录下的conf
   cp zoo_sample.cfg zoo.cfg
   vi zoo.cfg
   # 修改dataDir=/var/path/zookeeper，并创建文件夹这个目录
   mkdir /var/path/zookeeper
   # 添加
   server.1=node02:2888:3888
   server.2=node03:2888:3888
   server.3=node04:2888:3888
   

2. 分发zookeeper

   scp -r apache-zookeeper-3.5.5/ node03:`pwd`
   scp -r apache-zookeeper-3.5.5/ node04:`pwd`
   

3. 在234号节点设置id，分别执行

   echo 1 > /var/ihep/zookeeper/myid
   echo 2 > /var/ihep/zookeeper/myid
   echo 3 > /var/ihep/zookeeper/myid
   

4. 主节点修改环境变量

   vi /etc/profile
   # 添加export ZOOKEEPER_HOME=/opt/ihep/apache-zookeeper-3.5.5
   # export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$ZOOKEEPER_HOME/bin
   

5. 主节点分发

   scp /etc/profile node02:/etc/
   scp /etc/profile node03:/etc/
   scp /etc/profile node04:/etc/
   # 各节点执行
   . /etc/profile
   

6. 启动journalnode

   # 在234节点上执行，检查是否能启动
   zkServer.sh start
   # 启动journalnode，在123号节点
   hdfs --daemon start journalnode
   

7. 格式化

   # 主节点
   hdfs namenode -format
   

8. node01数据同步给node02

   # 主节点
   hdfs --daemon start namenode
   # 备节点
   hdfs namenode -bootstrapStandby
   

9. 注册Zookeeper

   hdfs zkfc -formatZK
   # 启动集群
   start-dfs.sh