hadoop-hdfs-ha 搭建及一些常见错误

hadoop-hdfs-ha 搭建

ps.省略了基础环境的配置（没有ssh免密以及主机名称，jdk）

1. zookeeper配置
   到zookeeper的conf目录下

   cp zoo_sample.cfg zoo.cfg
   

   对zoo.cfg进行配置

   # The number of milliseconds of each tick
   tickTime=2000
   # The number of ticks that the initial 
   # synchronization phase can take
   initLimit=10
   # The number of ticks that can pass between 
   # sending a request and getting an acknowledgement
   syncLimit=5
   # the directory where the snapshot is stored.
   # do not use /tmp for storage, /tmp here is just 
   # example sakes.
   dataDir=/var/zookeeper
   # the port at which the clients will connect
   clientPort=2181
   # the maximum number of client connections.
   # increase this if you need to handle more clients
   #maxClientCnxns=60
   #
   # Be sure to read the maintenance section of the 
   # administrator guide before turning on autopurge.
   #
   # http://zookeeper.apache.org/doc/current/zookeeperAdmin.html#sc_maintenance
   #
   # The number of snapshots to retain in dataDir
   #autopurge.snapRetainCount=3
   # Purge task interval in hours
   # Set to "0" to disable auto purge feature
   #autopurge.purgeInterval=1
   server.1=192.168.41.11:2888:3888 #第二个端口用来选举leader和follower
   server.2=192.168.41.12:2888:3888
   server.3=192.168.41.13:2888:3888
   
   

   注意我这里省略了分发的步骤，分发步骤见4

   mkdir -p /var/zookeeper #递归的创建目录
   

   echo 1 > /var/zookeeper/myid #这里注意myid和zookeeper服务器一一对应eg.第一台myid就1 ，第二台就2以此类推。
   

2. hdfs-site.xml配置

   <configuration>
       <property>
           <name>fs.replication</name><!--设置两个备份-->
           <value>2</value>
       </property>
       <property>
     		<name>dfs.nameservices</name><!--设置namenode的逻辑映射-->
     		<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>master:8020</value>
       </property>
       <property>
     		<name>dfs.namenode.rpc-address.mycluster.nn2</name>
     		<value>slave1:8020</value>
       </property>
       <property>
     		<name>dfs.namenode.http-address.mycluster.nn1</name>
      		<value>master:50070</value>
       </property>
       <property>
     		<name>dfs.namenode.http-address.mycluster.nn2</name>
   		<value>slave1:50070</value>
       </property>
       <property>
           <name>dfs.namenode.shared.edits.dir</name><!--设置journalnode地址-->
           <value>qjournal://master:8485;slave1:8485;slave2:8485/mycluster</value>
       </property>
       <property>
           <name>dfs.journalnode.edits.dir</name>
           <value>/var/hadoop/journalnode</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><!--通过ssh来控制-->
         <value>sshfence</value>
       </property>
       <property>
         <name>dfs.ha.fencing.ssh.private-key-files</name><!--ssh免密-->
         <value>/root/.ssh/id_rsa</value>
       </property>
       <property>
         <name>dfs.ha.automatic-failover.enabled</name><!--自动failover-->
         <value>true</value>
       </property>
   </configuration>
   
   

3. core-site.xml配置

   <configuration>
       <property>
   	<name>fs.defaultFS</name>
   	<value>hdfs://mycluster</value>
       </property>
       <property>
   	<name>hadoop.tmp.dir</name>
   	<value>/var/hadoop-2.6/ha</value>
       </property>
       <property>
      	<name>ha.zookeeper.quorum</name><!--zookeeper地址-->
      	<value>slave1:2181,slave2:2181,slave3:2181</value>
       </property>
   </configuration>
   

4. slaves文件配置
   在这个文件下添加datanode的主机名

5. 配置文件分发
   到目标目录下eg.我hadoop，zookeeper存放在/opt 下接下来bash命令以我的位置为例

   scp -r  ./zk root@目标主机:`pwd`/zk
   
   

   scp -r  ./hadoop root@目标主机:`pwd`/hadoop
   

6. 启动集群
   ~先启动journalnode

   hadoop-daemon.sh start journalnode
   

   ~格式化master的namenode并启动

   hdfs namenode -format
   

   hadoop-daemon.sh start namenode
   

   ~开启slave1 的namenode（注意千万别格式化）

   hdfs namenode -bootStrapStandby
   

   ~zk

   在zookeeper服务器下启动

   zkServer.sh start
   

   在master下格式化zookeeper

   hdfs zkfc -formatZK
   

   ~启动角色

   start-dfs.sh
   

master

slave1