hadoop HA 配置 + zookeeper 服务注册

环境测试 6台机器 centos6.7 x64

master ( namenode/cluster )
10.10.100.101    namenode1
10.10.100.105    namenode2
ResourceManager
manager 
datanode (datanode,NodeManager,JournalNnode,QuprumPeerMain)
10.10.100.102 datanode1 + zk1
10.10.100.103 datanode2 + zk2
10.10.100.104 datanode3 + zk3

节点服务部署：

节点服务创建 
zookeeper/data/目录下建立myid文件
datanode1为1 
datanode2为2
datanode3为3

 配置文件：

配置core-site.xml

需要配置nameservice，hadoop 文件存储位置和Zookeeper集群来确保多个namenode之间的切换，修改后内容如下：

<configuration>

<!-- 指定hdfs的nameservice为master -->
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://master</value>
    </property>

<!-- 指定hadoop临时目录 -->
    <property>
        <name>hadoop.tmp.dir</name>
        <value>file:/opt/hadoop/tmp</value>
    </property>

<!-- 指定zookeeper地址 -->
    <property>
        <name>ha.zookeeper.quorum</name>
        <value>datanode1:2181,datanode2:2181,datanode3:2181</value>
    </property>

    <property>   
        <name>ha.zookeeper.session-timeout.ms</name>   
        <value>300000</value>   
    </property>

</configuration>

 配置hdfs-site.xml

hdfs-site.xml主要配置namenode的高可用；

<configuration>
<!--指定hdfs的nameservice为master，需要和core-site.xml中的保持一致 -->
    <property>
        <name>dfs.nameservices</name>
        <value>master</value>
    </property>
<!-- master下面有两个NameNode，分别是namenode1，namenode2 -->
    <property>
        <name>dfs.ha.namenodes.master</name>
        <value>namenode1,namenode2</value>
    </property>
<!-- namenode1 的 RPC 通信地址 -->
<property>
        <name>dfs.namenode.rpc-address.master.namenode1</name>
        <value>namenode1:9000</value>
    </property>
<!-- namenode1 的http通信地址 -->
    <property>
        <name>dfs.namenode.http-address.master.namenode1</name>
        <value>namenode1:50070</value>
    </property>
<!-- namenode2 的 RPC 通信地址 -->
    <property>
        <name>dfs.namenode.rpc-address.master.namenode2</name>
        <value>namenode2:9000</value>
    </property>
<!-- namenode2 的http通信地址 -->
    <property>
        <name>dfs.namenode.http-address.master.namenode2</name>
        <value>namenode2:50070</value>
    </property>
<!-- 指定NameNode的元数据在JournalNode上的存放位置 -->
    <property>
        <name>dfs.namenode.shared.edits.dir</name>
        <value>qjournal://datanode1:8485;datanode2:8485;datanode3:8485/master</value>
    </property>
<!-- 指定JournalNode在本地磁盘存放数据的位置 (工作目录)-->
    <property>
        <name>dfs.journalnode.edits.dir</name>
        <value>/opt/hadoop/journal</value>
    </property>
<!-- 开启NameNode失败自动切换 -->
    <property>
        <name>dfs.ha.automatic-failover.enabled</name>
        <value>true</value>
    </property>
<!-- 配置失败自动切换实现方式 -->
    <property>
        <name>dfs.client.failover.proxy.provider.master</name>
        <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
    </property>
<!-- 配置sshfence隔离机制 -->
    <property>
        <name>dfs.ha.fencing.methods</name>
        <value>sshfence</value>
    </property>
<!-- 使用隔离机制时需要ssh免登陆 -->

    <property>
        <name>dfs.ha.fencing.ssh.private-key-files</name>
        <value>/root/.ssh/id_rsa</value>
    </property>


    <property>   
        <name>dfs.namenode.name.dir</name>     
        <value>/opt/hadoop/hdfs/name</value>   
    </property>   

    <property>   
        <name>dfs.datanode.data.dir</name>   
        <value>/opt/hadoop/hdfs/data</value>   
    </property> 

    <property>   
        <name>dfs.replication</name>   
        <value>3</value>   
    </property>   

    <property>   
        <name>dfs.webhdfs.enabled</name>   
        <value>true</value>   
    </property>


</configuration>

 配置mapreduce文件mapred-site.xml

默认是没有mapred-site.xml文件的，里面有一个mapred-site.xml.example,重命名为mapred-site.xml
mv mapred-site.xml.example mapred-site.xml
配置内容如下，这里就是指明mapreduce是用在YARN之上来执行的。

<configuration>
<!-- 指定mr框架为yarn方式 -->
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>

    <property> 
        <name>mapreduce.job.maps</name> 
        <value>12</value> 
    </property> 

    <property> 
        <name>mapreduce.job.reduces</name> 
        <value>12</value> 
    </property> 

</configuration>

 配置yarn-site.xml

做规划的时候就是配置hadoop03来运行yarn，配置如下：

<configuration>
<!-- 指定resourcemanager地址 -->
    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>manager</value>
    </property>

<!-- 指定nodemanager启动时加载server的方式为shuffle server -->
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>


<!-- 
    
  <property>   
        <name>yarn.log-aggregation-enable</name>   
        <value>true</value>   
    </property>   

    <property>   
        <name>yarn.log-aggregation.retain-seconds</name>   
        <value>259200</value>   
    </property>   

    <property>   
        <name>yarn.resourcemanager.zk-address</name>   
        <value>datanode1:2181,datanode3:2181,datanode2:2181</value>   
    </property>   

    <property>   
        <name>yarn.resourcemanager.cluster-id</name>   
        <value>cluster-yarn</value>   
    </property>   

    <property>   
        <name>yarn.resourcemanager.ha.enabled</name>   
        <value>true</value>   
    </property>   

    <property>   
        <name>yarn.resourcemanager.ha.master</name>   
        <value>namenode1,namenode2</value>   
    </property>   

    <property>   
        <name>yarn.resourcemanager.hostname.namenode1</name>   
        <value>namenode1</value>   
    </property>       

    <property>   
        <name>yarn.resourcemanager.hostname.namenode2</name>   
        <value>namenode2</value>   
    </property>   

<property>
       <name>yarn.resourcemanager.scheduler.address.namenode1</name>
        <value>namenode1:8030</value>
    </property>

    <property>
       <name>yarn.resourcemanager.scheduler.address.namenode2</name>
       <value>namenode2:8030</value>
    </property>

    <property>
        <name>yarn.resourcemanager.resource-tracker.address.namenode1</name>
        <value>namenode1:8031</value>
    </property>

    <property>
       <name>yarn.resourcemanager.resource-tracker.address.namenode2</name>
       <value>namenode2:8031</value>
    </property>

    <property>
       <name>yarn.resourcemanager.address.namenode1</name>
       <value>namenode1:8032</value>
    </property>

    <property>
       <name>yarn.resourcemanager.address.namenode2</name>
       <value>namenode2:8032</value>
    </property>

    <property>
       <name>yarn.resourcemanager.admin.address.namenode1</name>
       <value>namenode:8033</value>
    </property>

    <property>
        <name>yarn.resourcemanager.admin.address.namenode2</name>
        <value>namenode2:8033</value>
    </property>

    <property>
       <name>yarn.resourcemanager.webapp.address.namenode1</name>
       <value>namenode1:8088</value>
    </property>

    <property>
       <name>yarn.resourcemanager.webapp.address.namenode2</name>
       <value>namenode2:8088</value>
    </property> 

    <property> 
        <name>yarn.resourcemanager.ha.automatic-failover.enabled</name> 
        <value>true</value> 
    </property> 

    <property> 
        <name>yarn.resourcemanager.ha.automatic-failover.embedded</name> 
        <value>true</value> 
    </property> 

    <property> 
        <name>yarn.resourcemanager.ha.automatic-failover.zk-base-path</name> 
        <value>/yarn-leader-election</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.nodemanager.aux-services</name>   
        <value>mapreduce_shuffle</value>   
    </property>   

    <property>   
        <name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>   
        <value>org.apache.hadoop.mapred.ShuffleHandler</value>   
    </property>       

</configuration>

在hadoop master 上启动journalnode

[root@hadoop01 hadoop-2.7.1]# sbin/hadoop-daemons.sh start journalnode
journalnode的节点是datanode1、datanode2、datanode3，这三台机器上会出现JournalNode
[root@hadoop04 zookeeper-3.4.6]# jps
1532 JournalNode
1796 Jps
1470 QuorumPeerMain

在hadoop上格式化hadoop

hadoop namenode -format

hadoop 上格式化 zk
hdfs zkfc -formatZK

hdfs zkfc –formatZK
--格式化 zookeeper custer-ha主目录