zookpeer: ha配置

要点如下：

1. zookeeper集群搭建
2. hdfs高可用（hdfs + zookeeper:  zk管理namenode, 实现failover机制 )
3. 修改start-dfs.sh :  使得zk集群---- 先于 ---hdfs启动 

---

hdfs集群“热备份”（zk + hdfs =ha)

ha具体配置文件

/etc/hosts

192.168.56.111  s101
192.168.56.112  s102
192.168.56.113  slave1
192.168.56.114  slave2
192.168.56.115  slave3
192.168.56.116  zk1
192.168.56.117  zk2
192.168.56.118  zk3

core-site.xml

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

<!-- 指定hadoop临时目录 --> 
<property> 
<name>hadoop.tmp.dir</name> 
<value>/home/wang/ha</value> 
</property> 

<!-- 指定zookeeper地址 --> 
<property> 
<name>ha.zookeeper.quorum</name> 
<value>zk1:2181,zk2:2181,zk3:2181</value> 
</property>
</configuration>

hdfs-site.xml

<configuration> 
<!--指定hdfs的nameservice为mycluster，和core-site.xml 一致 -->
    <property>
        <name>dfs.nameservices</name>
        <value>mycluster</value>
    </property> 

<!-- mycluster下面有两个NameNode，分别是nn1，nn2 是逻辑名字-->
    <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>s101:9000</value>
    </property> 

<!-- nn1的http通信地址 -->
    <property>
        <name>dfs.namenode.http-address.mycluster.nn1</name>
        <value>s101:50070</value>
    </property> 

<!-- nn2的RPC通信地址 -->
    <property>
        <name>dfs.namenode.rpc-address.mycluster.nn2</name>
        <value>s102:9000</value>
    </property> 

<!-- nn2的http通信地址 -->
    <property>
        <name>dfs.namenode.http-address.mycluster.nn2</name>
        <value>s102:50070</value>
    </property> 

<!-- 指定NameNode的edits元数据在JournalNode上的存放位置 -->
    <property>
        <name>dfs.namenode.shared.edits.dir</name>
        <value>qjournal://slave1:8485;slave2:8485;slave3:8485/mycluster</value>
    </property> 

<!-- 指定JournalNode在本地磁盘存放数据的位置 -->
    <property>
        <name>dfs.journalnode.edits.dir</name>
        <value>/home/wang/ha/qjournal</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.mycluster</name>
        <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
    </property> 

<!-- 配置隔离机制方法，多个机制用换行分割，即每个机制暂用一行-->
    <property>
        <name>dfs.ha.fencing.methods</name>
        <value>sshfence
		 shell(/bin/true)
	</value>
    </property> 

<!-- 使用sshfence隔离机制时需要ssh免登陆 -->
    <property>
        <name>dfs.ha.fencing.ssh.private-key-files</name>
        <value>/home/wang/.ssh/id_rsa</value>
    </property>

 <!-- 配置sshfence隔离机制超时时间 -->
    <property>
        <name>dfs.ha.fencing.ssh.connect-timeout</name>
        <value>30000</value>
    </property>
</configuration>

mapred-site.xml 

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

yarn-site.xml 

<configuration> 
 <!-- 开启RM高可用 -->
    <property>
        <name>yarn.resourcemanager.ha.enabled</name>
        <value>true</value>
    </property> 

<!-- 指定RM的cluster id -->
    <property>
        <name>yarn.resourcemanager.cluster-id</name>
        <value>yarn-cluster</value>
    </property> 

<!-- 指定RM的名字 -->
    <property>
        <name>yarn.resourcemanager.ha.rm-ids</name>
        <value>rm1,rm2</value>
    </property> 

<!-- 分别指定RM的地址 -->
    <property>
        <name>yarn.resourcemanager.hostname.rm1</name>
        <value>s101</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname.rm2</name>
        <value>s102</value>
    </property> 

<!-- 指定zookeeper集群地址 -->
    <property>
        <name>yarn.resourcemanager.zk-address</name>
        <value>zk1:2181,zk2:2181,zk3:2181</value>
    </property>
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
</configuration>