1. 配置
1.修改 core-site.xml
<configuration>
<!-- 指定hdfs的nameservice为ns1 -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://hdzoo/</value>
</property>
<!-- 指定hadoop临时目录 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/root/hdptmp/</value>
</property>
<!-- 指定zookeeper地址 -->
<property>
<name>ha.zookeeper.quorum</name>
<value>master:2181,slave1:2181,slave2:2181</value>
</property>
</configuration>
2.修改 hdfs-site.xml
2.2.3修改hdfs-site.xml
<configuration>
<!--指定hdfs的nameservice为hdzoo,需要和core-site.xml中的保持一致 -->
<property>
<name>dfs.nameservices</name>
<value>hdzoo</value>
</property>
<!-- hdzoo下面有两个NameNode,分别是nn1,nn2 -->
<property>
<name>dfs.ha.namenodes.hdzoo</name>
<value>nn1,nn2</value>
</property>
<!-- nn1的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.hdzoo.nn1</name>
<value>master:9000</value>
</property>
<!-- nn1的http通信地址 -->
<property>
<name>dfs.namenode.http-address.hdzoo.nn1</name>
<value>master:50070</value>
</property>
<!-- nn2的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.hdzoo.nn2</name>
<value>slave1:9000</value>
</property>
<!-- nn2的http通信地址 -->
<property>
<name>dfs.namenode.http-address.hdzoo.nn2</name>
<value>slave1:50070</value>
</property>
<!-- 指定NameNode的edits元数据在机器本地磁盘的存放位置 -->
<property>
<name>dfs.namenode.name.dir</name>
<value>/root/hdpdata/name</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>/root/hdpdata/data</value>
</property>
<!-- 指定NameNode的共享edits元数据在JournalNode上的存放位置 -->
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://master:8485;slave1:8485;slave2:8485/hdzoo</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>/root/hdpdata/journaldata</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.hdzoo</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>/root/.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>
3.修改mapred-site.xml
<configuration>
<!-- 指定mr框架为yarn方式 -->
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
</configuration>
4.修改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>yrc</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>master</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>slave1</value>
</property>
<!-- 指定zk集群地址 -->
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>master:2181,slave1:2181,slave2:2181</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
</configuration>
2.启动
1.启动zookeeper集群(分别在master,slave1,slave2上启动zk)
/hadoop/zookeeper-3.4.5/bin/zkServer.sh start
2.手动启动journalnode(分别在在master,slave1,slave2上执行)
/hadoop/hadoop-2.6.4/sbin/hadoop-daemon.sh start journalnode
运行jps命令检验JournalNode进程
3.格式化namenode
在master上执行命令:hdfs namenode -format
格式化后会在根据core-site.xml中的hadoop.tmp.dir配置生成个文件,这里我配置的是/hadoop/hadoop-2.6.4/tmp,然后将/hadoop/hadoop-4./tmp拷贝到slave1的/hadoop/hadoop-2.6.4/下scp -r tmp/ slave1:/home/hadoop/app/hadoop-2.6.4/
5.格式化ZKFC(在master上执行即可)hdfs zkfc -formatZK
6.启动HDFS(在master上执行)sbin/start-dfs.sh
7.启动YARN,在slave1上执行start-yarn.shsbin/start-yarn.sh