hadoop HA集群搭建(2)

修改配置文件:

2.2.2修改core-site.xml

<configuration>
<!-- 集群名称在这里指定！该值来自于hdfs-site.xml中的配置 -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://cluster1</value>
</property>
<!-- 这里的路径默认是NameNode、DataNode、JournalNode等存放数据的公共目录 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/root/apps/hadoop/tmp</value>
</property>

<!-- ZooKeeper集群的地址和端口。注意，数量一定是奇数，且不少于三个节点-->
<property>
<name>ha.zookeeper.quorum</name>
<value>hadoop05:2181,hadoop06:2181,hadoop07:2181</value>
</property>
</configuration>

2.2.3修改hdfs-site.xml

<configuration>
<!--指定hdfs的nameservice为cluster1，需要和core-site.xml中的保持一致 -->
<property>
<name>dfs.nameservices</name>
<value>cluster1</value>
</property>
<!-- cluster1下面有两个NameNode，分别是nn1，nn2 -->
<property>
<name>dfs.ha.namenodes.cluster1</name>
<value>nn1,nn2</value>
</property>
<!-- nn1的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.cluster1.nn1</name>
<value>mini1:9000</value>
</property>
<!-- nn1的http通信地址 -->
<property>
<name>dfs.namenode.http-address.cluster1.nn1</name>
<value>hadoop00:50070</value>
</property>
<!-- nn2的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.cluster1.nn2</name>
<value>hadoop01:9000</value>
</property>
<!-- nn2的http通信地址 -->
<property>
<name>dfs.namenode.http-address.cluster1.nn2</name>
<value>hadoop01:50070</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://hadoop05:8485;hadoop06:8485;hadoop07:8485/cluster1</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/hadoop/app/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>
<!-- 指定该集群出故障时，哪个实现类负责执行故障切换 -->
<property>
<name>dfs.client.failover.proxy.provider.cluster1</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
</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/hadoop/.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>

2.2.4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>    

2.2.5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>node-11</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>node-12</value>
</property>
<!-- 指定zk集群地址 -->
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>node-11:2181,node-12:2181,node-13:2181</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
</configuration>

2.2.6修改slaves(slaves是指定子节点的位置，因为要在hadoop01上启动HDFS、在hadoop03启动yarn，所以hadoop01上的slaves文件指定的是datanode的位置，hadoop03上的slaves文件指定的是nodemanager的位置)
hadoop05
hadoop06
hadoop07
2.2.7配置免密码登陆
#首先要配置hadoop00到hadoop01、hadoop02、hadoop03、hadoop04、hadoop05、hadoop06、hadoop07的免密码登陆
#在hadoop01上生产一对钥匙
ssh-keygen -t rsa
#将公钥拷贝到其他节点，*包括自己*
ssh-coyp-id hadoop00
ssh-coyp-id hadoop01
ssh-coyp-id hadoop02
ssh-coyp-id hadoop03
ssh-coyp-id hadoop04
ssh-coyp-id hadoop05
ssh-coyp-id hadoop06
ssh-coyp-id hadoop07