hadoop HA配置文件

core-site.xml

<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://ns</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/opt/module/hadoop-2.7.7/tmp</value>
</property>
<property>
<name>ha.zookeeper.quorum</name>
<value>master:2181,slave1:2181,slave2:2181</value>
</property>
</configuration>

yarn-site.xml

<configuration>
  <!--启动HA -->
  <property>
    <name>yarn.resourcemanager.ha.enabled</name>
    <value>true</value>
  </property>
  <!--表示集群 -->
  <property>
    <name>yarn.resourcemanager.cluster-id</name>
    <value>yrc</value>
  </property>
  <!--指定两个ResourceManager的名称 -->
  <property>
    <name>yarn.resourcemanager.ha.rm-ids</name>
    <value>rm1,rm2</value>
  </property>
  <!--指定rm1的地址 -->
  <property>
    <name>yarn.resourcemanager.hostname.rm1</name>
    <value>master</value>
  </property>
  <!--指定rm2的地址 -->
  <property>
    <name>yarn.resourcemanager.hostname.rm2</name>
    <value>slave1</value>
  </property>
  <!--指定zookeeper集群 -->
  <property>
    <name>yarn.resourcemanager.zk-address</name>
    <value>master:2181,slave1:2181,slave2:2181</value>
  </property>
  <!--启动NodeManager时，server的加载方式 -->
  <property>
    <name>yarn.nodemanager.aux-services</name>
    <value>mapreduce_shuffle</value>
  </property>
<!--检查每个任务正使用的物理内存量，如果任务超出分配值，则将其杀掉，默认是true -->
 <property>
     <name>yarn.nodemanager.pmem-check-enabled</name>
     <value>false</value>
 </property>

 <!--检查每个任务正使用的虚拟内存量，如果任务超出分配值，则将其杀掉，默认是true -->
 <property>
     <name>yarn.nodemanager.vmem-check-enabled</name>
     <value>false</value>
 </property>

<!-- Site specific YARN configuration properties -->

</configuration>

hdfs-site.xml

<configuration>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<name>dfs.nameservices</name>
<value>ns</value>
</property>
<property>
<name>dfs.ha.namenodes.ns</name>
<value>nn1,nn2</value>
</property>
<property>
<name>dfs.namenode.rpc-address.ns.nn1</name>
<value>master:9000</value>
</property>
<property>
<name>dfs.namenode.http-address.ns.nn1</name>
<value>master:50070</value>
</property>
<property>
<name>dfs.namenode.rpc-address.ns.nn2</name>
<value>slave1:9000</value>
</property>
<property>
<name>dfs.namenode.http-address.ns.nn2</name>
<value>slave1:50070</value>
</property>
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://master:8485;slave1:8485;slave2:8485/ns</value>
</property>
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/opt/module/hadoop-2.7.7/journal/data</value>
</property>
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<property>
  <name>dfs.client.failover.proxy.provider.ns</name>
  <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<property>
  <name>dfs.ha.fencing.methods</name>
  <value>
        sshfence
        shell(/bin/true)
  </value>
</property>
<property>
  <name>dfs.ha.fencing.ssh.private-key-files</name>
  <value>/root/.ssh/id_rsa</value>
</property>
<property>
  <name>dfs.ha.fencing.ssh.connect-timeout</name>
  <value>30000</value>
</property>
</configuration>

mapred-site.xml

<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
</configuration>

slaves

master
slave1
slave2

在hadoop-env.sh中添加

JAVA_HOME和HADOOP_CONF_DIR

例如

export JAVA_HOME=/opt/module/jdk1.8.0_171

export HADOOP_CONF_DIR=/opt/module/hadoop-2.7.7/etc/hadoop