Hadoop高可用配置（HA）

一、组件部署架构

• tunabook102：NameNode、ResourceManager、ZooKeeper、ZKFC
• tunabook103：NameNode、ZKFC、ZooKeeper
• tunabook104：DataNode、QJM、ZooKeeper、NodeManager
• tunabook105：DataNode、QJM、ZooKeeper、NodeManager
• tunabook106：DataNode、QJM、ZooKeeper、NodeManager

二、配置文件（tunabook102tunabook103tunabook104tunabook105tunabook106）

• core-site.xml

  <configuration>
      <property>
  	<name>fs.defaultFS</name>
  	<value>hdfs://cluster1</value>
      </property>
      <property>
  	<name>hadoop.security.authorization</name>
  	<value>false</value>
      </property>
      <property>
  	<name>ha.zookeeper.quorum</name>
  	<value>
  	    tunabook102:2181,tunabook103:2181,tunabook:104:2181,tunabook:105,tunabook:106
  	</value>
      </property>
  </configuration>
  

• hadoop-env.sh

  export JAVA_HOME=/export/server/jdk1.8.0_65
  export HADOOP_MAPRED_HOME=/export/server/hadoop-3.3.0
  export HDFS_JOURNALNODE_USER=root
  export HDFS_NAMENODE_USER=root
  export HDFS_DATANODE_USER=root
  export HDFS_SECONDARYNAMENODE_USER=root
  export YARN_RESOURCEMANAGER_USER=root
  export YARN_NODEMANAGER_USER=root 
  export HDFS_ZKFC_USER=root
  

• hdfs-site.xml

  <configuration>
  	<property>
  		<name>dfs.replication</name>
  		<value>3</value>
  	</property>
  	<property>
  		<name>dfs.permissions</name>
  		<value>false</value>
  	</property>
  	<property>
  		<name>dfs.namenode.name.dir</name>
  		<value>/export/hdfs/namenode</value>
  	</property>
  	<property>
  		<name>dfs.datanode.data.dir</name>
  		<value>/export/hdfs/datanode</value>
  	</property>
  	<property>
  		<name>dfs.nameservices</name>
  		<value>cluster1</value>
  	</property>
  	<property>
  		<name>dfs.ha.namenodes.cluster1</name>
  		<value>nn1,nn2</value>	
  	</property>
  	<property>
  		<name>dfs.namenode.rpc-address.cluster1.nn1</name>
  		<value>tunabook102:9000</value>
  	</property>
  	<property>
  		<name>dfs.namenode.rpc-address.cluster1.nn2</name>
  		<value>tunabook103:9000</value>
  	</property>
  	<property>
  		<name>dfs.namenode.http-address.cluster1.nn1</name>
  		<value>tunabook102:9870</value>
  	</property>
  	<property>
  		<name>dfs.namenode.http-address.cluster1.nn2</name>
  		<value>tunabook103:9870</value>
  	</property>
  	<property>
  		<name>dfs.namenode.shared.edits.dir</name>
  		<value>qjournal://tunabook104:8485;tunabook105:8485;tunabook106:8485/cluster1</value>
  	</property>
  	<property>
  		<name>dfs.journalnode.edits.dir</name>
  		<value>/export/qjmdata</value>
  	</property>
  	<property>
  		<name>dfs.client.failover.proxy.provider.cluster1</name>
  		<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
  	</property>
  	<property>
     		<name>dfs.ha.automatic-failover.enabled</name>
  		<value>true</value>
  	</property>
  	<property>
  		<name>dfs.ha.fencing.methods</name>
  		<value>sshfence</value>
  	</property>
  </configuration>
  
  

• mapred-site.xml

  <configuration>
  	<property>
  		<name>mapreduce.framework.name</name>
  		<value>yarn</value>
  	</property>
  	<property>
  		<name>mapreduce.application.classpath</name>
  		<value>$HADOOP_MAPRED_HOME/share/hadoop/mapreduce/*,
  		$HADOOP_MAPRED_HOME/share/hadoop/mapreduce/lib/*</value>
  	</property>
  </configuration>
  

• workers

  tunabook104
  tunabook105
  tunabook106
  

• yarn-site.xml

  <configuration>
  	<property>
  		<name>yarn.nodemanager.aux-services</name>
  		<value>mapreduce_shuffle</value>
  	</property>
  	<property>
  		<name>yarn.nodemanager.env-whitelist</name>
  		<value>
  			JAVA_HOME,HADOOP_COMMON_HOME,HADOOP_HDFS_HOME,HADOOP_CONF_DIR,
  			CLASSPATH_PREPEND_DISTCACHE,HADOOP_YARN_HOME,HADOOP_MAPRED_HOME
  		</value>
  	</property>
  </configuration>
  

• zoo.cfg

  dataDir=/export/data/zkdata
  
  server.1=tunabook102:2888:3888
  server.2=tunabook103:2888:3888
  server.3=tunabook104:2888:3888
  server.4=tunabook105:2888:3888
  server.5=tunabook106:2888:3888
  

三、启动集群

1. 启动ZooKeeper（tunabook102tunabook103tunabook104tunabook105tunabook106）

   zkServer.sh start
   

2. 初始化HA HDFS所使用的数据(tunabook102）

   hdfs zkfc -formatZK
   

3. 启动QJM（tunabook104tunabook105tunabook106）

   hdfs --daemon start journalnode
   

4. 格式化HFDS （tunabook102）

   hdfs namenode -format
   

5. 启动namenode（tunabook102）

   hdfs --daemon start namenode
   

6. 同步初始化结果（tunabook103）

   hdfs namenode -bootstrapStandby
   

7. 关闭namenode（tunabook102）

   hdfs --daemon stop namenode
   

8. 开启hadoop服务

   start-all.sh
   

四、运行结果