【Hive部署搭建高可用集群 ha】

Hive搭建 ha高可用集群

第一步 修改hdfs-site.xml

<configuration>
<!--指定hdfs的nameservice为rootcloud，需要和core-site.xml中的保持一致 -->
<property>
	<name>dfs.nameservices</name>
	<value> rootcloud </value>
</property>
<!-- cluster1下面有两个NameNode，分别是nn1，nn2 -->
<property>
	<name>dfs.ha.namenodes .rootcloud </name>
	<value>nn1,nn2</value>
</property>
<!-- nn1的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.cluster1.nn1</name>
	<value>hadoop01:8020</value>
	</property>
<property>
    <name>dfs.namenode.servicerpc-address.rootcloud.nn1</name>
    <value>hadoop01:8021</value>
  </property>
<!-- nn1的http通信地址 -->
<property>
	<name>dfs.namenode.http-address.cluster1.nn1</name>
	<value> hadoop01:50070</value>
</property>
<!-- nn2的RPC通信地址 -->
<property>
	<name>dfs.namenode.rpc-address.cluster1.nn2</name>
	<value> hadoop02:8020</value>
</property>
<property>
    <name>dfs.namenode.servicerpc-address.rootcloud.nn1</name>
    <value>hadoop02:8021</value>
  </property>
<!-- nn2的http通信地址 -->
<property>
	<name>dfs.namenode.http-address.cluster1.nn2</name>
	<value> hadoop02:50070</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:// hadoop01:8485; hadoop02:8485; hadoop03:8485 /rootcloud-journal-new</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> /data/rootcloud/hadoop-3.2.2/journal</value>
</property>
<!-- 开启NameNode失败自动切换 -->
<property>
	<name>dfs.ha.automatic-failover.enabled</name>
	<value> shell(/bin/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.rootcloud</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> 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>50000</value>
</property>
</configuration>

第二步 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:// rootcloud</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> /data/app/hadoop-3.2.2/etc/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> hadoop01:2181,hadoop02:2181,hadoop03:2181 </value>
</property>
</configuration>

第三步 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>

第四步 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> yarn-ha</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> hadoop01</value>
</property>
<property>
	<name>yarn.resourcemanager.hostname.rm2</name>
	<value> hadoop02</value>
</property>
<!-- 指定zk集群地址 -->
<property>
	<name>yarn.resourcemanager.zk-address</name>
	<value> hadoop01:2181,hadoop02:2181,hadoop03:2181 </value>
</property>
<property>
	<name>yarn.nodemanager.aux-services</name>
	<value>mapreduce_shuffle</value>
</property>
</configuration>