步骤3:HDFS-HA集群配置文件
core-siet.xml
<configuration>
<!-- 指定NameNode的地址 -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://mycluster</value>
</property>
<!-- 指定hadoop数据的存储目录 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/opt/ha/hadoop-3.1.3/data</value>
</property>
<!-- 配置HDFS网页登录使用的静态用户为atguigu -->
<property>
<name>hadoop.http.staticuser.user</name>
<value>atguigu</value>
</property>
<!-- 配置该atguigu(superUser)允许通过代理访问的主机节点 -->
<property>
<name>hadoop.proxyuser.atguigu.hosts</name>
<value>*</value>
</property>
<!-- 配置该atguigu(superUser)允许通过代理用户所属组 -->
<property>
<name>hadoop.proxyuser.atguigu.groups</name>
<value>*</value>
</property>
<!-- 指定zkfc要连接的zkServer地址 -->
<property>
<name>ha.zookeeper.quorum</name>
<value>hadoop102:2181,hadoop103:2181,hadoop104:2181</value>
</property>
</configuration>
hdfs-site.xml
<configuration>
<!-- 完全分布式集群名称 -->
<property>
<name>dfs.nameservices</name>
<value>mycluster</value>
</property>
<!-- 集群中NameNode节点都有哪些 -->
<property>
<name>dfs.ha.namenodes.mycluster</name>
<value>nn1,nn2,nn3</value>
</property>
<!-- NameNode的RPC通信地址 -->
<property>
<name>dfs.namenode.rpc-address.mycluster.nn1</name>
<value>hadoop102:9820</value>
</property>
<property>
<name>dfs.namenode.rpc-address.mycluster.nn2</name>
<value>hadoop103:9820</value>
</property>
<property>
<name>dfs.namenode.rpc-address.mycluster.nn3</name>
<value>hadoop104:9820</value>
</property>
<!-- NameNode的http通信地址 -->
<property>
<name>dfs.namenode.http-address.mycluster.nn1</name>
<value>hadoop102:9870</value>
</property>
<property>
<name>dfs.namenode.http-address.mycluster.nn2</name>
<value>hadoop103:9870</value>
</property>
<property>
<name>dfs.namenode.http-address.mycluster.nn3</name>
<value>hadoop104:9870</value>
</property>
<!-- JournalNode数据存储目录 -->
<property>
<name>dfs.journalnode.edits.dir</name>
<value>${hadoop.tmp.dir}/jn</value>
</property>
<!-- 指定NameNode元数据在JournalNode上的存放位置 -->
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://hadoop102:8485;hadoop103:8485;hadoop104:8485/mycluster</value>
</property>
<!-- 访问代理类:client用于确定哪个NameNode为Active -->
<property>
<name>dfs.client.failover.proxy.provider.mycluster</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<!-- 配置隔离机制,即同一时刻只能有一台服务器对外响应 -->
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence</value>
</property>
<!-- 使用隔离机制时需要ssh秘钥登录-->
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/home/atguigu/.ssh/id_rsa</value>
</property>
<!-- 启动自动故障转移机制zkfc -->
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
</configuration>
步骤4:YARN-HA集群配置文件
yarn-site.xml
<configuration>
<!-- 指定MR走shuffle -->
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<!-- 启用resourcemanager ha -->
<property>
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>
<!-- 声明两台resourcemanager的地址 -->
<property>
<name>yarn.resourcemanager.cluster-id</name>
<value>cluster-yarn1</value>
</property>
<!--指定resourcemanager的逻辑列表-->
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<!-- ========== rm1的配置 ========== -->
<!-- 指定rm1的主机名 -->
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>hadoop102</value>
</property>
<!-- 指定rm1的web端地址 -->
<property>
<name>yarn.resourcemanager.webapp.address.rm1</name>
<value>hadoop102:8088</value>
</property>
<!-- 指定rm1的内部通信地址 -->
<property>
<name>yarn.resourcemanager.address.rm1</name>
<value>hadoop102:8032</value>
</property>
<!-- 指定AM向rm1申请资源的地址 -->
<property>
<name>yarn.resourcemanager.scheduler.address.rm1</name>
<value>hadoop102:8030</value>
</property>
<!-- 指定供NM连接的地址 -->
<property>
<name>yarn.resourcemanager.resource-tracker.address.rm1</name>
<value>hadoop102:8031</value>
</property>
<!-- ========== rm2的配置 ========== -->
<!-- 指定rm2的主机名 -->
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>hadoop103</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address.rm2</name>
<value>hadoop103:8088</value>
</property>
<property>
<name>yarn.resourcemanager.address.rm2</name>
<value>hadoop103:8032</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address.rm2</name>
<value>hadoop103:8030</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address.rm2</name>
<value>hadoop103:8031</value>
</property>
<!-- 指定zookeeper集群的地址 -->
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>hadoop102:2181,hadoop103:2181,hadoop104:2181</value>
</property>
<!-- 启用自动恢复 -->
<property>
<name>yarn.resourcemanager.recovery.enabled</name>
<value>true</value>
</property>
<!-- 指定resourcemanager的状态信息存储在zookeeper集群 -->
<property>
<name>yarn.resourcemanager.store.class</name> <value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
</property>
<!-- 环境变量的继承 -->
<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>
<!-- yarn容器允许分配的最大最小内存 -->
<property>
<name>yarn.scheduler.minimum-allocation-mb</name>
<value>512</value>
</property>
<property>
<name>yarn.scheduler.maximum-allocation-mb</name>
<value>4096</value>
</property>
<!-- yarn容器允许管理的物理内存大小 -->
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>4096</value>
</property>
<!-- 关闭yarn对物理内存和虚拟内存的限制检查 -->
<property>
<name>yarn.nodemanager.pmem-check-enabled</name>
<value>false</value>
</property>
<property>
<name>yarn.nodemanager.vmem-check-enabled</name>
<value>false</value>
</property>
<!-- 开启日志聚集功能 -->
<property>
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>
<!-- 设置日志聚集服务器地址 -->
<property>
<name>yarn.log.server.url</name>
<value>http://hadoop102:19888/jobhistory/logs</value>
</property>
<!-- 设置日志保留时间为7天 -->
<property>
<name>yarn.log-aggregation.retain-seconds</name>
<value>604800</value>
</property>
</configuration>