tee /usr/local/hadoop-3.2.4/etc/hadoop/core-site.xml<<-'EOF'
<configuration>
<property>
<name>io.compression.codecs</name>
<value>org.apache.hadoop.io.compress.SnappyCodec</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/data/hadoop/tmp</value>
</property>
<property>
<name>fs.defaultFS</name>
<value>hdfs://hadoopCluster</value>
</property>
<property>
<name>ha.zookeeper.quorum</name>
<value>hadoop1:2181,hadoop2:2181,hadoop3:2181</value>
</property>
<property>
<name>hadoop.proxyuser.root.hosts</name>
<value>*</value>
</property>
<property>
<name>hadoop.proxyuser.root.groups</name>
<value>*</value>
</property>
</configuration>
EOF
tee /usr/local/hadoop-3.2.4/etc/hadoop/hdfs-site.xml <<-'EOF'
<configuration>
<property>
<name>dfs.nameservices</name>
<value>hadoopCluster</value>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<!-- namenode 节点数据（即元数据）的存放位置，可以指定多个目录实现容错，多个目录用逗号分隔 -->
<name>dfs.namenode.name.dir</name>
<value>/data/hadoop/namenode</value>
</property>
<property>
<!-- datanode 节点数据（即数据块）的存放位置 -->
<name>dfs.datanode.data.dir</name>
<value>/data/hadoop/datanode</value>
</property>
<property>
<name>dfs.ha.namenodes.hadoopCluster</name>
<value>nn1,nn2</value>
</property>
<property>
<name>dfs.namenode.rpc-address.hadoopCluster.nn1</name>
<value>hadoop1:8020</value>
</property>
<property>
<name>dfs.namenode.rpc-address.hadoopCluster.nn2</name>
<value>hadoop2:8020</value>
</property>
<property>
<name>dfs.namenode.http-address.hadoopCluster.nn1</name>
<value>hadoop1:9870</value>
</property>
<property>
<name>dfs.namenode.http-address.hadoopCluster.nn2</name>
<value>hadoop2:9870</value>
</property>
<property>
<name>dfs.namenode.shared.edits.dir</name>
<value>qjournal://hadoop1:8485;hadoop2:8485;hadoop3:8485/hadoopCluster</value>
</property>
<property>
<!-- Journal Edit Files 的存储目录 -->
<name>dfs.journalnode.edits.dir</name>
<value>/data/hadoop/journalnode</value>
</property>
<property>
<name>dfs.ha.zkfc.failover-controller.active-standby-checks</name>
<value>true</value>
</property>
<property>
<!-- 开启故障自动转移 -->
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.namenode.heartbeat.recheck-interval</name>
<value>15000</value> <!-- 增加心跳检测的频率，减少 NameNode 宕机后切换的延迟： -->
</property>
<property>
<!-- 访问代理类，用于确定当前处于 Active 状态的 NameNode -->
<name>dfs.client.failover.proxy.provider.hadoopCluster</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<property>
<name>dfs.ha.fencing.methods</name>
<value>sshfence</value>
</property>
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/root/.ssh/id_rsa</value>
</property>
<property>
<name>dfs.datanode.du.reserved</name>
<value>21474836480</value>
<!-- 预留20GB -->
</property>
<property>
<!-- 动态排除 DataNode 节点-->
<name>dfs.hosts.exclude</name>
<value>/usr/local/hadoop-3.2.4/etc/hadoop/dfs.hosts.exclude</value>
</property>
<property>
<name>dfs.namenode.edits.dir.minimum.replication</name>
<value>2</value> </property>
</configuration>
EOF
tee /usr/local/hadoop-3.2.4/etc/hadoop/yarn-site.xml <<-'EOF'
<configuration>
<property>
<!--配置 NodeManager 上运行的附属服务。需要配置成 mapreduce_shuffle 后才可以在 Yarn 上运行 MapReduce 程序。-->
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<!-- 是否启用日志聚合 (可选) -->
<name>yarn.log-aggregation-enable</name>
<value>true</value>
</property>
<property>
<!-- 聚合日志的保存时间 (可选) -->
<name>yarn.log-aggregation.retain-seconds</name>
<value>86400</value>
</property>
<property>
<!-- 启用 RM HA -->
<name>yarn.resourcemanager.ha.enabled</name>
<value>true</value>
</property>
<property>
<!-- RM 集群标识 -->
<name>yarn.resourcemanager.cluster-id</name>
<value>my-yarn-cluster</value>
</property>
<property>
<!-- RM 的逻辑 ID 列表 -->
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<property>
<!-- RM1 的服务地址 -->
<name>yarn.resourcemanager.hostname.rm1</name>
<value>hadoop1</value>
</property>
<property>
<!-- RM2 的服务地址 -->
<name>yarn.resourcemanager.hostname.rm2</name>
<value>hadoop2</value>
</property>
<property>
<!-- RM1 Web 应用程序的地址 -->
<name>yarn.resourcemanager.webapp.address.rm1</name>
<value>hadoop1:8088</value>
</property>
<property>
<!-- RM2 Web 应用程序的地址 -->
<name>yarn.resourcemanager.webapp.address.rm2</name>
<value>hadoop2:8088</value>
</property>
<property>
<!-- ZooKeeper 集群的地址 -->
<name>yarn.resourcemanager.zk-address</name>
<value>hadoop1:2181,hadoop2:2181,hadoop3:2181</value>
</property>
<property>
<!-- 启用自动恢复 -->
<name>yarn.resourcemanager.recovery.enabled</name>
<value>true</value>
</property>
<property>
<!-- 用于进行持久化存储的类 -->
<name>yarn.resourcemanager.store.class</name>
<value>org.apache.hadoop.yarn.server.resourcemanager.recovery.ZKRMStateStore</value>
</property>
<property>
<name>yarn.nodemanager.remote-app-log-dir</name>
<value>/yarn/logs</value>
</property>
<property>
<name>yarn.nodemanager.remote-app-log-dir-suffix</name>
<value>logs</value>
</property>
<property>
<name>yarn.nodemanager.resource.memory-mb</name>
<value>12288</value> <!-- 根据服务器内存大小调整 -->
</property>
<property>
<name>yarn.nodemanager.resource.cpu-vcores</name>
<value>6</value> <!-- 根据服务器 CPU 核心数调整 -->
</property>
<property>
<name>mapreduce.task.io.sort.mb</name>
<value>256</value> <!-- 调整为适合任务规模的值 -->
</property>
</configuration>
EOF
tee /usr/local/hadoop-3.2.4/etc/hadoop/dfs.hosts.exclude <<-'EOF'
hadoop4
EOF