Hadoop2.7.2 HA部署
文章目录
解压
tar -zxvf hadoop-2.7.2.tar.gz -C /opt/
改名
cd /opt
mv hadoop-2.7.2 hadoop
配置环境变量
sudo vi /etc/profile
添加
#HADOOP_HOME
export HADOOP_HOME=/opt/hadoop
export PATH=$PATH:$HADOOP_HOME/bin
export PATH=$PATH:$HADOOP_HOME/sbin
使环境变量生效
source /etc/profile
配置 hadoop-env.sh
export JAVA_HOME=/opt/jdk
配置yarn-env.sh
export JAVA_HOME=/opt/jdk
配置mapred-env.sh
export JAVA_HOME=/opt/jdk
配置slaves
server1
server2
server3
配置 core-site.xml
<configuration>
<!-- 把两个 NameNode)的地址组装成一个集群 mycluster -->
<property>
<name>fs.defaultFS</name>
<value>hdfs://mycluster</value>
</property>
<!-- 指定 hadoop 运行时产生文件的存储目录 -->
<property>
<name>hadoop.tmp.dir</name>
<value>/opt/hadoop/data/tmp</value>
</property>
<property>
<name>ha.zookeeper.quorum</name>
<value>server1:2181,server2:2181,server3:2181</value>
</property>
<property>
<name>ipc.client.connect.max.retries</name>
<value>10</value>
</property>
<property>
<name>ipc.client.connect.retry.interval</name>
<value>1000</value>
</property>
</configuration>
配置 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</value>
</property>
<!-- nn1 的 RPC 通信地址 -->
<property>
<name>dfs.namenode.rpc-address.mycluster.nn1</name>
<value>server1:9000</value>
</property>
<!-- nn2 的 RPC 通信地址 -->
<property>
<name>dfs.namenode.rpc-address.mycluster.nn2</name>
<value>server2:9000</value>
</property>
<!-- nn1 的 http 通信地址 -->
<property>
<name>dfs.namenode.http-address.mycluster.nn1</name>
<value>server1:50070</value>
</property>
<!-- nn2 的 http 通信地址 -->
<property>
<name>dfs.namenode.http-address.mycluster.nn2</name>
<value>server2:50070</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://server1:8485;server2:8485;server3:8485/mycluster</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 无秘钥登录-->
<property>
<name>dfs.ha.fencing.ssh.private-key-files</name>
<value>/home/server/.ssh/id_rsa</value>
</property>
<!-- 声明 journalnode 服务器存储目录-->
<property>
<name>dfs.journalnode.edits.dir</name>
<value>/opt/hadoop/data/jn</value>
</property>
<!-- 关闭权限检查-->
<property>
<name>dfs.permissions.enable</name>
<value>false</value>
</property>
<!-- 访问代理类:client,mycluster,active 配置失败自动切换实现方式-->
<property>
<name>dfs.client.failover.proxy.provider.mycluster</name>
<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<property>
<name>dfs.ha.automatic-failover.enabled</name>
<value>true</value>
</property>
</configuration>
配置yarn-site.xml
<configuration>
<!-- Site specific YARN configuration properties -->
<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>
<property>
<name>yarn.resourcemanager.ha.rm-ids</name>
<value>rm1,rm2</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm1</name>
<value>server1</value>
</property>
<property>
<name>yarn.resourcemanager.hostname.rm2</name>
<value>server2</value>
</property>
<!--指定 zookeeper 集群的地址-->
<property>
<name>yarn.resourcemanager.zk-address</name>
<value>server1:2181,server2:2181,server3:2181</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>
</configuration>
初始化
各个节点启动journalnode
hadoop-daemon.sh start journalnode
节点一初始化namenode,然后启动namenode
hdfs namenode -format
hadoop-daemon.sh start namenode
节点二同步namenode的信息
hdfs namenode -bootstrapStandby
第二个节点启动第二个namenode
hadoop-daemon.sh start namenode
在节点一启动
hadoop-daemons.sh start datanode
检查完之后关闭
stop-dfs.sh
各个节点开启zookeeper
zkServer.sh start
第一个节点初始化hadoop在zookeeper里面的状态
hdfs zkfc -formatZK
再次启动
start-dfs.sh
第一个节点启动
start-yarn.sh
第二个节点启动
yarn-daemon.sh start resourcemanager
查看服务状态
hdfs haadmin -getServiceState nn1
hdfs haadmin -getServiceState nn2
yarn rmadmin -getServiceState rm1
yarn rmadmin -getServiceState rm2