当先锋百科网

首页 1 2 3 4 5 6 7

Hadoop HA 搭建（三台主机）

Hadoop HA 搭建

搭建准备

Centos 7 主机三台

主机名IP 地址
master192.168.1.121
slave1192.168.1.122
slave2192.168.1.123

软件版本

软件名称软件版本
JDK8u261
Zookeeper3.5.9
Hadoop2.7.7

软件安装
安装包： /home/apps/package
安装路径：/home/apps/

安装步骤

一、关闭防火墙

三个节点防火墙均关闭

[root@master ~]# systemctl stop firewalld
[root@master ~]# systemctl status firewalld

二、解压组件

解压zookeeper

[root@master package]# tar -zxvf apache-zookeeper-3.5.9-bin.tar.gz

配置zookeeper详请阅读

解压hadoop-2.7.7.tar.gz

[root@master package]# tar -zxvf hadoop-2.7.7.tar.gz

将Hadoop文件放在/home/apps/下

[root@master package]# pwd
/home/apps/package
[root@master package]# mv hadoop-2.7.7 ../

解压jdk-8u261-linux-x64.tar.gz

[root@master package]# tar -zxvf jdk-8u261-linux-x64.tar.gz

将jdk解压文件放在/home/apps/下

[root@master package]# mv jdk1.8.0_261 jdk1.8
[root@master package]# pwd
/home/apps/package
[root@master package]# mv jdk1.8 ../

三、配置文件

core-site.xml

[root@master hadoop]# vi /home/apps/hadoop-2.7.7/etc/hadoop/core-site.xml 
<configuration>

    <property>

        <name>fs.defaultFS</name>

        <value>hdfs://ns1</value>

    </property>

    <property>

        <name>hadoop.tmp.dir</name>

        <value>/home/apps/hdfs/tmp</value>

    </property>

    <property>

        <name>ha.zookeeper.quorum</name>

        <value>master,slave1,slave2</value>

    </property>

</configuration>

hdfs-site.xml

[root@master hadoop]# vi /home/apps/hadoop-2.7.7/etc/hadoop/hdfs-site.xml
<configuration>

    <property>

        <name>dfs.nameservices</name>

        <value>ns1</value>

    </property>

    <property>

        <name>dfs.ha.namenodes.ns1</name>

        <value>nn1,nn2</value>

    </property>

    <property>

        <name>dfs.namenode.rpc-address.ns1.nn1</name>

        <value>master:9000</value>

    </property>

    <property>

        <name>dfs.namenode.http-address.ns1.nn1</name>

        <value>master:50070</value>

    </property>

    <property>

        <name>dfs.namenode.rpc-address.ns1.nn2</name>

        <value>slave1:9000</value>

    </property>

    <property>

        <name>dfs.namenode.http-address.ns1.nn2</name>

        <value>slave1:50070</value>

    </property>

    <property>

        <name>dfs.namenode.shared.edits.dir</name>

        <value>qjournal://master;slave1;slave2/ns1</value>

    </property>

    <property>

        <name>dfs.journalnode.edits.dir</name>

        <value>/home/apps/hdfs/journal</value>

    </property>

    <property>

        <name>dfs.namenode.name.dir</name>

        <value>/home/apps/hdfs/name</value>

    </property>

    <property>

        <name>dfs.datanode.data.dir</name>

        <value>/home/apps/hdfs/data</value>

    </property>

    <property>

        <name>dfs.ha.automatic-failover.enabled</name>

        <value>true</value>

    </property>

    <property>

        <name>dfs.client.failover.proxy.provider.ns1</name>

        <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>

    </property>

    <property>

        <name>dfs.ha.fencing.methods</name>

        <value>

            sshfence

            shell(/bin/true)

        </value>

    </property>

    <property>

        <name>dfs.ha.fencing.ssh.private-key-files</name>

        <value>/root/.ssh/id_rsa</value>

    </property>

</configuration>

yarn-site.xml

[root@master hadoop]# vi /home/apps/hadoop-2.7.7/etc/hadoop/yarn-site.xml
<configuration>

    <property>

        <name>yarn.resourcemanager.ha.enabled</name>

        <value>true</value>

    </property>

    <property>

        <name>yarn.resourcemanager.cluster-id</name>

        <value>yrc</value>

    </property>

    <property>

        <name>yarn.resourcemanager.ha.rm-ids</name>

        <value>rm1,rm2</value>

    </property>

    <property>

        <name>yarn.resourcemanager.hostname.rm1</name>

        <value>slave1</value>

    </property>

    <property>

        <name>yarn.resourcemanager.hostname.rm2</name>

        <value>slave2</value>

    </property>

    <property>

        <name>yarn.resourcemanager.zk-address</name>

        <value>master,slave1,slave2</value>

    </property>

    <property>

        <name>yarn.nodemanager.aux-services</name>

        <value>mapreduce_shuffle</value>

    </property>

    <property>

        <name>yarn.log-aggregation-enable</name>

        <value>true</value>

    </property>

</configuration>

mapred-site.xml

[root@master hadoop]# vi /home/apps/hadoop-2.7.7/etc/hadoop/mapred-site.xml
<configuration>

    <property>

        <name>mapreduce.framework.name</name>

        <value>yarn</value>

    </property>

    <property>

        <name>yarn.app.mapreduce.am.staging-dir</name>

        <value>/home/apps/hdfs/history</value>

    </property>

</configuration>

slaves

[root@master hadoop]# vi /home/apps/hadoop-2.7.7/etc/hadoop/slaves
slave1
slave2

四、环境变量

设置全局环境变量
三台主机都要设置
/etc/profile

[root@master hadoop]# vi /etc/profile
export JAVA_HOME=/home/apps/jdk1.8
export PATH=$JAVA_HOME/bin:$PATH
export CLASSPATH=.:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar
export HADOOP_HOME=/home/apps/hadoop-2.7.7
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
[root@master hadoop]# source /etc/profile

hadoop-env.sh环境变量
hadoop-env.sh

[root@master hadoop]# vi /home/apps/hadoop-2.7.7/etc/hadoop/hadoop-env.sh
export HADOOP_HOME=/home/apps/hadoop-2.7.7/
export HADOOP_CONF_DIR=/home/apps/hadoop-2.7.7/etc/hadoop
export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
[root@master hadoop]# source /home/apps/hadoop-2.7.7/etc/hadoop/hadoop-env.sh

五、发送到其他两个节点

hadoop文件

[root@master hadoop]# scp -r /home/apps/hadoop slave1:/home/apps/ 
[root@master hadoop]# scp -r /home/apps/hadoop slave2:/home/apps/

JDK文件

[root@master apps]# scp -r /home/apps/jdk1.8 slave1:/home/apps/ 
[root@master apps]# scp -r /home/apps/jdk1.8 slave2:/home/apps/

在其他两个节点上面使环境变量立即生效

  • slave1
[root@slave1 hadoop]# source /home/apps/hadoop-2.7.7/etc/hadoop/hadoop-env.sh
[root@slave1 hadoop]# source /etc/profile
  • slave2
[root@slave2 hadoop]# source /home/apps/hadoop-2.7.7/etc/hadoop/hadoop-env.sh
[root@slave1 hadoop]# source /etc/profile

六、初始化HDFS

  • 三台机器都要启动
[root@master hadoop]# hadoop-daemon.sh start journalnode
  • 在master节点上面对HDFS和zookeeper进行格式化
[root@master apps]# hdfs namenode -format
[root@master apps]# hdfs zkfc -formatZK 
[root@master apps]# hadoop-daemon.sh start namenode
  • 在节点slave1上面将master格式化的元目录同步到slave1上
[root@slave1 ~]# hdfs namenode -bootstrapStandby

七、启动Hadoop

  • master
[root@master apps]# start-dfs.sh 
[root@master apps]# mr-jobhistory-daemon.sh start historyserver
  • slave1
[root@slave1 ~]# start-yarn.sh 
[root@master apps]# mr-jobhistory-daemon.sh start historyserver
  • slave2
[root@slave2 ~]# yarn-daemon.sh start resourcemanager 
[root@master apps]# mr-jobhistory-daemon.sh start historyserver

启动结果

  • master
[root@master ~]# jps
2454 NameNode
2154 DataNode
3215 Jps
2541 QuorumPeerMain
2231 DFSZKFailoverController
55412 JobHistoryServer
45751 JournalNode
  • slave1
[root@slave1 ~]# jps
3249 NodeManager
2403 DFSZKFailoverController
2292 DataNode
1926 JournalNode
1800 QuorumPeerMain
2201 NameNode
2940 JobHistoryServer
3724 Jps
3437 ResourceManager
  • slave2
[root@slave2 ~]# jps
2456 QuorumPeerMain
11547 NodeManager
54978 Jps
54121 JournalNode
21544 ResourceManager
22124 DataNode
1445 JobHistoryServer

结语：大数据笔记 Hadoop HA 搭建