【Hadoop】Hadoop生态系列之搭建HadoopHA集群

上一篇：Hadoop生态系列之MapReduce Shuffle概述及常见问题

Hadoop HA构建

概述

准备工作

• 至少需要CentOS7 x64三台，完成jdk的安装、SSH免密码认证、ip主机映射及关闭防火墙操作

详见：https://blog.csdn.net/qq_44664231/article/details/108804561

主机和服务启动映射表

主机	服务
CentOSA	NameNode、zkfc、DataNode、JournalNode、Zookeeper、NodeManager
CentOSB	NameNode、zkfc、DataNode、JournalNode、Zookeeper、NodeManager、ResourceManager
CentOSC	DataNode、JournalNode、Zookeeper、NodeManager、ResourceManager

主机信息

主机名	IP信息
CentOSA	192.168.73.131
CentOSB	192.168.73.132
CentOSC	192.168.73.133

JDK安装和配置

[root@CentOSX ~]# rpm -ivh jdk-8u171-linux-x64.rpm
[root@CentOSX ~]# vi .bashrc
JAVA_HOME=/usr/java/latest
PATH=$PATH:$JAVA_HOME/bin
CLASSPATH=.
export JAVA_HOME
export CLASSPATH
export PATH
[root@CentOSX ~]# source .bashrc

IP主机名映射

[root@CentOSX ~]# vi /etc/hosts

192.168.253.130 CentOSA
192.168.253.131 CentOSB
192.168..132 CentOSC

关闭防火墙

[root@CentOSX ~]# systemctl stop firewalld
[root@CentOSX ~]# systemctl disable firewalld
Removed symlink /etc/systemd/system/multi-user.target.wants/firewalld.service.
Removed symlink /etc/systemd/system/dbus-org.fedoraproject.FirewallD1.service.
[root@CentOSX ~]# firewall-cmd --state
not running

SSH免密码认证

[root@CentOSX ~]# ssh-keygen -t rsa
[root@CentOSX ~]# ssh-copy-id CentOSA
[root@CentOSX ~]# ssh-copy-id CentOSB
[root@CentOSX ~]# ssh-copy-id CentOSC

Zookeeper服务的安装与配置

[root@CentOSX ~]# tar -zxf zookeeper-3.4.6.tar.gz -C /usr/
[root@CentOSX ~]# mkdir /root/zkdata

[root@CentOSA ~]# echo 1 >> /root/zkdata/myid
[root@CentOSB ~]# echo 2 >> /root/zkdata/myid
[root@CentOSC ~]# echo 3 >> /root/zkdata/myid

[root@CentOSX ~]# touch /usr/zookeeper-3.4.6/conf/zoo.cfg
[root@CentOSX ~]# vi /usr/zookeeper-3.4.6/conf/zoo.cfg
tickTime=2000
dataDir=/root/zkdata
clientPort=2181
initLimit=5
syncLimit=2
server.1=CentOSA:2887:3887
server.2=CentOSB:2887:3887
server.3=CentOSC:2887:3887

[root@CentOSX ~]# /usr/zookeeper-3.4.6/bin/zkServer.sh start zoo.cfg
[root@CentOSX ~]# /usr/zookeeper-3.4.6/bin/zkServer.sh status zoo.cfg
JMX enabled by default
Using config: /usr/zookeeper-3.4.6/bin/../conf/zoo.cfg
Mode: `follower|leader`
[root@CentOSX ~]# jps
5879 `QuorumPeerMain`
7423 Jps

搭建Hadoop 集群（HDFS）

解压并配置HADOOP环境变量

[root@CentOSX ~]# tar -zxf hadoop-2.9.2.tar.gz -C /usr/
[root@CentOSX ~]# vi .bashrc
HADOOP_HOME=/usr/hadoop-2.9.2
JAVA_HOME=/usr/java/latest
PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
CLASSPATH=.
export JAVA_HOME
export CLASSPATH
export PATH
export HADOOP_HOME
[root@CentOSX ~]# source .bashrc

配置core-site.xml

<!--配置Namenode服务ID-->
<property>		
      <name>fs.defaultFS</name>		
      <value>hdfs://mycluster</value>	
</property>
<property>		
     <name>hadoop.tmp.dir</name>		
     <value>/usr/hadoop-2.9.2/hadoop-${user.name}</value>    
</property>
<property>		
     <name>fs.trash.interval</name>		
     <value>30</value>    
</property>
<!--配置机架脚本-->
<property>		
     <name>net.topology.script.file.name</name>		
     <value>/usr/hadoop-2.9.2/etc/hadoop/rack.sh</value>    
</property>
<!--配置ZK服务信息-->
<property>   
	<name>ha.zookeeper.quorum</name>
	<value>CentOSA:2181,CentOSB:2181,CentOSC:2181</value> 
</property>
<!--配置SSH秘钥位置-->
<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>

配置机架脚本

[root@CentOSX ~]# touch /usr/hadoop-2.9.2/etc/hadoop/rack.sh
[root@CentOSX ~]# chmod u+x /usr/hadoop-2.9.2/etc/hadoop/rack.sh
[root@CentOSX ~]# vi /usr/hadoop-2.9.2/etc/hadoop/rack.sh
while [ $# -gt 0 ] ; do
	  nodeArg=$1
	  exec</usr/hadoop-2.9.2/etc/hadoop/topology.data
	  result="" 
	  while read line ; do
		ar=( $line ) 
		if [ "${ar[0]}" = "$nodeArg" ] ; then
		  result="${ar[1]}"
		fi
	  done 
	  shift 
	  if [ -z "$result" ] ; then
		echo -n "/default-rack"
	  else
		echo -n "$result "
	  fi
done
[root@CentOSX ~]# touch /usr/hadoop-2.9.2/etc/hadoop/topology.data
[root@CentOSX ~]# vi /usr/hadoop-2.9.2/etc/hadoop/topology.data
192.168.253.130 /rack01
192.168.253.131 /rack01
192.168.253.132 /rack03

配置hdfs-site.xml

<property>
	<name>dfs.replication</name>
	<value>3</value>
</property> 
<!--开启自动故障转移-->
<property>
	<name>dfs.ha.automatic-failover.enabled</name>
	<value>true</value>
</property>
<!--解释core-site.xml内容-->
<property>
	<name>dfs.nameservices</name>
	<value>mycluster</value>
</property>
<property>
	<name>dfs.ha.namenodes.mycluster</name>
	<value>nn1,nn2</value>
</property>
<property>
	<name>dfs.namenode.rpc-address.mycluster.nn1</name>
	<value>CentOSA:9000</value>
</property>
<property>
	 <name>dfs.namenode.rpc-address.mycluster.nn2</name>
	 <value>CentOSB:9000</value>
</property>
<!--配置日志服务器的信息-->
<property>
  <name>dfs.namenode.shared.edits.dir</name>
  <value>qjournal://CentOSA:8485;CentOSB:8485;CentOSC:8485/mycluster</value>
</property>
<!--实现故障转切换的实现类-->
<property>
    <name>dfs.client.failover.proxy.provider.mycluster</name>	<value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>

配置slaves

CentOSA
CentOSB
CentOSC

这里因为是CentOS7,需要我们额外安装一个小插件psmic，否则NameNode无法实现故障自动切换。

[root@CentOSX ~]# yum install -y psmisc 

启动HDFS(集群初始化启动)

[root@CentOSX ~]# hadoop-daemon.sh start journalnode (等待10s钟)
[root@CentOSA ~]# hdfs namenode -format
[root@CentOSA ~]# hadoop-daemon.sh start namenode
[root@CentOSB ~]# hdfs namenode -bootstrapStandby
[root@CentOSB ~]# hadoop-daemon.sh start namenode
#注册Namenode信息到zookeeper中,只需要在CentOSA或者B上任意一台执行一下指令
[root@CentOSA|B ~]# hdfs zkfc -formatZK
[root@CentOSA ~]# hadoop-daemon.sh start zkfc
[root@CentOSB ~]# hadoop-daemon.sh start zkfc
[root@CentOSX ~]# hadoop-daemon.sh start datanode

查看机架信息

[root@CentOSC ~]# hdfs dfsadmin -printTopology
Rack: /rack01
   192.168.253.130:50010 (CentOSA)
   192.168.253.131:50010 (CentOSB)

Rack: /rack03
   192.168.253.132:50010 (CentOSC)

Resource Manager搭建

配置yarn-site.xml

<property>
    <name>yarn.nodemanager.aux-services</name>
    <value>mapreduce_shuffle</value>
</property>
<property>
    <name>yarn.resourcemanager.ha.enabled</name>
    <value>true</value>
</property>
<property>
    <name>yarn.resourcemanager.cluster-id</name>
    <value>cluster</value>
</property>
<property>
    <name>yarn.resourcemanager.ha.rm-ids</name>
    <value>rm1,rm2</value>
</property>
<property>
    <name>yarn.resourcemanager.hostname.rm1</name>
    <value>CentOSB</value>
</property>
<property>
    <name>yarn.resourcemanager.hostname.rm2</name>
    <value>CentOSC</value>
</property>
<property>
    <name>yarn.resourcemanager.zk-address</name>
    <value>CentOSA:2181,CentOSB:2181,CentOSC:2181</value>
</property>
<!--关闭物理内存检查-->
<property>
    <name>yarn.nodemanager.pmem-check-enabled</name>
    <value>false</value>
</property>
<!--关闭虚拟内存检查-->
<property>
    <name>yarn.nodemanager.vmem-check-enabled</name>
    <value>false</value>
</property>

配置mapred-site.xml

<property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
</property>

启动 | 关闭Yarn服务

[root@CentOSB ~]# yarn-daemon.sh start|stop resourcemanager
[root@CentOSC ~]# yarn-daemon.sh start|stop resourcemanager
[root@CentOSX ~]# yarn-daemon.sh start|stop nodemanager

---

至此，Hadoop集群就已经搭建完毕，可以使用jps命令查看当前的java进程，如果进程如下图所示，即为环境搭建成功！