HDFS高可用&YARN高可用集群(生产配置)

其他 2019-01-18 00:14:47 阅读次数: 0

准备CentOSC CentOSA CentOSB

CentOSA(192.168.169.140)

CentOSB(192.168.169.141)

CentOSC
 

 

zookeeper
 

zookeeper

zookeeper

zkfc

zkfc

 

nn1

 

nn2

 

 

 

journalnode

journalnode

journalnode

datenode

datenode

datenode

 

rm1

rm12

nodemanager

nodemanager

nodemanager

 

配置主机名和IP映射关系

[root@CentOSX ~]代表3个都配置

[root@CentOSX ~]# vi /etc/hosts
192.168.169.140 CentOSA
192.168.169.141 CentOSB
192.168.169.142 CentOSC

*关闭防火墙

[root@CentOSX ~]# service iptables stop #关闭防火墙
iptables: Setting chains to policy ACCEPT: filter          [  OK  ]
iptables: Flushing firewall rules:                         [  OK  ]
iptables: Unloading modules:                               [  OK  ]
[root@CentOSX ~]# chkconfig iptables off #关闭开机自启
[root@CentOSX ~]# chkconfig --list | grep iptables#查看
iptables       	0:off	1:off	2:off	3:off	4:off	5:off	6:off

 同步CentOSA/B/C上的时钟

[root@CentOSX ~]# date -s '2019-01-09 11:26:00' #设置同步时间
Wed Jan  9 11:26:00 CST 2019
[root@CentOSX ~]# clock -w

配置CentOSA/B/C机器间ssh免密码认证

[root@CentOSX ~]# ssh-keygen -t rsa
[root@CentOSX ~]# ssh-copy-id CentOSA #相互之间免密
[root@CentOSX ~]# ssh-copy-id CentOSB #相互之间免密
[root@CentOSX ~]# ssh-copy-id CentOSC #相互之间免密
[root@CentOSX ~]# ssh CentOSC #看是否成功
[root@CentOSX ~]# ssh CentOSB #看是否成功
[root@CentOSX ~]# ssh CentOSA #看是否成功

 

安装JDK并且配置JAVA_HOME环境变量

 yum install lrzsz -y #运行一个插件 上传文件 rz 选择上传的文件 jdk-8u171-linux-x64.rpm #hadoop-2.6.0_x64.tar.gz zookeeper-3.4.6.tar.gz

[root@CentOSA ~]# ls
anaconda-ks.cfg          install.log.syslog       yes.pub
hadoop-2.6.0_x64.tar.gz  jdk-8u171-linux-x64.rpm  zookeeper-3.4.6.tar.gz
install.log              yes

[root@CentOSA ~]# scp jdk-8u171-linux-x64.rpm CentOSB:~ #把文件给 b 和 c
jdk-8u171-linux-x64.rpm                               100%  167MB  83.6MB/s   00:02    
[root@CentOSA ~]# scp jdk-8u171-linux-x64.rpm CentOSC:~
jdk-8u171-linux-x64.rpm                               100%  167MB  55.7MB/s   00:03    
[root@CentOSA ~]# scp zookeeper-3.4.6.tar.gz CentOSB:~
zookeeper-3.4.6.tar.gz                                100%   17MB  16.9MB/s   00:00    
[root@CentOSA ~]# scp zookeeper-3.4.6.tar.gz CentOSC:~
zookeeper-3.4.6.tar.gz                                100%   17MB  16.9MB/s   00:01    
[root@CentOSA ~]# scp hadoop-2.6.0_x64.tar.gz CentOSB:~/
hadoop-2.6.0_x64.tar.gz                               100%  172MB  85.9MB/s   00:02    
[root@CentOSA ~]# scp hadoop-2.6.0_x64.tar.gz CentOSC:~/
hadoop-2.6.0_x64.tar.gz                               100%  172MB  85.9MB/s   00:02 

[root@CentOSX ~]# rpm -ivh jdk-8u171-linux-x64.rpm 
Preparing...                ########################################### [100%]
   1:jdk1.8                 ########################################### [100%]
Unpacking JAR files...
	tools.jar...
	plugin.jar...
	javaws.jar...
	deploy.jar...
	rt.jar...
	jsse.jar...
	charsets.jar...
	localedata.jar...
[root@CentOSX ~]# vi .bashrc 
JAVA_HOME=/usr/java/latest
PATH=$PATH:$JAVA_HOME/bin
CLASSPATH=.
export JAVA_HOME
export PATH
export CLASSPATH
[root@CentOSX ~]# source .bashrc

安装配置zookeeper集群

[root@CentOSX ~]# tar -zxf zookeeper-3.4.6.tar.gz -C /usr/
[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 ~]# mkdir /root/zkdata
[root@CentOSA ~]# echo 1 >> zkdata/myid
[root@CentOSB ~]# echo 2 >> zkdata/myid
[root@CentOSC ~]# echo 3 >> zkdata/myid
[root@CentOSX ~]# /usr/zookeeper-3.4.6/bin/zkServer.sh start zoo.cfg

 启动完成zookeeper之后需要用户执行/usr/zookeeper-3.4.6/bin/zkServer.sh status zoo.cfg查看集群状态,一定会有1个节点是leader其他节点是follower

安装配置hadoop

解压配置HADOOP_HOME

[root@CentOSX ~]# tar -zxf hadoop-2.6.0_x64.tar.gz -C /usr/
[root@CentOSX ~]# vi .bashrc

HADOOP_HOME=/usr/hadoop-2.6.0
JAVA_HOME=/usr/java/latest
PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
CLASSPATH=.
export JAVA_HOME
export PATH
export CLASSPATH
export HADOOP_HOME
[root@CentOSX ~]# source .bashrc

配置etc/hadoop/core-site.xml

<!--对namenode做命名服务,该服务会在hdfs-site.xml解释-->
<property>
   <name>fs.defaultFS</name>
   <value>hdfs://mycluster</value>
</property>
<property>
  <name>hadoop.tmp.dir</name>
  <value>/usr/hadoop-2.6.0/hadoop-${user.name}</value>  
</property>
<property>
  <name>fs.trash.interval</name>
  <value>30</value>  
</property>
<!--设置hadoop的机架脚本-->
<property>
  <name>net.topology.script.file.name</name>
  <value>/usr/hadoop-2.6.0/etc/hadoop/rack.sh</value>  
</property>

 创建机架脚本

`/usr/hadoop-2.6.0/etc/hadoop/rack.sh`

while [ $# -gt 0 ] ; do
	nodeArg=$1
	exec</usr/hadoop-2.6.0/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

 给rack.sh添加可执行权限chmod u+x /usr/hadoop-2.6.0/etc/hadoop/rack.sh

创建机架映射文件

/usr/hadoop-2.6.0/etc/hadoop/topology.data`

192.168.169.140 /rack1
192.168.169.141 /rack1
192.168.169.142 /rack2

 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>
<!--设置zookeeper服务地址-->
<property> 
    <name>ha.zookeeper.quorum</name>
    <value>CentOSA:2181,CentOSB:2181,CentOSC:2181</value>
</property>
<!--解析core-site.xml中mycluster配置-->
<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>
<!--连接日志服务-->
<property>
    <name>dfs.namenode.shared.edits.dir</name>
    <value>qjournal://CentOSA:8485;CentOSB:8485;CentOSC:8485/mycluster</value>
</property>
<!--配置转移处理者-->
<property>
    <name>dfs.client.failover.proxy.provider.mycluster</name>
    <value>org.apache.hadoop.hdfs.server.namenode.ha.ConfiguredFailoverProxyProvider</value>
</property>
<!--配置SSH防御信息-->
<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>

 编辑slaves信息

[root@CentOSX ~]# vi /usr/hadoop-2.6.0/etc/hadoop/slaves

CentOSA
CentOSB
CentOSC

启动HDFS服务(第一次初始化)

[root@CentOSX ~]# hadoop-daemon.sh start journalnode //等上10秒钟，再进行下一步操作
[root@CentOSA ~]# hdfs namenode -format
[root@CentOSA ~]# hadoop-daemon.sh start namenode
[root@CentOSB ~]# hdfs namenode -bootstrapStandby （下载active的namenode元数据）
[root@CentOSB ~]# hadoop-daemon.sh start namenode
[root@CentOSA|B ~]# hdfs zkfc -formatZK （可以在CentOSA或者CentOSB任意一台注册namenode信息）
[root@CentOSA ~]# hadoop-daemon.sh start zkfc (哨兵)
[root@CentOSB ~]# hadoop-daemon.sh start zkfc (哨兵)
[root@CentOSX ~]# hadoop-daemon.sh start datanode

日常维护

[root@CentOSA|B|C ~]start|stop-dfs.sh

参考:http://hadoop.apache.org/docs/stable/hadoop-project-dist/hadoop-hdfs/HDFSHighAvailabilityWithQJM.html

                                     Resource Manager HA

etc/hadoop/yarn-site.xml


<property>
    <name>yarn.nodemanager.aux-services</name>
    <value>mapreduce_shuffle</value>
</property>
<!--Resource Manager-->
<property>
    <name>yarn.resourcemanager.ha.enabled</name>
    <value>true</value>
</property>
<property>
    <name>yarn.resourcemanager.zk-address</name>
    <value>CentOSA:2181,CentOSB:2181,CentOSC:2181</value>
</property>
<property>
    <name>yarn.resourcemanager.cluster-id</name>
    <value>rmcluster01</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>

 etc/hadoop/mapred-site.xml

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

 启动yarn

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

 参考:http://hadoop.apache.org/docs/stable/hadoop-yarn/hadoop-yarn-site/ResourceManagerHA.html

猜你喜欢

转载自blog.csdn.net/weixin_43989957/article/details/86184100
今日推荐
《美国对全球网络空间安全与发展的威胁和破坏》报告发布
火速冲上 GitHub 热榜 —— 开源编程语言、框架哪有这么可爱？
北京人形机器人创新中心发布全球首个纯电驱拟人奔跑的全尺寸人形机器人“天工”
LFOSSA 源来如此公开课 | 掌握云原生未来：CNCF 认证全面攻略与备考秘籍
周排行
循环神经网络（rnn）讲解
Tigao教程四：单独的关节运动
金蝶K3WISE15.0-注册套打教程
如何在Mac上配置Kubernetes
Android应用结束自身进程的方法
SpringMVC学习 十三 拦截器栈
中国驻洛杉矶总领馆举行新春招待会
HttpClient get post 发送
11 - three.js 笔记 - 绘制三维字体模型
Mysql递归获取某个父节点下面的所有子节点和子节点上的所有父节点
每日归档
更多
2024-05-01(4)
2024-04-30(1)
2024-04-29(40)
2024-04-28(0)
2024-04-27(56)
2024-04-26(39)
2024-04-25(22)
2024-04-24(36)
2024-04-23(26)
2024-04-22(39)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022