Centos7上Hadoop 3.3.1的分布式集群安装过程

同样适用于Hadoop 3.0.0

1. 集群规划

  • 每台服务器相互设置ssh无密码登录,注意authorized_keys权限为600。可以用ssh-copy-id hostname将本机的id_rsa.pub内容复制到远程服务器的.ssh/authorized_key中
服务名安装服务器
java8bigdata001/2/3
NameNodebigdata001
DataNodebigdata002/3
ResourceManagerbigdata001
NodeManagerbigdata002/3

2. 下载(在bigdata001操作)

执行下面的命令进行下载和解压

curl -O https://ftp.nluug.nl/internet/apache/hadoop/common/hadoop-3.3.1/hadoop-3.3.1.tar.gz

tar -zxvf hadoop-3.3.1.tar.gz

进入hadoop目录

[root@bigdata001 opt]# 
[root@bigdata001 opt]# cd hadoop-3.3.1
[root@bigdata001 hadoop-3.3.1]# 
[root@bigdata001 hadoop-3.3.1]# pwd
/opt/hadoop-3.3.1
[root@bigdata001 hadoop-3.3.1]# 

3. 配置文件修改(在bigdata001操作)

3.1 hadoop-env.sh

创建pids和logs文件

[root@bigdata001 hadoop-3.3.1]# 
[root@bigdata001 hadoop-3.3.1]# mkdir pids				
[root@bigdata001 hadoop-3.3.1]# 
[root@bigdata001 hadoop-3.3.1]# mkdir logs				
[root@bigdata001 hadoop-3.3.1]# 
[root@bigdata001 hadoop-3.3.1]# ls
bin  etc  include  lib  libexec  LICENSE-binary  licenses-binary  LICENSE.txt  logs  NOTICE-binary  NOTICE.txt  pids  README.txt  sbin  share
[root@bigdata001 hadoop-3.3.1]#
[root@bigdata001 hadoop-3.3.1]# pwd
/opt/hadoop-3.3.1
[root@bigdata001 hadoop-3.3.1]#

修改etc/hadoop/hadoop-env.sh文件

修改部分:

export JAVA_HOME=/opt/jdk1.8.0_201       
export HADOOP_PID_DIR=/opt/hadoop-3.3.1/pids				
export HADOOP_LOG_DIR=/opt/hadoop-3.3.1/logs				

export HDFS_NAMENODE_USER=root

添加部分

export HDFS_DATANODE_USER=root
export HDFS_SECONDARYNAMENODE_USER=root
export YARN_RESOURCEMANAGER_USER=root
export YARN_NODEMANAGER_USER=root

3.2 core-site.xml

修改etc/hadoop/core-site.xml

添加部分:

    <property>
        <name>fs.defaultFS</name>		
        <value>hdfs://bigdata001:9000</value>
    </property>
    
    <property>
        <name>io.file.buffer.size</name>				
        <value>131072</value>
    </property>

    <property>
        <name>hadoop.proxyuser.root.hosts</name>
        <value>*</value>
        <description>Hadoop的超级用户root能代理的节点</description>
    </property>

    <property>
        <name>hadoop.proxyuser.root.groups</name>
        <value>*</value>
        <description>Hadoop的超级用户root能代理的用户组</description>
    </property>


3.3 hdfs-site.xml

修改etc/hadoop/hdfs-site.xml

添加namenode和datanode文件夹

[root@bigdata001 hadoop-3.3.1]# 
[root@bigdata001 hadoop-3.3.1]# mkdir namenode
[root@bigdata001 hadoop-3.3.1]# 
[root@bigdata001 hadoop-3.3.1]# mkdir datanode
[root@bigdata001 hadoop-3.3.1]# 
[root@bigdata001 hadoop-3.3.1]# pwd
/opt/hadoop-3.3.1
[root@bigdata001 hadoop-3.3.1]# 

添加部分:

    <property>
        <name>dfs.replication</name>			
        <value>1</value>
    </property>

    <property>
        <name>dfs.namenode.name.dir</name>				
        <value>/opt/hadoop-3.3.1/namenode</value>
    </property>
	
    <property>
        <name>dfs.blocksize</name>					
        <value>268435456</value>
    </property>

    <property>
        <name>dfs.namenode.handler.count</name>			
        <value>100</value>
    </property>
    
    <property>
        <name>dfs.datanode.data.dir</name>					
        <value>/opt/hadoop-3.3.1/datanode</value>
    </property>


3.4 mapred-site.xml

修改etc/hadoop/mapred-site.xml

添加部分:

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

3.5 yarn-site.xml

修改etc/hadoop/yarn-site.xml

[root@bigdata001 hadoop-3.3.1]# 
[root@bigdata001 hadoop-3.3.1]# pwd
/opt/hadoop-3.3.1
[root@bigdata001 hadoop-3.3.1]# 
[root@bigdata001 hadoop-3.3.1]# mkdir nm-local-dir
[root@bigdata001 hadoop-3.3.1]# mkdir nm-log-dir
[root@bigdata001 hadoop-3.3.1]# mkdir nm-remote-app-log-dir
[root@bigdata001 hadoop-3.3.1]# 

添加部分:


    <property>
        <name>yarn.acl.enable</name>				
        <value>false</value>
    </property>

    <property>
        <name>yarn.log-aggregation-enable</name>			
        <value>false</value>
    </property>

    <property>
        <name>yarn.resourcemanager.address</name>					
        <value>${yarn.resourcemanager.hostname}:8032</value>
    </property>
	
	
    <property>
        <name>yarn.resourcemanager.scheduler.address</name>			
        <value>${yarn.resourcemanager.hostname}:8030</value>
    </property>
	
    <property>
        <name>yarn.resourcemanager.resource-tracker.address</name>			
        <value>${yarn.resourcemanager.hostname}:8031</value>
    </property>
	
    <property>
        <name>yarn.resourcemanager.admin.address</name>			
        <value>${yarn.resourcemanager.hostname}:8033</value>
    </property>

    <property>
        <name>yarn.resourcemanager.webapp.address</name>		
        <value>${yarn.resourcemanager.hostname}:8088</value>
    </property>
	
    <property>
        <name>yarn.resourcemanager.hostname</name>   			
        <value>bigdata001</value>
    </property>
	
    <property>
        <name>yarn.resourcemanager.scheduler.class</name>			
        <value>org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler</value>
    </property>
	
    <property>
        <name>yarn.scheduler.minimum-allocation-mb</name>			
        <value>1024</value>
    </property>
	
    <property>
        <name>yarn.scheduler.maximum-allocation-mb</name>			
        <value>8192</value>
    </property>
	
    <property>
        <name>yarn.resourcemanager.nodes.include-path</name>			
        <value></value>
    </property>
	
    <property>
        <name>yarn.nodemanager.resource.memory-mb</name>			
        <value>8192</value>
    </property>

    <property>
        <name>yarn.nodemanager.vmem-pmem-ratio</name>				
        <value>2.1</value>
    </property>
	
    <property>
        <name>yarn.nodemanager.local-dirs</name>				
        <value>/opt/hadoop-3.3.1/nm-local-dir</value>
    </property>
	
    <property>
        <name>yarn.nodemanager.log-dirs</name>				
        <value>/opt/hadoop-3.3.1/nm-log-dir</value>
    </property>
	
    <property>
        <name>yarn.nodemanager.log.retain-seconds</name>				
        <value>10800</value>
    </property>
	
    <property>
        <name>yarn.nodemanager.remote-app-log-dir</name>			
        <value>/opt/hadoop-3.3.1/nm-remote-app-log-dir</value>
    </property>
	
    <property>
        <name>yarn.nodemanager.remote-app-log-dir-suffix</name>			
        <value>logs</value>
    </property>

    <property>
        <name>yarn.nodemanager.aux-services</name>			
        <value>mapreduce_shuffle</value>
    </property>

    <property>
        <name>yarn.nodemanager.env-whitelist</name>				
        <value>JAVA_HOME,HADOOP_COMMON_HOME,HADOOP_HDFS_HOME,HADOOP_CONF_DIR,CLASSPATH_PREPEND_DISTCACHE,HADOOP_YARN_HOME,HADOOP_HOME,PATH,LANG,TZ,HADOOP_MAPRED_HOME</value>
    </property>

3.6 修改workers文件

bigdata002			
bigdata003			

4. hadoop目录分发(在bigdata001操作)

将bigdata001上配置的hadoop目录分发到其余两台服务器

[root@bigdata001 opt]# scp -r /opt/hadoop-3.3.1 root@bigdata002:/opt
[root@bigdata001 opt]# scp -r /opt/hadoop-3.3.1 root@bigdata003:/opt

5. 初始化和启动(在bigdata001操作)

5.1 添加环境变量

  1. /etc/profile添加内容如下:
export HADOOP_HOME=/opt/hadoop-3.3.1

export PATH=$PATH:$HADOOP_HOME/bin:$HADOOP_HOME/sbin
  1. 使环境变量生效
[root@bigdata001 ~]# 
[root@bigdata001 ~]# source /etc/profile
[root@bigdata001 ~]#

5.2 HDFS

hdfs初始化

[root@bigdata001 opt]#
[root@bigdata001 opt]# hdfs namenode -format		
[root@bigdata001 opt]#

启动hdfs

[root@bigdata001 opt]#
[root@bigdata001 opt]# start-dfs.sh										
[root@bigdata001 opt]#
  1. 访问http://bigdata001:9870
    HDFS页面

5.3 YARN

启动yarn

[root@bigdata001 opt]# 
[root@bigdata001 opt]# start-yarn.sh													
[root@bigdata001 opt]#

访问http://bigdata001:8088

Yarn页面

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值