环境准备

安装hadoop需要jdk的环境，因此先安装jdk，因为环境变量配置是遍历 /etc/profile.d/**.sh文件，因此在此路径下面创建my_env.sh文件，把我们的环境变量全部配置到这里，包括hadoop的环境变量。

关闭防火墙，防止不必要的异常发生

安装jdk，关闭防火墙

yum install -y epel-release

关闭防火墙，和防火墙启动自启
[root@hadoop100 ~]# systemctl stop firewalld
[root@hadoop100 ~]# systemctl disable firewalld.service
Removed symlink /etc/systemd/system/multi-user.target.wants/firewalld.service.
Removed symlink /etc/systemd/system/dbus-org.fedoraproject.FirewallD1.service.
[root@hadoop100 ~]# reboot
#查看本机自带的jdk
[root@hadoop102 software]#  rpm -qa |grep -i java
#删除本机自带的jdk
[root@hadoop102 software]#  rpm -qa |grep -i java | xargs -n1 rpm -e --nodeps

#下载jdk
[root@hadoop102 software]# 上传jdk
#配置环境变量
[root@hadoop102 module]# cd /etc/profile.d/
[root@hadoop102 profile.d]# vim my_env.sh
#JAVA_HOME
export JAVA_HOME=/opt/module/jdk1.8.0_251
export PATH=$PATH:$JAVA_HOME/bin

保存退出
[root@hadoop102 profile.d]# source /etc/profile
[root@hadoop102 profile.d]# java -version
java version "1.8.0_251"
Java(TM) SE Runtime Environment (build 1.8.0_251-b08)
Java HotSpot(TM) 64-Bit Server VM (build 25.251-b08, mixed mode)
安装成功

安装hadoop，配置hadoop环境变量

[root@hadoop102 software]# wget http://archive.apache.org/dist/hadoop/core/hadoop-3.1.3/hadoop-3.1.3.tar.gz
##解压
[root@hadoop102 software]# tar -zxvf hadoop-3.1.3.tar.gz -C /opt/module/
##配置环境变量
[root@hadoop102 software]# vim  /etc/profile.d/my_env.sh

#JAVA_HOME
export JAVA_HOME=/opt/module/jdk1.8.0_251
export PATH=$PATH:$JAVA_HOME/bin


export HADOOP_HOME=/opt/module/jdk1.8.0_251
export PATH=$PATH:$HADOOP_HOME/bin
export PATH=$PATH:$HADOOP_HOME/sbin

source /etc/profile

安装jdk，hadoop之后，copy到hadoop103和104

[root@hadoop102 module]# scp -r jdk1.8.0_251/ root@hadoop103:/opt/module/
[root@hadoop102 module]# scp -r jdk1.8.0_251/ root@hadoop104:/opt/module/

[root@hadoop102 module]# scp -r hadoop-3.1.3/ root@hadoop103:/opt/module/
[root@hadoop102 module]# scp -r hadoop-3.1.3/ root@hadoop104:/opt/module/

创建快速同步工具xsync

#创建xsync文件 
[root@hadoop102 ~]# cd /usr/bin
[root@hadoop102 bin]# vim xsync

#!/bin/bash

#1.判断参数个数
if [ $# -lt 1 ]
then
    echo Not Enough Arguement!
    exit;
fi

#2.遍历集群所有机器
for host in hadoop102 hadoop103 hadoop104
do
    echo ================== $host ===============
    #3.遍历所有目录 挨个发送
    for file in $@
    do
        #4.判断文件是否存在
        if [ -e $file ]
            then
                #5. 获取父目录
                pdir=$(cd -P $(dirname $file); pwd)
                #6. 获取当前文件名称
                fname=$(basename $file)
                ssh $host "mkdir -p $pdir"
                rsync -av $pdir/$fname $host:$pdir
            else
                echo $file does not exists!
        fi
     done
done

[root@hadoop102 bin]# chmod 777 xsync 
分发
[root@hadoop102 opt]# xsync /etc/profile.d/my_env.sh

ssh免密登录

[root@hadoop102 .ssh]# ssh-keygen -t rsa
[root@hadoop102 .ssh]# ssh-copy-id hadoop102
[root@hadoop102 .ssh]# ssh-copy-id hadoop103
[root@hadoop102 .ssh]# ssh-copy-id hadoop104

[root@hadoop103 .ssh]# ssh-keygen -t rsa
[root@hadoop103 .ssh]# ssh-copy-id hadoop102
[root@hadoop103 .ssh]# ssh-copy-id hadoop103
[root@hadoop103 .ssh]# ssh-copy-id hadoop104

[root@hadoop104 .ssh]# ssh-keygen -t rsa
[root@hadoop104 .ssh]# ssh-copy-id hadoop102
[root@hadoop104 .ssh]# ssh-copy-id hadoop103
[root@hadoop104 .ssh]# ssh-copy-id hadoop104

集群配置

配置集群需要修改几个文件

core-site.xml? 主要配置namenode的地址，以及数据存储目录
hdfs-site.xml? 配置namenode.http-address和secondary.http-address，这里配置的hadoop104,因此当启动集群的时候，hadoop102的jps有NameNode，
hadoop104的jps会有SecondaryNameNode
yarn-site.xml??配置yarn的namemanager，这里配置的是hadoop103，因此hadoop103还需要启动start-yarn.sh
mapred-site.xml

修改core-site.xml?

[root@hadoop102 hadoop]# cd /opt/module/hadoop-3.1.3/etc/hadoop
[root@hadoop102 hadoop]# vim core-site.xml

<configuration>
    <!-- 制定NameNode地址 -->
    <property>
        <name>fs.default.name</name>
        <value>hdfs://hadoop102:8020</value>
    </property>
    
    <!-- 制定hadoop数据的存储目录 -->
    <property>
        <name>hadoop.tmp.dir</name>
        <value>/opt/module/hadoop-3.1.3/data</value>
    </property>
</configuration>

修改?hdfs-site.xml

[root@hadoop102 hadoop]# vim hdfs-site.xml

<configuration>
    <!-- nn web 端访问地址 -->
    <property>
        <name>dfs.namenode.http-address</name>
        <value>hadoop102:9870</value>
    </property>
    <!-- 2nn web 端访问地址 -->
    <property>
        <name>dfs.namenode.secondary.http-address</name>
        <value>hadoop104:9868</value>
    </property>

</configuration>

修改yarn-site.xml

    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>hadoop103</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_MAPRED_HOME</value>
    </property>
    <!-- 开启日志聚集功能 -->
    <property>
        <name>yarn.log-aggregation-enable</name>
        <value>true</value>
    </property>
    <!-- 设置日志聚集服务器地址 -->
    <property>
        <name>yarn.log.server.url</name>
        <value>http://hadoop102:19888/jobhistory/logs</value>
    </property>
    <!-- 设置日志保留时间为7天 -->
    <property>
        <name>yarn.log-aggregation.retain-seconds</name>
        <value>604800</value>
    </property>

修改mapred-site.xml

    <!-- 指定MapReduce程序运行在Yarn上 -->
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
    <!-- 历史服务器端地址 -->
    <property>
        <name>mapreduce.jobhistory.address</name>
        <value>hadoop102:10020</value>
    </property>
    
    <!-- 历史服务器web端地址 -->
    <property>
        <name>mapreduce.jobhistory.webapp.address</name>
        <value>hadoop102:19888</value>
    </property>

分发

[root@hadoop102 etc]# xsync hadoop/

[root@hadoop102 etc]# vim hadoop/workers 
[root@hadoop102 etc]# cat hadoop/workers 
hadoop102
hadoop103
hadoop104
[root@hadoop102 etc]# xsync hadoop/

启动集群第一次需要初始化

[root@hadoop102 etc]# hdfs namenode -format

启动集群

[root@hadoop102 hadoop-3.1.3]# sbin/start-dfs.sh 
[root@hadoop102 hadoop-3.1.3]# jps
66997 Jps
66717 DataNode
66559 NameNode

如果启动的时候出现

[root@hadoop102 hadoop-3.1.3]# sbin/start-dfs.sh 
Starting namenodes on [hadoop102]
ERROR: Attempting to operate on hdfs namenode as root
ERROR: but there is no HDFS_NAMENODE_USER defined. Aborting operation.
Starting datanodes
ERROR: Attempting to operate on hdfs datanode as root
ERROR: but there is no HDFS_DATANODE_USER defined. Aborting operation.
Starting secondary namenodes [hadoop104]
ERROR: Attempting to operate on hdfs secondarynamenode as root
ERROR: but there is no HDFS_SECONDARYNAMENODE_USER defined. Aborting operation.

就在my_env.sh添加配置

[root@hadoop102 ~]# vim /etc/profile.d/my_env.sh 
export HDFS_NAMENODE_USER=root
export HDFS_DATANODE_USER=root
export HDFS_SECONDARYNAMENODE_USER=root
export YARN_RESOURCEMANAGER_USER=root
export YARN_NODEMANAGER_USER=root

##分发
[root@hadoop102 ~]# xsync /etc/profile.d/my_env.sh 
================== hadoop102 ===============
sending incremental file list

sent 48 bytes  received 12 bytes  120.00 bytes/sec
total size is 377  speedup is 6.28
================== hadoop103 ===============
sending incremental file list
my_env.sh

sent 472 bytes  received 41 bytes  1,026.00 bytes/sec
total size is 377  speedup is 0.73
================== hadoop104 ===============
sending incremental file list
my_env.sh

sent 472 bytes  received 41 bytes  1,026.00 bytes/sec
total size is 377  speedup is 0.73

##
[root@hadoop102 ~]# source /etc/profile
在hadoop103下
[root@hadoop103 ~]# source /etc/profile
在hadoop104下
[root@hadoop104 ~]# source /etc/profile

启动yarn

在hadoop103下启动

[root@hadoop103 sbin]# start-yarn.sh 
Starting resourcemanager
上一次登录：六 10月 15 14:03:52 CST 2022从 192.168.10.1pts/0 上
Starting nodemanagers
上一次登录：六 10月 15 14:11:47 CST 2022pts/0 上
[root@hadoop103 sbin]# jps
2784 Jps
2437 NodeManager
2061 DataNode
2285 ResourceManager
[root@hadoop103 sbin]#

看一下hadoop104下的

[root@hadoop104 ~]# jps
2177 SecondaryNameNode
2212 Jps
2063 DataNode
[root@hadoop104 ~]#

启动完成看是否一致jps

?jpsall

[root@hadoop102 bin]# vim jpsall 
#!/bin/bash

for host in hadoop102 hadoop103 hadoop104
do
    echo ================= $host =================
    ssh $host jps
done
[root@hadoop102 bin]# chmod 777 jpsall 
[root@hadoop102 bin]# jpsall
================= hadoop102 =================
8544 DataNode
9042 JobHistoryServer
8403 NameNode
8876 NodeManager
9324 Jps
================= hadoop103 =================
7330 DataNode
7526 ResourceManager
8186 Jps
7659 NodeManager
================= hadoop104 =================
5360 SecondaryNameNode
5762 Jps
5446 NodeManager
5240 DataNode

启动历史服务器

[root@hadoop102 hadoop-3.1.3]# cd /opt/module/hadoop-3.1.3/bin/
[root@hadoop102 bin]# mapred --daemon start historyserver
[root@hadoop102 bin]# jps
4130 NodeManager
4146 Jps
4024 JobHistoryServer 历史服务器
2573 DataNode
2398 NameNode
#停止
[root@hadoop102 bin]# mapred --daemon stop historyserver

[root@hadoop102 /]# jps
6576 Jps
4854 NodeManager
2573 DataNode
2398 NameNode
6046 JobHistoryServer
[root@hadoop102 /]# kill -9 4854
[root@hadoop102 /]# jps
6597 Jps
2573 DataNode
2398 NameNode
6046 JobHistoryServer
[root@hadoop102 /]# yarn --daemon start nodemanager
[root@hadoop102 /]# jps
6691 Jps
6662 NodeManager
2573 DataNode
2398 NameNode
6046 JobHistoryServer

集群搭建完毕

一键启动停止hadoop

[root@hadoop102 bin]# vim myhadoop.sh 
#!/bin/bash
case $1 in
"start" ){ 
    echo "================启动hadoop集群================"
    echo "================启动hadoop102 hdfs================"
	ssh hadoop102 "/opt/module/hadoop-3.1.3/sbin/start-dfs.sh"
    echo "================启动hadoop103 yarn================"
	ssh hadoop103 "/opt/module/hadoop-3.1.3/sbin/start-yarn.sh"
    echo "================启动hadoop102 historyserver================"
	ssh hadoop102 "/opt/module/hadoop-3.1.3/bin/mapred --daemon start historyserver"
};;
"stop"){
    echo "================关闭hadoop集群================"
    echo "================关闭hadoop102 historyserver================"
	ssh hadoop102 "/opt/module/hadoop-3.1.3/bin/mapred --daemon stop historyserver"
    echo "================关闭hadoop103 yarn================"
	ssh hadoop103 "/opt/module/hadoop-3.1.3/sbin/stop-yarn.sh"
    echo "================关闭hadoop102 hdfs================"
	ssh hadoop102 "/opt/module/hadoop-3.1.3/sbin/stop-dfs.sh"
};;
esac
[root@hadoop102 bin]# chmod 777 myhadoop.sh 
######################################################测试停止
[root@hadoop102 hadoop-3.1.3]# myhadoop.sh stop
================关闭hadoop集群================
================关闭hadoop102 historyserver================
================关闭hadoop103 yarn================
Stopping nodemanagers
上一次登录：六 10月 15 16:18:58 CST 2022
Stopping resourcemanager
上一次登录：六 10月 15 16:19:10 CST 2022
================关闭hadoop102 hdfs================
Stopping namenodes on [hadoop102]
上一次登录：六 10月 15 16:18:48 CST 2022
Stopping datanodes
上一次登录：六 10月 15 16:19:22 CST 2022
Stopping secondary namenodes [hadoop104]
上一次登录：六 10月 15 16:19:24 CST 2022


######################################################测试启动
[root@hadoop102 hadoop-3.1.3]# myhadoop.sh start
================启动hadoop集群================
================启动hadoop102 hdfs================
Starting namenodes on [hadoop102]
上一次登录：六 10月 15 16:19:28 CST 2022
Starting datanodes
上一次登录：六 10月 15 16:20:48 CST 2022
Starting secondary namenodes [hadoop104]
上一次登录：六 10月 15 16:20:52 CST 2022
================启动hadoop103 yarn================
Starting resourcemanager
上一次登录：六 10月 15 16:20:29 CST 2022从 192.168.10.1pts/1 上
Starting nodemanagers
上一次登录：六 10月 15 16:21:18 CST 2022
================启动hadoop102 historyserver================