vim /etc/hostname  # 修改主机名称
vim /etc/hosts # 修改主机host映射


# 关闭防火墙
systemctl stop firewalld
systemctl disable firewalld.service

安装hadoop

上传 hadoop-3.2.4.tar.gz 到/opt/software/
tar -zxvf hadoop-3.2.4.tar.gz -C /opt/module/
mv hadoop-3.2.4 hadoop

sudo vim /etc/profile.d/my_env.sh

添加hadoop环境变量
#HADOOP_HOME
export HADOOP_HOME=/opt/module/hadoop
export PATH=$PATH:$HADOOP_HOME/bin
export PATH=$PATH:$HADOOP_HOME/sbin

source /etc/profile.d/my_env.sh

核心配置文件

core-site.xml配置

cd $HADOOP_HOME/etc/hadoop
vim core-site.xml

文件内容如下：

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<configuration>
    <!-- 指定NameNode的地址 -->
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://hadoop102:8020</value>
    </property>

   <!-- 指定hadoop数据的存储目录 -->
    <property>
        <name>hadoop.tmp.dir</name>
        <value>/opt/module/hadoop/data</value>
   </property>

    <!-- 配置HDFS网页登录使用的静态用户为qani -->
    <property>
        <name>hadoop.http.staticuser.user</name>
        <value>qani</value>
    </property>

    <!-- 配置该qani(superUser)允许通过代理访问的主机节点 -->
    <property>
        <name>hadoop.proxyuser.qani.hosts</name>
        <value>*</value>
    </property>

   <!-- 配置该qani(superUser)允许通过代理用户所属组 -->
   <property>
        <name>hadoop.proxyuser.qani.groups</name>
        <value>*</value>
   </property>

   <!-- 配置该qani(superUser)允许通过代理的用户-->
    <property>
        <name>hadoop.proxyuser.qani.users</name>
        <value>*</value>
    </property>
</configuration>

hdfs-site.xml配置

文件内容如下：

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<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>
    
    <!-- 测试环境指定HDFS副本的数量1 -->
    <property>
        <name>dfs.replication</name>
        <value>1</value>
    </property>
</configuration>

yarn-site.xml配置

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<configuration>
    <!-- 指定MR走shuffle -->
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
    
    <!-- 指定ResourceManager的地址-->
    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>hadoop103</value>
    </property>
    
    <!-- 环境变量的继承 -->
    <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>
    
    <!--yarn单个容器允许分配的最大最小内存 -->
    <property>
        <name>yarn.scheduler.minimum-allocation-mb</name>
        <value>512</value>
    </property>
    <property>
        <name>yarn.scheduler.maximum-allocation-mb</name>
        <value>4096</value>
    </property>
    
    <!-- yarn容器允许管理的物理内存大小 -->
    <property>
        <name>yarn.nodemanager.resource.memory-mb</name>
        <value>4096</value>
    </property>
    
    <!-- 关闭yarn对物理内存和虚拟内存的限制检查 -->
    <property>
        <name>yarn.nodemanager.pmem-check-enabled</name>
        <value>true</value>
    </property>
    <property>
        <name>yarn.nodemanager.vmem-check-enabled</name>
        <value>false</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>
</configuration>

mapred-site.xml配置

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<configuration>
    <!-- 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>
</configuration>

配置workers

vim /opt/module/hadoop/etc/hadoop/workers

在该文件中增加如下内容：

hadoop102
hadoop103
hadoop104

启动Hadoop

sbin/start-dfs.sh
sbin/start-yarn.sh
bin/mapred --daemon start historyserver  # 启动 historyserver

Web端查看HDFS的Web页面：http://hadoop102:9870/
Web端查看SecondaryNameNode，浏览器中输入：http://hadoop104:9868/status.html

Hadoop启动脚本

#!/bin/bash
if [ $# -lt 1 ]
then
    echo "No Args Input..."
    exit ;
fi

case $1 in
"start")
        echo " =================== 启动 hadoop集群 ==================="

        echo " --------------- 启动 hdfs ---------------"
        ssh hadoop102 "/opt/module/hadoop/sbin/start-dfs.sh"
        echo " --------------- 启动 yarn ---------------"
        ssh hadoop103 "/opt/module/hadoop/sbin/start-yarn.sh"
        echo " --------------- 启动 historyserver ---------------"
        ssh hadoop102 "/opt/module/hadoop/bin/mapred --daemon start historyserver"
;;
"stop")
        echo " =================== 关闭 hadoop集群 ==================="

        echo " --------------- 关闭 historyserver ---------------"
        ssh hadoop102 "/opt/module/hadoop/bin/mapred --daemon stop historyserver"
        echo " --------------- 关闭 yarn ---------------"
        ssh hadoop103 "/opt/module/hadoop/sbin/stop-yarn.sh"
        echo " --------------- 关闭 hdfs ---------------"
        ssh hadoop102 "/opt/module/hadoop/sbin/stop-dfs.sh"
;;
*)
    echo "Input Args Error..."
;;
esac

hadoop常用命令

查看 Job 信息：  
hadoop job -list 

杀掉 Job：         
hadoop job –kill job_id

yarn application --list --all