vim /etc/hostname  # 修改主機名稱
vim /etc/hosts # 修改主機host映射


# 關閉防火墻
systemctl stop firewalld
systemctl disable firewalld.service

安裝hadoop

上傳 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環(huán)境變量
#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

文件內容如下：

<?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數(shù)據(jù)的存儲目錄 -->
    <property>
        <name>hadoop.tmp.dir</name>
        <value>/opt/module/hadoop/data</value>
   </property>

    <!-- 配置HDFS網頁登錄使用的靜態(tài)用戶為qani -->
    <property>
        <name>hadoop.http.staticuser.user</name>
        <value>qani</value>
    </property>

    <!-- 配置該qani(superUser)允許通過代理訪問的主機節(jié)點 -->
    <property>
        <name>hadoop.proxyuser.qani.hosts</name>
        <value>*</value>
    </property>

   <!-- 配置該qani(superUser)允許通過代理用戶所屬組 -->
   <property>
        <name>hadoop.proxyuser.qani.groups</name>
        <value>*</value>
   </property>

   <!-- 配置該qani(superUser)允許通過代理的用戶-->
    <property>
        <name>hadoop.proxyuser.qani.users</name>
        <value>*</value>
    </property>
</configuration>

hdfs-site.xml配置

文件內容如下：

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

<configuration>
    <!-- nn web端訪問地址-->
    <property>
        <name>dfs.namenode.http-address</name>
        <value>hadoop102:9870</value>
    </property>
    
    <!-- 2nn web端訪問地址-->
    <property>
        <name>dfs.namenode.secondary.http-address</name>
        <value>hadoop104:9868</value>
    </property>
    
    <!-- 測試環(huán)境指定HDFS副本的數(shù)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>
    
    <!-- 環(huán)境變量的繼承 -->
    <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單個容器允許分配的最大最小內存 -->
    <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容器允許管理的物理內存大小 -->
    <property>
        <name>yarn.nodemanager.resource.memory-mb</name>
        <value>4096</value>
    </property>
    
    <!-- 關閉yarn對物理內存和虛擬內存的限制檢查 -->
    <property>
        <name>yarn.nodemanager.pmem-check-enabled</name>
        <value>true</value>
    </property>
    <property>
        <name>yarn.nodemanager.vmem-check-enabled</name>
        <value>false</value>
    </property>

    <!-- 開啟日志聚集功能 -->
    <property>
        <name>yarn.log-aggregation-enable</name>
        <value>true</value>
    </property>

    <!-- 設置日志聚集服務器地址 -->
    <property>  
        <name>yarn.log.server.url</name>  
        <value>http://hadoop102:19888/jobhistory/logs</value>
    </property>

    <!-- 設置日志保留時間為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程序運行在Yarn上 -->
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>

    <!-- 歷史服務器端地址 -->
    <property>
        <name>mapreduce.jobhistory.address</name>
        <value>hadoop102:10020</value>
    </property>

    <!-- 歷史服務器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

在該文件中增加如下內容：

hadoop102
hadoop103
hadoop104

啟動Hadoop

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

Web端查看HDFS的Web頁面：http://hadoop102:9870/
Web端查看SecondaryNameNode攒发，瀏覽器中輸入：http://hadoop104:9868/status.html

Hadoop啟動腳本

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

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

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

        echo " --------------- 關閉 historyserver ---------------"
        ssh hadoop102 "/opt/module/hadoop/bin/mapred --daemon stop historyserver"
        echo " --------------- 關閉 yarn ---------------"
        ssh hadoop103 "/opt/module/hadoop/sbin/stop-yarn.sh"
        echo " --------------- 關閉 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 

殺掉 Job：         
hadoop job –kill job_id

yarn application --list --all