三台虚拟机对Hadoop集群的搭建

1.修改主机名

# hostnamectl set-hostname master 
# hostnamectl set-hostname slave1
# hostnamectl set-hostname slave2

#reboot  重启

2.映射

# vi /etc/hosts   写入IP，主机名
  192.168.118.135  master
  192.168.118.128  slave1
  192.168.118.129  slave2
# cat /etc/hosts   检查

3. 免密（master和slave1、slave2都需要输入）

# ssh-keygen  产生公钥、密钥  -t rsa 指定rsa(常用),dsa;
# cd .ssh   
# ls  ls看有id_rsa.pub(公钥) id_rsa(密钥)
# cat id_rsa.pub >> authorized_keys  
# scp id_rsa.pub @slave1:~   /@master：~   /@slave2:~
# cat id_rsa.pub >> ~/.ssh/authorized_keys 把传过来的公钥复制到au….下
# cat authorized_keys  检查是否已成功传入各节点公钥
# ssh master   /slave1  验证

4、安装jdk

#tar -zxf jdk-8u191-linux-x64.tar -C /opt 解压指定路径下
#cd /opt  
#mv jdk-8u191-linux-x64.tar  jdk   改名
#vi /etc/profile   添加环境变量

添：

 export JAVA_HOME=/opt/jdk
  PATH=$JAVA_HOME/bin:$JAVA_HOME/lib:$PATH

可一起添加Hadoop环境变量
添：

export JAVA_HOME=/opt/hadoop2.7.1
PATH=$JAVA_HOME/bin:$JAVA_HOME/lib:$HADOOP_HOME/bin:$HADOOP_HOME/sbin:$PATH 

#  source /etc/profile   刷新

5.安装hadoop

#tar -txf hadoop-2.7.1.tar -C /opt   解压指定路径下/opt
#mv hadoop-2.7.1.tar  hadoop2.7.1   改名

#vi /etc/profile  添加环境变量
#source /etc/profile 或 . /etc/profire    刷新环境变量
#echo $PATH

#cd hadoop2.7.1  ls
#mkdir hdfs
#cd hdfs
#mkdir data   /name
#cd etc/hadoop

5.1添加配置文件

# vi Hadoop-env.sh
        改 export JAVA_HOME=/opt/jdk
# vi mapred-env.sh
        改 JAVA_HOME=/opt/jdk
# vi yarn-env.sh
       同上
# vi slaves
       添：master
           slave1   
           slave2 (删除其中)

以下四个文件均在configuration内添加

# vi core-site.xml
添：
<property>
<name>fs.defaultFS</name>
<value>hdfs://master:9000</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>/opt/hadoop/tmp</value>
</property>
<property>
<name>hadoop.proxyuser.hadoop.hosts</name>
<value>*</value>
</property>
<property>
<name>hadoop.proxyuser.hadoop.groups</name>
<value>*</value>
</property>

# vi hdfs-site.xml
添：
<property>
<name>dfs.namenode.http-address</name>
<value>master:50070</value>
</property>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>master:50090</value>
</property>
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>file:///opt/hadoop2.7.1/hdfs/name</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>file:///opt/hadoop2.7.1/hdfs/name</value>
</property>
<property>
<name>dfs.namenode.checkpoint.dir</name>
<value>file:///opt/hadoop2.7.1/hdfs/name</value>
</property>
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.stream-buffer-size</name>
<value>131072</value>
</property>

#mv mapred-site.xml.template mapred-site.xml  改名
#vi mapred-site.xml
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<property>
<name>mapreduce.jobhistory.address</name>
<value>master:10020</value>
</property>
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>master:19888</value>
</property>

 # vi yarn-site.xml
 <property>
<name>yarn.resourcemanager.address</name>
<value>master:18040</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address</name>
<value>master:18030</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address</name>
<value>master:18088</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address</name>
<value>master:18025</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address</name>
<value>master:18141</value>
</property>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.nodemanager.auxservice.mapreduce.shuffle.class</name>
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
</property>

在Hadoop2.7.1下创建tmp

 #mkdir tmp 

#scp -r /opt/* slave1:/opt/    
#scp -r /opt/* slave2:/opt/   远程分发
#systemctl stop firewalld  关闭防火墙
# hadoop namenode -format  格式化
# start-all.sh   启动Hadoop集群

#jps  查看进程（4个）子节点（3个）