Hadoop创建（命令）

配置centos7网络

vi /etc/sysconfig/network-scripts/ifcfg-ens33

//修改
BOOTPROTO=static
ONBOOT=yes
//插入
IPADDR=192.168.43.128
NETMASK=255.255.255.0
GATEWAY=192.168.43.2
DNS1=192.168.43.2

vi /etc/hosts

//插入
192.168.43.128 master1
192.168.43.129 slave1
192.168.43.130 slave2

vi /etc/resolv.conf

//插入
nameserver 192.168.43.2

注：如果存在就不需要加了，启动后ping不通的话可以优先检查一下这个文件

hostnamectl set-hostname master1

reboot

关闭防火墙

systemctl status firewalld.service
systemctl stop firewalld.service
systemctl status firewalld.service

安装jdk1.8.0_141

保存路径：/usr/mysoft/jdk1.8.0_141

cd /usr
mkdir mysoft

上传jdk1.8.0_141到mysoft

解压

cd /usr/mysoft/
tar -zxvf jdk(按Tab键补全)

配置jdk环境

vi /etc/profile

export JAVA_HOME=/usr/mysoft/jdk1.8.0_141
export PATH=$PATH:$JAVA_HOME/bin

source /etc/profile

java -version

安装hadoop-2.7.4

保存路径：/usr/mysoft/hadoop-2.7.4

cd /usr/mysoft
tar -zxvf hadoop(按Tab键补全)
cd hadoop-2.7.4/etc/hadoop

vi hadoop-env.sh

//修改
export JAVA_HOME=/usr/mysoft/jdk1.8.0_141

vi core-site.xml

//插入
<configuration>
       <!-- 指定HDFS中NameNode的地址 -->
       <!-- 9000是内部通信一个地址,也就是NameNode和DataNode通信的地址 -->
        <property>
                <name>fs.defaultFS</name>
        		<value>hdfs://192.168.43.128:9000</value> 
        </property>
        <!-- 指定hadoop运行时产生文件的存储目录 -->
        <property>
                <name>hadoop.tmp.dir</name>
                <value>/usr/mysoft/hadoop-2.7.4/tmp</value>
        </property>
</configuration>

vi hdfs-site.xml

<configuration>
        <property>
              <name>dfs.replication</name>
              <value>2</value>
        </property>
        <property>
                <name>dfs.namenode.name.dir</name>
                <value>file:/usr/mysoft/hadoop-2.7.4/dfs/name</value>
        </property>
        <property>
                <name>dfs.namenode.data.dir</name>
                <value>file:/usr/mysoft/hadoop-2.7.4/dfs/data</value>
        </property>
        <property>
           <name>dfs.namenode.http-address</name>
           <value>192.168.43.128:50090</value>
        </property>
		<property> 
		     <name>dfs.permissions</name> 
		     <value>false</value> 
		</property>
</configuration>

修改mapred-site.xml

cp mapred-site.xml.template mapred-site.xml
vi mapred-site.xml

<configuration>
    <!-- 指定mr运行在yarn上 -->
    <property>
       <name>mapreduce.framework.name</name>
       <value>yarn</value>
    </property>
</configuration>

vi yarn-site.xml

<configuration>
     <!-- Site specific YARN configuration properties -->
     <!-- reducer获取数据的方式 -->
     <property>
           <name>yarn.nodemanager.aux-services</name>
           <value>mapreduce_shuffle</value>
     </property>
     <!-- 指定YARN的ResourceManager的地址 -->
     <property>
          <name>yarn.resourcemanager.hostname</name>
         <value>master1</value>
    </property>
</configuration>

配置环境变量vi /etc/profile

export JAVA_HOME=/usr/mysoft/jdk1.8.0_141
export HADOOP_HOME=/usr/mysoft/hadoop-2.7.4
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin
export PATH=$PATH:$HADOOP_HOME/sbin
export HADOOP_MAPRED_HOME=$HADOOP_HOME
export HADOOP_COMMON_HOME=$HADOOP_HOME
export HADOOP_HDFS_HOME=$HADOOP_HOME
export YARN_HOME=$HADOOP_HOME
export HADOOP_COMMON_LIB_NATIVE_DIR=$HADOOP_HOME/lib/native
export HADOOP_OPTS="-Djava.library.path=$HADOOP_INSTALL/lib"

source /etc/profile

配置slaves

//删除
localhost
//插入
master1
slave1
slave2

复制虚拟机

改ip、主机名、重启、互ping

安装密匙

1. 方法一：

master1，slave1，slave2生成密匙

~目录：

ssh-keygen -t rsa
//一直回车

ssh-copy-id master1
ssh-copy-id slave1
ssh-copy-id slave2

检验

ssh master1		//不需要密码就转换了
exit		
ssh slave1
exit
ssh slave2
exit

初始化

cd /usr/mysoft/hadoop-2.7.4/bin
hdfs namenode -format

出现successful字眼就成功

此时还不会出现tmp文件

启动HDFS(master1上)

cd /usr/mysoft/hadoop-2.7.4
sbin/start-all.sh
jps

启动HDFS(slave1、slave2上)

cd /usr/mysoft/hadoop-2.7.4
sbin/start-all.sh
jps

可以看到，在master1上成功启动了NameNode节点和ResourceManager；在slave1、slave2上成功启动了NodeManager节点和DataNode节点

验证集群是否启动成功

查看HDFS文件

hadoop fs -ls /

没有报错说明启动成功（警告可以忽略）

关闭集群

sbin/stop-all.sh