1.安装centos

30G空间
/boot 300M
swap 2048
/ Fill

2.修改IP地址

vi /etc/sysconfig/network-scripts/ifcfg-eno16777736

DEVICE=eno16777736
TYPE=Ethernet
ONBOOT=yes
BOOTPROTO=static
IPADDR=192.168.121.150
GATEWAY=192.168.121.2
NETMASK=255.255.255.0
DNS1=8.8.8.8
DNS2=114.114.114.114

systemctl restart network
ping www.baidu.com
ping 本机ip

3.修改主机映射

hostnamectl set-hostname single

vi /etc/sysconfig/network
HOSTNAME=single
reboot

4.修改IP映射

vi /etc/hosts
#添加 ip 名字
192.168.121.150 single

5.查看防火墙和selinux,确认关闭

systemctl status firewalld
#输出如下
● firewalld.service - firewalld - dynamic firewall daemon
   Loaded: loaded (/usr/lib/systemd/system/firewalld.service; disabled; vendor preset: enabled)
   Active: inactive (dead)
   
sestatus
#输入如下
SELinux status:                 disabled

6.密钥

ssh-keygen -t rsa -P '' -f ~/.ssh/id_rsa
ssh-copy-id single

[root@single .ssh]# ssh-copy-id -i ~/.ssh/id_rsa.pub root@192.168.121.150
The authenticity of host '192.168.121.150 (192.168.121.150)' can't be established.
ECDSA key fingerprint is 7e:62:21:88:c3:41:ba:83:44:54:a9:63:6e:93:8f:67.
Are you sure you want to continue connecting (yes/no)? yes
/usr/bin/ssh-copy-id: INFO: attempting to log in with the new key(s), to filter out any that are already installed
/usr/bin/ssh-copy-id: INFO: 1 key(s) remain to be installed -- if you are prompted now it is to install the new keys
Permission denied (publickey,gssapi-keyex,gssapi-with-mic).


如果 是报的这个错:

Host key verification failed.
vi /etc/ssh/sshd_config
修改 PasswordAuthentication no
为 PasswordAuthentication yes
重启 sudo systemctl restart sshd
如果 是报的是 publickey,gssapi-keyex,gssapi-with-mic
passwd root 下
最近再给登陆的用户设置个密码,就解决了

7.上传文件到/export/software

tar -xzvf hadoop-2.7.4.tar.gz -C /export/servers
tar -xzvf jdk-8u301-linux-x64.tar.gz -C /export/servers
cd /export/servers
ln -s jdk1.8.0_301 jdk
ls -s hadoop-2.7.4 hadoop

8.配置环境变量

touch /etc/profile.d/hadoop_env.sh
vi /etc/profile.d/hadoop_env.sh

export JAVA_HOME=/export/servers/jdk
export HADOOP_HOME=/export/servers/hadoop
export PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin:$HADOOP_HOME/sbin

9.修改配置文件

9.1 hadoop-env.sh

vi /export/servers/hadoop/etc/hadoop/hadoop-env.sh

JAVA_HOME=/export/servers/jdk

9.2 修改core-site.xml

vi /export/servers/hadoop/etc/hadoop/core-site.xml
<!--指定HDFS中NameNode的地址-->
<property>
    <name>fs.defaultFS</name>
    <value>hdfs://single: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>/export/servers/hadoop/tmp</value>
</property>

9.3 修改hdfs-site.xml

vi /export/servers/hadoop/etc/hadoop/hdfs-site.xml
<!--指定HDFS中副本的数量-->
<property>
    <name>dfs.replication</name>
    <value>1</value>
</property>

9.4 修改mapred-site.xml

cp /export/servers/hadoop/etc/hadoop/mapred-site.xml.template /export/servers/hadoop/etc/hadoop/mapred-site.xml
vi /export/servers/hadoop/etc/hadoop/mapred-site.xml
<property>
    <name>mapreduce.framework.name</name>
    <value>yarn</value>
</property>

9.5 修改yarn-env.sh

yarn-env.sh用来保证YARN的守护进程ResourceManager和NodeManager，这个文件需要修改JAVA_HOME

 vi /export/servers/hadoop/etc/hadoop/yarn-env.sh
#修改内容如下
export JAVA_HOME=/export/servers/jdk

9.6 修改yarn-site.xml

 vi /export/servers/hadoop/etc/hadoop/yarn-site.xml
#配置内容如下
<configuration>
  <!-- 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>single</value>
  </property>
</configuration>

10.开启集群

hdfs namenode -format
start-all.sh
#也可以使用
hadoop-daemon.sh start namenode
hadoop-daemon.sh start datanode

测试启动的进程

[root@single sbin]# jps
15264 NodeManager
14853 DataNode
15013 SecondaryNameNode
15670 Jps
14729 NameNode
15163 ResourceManager

11.访问网址

访问
http://single:50070/