CentOS 7 安装Hadoop 2.7.1

共计 10686 个字符，预计需要花费 27 分钟才能阅读完成。

两台机器 CentOS7（机器名分别为 master-CentOS7、slave-CentOS7）内存 2G（笔记本开虚拟机快撑不住了╮(╯-╰)╭
CentOS7 与 CetnOS6 有一些区别

网络配置

master-CentOS7

[root@localhost ~]# vi /etc/sysconfig/network-scripts/ifcfg-eno16777736
TYPE=Ethernet
BOOTPROTO=static
DEFROUTE=yes
PEERDNS=yes
PEERROUTES=yes
IPV4_FAILURE_FATAL=no
IPV6INIT=yes
IPV6_AUTOCONF=yes
IPV6_DEFROUTE=yes
IPV6_PEERDNS=yes
IPV6_PEERROUTES=yes
IPV6_FAILURE_FATAL=no
NAME=eno16777736
UUID=b30f5765-ecd7-4dba-a0ed-ebac92c836bd
DEVICE=eno16777736
ONBOOT=yes
IPADDR=192.168.1.182
NETMASK=255.255.255.0
GATEWAY=192.168.1.1
DNS1=114.114.114.114
DNS2=8.8.4.4
网络信息根据自己实际的网络情况配置。[root@localhost ~]# systemctl restart network
[root@localhost ~]# ifconfig

slave-CentOS7

[root@localhost ~]# vi /etc/sysconfig/network-scripts/ifcfg-eno16777736
TYPE=Ethernet
BOOTPROTO=static
DEFROUTE=yes
PEERDNS=yes
PEERROUTES=yes
IPV4_FAILURE_FATAL=no
IPV6INIT=yes
IPV6_AUTOCONF=yes
IPV6_DEFROUTE=yes
IPV6_PEERDNS=yes
IPV6_PEERROUTES=yes
IPV6_FAILURE_FATAL=no
NAME=eno16777736
UUID=b30f5765-ecd7-4dba-a0ed-ebac92c836bd
DEVICE=eno16777736
ONBOOT=yes
IPADDR=192.168.1.183
NETMASK=255.255.255.0
GATEWAY=192.168.1.1
DNS1=114.114.114.114
DNS2=8.8.4.4
网络信息根据自己实际的网络情况配置。[root@localhost ~]# systemctl restart network
[root@localhost ~]# ifconfig

设置 hosts、hostname

master-CentOS7

[root@localhost ~]# vi /etc/hosts
添加
192.168.1.182 master
192.168.1.183 slave
[root@localhost ~]# vi /etc/hostname
localhost.localdomain
内容修改为
master

slave-CentOS7

[root@localhost ~]# vi /etc/hosts
添加
192.168.1.182 master
192.168.1.183 slave
[root@localhost ~]# vi /etc/hostname
localhost.localdomain
内容修改为
slave

关闭 selinux

master-CentOS7

[root@master ~]# getenforce
Enforcing
[root@master ~]# vi /etc/selinux/config
SELINUX=enforcing
修改为
SELINUX=disabled
保存重启
[root@master ~]# getenforce
Disabled

slave-CentOS7

[root@slave ~]# getenforce
Enforcing
[root@slave ~]# vi /etc/selinux/config
SELINUX=enforcing
修改为
SELINUX=disabled
保存重启
[root@slave ~]# getenforce
Disabled

关闭 firewalld

master-CentOS7

[root@master ~]# systemctl disable firewalld
Removed symlink /etc/systemd/system/dbus-org.Fedoraproject.FirewallD1.service.
Removed symlink /etc/systemd/system/basic.target.wants/firewalld.service.
[root@master ~]# systemctl stop firewalld
[root@master ~]# iptables -nvL
Chain INPUT (policy ACCEPT 0 packets, 0 bytes)
 pkts bytes target     prot opt in     out     source               destination

Chain FORWARD (policy ACCEPT 0 packets, 0 bytes)
 pkts bytes target     prot opt in     out     source               destination

Chain OUTPUT (policy ACCEPT 0 packets, 0 bytes)
 pkts bytes target     prot opt in     out     source               destination
[root@master ~]# yum install -y iptables-services
[root@master ~]# service iptables save
iptables: Saving firewall rules to /etc/sysconfig/iptables:[确定]
[root@master ~]# systemctl enable iptables
Created symlink from /etc/systemd/system/basic.target.wants/iptables.service to /usr/lib/systemd/system/iptables.service.

slave-CentOS7

[root@slave ~]# systemctl disable firewalld
Removed symlink /etc/systemd/system/dbus-org.fedoraproject.FirewallD1.service.
Removed symlink /etc/systemd/system/basic.target.wants/firewalld.service.
[root@slave ~]# systemctl stop firewalld
[root@slave ~]# iptables -nvL
Chain INPUT (policy ACCEPT 0 packets, 0 bytes)
 pkts bytes target     prot opt in     out     source               destination        

Chain FORWARD (policy ACCEPT 0 packets, 0 bytes)
 pkts bytes target     prot opt in     out     source               destination        

Chain OUTPUT (policy ACCEPT 0 packets, 0 bytes)
 pkts bytes target     prot opt in     out     source               destination        
[root@slave ~]# yum install -y iptables-services
[root@slave ~]# service iptables save
iptables: Saving firewall rules to /etc/sysconfig/iptables:[确定]
[root@slave ~]# systemctl enable iptables
Created symlink from /etc/systemd/system/basic.target.wants/iptables.service to /usr/lib/systemd/system/iptables.service.

密钥登陆

master-CentOS7

[root@master ~]# ssh-keygen
一直回车
[root@master ~]# cat .ssh/id_rsa.pub
复制~/.ssh/id_rsa.pub 内容

slave-CentOS7

[root@slave ~]# vi .ssh/authorized_keys
复制~/.ssh/id_rsa.pub 内容到 ~/.ssh/authorized_keys 时报错
".ssh/authorized_keys" E212: Can't open file for writing
解决方案
[root@slave ~]# ls -ld .ssh
ls: 无法访问.ssh: 没有那个文件或目录
[root@slave ~]# mkdir .ssh; chmod 700 .ssh
[root@slave ~]# ls -ld .ssh
drwx------ 2 root root 6 8 月  28 15:59 .ssh
[root@slave ~]# vi .ssh/authorized_keys
复制~/.ssh/id_rsa.pub 内容到 ~/.ssh/authorized_keys
[root@slave ~]# ls -l !$
ls -l .ssh/authorized_keys
-rw-r--r-- 1 root root 418 8 月  28 16:02 .ssh/authorized_keys

master-CentOS7

[root@master ~]# vi .ssh/authorized_keys
复制~/.ssh/id_rsa.pub 内容到 ~/.ssh/authorized_keys

测试

master-CentOS7

[root@master ~]# ssh master
[root@master ~]# exit
[root@master ~]# ssh slave
[root@slave ~]# exit

安装 JDK

Hadoop2.7 需要安装 jdk1.7 版本，下载地址 http://www.oracle.com/technetwork/java/javase/downloads/jdk7-downloads-1880260.html

先卸载 CetnOS7 自带的 JDK
以 slave-CentOS7 为例（master-CetnOS7、slave-CentOS7 上都需要卸载 CetnOS7 自带的 JDK）

[root@slave ~]# java -version
openjdk version "1.8.0_101"
OpenJDK Runtime Environment (build 1.8.0_101-b13)
OpenJDK 64-Bit Server VM (build 25.101-b13, mixed mode)
[root@master ~]# rpm -qa |grep jdk
java-1.7.0-openjdk-headless-1.7.0.111-2.6.7.2.el7_2.x86_64
java-1.8.0-openjdk-1.8.0.101-3.b13.el7_2.x86_64
java-1.8.0-openjdk-headless-1.8.0.101-3.b13.el7_2.x86_64
java-1.7.0-openjdk-1.7.0.111-2.6.7.2.el7_2.x86_64
[root@slave ~]# yum -y remove java-1.7.0-openjdk-headless-1.7.0.111-2.6.7.2.el7_2.x86_64
[root@slave ~]# yum -y remove java-1.8.0-openjdk-1.8.0.101-3.b13.el7_2.x86_64
[root@slave ~]# yum -y remove java-1.8.0-openjdk-headless-1.8.0.101-3.b13.el7_2.x86_64
[root@slave ~]# java -version
-bash: /usr/bin/java: 没有那个文件或目录

master-CentOS7

[root@master ~]# wget 'http://download.Oracle.com/otn-pub/java/jdk/7u79-b15/jdk-7u79-linux-x64.tar.gz?AuthParam=1472372876_f3205a608139acb432d3c48638502428' 
[root@master ~]# mv jdk-7u79-linux-x64.tar.gz\?AuthParam\=1472372876_f3205a608139acb432d3c48638502428  jdk-7u79-linux-x64.tar.gz
[root@master ~]# tar zxvf jdk-7u79-linux-x64.tar.gz
[root@master ~]# mv jdk1.7.0_79 /usr/local/
[root@master ~]# vi /etc/profile.d/java.sh
添加
export JAVA_HOME=/usr/local/jdk1.7.0_79
export CLASSPATH=.:$JAVA_HOME/jre/lib/rt.jar:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar
export PATH=$PATH:$JAVA_HOME/bin
[root@master ~]# source !$
source /etc/profile.d/java.sh
[root@master ~]# java -version
java version "1.7.0_79"
Java(TM) SE Runtime Environment (build 1.7.0_79-b15)
Java HotSpot(TM) 64-Bit Server VM (build 24.79-b02, mixed mode)
[root@master ~]# scp jdk-7u79-linux-x64.tar.gz slave:/root/
[root@master ~]# scp /etc/profile.d/java.sh slave:/etc/profile.d/

slave-CentOS7

[root@slave ~]# tar zxvf jdk-7u79-linux-x64.tar.gz
[root@slave ~]# mv jdk1.7.0_79 /usr/local/
[root@slave ~]# source /etc/profile.d/java.sh
[root@slave ~]# java -version
java version "1.7.0_79"
Java(TM) SE Runtime Environment (build 1.7.0_79-b15)
Java HotSpot(TM) 64-Bit Server VM (build 24.79-b02, mixed mode)

安装 Hadoop

master-CentOS7

[root@master ~]# wget 'http://mirror.bit.edu.cn/apache/hadoop/common/hadoop-2.7.1/hadoop-2.7.1.tar.gz'
[root@master ~]# tar zxvf hadoop-2.7.1.tar.gz
[root@master ~]# mv hadoop-2.7.1 /usr/local/Hadoop
[root@master ~]# ls !$
ls /usr/local/hadoop
bin  include  libexec      NOTICE.txt  sbin
etc  lib      LICENSE.txt  README.txt  share
[root@master ~]# mkdir /usr/local/hadoop/tmp  /usr/local/hadoop/dfs  /usr/local/hadoop/dfs/data  /usr/local/hadoop/dfs/name
[root@master ~]# ls /usr/local/hadoop
bin  dfs  etc  include  lib  libexec  LICENSE.txt  NOTICE.txt  README.txt  sbin  share  tmp
[root@master ~]# rsync -av /usr/local/hadoop  slave:/usr/local

slave-CentOS7

[root@slave ~]# ls /usr/local/hadoop
bin  etc      lib      LICENSE.txt  README.txt  share
dfs  include  libexec  NOTICE.txt   sbin        tmp

配置 Hadoop

master-CentOS7

[root@master ~]# vi /usr/local/hadoop/etc/hadoop/core-site.xml
添加
<configuration>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://192.168.1.182:9000</value>
    </property>
    <property>
        <name>hadoop.tmp.dir</name>
        <value>file:/usr/local/hadoop/tmp</value>
    </property>
    <property>
        <name>io.file.buffer.size</name>
        <value>131702</value>
    </property>
</configuration>
注意 master-CentOS7 主机的 IP
[root@master ~]# vi /usr/local/hadoop/etc/hadoop/hdfs-site.xml
添加
<configuration>
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>file:/usr/local/hadoop/dfs/name</value>
    </property>
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>file:/usr/local/hadoop/dfs/data</value>
    </property>
    <property>
        <name>dfs.replication</name>
        <value>2</value>
    </property>
    <property>
        <name>dfs.namenode.secondary.http-address</name>
        <value>192.168.1.182:9001</value>
    </property>
    <property>
    <name>dfs.webhdfs.enabled</name>
    <value>true</value>
    </property>
</configuration>
注意 master-CentOS7 主机的 IP
[root@master ~]# mv /usr/local/hadoop/etc/hadoop/mapred-site.xml.template  /usr/local/hadoop/etc/hadoop/mapred-site.xml
[root@master ~]# vi /usr/local/hadoop/etc/hadoop/mapred-site.xml
添加
<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
    <property>
        <name>mapreduce.jobhistory.address</name>
        <value>192.168.1.182:10020</value>
    </property>
    <property>
        <name>mapreduce.jobhistory.webapp.address</name>
        <value>192.168.1.182:19888</value>
    </property>
</configuration>
注意 master-CentOS7 主机的 IP
[root@master ~]# vi /usr/local/hadoop/etc/hadoop/yarn-site.xml
添加
<configuration>

<!-- Site specific YARN configuration properties -->
    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>
    <property>
        <name>yarn.nodemanager.auxservices.mapreduce.shuffle.class</name>
        <value>org.apache.hadoop.mapred.ShuffleHandler</value>
    </property>
    <property>
        <name>yarn.resourcemanager.address</name>
        <value>192.168.1.182:8032</value>
    </property>
    <property>
        <name>yarn.resourcemanager.scheduler.address</name>
        <value>192.168.1.182:8030</value>
    </property>
    <property>
        <name>yarn.resourcemanager.resource-tracker.address</name>
        <value>192.168.1.182:8031</value>
    </property>
    <property>
        <name>yarn.resourcemanager.admin.address</name>
        <value>192.168.1.182:8033</value>
    </property>
    <property>
        <name>yarn.resourcemanager.webapp.address</name>
        <value>192.168.1.182:8088</value>
    </property>
    <property>
        <name>yarn.nodemanager.resource.memory-mb</name>
        <value>2048</value>
    </property>

</configuration>
注意 master-CentOS7 主机的 IP
[root@master ~]# cd /usr/local/hadoop/etc/hadoop
[root@master hadoop]# vi hadoop-env.sh
更改
export JAVA_HOME=/usr/local/jdk1.7.0_79
[root@master hadoop]# vi yarn-env.sh
更改
export JAVA_HOME=/usr/local/jdk1.7.0_79
[root@master hadoop]# vi slaves
更改为
192.168.1.183
注意 slave-CentOS7 的 IP
[root@master hadoop]# rsync -av /usr/local/hadoop/etc/ slave:/usr/local/hadoop/etc/

slave-CentOS7

[root@slave ~]# cd /usr/local/hadoop/etc/hadoop/
[root@slave hadoop]# cat slaves
192.168.1.183
检查 slave 没问题

启动 Hadoop

master-CentOS7

[root@master hadoop]# /usr/local/hadoop/bin/hdfs namenode -format
[root@master hadoop]# echo $?
0
[root@master hadoop]# /usr/local/hadoop/sbin/start-all.sh
[root@master hadoop]# jps
19907 ResourceManager
19604 SecondaryNameNode
19268 NameNode
20323 Jps

slave-CentOS7

[root@slave hadoop]# jps
18113 NodeManager
18509 Jps
17849 DataNode

浏览器打开
http://192.168.1.182:8088/
http://192.168.1.182:50070/

测试 Hadoop

master-CentOS7

[root@master hadoop]# cd /usr/local/hadoop/
[root@master hadoop]# bin/hadoop jar ./share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.1.jar pi 10 10

停止服务

master-CentOS7

[root@master hadoop]# cd /usr/local/hadoop
[root@master hadoop]# sbin/stop-all.sh

---

• 如果提示 copyFromLocal: Cannot create directory /123/. Name node is in safe mode.
  这是因为开启了安全模式
  解决方法：
  cd /usr/local/Hadoop
  bin/hdfs dfsadmin -safemode leave

更多 Hadoop 相关信息见 Hadoop 专题页面 http://www.linuxidc.com/topicnews.aspx?tid=13

本文永久更新链接地址 ：http://www.linuxidc.com/Linux/2016-09/135522.htm