3.1-3.5 分布式部署hadoop2.x的准备和配置

一、环境

192.168.1.130     master

192.168.1.131     slave1

192.168.1.132     slave2

所有主机：

1、关闭防火墙、selinux

2、配置hosts文件

3、yum -y install vim wget tree ntpdate lrzsz openssh-clients

4、配置文件描述符等，同步时间；

5、mkdir -p /opt/app             #hadoop安装目录

6、mkdir -p /opt/{datas,modules,softwares,tools}       #存放其他程序或文件的目录

二、节点配置规划

服务：

服务	master	slave1	slave2
HDFS	namenode		secondarynamenode
HDFS	datanode	datanode	datanode
yarn		resourcemanager
yarn	nodemanager	nodemanager	nodemanager
mapreduce	jobhistoryserver

配置文件：

HDFS：
    hadoop-env.sh     -->JDK
     core-site.xml    -->namenode
    hdfs-site.xml    -->secondarynamenode
    slaves        -->datanode

YARN：
    yarn-env.sh    -->JDK
    yarn-site.xml    -->resourcemanager
    slaves        -->nodemanager

MapReduce:
    mapred-env.sh    -->JDK
    mapred-site.xml    -->Jobhistoryserver

三、安装

1、安装JDK(所有节点)

#先卸载系统自带的JDK

[root@master softwares]# pwd    #softwares目录存放安装包
/opt/softwares

[root@master softwares]# ls
hadoop-2.5.0.tar.gz  jdk-7u80-linux-x64.tar.gz

[root@master softwares]# tar zxf jdk-7u80-linux-x64.tar.gz -C /opt/moduls/

#配置环境变量
vim /etc/profile
#JDK
export JAVA_HOME=/opt/modules/jdk1.7.0_80
export PATH=$PATH:$JAVA_HOME/bin

#source
source /etc/profile

java -version

2、安装hadoop

(1)hdfs

#解压
[root@master softwares]# tar zxf hadoop-2.5.0.tar.gz -C /opt/app/  #现在只解压到master，后面会分发

#hadoop-env.sh 
export JAVA_HOME=/opt/modules/jdk1.7.0_80

#core-site.xml
<configuration>

    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://master:8020</value>
    </property>

    <property>
        <name>hadoop.tmp.dir</name>
        <value>/opt/app/hadoop-2.5.0/data/tmp</value>
    </property>
    
    <property>
        <name>fs.trash.interval</name>
        <value>10080</value>
    </property>
    
</configuration>

#创建 /opt/app/hadoop-2.5.0/data/tmp
[root@master ~]# mkdir -p /opt/app/hadoop-2.5.0/data/tmp

#hdfs-site.xml
<configuration>

    <property>
        <name>dfs.namenode.secondary.http-address</name>
        <value>slave2:50090</value>
    </property>
    
</configuration>

#slaves  (datanode和nodemanager都在是这里面配置的)
master
slave1
slave2

(2)yarn

#yarn-env.sh
export JAVA_HOME=/opt/modules/jdk1.7.0_80

#yarn-site.xml
<configuration>

    <property>
        <name>yarn.nodemanager.aux-services</name>
        <value>mapreduce_shuffle</value>
    </property>

    <property>
        <name>yarn.resourcemanager.hostname</name>
        <value>slave1</value>
    </property>

    <property>
        <name>yarn.nodemanager.resource.memory-mb</name>
        <value>4096</value>
    </property>
    
    <property>
        <name>yarn.nodemanager.resource.cpu-vcores</name>
        <value>4</value>
    </property>
    
    <property>
        <name>yarn.log-aggregation-enable</name>
        <value>true</value>
    </property>
    
    <property>
        <name>yarn.log-aggregation.retain-seconds</name>
        <value>604800</value>
    </property>
    
</configuration>

#slaves
master
slave1
slave2

(3)mapreduce

#mapred-env.sh
export JAVA_HOME=/opt/modules/jdk1.7.0_80

#mapred-site.xml
<configuration>

    <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>
    
</configuration>

四、配置ssh免密登陆

此步骤不难，基本可以略过；

cd /root/.ssh/
ssh-keygen -t rsa
cat id_rsa.pub >>authorized_keys

五、分发

分发HADOOP安装包至各个机器节点；

#master上
[root@master ~]# scp -r /opt/app/hadoop-2.5.0 root@slave1:/opt/app/

[root@master ~]# scp -r /opt/app/hadoop-2.5.0 root@slave2:/opt/app/

#slave1
[root@slave1 ~]# ls /opt/app/
hadoop-2.5.0

#slave2
[root@slave2 ~]# ls /opt/app/
hadoop-2.5.0