Hadoop centos 6.5 配置

時間 2019-11-17

原文原文鏈接

配置網絡(虛擬主機須要更改網絡適配器爲：橋接模式-複製物理網絡鏈接狀態)

//vi /etc/sysconfig/network-scripts/ifcfg-eth0

BOOTPROTO=static
IPADDR=192.168.0.205
GATEWAY=192.168.0.1
DNS1=192.168.0.1

修改當前機器名稱

NETWORKING 是否利用網絡
GATEWAY 默認網關
IPGATEWAYDEV 默認網關的接口名
HOSTNAME 主機名
DOMAIN 域名

//vi /etc/sysconfig/network

HOSTNAME=Master.Hadoop

添加用戶

//添加用戶
sudo useradd -m hadoop -s /bin/bash

//修改密碼
sudo passwd hadoop

//賦予root權限
vi /etc/sudoers
hadoop ALL=(ALL) ALL

修改hosts

vi /etc/hosts

192.168.0.205   Master.Hadoop
192.168.0.206   Slave1.Hadoop
192.168.0.207   Slave2.Hadoop
192.168.0.208   Slave3.Hadoop

java 環境安裝(jdk 8)

下載地址：http://www.oracle.com/technetwork/java/javase/downloads/index.html (http://download.oracle.com/otn-pub/java/jdk/8u112-b15/jdk-8u112-linux-x64.rpm)
安裝方式

//建立jave目錄
mkdir -p /usr/java/

//複製rpm包到java目錄下
cp jdk-8u112-linux-x64.rpm /usr/java/jdk-8u112-linux-x64.rpm

//切換至java目錄
cd /usr/java

//安裝java
rpm -ivh jdk-8u112-linux-x64.rpm

//在profile文件最後追加入以下內容：
vi /etc/profile

export  JAVA_HOME=/usr/java/jdk1.8.0_112
export  CLASSPATH=.:$JAVA_HOME/jre/lib/rt.jar:$JAVA_HOME/lib/dt.jar:$JAVA_HOME/lib/tools.jar
export  PATH=$PATH:$JAVA_HOME/bin

//從新加載環境變量（也能夠重啓計算機）
source /etc/profile

hadoop安裝(2.7)

下載地址：http://www.apache.org/dyn/closer.cgi/hadoop/common/hadoop-2.7.3/hadoop-2.7.3.tar.gz
完整性比對文件：https://dist.apache.org/repos/dist/release/hadoop/common/hadoop-2.7.3/hadoop-2.7.3.tar.gz.mds
完整性檢測：

//SHA-256
sha256sum hadoop-2.7.3.tar.gz

//MD5
md5sum hadoop-2.7.3.tar.gz

4.安裝方式html

//建立目錄
在/home/hadoop目錄下建立數據存放的文件夾，tmp、hdfs、hdfs/data、hdfs/name

//配置/home/hadoop/hadoop-2.7.0/etc/hadoop目錄下的core-site.xml
<configuration>
    <property>
        <name>fs.defaultFS</name>
        <value>hdfs://192.168.0.205:9000</value>
    </property>
    <property>
        <name>hadoop.tmp.dir</name>
        <value>file:/home/hadoop/tmp</value>
    </property>
    <property>
        <name>io.file.buffer.size</name>
        <value>131702</value>
    </property>
</configuration>


//配置/home/hadoop/hadoop-2.7.0/etc/hadoop目錄下的hdfs-site.xml
<configuration>
    <property>
        <name>dfs.namenode.name.dir</name>
        <value>file:/home/hadoop/dfs/name</value>
    </property>
    <property>
        <name>dfs.datanode.data.dir</name>
        <value>file:/home/hadoop/dfs/data</value>
    </property>
    <property>
        <name>dfs.replication</name>
        <value>2</value>
    </property>
    <property>
        <name>dfs.namenode.secondary.http-address</name>
        <value>192.168.0.205:9001</value>
    </property>
    <property>
    <name>dfs.webhdfs.enabled</name>
    <value>true</value>
    </property>
</configuration>


//配置/home/hadoop/hadoop-2.7.0/etc/hadoop目錄下的mapred-site.xml
<configuration>
    <property>
        <name>mapreduce.framework.name</name>
        <value>yarn</value>
    </property>
    <property>
        <name>mapreduce.jobhistory.address</name>
        <value>192.168.0.205:10020</value>
    </property>
    <property>
        <name>mapreduce.jobhistory.webapp.address</name>
        <value>192.168.0.205:19888</value>
    </property>
</configuration>


//配置/home/hadoop/hadoop-2.7.0/etc/hadoop目錄下的yarn-site.xml
<configuration>
    <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>192.168.0.205:8032</value>
    </property>
    <property>
        <name>yarn.resourcemanager.scheduler.address</name>
        <value>192.168.0.205:8030</value>
    </property>
    <property>
        <name>yarn.resourcemanager.resource-tracker.address</name>
        <value>192.168.0.205:8031</value>
    </property>
    <property>
        <name>yarn.resourcemanager.admin.address</name>
        <value>192.168.0.205:8033</value>
    </property>
    <property>
        <name>yarn.resourcemanager.webapp.address</name>
        <value>192.168.0.205:8088</value>
    </property>
    <property>
        <name>yarn.nodemanager.resource.memory-mb</name>
        <value>768</value>
    </property>
</configuration>

//配置/home/hadoop/hadoop-2.7.0/etc/hadoop目錄下hadoop-env.sh、yarn-env.sh的JAVA_HOME，不設置的話，啓動不了，
export JAVA_HOME=/usr/java/jdk1.8.0_112

//在Master服務器啓動hadoop，從節點會自動啓動，進入/home/hadoop/hadoop-2.7.0目錄
(1)初始化，輸入命令，bin/hdfs namenode -format
(2)所有啓動sbin/start-all.sh，也能夠分開sbin/start-dfs.sh、sbin/start-yarn.sh
(3)中止的話，輸入命令，sbin/stop-all.sh
(4)輸入命令，jps，能夠看到相關信息

//Web訪問，要先開放端口或者直接關閉防火牆
(1)輸入命令，systemctl stop firewalld.service
(2)瀏覽器打開http://192.168.0.182:8088/
(3)瀏覽器打開http://192.168.0.182:50070/


//安裝完成。這只是大數據應用的開始，以後的工做就是，結合本身的狀況，編寫程序調用Hadoop的接口，發揮hdfs、mapreduce的做用。

ssh免登錄設置

//生成免登錄公鑰和祕鑰
ssh-keygen -t rsa -P ''

//打開master ssh權限文件目錄
cd ~/.ssh/

//公鑰庫文件生成
cp ~/.ssh/id_rsa.pub ~/.ssh/authorized_keys

//slave1公鑰同步到master上
scp ~/.ssh/id_rsa.pub hadoop@Master.Hadoop:~/.ssh/id_rsa.pub.slave1

//追加slave1到master
cat ~/.ssh/id_rsa.pub.slave1 >> ~/.ssh/authorized_keys

//其它slave相似的處理方法

//authorized_keys完整的公鑰文件拷貝到slave上（master、slave一、slave2等）
scp ~/.ssh/authorized_keys hadoop@Slave1.Hadoop:~/.ssh/authorized_keys