下载Hadoop
wget http://mirror.bit.edu.cn/apache/hadoop/common/hadoop-2.7.4/hadoop-2.7.4.tar.gz
如果wget不存在,使用如下命令安装
yum install -y wget
系统配置
host(别名不能出现.号)
192.168.1.211 hd211
192.168.1.212 hd212
192.168.1.214 hd214
免密码登录
cd /root/.ssh/
ssh-keygen -t rsa
一路回车
同步到其它服务器
ssh-copy-id hd211
ssh-copy-id hd212
ssh-copy-id hd214
安装、配置Hadoop
解压安装包
tar -zxvf hadoop-2.7.4.tar.gz
进入Hadoop配置文件目录
cd hadoop-2.7.4/
编辑hadoop-env.sh
vi etc/hadoop/hadoop-env.sh
export JAVA_HOME=/usr/lib/jvm/jre
export HADOOP_LOG_DIR=/data/hadoop/logs
编辑yarn-env.sh
vi etc/hadoop/yarn-env.sh
YARN_LOG_DIR="/data/hadoop/logs"
编辑core-site.xml
vi etc/hadoop/core-site.xml
内容
<configuration>
<property>
<name>fs.defaultFS</name>
<value>hdfs://hd212:9000</value>
</property>
<property>
<name>io.file.buffer.size</name>
<value>131072</value>
</property>
<property>
<name>hadoop.tmp.dir</name>
<value>file:/data/hadoop/tmp</value>
<description>Abase for other temporary directories.</description>
</property>
</configuration>
编辑hdfs-site.xml
vi etc/hadoop/hdfs-site.xml
内容
<configuration>
<property>
<name>dfs.permissions.enabled</name>
<value>false</value>
</property>
<property>
<name>dfs.webhdfs.enabled</name>
<value>true</value>
</property>
<property>
<name>dfs.blocksize</name>
<value>64m</value>
</property>
<property>
<name>dfs.nameservices</name>
<value>hadoop-cluster-zgw</value>
</property>
<!-- 上传文件时rep系数由client决定 -->
<property>
<name>dfs.replication</name>
<value>3</value>
</property>
<property>
<name>dfs.namenode.name.dir</name>
<value>/data/hadoop/hdfs/name</value>
</property>
<property>
<name>dfs.namenode.checkpoint.dir</name>
<value>/data/hadoop/hdfs/checkpoint</value>
</property>
<property>
<name>dfs.namenode.checkpoint.edits.dir</name>
<value>/data/hadoop/hdfs/checkpoint</value>
</property>
<property>
<name>dfs.datanode.data.dir</name>
<value>/data/hadoop/hdfs/data</value>
</property>
<property>
<name>dfs.namenode.secondary.http-address</name>
<value>hd211:50090</value>
</property>
</configuration>
编辑mapred-site.xml
cp etc/hadoop/mapred-site.xml.template etc/hadoop/mapred-site.xml
vi etc/hadoop/mapred-site.xml
内容
<configuration>
<property>
<name>mapreduce.framework.name</name>
<value>yarn</value>
</property>
<property>
<name>mapreduce.jobhistory.address</name>
<value>hd212:10020</value>
</property>
<property>
<name>mapreduce.jobhistory.webapp.address</name>
<value>hd212:19888</value>
</property>
</configuration>
编辑yarn-site.xml
vi etc/hadoop/yarn-site.xml
内容
<configuration>
<property>
<name>yarn.nodemanager.aux-services</name>
<value>mapreduce_shuffle</value>
</property>
<property>
<name>yarn.nodemanager.aux-services.mapreduce.shuffle.class</name>
<value>org.apache.hadoop.mapred.ShuffleHandler</value>
</property>
<property>
<name>yarn.nodemanager.local-dirs</name>
<value>/data/hadoop/yarn/nodemanager</value>
</property>
<property>
<name>yarn.resourcemanager.hostname</name>
<value>hd212</value>
</property>
<property>
<name>yarn.resourcemanager.address</name>
<value>hd212:8032</value>
</property>
<property>
<name>yarn.resourcemanager.scheduler.address</name>
<value>hd212:8030</value>
</property>
<property>
<name>yarn.resourcemanager.resource-tracker.address</name>
<value>hd212:8031</value>
</property>
<property>
<name>yarn.resourcemanager.admin.address</name>
<value>hd212:8033</value>
</property>
<property>
<name>yarn.resourcemanager.webapp.address</name>
<value>hd212:8034</value>
</property>
</configuration>
编辑slaves
vi etc/hadoop/slaves
内容
hd211
hd212
hd214
环境变量
vi /etc/profile
#jdk
export JAVA_HOME=/usr/lib/jvm/jre
export PATH=$PATH:$JAVA_HOME/bin
#hadoop
export HADOOP_HOME=/usr/hadoop/hadoop-2.7.4
export PATH=$PATH:$HADOOP_HOME/sbin
export PATH=$PATH:$HADOOP_HOME/bin
source /etc/profile
创建目录
mkdir /data/hadoop
mkdir /data/hadoop/hdfs
mkdir /data/hadoop/hdfs/data
mkdir /data/hadoop/hdfs/checkpoint
mkdir /data/hadoop/hdfs/name
mkdir /data/hadoop/yarn
mkdir /data/hadoop/yarn/nodemanager
mkdir /data/hadoop/tmp
防火墙配置
firewall-cmd --permanent --add-port=9000/tcp
firewall-cmd --permanent --add-port=50070/tcp
firewall-cmd --permanent --add-port=50090/tcp
firewall-cmd --permanent --add-port=10020/tcp
firewall-cmd --permanent --add-port=19888/tcp
firewall-cmd --permanent --add-port=8030/tcp
firewall-cmd --permanent --add-port=8031/tcp
firewall-cmd --permanent --add-port=8032/tcp
firewall-cmd --permanent --add-port=8033/tcp
firewall-cmd --permanent --add-port=8088/tcp
firewall-cmd --reload
格式华HDFS文件系统
hdfs namenode –format
启动hadoop
start-all.sh
浏览器访问
hd212:50070
其他
1.管理界面只能看到一个DataNode
2.SHUTDOWN_MSG: Shutting down NameNode at localhost/127.0.0.1
注意 -format 是否为中文符号