hadoop笔记

环境：docker
目录：hadoop将会安装在/root/hadoop

获取centos镜像及创建容器

docker pull centos
docker run -it --name hadoop centos /bin/bash

安装java

yum install -y java-1.8.0-openjdk.x86_64
yum install -y java-1.8.0-openjdk-devel.x86_64

安装工具

yum install wget.x86_64
yum -y install openssh-server openssh-clients

安装hadoop

wget http://mirrors.hust.edu.cn/apache/hadoop/common/hadoop-2.8.5/hadoop-2.8.5.tar.gz
tar -zxvf hadoop-2.8.5.tar.gz
mv hadoop-2.8.5/ hadoop

配置环境变量

vi ~/.bashrc

export JAVA_HOME=/usr/lib/jvm/java-1.8.0-openjdk-1.8.0.181-3.b13.el7_5.x86_64/
export HADOOP_HOME=/root/hadoop
export PATH=$PATH:$HADOOP_HOME/bin
export PATH=$PATH:$HADOOP_HOME/sbin

source ~/.bashrc

配置hadoop

cd /root/hadoop/etc/hadoop

//vi hadoop-env.sh
export JAVA_HOME=/usr/lib/jvm/java-1.8.0-openjdk-1.8.0.181-3.b13.el7_5.x86_64/



//hdfs-site.xml
<!--配置HDFS的冗余度-->
<property>
  <name>dfs.replication</name>
  <value>1</value>
</property>

<!--配置是否检查权限-->
<property>
  <name>dfs.permissions</name>
  <value>false</value>
</property> 




//core-site.xml
<!--配置HDFS的NameNode-->
<property>
  <name>fs.defaultFS</name>
  <value>hdfs://192.168.88.11:9000</value>
</property>

<!--配置DataNode保存数据的位置-->
<property>
<name>hadoop.tmp.dir</name>
<value>/root/hadoop-2.4.1/tmp</value>
</property>     
            
            



//mapred-site.xml
<!--配置MR运行的框架-->
<property>
  <name>mapreduce.framework.name</name>
  <value>yarn</value>
</property>     
            




// yarn-site.xml
<!--配置ResourceManager的地址-->
<property>
  <name>yarn.resourcemanager.hostname</name>
  <value>192.168.88.11</value>
</property>

<!--配置NodeManager执行任务的方式-->
<property>
  <name>yarn.nodemanager.aux-services</name>
  <value>mapreduce_shuffle</value>
</property> 

配置ssh无密码登陆

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

格式化及启动停止

/root/hadoop/bin/hdfs namenode -format
sh /root/hadoop/sbin/start-all.sh
sh /root/hadoop/sbin/stop-all.sh

查看运行情况

netstat -nultp //查看端口号
jps //查看java服务是否开启