docker配置hadoop3.2.2全分布式集群

docker 配置

在此之前需要完成docker的安装

mkdir centos-ssh && cd centos-ssh && vi Dockerfile
sudo docker pull hub.c.163.com/public/centos

FROM centos # 基础镜像，在使用之前需要pull

 MAINTAINER bernard

# 安装openssh-server和sudo软件包，并且将sshd的UsePAM参数设置成no  
RUN yum install -y openssh-server sudo
RUN sed -i 's/UsePAM yes/UsePAM no/g' /etc/ssh/sshd_config
#安装openssh-clients
RUN yum  install -y openssh-clients

# 添加测试用户root，密码root，并且将此用户添加到sudoers里  
RUN echo "root:root" | chpasswd
RUN echo "root   ALL=(ALL)       ALL" >> /etc/sudoers
RUN ssh-keygen -t dsa -f /etc/ssh/ssh_host_dsa_key
RUN ssh-keygen -t rsa -f /etc/ssh/ssh_host_rsa_key
# 启动sshd服务并且暴露22端口  
RUN mkdir /var/run/sshd
EXPOSE 22
CMD ["/usr/sbin/sshd", "-D"]

docker build -t 'bernard/centos-ssh' . # 构建

mkdir centos-ssh-root-jdk && cd centos-ssh-root-jdk 
# 拷贝一个jdk到这个文件夹下
vi Dockerfile


#基于上一个ssh镜像构建
FROM bernard/centos-ssh    
#拷贝并解压jdk                                        
ADD jdk-8u301-linux-x64.tar.gz /usr/local/
RUN mv /usr/local/jdk1.8.0_231 /usr/local/jdk1.8
ENV JAVA_HOME /usr/local/jdk1.8
ENV PATH $JAVA_HOME/bin:$PATH


# wq
docker build -t 'bernard/centos-jdk' .

mkdir centos-ssh-root-jdk-hadoop && cd centos-ssh-root-jdk-hadoop
# 拷贝一个hadoop-3.2.2到这个文件夹下
vi Dockerfile

FROM bernard/centos-jdk
ADD hadoop-3.2.2.tar.gz /usr/local
RUN mv /usr/local/hadoop-3.2.2 /usr/local/hadoop
ENV HADOOP_HOME /usr/local/hadoop
ENV PATH $HADOOP_HOME/bin:$PATH

# wq
docker build -t 'bernard/hadoop' .

分别开三个窗口。

docker run --name hadoop0 --hostname hadoop0 -d -P -p bernard/hadoop    
docker run --name hadoop1 --hostname hadoop1 -d -P bernard/hadoop
docker run --name hadoop2 --hostname hadoop2 -d -P bernard/hadoop

配置免密登陆

1. 配置hadoop0到1/2上的免密登陆
2. 在hadoop0 hadoop1 hadoop2的host上增加三者的IP地址

# src
ssh localhost
ssh-keygen -t rsa
scp ~/.ssh/id_rsa.pub root@hadoop1:~
# dst
cat ~/id_rsa.pub >> ~/.ssh/authorized_keys

172.17.0.3      hadoop0
172.17.0.4      hadoop1
172.17.0.5      hadoop2
# IP地址要根据你的改

配置hadoop

bashrc

vi ~/.bashrc

export JAVA_HOME=/usr/local/jdk1.8
export JRE_HOME=${JAVA_HOME}/jre
export CLASSPATH=.:${JAVA_HOME}/lib:${JRE_HOME}/lib:$CLASSPATH
export JAVA_PATH=${JAVA_HOME}/bin:${JRE_HOME}/bin
export PATH=$PATH:${JAVA_PATH}

export HADOOP_HOME=/usr/local/hadoop
export PATH=$PATH:$HADOOP_HOME/bin
export PATH=$PATH:$HADOOP_HOME/sbin

export HDFS_NAMENODE_USER=root
export HDFS_DATANODE_USER=root
export HDFS_SECONDARYNAMENODE_USER=root
export YARN_RESOURCEMANAGER_USER=root
export YARN_NODEMANAGER_USER=root

source ~/.bashrc

hadoop-env.sh

本文件和以下文件均在HADOOP_HOME/etc/hadoop下

cd /usr/local/hadoop/etc/hadoop
vi hadoop-env.sh

export JAVA_HOME=/usr/local/jdk1.8

core-site.xml

<configuration>
        <property>
                <name>fs.defaultFS</name>
                <value>hdfs://hadoop0:9000</value>
        </property>
        <property>
                <name>hadoop.tmp.dir</name>
                <value>/usr/local/hadoop/tmp</value>
                <description>Abase for other temporary directories.</description>
        </property>
<!--
        <property>
                 <name>fs.trash.interval</name>
                 <value>1440</value>
        </property>
-->
</configuration>

hdfs-site.xml

<configuration>
        <property>
                <name>dfs.namenode.secondary.http-address</name>
                <value>hadoop0:50090</value>
        </property>
        <property>
                <name>dfs.replication</name>
                <value>1</value>
        </property>
        <property>
                <name>dfs.namenode.name.dir</name>
                <value>file:/usr/local/hadoop/tmp/dfs/name</value>
        </property>
        <property>
                <name>dfs.datanode.data.dir</name>
                <value>file:/usr/local/hadoop/tmp/dfs/data</value>
        </property>
</configuration>

mapred-site.xml

<configuration>
        <property>
                <name>mapreduce.framework.name</name>
                <value>yarn</value>
        </property>
        <property>
                <name>mapreduce.jobhistory.address</name>
                <value>hadoop0:10020</value>
        </property>
        <property>
                <name>mapreduce.jobhistory.webapp.address</name>
                <value>hadoop0:19888</value>
        </property>
        <property>
                <name>yarn.app.mapreduce.am.env</name>
                <value>HADOOP_MAPRED_HOME=/usr/local/hadoop</value>
        </property>
        <property>
                <name>mapreduce.map.env</name>
                <value>HADOOP_MAPRED_HOME=/usr/local/hadoop</value>
        </property>
        <property>
  				      <name>mapreduce.reduce.env</name>
	        				<value>HADOOP_MAPRED_HOME=/usr/local/hadoop</value>
        </property>
</configuration>

yarn-site.xml

<configuration>
        <property>
                <name>yarn.resourcemanager.hostname</name>
                <value>hadoop0</value>
        </property>
        <property>
                <name>yarn.nodemanager.aux-services</name>
                <value>mapreduce_shuffle</value>
        </property>
</configuration>

workers

hadoop0
hadoop1
hadoop2

scp * root@hadoop1:/usr/local/hadoop/etc/hadoop
scp * root@hadoop2:/usr/local/hadoop/etc/hadoop

启动

start-dfs.sh

reference

https://zhuanlan.zhihu.com/p/59758201
https://www.cnblogs.com/rmxd/p/12051866.html#_label1

git clone https://github.com/jpetazzo/pipework.git
sudo cp -rp pipework-master/pipework /usr/local/bin/

sudo brctl addbr br0
sudo ip link set dev br0 up
sudo ip addr add 192.168.2.1/24 dev br0