Hadoop的Docker镜像构建

1、Dockerfile

###Dockerfile   -- beagin
FROM ubuntu:trusty
#MAINTAINER The Hue Team "https://github.com/cloudera/hue"

RUN apt-get update -y

RUN apt-get install -y software-properties-common
RUN add-apt-repository -y ppa:webupd8team/java
RUN apt-get update -y

RUN echo oracle-java8-installer shared/accepted-oracle-license-v1-1 select true | sudo /usr/bin/debconf-set-selections
RUN apt-get install -y oracle-java8-installer

RUN apt-get update -y
RUN apt-get install --fix-missing -q -y 
  git 
  ant 
  gcc 
  g++ 
  libkrb5-dev 
  libmysqlclient-dev 
  libssl-dev 
  libsasl2-dev 
  libsasl2-modules-gssapi-mit 
  libsqlite3-dev 
  libtidy-0.99-0 
  libxml2-dev 
  libxslt-dev 
  libffi-dev 
  make 
  maven 
  libldap2-dev 
  python-dev 
  python-setuptools 
  libgmp3-dev 
  libz-dev
#Download Hadoop from one of these mirrors. Change the version number appropriately:
RUN wget http://apache.mirrors.tds.net/hadoop/common/hadoop-2.7.2/hadoop-2.7.2.tar.gz -P ~/Downloads
#Extract it to /usr/local:
RUN tar zxvf ~/Downloads/hadoop-* -C /usr/local
#Rename the directory to just hadoop:
RUN mv /usr/local/hadoop-* /usr/local/hadoop
###Dockerfile   -- end

2、修改配置

#Set Environment Variables
#Find Java with:
#readlink -f $(which java)
#Environment variables:
$ echo "export JAVA_HOME=/usr/lib/jvm/java-8-oracle" >> ~/.bashrc
#$ source ~/.bashrc

$ echo "export PATH=$PATH:$JAVA_HOME/bin" >> ~/.bashrc
#$ source ~/.bashrc

$ echo "export HADOOP_HOME=/usr/local/hadoop" >> ~/.bashrc
#$ source ~/.bashrc

$ echo "export PATH=$PATH:$HADOOP_HOME/bin" >> ~/.bashrc
#$ source ~/.bashrc

$ echo "export HADOOP_CONF_DIR=/usr/local/hadoop/etc/hadoop" >> ~/.bashrc
$ source ~/.bashrc

3、构建镜像

docker build -t hadoop .