Stand-alone Hadoop Container

Dockerfile

# Single cluster Hadoop tutorial
# - https://hadoop.apache.org/docs/current/hadoop-project-dist/hadoop-common/SingleCluster.html

FROM ubuntu:14.04
MAINTAINER Anthony Troy

# Linux deps
ENV DEBIAN_FRONTEND noninteractive
RUN sed -i 's/# \(.*multiverse$\)/\1/g' /etc/apt/sources.list
RUN apt-get update
RUN apt-get install -y build-essential
RUN apt-get install -y software-properties-common
RUN apt-get install -y wget rsync ssh

# Sshd config
RUN ssh-keygen -t rsa -N "" -f /root/.ssh/id_rsa
RUN cp /root/.ssh/id_rsa.pub /root/.ssh/authorized_keys
RUN mkdir -p /var/run/sshd
RUN echo "Host localhost\n    UserKnownHostsFile=/dev/null\n    StrictHostKeyChecking=no" >> /root/.ssh/config

# Java dep
RUN echo oracle-java8-installer shared/accepted-oracle-license-v1-1 select true | debconf-set-selections
RUN add-apt-repository -y ppa:webupd8team/java
RUN apt-get update
RUN apt-get install -y oracle-java8-installer
ENV JAVA_HOME /usr/lib/jvm/java-8-oracle

# Hadoop
RUN wget http://ftp.heanet.ie/mirrors/www.apache.org/dist/hadoop/common/stable/hadoop-2.7.2.tar.gz
RUN tar xzf hadoop-2.7.2.tar.gz
RUN mv hadoop-2.7.2 /usr/local/hadoop
ENV HADOOP_HOME /usr/local/hadoop
ENV PATH $PATH:$HADOOP_HOME/bin

# Cleanup
RUN rm -rf hadoop-2.7.2.tar.gz
RUN rm -rf /var/lib/apt/lists/*
RUN rm -rf /var/cache/oracle-jdk8-installer


CMD service ssh start

test.sh

#!/bin/bash

##************************************************************#
#                   test.sh                                   #
#                                                             #
# Build and run the container                                 #
#   docker build -t hadoop_test . && docker run hadoop_test   #
#                                                             #
# Run this script on the container                            #
#   docker run hadoop_test bash -c "`cat test.sh`"            #
#                                                             #
#*************************************************************#

COUNT_FILES="${COUNT_FILES:-$(find / -name LICENSE.txt)}"
OUTPUT_DIR="${OUTPUT_DIR:-test_output)}"

rm -fr $OUTPUT_DIR
hadoop jar $HADOOP_HOME/share/hadoop/mapreduce/hadoop*examples*.jar wordcount $COUNT_FILES $OUTPUT_DIR
cat $OUTPUT_DIR/part-r-00000