Création manuelle d'une image docker avec scala et spark
bigdata scala / spark / docker

Construction manuelle d'une petite image java:alpine + scala + spark

docker run -ti java:alpine /bin/sh 

apk update
apk add bash
apk add nano

cd
nano ~/.profile

    # ~/.profile: executed by Bourne-compatible login shells.

    if [ -e /bin/bash ]; then
      if [ -f ~/.bashrc ]; then
        . ~/.bashrc
      fi
    fi

    mesg n

nano ~/.bashrc
    SCALA_HOME=/opt/scala-2.11.8
    PATH=$PATH:$SCALA_HOME/bin
    SPARK_HOME=/opt/spark-2.0.0-bin-hadoop2.7
    PATH=$PATH:$SPARK_HOME/bin

mkdir /opt
cd /opt
wget downloads.lightbend.com/scala/2.11.8/scala-2.11.8.tgz
tar xvzf scala-2.11.8.tgz
rm  scala-2.11.8.tgz

wget http://d3kbcqa49mib13.cloudfront.net/spark-2.0.0-bin-hadoop2.7.tgz
tar xvzf spark-2.0.0-bin-hadoop2.7.tgz
rm spark-2.0.0-bin-hadoop2.7.tgz

Sauvegarde de l'image et lancement

    docker commit 5262e673ffa6 tintouli/spark:alpine
    docker run -ti tintouli/spark:alpine bash -cli spark-shell

Update : génération à partir d'un Dockerfile

cat Dockerfile

FROM java:alpine

#use bash
RUN apk update
RUN apk add --no-cache bash

#download and install scala and spark
RUN mkdir /opt
RUN wget -O /opt/scala-2.11.8.tgz downloads.lightbend.com/scala/2.11.8/scala-2.11.8.tgz
RUN tar xvzf /opt/scala-2.11.8.tgz  -C /opt
RUN rm  /opt/scala-2.11.8.tgz

RUN wget http://d3kbcqa49mib13.cloudfront.net/spark-2.0.0-bin-hadoop2.7.tgz
RUN tar xvzf spark-2.0.0-bin-hadoop2.7.tgz  -C /opt
RUN rm spark-2.0.0-bin-hadoop2.7.tgz

# Default to UTF-8 file.encoding
ENV LANG C.UTF-8

# Environment variables
ENV SCALA_HOME /opt/scala-2.11.8
ENV PATH $PATH:$SCALA_HOME/bin
ENV SPARK_HOME /opt/spark-2.0.0-bin-hadoop2.7
ENV PATH $PATH:$SPARK_HOME/bin

- Tintouli