# Copyright (c) Jupyter Development Team. # Distributed under the terms of the Modified BSD License. FROM jupyter/scipy-notebook MAINTAINER Jupyter Project USER root # Spark dependencies ENV APACHE_SPARK_VERSION 2.1.0 ENV HADOOP_VERSION 2.7 # Temporarily add jessie backports to get openjdk 8, but then remove that source RUN echo 'deb http://cdn-fastly.deb.debian.org/debian jessie-backports main' > /etc/apt/sources.list.d/jessie-backports.list && \ apt-get -y update && \ apt-get install --no-install-recommends -t jessie-backports -y openjdk-8-jre-headless ca-certificates-java && \ rm /etc/apt/sources.list.d/jessie-backports.list && \ apt-get clean && \ rm -rf /var/lib/apt/lists/* RUN cd /tmp && \ wget -q http://d3kbcqa49mib13.cloudfront.net/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz && \ echo "3fc94096ae34f9a1a148d37e5ed640a7e5de1812f1f2ecd715d92bbf2901e895cf4b93e6d8ee0d64debb5df7c56d673c0a36e5fc49503ec0f4507eb0edf961a4 *spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" | sha512sum -c - && \ tar xzf spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz -C /usr/local && \ rm spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz RUN cd /usr/local && ln -s spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION} spark # Mesos dependencies RUN apt-key adv --keyserver keyserver.ubuntu.com --recv E56151BF && \ DISTRO=debian && \ CODENAME=jessie && \ echo "deb http://repos.mesosphere.io/${DISTRO} ${CODENAME} main" > /etc/apt/sources.list.d/mesosphere.list && \ apt-get -y update && \ apt-get --no-install-recommends -y --force-yes install mesos=1.2\* && \ apt-get clean && \ rm -rf /var/lib/apt/lists/* # Spark and Mesos config ENV SPARK_HOME /usr/local/spark ENV PYTHONPATH $SPARK_HOME/python:$SPARK_HOME/python/lib/py4j-0.10.4-src.zip ENV MESOS_NATIVE_LIBRARY /usr/local/lib/libmesos.so ENV SPARK_OPTS --driver-java-options=-Xms1024M --driver-java-options=-Xmx4096M --driver-java-options=-Dlog4j.logLevel=info USER $NB_USER