Files
docker-stacks/pyspark-notebook/Dockerfile
2017-08-09 11:07:29 +02:00

42 lines
1.8 KiB
Docker

# Copyright (c) Jupyter Development Team.
# Distributed under the terms of the Modified BSD License.
FROM jupyter/scipy-notebook
MAINTAINER Jupyter Project <jupyter@googlegroups.com>
USER root
# Spark dependencies
ENV APACHE_SPARK_VERSION 2.2.0
ENV HADOOP_VERSION 2.7
RUN apt-get -y update && \
apt-get install --no-install-recommends -y openjdk-8-jre-headless ca-certificates-java && \
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 "7a186a2a007b2dfd880571f7214a7d329c972510a460a8bdbef9f7f2a891019343c020f74b496a61e5aa42bc9e9a79cc99defe5cb3bf8b6f49c07e01b259bc6b *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 . /etc/os-release && \
apt-key adv --keyserver keyserver.ubuntu.com --recv E56151BF && \
DISTRO=$ID && \
CODENAME=$VERSION_CODENAME && \
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