diff --git a/pyspark-notebook/Dockerfile b/pyspark-notebook/Dockerfile index 58a01a0e..394da2a4 100644 --- a/pyspark-notebook/Dockerfile +++ b/pyspark-notebook/Dockerfile @@ -7,7 +7,7 @@ MAINTAINER Jupyter Project USER root # Spark dependencies -ENV APACHE_SPARK_VERSION 2.1.0 +ENV APACHE_SPARK_VERSION 2.1.1 ENV HADOOP_VERSION 2.7 # Temporarily add jessie backports to get openjdk 8, but then remove that source @@ -19,7 +19,7 @@ RUN echo 'deb http://cdn-fastly.deb.debian.org/debian jessie-backports main' > / 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 - && \ + echo "4b6427ca6dc6f888b21bff9f9a354260af4a0699a1f43caabf58ae6030951ee5fa8b976497aa33de7e4ae55609d47a80bfe66dfc48c79ea28e3e5b03bdaaba11 *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 diff --git a/pyspark-notebook/README.md b/pyspark-notebook/README.md index fcceae88..0312b42b 100644 --- a/pyspark-notebook/README.md +++ b/pyspark-notebook/README.md @@ -7,8 +7,8 @@ * Jupyter Notebook 5.0.x * Conda Python 3.x and Python 2.7.x environments * pyspark, pandas, matplotlib, scipy, seaborn, scikit-learn pre-installed -* Spark 2.1.0 with Hadoop 2.7 for use in local mode or to connect to a cluster of Spark workers -* Mesos client 0.25 binary that can communicate with a Mesos master +* Spark 2.1.1 with Hadoop 2.7 for use in local mode or to connect to a cluster of Spark workers +* Mesos client 1.2 binary that can communicate with a Mesos master * Unprivileged user `jovyan` (uid=1000, configurable, see options) in group `users` (gid=100) with ownership over `/home/jovyan` and `/opt/conda` * [tini](https://github.com/krallin/tini) as the container entrypoint and [start-notebook.sh](../base-notebook/start-notebook.sh) as the default command * A [start-singleuser.sh](../base-notebook/start-singleuser.sh) script useful for running a single-user instance of the Notebook server, as required by JupyterHub