mirror of
https://github.com/jupyter/docker-stacks.git
synced 2025-10-10 11:32:57 +00:00
68 lines
2.9 KiB
Docker
68 lines
2.9 KiB
Docker
# Copyright (c) Jupyter Development Team.
|
|
# Distributed under the terms of the Modified BSD License.
|
|
ARG BASE_CONTAINER=jupyter/scipy-notebook
|
|
FROM $BASE_CONTAINER
|
|
|
|
LABEL maintainer="Jupyter Project <jupyter@googlegroups.com>"
|
|
|
|
# Fix DL4006
|
|
SHELL ["/bin/bash", "-o", "pipefail", "-c"]
|
|
|
|
USER root
|
|
|
|
# Spark dependencies
|
|
# Default values can be overridden at build time
|
|
# (ARGS are in lower case to distinguish them from ENV)
|
|
ARG spark_version="3.0.1"
|
|
ARG hadoop_version="3.2"
|
|
ARG spark_checksum="E8B47C5B658E0FBC1E57EEA06262649D8418AE2B2765E44DA53AAF50094877D17297CC5F0B9B35DF2CEEF830F19AA31D7E56EAD950BBE7F8830D6874F88CFC3C"
|
|
ARG openjdk_version="11"
|
|
|
|
ENV APACHE_SPARK_VERSION="${spark_version}" \
|
|
HADOOP_VERSION="${hadoop_version}"
|
|
|
|
RUN apt-get -y update && \
|
|
apt-get install --no-install-recommends -y \
|
|
"openjdk-${openjdk_version}-jre-headless" \
|
|
ca-certificates-java && \
|
|
apt-get clean && rm -rf /var/lib/apt/lists/*
|
|
|
|
# Spark installation
|
|
WORKDIR /tmp
|
|
# Using the preferred mirror to download Spark
|
|
# hadolint ignore=SC2046
|
|
RUN wget -q $(wget -qO- https://www.apache.org/dyn/closer.lua/spark/spark-${APACHE_SPARK_VERSION}/spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz\?as_json | \
|
|
python -c "import sys, json; content=json.load(sys.stdin); print(content['preferred']+content['path_info'])") && \
|
|
echo "${spark_checksum} *spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" | sha512sum -c - && \
|
|
tar xzf "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz" -C /usr/local --owner root --group root --no-same-owner && \
|
|
rm "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}.tgz"
|
|
|
|
WORKDIR /usr/local
|
|
|
|
# Configure Spark
|
|
ENV SPARK_HOME=/usr/local/spark
|
|
ENV SPARK_OPTS="--driver-java-options=-Xms1024M --driver-java-options=-Xmx4096M --driver-java-options=-Dlog4j.logLevel=info" \
|
|
PATH=$PATH:$SPARK_HOME/bin
|
|
|
|
RUN ln -s "spark-${APACHE_SPARK_VERSION}-bin-hadoop${HADOOP_VERSION}" spark && \
|
|
# Add a link in the before_notebook hook in order to source automatically PYTHONPATH
|
|
mkdir -p /usr/local/bin/before-notebook.d && \
|
|
ln -s "${SPARK_HOME}/sbin/spark-config.sh" /usr/local/bin/before-notebook.d/spark-config.sh
|
|
|
|
# Fix Spark installation for Java 11 and Apache Arrow library
|
|
# see: https://github.com/apache/spark/pull/27356, https://spark.apache.org/docs/latest/#downloading
|
|
RUN cp -p "$SPARK_HOME/conf/spark-defaults.conf.template" "$SPARK_HOME/conf/spark-defaults.conf" && \
|
|
echo 'spark.driver.extraJavaOptions="-Dio.netty.tryReflectionSetAccessible=true"' >> $SPARK_HOME/conf/spark-defaults.conf && \
|
|
echo 'spark.executor.extraJavaOptions="-Dio.netty.tryReflectionSetAccessible=true"' >> $SPARK_HOME/conf/spark-defaults.conf
|
|
|
|
USER $NB_UID
|
|
|
|
# Install pyarrow
|
|
RUN conda install --quiet --yes --satisfied-skip-solve \
|
|
'pyarrow=2.0.*' && \
|
|
conda clean --all -f -y && \
|
|
fix-permissions "${CONDA_DIR}" && \
|
|
fix-permissions "/home/${NB_USER}"
|
|
|
|
WORKDIR $HOME
|