spark-on-k8s python pyspark

Dockerfile--spark8s-pyspark

# I was having problems to create docker images for spark-on-k8s using docker-image-tool.sh in spark (it always gives spark-r).
# Thus here is the docker file to creat for running pyspark.
# The image is available on sunnybingome/spark8s:pyspark240py368 with spark 2.4.0
# For clie-mode (interactive mode), please use pipenv to ensure py version. The image is in using py 3.6(.8).

# Sunny modified from spark-2.4.0-bin-hadoop2.7/kubernetes/dockerfiles/spark/Dockerfile

#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#

FROM openjdk:8-alpine

ARG spark_jars=jars
ARG img_path=kubernetes/dockerfiles
ARG k8s_tests=kubernetes/tests

## sunny: install python ## pyv='/opt/entrypoint.sh: line 75: python: command not found'
RUN apk update \
&& apk upgrade \
&& apk add --no-cache bash \
&& apk add --no-cache --virtual=build-dependencies unzip \
&& apk add --no-cache curl \
&& apk add --no-cache openjdk7-jre
RUN apk add --no-cache python3 \
&& python3 -m ensurepip \
&& pip3 install --upgrade pip setuptools \
&& rm -r /usr/lib/python*/ensurepip && \
if [ ! -e /usr/bin/pip ]; then ln -s pip3 /usr/bin/pip ; fi && \
if [[ ! -e /usr/bin/python ]]; then ln -sf /usr/bin/python3 /usr/bin/python; fi && \
rm -r /root/.cache
RUN pip3 install pyspark==2.4.0

# Before building the docker image, first build and make a Spark distribution following
# the instructions in http://spark.apache.org/docs/latest/building-spark.html.
# If this docker file is being used in the context of building your images from a Spark
# distribution, the docker build command should be invoked from the top level directory
# of the Spark distribution. E.g.:
# docker build -t spark:latest -f kubernetes/dockerfiles/spark/Dockerfile .

RUN set -ex && \
    apk upgrade --no-cache && \
    apk add --no-cache bash tini libc6-compat linux-pam && \
    mkdir -p /opt/spark && \
    mkdir -p /opt/spark/work-dir && \
    touch /opt/spark/RELEASE && \
    rm /bin/sh && \
    ln -sv /bin/bash /bin/sh && \
    echo "auth required pam_wheel.so use_uid" >> /etc/pam.d/su && \
    chgrp root /etc/passwd && chmod ug+rw /etc/passwd

COPY ${spark_jars} /opt/spark/jars
COPY bin /opt/spark/bin
COPY sbin /opt/spark/sbin
COPY ${img_path}/spark/entrypoint.sh /opt/
COPY examples /opt/spark/examples
COPY ${k8s_tests} /opt/spark/tests
COPY data /opt/spark/data

ENV SPARK_HOME /opt/spark

WORKDIR /opt/spark/work-dir

ENTRYPOINT [ "/opt/entrypoint.sh" ]