FROM python:3.6-alpine ENV SPARK_VERSION="2.4.3" \ HADOOP_VERSION="2.7" \ SPARK_INSTALL="/usr/local" RUN apk add --no-cache \ bash \ openjdk8 \ tini \ zeromq RUN apk add --no-cache --virtual .fetch-deps \ curl \ tar RUN curl -s https://www-us.apache.org/dist/spark/spark-$SPARK_VERSION/spark-$SPARK_VERSION-bin-hadoop$HADOOP_VERSION.tgz | tar -xz -C $SPARK_INSTALL && \ cd $SPARK_INSTALL && ln -s spark-$SPARK_VERSION-bin-hadoop$HADOOP_VERSION spark RUN apk del .fetch-deps COPY start-master.sh start-worker.sh /usr/local/bin/ ENV SPARK_HOME="$SPARK_INSTALL/spark" \ SPARK_HOSTNAME="localhost" \ SPARK_MASTER_PORT="7077" \ SPARK_MASTER_WEBUI_PORT="8080" COPY spark-defaults.conf $SPARK_HOME/conf ENV SPARK_MASTER="spark://$SPARK_HOSTNAME:$SPARK_MASTER_PORT" # Spark doesn't seem to respond directly to SIGTERM as the exit status is # for SIGKILL (137), after a pause. Presumably docker-compose down times out. # Using tini gives immediate exit with status 143 (SIGTERM). ENTRYPOINT ["/sbin/tini", "--"] CMD ["/usr/local/bin/start-master.sh"]