Changed spark environment

nigel.stanger / docker-analytics

Browse code Changed spark environment • Added SPARK_MASTER. • Changed SPARK_LOCAL_IP to localhost. master spark3
1 parent c822450 commit 37410f339acd983aefd69768471f4d37b31763bc Nigel Stanger authored on 13 May 2019

Patch

Showing 1 changed file

Ignore Space Show notes View spark/Dockerfile
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$HADOOP_VERSION spark RUN apk del .fetch-deps COPY start-master.sh /usr/local/bin/start-master.sh COPY start-worker.sh /usr/local/bin/start-worker.sh ENV SPARK_HOME="$SPARK_INSTALL/spark" \ SPARK_LOCAL_IP="localhost" \ SPARK_MASTER_PORT="7077" \ SPARK_MASTER="spark://$SPARK_LOCAL_IP:$SPARK_MASTER_PORT" \ SPARK_MASTER_WEBUI_PORT="8080" \ PYSPARK_PYTHON="/usr/local/bin/python3" # 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"] 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$HADOOP_VERSION spark RUN apk del .fetch-deps COPY start-master.sh /usr/local/bin/start-master.sh COPY start-worker.sh /usr/local/bin/start-worker.sh ENV SPARK_HOME="$SPARK_INSTALL/spark" \ SPARK_LOCAL_IP="127.0.0.1" \ SPARK_MASTER_PORT="7077" \ SPARK_MASTER_WEBUI_PORT="8080" \ PYSPARK_PYTHON="/usr/local/bin/python3" # 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"]

Ignore Space Show notes View

spark/Dockerfile

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 /usr/local/bin/start-master.sh
COPY start-worker.sh /usr/local/bin/start-worker.sh

ENV SPARK_HOME="$SPARK_INSTALL/spark" \
    SPARK_LOCAL_IP="localhost" \
    SPARK_MASTER_PORT="7077" \
    SPARK_MASTER="spark://$SPARK_LOCAL_IP:$SPARK_MASTER_PORT" \
    SPARK_MASTER_WEBUI_PORT="8080" \
    PYSPARK_PYTHON="/usr/local/bin/python3"

# 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"]