kubernetes/examples/spark/images/base/Dockerfile

40 lines
1.4 KiB
Docker

FROM java:openjdk-8-jdk
ENV hadoop_ver 2.6.1
ENV spark_ver 1.5.1
# Get Hadoop from US Apache mirror and extract just the native
# libs. (Until we care about running HDFS with these containers, this
# is all we need.)
RUN mkdir -p /opt && \
cd /opt && \
curl http://www.us.apache.org/dist/hadoop/common/hadoop-${hadoop_ver}/hadoop-${hadoop_ver}.tar.gz | \
tar -zx hadoop-${hadoop_ver}/lib/native && \
ln -s hadoop-${hadoop_ver} hadoop && \
echo Hadoop ${hadoop_ver} native libraries installed in /opt/hadoop/lib/native
# Get Spark from US Apache mirror.
RUN mkdir -p /opt && \
cd /opt && \
curl http://www.us.apache.org/dist/spark/spark-${spark_ver}/spark-${spark_ver}-bin-hadoop2.6.tgz | \
tar -zx && \
ln -s spark-${spark_ver}-bin-hadoop2.6 spark && \
echo Spark ${spark_ver} installed in /opt
# Add the GCS connector.
RUN cd /opt/spark/lib && \
curl -O https://storage.googleapis.com/hadoop-lib/gcs/gcs-connector-latest-hadoop2.jar
# if numpy is installed on a driver it needs to be installed on all
# workers, so install it everywhere
RUN apt-get update && \
apt-get install -y python-numpy && \
apt-get clean && \
rm -rf /var/lib/apt/lists/*
ADD log4j.properties /opt/spark/conf/log4j.properties
ADD start-common.sh /
ADD core-site.xml /opt/spark/conf/core-site.xml
ADD spark-defaults.conf /opt/spark/conf/spark-defaults.conf
ENV PATH $PATH:/opt/spark/bin