SparkLE/docker/hibench-kube/Dockerfile

FROM pl4tinum/spark-kube:3.0

USER root

RUN apt -y update
RUN mkdir -p /usr/share/man/man1
RUN apt -y install git bc wget vim maven scala python2.7 build-essential software-properties-common
RUN wget -qO - https://adoptopenjdk.jfrog.io/adoptopenjdk/api/gpg/key/public | apt-key add -
RUN add-apt-repository --yes https://adoptopenjdk.jfrog.io/adoptopenjdk/deb/
RUN apt update
RUN apt install adoptopenjdk-8-hotspot


WORKDIR /
RUN git clone https://github.com/Intel-bigdata/HiBench.git
WORKDIR /HiBench
ENV JAVA_HOME=/usr/lib/jvm/adoptopenjdk-8-hotspot-amd64
RUN mvn -Psparkbench -Dspark=3.0 -Dhadoop=2.7 -Dscala=2.12 clean package
ENV HIBENCH_HOME=/HiBench

WORKDIR /usr/local

RUN wget https://archive.apache.org/dist/hadoop/common/hadoop-2.7.4/hadoop-2.7.4.tar.gz
RUN tar xzvf hadoop-2.7.4.tar.gz
RUN mv hadoop-2.7.4 hadoop
ENV HADOOP_HOME=/usr/local/hadoop
ENV HADOOP_INSTALL=/usr/local/hadoop
ENV HADOOP_PREFIX /usr/local/hadoop
ENV HADOOP_COMMON_HOME /usr/local/hadoop
ENV HADOOP_HDFS_HOME /usr/local/hadoop
ENV HADOOP_MAPRED_HOME /usr/local/hadoop
ENV HADOOP_YARN_HOME /usr/local/hadoop
ENV HADOOP_CONF_DIR /usr/local/hadoop/etc/hadoop
ENV HADOOP_EXAMPLES_JAR=/usr/local/hadoop/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.4.jar
ENV JAVA_HOME=/usr/local/openjdk-8/
ENV PATH=$PATH:$JAVA_HOME/bin:$HADOOP_HOME/bin
RUN rm ${HADOOP_CONF_DIR}/core-site.xml

RUN mkdir /root/.kube
COPY config /root/.kube/config
COPY conf/core-site-nfs.xml /usr/local/hadoop/etc/hadoop/core-site.xml
COPY conf/hadoop-nfs.conf /HiBench/conf/hadoop.conf
COPY conf/spark.conf /HiBench/conf/spark.conf

WORKDIR /
RUN git clone https://github.com/opcm/pcm.git
WORKDIR /pcm
RUN make

WORKDIR /
COPY entrypoint.sh /entrypoint.sh
RUN chmod ugo+x /entrypoint.sh

COPY 

RUN mkdir /results

ENTRYPOINT ["/entrypoint.sh"]