使用docker快速搭建Spark集群的方法教程

 npm install http-server -g
 http-server -p 54321 ~/Downloads

FROM centos:7
MAINTAINER RavenZZ <raven.zhu@outlook.com>

# 安装系统工具
RUN yum update -y
RUN yum upgrade -y
RUN yum install -y byobu curl htop man unzip nano wget
RUN yum clean all

# 安装 Java
ENV JDK_VERSION 8u11
ENV JDK_BUILD_VERSION b12
# 如果网速快,可以直接从源站下载
#RUN curl -LO "http://download.oracle.com/otn-pub/java/jdk/$JDK_VERSION-$JDK_BUILD_VERSION/jdk-$JDK_VERSION-linux-x64.rpm" -H 'Cookie: oraclelicense=accept-securebackup-cookie' && rpm -i jdk-$JDK_VERSION-linux-x64.rpm; rm -f jdk-$JDK_VERSION-linux-x64.rpm;
RUN curl -LO "http://192.168.199.102:54321/jdk-8u11-linux-x64.rpm" && rpm -i jdk-$JDK_VERSION-linux-x64.rpm; rm -f jdk-$JDK_VERSION-linux-x64.rpm;
ENV JAVA_HOME /usr/java/default
RUN yum remove curl; yum clean all
WORKDIR spark

RUN \
 curl -LO 'http://192.168.199.102:54321/spark-2.1.0-bin-hadoop2.7.tgz' && \
 tar zxf spark-2.1.0-bin-hadoop2.7.tgz

RUN rm -rf spark-2.1.0-bin-hadoop2.7.tgz
RUN mv spark-2.1.0-bin-hadoop2.7/* ./

ENV SPARK_HOME /spark
ENV PATH /spark/bin:$PATH
ENV PATH /spark/sbin:$PATH

FROM ravenzz/spark-hadoop

MAINTAINER RavenZZ <raven.zhu@outlook.com>

COPY master.sh /

ENV SPARK_MASTER_PORT 7077
ENV SPARK_MASTER_WEBUI_PORT 8080
ENV SPARK_MASTER_LOG /spark/logs

EXPOSE 8080 7077 6066

CMD ["/bin/bash","/master.sh"]

 FROM ravenzz/spark-hadoop

 MAINTAINER RavenZZ <raven.zhu@outlook.com> 
 COPY worker.sh /

 ENV SPARK_WORKER_WEBUI_PORT 8081
 ENV SPARK_WORKER_LOG /spark/logs
 ENV SPARK_MASTER "spark://spark-master:32769"

 EXPOSE 8081

 CMD ["/bin/bash","/worker.sh"]

 version: '3'

services:
 spark-master:
 build:
 context: ./master
 dockerfile: Dockerfile
 ports:
 - "50001:6066"
 - "50002:7077" # SPARK_MASTER_PORT
 - "50003:8080" # SPARK_MASTER_WEBUI_PORT
 expose:
 - 7077

 spark-worker1:
 build:
 context: ./worker
 dockerfile: Dockerfile
 ports:
 - "50004:8081"
 links:
 - spark-master
 environment:
 - SPARK_MASTER=spark://spark-master:7077

 spark-worker2:
 build:
 context: ./worker
 dockerfile: Dockerfile
 ports:
 - "50005:8081"
 links:
 - spark-master
 environment:
 - SPARK_MASTER=spark://spark-master:7077

docker-compose up