docker-hadoop环境

一直在间断的玩hadoop，方便随时环境迁移，利用docker搭建的三种hadoop环境，方便随时玩。不逼逼了，直接上源码

githup链接

本地Dockerfile

FROM registry.cn-beijing.aliyuncs.com/douguohai/centos8-jdk8:v2

MAINTAINER douguohai 


# 下载源码包 、解压包 安装 which
COPY ../hadoop-2.9.2.tar.gz /usr/local/

ENV HADOOP_HOME=/usr/local/hadoop-2.9.2
ENV PATH=${PATH}:${HADOOP_HOME}/bin:

RUN yum clean all && yum -y update && yum -y install which && yum clean all && cd /usr/local/ &&tar -xvf  hadoop-2.9.2.tar.gz && rm -rf hadoop-2.9.2.tar.gz && cd hadoop-2.9.2 \
&& mkdir input && cp etc/hadoop/*.xml input/ && bin/hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.9.2.jar grep input output 'dfs[a-z.]+' && cat output/* \
&& echo "export HADOOP_HOME=${HADOOP_HOME}" >>/etc/profile && echo "export PATH=${PATH}:${HADOOP_HOME}/bin:">>/etc/profile

# 工作空间
WORKDIR /usr/local/hadoop-2.9.2

# 跑测试代码
CMD ["bash"]

伪分布式Dockerfile

FROM centos8-ssh-java:v1

MAINTAINER douguohai 


# 下载源码包 、解压包 安装 which
# COPY hadoop-2.9.2.tar.gz /usr/local/
COPY entrypoint.sh /usr/local/bin/entrypoint.sh

ENV HADOOP_HOME=/usr/local/hadoop-2.9.2
ENV PATH=${PATH}:${HADOOP_HOME}/bin:

RUN wget -P /usr/local/ https://code.aliyun.com/douguohai/sourcepack/raw/6414d2419c9f7c01648eccafa19de265090162fd/hadoop-2.9.2.tar.gz \

&&  yum clean all && yum -y update && yum -y install which  && yum clean all && cd /usr/local/ \

&&tar -xvf  hadoop-2.9.2.tar.gz && rm -rf hadoop-2.9.2.tar.gz && rm -rf /usr/local/hadoop-2.9.2/share/doc && cd hadoop-2.9.2 \

&& echo "export HADOOP_HOME=${HADOOP_HOME}" >>/etc/profile && echo "export PATH=${PATH}:${HADOOP_HOME}/bin:">>/etc/profile \

&& chmod +x /usr/local/bin/entrypoint.sh

COPY ./hadoop-2.9.2/etc/hadoop/core-site.xml /usr/local/hadoop-2.9.2/etc/hadoop/core-site.xml
COPY ./hadoop-2.9.2/etc/hadoop/hadoop-env.sh /usr/local/hadoop-2.9.2/etc/hadoop/hadoop-env.sh
COPY ./hadoop-2.9.2/etc/hadoop/hdfs-site.xml /usr/local/hadoop-2.9.2/etc/hadoop/hdfs-site.xml
COPY ./hadoop-2.9.2/etc/hadoop/mapred-site.xml /usr/local/hadoop-2.9.2/etc/hadoop/mapred-site.xml
COPY ./hadoop-2.9.2/etc/hadoop/yarn-env.sh /usr/local/hadoop-2.9.2/etc/hadoop/yarn-env.sh
COPY ./hadoop-2.9.2/etc/hadoop/yarn-site.xml /usr/local/hadoop-2.9.2/etc/hadoop/yarn-site.xml

# 工作空间
WORKDIR /usr/local/hadoop-2.9.2

ENTRYPOINT ["sh", "/usr/local/bin/entrypoint.sh"]

EXPOSE 50070
EXPOSE 8088

# 跑测试代码
CMD ["/bin/bash"]

完全分布式 docker-compose

# yaml 配置实例
version: '3'
services:
  hadoop-master:
   image: registry.cn-beijing.aliyuncs.com/douguohai/hadoop-distributed-master:v1
   container_name: hadoop-master
   ports:
    - "50070:50070"
    - "8088:8088"
   networks:
    mynetwork:
     ipv4_address: 199.18.0.2
   environment:
    HOSTNAME: hadoop-master
   depends_on:
    - hadoop-slave3
    - hadoop-slave4
    - hadoop-slave5
  hadoop-slave3:
   image: registry.cn-beijing.aliyuncs.com/douguohai/hadoop-distributed-slave:v1
   container_name: hadoop-slave3
   networks:
    mynetwork:
     ipv4_address: 199.18.0.3
   environment:
    HOSTNAME: hadoop-slave3
  hadoop-slave4:
   image: registry.cn-beijing.aliyuncs.com/douguohai/hadoop-distributed-slave:v1
   container_name: hadoop-slave4
   networks:
    mynetwork:
     ipv4_address: 199.18.0.4
   environment:
    HOSTNAME: hadoop-slave4
  hadoop-slave5:
   image: registry.cn-beijing.aliyuncs.com/douguohai/hadoop-distributed-slave:v1
   container_name: hadoop-slave5
   networks:
    mynetwork:
     ipv4_address: 199.18.0.5
   environment:
    HOSTNAME: hadoop-slave5
networks:
 mynetwork:
  ipam:
   config:
    - subnet: 199.18.0.0/16