sudo docker pull donaldding/donaldding/hadoop-pypip:1.0
git clone https://github.com/donalddinglt/docker_hadoop_with_pypip3.git
sudo docker network create --driver=bridge hadoop
cd hadoop-cluster-docker
sudo ./start-container.sh
output:
start hadoop-master container...
start hadoop-slave1 container...
start hadoop-slave2 container...
root@hadoop-master:~#
- start 3 containers with 1 master and 2 slaves
- you will get into the /root directory of hadoop-master container
./start-hadoop.sh
./run-wordcount.sh
output
input file1.txt:
Hello Hadoop
input file2.txt:
Hello Docker
wordcount output:
Docker 1
Hadoop 1
Hello 2
do 1~3 like section A
sudo ./resize-cluster.sh 5
- specify parameter > 1: 2, 3..
- this script just rebuild hadoop image with different slaves file, which pecifies the name of all slave nodes
sudo ./start-container.sh 5
- use the same parameter as the step 2
do 5~6 like section A