使用Docker运行hadoop

sudo docker pull sequenceiq/hadoop-docker:2.7.0

sudo docker run -it --name hadoop --rm sequenceiq/hadoop-docker:2.7.0 /etc/bootstrap.sh -bash

# 先看一下是否测试数据已经存在
$ bin/hdfs dfs -ls /user/root/input

# 运行作业
$ bin/hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-*.jar grep input output 'dfs[a-z.]+'

# 查看作业执行结果
$ bin/hdfs dfs -cat output/*

# 清空执行结果
$ bin/hdfs dfs -rm output/*
$ bin/hdfs dfs -rmdir output/