1.在hadoop所在目录“usr/local”下创建一个文件夹input
root@ubuntu:/usr/local# mkdir input
2.在文件夹input中创建两个文本文件file1.txt和file2.txt，file1.txt中内容是“hello word”,file2.txt中内容是“hello hadoop”、“hello mapreduce”(分两行)。
root@ubuntu:/usr/local# cd input
root@ubuntu:/usr/local/input# echo "hello word" > file1.txt
root@ubuntu:/usr/local/input# echo "hello hadoop" > file2.txt
root@ubuntu:/usr/local/input# echo "hello mapreduce" > file2.txt （hello mapreduce 会覆盖原来写入的hello hadoop ,可以使用gedit编辑file2.txt）
root@ubuntu:/usr/local/input# ls
file1.txt file2.txt
显示文件内容可用：
root@ubuntu:/usr/local/input# more file1.txt
hello word
root@ubuntu:/usr/local/input# more file2.txt
hello mapreduce
hello hadoop
3.在HDFS上创建输入文件夹wc_input,并将本地文件夹input中的两个文本文件上传到集群的wc_input下
root@ubuntu:/usr/local/hadoop-1.2.1# bin/hadoop fs -mkdir wc_input
root@ubuntu:/usr/local/hadoop-1.2.1# bin/hadoop fs -put /usr/local/input/file* wc_input
查看wc_input中的文件：
root@ubuntu:/usr/local/hadoop-1.2.1# bin/hadoop fs -ls wc_input
Found 2 items
-rw-r--r-- 1 root supergroup 11 2014-03-13 01:19 /user/root/wc_input/file1.txt
-rw-r--r-- 1 root supergroup 29 2014-03-13 01:19 /user/root/wc_input/file2.txt
4.启动所有进程并查看进程：
root@ubuntu:/# ssh localhost (用于验证能否实现无密码登陆localhost,如果能会出现下面的信息。否则需要设置具体步骤见http://blog.csdn.net/joe_007/article/details/8298814)
Welcome to Ubuntu 12.04.3 LTS (GNU/Linux 3.2.0-24-generic-pae i686)
* Documentation: https://help.ubuntu.com/
Last login: Mon Mar 3 04:44:23 2014 from localhost
root@ubuntu:~# exit
logout
Connection to localhost closed.
root@ubuntu:/usr/local/hadoop-1.2.1/bin# ./start-all.sh
starting namenode, logging to /usr/local/hadoop-1.2.1/libexec/../logs/hadoop-root-namenode-ubuntu.out
localhost: starting datanode, logging to /usr/local/hadoop-1.2.1/libexec/../logs/hadoop-root-datanode-ubuntu.out
localhost: starting secondarynamenode, logging to /usr/local/hadoop-1.2.1/libexec/../logs/hadoop-root-secondarynamenode-ubuntu.out
starting jobtracker, logging to /usr/local/hadoop-1.2.1/libexec/../logs/hadoop-root-jobtracker-ubuntu.out
localhost: starting tasktracker, logging to /usr/local/hadoop-1.2.1/libexec/../logs/hadoop-root-tasktracker-ubuntu.out
root@ubuntu:/usr/local/hadoop-1.2.1/bin# jps
7847 SecondaryNameNode
4196
7634 DataNode
7423 NameNode
8319 Jps
7938 JobTracker
8157 TaskTracker
运行hadoop自带的wordcount jar包(注：再次运行时一定要先将前一次运行的输出文件夹删除)
root@ubuntu:/usr/local/hadoop-1.2.1# bin/hadoop jar ./hadoop-examples-1.2.1.jar wordcount wc_input wc_output
14/03/13 01:48:40 INFO input.FileInputFormat: Total input paths to process : 2
14/03/13 01:48:40 INFO util.NativeCodeLoader: Loaded the native-hadoop library
14/03/13 01:48:40 WARN snappy.LoadSnappy: Snappy native library not loaded
14/03/13 01:48:42 INFO mapred.JobClient: Running job: job_201403130031_0001
14/03/13 01:48:44 INFO mapred.JobClient: map 0% reduce 0%
14/03/13 01:52:47 INFO mapred.JobClient: map 50% reduce 0%
14/03/13 01:53:50 INFO mapred.JobClient: map 100% reduce 0%
14/03/13 01:54:14 INFO mapred.JobClient: map 100% reduce 100%
... ...
5.查看输出文件夹
root@ubuntu:/usr/local/hadoop-1.2.1# bin/hadoop fs -ls wc_output
Found 3 items
-rw-r--r-- 1 root supergroup 0 2014-03-13 01:54 /user/root/wc_output/_SUCCESS
drwxr-xr-x - root supergroup 0 2014-03-13 01:48 /user/root/wc_output/_logs
-rw-r--r-- 1 root supergroup 36 2014-03-13 01:54 /user/root/wc_output/part-r-00000 (实际输出结果在part-r-00000中)
6.查看输出文件part-r-00000中的内容
root@ubuntu:/usr/local/hadoop-1.2.1# bin/hadoop fs -cat /user/root/wc_output/part-r-00000
hadoop 1
hello 3
mapreduce 1
word 1
7.关闭所有进程
root@ubuntu:/usr/local/hadoop-1.2.1/bin# ./stop-all.sh
stopping jobtracker
localhost: stopping tasktracker
stopping namenode
localhost: stopping datanode
localhost: stopping secondarynamenode