具体的官网链接为:https://hadoop.apache.org/docs/r2.10.0/hadoop-project-dist/hadoop-common/SingleCluster.html
官方Grep案例
[root@iZbp1efx14jd8471u20gpaZ hadoop-2.7.2]# mkdir input [root@iZbp1efx14jd8471u20gpaZ hadoop-2.7.2]# cp etc/hadoop/*.xml input [root@iZbp1efx14jd8471u20gpaZ hadoop-2.7.2]# bin/hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.2.jar grep input output 'dfs[a-z.]+' 20/01/13 21:56:11 INFO Configuration.deprecation: session.id is deprecated. Instead, use dfs.metrics.session-id 20/01/13 21:56:11 INFO jvm.JvmMetrics: Initializing JVM Metrics with processName=JobTracker, sessionId= 20/01/13 21:56:12 INFO input.FileInputFormat: Total input paths to process : 8 20/01/13 21:56:12 INFO mapreduce.JobSubmitter: number of splits:8 20/01/13 21:56:12 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_local1665352450_0001 20/01/13 21:56:12 INFO mapreduce.Job: The url to track the job: http://localhost:8080/ 20/01/13 21:56:12 INFO mapreduce.Job: Running job: job_local1665352450_0001
[root@iZbp1efx14jd8471u20gpaZ hadoop-2.7.2]# ll total 60 drwxr-xr-x 2 root root 4096 May 22 2017 bin drwxr-xr-x 3 root root 4096 May 22 2017 etc drwxr-xr-x 2 root root 4096 May 22 2017 include drwxr-xr-x 2 root root 4096 Jan 13 21:55 input drwxr-xr-x 3 root root 4096 May 22 2017 lib drwxr-xr-x 2 root root 4096 May 22 2017 libexec -rw-r--r-- 1 root root 15429 May 22 2017 LICENSE.txt -rw-r--r-- 1 root root 101 May 22 2017 NOTICE.txt drwxr-xr-x 2 root root 4096 Jan 13 21:56 output -rw-r--r-- 1 root root 1366 May 22 2017 README.txt drwxr-xr-x 2 root root 4096 May 22 2017 sbin drwxr-xr-x 4 root root 4096 May 22 2017 share [root@iZbp1efx14jd8471u20gpaZ hadoop-2.7.2]# cd output/ [root@iZbp1efx14jd8471u20gpaZ output]# ll total 4 -rw-r--r-- 1 root root 11 Jan 13 21:56 part-r-00000 -rw-r--r-- 1 root root 0 Jan 13 21:56 _SUCCESS [root@iZbp1efx14jd8471u20gpaZ output]# cat part-r-00000 1 dfsadmin
官方WordCount案例
root@iZbp1efx14jd8471u20gpaZ hadoop-2.7.2]# mkdir wcinput [root@iZbp1efx14jd8471u20gpaZ hadoop-2.7.2]# cd wcinput [root@iZbp1efx14jd8471u20gpaZ wcinput]# touch wc.input [root@iZbp1efx14jd8471u20gpaZ wcinput]# vi wc.input [root@iZbp1efx14jd8471u20gpaZ wcinput]# cd .. [root@iZbp1efx14jd8471u20gpaZ hadoop-2.7.2]# ll total 64 drwxr-xr-x 2 root root 4096 May 22 2017 bin drwxr-xr-x 3 root root 4096 May 22 2017 etc drwxr-xr-x 2 root root 4096 May 22 2017 include drwxr-xr-x 2 root root 4096 Jan 13 21:55 input drwxr-xr-x 3 root root 4096 May 22 2017 lib drwxr-xr-x 2 root root 4096 May 22 2017 libexec -rw-r--r-- 1 root root 15429 May 22 2017 LICENSE.txt -rw-r--r-- 1 root root 101 May 22 2017 NOTICE.txt drwxr-xr-x 2 root root 4096 Jan 13 21:56 output -rw-r--r-- 1 root root 1366 May 22 2017 README.txt drwxr-xr-x 2 root root 4096 May 22 2017 sbin drwxr-xr-x 4 root root 4096 May 22 2017 share drwxr-xr-x 2 root root 4096 Jan 13 22:30 wcinput [root@iZbp1efx14jd8471u20gpaZ hadoop-2.7.2]# hadoop jar share/hadoop/mapreduce/hadoop-mapreduce-examples-2.7.2.jar wordcount wcinput wcoutput 20/01/13 22:30:43 INFO Configuration.deprecation: session.id is deprecated. Instead, use dfs.metrics.session-id 20/01/13 22:30:43 INFO jvm.JvmMetrics: Initializing JVM Metrics with processName=JobTracker, sessionId= 20/01/13 22:30:44 INFO input.FileInputFormat: Total input paths to process : 1 20/01/13 22:30:44 INFO mapreduce.JobSubmitter: number of splits:1 20/01/13 22:30:44 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_local981224535_0001
[root@iZbp1efx14jd8471u20gpaZ hadoop-2.7.2]# cat wcoutput/part-r-00000 hadoop 2 mapreduce 1 topcheer 2 yarn 1 [root@iZbp1efx14jd8471u20gpaZ hadoop-2.7.2]# cat wcinput/wc.input bin/ include/ lib/ LICENSE.txt output/ sbin/ wcinput/ etc/ input/ libexec/ NOTICE.txt README.txt share/ wcoutput/ [root@iZbp1efx14jd8471u20gpaZ hadoop-2.7.2]# cat wcinput/wc.input hadoop yarn hadoop mapreduce topcheer topcheer [root@iZbp1efx14jd8471u20gpaZ hadoop-2.7.2]#