|
|
推荐
MapReduce分析明星微博数据
http://git.oschina.net/ljc520313/codeexample/tree/master/bigdata/hadoop/mapreduce/05.%E6%98%8E%E6%98%9F%E5%BE%AE%E5%8D%9A%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90?dir=1&filepath=bigdata%2Fhadoop%2Fmapreduce%2F05.%E6%98%8E%E6%98%9F%E5%BE%AE%E5%8D%9A%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90&oid=854b4300ccc9fbae894f2f8c29df3ca06193f97b&sha=79a86bf0ff190e38a133bc2446b6b4ad9490f40f
这篇博客，给大家，体会不一样的版本编程。
执行
2016-12-12 15:07:51,762 INFO [org.apache.hadoop.metrics.jvm.JvmMetrics] - Initializing JVM Metrics with processName=JobTracker, sessionId=
2016-12-12 15:07:52,197 WARN [org.apache.hadoop.mapreduce.JobSubmitter] - Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
2016-12-12 15:07:52,199 WARN [org.apache.hadoop.mapreduce.JobSubmitter] - No job jar file set. User> 2016-12-12 15:07:52,216 INFO [org.apache.hadoop.mapreduce.lib.input.FileInputFormat] - Total input paths to process : 1
2016-12-12 15:07:52,265 INFO [org.apache.hadoop.mapreduce.JobSubmitter] - number of splits:1
2016-12-12 15:07:52,541 INFO [org.apache.hadoop.mapreduce.JobSubmitter] - Submitting tokens for job: job_local1414008937_0001
2016-12-12 15:07:53,106 INFO [org.apache.hadoop.mapreduce.Job] - The url to track the job: http://localhost:8080/
2016-12-12 15:07:53,107 INFO [org.apache.hadoop.mapreduce.Job] - Running job: job_local1414008937_0001
2016-12-12 15:07:53,114 INFO [org.apache.hadoop.mapred.LocalJobRunner] - OutputCommitter set in config null
2016-12-12 15:07:53,128 INFO [org.apache.hadoop.mapred.LocalJobRunner] - OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
2016-12-12 15:07:53,203 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Waiting for map tasks
2016-12-12 15:07:53,216 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local1414008937_0001_m_000000_0
2016-12-12 15:07:53,271 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:07:53,374 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@65f3724c
2016-12-12 15:07:53,382 INFO [org.apache.hadoop.mapred.MapTask] - Processing split: file:/D:/Code/MyEclipseJavaCode/myMapReduce/data/Weibodata.txt:0+174116
2016-12-12 15:07:53,443 INFO [org.apache.hadoop.mapred.MapTask] - (EQUATOR) 0 kvi 26214396(104857584)
2016-12-12 15:07:53,443 INFO [org.apache.hadoop.mapred.MapTask] - mapreduce.task.io.sort.mb: 100
2016-12-12 15:07:53,443 INFO [org.apache.hadoop.mapred.MapTask] - soft limit at 83886080
2016-12-12 15:07:53,444 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufvoid = 104857600
2016-12-12 15:07:53,444 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396; length = 6553600
2016-12-12 15:07:53,450 INFO [org.apache.hadoop.mapred.MapTask] - Map output collector> 2016-12-12 15:07:54,110 INFO [org.apache.hadoop.mapreduce.Job] - Job job_local1414008937_0001 running in uber mode : false
2016-12-12 15:07:54,112 INFO [org.apache.hadoop.mapreduce.Job] - map 0% reduce 0%
2016-12-12 15:07:55,068 INFO [org.apache.hadoop.mapred.LocalJobRunner] -
2016-12-12 15:07:55,068 INFO [org.apache.hadoop.mapred.MapTask] - Starting flush of map output
2016-12-12 15:07:55,068 INFO [org.apache.hadoop.mapred.MapTask] - Spilling map output
2016-12-12 15:07:55,068 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufend = 747379; bufvoid = 104857600
2016-12-12 15:07:55,068 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396(104857584); kvend = 26101152(104404608); length = 113245/6553600
count___________1065
2016-12-12 15:07:55,674 INFO [org.apache.hadoop.mapred.MapTask] - Finished spill 0
2016-12-12 15:07:55,685 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local1414008937_0001_m_000000_0 is done. And is in the process of committing
2016-12-12 15:07:55,706 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map
2016-12-12 15:07:55,706 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local1414008937_0001_m_000000_0' done.
2016-12-12 15:07:55,706 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local1414008937_0001_m_000000_0
2016-12-12 15:07:55,707 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map task executor complete.
2016-12-12 15:07:55,714 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Waiting for reduce tasks
2016-12-12 15:07:55,714 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local1414008937_0001_r_000000_0
2016-12-12 15:07:55,727 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:07:55,754 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@24a11405
2016-12-12 15:07:55,758 INFO [org.apache.hadoop.mapred.ReduceTask] - Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@12efdb85
2016-12-12 15:07:55,776 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - MergerManager: memoryLimit=1327077760, maxSingleShuffleLimit=331769440, mergeThreshold=875871360, ioSortFactor=10, memToMemMergeOutputsThreshold=10
2016-12-12 15:07:55,778 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - attempt_local1414008937_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events
2016-12-12 15:07:55,810 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#1 about to shuffle output of map attempt_local1414008937_0001_m_000000_0 decomp: 222260 len: 222264 to MEMORY
2016-12-12 15:07:55,818 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 222260 bytes from map-output for attempt_local1414008937_0001_m_000000_0
2016-12-12 15:07:55,863 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of> 2016-12-12 15:07:55,865 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - EventFetcher is interrupted.. Returning
2016-12-12 15:07:55,866 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2016-12-12 15:07:55,867 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs
2016-12-12 15:07:55,876 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
2016-12-12 15:07:55,876 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total> 2016-12-12 15:07:55,952 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merged 1 segments, 222260 bytes to disk to satisfy reduce memory limit
2016-12-12 15:07:55,953 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 1 files, 222264 bytes from disk
2016-12-12 15:07:55,954 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 0 segments, 0 bytes from memory into reduce
2016-12-12 15:07:55,955 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
2016-12-12 15:07:55,987 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total> 2016-12-12 15:07:55,989 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2016-12-12 15:07:55,994 INFO [org.apache.hadoop.conf.Configuration.deprecation] - mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
2016-12-12 15:07:56,124 INFO [org.apache.hadoop.mapreduce.Job] - map 100% reduce 0%
2016-12-12 15:07:56,347 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local1414008937_0001_r_000000_0 is done. And is in the process of committing
2016-12-12 15:07:56,349 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2016-12-12 15:07:56,349 INFO [org.apache.hadoop.mapred.Task] - Task attempt_local1414008937_0001_r_000000_0 is allowed to commit now
2016-12-12 15:07:56,357 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - Saved output of task 'attempt_local1414008937_0001_r_000000_0' to file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo1/_temporary/0/task_local1414008937_0001_r_000000
2016-12-12 15:07:56,358 INFO [org.apache.hadoop.mapred.LocalJobRunner] - reduce > reduce
2016-12-12 15:07:56,359 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local1414008937_0001_r_000000_0' done.
2016-12-12 15:07:56,359 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local1414008937_0001_r_000000_0
2016-12-12 15:07:56,359 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local1414008937_0001_r_000001_0
2016-12-12 15:07:56,365 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:07:56,391 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@464d02ee
2016-12-12 15:07:56,392 INFO [org.apache.hadoop.mapred.ReduceTask] - Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@69fb7b50
2016-12-12 15:07:56,394 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - MergerManager: memoryLimit=1327077760, maxSingleShuffleLimit=331769440, mergeThreshold=875871360, ioSortFactor=10, memToMemMergeOutputsThreshold=10
2016-12-12 15:07:56,395 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - attempt_local1414008937_0001_r_000001_0 Thread started: EventFetcher for fetching Map Completion Events
2016-12-12 15:07:56,399 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#2 about to shuffle output of map attempt_local1414008937_0001_m_000000_0 decomp: 226847 len: 226851 to MEMORY
2016-12-12 15:07:56,401 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 226847 bytes from map-output for attempt_local1414008937_0001_m_000000_0
2016-12-12 15:07:56,401 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of> 2016-12-12 15:07:56,402 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - EventFetcher is interrupted.. Returning
2016-12-12 15:07:56,402 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2016-12-12 15:07:56,402 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs
2016-12-12 15:07:56,407 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
2016-12-12 15:07:56,407 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total> 2016-12-12 15:07:56,488 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merged 1 segments, 226847 bytes to disk to satisfy reduce memory limit
2016-12-12 15:07:56,488 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 1 files, 226851 bytes from disk
2016-12-12 15:07:56,489 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 0 segments, 0 bytes from memory into reduce
2016-12-12 15:07:56,489 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
2016-12-12 15:07:56,490 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total> 2016-12-12 15:07:56,491 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2016-12-12 15:07:56,581 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local1414008937_0001_r_000001_0 is done. And is in the process of committing
2016-12-12 15:07:56,584 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2016-12-12 15:07:56,584 INFO [org.apache.hadoop.mapred.Task] - Task attempt_local1414008937_0001_r_000001_0 is allowed to commit now
2016-12-12 15:07:56,591 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - Saved output of task 'attempt_local1414008937_0001_r_000001_0' to file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo1/_temporary/0/task_local1414008937_0001_r_000001
2016-12-12 15:07:56,593 INFO [org.apache.hadoop.mapred.LocalJobRunner] - reduce > reduce
2016-12-12 15:07:56,593 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local1414008937_0001_r_000001_0' done.
2016-12-12 15:07:56,593 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local1414008937_0001_r_000001_0
2016-12-12 15:07:56,593 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local1414008937_0001_r_000002_0
2016-12-12 15:07:56,596 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:07:56,640 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@36d0c62b
2016-12-12 15:07:56,640 INFO [org.apache.hadoop.mapred.ReduceTask] - Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@44824d2a
2016-12-12 15:07:56,641 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - MergerManager: memoryLimit=1327077760, maxSingleShuffleLimit=331769440, mergeThreshold=875871360, ioSortFactor=10, memToMemMergeOutputsThreshold=10
2016-12-12 15:07:56,643 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - attempt_local1414008937_0001_r_000002_0 Thread started: EventFetcher for fetching Map Completion Events
2016-12-12 15:07:56,648 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#3 about to shuffle output of map attempt_local1414008937_0001_m_000000_0 decomp: 224215 len: 224219 to MEMORY
2016-12-12 15:07:56,650 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 224215 bytes from map-output for attempt_local1414008937_0001_m_000000_0
2016-12-12 15:07:56,650 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of> 2016-12-12 15:07:56,651 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - EventFetcher is interrupted.. Returning
2016-12-12 15:07:56,651 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2016-12-12 15:07:56,652 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs
2016-12-12 15:07:56,658 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
2016-12-12 15:07:56,658 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total> 2016-12-12 15:07:56,675 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merged 1 segments, 224215 bytes to disk to satisfy reduce memory limit
2016-12-12 15:07:56,676 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 1 files, 224219 bytes from disk
2016-12-12 15:07:56,676 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 0 segments, 0 bytes from memory into reduce
2016-12-12 15:07:56,676 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
2016-12-12 15:07:56,677 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total> 2016-12-12 15:07:56,678 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2016-12-12 15:07:56,711 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local1414008937_0001_r_000002_0 is done. And is in the process of committing
2016-12-12 15:07:56,714 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2016-12-12 15:07:56,714 INFO [org.apache.hadoop.mapred.Task] - Task attempt_local1414008937_0001_r_000002_0 is allowed to commit now
2016-12-12 15:07:56,725 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - Saved output of task 'attempt_local1414008937_0001_r_000002_0' to file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo1/_temporary/0/task_local1414008937_0001_r_000002
2016-12-12 15:07:56,726 INFO [org.apache.hadoop.mapred.LocalJobRunner] - reduce > reduce
2016-12-12 15:07:56,727 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local1414008937_0001_r_000002_0' done.
2016-12-12 15:07:56,727 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local1414008937_0001_r_000002_0
2016-12-12 15:07:56,727 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local1414008937_0001_r_000003_0
2016-12-12 15:07:56,729 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:07:56,749 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@42ed705f
2016-12-12 15:07:56,750 INFO [org.apache.hadoop.mapred.ReduceTask] - Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@726c8f4c
2016-12-12 15:07:56,751 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - MergerManager: memoryLimit=1327077760, maxSingleShuffleLimit=331769440, mergeThreshold=875871360, ioSortFactor=10, memToMemMergeOutputsThreshold=10
2016-12-12 15:07:56,752 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - attempt_local1414008937_0001_r_000003_0 Thread started: EventFetcher for fetching Map Completion Events
2016-12-12 15:07:56,757 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#4 about to shuffle output of map attempt_local1414008937_0001_m_000000_0 decomp: 14 len: 18 to MEMORY
2016-12-12 15:07:56,758 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 14 bytes from map-output for attempt_local1414008937_0001_m_000000_0
2016-12-12 15:07:56,758 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of> 2016-12-12 15:07:56,759 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - EventFetcher is interrupted.. Returning
2016-12-12 15:07:56,759 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2016-12-12 15:07:56,759 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs
2016-12-12 15:07:56,764 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
2016-12-12 15:07:56,764 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total> 2016-12-12 15:07:56,765 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merged 1 segments, 14 bytes to disk to satisfy reduce memory limit
2016-12-12 15:07:56,765 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 1 files, 18 bytes from disk
2016-12-12 15:07:56,765 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 0 segments, 0 bytes from memory into reduce
2016-12-12 15:07:56,765 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
2016-12-12 15:07:56,766 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total> 2016-12-12 15:07:56,766 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
count___________1065
2016-12-12 15:07:56,770 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local1414008937_0001_r_000003_0 is done. And is in the process of committing
2016-12-12 15:07:56,771 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 1 / 1 copied.
2016-12-12 15:07:56,771 INFO [org.apache.hadoop.mapred.Task] - Task attempt_local1414008937_0001_r_000003_0 is allowed to commit now
2016-12-12 15:07:56,777 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - Saved output of task 'attempt_local1414008937_0001_r_000003_0' to file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo1/_temporary/0/task_local1414008937_0001_r_000003
2016-12-12 15:07:56,778 INFO [org.apache.hadoop.mapred.LocalJobRunner] - reduce > reduce
2016-12-12 15:07:56,778 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local1414008937_0001_r_000003_0' done.
2016-12-12 15:07:56,778 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local1414008937_0001_r_000003_0
2016-12-12 15:07:56,779 INFO [org.apache.hadoop.mapred.LocalJobRunner] - reduce task executor complete.
2016-12-12 15:07:57,127 INFO [org.apache.hadoop.mapreduce.Job] - map 100% reduce 100%
2016-12-12 15:07:57,137 INFO [org.apache.hadoop.mapreduce.Job] - Job job_local1414008937_0001 completed successfully
2016-12-12 15:07:57,186 INFO [org.apache.hadoop.mapreduce.Job] - Counters: 33
File System Counters
FILE: Number of bytes read=4937350
FILE: Number of bytes written=8113860
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
Map-Reduce Framework
Map input records=1065
Map output records=28312
Map output bytes=747379
Map output materialized bytes=673352
Input split bytes=127
Combine input records=28312
Combine output records=23098
Reduce input groups=23098
Reduce shuffle bytes=673352
Reduce input records=23098
Reduce output records=23098
Spilled Records=46196
Shuffled Maps =4
Failed Shuffles=0
Merged Map outputs=4
GC time elapsed (ms)=165
CPU time spent (ms)=0
Physical memory (bytes) snapshot=0
Virtual memory (bytes) snapshot=0
Total committed heap usage (bytes)=1672478720
Shuffle Errors
BAD_ID=0
CONNECTION=0
IO_ERROR=0
WRONG_LENGTH=0
WRONG_MAP=0
WRONG_REDUCE=0
File Input Format Counters
Bytes Read=174116
File Output Format Counters
Bytes Written=585532
执行
2016-12-12 15:10:36,011 INFO [org.apache.hadoop.metrics.jvm.JvmMetrics] - Initializing JVM Metrics with processName=JobTracker, sessionId=
2016-12-12 15:10:36,436 WARN [org.apache.hadoop.mapreduce.JobSubmitter] - Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
2016-12-12 15:10:36,438 WARN [org.apache.hadoop.mapreduce.JobSubmitter] - No job jar file set. User> 2016-12-12 15:10:36,892 INFO [org.apache.hadoop.mapreduce.lib.input.FileInputFormat] - Total input paths to process : 4
2016-12-12 15:10:36,959 INFO [org.apache.hadoop.mapreduce.JobSubmitter] - number of splits:4
2016-12-12 15:10:37,215 INFO [org.apache.hadoop.mapreduce.JobSubmitter] - Submitting tokens for job: job_local564512176_0001
2016-12-12 15:10:37,668 INFO [org.apache.hadoop.mapreduce.Job] - The url to track the job: http://localhost:8080/
2016-12-12 15:10:37,670 INFO [org.apache.hadoop.mapreduce.Job] - Running job: job_local564512176_0001
2016-12-12 15:10:37,672 INFO [org.apache.hadoop.mapred.LocalJobRunner] - OutputCommitter set in config null
2016-12-12 15:10:37,685 INFO [org.apache.hadoop.mapred.LocalJobRunner] - OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
2016-12-12 15:10:37,757 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Waiting for map tasks
2016-12-12 15:10:37,759 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local564512176_0001_m_000000_0
2016-12-12 15:10:37,822 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:10:37,854 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@12633e10
2016-12-12 15:10:37,861 INFO [org.apache.hadoop.mapred.MapTask] - Processing split: file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo1/part-r-00001:0+195718
2016-12-12 15:10:37,924 INFO [org.apache.hadoop.mapred.MapTask] - (EQUATOR) 0 kvi 26214396(104857584)
2016-12-12 15:10:37,924 INFO [org.apache.hadoop.mapred.MapTask] - mapreduce.task.io.sort.mb: 100
2016-12-12 15:10:37,925 INFO [org.apache.hadoop.mapred.MapTask] - soft limit at 83886080
2016-12-12 15:10:37,925 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufvoid = 104857600
2016-12-12 15:10:37,925 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396; length = 6553600
2016-12-12 15:10:37,932 INFO [org.apache.hadoop.mapred.MapTask] - Map output collector> 2016-12-12 15:10:38,401 INFO [org.apache.hadoop.mapred.LocalJobRunner] -
2016-12-12 15:10:38,402 INFO [org.apache.hadoop.mapred.MapTask] - Starting flush of map output
2016-12-12 15:10:38,402 INFO [org.apache.hadoop.mapred.MapTask] - Spilling map output
2016-12-12 15:10:38,402 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufend = 78968; bufvoid = 104857600
2016-12-12 15:10:38,402 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396(104857584); kvend = 26183268(104733072); length = 31129/6553600
2016-12-12 15:10:38,673 INFO [org.apache.hadoop.mapreduce.Job] - Job job_local564512176_0001 running in uber mode : false
2016-12-12 15:10:38,676 INFO [org.apache.hadoop.mapreduce.Job] - map 0% reduce 0%
2016-12-12 15:10:38,724 INFO [org.apache.hadoop.mapred.MapTask] - Finished spill 0
2016-12-12 15:10:38,730 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local564512176_0001_m_000000_0 is done. And is in the process of committing
2016-12-12 15:10:38,744 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map
2016-12-12 15:10:38,744 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local564512176_0001_m_000000_0' done.
2016-12-12 15:10:38,745 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local564512176_0001_m_000000_0
2016-12-12 15:10:38,745 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local564512176_0001_m_000001_0
2016-12-12 15:10:38,748 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:10:38,778 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@43aa735f
2016-12-12 15:10:38,784 INFO [org.apache.hadoop.mapred.MapTask] - Processing split: file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo1/part-r-00002:0+193443
2016-12-12 15:10:38,820 INFO [org.apache.hadoop.mapred.MapTask] - (EQUATOR) 0 kvi 26214396(104857584)
2016-12-12 15:10:38,820 INFO [org.apache.hadoop.mapred.MapTask] - mapreduce.task.io.sort.mb: 100
2016-12-12 15:10:38,820 INFO [org.apache.hadoop.mapred.MapTask] - soft limit at 83886080
2016-12-12 15:10:38,821 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufvoid = 104857600
2016-12-12 15:10:38,821 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396; length = 6553600
2016-12-12 15:10:38,822 INFO [org.apache.hadoop.mapred.MapTask] - Map output collector> 2016-12-12 15:10:39,017 INFO [org.apache.hadoop.mapred.LocalJobRunner] -
2016-12-12 15:10:39,017 INFO [org.apache.hadoop.mapred.MapTask] - Starting flush of map output
2016-12-12 15:10:39,018 INFO [org.apache.hadoop.mapred.MapTask] - Spilling map output
2016-12-12 15:10:39,018 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufend = 78027; bufvoid = 104857600
2016-12-12 15:10:39,018 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396(104857584); kvend = 26183624(104734496); length = 30773/6553600
2016-12-12 15:10:39,157 INFO [org.apache.hadoop.mapred.MapTask] - Finished spill 0
2016-12-12 15:10:39,162 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local564512176_0001_m_000001_0 is done. And is in the process of committing
2016-12-12 15:10:39,166 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map
2016-12-12 15:10:39,166 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local564512176_0001_m_000001_0' done.
2016-12-12 15:10:39,166 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local564512176_0001_m_000001_0
2016-12-12 15:10:39,167 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local564512176_0001_m_000002_0
2016-12-12 15:10:39,171 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:10:39,219 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@405f4f03
2016-12-12 15:10:39,222 INFO [org.apache.hadoop.mapred.MapTask] - Processing split: file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo1/part-r-00000:0+191780
2016-12-12 15:10:39,265 INFO [org.apache.hadoop.mapred.MapTask] - (EQUATOR) 0 kvi 26214396(104857584)
2016-12-12 15:10:39,265 INFO [org.apache.hadoop.mapred.MapTask] - mapreduce.task.io.sort.mb: 100
2016-12-12 15:10:39,265 INFO [org.apache.hadoop.mapred.MapTask] - soft limit at 83886080
2016-12-12 15:10:39,265 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufvoid = 104857600
2016-12-12 15:10:39,265 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396; length = 6553600
2016-12-12 15:10:39,270 INFO [org.apache.hadoop.mapred.MapTask] - Map output collector> 2016-12-12 15:10:39,311 INFO [org.apache.hadoop.mapred.LocalJobRunner] -
2016-12-12 15:10:39,311 INFO [org.apache.hadoop.mapred.MapTask] - Starting flush of map output
2016-12-12 15:10:39,311 INFO [org.apache.hadoop.mapred.MapTask] - Spilling map output
2016-12-12 15:10:39,311 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufend = 77478; bufvoid = 104857600
2016-12-12 15:10:39,312 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396(104857584); kvend = 26183920(104735680); length = 30477/6553600
2016-12-12 15:10:39,360 INFO [org.apache.hadoop.mapred.MapTask] - Finished spill 0
2016-12-12 15:10:39,365 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local564512176_0001_m_000002_0 is done. And is in the process of committing
2016-12-12 15:10:39,368 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map
2016-12-12 15:10:39,369 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local564512176_0001_m_000002_0' done.
2016-12-12 15:10:39,369 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local564512176_0001_m_000002_0
2016-12-12 15:10:39,369 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local564512176_0001_m_000003_0
2016-12-12 15:10:39,372 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:10:39,416 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@4e5497cb
2016-12-12 15:10:39,419 INFO [org.apache.hadoop.mapred.MapTask] - Processing split: file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo1/part-r-00003:0+11
2016-12-12 15:10:39,461 INFO [org.apache.hadoop.mapred.MapTask] - (EQUATOR) 0 kvi 26214396(104857584)
2016-12-12 15:10:39,461 INFO [org.apache.hadoop.mapred.MapTask] - mapreduce.task.io.sort.mb: 100
2016-12-12 15:10:39,461 INFO [org.apache.hadoop.mapred.MapTask] - soft limit at 83886080
2016-12-12 15:10:39,461 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufvoid = 104857600
2016-12-12 15:10:39,462 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396; length = 6553600
2016-12-12 15:10:39,463 INFO [org.apache.hadoop.mapred.MapTask] - Map output collector> 2016-12-12 15:10:39,466 INFO [org.apache.hadoop.mapred.LocalJobRunner] -
2016-12-12 15:10:39,466 INFO [org.apache.hadoop.mapred.MapTask] - Starting flush of map output
2016-12-12 15:10:39,479 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local564512176_0001_m_000003_0 is done. And is in the process of committing
2016-12-12 15:10:39,482 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map
2016-12-12 15:10:39,482 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local564512176_0001_m_000003_0' done.
2016-12-12 15:10:39,482 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local564512176_0001_m_000003_0
2016-12-12 15:10:39,482 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map task executor complete.
2016-12-12 15:10:39,487 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Waiting for reduce tasks
2016-12-12 15:10:39,488 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local564512176_0001_r_000000_0
2016-12-12 15:10:39,497 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:10:39,519 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@6d565f45
2016-12-12 15:10:39,523 INFO [org.apache.hadoop.mapred.ReduceTask] - Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@1f719a8d
2016-12-12 15:10:39,538 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - MergerManager: memoryLimit=1327077760, maxSingleShuffleLimit=331769440, mergeThreshold=875871360, ioSortFactor=10, memToMemMergeOutputsThreshold=10
2016-12-12 15:10:39,541 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - attempt_local564512176_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events
2016-12-12 15:10:39,583 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#1 about to shuffle output of map attempt_local564512176_0001_m_000002_0 decomp: 37768 len: 37772 to MEMORY
2016-12-12 15:10:39,589 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 37768 bytes from map-output for attempt_local564512176_0001_m_000002_0
2016-12-12 15:10:39,638 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of> 2016-12-12 15:10:39,644 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#1 about to shuffle output of map attempt_local564512176_0001_m_000001_0 decomp: 37233 len: 37237 to MEMORY
2016-12-12 15:10:39,646 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 37233 bytes from map-output for attempt_local564512176_0001_m_000001_0
2016-12-12 15:10:39,647 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of> 2016-12-12 15:10:39,652 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#1 about to shuffle output of map attempt_local564512176_0001_m_000000_0 decomp: 37343 len: 37347 to MEMORY
2016-12-12 15:10:39,653 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 37343 bytes from map-output for attempt_local564512176_0001_m_000000_0
2016-12-12 15:10:39,654 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of> 2016-12-12 15:10:39,658 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#1 about to shuffle output of map attempt_local564512176_0001_m_000003_0 decomp: 2 len: 6 to MEMORY
2016-12-12 15:10:39,659 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 2 bytes from map-output for attempt_local564512176_0001_m_000003_0
2016-12-12 15:10:39,660 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of> 2016-12-12 15:10:39,660 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - EventFetcher is interrupted.. Returning
2016-12-12 15:10:39,661 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 4 / 4 copied.
2016-12-12 15:10:39,662 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - finalMerge called with 4 in-memory map-outputs and 0 on-disk map-outputs
2016-12-12 15:10:39,673 INFO [org.apache.hadoop.mapred.Merger] - Merging 4 sorted segments
2016-12-12 15:10:39,674 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 3 segments left of total> 2016-12-12 15:10:39,678 INFO [org.apache.hadoop.mapreduce.Job] - map 100% reduce 0%
2016-12-12 15:10:39,780 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merged 4 segments, 112346 bytes to disk to satisfy reduce memory limit
2016-12-12 15:10:39,781 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 1 files, 112344 bytes from disk
2016-12-12 15:10:39,783 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 0 segments, 0 bytes from memory into reduce
2016-12-12 15:10:39,784 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
2016-12-12 15:10:39,785 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total> 2016-12-12 15:10:39,785 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 4 / 4 copied.
2016-12-12 15:10:39,792 INFO [org.apache.hadoop.conf.Configuration.deprecation] - mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
2016-12-12 15:10:40,343 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local564512176_0001_r_000000_0 is done. And is in the process of committing
2016-12-12 15:10:40,346 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 4 / 4 copied.
2016-12-12 15:10:40,346 INFO [org.apache.hadoop.mapred.Task] - Task attempt_local564512176_0001_r_000000_0 is allowed to commit now
2016-12-12 15:10:40,353 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - Saved output of task 'attempt_local564512176_0001_r_000000_0' to file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo2/_temporary/0/task_local564512176_0001_r_000000
2016-12-12 15:10:40,363 INFO [org.apache.hadoop.mapred.LocalJobRunner] - reduce > reduce
2016-12-12 15:10:40,364 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local564512176_0001_r_000000_0' done.
2016-12-12 15:10:40,364 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local564512176_0001_r_000000_0
2016-12-12 15:10:40,364 INFO [org.apache.hadoop.mapred.LocalJobRunner] - reduce task executor complete.
2016-12-12 15:10:40,678 INFO [org.apache.hadoop.mapreduce.Job] - map 100% reduce 100%
2016-12-12 15:10:40,678 INFO [org.apache.hadoop.mapreduce.Job] - Job job_local564512176_0001 completed successfully
2016-12-12 15:10:40,701 INFO [org.apache.hadoop.mapreduce.Job] - Counters: 33
File System Counters
FILE: Number of bytes read=2579152
FILE: Number of bytes written=1581170
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
Map-Reduce Framework
Map input records=23098
Map output records=23097
Map output bytes=234473
Map output materialized bytes=112362
Input split bytes=528
Combine input records=23097
Combine output records=8774
Reduce input groups=5567
Reduce shuffle bytes=112362
Reduce input records=8774
Reduce output records=5567
Spilled Records=17548
Shuffled Maps =4
Failed Shuffles=0
Merged Map outputs=4
GC time elapsed (ms)=48
CPU time spent (ms)=0
Physical memory (bytes) snapshot=0
Virtual memory (bytes) snapshot=0
Total committed heap usage (bytes)=2114977792
Shuffle Errors
BAD_ID=0
CONNECTION=0
IO_ERROR=0
WRONG_LENGTH=0
WRONG_MAP=0
WRONG_REDUCE=0
File Input Format Counters
Bytes Read=585564
File Output Format Counters
Bytes Written=50762
执行job成功
执行
2016-12-12 15:12:33,225 INFO [org.apache.hadoop.metrics.jvm.JvmMetrics] - Initializing JVM Metrics with processName=JobTracker, sessionId=
2016-12-12 15:12:33,823 WARN [org.apache.hadoop.mapreduce.JobSubmitter] - Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
2016-12-12 15:12:33,824 WARN [org.apache.hadoop.mapreduce.JobSubmitter] - No job jar file set. User> 2016-12-12 15:12:34,364 INFO [org.apache.hadoop.mapreduce.lib.input.FileInputFormat] - Total input paths to process : 4
2016-12-12 15:12:34,410 INFO [org.apache.hadoop.mapreduce.JobSubmitter] - number of splits:4
2016-12-12 15:12:34,729 INFO [org.apache.hadoop.mapreduce.JobSubmitter] - Submitting tokens for job: job_local671371338_0001
2016-12-12 15:12:35,471 INFO [org.apache.hadoop.mapred.LocalDistributedCacheManager] - Creating symlink: \tmp\hadoop-Administrator\mapred\local\1481526755080\part-r-00003 <- D:\Code\MyEclipseJavaCode\myMapReduce/part-r-00003
2016-12-12 15:12:35,516 INFO [org.apache.hadoop.mapred.LocalDistributedCacheManager] - Localized file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo1/part-r-00003 as file:/tmp/hadoop-Administrator/mapred/local/1481526755080/part-r-00003
2016-12-12 15:12:35,521 INFO [org.apache.hadoop.mapred.LocalDistributedCacheManager] - Creating symlink: \tmp\hadoop-Administrator\mapred\local\1481526755081\part-r-00000 <- D:\Code\MyEclipseJavaCode\myMapReduce/part-r-00000
2016-12-12 15:12:35,544 INFO [org.apache.hadoop.mapred.LocalDistributedCacheManager] - Localized file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo2/part-r-00000 as file:/tmp/hadoop-Administrator/mapred/local/1481526755081/part-r-00000
2016-12-12 15:12:35,696 INFO [org.apache.hadoop.mapreduce.Job] - The url to track the job: http://localhost:8080/
2016-12-12 15:12:35,697 INFO [org.apache.hadoop.mapreduce.Job] - Running job: job_local671371338_0001
2016-12-12 15:12:35,703 INFO [org.apache.hadoop.mapred.LocalJobRunner] - OutputCommitter set in config null
2016-12-12 15:12:35,715 INFO [org.apache.hadoop.mapred.LocalJobRunner] - OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
2016-12-12 15:12:35,772 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Waiting for map tasks
2016-12-12 15:12:35,772 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local671371338_0001_m_000000_0
2016-12-12 15:12:35,819 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:12:35,852 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@50b97c8b
2016-12-12 15:12:35,858 INFO [org.apache.hadoop.mapred.MapTask] - Processing split: file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo1/part-r-00001:0+195718
2016-12-12 15:12:35,926 INFO [org.apache.hadoop.mapred.MapTask] - (EQUATOR) 0 kvi 26214396(104857584)
2016-12-12 15:12:35,926 INFO [org.apache.hadoop.mapred.MapTask] - mapreduce.task.io.sort.mb: 100
2016-12-12 15:12:35,926 INFO [org.apache.hadoop.mapred.MapTask] - soft limit at 83886080
2016-12-12 15:12:35,926 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufvoid = 104857600
2016-12-12 15:12:35,927 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396; length = 6553600
2016-12-12 15:12:35,938 INFO [org.apache.hadoop.mapred.MapTask] - Map output collector> ******************
2016-12-12 15:12:36,701 INFO [org.apache.hadoop.mapreduce.Job] - Job job_local671371338_0001 running in uber mode : false
2016-12-12 15:12:36,703 INFO [org.apache.hadoop.mapreduce.Job] - map 0% reduce 0%
2016-12-12 15:12:36,965 INFO [org.apache.hadoop.mapred.LocalJobRunner] -
2016-12-12 15:12:36,966 INFO [org.apache.hadoop.mapred.MapTask] - Starting flush of map output
2016-12-12 15:12:36,966 INFO [org.apache.hadoop.mapred.MapTask] - Spilling map output
2016-12-12 15:12:36,966 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufend = 239755; bufvoid = 104857600
2016-12-12 15:12:36,966 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396(104857584); kvend = 26183268(104733072); length = 31129/6553600
2016-12-12 15:12:37,135 INFO [org.apache.hadoop.mapred.MapTask] - Finished spill 0
2016-12-12 15:12:37,141 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local671371338_0001_m_000000_0 is done. And is in the process of committing
2016-12-12 15:12:37,153 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map
2016-12-12 15:12:37,153 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local671371338_0001_m_000000_0' done.
2016-12-12 15:12:37,154 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local671371338_0001_m_000000_0
2016-12-12 15:12:37,154 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local671371338_0001_m_000001_0
2016-12-12 15:12:37,156 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:12:37,191 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@70849e34
2016-12-12 15:12:37,194 INFO [org.apache.hadoop.mapred.MapTask] - Processing split: file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo1/part-r-00002:0+193443
2016-12-12 15:12:37,229 INFO [org.apache.hadoop.mapred.MapTask] - (EQUATOR) 0 kvi 26214396(104857584)
2016-12-12 15:12:37,229 INFO [org.apache.hadoop.mapred.MapTask] - mapreduce.task.io.sort.mb: 100
2016-12-12 15:12:37,229 INFO [org.apache.hadoop.mapred.MapTask] - soft limit at 83886080
2016-12-12 15:12:37,230 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufvoid = 104857600
2016-12-12 15:12:37,230 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396; length = 6553600
2016-12-12 15:12:37,230 INFO [org.apache.hadoop.mapred.MapTask] - Map output collector> ******************
2016-12-12 15:12:37,601 INFO [org.apache.hadoop.mapred.LocalJobRunner] -
2016-12-12 15:12:37,602 INFO [org.apache.hadoop.mapred.MapTask] - Starting flush of map output
2016-12-12 15:12:37,602 INFO [org.apache.hadoop.mapred.MapTask] - Spilling map output
2016-12-12 15:12:37,602 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufend = 237126; bufvoid = 104857600
2016-12-12 15:12:37,602 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396(104857584); kvend = 26183624(104734496); length = 30773/6553600
2016-12-12 15:12:37,651 INFO [org.apache.hadoop.mapred.MapTask] - Finished spill 0
2016-12-12 15:12:37,683 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local671371338_0001_m_000001_0 is done. And is in the process of committing
2016-12-12 15:12:37,687 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map
2016-12-12 15:12:37,687 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local671371338_0001_m_000001_0' done.
2016-12-12 15:12:37,687 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local671371338_0001_m_000001_0
2016-12-12 15:12:37,687 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local671371338_0001_m_000002_0
2016-12-12 15:12:37,690 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:12:37,722 INFO [org.apache.hadoop.mapreduce.Job] - map 100% reduce 0%
2016-12-12 15:12:37,810 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@544b0d4c
2016-12-12 15:12:37,813 INFO [org.apache.hadoop.mapred.MapTask] - Processing split: file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo1/part-r-00000:0+191780
2016-12-12 15:12:37,851 INFO [org.apache.hadoop.mapred.MapTask] - (EQUATOR) 0 kvi 26214396(104857584)
2016-12-12 15:12:37,851 INFO [org.apache.hadoop.mapred.MapTask] - mapreduce.task.io.sort.mb: 100
2016-12-12 15:12:37,851 INFO [org.apache.hadoop.mapred.MapTask] - soft limit at 83886080
2016-12-12 15:12:37,851 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufvoid = 104857600
2016-12-12 15:12:37,852 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396; length = 6553600
2016-12-12 15:12:37,853 INFO [org.apache.hadoop.mapred.MapTask] - Map output collector> ******************
2016-12-12 15:12:37,915 INFO [org.apache.hadoop.mapred.LocalJobRunner] -
2016-12-12 15:12:37,915 INFO [org.apache.hadoop.mapred.MapTask] - Starting flush of map output
2016-12-12 15:12:37,916 INFO [org.apache.hadoop.mapred.MapTask] - Spilling map output
2016-12-12 15:12:37,916 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufend = 234731; bufvoid = 104857600
2016-12-12 15:12:37,916 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396(104857584); kvend = 26183920(104735680); length = 30477/6553600
2016-12-12 15:12:37,939 INFO [org.apache.hadoop.mapred.MapTask] - Finished spill 0
2016-12-12 15:12:37,943 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local671371338_0001_m_000002_0 is done. And is in the process of committing
2016-12-12 15:12:37,946 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map
2016-12-12 15:12:37,946 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local671371338_0001_m_000002_0' done.
2016-12-12 15:12:37,946 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local671371338_0001_m_000002_0
2016-12-12 15:12:37,947 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local671371338_0001_m_000003_0
2016-12-12 15:12:37,950 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:12:37,999 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@6c241f31
2016-12-12 15:12:38,002 INFO [org.apache.hadoop.mapred.MapTask] - Processing split: file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo1/part-r-00003:0+11
2016-12-12 15:12:38,046 INFO [org.apache.hadoop.mapred.MapTask] - (EQUATOR) 0 kvi 26214396(104857584)
2016-12-12 15:12:38,046 INFO [org.apache.hadoop.mapred.MapTask] - mapreduce.task.io.sort.mb: 100
2016-12-12 15:12:38,046 INFO [org.apache.hadoop.mapred.MapTask] - soft limit at 83886080
2016-12-12 15:12:38,046 INFO [org.apache.hadoop.mapred.MapTask] - bufstart = 0; bufvoid = 104857600
2016-12-12 15:12:38,046 INFO [org.apache.hadoop.mapred.MapTask] - kvstart = 26214396; length = 6553600
2016-12-12 15:12:38,047 INFO [org.apache.hadoop.mapred.MapTask] - Map output collector> ******************
2016-12-12 15:12:38,050 INFO [org.apache.hadoop.mapred.LocalJobRunner] -
2016-12-12 15:12:38,050 INFO [org.apache.hadoop.mapred.MapTask] - Starting flush of map output
2016-12-12 15:12:38,060 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local671371338_0001_m_000003_0 is done. And is in the process of committing
2016-12-12 15:12:38,063 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map
2016-12-12 15:12:38,063 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local671371338_0001_m_000003_0' done.
2016-12-12 15:12:38,064 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local671371338_0001_m_000003_0
2016-12-12 15:12:38,064 INFO [org.apache.hadoop.mapred.LocalJobRunner] - map task executor complete.
2016-12-12 15:12:38,067 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Waiting for reduce tasks
2016-12-12 15:12:38,067 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Starting task: attempt_local671371338_0001_r_000000_0
2016-12-12 15:12:38,079 INFO [org.apache.hadoop.yarn.util.ProcfsBasedProcessTree] - ProcfsBasedProcessTree currently is supported only on Linux.
2016-12-12 15:12:38,104 INFO [org.apache.hadoop.mapred.Task] - Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@777da320
2016-12-12 15:12:38,116 INFO [org.apache.hadoop.mapred.ReduceTask] - Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@76a01b4b
2016-12-12 15:12:38,133 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - MergerManager: memoryLimit=1327077760, maxSingleShuffleLimit=331769440, mergeThreshold=875871360, ioSortFactor=10, memToMemMergeOutputsThreshold=10
2016-12-12 15:12:38,135 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - attempt_local671371338_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events
2016-12-12 15:12:38,165 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#1 about to shuffle output of map attempt_local671371338_0001_m_000001_0 decomp: 252516 len: 252520 to MEMORY
2016-12-12 15:12:38,169 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 252516 bytes from map-output for attempt_local671371338_0001_m_000001_0
2016-12-12 15:12:38,216 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of> 2016-12-12 15:12:38,221 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#1 about to shuffle output of map attempt_local671371338_0001_m_000002_0 decomp: 249973 len: 249977 to MEMORY
2016-12-12 15:12:38,223 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 249973 bytes from map-output for attempt_local671371338_0001_m_000002_0
2016-12-12 15:12:38,224 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of> 2016-12-12 15:12:38,230 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#1 about to shuffle output of map attempt_local671371338_0001_m_000000_0 decomp: 255323 len: 255327 to MEMORY
2016-12-12 15:12:38,233 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 255323 bytes from map-output for attempt_local671371338_0001_m_000000_0
2016-12-12 15:12:38,233 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of> 2016-12-12 15:12:38,235 INFO [org.apache.hadoop.mapreduce.task.reduce.LocalFetcher] - localfetcher#1 about to shuffle output of map attempt_local671371338_0001_m_000003_0 decomp: 2 len: 6 to MEMORY
2016-12-12 15:12:38,236 INFO [org.apache.hadoop.mapreduce.task.reduce.InMemoryMapOutput] - Read 2 bytes from map-output for attempt_local671371338_0001_m_000003_0
2016-12-12 15:12:38,236 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - closeInMemoryFile -> map-output of> 2016-12-12 15:12:38,237 INFO [org.apache.hadoop.mapreduce.task.reduce.EventFetcher] - EventFetcher is interrupted.. Returning
2016-12-12 15:12:38,238 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 4 / 4 copied.
2016-12-12 15:12:38,238 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - finalMerge called with 4 in-memory map-outputs and 0 on-disk map-outputs
2016-12-12 15:12:38,252 INFO [org.apache.hadoop.mapred.Merger] - Merging 4 sorted segments
2016-12-12 15:12:38,253 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 3 segments left of total> 2016-12-12 15:12:38,413 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merged 4 segments, 757814 bytes to disk to satisfy reduce memory limit
2016-12-12 15:12:38,414 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 1 files, 757812 bytes from disk
2016-12-12 15:12:38,415 INFO [org.apache.hadoop.mapreduce.task.reduce.MergeManagerImpl] - Merging 0 segments, 0 bytes from memory into reduce
2016-12-12 15:12:38,415 INFO [org.apache.hadoop.mapred.Merger] - Merging 1 sorted segments
2016-12-12 15:12:38,416 INFO [org.apache.hadoop.mapred.Merger] - Down to the last merge-pass, with 1 segments left of total> 2016-12-12 15:12:38,433 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 4 / 4 copied.
2016-12-12 15:12:38,439 INFO [org.apache.hadoop.conf.Configuration.deprecation] - mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
2016-12-12 15:12:38,844 INFO [org.apache.hadoop.mapred.Task] - Task:attempt_local671371338_0001_r_000000_0 is done. And is in the process of committing
2016-12-12 15:12:38,846 INFO [org.apache.hadoop.mapred.LocalJobRunner] - 4 / 4 copied.
2016-12-12 15:12:38,846 INFO [org.apache.hadoop.mapred.Task] - Task attempt_local671371338_0001_r_000000_0 is allowed to commit now
2016-12-12 15:12:38,857 INFO [org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter] - Saved output of task 'attempt_local671371338_0001_r_000000_0' to file:/D:/Code/MyEclipseJavaCode/myMapReduce/out/weibo3/_temporary/0/task_local671371338_0001_r_000000
2016-12-12 15:12:38,861 INFO [org.apache.hadoop.mapred.LocalJobRunner] - reduce > reduce
2016-12-12 15:12:38,861 INFO [org.apache.hadoop.mapred.Task] - Task 'attempt_local671371338_0001_r_000000_0' done.
2016-12-12 15:12:38,861 INFO [org.apache.hadoop.mapred.LocalJobRunner] - Finishing task: attempt_local671371338_0001_r_000000_0
2016-12-12 15:12:38,862 INFO [org.apache.hadoop.mapred.LocalJobRunner] - reduce task executor complete.
2016-12-12 15:12:39,724 INFO [org.apache.hadoop.mapreduce.Job] - map 100% reduce 100%
2016-12-12 15:12:39,726 INFO [org.apache.hadoop.mapreduce.Job] - Job job_local671371338_0001 completed successfully
2016-12-12 15:12:39,841 INFO [org.apache.hadoop.mapreduce.Job] - Counters: 33
File System Counters
FILE: Number of bytes read=4124093
FILE: Number of bytes written=5365498
FILE: Number of read operations=0
FILE: Number of large read operations=0
FILE: Number of write operations=0
Map-Reduce Framework
Map input records=23098
Map output records=23097
Map output bytes=711612
Map output materialized bytes=757830
Input split bytes=528
Combine input records=0
Combine output records=0
Reduce input groups=1065
Reduce shuffle bytes=757830
Reduce input records=23097
Reduce output records=1065
Spilled Records=46194
Shuffled Maps =4
Failed Shuffles=0
Merged Map outputs=4
GC time elapsed (ms)=30
CPU time spent (ms)=0
Physical memory (bytes) snapshot=0
Virtual memory (bytes) snapshot=0
Total committed heap usage (bytes)=2353528832
Shuffle Errors
BAD_ID=0
CONNECTION=0
IO_ERROR=0
WRONG_LENGTH=0
WRONG_MAP=0
WRONG_REDUCE=0
File Input Format Counters
Bytes Read=585564
File Output Format Counters
Bytes Written=340785
执行job成功
代码
1 package zhouls.bigdata.myMapReduce.weibo;
2
3 import java.io.IOException;
4
5 import java.io.StringReader;
6
7 import org.apache.hadoop.io.IntWritable;
8 import org.apache.hadoop.io.LongWritable;
9 import org.apache.hadoop.io.Text;
10 import org.apache.hadoop.mapreduce.Mapper;
11 import org.wltea.analyzer.core.IKSegmenter;
12 import org.wltea.analyzer.core.Lexeme;
13
14 /**
15 * 第一个MR，计算TF和计算N(微博总数)
16 * @author root
17 *
18 */
19 public>
20
21 protected void map(LongWritable key, Text value,
22 Context context)
23 throws IOException, InterruptedException {
24 // 3823890201582094 今天我约了豆浆，油条。约了电饭煲几小时后饭就自动煮好，还想约豆浆机，让我早晨多睡一小时，豆浆就自然好。起床就可以喝上香喷喷的豆浆了。
25 // 3823890210294392 今天我约了豆浆，油条
26 String[] v =value.toString().trim().split("\t");
27 if(v.length>=2){
28 String>
29 String content =v[1].trim();
30
31 StringReader sr =new StringReader(content);//content是新浪微博内容
32 IKSegmenter ikSegmenter =new IKSegmenter(sr, true);
33 Lexeme word=null;
34 //第一件事情，就是通过IK分词器（IKAnalyzer），把weibo2.txt里 的内容
35 //这里，单独可以去网上找到IKAnalyzer2012_FF.jar。然后像我这样，放到lib下，必须要选中，然后Build Path -> Add Build Path
36
37 while( (word=ikSegmenter.next()) !=null ){
38 String w= word.getLexemeText();//w是词条
39 context.write(new Text(w+"_"+id), new IntWritable(1));
40 }
41 context.write(new Text("count"), new IntWritable(1));
42 }else{
43 System.out.println(value.toString()+"-------------");//为什么要来----------，是因为方便统计TF，因为TF是某一篇微博词条的词频。
44 }
45 }
46
47
48
49 }
1 package zhouls.bigdata.myMapReduce.weibo;
2
3 import org.apache.hadoop.io.IntWritable;
4 import org.apache.hadoop.io.LongWritable;
5 import org.apache.hadoop.io.Text;
6 import org.apache.hadoop.mapreduce.Partitioner;
7 import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;
8
9 /**
10 * 第一个MR自定义分区
11 * @author root
12 *
13 */
14 public>
15
16
17 public int getPartition(Text key, IntWritable value, int reduceCount) {
18 if(key.equals(new Text("count")))
19 return 3;//总共拿4个reduce，其中拿1个reduce去输出微博总数，拿3个reduce去输出微博词频。
20 else
21 return super.getPartition(key, value, reduceCount-1);
22 }
23
24 }
1 package zhouls.bigdata.myMapReduce.weibo;
2
3 import java.io.IOException;
4
5 import org.apache.hadoop.io.IntWritable;
6 import org.apache.hadoop.io.LongWritable;
7 import org.apache.hadoop.io.Text;
8 import org.apache.hadoop.mapreduce.Reducer;
9 /**
10 * c1_001,2
11 * c2_001,1
12 * count,10000
13 * @author root
14 *
15 */
16 public>
17
18 protected void reduce(Text arg0, Iterable<IntWritable> arg1,
19 Context arg2)
20 throws IOException, InterruptedException {
21
22 int sum =0;
23 for( IntWritable i :arg1 ){
24 sum= sum+i.get();
25 }
26 if(arg0.equals(new Text("count"))){
27 System.out.println(arg0.toString() +"___________"+sum);
28 }
29 arg2.write(arg0, new IntWritable(sum));
30 }
31
32 }
1 package zhouls.bigdata.myMapReduce.weibo;
2
3
4 import java.io.IOException;
5
6 import org.apache.hadoop.conf.Configuration;
7 import org.apache.hadoop.fs.FileSystem;
8 import org.apache.hadoop.fs.Path;
9 import org.apache.hadoop.io.IntWritable;
10 import org.apache.hadoop.io.LongWritable;
11 import org.apache.hadoop.io.Text;
12 import org.apache.hadoop.mapred.JobConf;
13 import org.apache.hadoop.mapred.TextInputFormat;
14 import org.apache.hadoop.mapreduce.Job;
15 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
16 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
17
18
19 public>
20
21 public static void main(String[] args) {
22 Configuration config =new Configuration();
23 // config.set("fs.defaultFS", "hdfs://HadoopMaster:9000");
24 // config.set("yarn.resourcemanager.hostname", "HadoopMaster");
25 try {
26 FileSystem fs =FileSystem.get(config);
27 // JobConf job =new JobConf(config);
28 Job job =Job.getInstance(config);
29 job.setJarByClass(FirstJob.class);
30 job.setJobName("weibo1");
31
32 job.setOutputKeyClass(Text.class);
33 job.setOutputValueClass(IntWritable.class);
34 // job.setMapperClass();
35 job.setNumReduceTasks(4);
36 job.setPartitionerClass(FirstPartition.class);
37 job.setMapperClass(FirstMapper.class);
38 job.setCombinerClass(FirstReduce.class);
39 job.setReducerClass(FirstReduce.class);
40
41 //
42 // FileInputFormat.addInputPath(job, new Path("hdfs://HadoopMaster:9000/Weibodata.txt"));//下有数据源，Weibodata.txt
43 //
44 // Path path =new Path("hdfs://HadoopMaster:9000/out/weibo1");
45
46
47 FileInputFormat.addInputPath(job, new Path("./data/weibo/Weibodata.txt"));//下有数据源，Weibodata.txt
48
49 Path path =new Path("./out/weibo1");
50
51
52
53 // part-r-00000
54 // part-r-00001
55 // part-r-00002 拿3个reduce去输出微博词频。
56 // part-r-00003 最后这个是输出微博总数，
57 if(fs.exists(path)){
58 fs.delete(path, true);
59 }
60 FileOutputFormat.setOutputPath(job,path);
61
62 boolean f= job.waitForCompletion(true);
63 if(f){
64
65 }
66 } catch (Exception e) {
67 e.printStackTrace();
68 }
69 }
70 }
1 package zhouls.bigdata.myMapReduce.weibo;
2
3 import java.io.IOException;
4
5 import java.io.StringReader;
6
7 import org.apache.hadoop.io.IntWritable;
8 import org.apache.hadoop.io.LongWritable;
9 import org.apache.hadoop.io.Text;
10 import org.apache.hadoop.mapreduce.Mapper;
11 import org.apache.hadoop.mapreduce.lib.input.FileSplit;
12 import org.wltea.analyzer.core.IKSegmenter;
13 import org.wltea.analyzer.core.Lexeme;
14 //统计df：词在多少个微博中出现过。
15 public>
16
17 protected void map(LongWritable key, Text value, Context context)
18 throws IOException, InterruptedException {
19
20 //获取当前 mapper task的数据片段（split）
21 FileSplit fs = (FileSplit) context.getInputSplit();
22
23 if (!fs.getPath().getName().contains("part-r-00003")) {
24
25 String[] v = value.toString().trim().split("\t");
26 if (v.length >= 2) {
27 String[] ss = v[0].split("_");
28 if (ss.length >= 2) {
29 String w = ss[0];
30 context.write(new Text(w), new IntWritable(1));
31 }
32 } else {
33 System.out.println(value.toString() + "-------------");
34 }
35 }
36
37 }
38 }
1 package zhouls.bigdata.myMapReduce.weibo;
2
3 import java.io.IOException;
4
5 import org.apache.hadoop.io.IntWritable;
6 import org.apache.hadoop.io.LongWritable;
7 import org.apache.hadoop.io.Text;
8 import org.apache.hadoop.mapreduce.Reducer;
9
10 public>
11
12 protected void reduce(Text key, Iterable<IntWritable> arg1,
13 Context context)
14 throws IOException, InterruptedException {
15
16 int sum =0;
17 for( IntWritable i :arg1 ){
18 sum= sum+i.get();
19 }
20
21 context.write(key, new IntWritable(sum));
22 }
23
24 }
1 package zhouls.bigdata.myMapReduce.weibo;
2
3 import java.io.IOException;
4
5 import org.apache.hadoop.conf.Configuration;
6 import org.apache.hadoop.fs.Path;
7 import org.apache.hadoop.io.IntWritable;
8 import org.apache.hadoop.io.LongWritable;
9 import org.apache.hadoop.io.Text;
10 import org.apache.hadoop.mapred.JobConf;
11 import org.apache.hadoop.mapred.TextInputFormat;
12 import org.apache.hadoop.mapreduce.Job;
13 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
14 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
15
16
17 public>
18
19 public static void main(String[] args) {
20 Configuration config =new Configuration();
21 // config.set("fs.defaultFS", "hdfs://HadoopMaster:9000");
22 // config.set("yarn.resourcemanager.hostname", "HadoopMaster");
23 try {
24 // JobConf job =new JobConf(config);
25 Job job =Job.getInstance(config);
26 job.setJarByClass(TwoJob.class);
27 job.setJobName("weibo2");
28 //设置map任务的输出key类型、value类型
29 job.setOutputKeyClass(Text.class);
30 job.setOutputValueClass(IntWritable.class);
31 // job.setMapperClass();
32 job.setMapperClass(TwoMapper.class);
33 job.setCombinerClass(TwoReduce.class);
34 job.setReducerClass(TwoReduce.class);
35
36 //mr运行时的输入数据从hdfs的哪个目录中获取
37 // FileInputFormat.addInputPath(job, new Path("hdfs://HadoopMaster:9000/out/weibo1/"));
38 // FileOutputFormat.setOutputPath(job, new Path("hdfs://HadoopMaster:9000/out/weibo2"));
39
40 FileInputFormat.addInputPath(job, new Path("./out/weibo1/"));
41 FileOutputFormat.setOutputPath(job, new Path("./out/weibo2"));
42
43 boolean f= job.waitForCompletion(true);
44 if(f){
45 System.out.println("执行job成功");
46 }
47 } catch (Exception e) {
48 e.printStackTrace();
49 }
50 }
51 }
1 package zhouls.bigdata.myMapReduce.weibo;
2
3 import java.io.BufferedReader;
4
5 import java.io.File;
6 import java.io.FileInputStream;
7 import java.io.FileReader;
8 import java.io.IOException;
9 import java.io.InputStreamReader;
10 import java.io.StringReader;
11 import java.net.URI;
12 import java.text.NumberFormat;
13 import java.util.HashMap;
14 import java.util.Map;
15
16 import org.apache.hadoop.conf.Configuration;
17 import org.apache.hadoop.fs.FileSystem;
18 import org.apache.hadoop.fs.Path;
19 import org.apache.hadoop.io.IntWritable;
20 import org.apache.hadoop.io.LongWritable;
21 import org.apache.hadoop.io.Text;
22 import org.apache.hadoop.mapreduce.Mapper;
23 import org.apache.hadoop.mapreduce.lib.input.FileSplit;
24 import org.wltea.analyzer.core.IKSegmenter;
25 import org.wltea.analyzer.core.Lexeme;
26
27 /**
28 * 最后计算
29 * @author root
30 *
31 */
32 public>
33 //存放微博总数
34 public static Map<String, Integer> cmap = null;
35 //存放df
36 public static Map<String, Integer> df = null;
37
38 // 在map方法执行之前
39 protected void setup(Context context) throws IOException,
40 InterruptedException {
41 System.out.println("******************");
42 if (cmap == null || cmap.size() == 0 || df == null || df.size() == 0) {
43
44 URI[] ss = context.getCacheFiles();
45 if (ss != null) {
46 for (int i = 0; i < ss.length; i++) {
47 URI uri = ss;
48 if (uri.getPath().endsWith("part-r-00003")) {//微博总数
49 Path path =new Path(uri.getPath());
50 // FileSystem fs =FileSystem.get(context.getConfiguration());
51 // fs.open(path);
52 BufferedReader br = new BufferedReader(new FileReader(path.getName()));
53 String line = br.readLine();
54 if (line.startsWith("count")) {
55 String[] ls = line.split("\t");
56 cmap = new HashMap<String, Integer>();
57 cmap.put(ls[0], Integer.parseInt(ls[1].trim()));
58 }
59 br.close();
60 } else if (uri.getPath().endsWith("part-r-00000")) {//词条的DF
61 df = new HashMap<String, Integer>();
62 Path path =new Path(uri.getPath());
63 BufferedReader br = new BufferedReader(new FileReader(path.getName()));
64 String line;
65 while ((line = br.readLine()) != null) {
66 String[] ls = line.split("\t");
67 df.put(ls[0], Integer.parseInt(ls[1].trim()));
68 }
69 br.close();
70 }
71 }
72 }
73 }
74 }
75
76 protected void map(LongWritable key, Text value, Context context)
77 throws IOException, InterruptedException {
78 FileSplit fs = (FileSplit) context.getInputSplit();
79 // System.out.println("--------------------");
80 if (!fs.getPath().getName().contains("part-r-00003")) {
81
82 String[] v = value.toString().trim().split("\t");
83 if (v.length >= 2) {
84 int tf =Integer.parseInt(v[1].trim());//tf值
85 String[] ss = v[0].split("_");
86 if (ss.length >= 2) {
87 String w = ss[0];
88 String>
89
90 double s=tf * Math.log(cmap.get("count")/df.get(w));
91 NumberFormat nf =NumberFormat.getInstance();
92 nf.setMaximumFractionDigits(5);
93 context.write(new Text(id), new Text(w+":"+nf.format(s)));
94 }
95 } else {
96 System.out.println(value.toString() + "-------------");
97 }
98 }
99 }
100 }
1 package zhouls.bigdata.myMapReduce.weibo;
2
3 import java.io.IOException;
4
5 import org.apache.hadoop.io.IntWritable;
6 import org.apache.hadoop.io.LongWritable;
7 import org.apache.hadoop.io.Text;
8 import org.apache.hadoop.mapreduce.Reducer;
9
10 public>
11
12 protected void reduce(Text key, Iterable<Text> arg1,
13 Context context)
14 throws IOException, InterruptedException {
15
16 StringBuffer sb =new StringBuffer();
17
18 for( Text i :arg1 ){
19 sb.append(i.toString()+"\t");
20 }
21
22 context.write(key, new Text(sb.toString()));
23 }
24
25 }
1 package zhouls.bigdata.myMapReduce.weibo;
2
3 import java.io.IOException;
4
5 import org.apache.hadoop.conf.Configuration;
6 import org.apache.hadoop.filecache.DistributedCache;
7 import org.apache.hadoop.fs.FileSystem;
8 import org.apache.hadoop.fs.Path;
9 import org.apache.hadoop.io.IntWritable;
10 import org.apache.hadoop.io.LongWritable;
11 import org.apache.hadoop.io.Text;
12 import org.apache.hadoop.mapred.JobConf;
13 import org.apache.hadoop.mapred.TextInputFormat;
14 import org.apache.hadoop.mapreduce.Job;
15 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
16 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
17
18
19 public>
20 public static void main(String[] args) {
21 Configuration config =new Configuration();
22 // config.set("fs.defaultFS", "hdfs://HadoopMaster:9000");
23 // config.set("yarn.resourcemanager.hostname", "HadoopMaster");
24 // config.set("mapred.jar", "C:\\Users\\Administrator\\Desktop\\weibo3.jar");
25 try {
26 FileSystem fs =FileSystem.get(config);
27 // JobConf job =new JobConf(config);
28 Job job =Job.getInstance(config);
29 job.setJarByClass(LastJob.class);
30 job.setJobName("weibo3");
31
32 // DistributedCache.addCacheFile(uri, conf);
33 //2.5
34 //把微博总数加载到内存
35 // job.addCacheFile(new Path("hdfs://HadoopMaster:9000/out/weibo1/part-r-00003").toUri());
36 // //把df加载到内存
37 // job.addCacheFile(new Path("hdfs://HadoopMaster:9000/out/weibo2/part-r-00000").toUri());
38
39
40 job.addCacheFile(new Path("./out/weibo1/part-r-00003").toUri());
41 //把df加载到内存
42 job.addCacheFile(new Path("./out/weibo2/part-r-00000").toUri());
43
44
45
46 //设置map任务的输出key类型、value类型
47 job.setOutputKeyClass(Text.class);
48 job.setOutputValueClass(Text.class);
49 // job.setMapperClass();
50 job.setMapperClass(LastMapper.class);
51 job.setReducerClass(LastReduce.class);
52
53 //mr运行时的输入数据从hdfs的哪个目录中获取
54 // FileInputFormat.addInputPath(job, new Path("hdfs://HadoopMaster:9000/out/weibo1"));
55 // Path outpath =new Path("hdfs://HadoopMaster:9000/out/weibo3/");
56
57 FileInputFormat.addInputPath(job, new Path("./out/weibo1"));
58 Path outpath =new Path("./out/weibo3/");
59
60
61 if(fs.exists(outpath)){
62 fs.delete(outpath, true);
63 }
64 FileOutputFormat.setOutputPath(job,outpath );
65
66 boolean f= job.waitForCompletion(true);
67 if(f){
68 System.out.println("执行job成功");
69 }
70 } catch (Exception e) {
71 e.printStackTrace();
72 }
73 }
74 }
1 package zhouls.bigdata.myMapReduce.weibo;
2
3 import java.text.NumberFormat;
4
5 public>
6
7 public static void main(String[] args) {
8 double s=34 * Math.log(1056/5);
9 NumberFormat nf =NumberFormat.getInstance();
10 nf.setMaximumFractionDigits(5);
11 System.out.println(nf.format(s));
12 }
13 }
|
|
QQ群⑧：
窥视卡
雷达卡
发表于 2017-12-18 10:15:12
提升卡
置顶卡
沉默卡
喧嚣卡
变色卡
千斤顶
显身卡