我的wordcount代码：
1 package com.walloce.wordcount; 2 3 import java.io.IOException; 4 import org.apache.hadoop.conf.Configuration; 5 import org.apache.hadoop.conf.Configured; 6 import org.apache.hadoop.fs.FileSystem; 7 import org.apache.hadoop.fs.Path; 8 import org.apache.hadoop.io.IntWritable; 9 import org.apache.hadoop.io.LongWritable; 10 import org.apache.hadoop.io.Text; 11 import org.apache.hadoop.mapreduce.Job; 12 import org.apache.hadoop.mapreduce.Mapper; 13 import org.apache.hadoop.mapreduce.Reducer; 14 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; 15 import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; 16 import org.apache.hadoop.util.Tool; 17 import org.apache.hadoop.util.ToolRunner; 18 19 import com.walloce.wordcount.MyMapReduce.myMap.myReduce; 20 21 public class MyMapReduce extends Configured implements Tool { 22 23 /** 24 * KEYIN LongWritable 传入的key类型(偏移量) 25 * VALUEIN Text 传入的value类型(文本) 26 * KEYOUT 传出的key类型 27 * VALUEOUT 传出的value类型 28 * @author Walloce 29 * 2018 30 */ 31 static class myMap extends Mapper<LongWritable, Text, Text, IntWritable> { 32 //输出结果的key 33 Text text = new Text(); 34 //输出结果的value 35 IntWritable mr_value = new IntWritable(1); 36 37 int line_count = 1; 38 39 @Override 40 protected void map(LongWritable key, Text value, Context context) 41 throws IOException, InterruptedException { 42 43 System.out.println("map阶段开始..."); 44 //将获取的文本类型转为字符串类型 45 String line = value.toString(); 46 47 System.out.println("第 "+ line_count +" 行的字符串的偏移量为：" + key.get()); 48 49 //将的到的一行字符串拆解为多个单词的字符串数组 50 String[] words = line.split(" "); 51 52 //遍历得到的所有word 53 for (String word : words) { 54 text.set(word); 55 context.write(text, mr_value); 56 } 57 line_count++; 58 } 59 60 /** 61 * Text, IntWritable, Text, IntWritable 62 * reduce时输入的key-value和输出的key-value. 63 * eg:(hello,2) 64 * @author Walloce 65 * 2018 66 */ 67 static class myReduce extends Reducer<Text, IntWritable, Text, IntWritable> { 68 69 private IntWritable result = new IntWritable(); 70 71 int reduce_time = 0; 72 73 @Override 74 protected void reduce(Text key, Iterable<IntWritable> values, Context context) 75 throws IOException, InterruptedException { 76 System.out.println("这是第"+ reduce_time +"次reduce"); 77 System.out.println("Reduce阶段开始...."); 78 79 int sum = 0; 80 for (IntWritable value : values) { 81 sum += value.get(); 82 } 83 result.set(sum); 84 context.write(key, result); 85 reduce_time++; 86 } 87 88 } 89 90 } 91 92 public int run(String[] args) throws Exception { 93 94 //hadoop的八股文 95 Configuration conf = this.getConf(); 96 Job job = Job.getInstance(conf, this.getClass().getSimpleName()); 97 //对job进行具体的配置 98 99 //当你本地运行，这个设置可以不写，不会报错 100 //当提价到集群上面运行的时候，这个设置不写，会报类找不到的异常 101 job.setJarByClass(MyMapReduce.class); 102 103 //写一个输入路径 104 Path input = new Path(args[0]); 105 FileInputFormat.addInputPath(job, input); 106 //写一个输出路径 107 Path output = new Path(args[1]); 108 FileOutputFormat.setOutputPath(job, output); 109 110 //执行前先判断输出路径是否存在，存在就删除 111 FileSystem fs = output.getFileSystem(conf); 112 if(fs.exists(output)){ 113 fs.delete(output,true); 114 } 115 116 //设置运行的map类的相关参数 117 job.setMapperClass(myMap.class); 118 job.setMapOutputKeyClass(Text.class); 119 job.setMapOutputValueClass(IntWritable.class); 120 //==============shuffle======================= 121 // job.setCombinerClass(MyCombiner.class); 122 123 124 //==============shuffle======================= 125 //设置运行的Reduce的相关参数 126 job.setReducerClass(myReduce.class); 127 job.setOutputKeyClass(Text.class); 128 job.setOutputValueClass(IntWritable.class); 129 130 boolean isSuccess = job.waitForCompletion(true); 131 132 133 return isSuccess?0:1; 134 } 135 136 public static void main(String[] args) { 137 // TODO Auto-generated method stub 138 Configuration conf = new Configuration(); 139 args = new String[]{ 140 "hdfs://bigdata-study-104:8020/testdata/word.txt", 141 "hdfs://bigdata-study-104:8020/testresult/output/" 142 }; 143 144 try { 145 ToolRunner.run(conf, new MyMapReduce(), args); 146 } catch (Exception e) { 147 // TODO Auto-generated catch block 148 e.printStackTrace(); 149 } 150 } 151 152 }
异常信息：
1 18/03/22 20:41:24 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable 2 18/03/22 20:41:25 INFO Configuration.deprecation: session.id is deprecated. Instead, use dfs.metrics.session-id 3 18/03/22 20:41:25 INFO jvm.JvmMetrics: Initializing JVM Metrics with processName=JobTracker, sessionId= 4 18/03/22 20:41:25 WARN mapreduce.JobSubmitter: No job jar file set. User classes may not be found. See Job or Job#setJar(String). 5 18/03/22 20:41:25 INFO input.FileInputFormat: Total input paths to process : 1 6 18/03/22 20:41:26 INFO mapreduce.JobSubmitter: number of splits:1 7 18/03/22 20:41:26 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_local1064879045_0001 8 18/03/22 20:41:26 WARN conf.Configuration: file:/opt/modules/cdh/hadoop-2.5.0-cdh5.3.6/data/temp/mapred/staging/Walloce1064879045/.staging/job_local1064879045_0001/job.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.retry.interval; Ignoring. 9 18/03/22 20:41:26 WARN conf.Configuration: file:/opt/modules/cdh/hadoop-2.5.0-cdh5.3.6/data/temp/mapred/staging/Walloce1064879045/.staging/job_local1064879045_0001/job.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.attempts; Ignoring. 10 18/03/22 20:41:26 INFO mapreduce.JobSubmitter: Cleaning up the staging area file:/opt/modules/cdh/hadoop-2.5.0-cdh5.3.6/data/temp/mapred/staging/Walloce1064879045/.staging/job_local1064879045_0001 11 Exception in thread "main" java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Ljava/lang/String;I)Z 12 at org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Native Method) 13 at org.apache.hadoop.io.nativeio.NativeIO$Windows.access(NativeIO.java:571) 14 at org.apache.hadoop.fs.FileUtil.canRead(FileUtil.java:977) 15 at org.apache.hadoop.util.DiskChecker.checkAccessByFileMethods(DiskChecker.java:173) 16 at org.apache.hadoop.util.DiskChecker.checkDirAccess(DiskChecker.java:160) 17 at org.apache.hadoop.util.DiskChecker.checkDir(DiskChecker.java:94) 18 at org.apache.hadoop.fs.LocalDirAllocator$AllocatorPerContext.confChanged(LocalDirAllocator.java:285) 19 at org.apache.hadoop.fs.LocalDirAllocator$AllocatorPerContext.getLocalPathForWrite(LocalDirAllocator.java:344) 20 at org.apache.hadoop.fs.LocalDirAllocator.getLocalPathForWrite(LocalDirAllocator.java:150) 21 at org.apache.hadoop.fs.LocalDirAllocator.getLocalPathForWrite(LocalDirAllocator.java:131) 22 at org.apache.hadoop.fs.LocalDirAllocator.getLocalPathForWrite(LocalDirAllocator.java:115) 23 at org.apache.hadoop.mapred.LocalDistributedCacheManager.setup(LocalDistributedCacheManager.java:131) 24 at org.apache.hadoop.mapred.LocalJobRunner$Job.<init>(LocalJobRunner.java:163) 25 at org.apache.hadoop.mapred.LocalJobRunner.submitJob(LocalJobRunner.java:731) 26 at org.apache.hadoop.mapreduce.JobSubmitter.submitJobInternal(JobSubmitter.java:432) 27 at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1285) 28 at org.apache.hadoop.mapreduce.Job$10.run(Job.java:1282) 29 at java.security.AccessController.doPrivileged(Native Method) 30 at javax.security.auth.Subject.doAs(Unknown Source) 31 at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1614) 32 at org.apache.hadoop.mapreduce.Job.submit(Job.java:1282) 33 at org.apache.hadoop.mapreduce.Job.waitForCompletion(Job.java:1303) 34 at com.walloce.wordcount.MyMapReduce.run(MyMapReduce.java:130) 35 at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:70) 36 at com.walloce.wordcount.MyMapReduce.main(MyMapReduce.java:145)
修改代码：将570行注释掉，直接return true;
再运行还是报错！！！
1 18/03/22 20:53:42 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable 2 18/03/22 20:53:42 INFO Configuration.deprecation: session.id is deprecated. Instead, use dfs.metrics.session-id 3 18/03/22 20:53:42 INFO jvm.JvmMetrics: Initializing JVM Metrics with processName=JobTracker, sessionId= 4 18/03/22 20:53:43 WARN mapreduce.JobSubmitter: No job jar file set. User classes may not be found. See Job or Job#setJar(String). 5 18/03/22 20:53:43 INFO input.FileInputFormat: Total input paths to process : 1 6 18/03/22 20:53:43 INFO mapreduce.JobSubmitter: number of splits:1 7 18/03/22 20:53:43 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_local105563724_0001 8 18/03/22 20:53:43 INFO mapreduce.Job: The url to track the job: http://localhost:8080/ 9 18/03/22 20:53:43 INFO mapreduce.Job: Running job: job_local105563724_0001 10 18/03/22 20:53:43 INFO mapred.LocalJobRunner: OutputCommitter set in config null 11 18/03/22 20:53:43 INFO mapred.LocalJobRunner: OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter 12 18/03/22 20:53:43 INFO mapred.LocalJobRunner: Waiting for map tasks 13 18/03/22 20:53:43 INFO mapred.LocalJobRunner: Starting task: attempt_local105563724_0001_m_000000_0 14 18/03/22 20:53:43 INFO util.ProcfsBasedProcessTree: ProcfsBasedProcessTree currently is supported only on Linux. 15 18/03/22 20:53:43 INFO mapred.Task: Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@4a86a3cd 16 18/03/22 20:53:43 INFO mapred.MapTask: Processing split: hdfs://bigdata-study-104:8020/testdata/word.txt:0+210 17 18/03/22 20:53:43 INFO mapred.MapTask: Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer 18 18/03/22 20:53:43 INFO mapred.MapTask: (EQUATOR) 0 kvi 26214396(104857584) 19 18/03/22 20:53:43 INFO mapred.MapTask: mapreduce.task.io.sort.mb: 100 20 18/03/22 20:53:43 INFO mapred.MapTask: soft limit at 83886080 21 18/03/22 20:53:43 INFO mapred.MapTask: bufstart = 0; bufvoid = 104857600 22 18/03/22 20:53:43 INFO mapred.MapTask: kvstart = 26214396; length = 6553600 23 map阶段开始... 24 第 1 行的字符串的偏移量为：0 25 map阶段开始... 26 第 2 行的字符串的偏移量为：46 27 map阶段开始... 28 第 3 行的字符串的偏移量为：86 29 map阶段开始... 30 第 4 行的字符串的偏移量为：120 31 map阶段开始... 32 第 5 行的字符串的偏移量为：149 33 map阶段开始... 34 第 6 行的字符串的偏移量为：172 35 map阶段开始... 36 第 7 行的字符串的偏移量为：190 37 map阶段开始... 38 第 8 行的字符串的偏移量为：204 39 18/03/22 20:53:44 INFO mapred.LocalJobRunner: 40 18/03/22 20:53:44 INFO mapred.MapTask: Starting flush of map output 41 18/03/22 20:53:44 INFO mapred.MapTask: Spilling map output 42 18/03/22 20:53:44 INFO mapred.MapTask: bufstart = 0; bufend = 348; bufvoid = 104857600 43 18/03/22 20:53:44 INFO mapred.MapTask: kvstart = 26214396(104857584); kvend = 26214256(104857024); length = 141/6553600 44 18/03/22 20:53:44 INFO mapred.MapTask: Finished spill 0 45 18/03/22 20:53:44 INFO mapred.Task: Task:attempt_local105563724_0001_m_000000_0 is done. And is in the process of committing 46 18/03/22 20:53:44 INFO mapred.LocalJobRunner: map 47 18/03/22 20:53:44 INFO mapred.Task: Task ‘attempt_local105563724_0001_m_000000_0‘ done. 48 18/03/22 20:53:44 INFO mapred.LocalJobRunner: Finishing task: attempt_local105563724_0001_m_000000_0 49 18/03/22 20:53:44 INFO mapred.LocalJobRunner: map task executor complete. 50 18/03/22 20:53:44 INFO mapred.LocalJobRunner: Waiting for reduce tasks 51 18/03/22 20:53:44 INFO mapred.LocalJobRunner: Starting task: attempt_local105563724_0001_r_000000_0 52 18/03/22 20:53:44 INFO util.ProcfsBasedProcessTree: ProcfsBasedProcessTree currently is supported only on Linux. 53 18/03/22 20:53:44 INFO mapred.Task: Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@66a2f2c4 54 18/03/22 20:53:44 INFO mapred.ReduceTask: Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@7c3f147f 55 18/03/22 20:53:44 INFO reduce.MergeManagerImpl: MergerManager: memoryLimit=1323407744, maxSingleShuffleLimit=330851936, mergeThreshold=873449152, ioSortFactor=10, memToMemMergeOutputsThreshold=10 56 18/03/22 20:53:44 INFO reduce.EventFetcher: attempt_local105563724_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events 57 18/03/22 20:53:44 INFO reduce.LocalFetcher: localfetcher#1 about to shuffle output of map attempt_local105563724_0001_m_000000_0 decomp: 422 len: 426 to MEMORY 58 18/03/22 20:53:44 INFO reduce.InMemoryMapOutput: Read 422 bytes from map-output for attempt_local105563724_0001_m_000000_0 59 18/03/22 20:53:44 INFO reduce.MergeManagerImpl: closeInMemoryFile -> map-output of size: 422, inMemoryMapOutputs.size() -> 1, commitMemory -> 0, usedMemory ->422 60 18/03/22 20:53:44 INFO reduce.EventFetcher: EventFetcher is interrupted.. Returning 61 18/03/22 20:53:44 INFO mapred.LocalJobRunner: 1 / 1 copied. 62 18/03/22 20:53:44 INFO reduce.MergeManagerImpl: finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs 63 18/03/22 20:53:44 INFO mapred.Merger: Merging 1 sorted segments 64 18/03/22 20:53:44 INFO mapred.Merger: Down to the last merge-pass, with 1 segments left of total size: 413 bytes 65 18/03/22 20:53:44 INFO reduce.MergeManagerImpl: Merged 1 segments, 422 bytes to disk to satisfy reduce memory limit 66 18/03/22 20:53:44 INFO reduce.MergeManagerImpl: Merging 1 files, 426 bytes from disk 67 18/03/22 20:53:44 INFO reduce.MergeManagerImpl: Merging 0 segments, 0 bytes from memory into reduce 68 18/03/22 20:53:44 INFO mapred.Merger: Merging 1 sorted segments 69 18/03/22 20:53:44 INFO mapred.Merger: Down to the last merge-pass, with 1 segments left of total size: 413 bytes 70 18/03/22 20:53:44 INFO mapred.LocalJobRunner: 1 / 1 copied. 71 18/03/22 20:53:44 INFO mapred.LocalJobRunner: reduce task executor complete. 72 18/03/22 20:53:44 WARN mapred.LocalJobRunner: job_local105563724_0001 73 java.lang.Exception: java.lang.NoSuchMethodError: org.apache.hadoop.fs.FSOutputSummer.<init>(Ljava/util/zip/Checksum;II)V 74 at org.apache.hadoop.mapred.LocalJobRunner$Job.runTasks(LocalJobRunner.java:462) 75 at org.apache.hadoop.mapred.LocalJobRunner$Job.run(LocalJobRunner.java:529) 76 Caused by: java.lang.NoSuchMethodError: org.apache.hadoop.fs.FSOutputSummer.<init>(Ljava/util/zip/Checksum;II)V 77 at org.apache.hadoop.hdfs.DFSOutputStream.<init>(DFSOutputStream.java:1563) 78 at org.apache.hadoop.hdfs.DFSOutputStream.<init>(DFSOutputStream.java:1594) 79 at org.apache.hadoop.hdfs.DFSOutputStream.newStreamForCreate(DFSOutputStream.java:1626) 80 at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1488) 81 at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1413) 82 at org.apache.hadoop.hdfs.DistributedFileSystem$6.doCall(DistributedFileSystem.java:387) 83 at org.apache.hadoop.hdfs.DistributedFileSystem$6.doCall(DistributedFileSystem.java:383) 84 at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81) 85 at org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:383) 86 at org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:327) 87 at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:908) 88 at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:889) 89 at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:786) 90 at org.apache.hadoop.mapreduce.lib.output.TextOutputFormat.getRecordWriter(TextOutputFormat.java:132) 91 at org.apache.hadoop.mapred.ReduceTask$NewTrackingRecordWriter.<init>(ReduceTask.java:540) 92 at org.apache.hadoop.mapred.ReduceTask.runNewReducer(ReduceTask.java:614) 93 at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:389) 94 at org.apache.hadoop.mapred.LocalJobRunner$Job$ReduceTaskRunnable.run(LocalJobRunner.java:319) 95 at java.util.concurrent.Executors$RunnableAdapter.call(Unknown Source) 96 at java.util.concurrent.FutureTask.run(Unknown Source) 97 at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source) 98 at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source) 99 at java.lang.Thread.run(Unknown Source) 100 18/03/22 20:53:44 INFO mapreduce.Job: Job job_local105563724_0001 running in uber mode : false 101 18/03/22 20:53:44 INFO mapreduce.Job: map 100% reduce 0% 102 18/03/22 20:53:44 INFO mapreduce.Job: Job job_local105563724_0001 failed with state FAILED due to: NA 103 18/03/22 20:53:44 INFO mapreduce.Job: Counters: 38 104 File System Counters 105 FILE: Number of bytes read=175 106 FILE: Number of bytes written=262184 107 FILE: Number of read operations=0 108 FILE: Number of large read operations=0 109 FILE: Number of write operations=0 110 HDFS: Number of bytes read=210 111 HDFS: Number of bytes written=0 112 HDFS: Number of read operations=6 113 HDFS: Number of large read operations=0 114 HDFS: Number of write operations=2 115 Map-Reduce Framework 116 Map input records=8 117 Map output records=36 118 Map output bytes=348 119 Map output materialized bytes=426 120 Input split bytes=112 121 Combine input records=0 122 Combine output records=0 123 Reduce input groups=0 124 Reduce shuffle bytes=426 125 Reduce input records=0 126 Reduce output records=0 127 Spilled Records=36 128 Shuffled Maps =1 129 Failed Shuffles=0 130 Merged Map outputs=1 131 GC time elapsed (ms)=0 132 CPU time spent (ms)=0 133 Physical memory (bytes) snapshot=0 134 Virtual memory (bytes) snapshot=0 135 Total committed heap usage (bytes)=232783872 136 Shuffle Errors 137 BAD_ID=0 138 CONNECTION=0 139 IO_ERROR=0 140 WRONG_LENGTH=0 141 WRONG_MAP=0 142 WRONG_REDUCE=0 143 File Input Format Counters 144 Bytes Read=210 145 File Output Format Counters 146 Bytes Written=0
主要异常信息：
1 java.lang.Exception: java.lang.NoSuchMethodError: org.apache.hadoop.fs.FSOutputSummer.<init>(Ljava/util/zip/Checksum;II)V
好不容易解决一个，又来一个....要崩溃了，继续百度！
问题大致的原因是因为jar包冲突了，所以我buildpath看下导入的jar包有哪些，结果发现问题了。。。。。
同时存在cdh版本的和apache版本的hadoop-common-2.5.0jar包，删掉cdh版本的后运行结果：
1 18/03/22 20:57:26 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable 2 18/03/22 20:57:26 INFO Configuration.deprecation: session.id is deprecated. Instead, use dfs.metrics.session-id 3 18/03/22 20:57:26 INFO jvm.JvmMetrics: Initializing JVM Metrics with processName=JobTracker, sessionId= 4 18/03/22 20:57:27 WARN mapreduce.JobSubmitter: No job jar file set. User classes may not be found. See Job or Job#setJar(String). 5 18/03/22 20:57:27 INFO input.FileInputFormat: Total input paths to process : 1 6 18/03/22 20:57:27 INFO mapreduce.JobSubmitter: number of splits:1 7 18/03/22 20:57:27 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_local1889225814_0001 8 18/03/22 20:57:27 WARN conf.Configuration: file:/opt/modules/cdh/hadoop-2.5.0-cdh5.3.6/data/temp/mapred/staging/Walloce1889225814/.staging/job_local1889225814_0001/job.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.retry.interval; Ignoring. 9 18/03/22 20:57:27 WARN conf.Configuration: file:/opt/modules/cdh/hadoop-2.5.0-cdh5.3.6/data/temp/mapred/staging/Walloce1889225814/.staging/job_local1889225814_0001/job.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.attempts; Ignoring. 10 18/03/22 20:57:27 WARN conf.Configuration: file:/opt/modules/cdh/hadoop-2.5.0-cdh5.3.6/data/temp/mapred/local/localRunner/Walloce/job_local1889225814_0001/job_local1889225814_0001.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.retry.interval; Ignoring. 11 18/03/22 20:57:27 WARN conf.Configuration: file:/opt/modules/cdh/hadoop-2.5.0-cdh5.3.6/data/temp/mapred/local/localRunner/Walloce/job_local1889225814_0001/job_local1889225814_0001.xml:an attempt to override final parameter: mapreduce.job.end-notification.max.attempts; Ignoring. 12 18/03/22 20:57:27 INFO mapreduce.Job: The url to track the job: http://localhost:8080/ 13 18/03/22 20:57:27 INFO mapreduce.Job: Running job: job_local1889225814_0001 14 18/03/22 20:57:27 INFO mapred.LocalJobRunner: OutputCommitter set in config null 15 18/03/22 20:57:27 INFO mapred.LocalJobRunner: OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter 16 18/03/22 20:57:28 INFO mapred.LocalJobRunner: Waiting for map tasks 17 18/03/22 20:57:28 INFO mapred.LocalJobRunner: Starting task: attempt_local1889225814_0001_m_000000_0 18 18/03/22 20:57:28 INFO util.ProcfsBasedProcessTree: ProcfsBasedProcessTree currently is supported only on Linux. 19 18/03/22 20:57:28 INFO mapred.Task: Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@73a61b48 20 18/03/22 20:57:28 INFO mapred.MapTask: Processing split: hdfs://bigdata-study-104:8020/testdata/word.txt:0+210 21 18/03/22 20:57:28 INFO mapred.MapTask: Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer 22 18/03/22 20:57:28 INFO mapred.MapTask: (EQUATOR) 0 kvi 26214396(104857584) 23 18/03/22 20:57:28 INFO mapred.MapTask: mapreduce.task.io.sort.mb: 100 24 18/03/22 20:57:28 INFO mapred.MapTask: soft limit at 83886080 25 18/03/22 20:57:28 INFO mapred.MapTask: bufstart = 0; bufvoid = 104857600 26 18/03/22 20:57:28 INFO mapred.MapTask: kvstart = 26214396; length = 6553600 27 map阶段开始... 28 第 1 行的字符串的偏移量为：0 29 map阶段开始... 30 第 2 行的字符串的偏移量为：46 31 map阶段开始... 32 第 3 行的字符串的偏移量为：86 33 map阶段开始... 34 第 4 行的字符串的偏移量为：120 35 map阶段开始... 36 第 5 行的字符串的偏移量为：149 37 map阶段开始... 38 第 6 行的字符串的偏移量为：172 39 map阶段开始... 40 第 7 行的字符串的偏移量为：190 41 map阶段开始... 42 第 8 行的字符串的偏移量为：204 43 18/03/22 20:57:28 INFO mapred.LocalJobRunner: 44 18/03/22 20:57:28 INFO mapred.MapTask: Starting flush of map output 45 18/03/22 20:57:28 INFO mapred.MapTask: Spilling map output 46 18/03/22 20:57:28 INFO mapred.MapTask: bufstart = 0; bufend = 348; bufvoid = 104857600 47 18/03/22 20:57:28 INFO mapred.MapTask: kvstart = 26214396(104857584); kvend = 26214256(104857024); length = 141/6553600 48 18/03/22 20:57:28 INFO mapred.MapTask: Finished spill 0 49 18/03/22 20:57:28 INFO mapred.Task: Task:attempt_local1889225814_0001_m_000000_0 is done. And is in the process of committing 50 18/03/22 20:57:28 INFO mapred.LocalJobRunner: map 51 18/03/22 20:57:28 INFO mapred.Task: Task ‘attempt_local1889225814_0001_m_000000_0‘ done. 52 18/03/22 20:57:28 INFO mapred.LocalJobRunner: Finishing task: attempt_local1889225814_0001_m_000000_0 53 18/03/22 20:57:28 INFO mapred.LocalJobRunner: map task executor complete. 54 18/03/22 20:57:28 INFO mapred.LocalJobRunner: Waiting for reduce tasks 55 18/03/22 20:57:28 INFO mapred.LocalJobRunner: Starting task: attempt_local1889225814_0001_r_000000_0 56 18/03/22 20:57:28 INFO util.ProcfsBasedProcessTree: ProcfsBasedProcessTree currently is supported only on Linux. 57 18/03/22 20:57:28 INFO mapred.Task: Using ResourceCalculatorProcessTree : org.apache.hadoop.yarn.util.WindowsBasedProcessTree@504037fc 58 18/03/22 20:57:28 INFO mapred.ReduceTask: Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@1de1d428 59 18/03/22 20:57:28 INFO reduce.MergeManagerImpl: MergerManager: memoryLimit=1323407744, maxSingleShuffleLimit=330851936, mergeThreshold=873449152, ioSortFactor=10, memToMemMergeOutputsThreshold=10 60 18/03/22 20:57:28 INFO reduce.EventFetcher: attempt_local1889225814_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events 61 18/03/22 20:57:28 INFO reduce.LocalFetcher: localfetcher#1 about to shuffle output of map attempt_local1889225814_0001_m_000000_0 decomp: 422 len: 426 to MEMORY 62 18/03/22 20:57:28 INFO reduce.InMemoryMapOutput: Read 422 bytes from map-output for attempt_local1889225814_0001_m_000000_0 63 18/03/22 20:57:28 INFO reduce.MergeManagerImpl: closeInMemoryFile -> map-output of size: 422, inMemoryMapOutputs.size() -> 1, commitMemory -> 0, usedMemory ->422 64 18/03/22 20:57:28 INFO reduce.EventFetcher: EventFetcher is interrupted.. Returning 65 18/03/22 20:57:28 INFO mapred.LocalJobRunner: 1 / 1 copied. 66 18/03/22 20:57:28 INFO reduce.MergeManagerImpl: finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs 67 18/03/22 20:57:28 INFO mapred.Merger: Merging 1 sorted segments 68 18/03/22 20:57:28 INFO mapred.Merger: Down to the last merge-pass, with 1 segments left of total size: 413 bytes 69 18/03/22 20:57:28 INFO reduce.MergeManagerImpl: Merged 1 segments, 422 bytes to disk to satisfy reduce memory limit 70 18/03/22 20:57:28 INFO reduce.MergeManagerImpl: Merging 1 files, 426 bytes from disk 71 18/03/22 20:57:28 INFO reduce.MergeManagerImpl: Merging 0 segments, 0 bytes from memory into reduce 72 18/03/22 20:57:28 INFO mapred.Merger: Merging 1 sorted segments 73 18/03/22 20:57:28 INFO mapred.Merger: Down to the last merge-pass, with 1 segments left of total size: 413 bytes 74 18/03/22 20:57:28 INFO mapred.LocalJobRunner: 1 / 1 copied. 75 18/03/22 20:57:28 INFO Configuration.deprecation: mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords 76 这是第0次reduce 77 Reduce阶段开始.... 78 这是第1次reduce 79 Reduce阶段开始.... 80 这是第2次reduce 81 Reduce阶段开始.... 82 这是第3次reduce 83 Reduce阶段开始.... 84 这是第4次reduce 85 Reduce阶段开始.... 86 这是第5次reduce 87 Reduce阶段开始.... 88 这是第6次reduce 89 Reduce阶段开始.... 90 这是第7次reduce 91 Reduce阶段开始.... 92 18/03/22 20:57:28 INFO mapred.Task: Task:attempt_local1889225814_0001_r_000000_0 is done. And is in the process of committing 93 18/03/22 20:57:28 INFO mapred.LocalJobRunner: 1 / 1 copied. 94 18/03/22 20:57:28 INFO mapred.Task: Task attempt_local1889225814_0001_r_000000_0 is allowed to commit now 95 18/03/22 20:57:28 INFO output.FileOutputCommitter: Saved output of task ‘attempt_local1889225814_0001_r_000000_0‘ to hdfs://bigdata-study-104:8020/testresult/output/_temporary/0/task_local1889225814_0001_r_000000 96 18/03/22 20:57:28 INFO mapred.LocalJobRunner: reduce > reduce 97 18/03/22 20:57:28 INFO mapred.Task: Task ‘attempt_local1889225814_0001_r_000000_0‘ done. 98 18/03/22 20:57:28 INFO mapred.LocalJobRunner: Finishing task: attempt_local1889225814_0001_r_000000_0 99 18/03/22 20:57:28 INFO mapred.LocalJobRunner: reduce task executor complete. 100 18/03/22 20:57:28 INFO mapreduce.Job: Job job_local1889225814_0001 running in uber mode : false 101 18/03/22 20:57:28 INFO mapreduce.Job: map 100% reduce 100% 102 18/03/22 20:57:28 INFO mapreduce.Job: Job job_local1889225814_0001 completed successfully 103 18/03/22 20:57:28 INFO mapreduce.Job: Counters: 38 104 File System Counters 105 FILE: Number of bytes read=1234 106 FILE: Number of bytes written=508548 107 FILE: Number of read operations=0 108 FILE: Number of large read operations=0 109 FILE: Number of write operations=0 110 HDFS: Number of bytes read=420 111 HDFS: Number of bytes written=61 112 HDFS: Number of read operations=15 113 HDFS: Number of large read operations=0 114 HDFS: Number of write operations=6 115 Map-Reduce Framework 116 Map input records=8 117 Map output records=36 118 Map output bytes=348 119 Map output materialized bytes=426 120 Input split bytes=112 121 Combine input records=0 122 Combine output records=0 123 Reduce input groups=8 124 Reduce shuffle bytes=426 125 Reduce input records=36 126 Reduce output records=8 127 Spilled Records=72 128 Shuffled Maps =1 129 Failed Shuffles=0 130 Merged Map outputs=1 131 GC time elapsed (ms)=0 132 CPU time spent (ms)=0 133 Physical memory (bytes) snapshot=0 134 Virtual memory (bytes) snapshot=0 135 Total committed heap usage (bytes)=471859200 136 Shuffle Errors 137 BAD_ID=0 138 CONNECTION=0 139 IO_ERROR=0 140 WRONG_LENGTH=0 141 WRONG_MAP=0 142 WRONG_REDUCE=0 143 File Input Format Counters 144 Bytes Read=210 145 File Output Format Counters 146 Bytes Written=61
运行成功，在dfs上看到运行的结果文件！！
参考：https://getpocket.com/a/read/2123376367 解决问题。
