hadoop实践 | 各省份的学生平均成绩

最新推荐文章于 2024-09-04 07:30:00 发布

TaiKuLaHa

最新推荐文章于 2024-09-04 07:30:00 发布

阅读量1.2k

点赞数

本文链接：https://blog.csdn.net/JH_Zhai/article/details/79692423

版权

问题描述

建立两张表，第1张表有学生姓名和出生省份数据，第2张表有学生姓名和英语成绩数据，用map-reduce程序来统计同一省份的学生英语平均成绩。

数据自备

一个解析

实在想不到如何一次MapReduce完成，菜鸡的我只能分两次完成。如果有更好的思路希望私信或留言

分两次，先多表关联，然后算平均值

里面有条数据 shanghai打成shagnhai了

这里写图片描述

程序

JoinTable.java

package examples;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class JoinTable {  
    public static class SMMapper extends Mapper<LongWritable, Text, Text, Text> {  
        private String flag = null;  

        @Override  
        protected void setup(Context context) throws IOException,  
                InterruptedException {  
            FileSplit split = (FileSplit) context.getInputSplit();  
            flag = split.getPath().getName();  
        }  

        @Override  
        protected void map(LongWritable key, Text value, Context context)  
                throws IOException, InterruptedException {  
            String[] val = value.toString().split(",");  
            if ("placeTable".equals(flag)) {   
                context.write(new Text(val[0]), new Text("a,"  
                        + val[1]));  
            } else if ("scoreTable".equals(flag)) {  
                context.write(new Text(val[0]), new Text("b,"  
                        + val[1]));  
            }  
        }  
    }  

    public static class SMReducer extends  
            Reducer<Text, Text, Text, Text> {  
        @Override  
        protected void reduce(Text key, Iterable<Text> values, Context context)  
                throws IOException, InterruptedException {  

            String[] ArrStr = new String[2];

            for (Text value : values) {  
                String[] val = value.toString().split(",");  
                if ("a".equals(val[0])) {  
                    ArrStr[0] =  val[1];
                } else if ("b".equals(val[0])) {  
                    ArrStr[1] =  val[1]; 
                }  
            }  
            context.write(new Text(ArrStr[0]), new Text(ArrStr[1]));  
        }  
    }  

    public static void main(String[] args) throws IOException,  
            ClassNotFoundException, InterruptedException {  
        String input1 = "hdfs:/score/placeTable";  
        String input2 = "hdfs:/score/scoreTable";  
        String output = "hdfs:/score/out";  

        Configuration conf = new Configuration();  
        conf.addResource("classpath:/core-site.xml");  
        conf.addResource("classpath:/hdfs-site.xml");  

        Job job = Job.getInstance(conf, "JoinTable");  
        job.setJarByClass(JoinTable.class);  
        job.setOutputKeyClass(Text.class);  
        job.setOutputValueClass(Text.class);  

        job.setMapperClass(SMMapper.class);  
        job.setReducerClass(SMReducer.class);  

        job.setInputFormatClass(TextInputFormat.class);  
        job.setOutputFormatClass(TextOutputFormat.class);  

        FileInputFormat.setInputPaths(job, new Path(input1), new Path(input2));// 加载2个输入数据集  
        Path outputPath = new Path(output);  
        outputPath.getFileSystem(conf).delete(outputPath, true);  
        FileOutputFormat.setOutputPath(job, outputPath);  

        System.exit(job.waitForCompletion(true) ? 0 : 1);  
    }  
}

AverageScore.java

package examples;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.DoubleWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;

public class AverageScore {  
    public static class SMMapper extends Mapper<LongWritable, Text, Text, Text> {  
        @Override  
        protected void setup(Context context) throws IOException,  
                InterruptedException {  
            FileSplit split = (FileSplit) context.getInputSplit();  
            split.getPath().getName();  
        }  

        @Override  
        protected void map(LongWritable key, Text value, Context context)  
                throws IOException, InterruptedException { 
            String str = value.toString();
            char[] ArrCh = str.toCharArray();
            int i = 0;
            for(; i<ArrCh.length; i++){
                if(ArrCh[i]=='\t') break; 
            }
            String key_ = str.substring(0,i);
            String val_ = str.substring(i+1);
            context.write(new Text(key_), new Text(val_));  

        }  
    }  

    public static class SMReducer extends  
            Reducer<Text, Text, Text, DoubleWritable> {  
        private DoubleWritable result = new DoubleWritable();
        @Override  
        protected void reduce(Text key, Iterable<Text> values, Context context)  
                throws IOException, InterruptedException {  
            double sum = 0;
            int len_ = 0;
            for(Text val:values){
                sum += Double.parseDouble(val.toString());
                ++len_;
            }
            result.set(sum/len_);

            context.write(key, result);  
        }  
    }  

    public static void main(String[] args) throws IOException,  
            ClassNotFoundException, InterruptedException {  
        String input1 = "hdfs:/score/out/part-r-00000";   
        String output = "hdfs:/score/out/lastout";  

        Configuration conf = new Configuration();  
        conf.addResource("classpath:/core-site.xml");  
        conf.addResource("classpath:/hdfs-site.xml");  

        Job job = Job.getInstance(conf, "AverageScore");  
        job.setJarByClass(AverageScore.class);  
        job.setOutputKeyClass(Text.class);  
        job.setOutputValueClass(Text.class);  

        job.setMapperClass(SMMapper.class);  
        job.setReducerClass(SMReducer.class);  

        job.setInputFormatClass(TextInputFormat.class);  
        job.setOutputFormatClass(TextOutputFormat.class);  

        FileInputFormat.setInputPaths(job, new Path(input1));
        Path outputPath = new Path(output);  
        outputPath.getFileSystem(conf).delete(outputPath, true);  
        FileOutputFormat.setOutputPath(job, outputPath);  

        System.exit(job.waitForCompletion(true) ? 0 : 1);  
    }  
}

日志

JoinTable.java

18/03/25 08:34:31 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
18/03/25 08:34:32 INFO Configuration.deprecation: session.id is deprecated. Instead, use dfs.metrics.session-id
18/03/25 08:34:32 INFO jvm.JvmMetrics: Initializing JVM Metrics with processName=JobTracker, sessionId=
18/03/25 08:34:33 WARN mapreduce.JobResourceUploader: Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
18/03/25 08:34:33 WARN mapreduce.JobResourceUploader: No job jar file set.  User classes may not be found. See Job or Job#setJar(String).
18/03/25 08:34:33 INFO input.FileInputFormat: Total input paths to process : 2
18/03/25 08:34:33 INFO mapreduce.JobSubmitter: number of splits:2
18/03/25 08:34:33 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_local371132637_0001
18/03/25 08:34:33 INFO mapreduce.Job: The url to track the job: http://localhost:8080/
18/03/25 08:34:33 INFO mapreduce.Job: Running job: job_local371132637_0001
18/03/25 08:34:33 INFO mapred.LocalJobRunner: OutputCommitter set in config null
18/03/25 08:34:33 INFO output.FileOutputCommitter: File Output Committer Algorithm version is 1
18/03/25 08:34:33 INFO mapred.LocalJobRunner: OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
18/03/25 08:34:34 INFO mapred.LocalJobRunner: Waiting for map tasks
18/03/25 08:34:34 INFO mapred.LocalJobRunner: Starting task: attempt_local371132637_0001_m_000000_0
18/03/25 08:34:34 INFO output.FileOutputCommitter: File Output Committer Algorithm version is 1
18/03/25 08:34:34 INFO mapred.Task:  Using ResourceCalculatorProcessTree : [ ]
18/03/25 08:34:34 INFO mapred.MapTask: Processing split: hdfs://master:9000/score/placeTable:0+104
18/03/25 08:34:34 INFO mapred.MapTask: (EQUATOR) 0 kvi 26214396(104857584)
18/03/25 08:34:34 INFO mapred.MapTask: mapreduce.task.io.sort.mb: 100
18/03/25 08:34:34 INFO mapred.MapTask: soft limit at 83886080
18/03/25 08:34:34 INFO mapred.MapTask: bufstart = 0; bufvoid = 104857600
18/03/25 08:34:34 INFO mapred.MapTask: kvstart = 26214396; length = 6553600
18/03/25 08:34:34 INFO mapred.MapTask: Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
18/03/25 08:34:34 INFO mapred.LocalJobRunner: 
18/03/25 08:34:34 INFO mapred.MapTask: Starting flush of map output
18/03/25 08:34:34 INFO mapred.MapTask: Spilling map output
18/03/25 08:34:34 INFO mapred.MapTask: bufstart = 0; bufend = 118; bufvoid = 104857600
18/03/25 08:34:34 INFO mapred.MapTask: kvstart = 26214396(104857584); kvend = 26214372(104857488); length = 25/6553600
18/03/25 08:34:34 INFO mapred.MapTask: Finished spill 0
18/03/25 08:34:34 INFO mapred.Task: Task:attempt_local371132637_0001_m_000000_0 is done. And is in the process of committing
18/03/25 08:34:34 INFO mapreduce.Job: Job job_local371132637_0001 running in uber mode : false
18/03/25 08:34:34 INFO mapred.LocalJobRunner: map
18/03/25 08:34:34 INFO mapred.Task: Task 'attempt_local371132637_0001_m_000000_0' done.
18/03/25 08:34:34 INFO mapred.LocalJobRunner: Finishing task: attempt_local371132637_0001_m_000000_0
18/03/25 08:34:34 INFO mapred.LocalJobRunner: Starting task: attempt_local371132637_0001_m_000001_0
18/03/25 08:34:34 INFO output.FileOutputCommitter: File Output Committer Algorithm version is 1
18/03/25 08:34:34 INFO mapred.Task:  Using ResourceCalculatorProcessTree : [ ]
18/03/25 08:34:34 INFO mapreduce.Job:  map 0% reduce 0%
18/03/25 08:34:34 INFO mapred.MapTask: Processing split: hdfs://master:9000/score/scoreTable:0+65
18/03/25 08:34:35 INFO mapred.MapTask: (EQUATOR) 0 kvi 26214396(104857584)
18/03/25 08:34:35 INFO mapred.MapTask: mapreduce.task.io.sort.mb: 100
18/03/25 08:34:35 INFO mapred.MapTask: soft limit at 83886080
18/03/25 08:34:35 INFO mapred.MapTask: bufstart = 0; bufvoid = 104857600
18/03/25 08:34:35 INFO mapred.MapTask: kvstart = 26214396; length = 6553600
18/03/25 08:34:35 INFO mapred.MapTask: Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
18/03/25 08:34:35 INFO mapred.LocalJobRunner: 
18/03/25 08:34:35 INFO mapred.MapTask: Starting flush of map output
18/03/25 08:34:35 INFO mapred.MapTask: Spilling map output
18/03/25 08:34:35 INFO mapred.MapTask: bufstart = 0; bufend = 79; bufvoid = 104857600
18/03/25 08:34:35 INFO mapred.MapTask: kvstart = 26214396(104857584); kvend = 26214372(104857488); length = 25/6553600
18/03/25 08:34:35 INFO mapred.MapTask: Finished spill 0
18/03/25 08:34:35 INFO mapred.Task: Task:attempt_local371132637_0001_m_000001_0 is done. And is in the process of committing
18/03/25 08:34:35 INFO mapred.LocalJobRunner: map
18/03/25 08:34:35 INFO mapred.Task: Task 'attempt_local371132637_0001_m_000001_0' done.
18/03/25 08:34:35 INFO mapred.LocalJobRunner: Finishing task: attempt_local371132637_0001_m_000001_0
18/03/25 08:34:35 INFO mapred.LocalJobRunner: map task executor complete.
18/03/25 08:34:35 INFO mapred.LocalJobRunner: Waiting for reduce tasks
18/03/25 08:34:35 INFO mapred.LocalJobRunner: Starting task: attempt_local371132637_0001_r_000000_0
18/03/25 08:34:35 INFO output.FileOutputCommitter: File Output Committer Algorithm version is 1
18/03/25 08:34:35 INFO mapred.Task:  Using ResourceCalculatorProcessTree : [ ]
18/03/25 08:34:35 INFO mapred.ReduceTask: Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@2f36f1ce
18/03/25 08:34:35 INFO reduce.MergeManagerImpl: MergerManager: memoryLimit=322594400, maxSingleShuffleLimit=80648600, mergeThreshold=212912320, ioSortFactor=10, memToMemMergeOutputsThreshold=10
18/03/25 08:34:35 INFO reduce.EventFetcher: attempt_local371132637_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events
18/03/25 08:34:35 INFO reduce.LocalFetcher: localfetcher#1 about to shuffle output of map attempt_local371132637_0001_m_000000_0 decomp: 134 len: 138 to MEMORY
18/03/25 08:34:35 INFO reduce.InMemoryMapOutput: Read 134 bytes from map-output for attempt_local371132637_0001_m_000000_0
18/03/25 08:34:35 INFO reduce.MergeManagerImpl: closeInMemoryFile -> map-output of size: 134, inMemoryMapOutputs.size() -> 1, commitMemory -> 0, usedMemory ->134
18/03/25 08:34:35 INFO reduce.LocalFetcher: localfetcher#1 about to shuffle output of map attempt_local371132637_0001_m_000001_0 decomp: 95 len: 99 to MEMORY
18/03/25 08:34:35 INFO reduce.InMemoryMapOutput: Read 95 bytes from map-output for attempt_local371132637_0001_m_000001_0
18/03/25 08:34:35 INFO reduce.MergeManagerImpl: closeInMemoryFile -> map-output of size: 95, inMemoryMapOutputs.size() -> 2, commitMemory -> 134, usedMemory ->229
18/03/25 08:34:35 INFO reduce.EventFetcher: EventFetcher is interrupted.. Returning
18/03/25 08:34:35 INFO mapred.LocalJobRunner: 2 / 2 copied.
18/03/25 08:34:35 INFO reduce.MergeManagerImpl: finalMerge called with 2 in-memory map-outputs and 0 on-disk map-outputs
18/03/25 08:34:35 INFO mapred.Merger: Merging 2 sorted segments
18/03/25 08:34:35 INFO mapred.Merger: Down to the last merge-pass, with 2 segments left of total size: 215 bytes
18/03/25 08:34:35 INFO reduce.MergeManagerImpl: Merged 2 segments, 229 bytes to disk to satisfy reduce memory limit
18/03/25 08:34:35 INFO reduce.MergeManagerImpl: Merging 1 files, 231 bytes from disk
18/03/25 08:34:35 INFO reduce.MergeManagerImpl: Merging 0 segments, 0 bytes from memory into reduce
18/03/25 08:34:35 INFO mapred.Merger: Merging 1 sorted segments
18/03/25 08:34:35 INFO mapred.Merger: Down to the last merge-pass, with 1 segments left of total size: 220 bytes
18/03/25 08:34:35 INFO mapred.LocalJobRunner: 2 / 2 copied.
18/03/25 08:34:35 INFO Configuration.deprecation: mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
18/03/25 08:34:35 INFO mapreduce.Job:  map 100% reduce 0%
18/03/25 08:34:36 INFO mapred.Task: Task:attempt_local371132637_0001_r_000000_0 is done. And is in the process of committing
18/03/25 08:34:36 INFO mapred.LocalJobRunner: 2 / 2 copied.
18/03/25 08:34:36 INFO mapred.Task: Task attempt_local371132637_0001_r_000000_0 is allowed to commit now
18/03/25 08:34:36 INFO output.FileOutputCommitter: Saved output of task 'attempt_local371132637_0001_r_000000_0' to hdfs://master:9000/score/out/_temporary/0/task_local371132637_0001_r_000000
18/03/25 08:34:36 INFO mapred.LocalJobRunner: reduce > reduce
18/03/25 08:34:36 INFO mapred.Task: Task 'attempt_local371132637_0001_r_000000_0' done.
18/03/25 08:34:36 INFO mapred.LocalJobRunner: Finishing task: attempt_local371132637_0001_r_000000_0
18/03/25 08:34:36 INFO mapred.LocalJobRunner: reduce task executor complete.
18/03/25 08:34:36 INFO mapreduce.Job:  map 100% reduce 100%
18/03/25 08:34:36 INFO mapreduce.Job: Job job_local371132637_0001 completed successfully
18/03/25 08:34:37 INFO mapreduce.Job: Counters: 35
    File System Counters
        FILE: Number of bytes read=1795
        FILE: Number of bytes written=869992
        FILE: Number of read operations=0
        FILE: Number of large read operations=0
        FILE: Number of write operations=0
        HDFS: Number of bytes read=442
        HDFS: Number of bytes written=79
        HDFS: Number of read operations=28
        HDFS: Number of large read operations=0
        HDFS: Number of write operations=8
    Map-Reduce Framework
        Map input records=14
        Map output records=14
        Map output bytes=197
        Map output materialized bytes=237
        Input split bytes=200
        Combine input records=0
        Combine output records=0
        Reduce input groups=7
        Reduce shuffle bytes=237
        Reduce input records=14
        Reduce output records=7
        Spilled Records=28
        Shuffled Maps =2
        Failed Shuffles=0
        Merged Map outputs=2
        GC time elapsed (ms)=13
        Total committed heap usage (bytes)=950009856
    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=169
    File Output Format Counters 
        Bytes Written=79

AverageScore.java

18/03/25 08:36:41 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
18/03/25 08:36:43 INFO Configuration.deprecation: session.id is deprecated. Instead, use dfs.metrics.session-id
18/03/25 08:36:43 INFO jvm.JvmMetrics: Initializing JVM Metrics with processName=JobTracker, sessionId=
18/03/25 08:36:43 WARN mapreduce.JobResourceUploader: Hadoop command-line option parsing not performed. Implement the Tool interface and execute your application with ToolRunner to remedy this.
18/03/25 08:36:43 WARN mapreduce.JobResourceUploader: No job jar file set.  User classes may not be found. See Job or Job#setJar(String).
18/03/25 08:36:43 INFO input.FileInputFormat: Total input paths to process : 1
18/03/25 08:36:43 INFO mapreduce.JobSubmitter: number of splits:1
18/03/25 08:36:43 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_local1381911508_0001
18/03/25 08:36:44 INFO mapreduce.Job: The url to track the job: http://localhost:8080/
18/03/25 08:36:44 INFO mapreduce.Job: Running job: job_local1381911508_0001
18/03/25 08:36:44 INFO mapred.LocalJobRunner: OutputCommitter set in config null
18/03/25 08:36:44 INFO output.FileOutputCommitter: File Output Committer Algorithm version is 1
18/03/25 08:36:44 INFO mapred.LocalJobRunner: OutputCommitter is org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
18/03/25 08:36:44 INFO mapred.LocalJobRunner: Waiting for map tasks
18/03/25 08:36:44 INFO mapred.LocalJobRunner: Starting task: attempt_local1381911508_0001_m_000000_0
18/03/25 08:36:44 INFO output.FileOutputCommitter: File Output Committer Algorithm version is 1
18/03/25 08:36:44 INFO mapred.Task:  Using ResourceCalculatorProcessTree : [ ]
18/03/25 08:36:44 INFO mapred.MapTask: Processing split: hdfs://master:9000/score/out/part-r-00000:0+79
18/03/25 08:36:44 INFO mapred.MapTask: (EQUATOR) 0 kvi 26214396(104857584)
18/03/25 08:36:44 INFO mapred.MapTask: mapreduce.task.io.sort.mb: 100
18/03/25 08:36:44 INFO mapred.MapTask: soft limit at 83886080
18/03/25 08:36:44 INFO mapred.MapTask: bufstart = 0; bufvoid = 104857600
18/03/25 08:36:44 INFO mapred.MapTask: kvstart = 26214396; length = 6553600
18/03/25 08:36:44 INFO mapred.MapTask: Map output collector class = org.apache.hadoop.mapred.MapTask$MapOutputBuffer
18/03/25 08:36:44 INFO mapred.LocalJobRunner: 
18/03/25 08:36:44 INFO mapred.MapTask: Starting flush of map output
18/03/25 08:36:44 INFO mapred.MapTask: Spilling map output
18/03/25 08:36:44 INFO mapred.MapTask: bufstart = 0; bufend = 79; bufvoid = 104857600
18/03/25 08:36:44 INFO mapred.MapTask: kvstart = 26214396(104857584); kvend = 26214372(104857488); length = 25/6553600
18/03/25 08:36:45 INFO mapred.MapTask: Finished spill 0
18/03/25 08:36:45 INFO mapred.Task: Task:attempt_local1381911508_0001_m_000000_0 is done. And is in the process of committing
18/03/25 08:36:45 INFO mapred.LocalJobRunner: map
18/03/25 08:36:45 INFO mapred.Task: Task 'attempt_local1381911508_0001_m_000000_0' done.
18/03/25 08:36:45 INFO mapred.LocalJobRunner: Finishing task: attempt_local1381911508_0001_m_000000_0
18/03/25 08:36:45 INFO mapred.LocalJobRunner: map task executor complete.
18/03/25 08:36:45 INFO mapred.LocalJobRunner: Waiting for reduce tasks
18/03/25 08:36:45 INFO mapred.LocalJobRunner: Starting task: attempt_local1381911508_0001_r_000000_0
18/03/25 08:36:45 INFO output.FileOutputCommitter: File Output Committer Algorithm version is 1
18/03/25 08:36:45 INFO mapred.Task:  Using ResourceCalculatorProcessTree : [ ]
18/03/25 08:36:45 INFO mapred.ReduceTask: Using ShuffleConsumerPlugin: org.apache.hadoop.mapreduce.task.reduce.Shuffle@83f8595
18/03/25 08:36:45 INFO mapreduce.Job: Job job_local1381911508_0001 running in uber mode : false
18/03/25 08:36:45 INFO mapreduce.Job:  map 100% reduce 0%
18/03/25 08:36:45 INFO reduce.MergeManagerImpl: MergerManager: memoryLimit=322594400, maxSingleShuffleLimit=80648600, mergeThreshold=212912320, ioSortFactor=10, memToMemMergeOutputsThreshold=10
18/03/25 08:36:45 INFO reduce.EventFetcher: attempt_local1381911508_0001_r_000000_0 Thread started: EventFetcher for fetching Map Completion Events
18/03/25 08:36:45 INFO reduce.LocalFetcher: localfetcher#1 about to shuffle output of map attempt_local1381911508_0001_m_000000_0 decomp: 95 len: 99 to MEMORY
18/03/25 08:36:45 INFO reduce.InMemoryMapOutput: Read 95 bytes from map-output for attempt_local1381911508_0001_m_000000_0
18/03/25 08:36:45 INFO reduce.MergeManagerImpl: closeInMemoryFile -> map-output of size: 95, inMemoryMapOutputs.size() -> 1, commitMemory -> 0, usedMemory ->95
18/03/25 08:36:45 INFO reduce.EventFetcher: EventFetcher is interrupted.. Returning
18/03/25 08:36:45 INFO mapred.LocalJobRunner: 1 / 1 copied.
18/03/25 08:36:45 INFO reduce.MergeManagerImpl: finalMerge called with 1 in-memory map-outputs and 0 on-disk map-outputs
18/03/25 08:36:45 INFO mapred.Merger: Merging 1 sorted segments
18/03/25 08:36:45 INFO mapred.Merger: Down to the last merge-pass, with 1 segments left of total size: 85 bytes
18/03/25 08:36:45 INFO reduce.MergeManagerImpl: Merged 1 segments, 95 bytes to disk to satisfy reduce memory limit
18/03/25 08:36:45 INFO reduce.MergeManagerImpl: Merging 1 files, 99 bytes from disk
18/03/25 08:36:45 INFO reduce.MergeManagerImpl: Merging 0 segments, 0 bytes from memory into reduce
18/03/25 08:36:45 INFO mapred.Merger: Merging 1 sorted segments
18/03/25 08:36:45 INFO mapred.Merger: Down to the last merge-pass, with 1 segments left of total size: 85 bytes
18/03/25 08:36:45 INFO mapred.LocalJobRunner: 1 / 1 copied.
18/03/25 08:36:45 INFO Configuration.deprecation: mapred.skip.on is deprecated. Instead, use mapreduce.job.skiprecords
18/03/25 08:36:45 INFO mapred.Task: Task:attempt_local1381911508_0001_r_000000_0 is done. And is in the process of committing
18/03/25 08:36:45 INFO mapred.LocalJobRunner: 1 / 1 copied.
18/03/25 08:36:45 INFO mapred.Task: Task attempt_local1381911508_0001_r_000000_0 is allowed to commit now
18/03/25 08:36:45 INFO output.FileOutputCommitter: Saved output of task 'attempt_local1381911508_0001_r_000000_0' to hdfs://master:9000/score/out/lastout/_temporary/0/task_local1381911508_0001_r_000000
18/03/25 08:36:45 INFO mapred.LocalJobRunner: reduce > reduce
18/03/25 08:36:45 INFO mapred.Task: Task 'attempt_local1381911508_0001_r_000000_0' done.
18/03/25 08:36:45 INFO mapred.LocalJobRunner: Finishing task: attempt_local1381911508_0001_r_000000_0
18/03/25 08:36:45 INFO mapred.LocalJobRunner: reduce task executor complete.
18/03/25 08:36:46 INFO mapreduce.Job:  map 100% reduce 100%
18/03/25 08:36:46 INFO mapreduce.Job: Job job_local1381911508_0001 completed successfully
18/03/25 08:36:46 INFO mapreduce.Job: Counters: 35
    File System Counters
        FILE: Number of bytes read=558
        FILE: Number of bytes written=582457
        FILE: Number of read operations=0
        FILE: Number of large read operations=0
        FILE: Number of write operations=0
        HDFS: Number of bytes read=158
        HDFS: Number of bytes written=54
        HDFS: Number of read operations=13
        HDFS: Number of large read operations=0
        HDFS: Number of write operations=6
    Map-Reduce Framework
        Map input records=7
        Map output records=7
        Map output bytes=79
        Map output materialized bytes=99
        Input split bytes=106
        Combine input records=0
        Combine output records=0
        Reduce input groups=4
        Reduce shuffle bytes=99
        Reduce input records=7
        Reduce output records=4
        Spilled Records=14
        Shuffled Maps =1
        Failed Shuffles=0
        Merged Map outputs=1
        GC time elapsed (ms)=19
        Total committed heap usage (bytes)=463470592
    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=79
    File Output Format Counters 
        Bytes Written=54