MapReduce编程系列 — 4：排序

1、项目名称：

2、程序代码：

package com.sort;

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;


public class Sort {
    //map将输入中的value化成IntWritable类型，作为输出的key
    public static class Map extends Mapper<Object, Text , IntWritable, IntWritable>{
        public static IntWritable data = new IntWritable();

        public void map(Object key , Text value, Context context) throws IOException,InterruptedException{
            System.out.println("Mapper.................");
            System.out.println("key:"+key+"  value:"+value);

            String line = value.toString();
            data.set(Integer.parseInt(line));
            context.write(data, new IntWritable(1));
            System.out.println("data:"+data+" context:"+context);
        }
    }

    //reduce将输入的key复制到输出的value上，然后根据输入的value-list中元素的个数决定key的输出次数
    //用全局linenum来代表key的位次
    public static class Reduce extends Reducer<IntWritable , IntWritable, IntWritable, IntWritable >{
        public static IntWritable linenum = new IntWritable(1);

        public void reduce(IntWritable key, Iterable<IntWritable> values , Context context)throws IOException,InterruptedException{
            System.out.println("Reducer.................");
            System.out.println("key:"+key+"  value:"+values);

            for(IntWritable val : values){
                context.write(linenum, key);
                System.out.println("linenum:" + linenum +"  key:"+key+" context:"+context);
                linenum = new IntWritable(linenum.get()+1);

            }
        }
    }
    public static void main(String [] args) throws Exception{
        Configuration conf = new Configuration();
        String [] otherArgs = new GenericOptionsParser(conf,args).getRemainingArgs();
        if(otherArgs.length != 2){
            System.out.println("Usage: sort<in><out>");
            System.exit(2);
        }
        Job job = new Job(conf,"sort");
        job.setJarByClass(Sort.class);
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);

        job.setOutputKeyClass(IntWritable.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));        
        FileOutputFormat.setOutputPath(job,new Path(otherArgs[1]));

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

3、测试数据：

file1：

2
32
654
32
15
756
65223

 

file2：

5956
22
650
92

 

file3：

26
54
6

 

4、运行过程：

14/09/21 17:44:27 WARN util.NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
14/09/21 17:44:27 WARN mapred.JobClient: No job jar file set.  User classes may not be found. See JobConf(Class) or JobConf#setJar(String).
14/09/21 17:44:28 INFO input.FileInputFormat: Total input paths to process : 3
14/09/21 17:44:28 WARN snappy.LoadSnappy: Snappy native library not loaded
14/09/21 17:44:28 INFO mapred.JobClient: Running job: job_local_0001
14/09/21 17:44:28 INFO util.ProcessTree: setsid exited with exit code 0
14/09/21 17:44:28 INFO mapred.Task:  Using ResourceCalculatorPlugin : org.apache.hadoop.util.LinuxResourceCalculatorPlugin@365f3cec
14/09/21 17:44:28 INFO mapred.MapTask: io.sort.mb = 100
14/09/21 17:44:28 INFO mapred.MapTask: data buffer = 79691776/99614720
14/09/21 17:44:28 INFO mapred.MapTask: record buffer = 262144/327680
Mapper.................
key:0  value:2
data:2 context:org.apache.hadoop.mapreduce.Mapper$Context@40804be
Mapper.................
key:2  value:32
data:32 context:org.apache.hadoop.mapreduce.Mapper$Context@40804be
Mapper.................
key:5  value:654
data:654 context:org.apache.hadoop.mapreduce.Mapper$Context@40804be
Mapper.................
key:9  value:32
data:32 context:org.apache.hadoop.mapreduce.Mapper$Context@40804be
Mapper.................
key:12  value:15
data:15 context:org.apache.hadoop.mapreduce.Mapper$Context@40804be
Mapper.................
key:15  value:756
data:756 context:org.apache.hadoop.mapreduce.Mapper$Context@40804be
Mapper.................
key:19  value:65223
data:65223 context:org.apache.hadoop.mapreduce.Mapper$Context@40804be
14/09/21 17:44:28 INFO mapred.MapTask: Starting flush of map output
14/09/21 17:44:28 INFO mapred.MapTask: Finished spill 0
14/09/21 17:44:28 INFO mapred.Task: Task:attempt_local_0001_m_000000_0 is done. And is in the process of commiting
14/09/21 17:44:29 INFO mapred.JobClient:  map 0% reduce 0%
14/09/21 17:44:31 INFO mapred.LocalJobRunner:
14/09/21 17:44:31 INFO mapred.Task: Task 'attempt_local_0001_m_000000_0' done.
14/09/21 17:44:31 INFO mapred.Task:  Using ResourceCalculatorPlugin : org.apache.hadoop.util.LinuxResourceCalculatorPlugin@5c72877c
14/09/21 17:44:31 INFO mapred.MapTask: io.sort.mb = 100
14/09/21 17:44:31 INFO mapred.MapTask: data buffer = 79691776/99614720
14/09/21 17:44:31 INFO mapred.MapTask: record buffer = 262144/327680
Mapper.................
key:0  value:5956
data:5956 context:org.apache.hadoop.mapreduce.Mapper$Context@5c0134fb
Mapper.................
key:5  value:22
data:22 context:org.apache.hadoop.mapreduce.Mapper$Context@5c0134fb
Mapper.................
key:8  value:650
data:650 context:org.apache.hadoop.mapreduce.Mapper$Context@5c0134fb
Mapper.................
key:12  value:92
data:92 context:org.apache.hadoop.mapreduce.Mapper$Context@5c0134fb
14/09/21 17:44:31 INFO mapred.MapTask: Starting flush of map output
14/09/21 17:44:31 INFO mapred.MapTask: Finished spill 0
14/09/21 17:44:31 INFO mapred.Task: Task:attempt_local_0001_m_000001_0 is done. And is in the process of commiting
14/09/21 17:44:32 INFO mapred.JobClient:  map 100% reduce 0%
14/09/21 17:44:34 INFO mapred.LocalJobRunner:
14/09/21 17:44:34 INFO mapred.Task: Task 'attempt_local_0001_m_000001_0' done.
14/09/21 17:44:34 INFO mapred.Task:  Using ResourceCalculatorPlugin : org.apache.hadoop.util.LinuxResourceCalculatorPlugin@5c88c5d3
14/09/21 17:44:34 INFO mapred.MapTask: io.sort.mb = 100
14/09/21 17:44:34 INFO mapred.MapTask: data buffer = 79691776/99614720
14/09/21 17:44:34 INFO mapred.MapTask: record buffer = 262144/327680
Mapper.................
key:0  value:26
data:26 context:org.apache.hadoop.mapreduce.Mapper$Context@36a05d78
Mapper.................
key:3  value:54
data:54 context:org.apache.hadoop.mapreduce.Mapper$Context@36a05d78
Mapper.................
key:6  value:6
data:6 context:org.apache.hadoop.mapreduce.Mapper$Context@36a05d78
14/09/21 17:44:34 INFO mapred.MapTask: Starting flush of map output
14/09/21 17:44:34 INFO mapred.MapTask: Finished spill 0
14/09/21 17:44:34 INFO mapred.Task: Task:attempt_local_0001_m_000002_0 is done. And is in the process of commiting
14/09/21 17:44:37 INFO mapred.LocalJobRunner:
14/09/21 17:44:37 INFO mapred.Task: Task 'attempt_local_0001_m_000002_0' done.
14/09/21 17:44:37 INFO mapred.Task:  Using ResourceCalculatorPlugin : org.apache.hadoop.util.LinuxResourceCalculatorPlugin@3c521e5d
14/09/21 17:44:37 INFO mapred.LocalJobRunner:
14/09/21 17:44:37 INFO mapred.Merger: Merging 3 sorted segments
14/09/21 17:44:37 INFO mapred.Merger: Down to the last merge-pass, with 3 segments left of total size: 146 bytes
14/09/21 17:44:37 INFO mapred.LocalJobRunner:
Reducer.................
key:2  value:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@38839cf7
linenum:1  key:2 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
Reducer.................
key:6  value:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@38839cf7
linenum:2  key:6 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
Reducer.................
key:15  value:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@38839cf7
linenum:3  key:15 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
Reducer.................
key:22  value:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@38839cf7
linenum:4  key:22 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
Reducer.................
key:26  value:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@38839cf7
linenum:5  key:26 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
Reducer.................
key:32  value:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@38839cf7
linenum:6  key:32 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
linenum:7  key:32 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
Reducer.................
key:54  value:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@38839cf7
linenum:8  key:54 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
Reducer.................
key:92  value:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@38839cf7
linenum:9  key:92 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
Reducer.................
key:650  value:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@38839cf7
linenum:10  key:650 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
Reducer.................
key:654  value:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@38839cf7
linenum:11  key:654 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
Reducer.................
key:756  value:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@38839cf7
linenum:12  key:756 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
Reducer.................
key:5956  value:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@38839cf7
linenum:13  key:5956 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
Reducer.................
key:65223  value:org.apache.hadoop.mapreduce.ReduceContext$ValueIterable@38839cf7
linenum:14  key:65223 context:org.apache.hadoop.mapreduce.Reducer$Context@23475bbf
14/09/21 17:44:37 INFO mapred.Task: Task:attempt_local_0001_r_000000_0 is done. And is in the process of commiting
14/09/21 17:44:37 INFO mapred.LocalJobRunner:
14/09/21 17:44:37 INFO mapred.Task: Task attempt_local_0001_r_000000_0 is allowed to commit now
14/09/21 17:44:37 INFO output.FileOutputCommitter: Saved output of task 'attempt_local_0001_r_000000_0' to hdfs://localhost:9000/user/hadoop/sort_output
14/09/21 17:44:40 INFO mapred.LocalJobRunner: reduce > reduce
14/09/21 17:44:40 INFO mapred.Task: Task 'attempt_local_0001_r_000000_0' done.
14/09/21 17:44:41 INFO mapred.JobClient:  map 100% reduce 100%
14/09/21 17:44:41 INFO mapred.JobClient: Job complete: job_local_0001
14/09/21 17:44:41 INFO mapred.JobClient: Counters: 22
14/09/21 17:44:41 INFO mapred.JobClient:   Map-Reduce Framework
14/09/21 17:44:41 INFO mapred.JobClient:     Spilled Records=28
14/09/21 17:44:41 INFO mapred.JobClient:     Map output materialized bytes=158
14/09/21 17:44:41 INFO mapred.JobClient:     Reduce input records=14
14/09/21 17:44:41 INFO mapred.JobClient:     Virtual memory (bytes) snapshot=0
14/09/21 17:44:41 INFO mapred.JobClient:     Map input records=14
14/09/21 17:44:41 INFO mapred.JobClient:     SPLIT_RAW_BYTES=345
14/09/21 17:44:41 INFO mapred.JobClient:     Map output bytes=112
14/09/21 17:44:41 INFO mapred.JobClient:     Reduce shuffle bytes=0
14/09/21 17:44:41 INFO mapred.JobClient:     Physical memory (bytes) snapshot=0
14/09/21 17:44:41 INFO mapred.JobClient:     Reduce input groups=13
14/09/21 17:44:41 INFO mapred.JobClient:     Combine output records=0
14/09/21 17:44:41 INFO mapred.JobClient:     Reduce output records=14
14/09/21 17:44:41 INFO mapred.JobClient:     Map output records=14
14/09/21 17:44:41 INFO mapred.JobClient:     Combine input records=0
14/09/21 17:44:41 INFO mapred.JobClient:     CPU time spent (ms)=0
14/09/21 17:44:41 INFO mapred.JobClient:     Total committed heap usage (bytes)=1325400064
14/09/21 17:44:41 INFO mapred.JobClient:   File Input Format Counters
14/09/21 17:44:41 INFO mapred.JobClient:     Bytes Read=48
14/09/21 17:44:41 INFO mapred.JobClient:   FileSystemCounters
14/09/21 17:44:41 INFO mapred.JobClient:     HDFS_BYTES_READ=161
14/09/21 17:44:41 INFO mapred.JobClient:     FILE_BYTES_WRITTEN=162878
14/09/21 17:44:41 INFO mapred.JobClient:     FILE_BYTES_READ=3682
14/09/21 17:44:41 INFO mapred.JobClient:     HDFS_BYTES_WRITTEN=81
14/09/21 17:44:41 INFO mapred.JobClient:   File Output Format Counters
14/09/21 17:44:41 INFO mapred.JobClient:     Bytes Written=81

 

5、运行结果：

1    2
2    6
3    15
4    22
5    26
6    32
7    32
8    54
9    92
10    650
11    654
12    756
13    5956
14    65223