Linux巩固记录（5） hadoop 2.7.4下自己编译代码并运行MapReduce程序

[root@master classes]# tree /home/jars/
/home/jars/
├── commons-cli-1.4.jar
├── hadoop-common-2.7.4.jar
└── hadoop-mapreduce-client-core-2.7.4.jar

[root@master classes]# 
[root@master classes]# pwd
/home/classes
[root@master classes]# tree
.

0 directories, 0 files
[root@master classes]# tree /home/javaFile/
/home/javaFile/
└── WordCount.java

0 directories, 1 file
[root@master classes]# tree /home/jars/
/home/jars/
├── commons-cli-1.4.jar
├── hadoop-common-2.7.4.jar
└── hadoop-mapreduce-client-core-2.7.4.jar

0 directories, 3 files
[root@master classes]# javac -classpath .:/home/jars/* -d /home/classes/ /home/javaFile/WordCount.java 
[root@master classes]# tree 
.
├── WordCount.class
├── WordCount$IntSumReducer.class
└── WordCount$TokenizerMapper.class

0 directories, 3 files
[root@master classes]# jar -cvf wordc.jar ./*.class
added manifest
adding: WordCount.class(in = 1907) (out= 1040)(deflated 45%)
adding: WordCount$IntSumReducer.class(in = 1739) (out= 742)(deflated 57%)
adding: WordCount$TokenizerMapper.class(in = 1736) (out= 753)(deflated 56%)
[root@master classes]# tree
.
├── wordc.jar
├── WordCount.class
├── WordCount$IntSumReducer.class
└── WordCount$TokenizerMapper.class

0 directories, 4 files
[root@master classes]# /home/hadoop-2.7.4/bin/hadoop jar /home/classes/wordc.jar WordCount /hdfs-input.txt /result-self-compile
17/09/02 02:11:45 INFO client.RMProxy: Connecting to ResourceManager at master/192.168.0.80:8032
17/09/02 02:11:47 INFO input.FileInputFormat: Total input paths to process : 1
17/09/02 02:11:47 INFO mapreduce.JobSubmitter: number of splits:1
17/09/02 02:11:47 INFO mapreduce.JobSubmitter: Submitting tokens for job: job_1504320356950_0010
17/09/02 02:11:47 INFO impl.YarnClientImpl: Submitted application application_1504320356950_0010
17/09/02 02:11:47 INFO mapreduce.Job: The url to track the job: http://master:8088/proxy/application_1504320356950_0010/
17/09/02 02:11:47 INFO mapreduce.Job: Running job: job_1504320356950_0010
17/09/02 02:11:56 INFO mapreduce.Job: Job job_1504320356950_0010 running in uber mode : false
17/09/02 02:11:56 INFO mapreduce.Job:  map 0% reduce 0%
17/09/02 02:12:02 INFO mapreduce.Job:  map 100% reduce 0%
17/09/02 02:12:09 INFO mapreduce.Job:  map 100% reduce 100%
17/09/02 02:12:09 INFO mapreduce.Job: Job job_1504320356950_0010 completed successfully
17/09/02 02:12:10 INFO mapreduce.Job: Counters: 49
    File System Counters
        FILE: Number of bytes read=118
        FILE: Number of bytes written=241697
        FILE: Number of read operations=0
        FILE: Number of large read operations=0
        FILE: Number of write operations=0
        HDFS: Number of bytes read=174
        HDFS: Number of bytes written=76
        HDFS: Number of read operations=6
        HDFS: Number of large read operations=0
        HDFS: Number of write operations=2
    Job Counters 
        Launched map tasks=1
        Launched reduce tasks=1
        Data-local map tasks=1
        Total time spent by all maps in occupied slots (ms)=3745
        Total time spent by all reduces in occupied slots (ms)=4081
        Total time spent by all map tasks (ms)=3745
        Total time spent by all reduce tasks (ms)=4081
        Total vcore-milliseconds taken by all map tasks=3745
        Total vcore-milliseconds taken by all reduce tasks=4081
        Total megabyte-milliseconds taken by all map tasks=3834880
        Total megabyte-milliseconds taken by all reduce tasks=4178944
    Map-Reduce Framework
        Map input records=6
        Map output records=12
        Map output bytes=118
        Map output materialized bytes=118
        Input split bytes=98
        Combine input records=12
        Combine output records=9
        Reduce input groups=9
        Reduce shuffle bytes=118
        Reduce input records=9
        Reduce output records=9
        Spilled Records=18
        Shuffled Maps =1
        Failed Shuffles=0
        Merged Map outputs=1
        GC time elapsed (ms)=155
        CPU time spent (ms)=1430
        Physical memory (bytes) snapshot=299466752
        Virtual memory (bytes) snapshot=4159479808
        Total committed heap usage (bytes)=141385728
    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=76
    File Output Format Counters 
        Bytes Written=76
[root@master classes]# /home/hadoop-2.7.4/bin/hadoop fs -ls /
Found 3 items
-rw-r--r--   2 root supergroup         76 2017-09-02 00:57 /hdfs-input.txt
drwxr-xr-x   - root supergroup          0 2017-09-02 02:12 /result-self-compile
drwx------   - root supergroup          0 2017-09-02 02:11 /tmp
[root@master classes]# 
[root@master classes]# 

package org.apache.hadoop.examples;

import java.io.IOException;
import java.util.StringTokenizer;

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 WordCount {

  public static class TokenizerMapper 
       extends Mapper<Object, Text, Text, IntWritable>{
    
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
      
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one);
      }
    }
  }
  
  public static class IntSumReducer 
       extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();

    public void reduce(Text key, Iterable<IntWritable> values, 
                       Context context
                       ) throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }
      result.set(sum);
      context.write(key, result);
    }
  }

  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length < 2) {
      System.err.println("Usage: wordcount <in> [<in>...] <out>");
      System.exit(2);
    }
    Job job = Job.getInstance(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    for (int i = 0; i < otherArgs.length - 1; ++i) {
      FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
    }
    FileOutputFormat.setOutputPath(job,
      new Path(otherArgs[otherArgs.length - 1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}