通过多个Reducers改善hadoop的工作绩效？

Question

我使用MapReduce Jobs Performance进行了一些测试。

1. WithOut Combiner -
2. WithCombiner -

我确信并理解Using Combiner改善了作业的性能。  请在表格中找到工作的统计数据。从理论上讲，使用多个Reducer进行并行处理可以改善Job的运行时间，但统计数据并不能证明这一点。有人可以回答为什么多个减速器没有改善工作性能。

1. 使用1 Reducer
2. 使用10个Reducers

使用Combiner降低10个Reducers性能

CPU time spent (ms)=27380
Physical memory (bytes) snapshot=1430097920
Virtual memory (bytes) snapshot=7202680832
Total committed heap usage (bytes)=502865920
Total time spent by all map tasks (ms)=61027
Total time spent by all reduce tasks (ms)=273752

1合并器的减速器性能

CPU time spent (ms)=17280
Physical memory (bytes) snapshot=491397120
Virtual memory (bytes) snapshot=1753538560
Total committed heap usage (bytes)=291643392
Total time spent by all map tasks (ms)=37374
Total time spent by all reduce tasks (ms)=11416


   Here is the Code : 

   import java.io.IOException;
   import org.apache.hadoop.io.IntWritable;
    import org.apache.hadoop.io.LongWritable;
    import org.apache.hadoop.io.Text;
    import org.apache.hadoop.mapreduce.Mapper;

public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    private Text Words = new Text(); 
    private final static IntWritable one = new IntWritable(1); 
    @Override
    public void map(LongWritable k1, Text v1, Context con) throws IOException, InterruptedException 
    {
        String line = v1.toString(); 
        String tokens[] = line.split(" ");
        int count = tokens.length;
        int i = 0; 
        while (count >= 1)
        {
            //String a1 = tokens[i];    
            if(tokens[i].contains("172"))
            {
                Words.set(tokens[i]);   
            }
            i++;
            count --; 
            con.write(Words, one);
        }


}}

    import java.io.IOException;
import java.lang.Iterable;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapreduce.Reducer;

public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {

    public void reduce(Text key1, Iterable<IntWritable> values1, Context context) throws IOException, InterruptedException  
    {
        int sum=0; 

        IntWritable result = new IntWritable();

        for (IntWritable val : values1)
        {
        sum = sum + val.get(); 
        }
        result.set(sum);
        context.write(key1, result);

    }
}

    import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
//import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;



public class WordCountJob extends Configured implements Tool 

{

    public int  run(String args[]) throws Exception 

    {

        Configuration conf = getConf(); 
        @SuppressWarnings("deprecation")
        Job job =  new Job(conf); 
        job.setJarByClass(WordCountJob.class);

        Path in = new Path(args[0]); 
        Path out = new Path(args[1]); 

        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class); 
        //job.setCombinerClass(WordCountReducer.class);
        job.setNumReduceTasks(1);
        job.getNumReduceTasks(); 
        job.getCluster(); 
        //job.getStartTime();
        //job.getStatus();



        //Location of the Input  File; Type of the File;
        FileInputFormat.addInputPath(job, in);
        job.setInputFormatClass(TextInputFormat.class); 

        //Location of the Output File; Type of the File 
        FileOutputFormat.setOutputPath(job, out); 
        job.setOutputFormatClass(TextOutputFormat.class) ; 

        //Type of the Data written in Output File. 
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        job.waitForCompletion(true); 

        return 0 ;
    }


    public static void main(String pars[]) throws Exception 

    {

            int output = ToolRunner.run(new Configuration(),new WordCountJob(), pars);
            System.exit(output); 
    }



    }