MR Combiner的介绍与使用

什么是Combiner

• Combiner的父类就是Reducer。
• Combiner和Reducer的区别是运行位置不同。Combiner运行在每个maptask所在节点上，Reducer是接收全局所有Mapper的输出结果。
• Combiner的作用是对每一个maptask的输出结果进行局部汇总，减小网络IO和磁盘IO。
• Combiner的使用前提是不能影响业务逻辑。比如求平均数就不可使用Combiner。

Combiner的使用（以wordcount为例）

1.创建Mapper类。

package com.aura.hadoop.combiner;

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

import java.io.IOException;

/**
 * @author panghu
 * @description
 * @create 2021-02-15-18:22
 */
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
    private Text word = new Text();
    private IntWritable one = new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        word.set(value);
        context.write(word, one);
    }
}

2.创建Reducer类

package com.aura.hadoop.combiner;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

/**
 * @author panghu
 * @description
 * @create 2021-02-15-18:26
 */
public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
    private Text word = new Text();
    private IntWritable cnt = new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int sum = 1;
        for (IntWritable value : values) {
            sum += value.get();
        }
        word.set(key);
        cnt.set(sum);
        context.write(word, cnt);
    }
}

3.创建Driver类。因为Combiner本质上就是一个Reducer，我们可以直接指定Combiner类是我们创建的Reducer类。

package com.aura.hadoop.combiner;

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

/**
 * @author panghu
 * @description
 * @create 2021-02-15-18:31
 */
public class WordCountDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Job job = Job.getInstance(new Configuration());

        job.setJarByClass(WordCountDriver.class);

        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        // 设置combiner，combiner本质上就是一个reducer
        job.setCombinerClass(WordCountReducer.class);

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

        FileInputFormat.setInputPaths(job, new Path("D:\\data\\hadoopdata\\word.txt"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\data\\out\\wordcount"));

        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);

    }
}