结合案例讲解MapReduce重要知识点 ---------- Combiner

• combiner是MR程序中Mapper和Reducer之外的一种组件

• combiner组件的父类就是Reducer

• combiner和reducer的区别在于运行的位置：

  • Combiner是在每一个maptask所在的节点运行

  • Reducer是接收全局所有Mapper的输出结果；

• combiner的意义就是对每一个maptask的输出进行局部汇总，以减小网络传输量。具体实现步骤：

  1. 自定义一个combiner继承Reducer，重写reduce方法

  2. 在job中设置： job.setCombinerClass(CustomCombiner.class)

• combiner能够应用的前提是不能影响最终的业务逻辑，而且combiner的输出kv应该跟reducer的输入kv类型要对应起来

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
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.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;


public class WordCountCombiner extends ToolRunner implements Tool{

	/**
	 * 自定义的myMapper
	 * @author lyd
	 *
	 */
	static class MyMapper extends Mapper{

		@Override
		protected void setup(Context context)throws IOException, InterruptedException {
		}

		@Override
		protected void map(LongWritable key, Text value,Context context)
				throws IOException, InterruptedException {
			String line = value.toString();
			StringTokenizer st = new StringTokenizer(line);
			while (st.hasMoreTokens()) {
				context.write(new Text(st.nextToken()), new Text(1+""));
			}
		}

		@Override
		protected void cleanup(Context context)throws IOException, InterruptedException {
		}
		
	}
	
	/**
	 * 自定义MyReducer
	 * @author lyd
	 *
	 */
	static class MyReducer extends Reducer{

		@Override
		protected void setup(Context context)throws IOException, InterruptedException {
		}
		
		@Override
		protected void reduce(Text key, Iterable value,Context context)
				throws IOException, InterruptedException {
			int counter = 0;
			for (Text t: value) {
				counter += Integer.parseInt(t.toString());
			}
			context.write(key, new Text(counter+""));
		}
		
		@Override
		protected void cleanup(Context context)throws IOException, InterruptedException {
		}
	}
	
	
	@Override
	public void setConf(Configuration conf) {
		conf.set("fs.defaultFS", "hdfs://hadoop01:9000");
	}

	@Override
	public Configuration getConf() {
		return new Configuration();
	}
	
	/**
	 * 驱动方法
	 */
	@Override
	public int run(String[] args) throws Exception {
		//1、获取conf对象
		Configuration conf = getConf();
		//2、创建job
		Job job = Job.getInstance(conf, "model01");
		//3、设置运行job的class
		job.setJarByClass(WordCountCombiner.class);
		//4、设置map相关属性
		job.setMapperClass(MyMapper.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(Text.class);
		FileInputFormat.addInputPath(job, new Path(args[0]));
		
		//设置combiner类
		//job.setCombinerClass(WCC.class);
		job.setCombinerClass(MyReducer.class);
		
		//5、设置reduce相关属性
		job.setReducerClass(MyReducer.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(Text.class);
		//判断输出目录是否存在，若存在则删除
		FileSystem fs = FileSystem.get(conf);
		if(fs.exists(new Path(args[1]))){
			fs.delete(new Path(args[1]), true);
		}
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		
		//6、提交运行job
		int isok = job.waitForCompletion(true) ? 0 : 1;
		return isok;
	}
	
	/**
	 * job的主入口
	 * @param args
	 */
	public static void main(String[] args) {
		try {
			//对输入参数作解析
			String [] argss = new GenericOptionsParser(new Configuration(), args).getRemainingArgs();
			System.exit(ToolRunner.run(new WordCountCombiner(), argss));
		} catch (Exception e) {
			e.printStackTrace();
		}
	}
}