Hadoop_MapReduce压缩案例

Hadoop_MapReduce压缩案例

---

在map输出端压缩

修改 Hadoop_WordCount单词统计 工程
只需要修改 MyWordCount 的main方法即可：

package com.blu.mywordcount;


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.io.compress.BZip2Codec;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class MyWordCount {
	
	public static void main(String[] args) {
		
		try {
			Configuration conf = new Configuration();
			//设置在mapper输出端进行压缩
			conf.set("mapreduce.map.output.compress", "true");
			//设置压缩方式
			//参数2为要使用的压缩类型
			//参数3为参数2的父类
			conf.setClass("mapreduce.map.output.compress.codec", BZip2Codec.class, CompressionCodec.class);
			
			Job job = Job.getInstance(conf);
			
			//设置运行的类
			job.setJarByClass(MyWordCount.class);
			
			//设置mapper和reducer对应的类
			job.setMapperClass(MyWordCountMapper.class);
			job.setReducerClass(MyWordCountReducer.class);
			
			//运行mapper和最终输出的数据类型
			job.setMapOutputKeyClass(Text.class);
			job.setMapOutputValueClass(IntWritable.class);
			job.setOutputKeyClass(Text.class);
			job.setOutputValueClass(IntWritable.class);
			
			//设置文件的输入和输出的路径
//			hadoop jar example.jar wordcount /input/a.txt /output
			FileInputFormat.addInputPath(job, new Path(args[0]));
			FileOutputFormat.setOutputPath(job, new Path(args[1]));
			
			//运行job
			boolean flag = job.waitForCompletion(true);
			//0表示正常退出
			//1表示不正常退出
			System.exit(flag ?0 : 1);
			
			
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

}

具体修改的内容（配置 Configuration ）：

1. 开启mapper输出端的压缩功能
2. 指定压缩类型

//设置在mapper输出端进行压缩
conf.set("mapreduce.map.output.compress", "true");
//设置压缩方式
//参数2为要使用的压缩类型
//参数3为参数2的父类
conf.setClass("mapreduce.map.output.compress.codec", BZip2Codec.class, CompressionCodec.class);

---

在reduce输出端压缩

同样只需要修改 MyWordCount 的main方法即可：

package com.blu.mywordcount;


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.io.compress.BZip2Codec;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class MyWordCount {
	
	public static void main(String[] args) {
		
		try {
			Configuration conf = new Configuration();
			conf.set("mapreduce.map.output.compress", "true");
			conf.setClass("mapreduce.map.output.compress.codec", BZip2Codec.class, CompressionCodec.class);
			
			Job job = Job.getInstance(conf);
			job.setJarByClass(MyWordCount.class);
			job.setMapperClass(MyWordCountMapper.class);
			job.setReducerClass(MyWordCountReducer.class);
			job.setMapOutputKeyClass(Text.class);
			job.setMapOutputValueClass(IntWritable.class);
			job.setOutputKeyClass(Text.class);
			job.setOutputValueClass(IntWritable.class);
			FileInputFormat.addInputPath(job, new Path(args[0]));
			FileOutputFormat.setOutputPath(job, new Path(args[1]));
			//设置在reduce输出端进行压缩
			FileOutputFormat.setCompressOutput(job, true);
			//设置压缩格式
			FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);
			boolean flag = job.waitForCompletion(true);
			System.exit(flag ?0 : 1);
			
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

}

具体修改的内容（配置 job ）：

1. 开启reduce输出端的压缩功能
2. 指定压缩类型

//设置在reduce输出端进行压缩
FileOutputFormat.setCompressOutput(job, true);
//设置压缩格式
FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);

运行结果：在D:\data\output目录生成以下文件，其中part-r-00000为压缩包格式