大数据之Hadoop(MapReduce)：Map输出端采用压缩

Posted 2021-06-27 浊酒南街

目录

• 1.Hadoop源码支持的压缩格式有：BZip2Codec 、DefaultCodec
• 2.Mapper保持不变
• 3.Reducer保持不变

即使你的MapReduce的输入输出文件都是未压缩的文件，你仍然可以对Map任务的中间结果输出做压缩，因为它要写在硬盘并且通过网络传输到Reduce节点，对其压缩可以提高很多性能，这些工作只要设置两个属性即可，我们来看下代码怎么设置。

1.Hadoop源码支持的压缩格式有：BZip2Codec 、DefaultCodec

package com.jinghang.mapreduce.compress;
import java.io.IOException;
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 WordCountDriver {

	public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

		Configuration configuration = new Configuration();

		// 开启map端输出压缩
	configuration.setBoolean("mapreduce.map.output.compress", true);
		// 设置map端输出压缩方式
	configuration.setClass("mapreduce.map.output.compress.codec", BZip2Codec.class, CompressionCodec.class);

		Job job = Job.getInstance(configuration);

		job.setJarByClass(WordCountDriver.class);

		job.setMapperClass(WordCountMapper.class);
		job.setReducerClass(WordCountReducer.class);

		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);

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

		FileInputFormat.setInputPaths(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));

		boolean result = job.waitForCompletion(true);

		System.exit(result ? 1 : 0);
	}
}

2.Mapper保持不变

package com.jinghang.mapreduce.compress;
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>{

Text k = new Text();
	IntWritable v = new IntWritable(1);

	@Override
	protected void map(LongWritable key, Text value, Context context)throws IOException, InterruptedException {

		// 1 获取一行
		String line = value.toString();

		// 2 切割
		String[] words = line.split(" ");

		// 3 循环写出
		for(String word:words){
k.set(word);
			context.write(k, v);
		}
	}
}

3.Reducer保持不变

package com.jinghang.mapreduce.compress;
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

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

	IntWritable v = new IntWritable();

	@Override
	protected void reduce(Text key, Iterable<IntWritable> values,
			Context context) throws IOException, InterruptedException {
		
		int sum = 0;

		// 1 汇总
		for(IntWritable value:values){
			sum += value.get();
		}
		
        v.set(sum);

        // 2 输出
		context.write(key, v);
	}
}