大数据——mapreduce打散倾斜方式解决reduce task的负载均衡

打散倾斜原理：
1、获取NumReduceTasks的个数，并将其随机
2、在map结果的返回值中，将随机数拼接到key上。
3、得出的结果再重新进行mapreduce计算，将后缀切掉，重新聚合。

第一次mapreduce：

public class SkewWordcount {

	public static class SkewWordcountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
		Random random = new Random();
		Text k = new Text();
		IntWritable v = new IntWritable(1);
		int numReduceTasks = 0;

		@Override
		protected void setup(Mapper<LongWritable, Text, Text, IntWritable>.Context context)
				throws IOException, InterruptedException {
			numReduceTasks = context.getNumReduceTasks();
		}

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

			String[] words = value.toString().split(" ");
			for (String w : words) {
				k.set(w + "\001" + random.nextInt(numReduceTasks));
				context.write(k, v);

			}

		}

	}

	public static class SkewWordcountReducer 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 count = 0;
			for (IntWritable value : values) {
				count += value.get();
			}
			v.set(count);
			context.write(key, v);
		}

	}

	public static void main(String[] args) throws Exception {

		
		Configuration conf = new Configuration();

		Job job = Job.getInstance(conf);
		
		job.setJarByClass(SkewWordcount.class);
		
		job.setMapperClass(SkewWordcountMapper.class);
		job.setReducerClass(SkewWordcountReducer.class);
		
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		// 设置maptask端的局部聚合逻辑类
		job.setCombinerClass(SkewWordcountReducer.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		FileInputFormat.setInputPaths(job, new Path("f:/mrdata/wordcount/input"));
		FileOutputFormat.setOutputPath(job, new Path("f:/mrdata/wordcount/skew-out"));
		
		job.setNumReduceTasks(3);
		
		boolean res = job.waitForCompletion(true);
		System.exit(res?0:1);
	
	}
	
	
}

第二次mapreduce

public class SkewWordcount2 {

	public static class SkewWordcountMapper 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 {
			String[] wordAndCount = value.toString().split("\t");
			v.set(Integer.parseInt(wordAndCount[1]));
			k.set(wordAndCount[0].split("\001")[0]);
			
			context.write(k, v);

		}

	}

	public static class SkewWordcountReducer 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 count = 0;
			for (IntWritable value : values) {
				count += value.get();
			}
			v.set(count);
			context.write(key, v);
		}

	}

	public static void main(String[] args) throws Exception {

		
		Configuration conf = new Configuration();

		Job job = Job.getInstance(conf);
		
		job.setJarByClass(SkewWordcount2.class);
		
		job.setMapperClass(SkewWordcountMapper.class);
		job.setReducerClass(SkewWordcountReducer.class);
		
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(IntWritable.class);
		
		// 设置maptask端的局部聚合逻辑类
		job.setCombinerClass(SkewWordcountReducer.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
		
		FileInputFormat.setInputPaths(job, new Path("f:/mrdata/wordcount/skew-out"));
		FileOutputFormat.setOutputPath(job, new Path("f:/mrdata/wordcount/skew-out2"));
		
		job.setNumReduceTasks(3);
		
		boolean res = job.waitForCompletion(true);
		System.exit(res?0:1);
	
	}
	
	
}