hadoop之数据倾斜

数据倾斜

1.产生原因   大量的key进入到了一个或者是少数的几个reduce.

2.解决办法：

  　　1.重新设计key；

     2.设计分区类    随机分区 (常用）；

     3.自定义Shuffle机制。   

实例：

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

/**
 * Created by Administrator on 2017/6/1.
 */
public class App {
    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", "file:///");
        conf.set("mapreduce.framework.name", "local");
        Job job = Job.getInstance(conf);
        job.setJobName("WordCount");
        job.setJarByClass(App.class);

        FileInputFormat.addInputPath(job, new Path("d:/mr/wc.txt"));
        FileOutputFormat.setOutputPath(job, new Path("d:/mr/out"));
        
        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        
        job.setNumReduceTasks(3);

        //设置输出kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //设置分区类
        job.setPartitionerClass(RandomPartitioner.class);
        boolean b = job.waitForCompletion(true);
        //进行二次job
        if(b){
            conf = new Configuration();
            conf.set("fs.defaultFS", "file:///");
            conf.set("mapreduce.framework.name", "local");
            job = Job.getInstance(conf);
            job.setJobName("WordCount2");
            job.setJarByClass(App.class);
            FileInputFormat.addInputPath(job, new Path("d:/mr/out/part-r*"));
            FileOutputFormat.setOutputPath(job, new Path("d:/mr/out2"));

            job.setInputFormatClass(KeyValueTextInputFormat.class);

            job.setMapperClass(WordCountMapper2.class);
            job.setReducerClass(WordCountReducer.class);

            job.setNumReduceTasks(3);

            //设置输出kv类型
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(IntWritable.class);
            job.waitForCompletion(true);
        }
    }
}


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;

/**
 * 创建Mapper
 */
public class WordCountMapper extends Mapper<LongWritable,Text,Text,IntWritable> {
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] arr = value.toString().split(" ");
        for(String word : arr){
            context.write(new Text(word),new IntWritable(1));
        }
    }
}



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;

/**
 * 创建Mapper2
 */
public class WordCountMapper2 extends Mapper<Text,Text,Text,IntWritable> {
    protected void map(Text key, Text value, Context context) throws IOException, InterruptedException {
        context.write(key,new IntWritable(Integer.parseInt(value.toString())));
    }
}



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

import java.io.IOException;

/**
 * Reducer
 */
public class WordCountReducer extends Reducer<Text, IntWritable,Text,IntWritable> {
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int count = 0 ;
        for(IntWritable iw : values){
            count = count + iw.get();
        }
        context.write(key,new IntWritable(count));
    }
}


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

import java.util.Random;

/**
 * Created by Administrator on 2017/6/1.
 */
public class RandomPartitioner extends Partitioner<Text,IntWritable>{
    Random r = new Random();
    public int getPartition(Text text, IntWritable intWritable, int numPartitions) {
        return r.nextInt(numPartitions);
    }
}