Shuffle机制

Map方法之后，Reduce方法之前的数据处理过程称之为Shuffle

 Partition分区

 默认分区是根据key的hashCode对ReduceTasks个数取模得到的。用户没法控制哪个key存在哪个分区

自定义Partitioner步骤

（1）自定义类继承Partitioner,重写getPartition()方法

 （2）在Job驱动中，设置自定义Partitioner

 (3)  自定义Partition后，要根据自定义Partitioner的逻辑设置相应数量的ReduceTask（）

4 分区总结

 （1） 如果ReduceTask   的数量>getPartiton的结果数，则会多产生几个空的输出文件part-r-000xx;

(2)如果1

（3）如果ReduceTask的数量=1,则不管MapTask端输出多少个分区文件，最终结果都会交给一个ReduceTask，最终也会只产生一个结果文件part-r-00000;

(4)分区号必须从零开始，逐一累加

Partition分区案例实操

（1）需求

将 统计结果按照手机归属地不同省份输出到不同文件中

（1）输入数据

phone_data

(2)期望输出结果

手机号136、137、138、139开头都分别放到一个独立的4个文件中，其他开头的放到一个文件中。

（3）代码

分区类

package com.chenxiang.mapreduce.partioner2;
 
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Partitioner;
 
public class ProvincePartitioner extends Partitioner {
    @Override
    public int getPartition(Text text, FlowBean flowBean, int numPartitions) {
 
        //text手机号
        String phone = text.toString();
        String prePhone = phone.substring(0, 3);
        int partition;
        if ("136".equals(prePhone)) {
            partition = 0;
        } else if ("137".equals(prePhone)) {
            partition = 1;
 
        } else if ("138".equals(prePhone)) {
            partition = 2;
        } else if ("139".equals(prePhone)) {
            partition = 3;
        } else {
            partition = 4;
        }
 
        return partition;
    }
}

Map类

package com.chenxiang.mapreduce.partioner2;
 
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
 
import java.io.IOException;
 
 
public class FlowMapper extends Mapper {
 
    private Text outK = new Text();
    private FlowBean outV = new FlowBean();
 
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        // //获取一行信息
        String line = value.toString();
 
        String[] split = line.split("\t");//切割
 
        // 抓取数据
 
        String phone = split[1];
        String up = split[split.length - 3];
        String down = split[split.length - 2];
 
        //封装
            outK.set(phone);
            outV.setUpFlow(Long.parseLong(up));
            outV.setDownFlow(Long.parseLong(down));
            outV.setSumFlow();
 
            // 写出
        context.write(outK,outV);
 
 
    }
}

Reducer类

package com.chenxiang.mapreduce.partioner2;
 
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
 
import java.io.IOException;
 
public class FlowReducer extends Reducer {
 
    private FlowBean outV =new FlowBean();
    @Override
    protected void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException {
 
 
        //遍历累加值
        long totalUp=0;
        long totalDown=0;
        for(FlowBean value:values)
        {
            totalUp+=value.getUpFlow();
            totalDown+=value.getDownFlow();
 
        }
        //2 封装
        outV.setDownFlow(totalDown);
        outV.setUpFlow(totalUp);
        outV.setSumFlow();
        context.write(key,outV);
 
    }
}

Driver类

package com.chenxiang.mapreduce.partioner2;
 
 
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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.output.FileOutputFormat;
 
import java.io.IOException;
 
public class FlowDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
 
        // 1 获取job
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
 
        //2 设置jar
        job.setJarByClass(FlowDriver.class);
        //3 关联 mapper reducer
 
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);
 
        // 4 设置Mapper输出类型
        job.setMapOutputValueClass(FlowBean.class);
        job.setMapOutputKeyClass(Text.class);
 
        job.setPartitionerClass(ProvincePartitioner.class);
        job.setNumReduceTasks(5);
        //设置Mapper最终输出路径
        job.setOutputValueClass(FlowBean.class);
        job.setOutputKeyClass(Text.class);
        //6 设置数据的输入路径和输出路径
        FileInputFormat.setInputPaths(job, new Path("D:\\input\\inputflow"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\output\\output114514"));
 
        //7 提交job
 
        boolean result = job.waitForCompletion(true);
 
        System.exit(result ? 0 : 1);
 
 
    }
}

bean类

package com.chenxiang.mapreduce.partioner2;
 
import org.apache.hadoop.io.Writable;
 
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
 
/*
 *
 * 1 定义类实现writable接口
 * 2 重写序列化和反序列化方法
 * 3  空参构造方法
 * 4 toString 方法*/
public class FlowBean implements Writable {
    private long upFlow;//上行流量
    private long downFlow;//下行流量
    private long sumFlow;//总流量
    //空参构造
 
    public long getUpFlow() {
        return upFlow;
    }
 
    public void setUpFlow(long upFlow) {
        this.upFlow = upFlow;
    }
 
    public long getDownFlow() {
        return downFlow;
    }
 
    public void setDownFlow(long downFlow) {
        this.downFlow=downFlow;
 
    }
 
    public long getSumFlow() {
        return sumFlow;
    }
 
    public void setSumFlow() {
         this.sumFlow= this.upFlow+this.downFlow;
    }
 
    public FlowBean() {
    }
 
    @Override
    public void write(DataOutput out) throws IOException {
        out.writeLong(upFlow);
        out.writeLong(downFlow);
        out.writeLong(sumFlow);
 
 
    }
 
    @Override
    public void readFields(DataInput in) throws IOException {
 
       this.upFlow= in.readLong();
       this.downFlow=in.readLong();
       this.sumFlow=in.readLong();
 
    }
 
    @Override
    public String toString() {
        return upFlow+"\t"+downFlow+"\t"+sumFlow;    }
}