hadoop--Map Join

Map Join

使用场景

Map Join 适用于一张表十分小、一张表很大的场景。

优点

思考:在 Reduce 端处理过多的表，非常容易产生数据倾斜。怎么办?
在 Map 端缓存多张表，提前处理业务逻辑，这样增加 Map 端业务，减少 Reduce 端数
据的压力，尽可能的减少数据倾斜。

具体办法:采用 DistributedCache

1. 在 Mapper 的 setup 阶段，将文件读取到缓存集合中；
2. 在 Driver 驱动类中加载缓存。

缓存普通文件到 Task 运行节点：

job.addCacheFile(new URI("file:///e:/cache/pd.txt")); 

如果是集群运行,需要设置 HDFS 路径：

job.addCacheFile(new URI("hdfs://hadoop102:8020/cache/pd.txt"));

Map Join 案例

需求

：同Reduce Join案例；

需求分析

MapJoin 适用于关联表中有小表的情形。

Map端表合并案例分析(Distributedcache)

源码

MapJoinMapper类

package com.xiaobai.mapreduce.mapjoin;

import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URI;
import java.util.HashMap;

public class MapJoinMapper extends Mapper<LongWritable, Text,Text, NullWritable> {

    private HashMap<String, String> pdMap = new HashMap<>();
    private Text outK = new Text();

    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        //获取缓存的文件，并把文件内容封装到集合 pd.txt
        URI[] cacheFiles = context.getCacheFiles();

        FileSystem fs = FileSystem.get(context.getConfiguration());
        FSDataInputStream fis = fs.open(new Path(cacheFiles[0]));

        //从流中读取数据
        BufferedReader reader = new BufferedReader(new InputStreamReader(fis, "UTF-8"));

        String line;
        while(StringUtils.isNotEmpty(line = reader.readLine())){
            //切割
            String[] fields = line.split("\t");

            //赋值
            pdMap.put(fields[0],fields[1]);
        }
        //关流
        IOUtils.closeStream(reader);
    }

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //处理order.txt
        String line = value.toString();
        String[] fields = line.split("\t");

        //获取pid
        String pname = pdMap.get(fields[1]);

        //获取订单id和订单数量
        //封装
        outK.set(fields[0] + "\t" + pname + "\t" + fields[2]);
        context.write(outK,NullWritable.get());

    }
}

MapJoinDriver类

package com.xiaobai.mapreduce.mapjoin;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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;
import java.net.URI;
import java.net.URISyntaxException;


public class MapJoinDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException, URISyntaxException {
        //1. 获取job信息
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        //2. 设置加载jar包路径
        job.setJarByClass(MapJoinDriver.class);
        //3. 关联mapper
        job.setMapperClass(MapJoinMapper.class);
        //4.设置Map输出kv类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
        //5.设置最终输出kv类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        //加载缓存数据
        job.addCacheFile(new URI("/Users/jane/Desktop/test/JoinTest/pd.txt"));
        //Map端join的逻辑不需要reduce阶段，设置reduceTask数量为0
        job.setNumReduceTasks(0);

        //6. 设置输入输出路径
        FileInputFormat.setInputPaths(job,new Path("/Users/jane/Desktop/test/JoinTest"));
        FileOutputFormat.setOutputPath(job,new Path("/Users/jane/Desktop/hadoop/MapJoinTestOutput"));

        //7. 提交
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}