MapJoin

Map Join适用于一张表十分小、一张表很大的场景。

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。

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"));

案例

和 Reduce Join 的案例一样，只不过这里是将合并的部分放在Mapper来做，完全抛弃掉Reduce

Mapper类

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;
import java.util.Map;

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

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

    //任务开始前将pd数据缓存进pdMap
    @Override
    protected void setup(Context context) throws IOException, InterruptedException {
        //通过缓存文件得到小表数据pd.txt
        URI[] cacheFiles = context.getCacheFiles();
        Path path = new Path(cacheFiles[0]);

        //获取文件系统对象,并开流
        FileSystem fs = FileSystem.get(context.getConfiguration());
        FSDataInputStream fis = fs.open(path);

        //通过包装流转换为reader,方便按行读取
        BufferedReader reader = new BufferedReader(new InputStreamReader(fis, "UTF-8"));

        //逐行读取，按行处理
        String line;
        while (StringUtils.isNotEmpty(line = reader.readLine())) {
            //切割一行
            String[] split = line.split("\t");
            pdMap.put(split[0], split[1]);
        }

        //关流
        IOUtils.closeStream(reader);
    }

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

        //读取大表数据
        String[] fields = value.toString().split("\t");
        //通过大表每行数据的pid,去pdMap里面取出pname
        String pname = pdMap.get(fields[1]);
        //将大表每行数据的pid替换为pname
        text.set(fields[0] + "\t" + pname + "\t" + fields[2]);
        //写出
        context.write(text,NullWritable.get());
    }
}

Driver类

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, URISyntaxException, ClassNotFoundException, InterruptedException {

        // 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("file:///C:/Users/MaHe666/Desktop/input/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("C:\\Users\\MaHe666\\Desktop\\input\\order.txt"));
        FileOutputFormat.setOutputPath(job, new Path("D:\\output"));
        
        // 7 提交
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}