MapReduce Join
Reduce Join
Map 端的主要工作:为来自不同表或文件的 key/value 对,打标签以区别不同来源的记录。然后用连接字段作为 key,其余部分和新加的标志作为 value,最后进行输出。
Reduce 端的主要工作:在 Reduce 端以连接字段作为 key 的分组已经完成,我们只需要在每一个分组当中将那些来源于不同文件的记录(在 Map 阶段已经打标志)分开,最后进行合并就 ok 了。
Reduce Join 案例
将商品信息表中数据根据商品 pid 合并到订单数据表中。
t_order
1001 01 1
1002 02 2
1003 03 3
1004 01 4
1005 02 5
1006 03 6
pd.txt
01 小米
02 华为
03 格力
通过将关联条件作为 Map 输出的 key,将两表满足 Join 条件的数据并携带数据所来源的文件信息,发往同一个 ReduceTask,在 Reduce 中进行数据的串联。
(1)创建商品和订单合并后的 TableBean 类
package com.xiaoqiu.mapreduce.ReduceJoin;
import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
/**
* @author 小邱
* @version 0.0.1
* @description TableBean
* @since 2021/12/4 18:49
*/
public class TableBean implements Writable {
private String id; //订单 id
private String pid; //产品 id
private int amount; //产品数量
private String pname; //产品名称
private String flag; //判断是 order 表还是 pd 表的标志字段
public TableBean() {
}
@Override
public void write(DataOutput dataOutput) throws IOException {
dataOutput.writeUTF(id);
dataOutput.writeUTF(pid);
dataOutput.writeInt(amount);
dataOutput.writeUTF(pname);
dataOutput.writeUTF(flag);
}
@Override
public void readFields(DataInput dataInput) throws IOException {
this.id = dataInput.readUTF();
this.pid = dataInput.readUTF();
this.amount = dataInput.readInt();
this.pname = dataInput.readUTF();
this.flag = dataInput.readUTF();
}
public TableBean(String id, String pid, int amount, String pname, String flag) {
this.id = id;
this.pid = pid;
this.amount = amount;
this.pname = pname;
this.flag = flag;
}
public String getId() {
return id;
}
public void setId(String id) {
this.id = id;
}
public String getPid() {
return pid;
}
public void setPid(String pid) {
this.pid = pid;
}
public int getAmount() {
return amount;
}
public void setAmount(int amount) {
this.amount = amount;
}
public String getPname() {
return pname;
}
public void setPname(String pname) {
this.pname = pname;
}
public String getFlag() {
return flag;
}
public void setFlag(String flag) {
this.flag = flag;
}
@Override
public String toString() {
return id + "\t" + pname + "\t" + amount;
}
}
(2)编写 TableMapper 类
package com.xiaoqiu.mapreduce.ReduceJoin;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import java.io.IOException;
/**
* @author 小邱
* @version 0.0.1
* @description TableMapper
* @since 2021/12/4 18:55
*/
public class TableMapper extends Mapper<LongWritable, Text,Text,TableBean> {
private String fileName;
private Text outK = new Text();
private TableBean outV = new TableBean();
@Override
protected void setup(Context context) throws IOException, InterruptedException {
//获取文件名
FileSplit split = (FileSplit) context.getInputSplit();
fileName = split.getPath().getName();
}
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//获取一行
String s = value.toString();
//判断是哪个文件,然后针对文件进行不同的操作
if (fileName.contains("order")){
String[] split = s.split("\t");
//封装 outK
outK.set(split[1]);
//封装 outV
outV.setId(split[0]);
outV.setPid(split[1]);
outV.setAmount(Integer.parseInt(split[2]));
outV.setPname("");
outV.setFlag("order");
}else{
String[] split = s.split("\t");
//封装 outK
outK.set(split[0]);
//封装 outV
outV.setId("");
outV.setPid(split[0]);
outV.setAmount(0);
outV.setPname(split[1]);
outV.setFlag("pd");
}
//写出 KV
context.write(outK,outV);
}
}
(3)编写 TableReducer 类
package com.xiaoqiu.mapreduce.ReduceJoin;
import org.apache.commons.beanutils.BeanUtils;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
import java.lang.reflect.InvocationTargetException;
import java.util.ArrayList;
/**
* @author 小邱
* @version 0.0.1
* @description TableReducer
* @since 2021/12/4 19:09
*/
public class TableReducer extends Reducer<Text, TableBean, TableBean, NullWritable> {
@Override
protected void reduce(Text key, Iterable<TableBean> values, Context context) throws IOException, InterruptedException {
ArrayList<TableBean> orderBeans = new ArrayList<>();
TableBean pdBean = new TableBean();
for (TableBean value : values) {
//判断数据来自哪个表
if ("order".equals(value.getFlag())) { //订单表
//创建一个临时 TableBean 对象接收 value
TableBean tmpOrderBean = new TableBean();
try {
BeanUtils.copyProperties(tmpOrderBean, value);
} catch (IllegalAccessException e) {
e.printStackTrace();
} catch (InvocationTargetException e) {
e.printStackTrace();
}
//将临时 TableBean 对象添加到集合 orderBeans
orderBeans.add(tmpOrderBean);
} else { //商品表
try {
BeanUtils.copyProperties(pdBean, value);
} catch (IllegalAccessException e) {
e.printStackTrace();
} catch (InvocationTargetException e) {
e.printStackTrace();
}
}
}
//遍历集合 orderBeans,替换掉每个 orderBean 的 pid 为 pname,然后写出
for (TableBean orderBean : orderBeans) {
orderBean.setPname(pdBean.getPname());
//写出修改后的 orderBean 对象
context.write(orderBean, NullWritable.get());
}
}
}
(4)编写 TableDriver 类
package com.xiaoqiu.mapreduce.ReduceJoin;
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;
/**
* @author 小邱
* @version 0.0.1
* @description TableDriver
* @since 2021/12/4 19:17
*/
public class TableDriver {
public static void main(String[] args) throws IOException,ClassNotFoundException, InterruptedException {
Job job = Job.getInstance(new Configuration());
job.setJarByClass(TableDriver.class);
job.setMapperClass(TableMapper.class);
job.setReducerClass(TableReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(TableBean.class);
job.setOutputKeyClass(TableBean.class);
job.setOutputValueClass(NullWritable.class);
FileInputFormat.setInputPaths(job, new Path("F:\\share\\inputTable"));
FileOutputFormat.setOutputPath(job, new Path("F:\\share\\output"));
boolean b = job.waitForCompletion(true);
System.exit(b ? 0 : 1);
}
}
测试结果
总结
缺点:这种方式中,合并的操作是在 Reduce 阶段完成,Reduce 端的处理压力太大,Map节点的运算负载则很低,资源利用率不高,且在 Reduce 阶段极易产生数据倾斜。
解决方案:Map 端实现数据合并。
Map Join
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。
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
MapJoin 适用于关联表中有小表的情形。
(1)先在 MapJoinDriver 驱动类中添加缓存文件
package com.xiaoqiu.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;
/**
* @author 小邱
* @version 0.0.1
* @description TableDriver
* @since 2021/12/4 19:17
*/
public class TableDriver {
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(TableDriver.class);
// 3 关联 mapper
job.setMapperClass(TableMapper.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:///F:/share/inputTable/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("F:\\share\\inputTable\\order.txt"));
FileOutputFormat.setOutputPath(job, new Path("F:\\share\\output"));
// 7 提交
boolean b = job.waitForCompletion(true);
System.exit(b ? 0 : 1);
}
}
(2)在 MapJoinMapper 类中的 setup 方法中读取缓存文件
package com.xiaoqiu.mapreduce.MapJoin;
import org.apache.commons.lang.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;
/**
* @author 小邱
* @version 0.0.1
* @description TableMapper
* @since 2021/12/4 18:55
*/
public class TableMapper 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());
}
}