Reduce Join
Reduce Join工作原理
Reduce Join案例实操
创建创建完毕:
第一步,对pom.xml文件依赖:
pom.xml
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>com.study</groupId>
<artifactId>join1205</artifactId>
<version>1.0-SNAPSHOT</version>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>8</source>
<target>8</target>
</configuration>
</plugin>
</plugins>
</build>
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>RELEASE</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-core</artifactId>
<version>2.8.2</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.7.2</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.7.2</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>2.7.2</version>
</dependency>
<dependency>
<groupId>jdk.tools</groupId>
<artifactId>jdk.tools</artifactId>
<version>1.8</version>
<scope>system</scope>
<systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
</dependency>
</dependencies>
</project>
接着,java目录文件下创建com.study.reducejoin包、并在该包下创建类:RJComparator、RJMapper、RJReducer、RJDriver
并创建bean包与类
OrderBean.java
package com.study.bean;
import org.apache.hadoop.io.WritableComparable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
public class OrderBean implements WritableComparable<OrderBean> {
private String id;
private String pid;
private int amount;
private String pname;
@Override
public String toString() {
return id + "\t" + pname + "\t" + amount;
}
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;
}
@Override
public int compareTo(OrderBean o) {
int compare = this.pid.compareTo(o.pid);
if (compare == 0) {
return o.pname.compareTo(this.pname);
} else {
return compare;
}
}
@Override
public void write(DataOutput out) throws IOException {
out.writeUTF(id);
out.writeUTF(pid);
out.writeInt(amount);
out.writeUTF(pname);
}
@Override
public void readFields(DataInput in) throws IOException {
this.id = in.readUTF();
this.pid = in.readUTF();
this.amount = in.readInt();
this.pname = in.readUTF();
}
}
RJMapper.java
package com.study.reducejoin;
import com.study.bean.OrderBean;
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 org.apache.hadoop.mapreduce.lib.input.FileSplit;
import java.io.IOException;
public class RJMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable> {
private OrderBean orderBean = new OrderBean();
private String filename;
@Override
protected void setup(Context context) throws IOException, InterruptedException {
FileSplit fs = (FileSplit) context.getInputSplit();
filename = fs.getPath().getName();
}
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String[] fields = value.toString().split("\t");
if (filename.equals("order.txt")) {
orderBean.setId(fields[0]);
orderBean.setPid(fields[1]);
orderBean.setAmount(Integer.parseInt(fields[2]));
orderBean.setPname("");
} else {
orderBean.setPid(fields[0]);
orderBean.setPname(fields[1]);
orderBean.setId("");
orderBean.setAmount(0);
}
context.write(orderBean, NullWritable.get());
}
}
RJComparator.java
package com.study.reducejoin;
import com.study.bean.OrderBean;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.WritableComparator;
public class RJComparator extends WritableComparator {
protected RJComparator() {
super(OrderBean.class, true);
}
@Override
public int compare(WritableComparable a, WritableComparable b) {
OrderBean oa = (OrderBean) a;
OrderBean ob = (OrderBean) b;
return oa.getPid().compareTo(ob.getPid());
}
}
RJReducer.java
package com.study.reducejoin;
import com.study.bean.OrderBean;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.Reducer;
import java.io.IOException;
import java.util.Iterator;
public class RJReducer extends Reducer<OrderBean, NullWritable, OrderBean, NullWritable> {
@Override
protected void reduce(OrderBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
//拿到迭代器
Iterator<NullWritable> iterator = values.iterator();
//数据指针下移,获取第一个OrderBean
iterator.next();
//从第一个OrderBean中取出品牌名称
String pname = key.getPname();
//遍历剩下的OrderBean,设置品牌名称并写出
while (iterator.hasNext()) {
iterator.next();
key.setPname(pname);
context.write(key, NullWritable.get());
}
}
}
RJDriver.java
package com.study.reducejoin;
import com.study.bean.OrderBean;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
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 RJDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Job job = Job.getInstance(new Configuration());
job.setJarByClass(RJDriver.class);
job.setMapperClass(RJMapper.class);
job.setReducerClass(RJReducer.class);
job.setMapOutputKeyClass(OrderBean.class);
job.setMapOutputValueClass(NullWritable.class);
job.setOutputKeyClass(OrderBean.class);
job.setOutputValueClass(NullWritable.class);
job.setGroupingComparatorClass(RJComparator.class);
FileInputFormat.setInputPaths(job, new Path("d:\\input"));
FileOutputFormat.setOutputPath(job, new Path("d:\\output"));
boolean b = job.waitForCompletion(true);
System.exit(b ? 0 : 1);
}
}
运行之前,先在d盘添加input文件并在该文件下添加数据:
order:
1001 01 1
1002 02 2
1003 03 3
1004 01 4
1005 02 5
1006 03 6
pd:
01 小米
02 华为
03 格力
注意:若d盘存在output文件需要删除在运行
运行程序后,生成文件
总结:
Map Join
1.使用场景
Map Join适用于一张表十分小、一张表很大的场景。
2.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。
3.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)在驱动函数中加载缓存。 // 缓存普通文件到Task运行节点。
job.addCacheFile(new URI(“file://e:/cache/pd.txt”));
Map Join案例实操
首先创建mapjoin包创建两个类
MJMapper.java
package com.study.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.*;
import java.net.URI;
import java.util.HashMap;
import java.util.Map;
public class MJMapper extends Mapper<LongWritable, Text, Text, NullWritable> {
private Map<String, String> pMap = new HashMap<>();
private Text k = new Text();
@Override
protected void setup(Context context) throws IOException, InterruptedException {
URI[] cacheFiles = context.getCacheFiles();
String path = cacheFiles[0].getPath().toString();
FileSystem fileSystem = FileSystem.get(context.getConfiguration());
FSDataInputStream bufferedReader = fileSystem.open(new Path(path));
String line;
while (StringUtils.isNotEmpty(line = bufferedReader.readLine())) {
String[] fields = line.split("\t");
pMap.put(fields[0], fields[1]);
}
IOUtils.closeStream(bufferedReader);
}
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String[] fields = value.toString().split("\t");
String pname = pMap.get(fields[1]);
if (pname == null) {
pname = "NULL";
}
k.set(fields[0] + "\t" + pname + "\t" + fields[2]);
context.write(k, NullWritable.get());
}
}
MJDriver.java
package com.study.mapjoin;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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;
public class MJDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Job job = Job.getInstance(new Configuration());
job.setJarByClass(MJDriver.class);
job.setMapperClass(MJMapper.class);
job.setNumReduceTasks(0);
job.addCacheFile(URI.create("file:///d:/input/pd.txt"));
FileInputFormat.setInputPaths(job, new Path("d:\\input\\order.txt"));
FileOutputFormat.setOutputPath(job, new Path("d:\\output"));
boolean b = job.waitForCompletion(true);
System.exit(b ? 0 : 1);
}
}
启动程序,运行