MapReduce的两表join操作优化

注：优化前的分析过程详见本博的上篇博文

案例

地址(Address)和人员(Person)的一对多关联

 

原始数据

地址(Address)数据

id AddreName

1 beijing
2 shanghai
3 guangzhou

人员(Person)数据

1 zhangsan 1
2 lisi 2
3 wangwu 1
4 zhaoliu 3
5 maqi 3

 

优化前，我们通过构造一个通用的JavaBean来存储两张表的属性。但是我们发现最后reduce时用List数组来存储和Address地址表区分开来的Person表数组，将造成大量的内存开销，所有我们想到重新构造Map的key类型，在数据进行reduce前重新group分组操作

优化前代码分析

1.自定义JavaBean代码

/*
 * 人员和地址的通用bean
 */
public class Bean implements WritableComparable<Bean> {
	private String userNo = "";
	private String userName = "";
	private String addreNo = "";
	private String addreName = "";
	private int flag;

	public Bean(Bean bean) {
		this.userName = bean.getUserName();
		this.userNo = bean.getUserNo();
		this.addreName = bean.getAddreName();
		this.addreNo = bean.getAddreNo();
		this.flag = bean.getFlag();
	}

	public Bean() {
		super();
		// TODO Auto-generated constructor stub
	}

	public Bean(String userNo, String userName, String addreNo,
			String addreName, int flag) {
		super();
		this.userNo = userNo;
		this.userName = userName;
		this.addreNo = addreNo;
		this.addreName = addreName;
		this.flag = flag;
	}

	public String getUserNo() {
		return userNo;
	}

	public void setUserNo(String userNo) {
		this.userNo = userNo;
	}

	public String getUserName() {
		return userName;
	}

	public void setUserName(String userName) {
		this.userName = userName;
	}

	public String getAddreNo() {
		return addreNo;
	}

	public void setAddreNo(String addreNo) {
		this.addreNo = addreNo;
	}

	public String getAddreName() {
		return addreName;
	}

	public void setAddreName(String addreName) {
		this.addreName = addreName;
	}

	public int getFlag() {
		return flag;
	}

	public void setFlag(int flag) {
		this.flag = flag;
	}

	@Override
	public void write(DataOutput out) throws IOException {
		out.writeUTF(userNo);
		out.writeUTF(userName);
		out.writeUTF(addreNo);
		out.writeUTF(addreName);
		out.writeInt(flag);

	}

	@Override
	public void readFields(DataInput in) throws IOException {
		this.userNo = in.readUTF();
		this.userName = in.readUTF();
		this.addreNo = in.readUTF();
		this.addreName = in.readUTF();
		this.flag = in.readInt();

	}

	@Override
	public int compareTo(Bean arg0) {
		// TODO Auto-generated method stub
		return 0;
	}

	@Override
	public String toString() {
		return "userNo=" + userNo + ", userName=" + userName + ", addreNo="
				+ addreNo + ", addreName=" + addreName;
	}

}

2.Map操作

public class PersonAddrMap extends
		Mapper<LongWritable, Text, IntWritable, Bean> {
	@Override
	protected void map(LongWritable key, Text value,
			Mapper<LongWritable, Text, IntWritable, Bean>.Context context)
			throws IOException, InterruptedException {
		String line = value.toString();
		String str[] = line.split("\t");
		if (str.length == 2) { // 地区信息表
			Bean bean = new Bean();
			bean.setAddreNo(str[0]);
			bean.setAddreName(str[1]);
			bean.setFlag(0); // 0表示地区
			context.write(new IntWritable(Integer.parseInt(str[0])), bean);
		} else {// 人员信息表
			Bean bean = new Bean();
			bean.setUserNo(str[0]);
			bean.setUserName(str[1]);
			bean.setAddreNo(str[2]);
			bean.setFlag(1); // 1表示人员表
			context.write(new IntWritable(Integer.parseInt(str[2])), bean);
		}
	}
}

3.reduce操作

public class PersonAddreRedu extends
		Reducer<IntWritable, Bean, NullWritable, Text> {
	@Override
	protected void reduce(IntWritable key, Iterable<Bean> values,
			Reducer<IntWritable, Bean, NullWritable, Text>.Context context)
			throws IOException, InterruptedException {
		Bean Addre = null;
		List<Bean> peoples = new ArrayList<Bean>();
		/*
		 * 如果values的第一个元素信息就是地址Addre的信息的话,
		 * 我们就不再需要一个List来缓存person信息了,values后面的全是人员信息
		 * 将减少巨大的内存空间
		 */
		/*
		 * partitioner和shuffer的过程：
		 * partitioner的主要功能是根据reduce的数量将map输出的结果进行分块,将数据送入到相应的reducer.
		 * 所有的partitioner都必须实现partitioner接口并实现getPartition方法,该方法的返回值为int类型，并且取值范围在0~(numOfReducer-1),
		 * 从而能将map的输出输入到对应的reducer中,对于某个mapreduce过程,hadoop框架定义了默认的partitioner为HashPartioner,
		 * 该partitioner使用key的hashCode来决定将该key输送到哪个reducer;
		 * shuffle将每个partitioner输出的结果根据key进行group以及排序,将具有相同key的value构成一个values的迭代器,并根据key进行排序分别调用
		 * 开发者定义的reduce方法进行排序,因此mapreducer的所以key必须实现comparable接口的compareto()方法从而能实现两个key对象的比较
		 */
		/*
		 * 我们需要自定义key的数据结构(shuffle按照key进行分组)来满足共同addreNo的情况下地址表的更小需求
		 * 
		 */
		for (Bean bean : values) {
			if (bean.getFlag() == 0) { // 表示地区表
				Addre = new Bean(bean);

			} else {
				peoples.add(new Bean(bean)); // 添加到peoplelist中
			}
		}
		for (Bean peo : peoples) { // 给peoplelist添加地区名字
			peo.setAddreName(Addre.getAddreName());
			context.write(NullWritable.get(), new Text(peo.toString()));
		}
	}
}

4.job操作

public class PersonAddreMain {
	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		Job job = new Job(conf);
		job.setJarByClass(PersonAddreMain.class);

		job.setMapperClass(PersonAddrMap.class);
		job.setMapOutputKeyClass(IntWritable.class);
		job.setMapOutputValueClass(Bean.class);

		job.setReducerClass(PersonAddreRedu.class);
		job.setOutputKeyClass(NullWritable.class);
		job.setOutputValueClass(Text.class);

		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		job.waitForCompletion(true);
	}
}

 

具体优化分析

在Reduce类的reduce()方法中如果values的第一个元素信息就是地址Addre的信息的话,我们就不再需要一个List来缓存person信息了,values后面的全是人员信息将减少巨大的内存空间。

 

partitioner和shuffer的过程
partitioner的主要功能是根据reduce的数量将map输出的结果进行分块,将数据送入到相应的reducer.
所有的partitioner都必须实现partitioner接口并实现getPartition方法,该方法的返回值为int类型，并且取值范围在0~(numOfReducer-1),
从而能将map的输出输入到对应的reducer中,对于某个mapreduce过程,hadoop框架定义了默认的partitioner为HashPartioner,
该partitioner使用key的hashCode来决定将该key输送到哪个reducer;
 shuffle将每个partitioner输出的结果根据key进行group以及排序,将具有相同key的value构成一个values的迭代器,并根据key进行排序分别调用
 开发者定义的reduce方法进行排序,因此mapreducer的所以key必须实现comparable接口的compareto()方法从而能实现两个key对象的比较

我们需要自定义key的数据结构(shuffle按照key进行分组)来满足共同addreNo的情况下地址表的更小需求

 

优化后

1.JavaBean操作

/*
 * 人员和地址的通用bean
 * 用作map输出的value
 */
public class Bean implements WritableComparable<Bean> {
	private String userNo = " ";
	private String userName = " ";
	private String addreNo = " ";
	private String addreName = " ";

	public Bean(Bean bean) {
		this.userName = bean.getUserName();
		this.userNo = bean.getUserNo();
		this.addreName = bean.getAddreName();
		this.addreNo = bean.getAddreNo();
	}

	public Bean() {
		super();
		// TODO Auto-generated constructor stub
	}

	public Bean(String userNo, String userName, String addreNo,
			String addreName, int flag) {
		super();
		this.userNo = userNo;
		this.userName = userName;
		this.addreNo = addreNo;
		this.addreName = addreName;
	}


	public String getUserNo() {
		return userNo;
	}

	public void setUserNo(String userNo) {
		this.userNo = userNo;
	}

	public String getUserName() {
		return userName;
	}

	public void setUserName(String userName) {
		this.userName = userName;
	}

	public String getAddreNo() {
		return addreNo;
	}

	public void setAddreNo(String addreNo) {
		this.addreNo = addreNo;
	}

	public String getAddreName() {
		return addreName;
	}

	public void setAddreName(String addreName) {
		this.addreName = addreName;
	}

	@Override
	public void write(DataOutput out) throws IOException {
		out.writeUTF(userNo);
		out.writeUTF(userName);
		out.writeUTF(addreNo);
		out.writeUTF(addreName);

	}

	@Override
	public void readFields(DataInput in) throws IOException {
		this.userNo = in.readUTF();
		this.userName = in.readUTF();
		this.addreNo = in.readUTF();
		this.addreName = in.readUTF();
	}

	@Override
	public int compareTo(Bean arg0) {
		// TODO Auto-generated method stub
		return 0;
	}

	@Override
	public String toString() {
		return "userNo=" + userNo + ", userName=" + userName + ", addreNo="
				+ addreNo + ", addreName=" + addreName;
	}

}

2.自定义个map输出的key

/*
 * map输出的key
 */
public class BeanKey implements WritableComparable<BeanKey> {
	private int AddreNo;
	private boolean isPrimary; // true：address false：person

	public BeanKey(int addreNo, boolean isPrimary) {
		super();
		this.AddreNo = addreNo;
		this.isPrimary = isPrimary;
	}

	public BeanKey() {
		super();
		// TODO Auto-generated constructor stub
	}

	@Override
	public void write(DataOutput out) throws IOException {
		out.writeInt(AddreNo);
		out.writeBoolean(isPrimary);

	}

	@Override
	public void readFields(DataInput in) throws IOException {
		this.AddreNo = in.readInt();
		this.isPrimary = in.readBoolean();

	}

	// partitioner执行时调用hashcode()方法和compareTo()方法
	// compareTo()方法作为shuffle排序的默认方法
	@Override
	public int hashCode() {
		return this.AddreNo; // 按AddreNo进行分组
	}

	//用于排序,将相同的AddressNo的地址表和人员表,将地址表放到首位
	@Override
	public int compareTo(BeanKey o) {
		if (this.AddreNo == o.getAddreNo()) { // 如果是同一个AddressNo的数据则判断是Person还是Address表
			if (this.isPrimary == o.isPrimary()) {  //如果属性相同属于同种类型的表,返回0
				return 0;
			} else {
				return this.isPrimary ? -1 : 1; // true表示Address表 返回更小的值,将排至values队首
			}
		} else {
			return this.AddreNo - o.getAddreNo() > 0 ? 1 : -1;  //按AddressNo排序
		}
	}

	public int getAddreNo() {
		return AddreNo;
	}

	public void setAddreNo(int addreNo) {
		AddreNo = addreNo;
	}

	public boolean isPrimary() {
		return isPrimary;
	}

	public void setPrimary(boolean isPrimary) {
		this.isPrimary = isPrimary;
	}

}

3.重新构造shuffle的group分组

实现Group分组
shuffle的group过程默认的是使用的key(BeanKey)的compareTo()方法
刚才我们添加的自定义的Key没有办法将具有相同AddressNo的地址和人员放到同一个group中(因为从compareTo()方法中可以看出他们是不相等的)
我们需要的就是自己定义一个groupComparer就可以
实现比较器

/*
 * 实现Group分组
 * shuffle的group过程默认的是使用的key(BeanKey)的compareTo()方法
 * 刚才我们添加的自定义的Key没有办法将具有相同AddressNo的地址和人员放到同一个group中(因为从compareTo()方法中可以看出他们是不相等的)
 * 我们需要的就是自己定义一个groupComparer就可以
 * 实现比较器
 */
public class PKFKCompartor extends WritableComparator{

	protected PKFKCompartor() {
		super(BeanKey.class, true);
	}
	//两个BeanKey进行比较排序
@Override
public int compare(WritableComparable a, WritableComparable b) {
	BeanKey a1=(BeanKey)a;
	BeanKey b1=(BeanKey)b;
	if(a1.getAddreNo()==b1.getAddreNo()){
		return 0;
	}else{
		return a1.getAddreNo()>b1.getAddreNo()?1:-1;
	}
}
}

4.实现map

/*
 * map类使key,value分别进行处理
 */
public class PersonAddreMap extends Mapper<LongWritable, Text, BeanKey, Bean> {
	@Override
	protected void map(LongWritable key, Text value,
			Mapper<LongWritable, Text, BeanKey, Bean>.Context context)
			throws IOException, InterruptedException {
		String line = value.toString();
		String str[] = line.split("\t");
		if (str.length == 2) {
			// Addre表
			Bean Addre = new Bean();
			Addre.setAddreNo(str[0]);
			Addre.setAddreName(str[1]);

			BeanKey AddreKey = new BeanKey();
			AddreKey.setAddreNo(Integer.parseInt(str[0]));
			AddreKey.setPrimary(true); // true表示地区表
			context.write(AddreKey, Addre);
		} else {
			// Person表
			Bean Person = new Bean();
			Person.setUserNo(str[0]);
			Person.setUserName(str[1]);
			Person.setAddreNo(str[2]);

			BeanKey PerKey = new BeanKey();
			PerKey.setAddreNo(Integer.parseInt(str[2]));
			PerKey.setPrimary(false);// false表示人员表
			context.write(PerKey, Person);

		}
	}

}

5.实现reduce

public class PersonAddreRedu extends Reducer<BeanKey, Bean, NullWritable, Text> {
	@Override
	protected void reduce(BeanKey key, Iterable<Bean> values,
			Reducer<BeanKey, Bean, NullWritable, Text>.Context context)
			throws IOException, InterruptedException {
		Bean Addre = null;
		int num = 0;
		for (Bean bean : values) {
			if (num == 0) {
				Addre = new Bean(bean); // Address地址表为values的第一个值
				num++;
			} else {
				// 其余全为person表
				// 没有list数组,节省大量内存空间
				bean.setAddreName(Addre.getAddreName());
				context.write(NullWritable.get(), new Text(bean.toString()));
			}
		}
	}
}

6.实现job

public class PersonAddreMain {
	public static void main(String[] args) throws Exception {
		Configuration conf = new Configuration();
		Job job = new Job(conf);
		job.setJarByClass(PersonAddreMain.class);

		//设置自定义的group
		job.setGroupingComparatorClass(PKFKCompartor.class);
		
		job.setMapperClass(PersonAddreMap.class);
		job.setMapOutputKeyClass(BeanKey.class);
		job.setMapOutputValueClass(Bean.class);

		job.setReducerClass(PersonAddreRedu.class);
		job.setOutputKeyClass(NullWritable.class);
		job.setOutputValueClass(Text.class);

		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
		job.waitForCompletion(true);
	}
}