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
需求
订单表order: 产品表pd:
将上述两表中的数据根据商品pid合并到订单数据表中,要求呈现出如下图:
需求分析
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。
Reduce端表合并(数据倾斜)
运行结果
本地order.txt 本地pd.txt 输出
缺点
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。
源码
tips: hadoop迭代器中使用了对象重用,即迭代时value始终指向一个内存地址(引用值始终不变),改变的是引用指向的内存地址中的数据。
TableBean类:
package com.xiaobai.mapreduce.reduceJoin;
import org.apache.hadoop.io.Writable;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
public class TableBean implements Writable {
private String id;
private String pid;
private int amount;
private String pname;
private String flag;
public TableBean() {
}
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 void write(DataOutput out) throws IOException {
out.writeUTF(id);
out.writeUTF(pid);
out.writeInt(amount);
out.writeUTF(pname);
out.writeUTF(flag);
}
@Override
public void readFields(DataInput in) throws IOException {
this.id = in.readUTF();
this.pid = in.readUTF();
this.amount = in.readInt();
this.pname = in.readUTF();
this.flag = in.readUTF();
}
@Override
public String toString() {
return id + "\t" + pname + "\t" + amount;
}
}
TableMapper类:
package com.xiaobai.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.File;
import java.io.IOException;
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 {
FileSplit split = (FileSplit)context.getInputSplit();
fileName = split.getPath().getName();
}
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
if(fileName.contains("order")){
String[] split = line.split("\t");
outK.set(split[1]);
outV.setId(split[0]);
outV.setPid(split[1]);
outV.setAmount(Integer.parseInt(split[2]));
outV.setPname("");
outV.setFlag("order");
}else{
String[] split = line.split("\t");
outK.set(split[0]);
outV.setId("");
outV.setPid(split[0]);
outV.setAmount(0);
outV.setPname(split[1]);
outV.setFlag("pd");
}
context.write(outK,outV);
}
}
TableReducer类:
package com.xiaobai.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;
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) {
if("order".equals(value.getFlag())){
TableBean tmptableBean = new TableBean();
try {
BeanUtils.copyProperties(tmptableBean,value);
} catch (IllegalAccessException e) {
e.printStackTrace();
} catch (InvocationTargetException e) {
e.printStackTrace();
}
orderBeans.add(tmptableBean);
}else{
try {
BeanUtils.copyProperties(pdBean,value);
} catch (IllegalAccessException e) {
e.printStackTrace();
} catch (InvocationTargetException e) {
e.printStackTrace();
}
}
}
for (TableBean orderBean : orderBeans) {
orderBean.setPname(pdBean.getPname());
context.write(orderBean,NullWritable.get());
}
}
}
TableDriver类:
package com.xiaobai.mapreduce.reduceJoin;
import org.apache.hadoop.conf.Configuration;
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 org.apache.hadoop.fs.Path;
import java.io.IOException;
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 org.apache.hadoop.fs.Path("/Users/jane/Desktop/test/JoinTest"));
FileOutputFormat.setOutputPath(job,new Path("/Users/jane/Desktop/hadoop/JoinTestOutput"));
boolean b = job.waitForCompletion(true);
System.exit(b ? 0 : 1);
}
}
|