假设从数据运营商可以获取用户(通过手机号来区分)的上网信息:
1363157985066 13726230503 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 24 27 2481 24681 200
1363157995052 13826544101 5C-0E-8B-C7-F1-E0:CMCC 120.197.40.4 4 0 264 0 200
1363157991076 13926435656 20-10-7A-28-CC-0A:CMCC 120.196.100.99 2 4 132 1512 200
1363154400022 13926251106 5C-0E-8B-8B-B1-50:CMCC 120.197.40.4 4 0 240 0 200
1363157993044 18211575961 94-71-AC-CD-E6-18:CMCC-EASY 120.196.100.99 iface.qiyi.com 视频网站 15 12 1527 2106 200
1363157995074 84138413 5C-0E-8B-8C-E8-20:7DaysInn 120.197.40.4 122.72.52.12 20 16 4116 1432 200
1363157993055 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 18 15 1116 954 200
1363157995033 15920133257 5C-0E-8B-C7-BA-20:CMCC 120.197.40.4 sug.so.360.cn 信息安全 20 20 3156 2936 200
1363157983019 13719199419 68-A1-B7-03-07-B1:CMCC-EASY 120.196.100.82 4 0 240 0 200
1363157984041 13660577991 5C-0E-8B-92-5C-20:CMCC-EASY 120.197.40.4 s19.cnzz.com 站点统计 24 9 6960 690 200
1363157973098 15013685858 5C-0E-8B-C7-F7-90:CMCC 120.197.40.4 rank.ie.sogou.com 搜索引擎 28 27 3659 3538 200
1363157986029 15989002119 E8-99-C4-4E-93-E0:CMCC-EASY 120.196.100.99 www.umeng.com 站点统计 3 3 1938 180 200
1363157992093 13560439658 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 15 9 918 4938 200
1363157986041 13480253104 5C-0E-8B-C7-FC-80:CMCC-EASY 120.197.40.4 3 3 180 180 200
1363157984040 13602846565 5C-0E-8B-8B-B6-00:CMCC 120.197.40.4 2052.flash2-http.qq.com 综合门户 15 12 1938 2910 200
1363157995093 13922314466 00-FD-07-A2-EC-BA:CMCC 120.196.100.82 img.qfc.cn 12 12 3008 3720 200
1363157982040 13502468823 5C-0A-5B-6A-0B-D4:CMCC-EASY 120.196.100.99 y0.ifengimg.com 综合门户 57 102 7335 110349 200
1363157986072 18320173382 84-25-DB-4F-10-1A:CMCC-EASY 120.196.100.99 input.shouji.sogou.com 搜索引擎 21 18 9531 2412 200
1363157990043 13925057413 00-1F-64-E1-E6-9A:CMCC 120.196.100.55 t3.baidu.com 搜索引擎 69 63 11058 48243 200
1363157988072 13760778710 00-FD-07-A4-7B-08:CMCC 120.196.100.82 2 2 120 120 200
1363157985066 13726238888 00-FD-07-A4-72-B8:CMCC 120.196.100.82 i02.c.aliimg.com 24 27 2481 24681 200
1363157993055 13560436666 C4-17-FE-BA-DE-D9:CMCC 120.196.100.99 18 15 1116 954 200
上面的这些数据,第二列的数据代表的是手机号(通过手机号来区分用户),从右边数,右边第三列代表上行流量,右边第二列代表下行流量
我们来写MapReduce程序来统计每个手机号的上行流量,下行流量,以及总流量,由于我们需要的是三个数据,所以我们可以将这三个数据封装成一个Bean,这个Bean必须要实现hadoop的序列化接口.
package com.thp.bigdata.flowsum;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import org.apache.hadoop.io.Writable;
public class FlowBean implements Writable {
private long upFlow; // 上行流量
private long downFlow; // 下行流量
private long sumFlow; // 总流量
// 反序列化时,需要反射调用空参构造函数,所以要显式定义一个
public FlowBean() {}
public FlowBean(long upFlow, long downFlow) {
this.upFlow = upFlow;
this.downFlow = downFlow;
this.sumFlow = upFlow + downFlow;
}
public long getUpFlow() {
return upFlow;
}
public void setUpFlow(long upFlow) {
this.upFlow = upFlow;
}
public long getDownFlow() {
return downFlow;
}
public void setDownFlow(long downFlow) {
this.downFlow = downFlow;
}
public long getSumFlow() {
return sumFlow;
}
public void setSumFlow(long sumFlow) {
this.sumFlow = sumFlow;
}
/**
* 序列化方法
*/
@Override
public void write(DataOutput out) throws IOException {
out.writeLong(upFlow);
out.writeLong(downFlow);
out.writeLong(sumFlow);
}
/**
* 反序列化方法:
* 注意 : 反序列化的顺序跟序列化的顺序完全一致
*/
@Override
public void readFields(DataInput in) throws IOException {
upFlow = in.readLong();
downFlow = in.readLong();
sumFlow = in.readLong();
}
// 输出打印的时候调用的是toString() 方法
@Override
public String toString() {
return upFlow + "\t" + downFlow + "\t" + sumFlow;
}
}
主程序,将Map task 跟 reduce task 全部写在同一个类中,作为静态内部类
package com.thp.bigdata.flowsum;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class FlowCount {
static class FlowCountMapper extends Mapper<LongWritable, Text, Text, FlowBean> {
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
// 将一行内容转换成string
String line = value.toString();
// 切分字段
String[] fields = line.split("\t");
// 取出手机号
String phoneNumber = fields[1];
// 取出上行流量和下行流量
long upFlow = Long.parseLong(fields[fields.length - 3]);
long downFlow = Long.parseLong(fields[fields.length - 2]);
context.write(new Text(phoneNumber), new FlowBean(upFlow, downFlow));
}
}
static class FlowCountReducer extends Reducer<Text, FlowBean, Text, FlowBean> {
@Override
protected void reduce(Text key, Iterable<FlowBean> values, Context context)
throws IOException, InterruptedException {
long sum_upFlow = 0;
long sum_downFlow = 0;
// 遍历所有的bean,将其中的上行流量,下行流量分别累加
for(FlowBean bean : values) {
sum_upFlow += bean.getUpFlow();
sum_downFlow += bean.getDownFlow();
}
FlowBean resultBean = new FlowBean(sum_upFlow, sum_downFlow);
context.write(key, resultBean);
}
}
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(FlowCount.class);
job.setMapperClass(FlowCountMapper.class);
job.setReducerClass(FlowCountReducer.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(FlowBean.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(FlowBean.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean res = job.waitForCompletion(true);
System.exit(res ? 0 : 1);
}
}
将数据上传到hadoop的hdfs文件系统
将写的整个项目打成jar包放在hadoop集群上.
hadoop jar mapReduce.jar com.thp.bigdata.flowsum.FlowCount /flowsum/input /flowsum/output
最后生成的文件:
MapTask并行度决定机制:
maptask的并行度决定map阶段的任务处理并发度,进而影响到整个job的处理速度,那么,maptask并行实例是否越多越好呢?其并行度又是如何决定呢?