Hadoop(12)-MapReduce框架原理-Hadoop序列化和源码追踪

1.什么是序列化

2.为什么要序列化

3.为什么不用Java的序列化

4.自定义bean对象实现序列化接口（Writable）

在企业开发中往往常用的基本序列化类型不能满足所有需求，比如在Hadoop框架内部传递一个bean对象，那么该对象就需要实现序列化接口。

具体实现bean对象序列化步骤如下7步:

1) 必须实现Writable接口

2) 反序列话时,需要反射调用无参构造方法,所以必须要有无参构造方法

3) 重写序列化方法write()

4) 重写反序列化方法readFields()

5) 反序列化的顺序和序列化的顺序务必一致

6) 要想把结果显示在文件中,需要重写toString()方法

7) 如果将自定义的Bean放在key中传输,则必须要实现comparable接口.因为MapReduce的Shuffle过程要求对key必须能排序

注:Hadoop的序列化只保存对象的指定属性数据,而Java保存的东西太多,显得太重,在传输和磁盘存储上,会造成资源的浪费和紧张

5. 序列化案例实操

如下文件,统计每一个手机号耗费的总上行流量、下行流量、总流量

1 13736230513 192.196.100.1 www.baidu.com 2481 24681 200
2	13846544121	192.196.100.2			264	0	200
3	13956435636	192.196.100.3			132	1512	200
4	13966251146	192.168.100.1			240	0	404
5	18271575951	192.168.100.2	www.baidu.com	1527	2106	200
6	84188413	192.168.100.3	www.baidu.com	4116	1432	200
7	13590439668	192.168.100.4			1116	954	200
8	15910133277	192.168.100.5	www.hao123.com	3156	2936	200
9	13729199489	192.168.100.6			240	0	200
10	13630577991	192.168.100.7	www.shouhu.com	6960	690	200
11	15043685818	192.168.100.8	www.baidu.com	3659	3538	200
12	15959002129	192.168.100.9	www.baidu.com	1938	180	500
13	13560439638	192.168.100.10			918	4938	200
14	13470253144	192.168.100.11			180	180	200
15	13682846555	192.168.100.12	www.qq.com	1938	2910	200
16	13992314666	192.168.100.13	www.gaga.com	3008	3720	200
17	13509468723	192.168.100.14	www.qinghua.com	7335	110349	404
18	18390173782	192.168.100.15	www.sogou.com	9531	2412	200
19	13975057813	192.168.100.16	www.baidu.com	11058	48243	200

FlowBean

package com.nty.writable;

import org.apache.hadoop.io.Writable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

/**
 * author nty
 * date time 2018-12-08 13:39
 */
//实现Writable接口
public class Flow implements Writable {

    private Long upflow;  //上行流量

    private Long downflow;  //下行流量

    private Long total;  //总流量

    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 getTotal() {
        return total;
    }

    public void setTotal(Long total) {
        this.total = total;
    }

    /**
     * 快速赋值
     * @param upflow
     * @param downflow
     */
    public void setFlow(long upflow, long downflow){
        this.upflow = upflow;
        this.downflow = downflow;
        this.total = upflow + downflow;
    }

    //序列化方法
    public void write(DataOutput out) throws IOException {
        out.writeLong(upflow);
        out.writeLong(downflow);
        out.writeLong(total);
    }

    //反序列化方法,读取数据的顺序和序列化写值得顺序一致
    public void readFields(DataInput in) throws IOException {
        upflow = in.readLong();
        downflow = in.readLong();
        total = in.readLong();
    }

    @Override
    public String toString() {
        return upflow + "\t" + downflow + "\t" + total;
    }
}

Mapper类

package com.nty.writable;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

/**
 * author nty
 * date time 2018-12-10 16:44
 */
//输入的K,V类型为偏移量和本行内容,输出的K,V类型为本行的手机号和Folw对象
public class FlowMapper extends Mapper<LongWritable, Text, Text, Flow> {

    private Flow flow = new Flow();
    private Text phone = new Text();

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String[] fields = value.toString().split("\t");

        //设置输入的K为手机号
        phone.set(fields[1]);
        //设置Flow,用倒取的原因是因为,有些行数据没有访问地址
        flow.setFlow( Long.parseLong(fields[fields.length-3]), Long.parseLong(fields[fields.length-2]) );
        //将map后的结果输出给context
        context.write(phone,flow);
    }
}

Reducer类

package com.nty.writable;

import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

/**
 * author nty
 * date time 2018-12-10 16:44
 */
//Reducer的输入K,V类型为Mapper的输出类型,即Text,Flow,输出K,V类型为手机号和Flow,即Text,Flow
public class FlowReducer extends Reducer<Text, Flow, Text, Flow> {
private Flow flow = new Flow();

    @Override
    protected void reduce(Text key, Iterable<Flow> values, Context context) throws IOException, InterruptedException {
        
　　　　long upflow = 0;
　　　　long downflow = 0;
        //遍历values,计算总的下行流量和上行流量
        for (Flow flow : values) {
            upflow += flow.getUpflow();
            downflow += flow.getDownflow();
        }

        //对象赋值
        flow.setFlow(upflow, downflow);

        //写出
        context.write(key, flow);

    }
}

Driver类

package com.nty.writable;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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;

/**
 * author nty
 * date time 2018-12-10 16:44
 */
public class FlowDriver {

    public static void main(String[] args) throws Exception {
        //获取配置信息和job
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        //设置jar类
        job.setJarByClass(FlowDriver.class);

        //设置Mapper和Reducer
        job.setMapperClass(FlowMapper.class);
        job.setReducerClass(FlowReducer.class);

        //设置Mapper的输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Flow.class);

        //设置Reduce的输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Flow.class);

        //设置文件的输入输出路径
        FileInputFormat.setInputPaths(job, new Path("d:\\Hadoop_test"));
        FileOutputFormat.setOutputPath(job, new Path("d:\\Hadoop_test_output"));

        //提交
        boolean res = job.waitForCompletion(true);

        System.exit(res ? 0 :1);

    }
}

最终输出结果

13470253144    180    180    360
13509468723    7335    110349    117684
13560439638    918    4938    5856
13590439668    1116    954    2070
13630577991    6960    690    7650
13682846555    1938    2910    4848
13729199489    240    0    240
13736230513    2481    24681    27162
13846544121    264    0    264
13956435636    132    1512    1644
13966251146    240    0    240
13975057813    11058    48243    59301
13992314666    3008    3720    6728
15043685818    3659    3538    7197
15910133277    3156    2936    6092
15959002129    1938    180    2118
18271575951    1527    2106    3633
18390173782    9531    2412    11943
84188413    4116    1432    5548

6.序列化执行过程(源码)

map方法将flow对象write出去,框架接收到flow对象,进行序列化

step into

这是key的序列化方法

再跳出看value的序列化

step into

最后value进入我们自己重写的序列化方法