linux进程序列化,深入理解 Hadoop 序列化

1.序列化概述

1.1 什么是序列化

序列化就是把内存中的对象，转换成字节序列(或其他数据传输协议)以便于存储到磁盘(持久化)和网络传输；

反序列化就是将收到字节序列(或其他数据传输协议)或者是磁盘的持久化数据，转换成内存中的对象；

1.2 为什么要序列化

一般来说，“活的”对象只生存在内存中，关机断电就没有了；而且“活的”对象只能由本地的进程使用，不能发送到网络上的另外一台计算机；然而序列化可以存储“活的”对象，可以将“活的”对象发送到远程计算机；

1.3 为甚不用Java的序列化

Java的序列化是一个重量级序列化框架(Serializable)，一个对象被序列化后，会附带很多额外的信息(各种效验信息，Header，继承体系等)，不便于在网络中高效传输，所以，Hadoop自己开发了一套序列化机制(Writable);

1.4 hadoop序列化特点

1.4.1 紧凑：高效使用存储空间；

1.4.2 快速：读写数据的额外开销小；

1.4.3 可扩展：随着通信协议的升级而可升级；

1.4.4 互操作：支持多语言的交互；

2.自定义bean对象实现序列接口(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；

2.1 必须实现Writable接口；

2.2 反序列化，需要反射调用空参构造函数，所以必须有空参构造；

publicFlowBean() {

super();

}

2.3 重写序列化方法

/*序列化方法

* dataOutput 框架给我们提供的数据出口

**/@Overridepublic voidwrite(DataOutput dataOutput) throws IOException {

dataOutput.writeLong(upFlow);

dataOutput.writeLong(downFlow);

dataOutput.writeLong(sumFlow);

}

2.4 重写反序列化方法

/*反序列化方法

* dataInput 框架提供的数据来源

**/@Overridepublic voidreadFields(DataInput dataInput) throws IOException {

upFlow=dataInput.readLong();

downFlow=dataInput.readLong();

sumFlow=dataInput.readLong();

}

3.案例

3.1 编写FlowwBean

package com.wn.flow;

import org.apache.hadoop.io.Writable;

import java.io.DataInput;

import java.io.DataOutput;

import java.io.IOException;public classFlowwBean implements Writable {private longupFlow;private longdownFlow;private longsumFlow;publicFlowwBean() {

}

@OverridepublicString toString() {return "FlowwBean{" +

"upFlow=" + upFlow +

", downFlow=" + downFlow +

", sumFlow=" + sumFlow +

'}';

}public void set(long upFlow, longdownFlow){this.upFlow=upFlow;this.downFlow=downFlow;this.sumFlow=upFlow+downFlow;

}public longgetDownFlow() {returndownFlow;

}public void setDownFlow(longdownFlow) {this.downFlow =downFlow;

}public longgetSumFlow() {returnsumFlow;

}public void setSumFlow(longsumFlow) {this.sumFlow =sumFlow;

}public longgetUpFlow() {returnupFlow;

}public void setUpFlow(longupFlow) {this.upFlow =upFlow;

}/*序列化方法

* dataOutput 框架给我们提供的数据出口

**/@Overridepublic voidwrite(DataOutput dataOutput) throws IOException {

dataOutput.writeLong(upFlow);

dataOutput.writeLong(downFlow);

dataOutput.writeLong(sumFlow);

}/*顺序要完全一致*/

/*反序列化方法

* dataInput 框架提供的数据来源

**/@Overridepublic voidreadFields(DataInput dataInput) throws IOException {

upFlow=dataInput.readLong();

downFlow=dataInput.readLong();

sumFlow=dataInput.readLong();

}

}

3.2 编写FlowMapper

package com.wn.flow;

import org.apache.hadoop.io.LongWritable;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;public class FlowMapper extends Mapper{private Text phone=newText();private FlowwBean flow=newFlowwBean();

@Overrideprotected voidmap(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

String[] split= value.toString().split("\t");

phone.set(split[1]);long upFlow = Long.parseLong(split[split.length - 3]);long downFlow = Long.parseLong(split[split.length - 2]);

flow.set(upFlow,downFlow);

context.write(phone,flow);

}

}

3.3 编写FlowReducer

package com.wn.flow;

import org.apache.hadoop.mapreduce.Reducer;

import javax.xml.soap.Text;

import java.io.IOException;public class FlowReducer extends Reducer{private FlowwBean sumFlow=newFlowwBean();

@Overrideprotected void reduce(Text key, Iterablevalues, Context context) throws IOException, InterruptedException {long sumUpFlow=0;long sumDownFlow=0;for(FlowwBean value:values){

sumUpFlow+=value.getUpFlow();

sumDownFlow+=value.getDownFlow();

}

sumFlow.set(sumUpFlow,sumDownFlow);

context.write(key,sumFlow);

}

}

3.4 编写FlowDriver

package com.wn.flow;

import com.wn.wordcount.WcDriver;

import com.wn.wordcount.WcMapper;

import com.wn.wordcount.WcReducer;

import org.apache.hadoop.conf.Configuration;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.IntWritable;

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 java.io.IOException;public classFlowDriver {public static voidmain(String[] args) throws IOException, ClassNotFoundException, InterruptedException {//获取一个Job实例

Job job = Job.getInstance(newConfiguration());//设置类路径

job.setJarByClass(WcDriver.class);//设置mapper和reducer

job.setMapperClass(FlowMapper.class);

job.setReducerClass(FlowReducer.class);//设置mapper和reducer输出类型

job.setMapOutputKeyClass(org.apache.hadoop.io.Text.class);

job.setMapOutputValueClass(FlowwBean.class);

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(FlowwBean.class);//设置输入的数据

FileInputFormat.setInputPaths(job,new Path(args[0]));

FileOutputFormat.setOutputPath(job,new Path(args[1]));//提交job

boolean b = job.waitForCompletion(true);

System.exit(b?0:1);

}

}