MapReduce实际案例，MapTask运行机制，ReduceTask运行机制，MapReduce执行流程，hadoop数据压缩，Join算法的实现

MapReduce实际案例

上行流量倒序排序

• 第一步：定义FlowBean实现WritableComparable实现比较排序
  java 的compareTo方法说明
  compareTo 方法用于将当前对象与方法的参数进行比较。
  如果指定的数与参数相等返回 0。
  如果指定的数小于参数返回 -1。
  如果指定的数大于参数返回 1。
  例如：o1.compareTo(o2);
  返回正数的话，当前对象（调用 compareTo 方法的对象 o1）要排在比较对象（compareTo 传参对象 o2）后面，返回负数的话，放在前面。

public class FlowBean implements WritableComparable<FlowBean> {
   
    private Integer upFlow;
    private Integer  downFlow;
    private Integer upCountFlow;
    private Integer downCountFlow;
    public FlowBean() {
   
    }
    public FlowBean(Integer upFlow, Integer downFlow, Integer upCountFlow, Integer downCountFlow) {
   
        this.upFlow = upFlow;
        this.downFlow = downFlow;
        this.upCountFlow = upCountFlow;
        this.downCountFlow = downCountFlow;
    }
    @Override
    public void write(DataOutput out) throws IOException {
   
        out.writeInt(upFlow);
        out.writeInt(downFlow);
        out.writeInt(upCountFlow);
        out.writeInt(downCountFlow);
    }
    @Override
    public void readFields(DataInput in) throws IOException {
   
        upFlow = in.readInt();
        downFlow = in.readInt();
        upCountFlow = in.readInt();
        downCountFlow = in.readInt();
    }
    public Integer getUpFlow() {
   
        return upFlow;
    }
    public void setUpFlow(Integer upFlow) {
   
        this.upFlow = upFlow;
    }
    public Integer getDownFlow() {
   
        return downFlow;
    }
    public void setDownFlow(Integer downFlow) {
   
        this.downFlow = downFlow;
    }
    public Integer getUpCountFlow() {
   
        return upCountFlow;
    }
    public void setUpCountFlow(Integer upCountFlow) {
   
        this.upCountFlow = upCountFlow;
    }
    public Integer getDownCountFlow() {
   
        return downCountFlow;
    }
    public void setDownCountFlow(Integer downCountFlow) {
   
        this.downCountFlow = downCountFlow;
    }
    @Override
    public String toString() {
   
        return upFlow+"\t"+downFlow+"\t"+upCountFlow+"\t"+downCountFlow;
    }
    @Override
    public int compareTo(FlowBean o) {
   
        return this.upCountFlow > o.upCountFlow ?-1:1;
    }
}

• 第二步：定义FlowMapper

public class FlowMapper extends Mapper<LongWritable,Text,FlowBean,Text> {
   
     Text outKey = new Text();
     FlowBean flowBean = new FlowBean();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
   
        String[] split = value.toString().split("\t");
        flowBean.setUpFlow(Integer.parseInt(split[1]));
        flowBean.setDownFlow(Integer.parseInt(split[2]));
        flowBean.setUpCountFlow(Integer.parseInt(split[3]));
        flowBean.setDownCountFlow(Integer.parseInt(split[4]));
        outKey.set(split[0]);
        context.write(flowBean,outKey);
    }
}

• 第三步：定义FlowReducer

public class FlowReducer extends Reducer<FlowBean,Text,Text,FlowBean> {
   
    FlowBean flowBean = new FlowBean();
    @Override
    protected void reduce(FlowBean key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
   
       context.write(values.iterator().next(),key);
    }
}

• 第四步：程序main函数入口

public class FlowMain extends Configured implements Tool {
   
    @Override
    public int run(String[] args) throws Exception {
   
        Configuration conf = super.getConf();
        conf.set(