MapReduce的数据流程、执行流程
jopen
10年前
MapReduce的数据流程：
- 预先加载本地的输入文件
- 经过MAP处理产生中间结果
- 经过shuffle程序将相同key的中间结果分发到同一节点上处理
- Recude处理产生结果输出
- 将结果输出保存在hdfs上
MAP
在map阶段，使用job.setInputFormatClass定义的InputFormat将输入的数据集分割成小数据块splites，
同时InputFormat提供一个RecordReder的实现。默认的是TextInputFormat，
他提供的RecordReder会将文本的一行的偏移量作为key，这一行的文本作为value。
这就是自定义Map的输入是
然后调用自定义Map的map方法，将一个个
最终是按照自定义的MAP的输出key类，输出class类生成一个List
Partitioner
在map阶段的最后，会先调用job.setPartitionerClass设置的类对这个List进行分区，
每个分区映射到一个reducer。每个分区内又调用job.setSortComparatorClass设置的key比较函数类排序。
可以看到，这本身就是一个二次排序。
如果没有通过job.setSortComparatorClass设置key比较函数类，则使用key的实现的compareTo方法。
Shuffle：
将每个分区根据一定的规则，分发到reducer处理
Sort
在reduce阶段，reducer接收到所有映射到这个reducer的map输出后，
也是会调用job.setSortComparatorClass设置的key比较函数类对所有数据对排序。
然后开始构造一个key对应的value迭代器。这时就要用到分组，
使用jobjob.setGroupingComparatorClass设置的分组函数类。只要这个比较器比较的两个key相同，
他们就属于同一个组，它们的value放在一个value迭代器
Reduce
最后就是进入Reducer的reduce方法，reduce方法的输入是所有的（key和它的value迭代器）。
同样注意输入与输出的类型必须与自定义的Reducer中声明的一致。
具体的例子：
是hadoop mapreduce example中的例子，自己改写了一下并加入的注释
import java.io.DataInput; import java.io.DataOutput; import java.io.IOException; import java.util.StringTokenizer; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.RawComparator; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.WritableComparable; import org.apache.hadoop.io.WritableComparator; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Partitioner; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.util.GenericOptionsParser; import com.catt.cdh.mr.example.SecondarySort2.FirstPartitioner; import com.catt.cdh.mr.example.SecondarySort2.Reduce; /** * This is an example Hadoop Map/Reduce application. * It reads the text input files that must contain two integers per a line. * The output is sorted by the first and second number and grouped on the * first number. * * To run: bin/hadoop jar build/hadoop-examples.jar secondarysort * in-dir out-dir */ public class SecondarySort { /** * Define a pair of integers that are writable. * They are serialized in a byte comparable format. */ public static class IntPair implements WritableComparable { private int first = 0; private int second = 0; /** * Set the left and right values. */ public void set(int left, int right) { first = left; second = right; } public int getFirst() { return first; } public int getSecond() { return second; } /** * Read the two integers. * Encoded as: MIN_VALUE -> 0, 0 -> -MIN_VALUE, MAX_VALUE-> -1 */ @Override public void readFields(DataInput in) throws IOException { first = in.readInt() + Integer.MIN_VALUE; second = in.readInt() + Integer.MIN_VALUE; } @Override public void write(DataOutput out) throws IOException { out.writeInt(first - Integer.MIN_VALUE); out.writeInt(second - Integer.MIN_VALUE); } @Override // The hashCode() method is used by the HashPartitioner (the default // partitioner in MapReduce) public int hashCode() { return first * 157 + second; } @Override public boolean equals(Object right) { if (right instanceof IntPair) { IntPair r = (IntPair) right; return r.first == first && r.second == second; } else { return false; } } /** A Comparator that compares serialized IntPair. */ public static class Comparator extends WritableComparator { public Comparator() { super(IntPair.class); } // 针对key进行比较，调用多次 public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) { return compareBytes(b1, s1, l1, b2, s2, l2); } } static { // 注意：如果不进行注册，则使用key.compareTo方法进行key的比较 // register this comparator WritableComparator.define(IntPair.class, new Comparator()); } // 如果不注册WritableComparator，则使用此方法进行key的比较 @Override public int compareTo(IntPair o) { if (first != o.first) { return first < o.first ? -1 : 1; } else if (second != o.second) { return second < o.second ? -1 : 1; } else { return 0; } } } /** * Partition based on the first part of the pair. */ public static class FirstPartitioner extends Partitioner { @Override public int getPartition(IntPair key, IntWritable value, int numPartitions) { return Math.abs(key.getFirst() * 127) % numPartitions; } } /** * Compare only the first part of the pair, so that reduce is called once * for each value of the first part. */ public static class FirstGroupingComparator implements RawComparator { // 针对key调用，调用多次 @Override public int compare(byte[] b1, int s1, int l1, byte[] b2, int s2, int l2) { return WritableComparator.compareBytes(b1, s1, Integer.SIZE / 8, b2, s2, Integer.SIZE / 8); } // 没有监控到被调用，不知道有什么用 @Override public int compare(IntPair o1, IntPair o2) { int l = o1.getFirst(); int r = o2.getFirst(); return l == r ? 0 : (l < r ? -1 : 1); } } /** * Read two integers from each line and generate a key, value pair * as ((left, right), right). */ public static class MapClass extends Mapper { private final IntPair key = new IntPair(); private final IntWritable value = new IntWritable(); @Override public void map(LongWritable inKey, Text inValue, Context context) throws IOException, InterruptedException { StringTokenizer itr = new StringTokenizer(inValue.toString()); int left = 0; int right = 0; if (itr.hasMoreTokens()) { left = Integer.parseInt(itr.nextToken()); if (itr.hasMoreTokens()) { right = Integer.parseInt(itr.nextToken()); } key.set(left, right); value.set(right); context.write(key, value); } } } /** * A reducer class that just emits the sum of the input values. */ public static class Reduce extends Reducer { private static final Text SEPARATOR = new Text( "------------------------------------------------"); private final Text first = new Text(); @Override public void reduce(IntPair key, Iterable values, Context context) throws IOException, InterruptedException { context.write(SEPARATOR, null); first.set(Integer.toString(key.getFirst())); for (IntWritable value : values) { context.write(first, value); } } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] ars = new String[] { "hdfs://data2.kt:8020/test/input", "hdfs://data2.kt:8020/test/output" }; conf.set("fs.default.name", "hdfs://data2.kt:8020/"); String[] otherArgs = new GenericOptionsParser(conf, ars) .getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: secondarysort "); System.exit(2); } Job job = new Job(conf, "secondary sort"); job.setJarByClass(SecondarySort.class); job.setMapperClass(MapClass.class); // 不再需要Combiner类型，因为Combiner的输出类型对Reduce的输入类型不适用 // job.setCombinerClass(Reduce.class); // Reducer类型 job.setReducerClass(Reduce.class); // 分区函数 job.setPartitionerClass(FirstPartitioner.class); // 设置setSortComparatorClass，在partition后， // 每个分区内又调用job.setSortComparatorClass设置的key比较函数类排序 // 另外，在reducer接收到所有映射到这个reducer的map输出后， // 也是会调用job.setSortComparatorClass设置的key比较函数类对所有数据对排序 // job.setSortComparatorClass(GroupingComparator2.class); // 分组函数 job.setGroupingComparatorClass(FirstGroupingComparator.class); // the map output is IntPair, IntWritable // 针对自定义的类型，需要指定MapOutputKeyClass job.setMapOutputKeyClass(IntPair.class); // job.setMapOutputValueClass(IntWritable.class); // the reduce output is Text, IntWritable job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }