public InputSplit[] getSplits(JobConf job, int numSplits)
    throws IOException {
	  //获取输入文件列表files，其中会遍历输入目录的子目录，并过滤掉部分文件，如文件_SUCCESS
    FileStatus[] files = listStatus(job);
    
    // Save the number of input files for metrics/loadgen
    job.setLong(NUM_INPUT_FILES, files.length);
    long totalSize = 0;                           // compute total size
    for (FileStatus file: files) {                // check we have valid files
      if (file.isDirectory()) {
        throw new IOException("Not a file: "+ file.getPath());
      }
      totalSize += file.getLen();
    }

    /*
     * numSplits为设置的map数目
     * 期待的分片大小
     */
    long goalSize = totalSize / (numSplits == 0 ? 1 : numSplits);
    /*
     * FileInputFormat.SPLIT_MINSIZE为参数值：mapreduce.input.fileinputformat.split.minsize，默认为0
     * minSplitSize默认为1
     */
     long minSize = Math.max(job.getLong(org.apache.hadoop.mapreduce.lib.input.
      FileInputFormat.SPLIT_MINSIZE, 1), minSplitSize);

    // generate splits
    ArrayList<FileSplit> splits = new ArrayList<FileSplit>(numSplits);
    NetworkTopology clusterMap = new NetworkTopology();
    for (FileStatus file: files) {
      Path path = file.getPath();
      long length = file.getLen();
      if (length != 0) {
        FileSystem fs = path.getFileSystem(job);
        BlockLocation[] blkLocations;
        if (file instanceof LocatedFileStatus) {
          blkLocations = ((LocatedFileStatus) file).getBlockLocations();
        } else {
          blkLocations = fs.getFileBlockLocations(file, 0, length);
        }
        if (isSplitable(fs, path)) {
          long blockSize = file.getBlockSize();
          /*
           * 计算分片的大小，每一个文件都要计算一次
           *computeSplitSize的计算公式为 Math.max(minSize, Math.min(goalSize, blockSize));
           */
          long splitSize = computeSplitSize(goalSize, minSize, blockSize);

          long bytesRemaining = length;
          while (((double) bytesRemaining)/splitSize > SPLIT_SLOP) {
            String[] splitHosts = getSplitHosts(blkLocations,
                length-bytesRemaining, splitSize, clusterMap);
            splits.add(makeSplit(path, length-bytesRemaining, splitSize,
                splitHosts));
            bytesRemaining -= splitSize;
          }

          if (bytesRemaining != 0) {
            String[] splitHosts = getSplitHosts(blkLocations, length
                - bytesRemaining, bytesRemaining, clusterMap);
            splits.add(makeSplit(path, length - bytesRemaining, bytesRemaining,
                splitHosts));
          }
        } else {
          String[] splitHosts = getSplitHosts(blkLocations,0,length,clusterMap);
          splits.add(makeSplit(path, 0, length, splitHosts));
        }
      } else { 
        //Create empty hosts array for zero length files
        splits.add(makeSplit(path, 0, length, new String[0]));
      }
    }
    LOG.debug("Total # of splits: " + splits.size());
    return splits.toArray(new FileSplit[splits.size()]);
  }

总结