Hadoop中FileInputFormat源码解析

基于Hadoop2.6.0

 //生成文件list，放进filesplits
  public List<InputSplit> getSplits(JobContext job) throws IOException {
    Stopwatch sw = new Stopwatch().start();
    long minSize = Math.max(getFormatMinSplitSize(), getMinSplitSize(job));
    long maxSize = getMaxSplitSize(job);

    // generate splits
    List<InputSplit> splits = new ArrayList<InputSplit>();
    List<FileStatus> files = listStatus(job);
    for (FileStatus file: files) {
      Path path = file.getPath();
      long length = file.getLen();
      if (length != 0) {
        BlockLocation[] blkLocations;
        if (file instanceof LocatedFileStatus) {
          blkLocations = ((LocatedFileStatus) file).getBlockLocations();
        } else {
          FileSystem fs = path.getFileSystem(job.getConfiguration());
          blkLocations = fs.getFileBlockLocations(file, 0, length);
        }
        if (isSplitable(job, path)) {
          long blockSize = file.getBlockSize();
          long splitSize = computeSplitSize(blockSize, minSize, maxSize);

          long bytesRemaining = length;
          while (((double) bytesRemaining)/splitSize > SPLIT_SLOP) {
            int blkIndex = getBlockIndex(blkLocations, length-bytesRemaining);
            splits.add(makeSplit(path, length-bytesRemaining, splitSize,
                        blkLocations[blkIndex].getHosts(),
                        blkLocations[blkIndex].getCachedHosts()));
            bytesRemaining -= splitSize;
          }

          if (bytesRemaining != 0) {
            int blkIndex = getBlockIndex(blkLocations, length-bytesRemaining);
            splits.add(makeSplit(path, length-bytesRemaining, bytesRemaining,
                       blkLocations[blkIndex].getHosts(),
                       blkLocations[blkIndex].getCachedHosts()));
          }
        } else { // not splitable
          splits.add(makeSplit(path, 0, length, blkLocations[0].getHosts(),
                      blkLocations[0].getCachedHosts()));
        }
      } else { 
        //Create empty hosts array for zero length files
        splits.add(makeSplit(path, 0, length, new String[0]));
      }
    }
    // Save the number of input files for metrics/loadgen
    job.getConfiguration().setLong(NUM_INPUT_FILES, files.size());
    sw.stop();
    if (LOG.isDebugEnabled()) {
      LOG.debug("Total # of splits generated by getSplits: " + splits.size()
          + ", TimeTaken: " + sw.elapsedMillis());
    }
    return splits;
  }

其中的

  /**
   * Get the lower bound on split size imposed by the format.
   * @return the number of bytes of the minimal split for this format
   */
  protected long getFormatMinSplitSize() {
    return 1;
  }

 /**
   * Get the minimum split size
   * @param job the job
   * @return the minimum number of bytes that can be in a split
   */
  public static long getMinSplitSize(JobContext job) {
    return job.getConfiguration().getLong(SPLIT_MINSIZE, 1L);
  }

 /**
   * Get the maximum split size.
   * @param context the job to look at.
   * @return the maximum number of bytes a split can include
   */
  public static long getMaxSplitSize(JobContext context) {
    return context.getConfiguration().getLong(SPLIT_MAXSIZE, 
                                              Long.MAX_VALUE);
  }

  protected long computeSplitSize(long blockSize, long minSize,
                                  long maxSize) {
    return Math.max(minSize, Math.min(maxSize, blockSize));
  }