goalSize： totalsize/numSplits  ; 
minSize： InputSplit 最小值 配置参数
blockSize： block大小

/** Splits files returned by {@link #listStatus(JobConf)} when
   * they're too big.*/ 
  public InputSplit[] getSplits(JobConf job, int numSplits)
    throws IOException {
    StopWatch sw = new StopWatch().start();
    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();
    }
 
    long goalSize = totalSize / (numSplits == 0 ? 1 : numSplits);
    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();
          long splitSize = computeSplitSize(goalSize, minSize, blockSize);
 
          long bytesRemaining = length;
          while (((double) bytesRemaining)/splitSize > SPLIT_SLOP) {
            String[][] splitHosts = getSplitHostsAndCachedHosts(blkLocations,
                length-bytesRemaining, splitSize, clusterMap);
            splits.add(makeSplit(path, length-bytesRemaining, splitSize,
                splitHosts[0], splitHosts[1]));
            bytesRemaining -= splitSize;
          }
 
          if (bytesRemaining != 0) {
            String[][] splitHosts = getSplitHostsAndCachedHosts(blkLocations, length
                - bytesRemaining, bytesRemaining, clusterMap);
            splits.add(makeSplit(path, length - bytesRemaining, bytesRemaining,
                splitHosts[0], splitHosts[1]));
          }
        } else {
          String[][] splitHosts = getSplitHostsAndCachedHosts(blkLocations,0,length,clusterMap);
          splits.add(makeSplit(path, 0, length, splitHosts[0], splitHosts[1]));
        }
      } else { 
        //Create empty hosts array for zero length files
        splits.add(makeSplit(path, 0, length, new String[0]));
      }
    }
    sw.stop();
    if (LOG.isDebugEnabled()) {
      LOG.debug("Total # of splits generated by getSplits: " + splits.size()
          + ", TimeTaken: " + sw.now(TimeUnit.MILLISECONDS));
    }
    return splits.toArray(new FileSplit[splits.size()]);
  }

public RecordReader<LongWritable, Text> getRecordReader(
                                          InputSplit genericSplit, JobConf job,
                                          Reporter reporter)
    throws IOException {
    
    reporter.setStatus(genericSplit.toString());
    String delimiter = job.get("textinputformat.record.delimiter");
    byte[] recordDelimiterBytes = null;
    if (null != delimiter) {
      recordDelimiterBytes = delimiter.getBytes(Charsets.UTF_8);
    }
    return new LineRecordReader(job, (FileSplit) genericSplit,
        recordDelimiterBytes);
  }

// If this is not the first split, we always throw away first record
// because we always (except the last split) read one extra line in
// next() method.
if (start != 0) {
start += in.readLine(new Text(), 0, maxBytesToConsume(start));
}
this.pos = start;

/**
   * Read a line.
   */
public synchronized boolean next(LongWritable key, Text value)
    throws IOException {

    // We always read one extra line, which lies outside the upper
    // split limit i.e. (end - 1)
    while (getFilePosition() <= end || in.needAdditionalRecordAfterSplit()) {
        key.set(pos);

        int newSize = 0;
        if (pos == 0) {
            newSize = skipUtfByteOrderMark(value);
        } else {
            newSize = in.readLine(value, maxLineLength, maxBytesToConsume(pos));
            pos += newSize;
        }

        if (newSize == 0) {
            return false;
        }
        if (newSize < maxLineLength) {
            return true;
        }

        // line too long. try again
        LOG.info("Skipped line of size " + newSize + " at pos " + (pos - newSize));
    }

    return false;
}