file1.txt    260M
file2.txt    10M

file1.txt.split1--  0~128
file1.txt.split2--  128~260 //如果剩余的文件长度/切片长度<=1.1则会将剩余文件的长度并未一个切片
file2.txt.split1--  0~10M

minsize：默认值：1  
   配置参数： mapreduce.input.fileinputformat.split.minsize    

maxsize：默认值：Long.MAXValue  
    配置参数：mapreduce.input.fileinputformat.split.maxsize

blocksize:值为hdfs的对应文件的blocksize

配置读取目录下文件数量的线程数:public static final String LIST_STATUS_NUM_THREADS =
      "mapreduce.input.fileinputformat.list-status.num-threads";

   //得到job的map任务的并行数量
   private int writeSplits(org.apache.hadoop.mapreduce.JobContext job,
      Path jobSubmitDir) throws IOException,
      InterruptedException, ClassNotFoundException {
    JobConf jConf = (JobConf)job.getConfiguration();
    int maps;
    if (jConf.getUseNewMapper()) {
      maps = writeNewSplits(job, jobSubmitDir);
    } else {
      maps = writeOldSplits(jConf, jobSubmitDir);
    }
    return maps;
  }
  
  @SuppressWarnings("unchecked")
  private <T extends InputSplit>
  int writeNewSplits(JobContext job, Path jobSubmitDir) throws IOException,
      InterruptedException, ClassNotFoundException {
    Configuration conf = job.getConfiguration();
    InputFormat<?, ?> input =
     ReflectionUtils.newInstance(job.getInputFormatClass(), conf);
　　　
    List<InputSplit> splits = input.getSplits(job);
    T[] array = (T[]) splits.toArray(new InputSplit[splits.size()]);

    // sort the splits into order based on size, so that the biggest
    // go first
    Arrays.sort(array, new SplitComparator());
    JobSplitWriter.createSplitFiles(jobSubmitDir, conf, 
        jobSubmitDir.getFileSystem(conf), array);
    return array.length;
  }

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);
　　 //遍历文件，对每一个文件进行如下处理:获得文件的blocksize,获取文件的长度，得到切片信息(spilt 文件路径，切片编号，偏移量范围)
    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;
  }

 public static final String SPLIT_MINSIZE = 
    "mapreduce.input.fileinputformat.split.minsize";
  
  public static final String SPLIT_MAXSIZE = 
    "mapreduce.input.fileinputformat.split.maxsize";
    
  long minSize = Math.max(getFormatMinSplitSize(), getMinSplitSize(job));
    
  //保证切分的文件长度最小不得小于1字节
  protected long getFormatMinSplitSize() {
    return 1;
  }
  
  //如果没有在conf中设置SPLIT_MINSIZE参数，则取默认值1字节。
  public static long getMinSplitSize(JobContext job) {
    return job.getConfiguration().getLong(SPLIT_MINSIZE, 1L);
  }
  
  //得到切片文件的最大长度
  long maxSize = getMaxSplitSize(job);
  
  //如果没有在conf中设置SPLIT_MAXSIZE参数，则去默认值Long.MAX_VALUE字节。
  public static long getMaxSplitSize(JobContext context) {
    return context.getConfiguration().getLong(SPLIT_MAXSIZE, 
                                              Long.MAX_VALUE);
  }
  
   //读取指定目录下的所有文件的信息
   List<FileStatus> files = listStatus(job);
   //如果没有指定开启几个线程读取，则默认一个线程去读文件信息，因为存在目录下有上亿个文件的情况，所以有需要开启多个线程加快读取。
   int numThreads = job.getConfiguration().getInt(LIST_STATUS_NUM_THREADS,
        DEFAULT_LIST_STATUS_NUM_THREADS);
   public static final String LIST_STATUS_NUM_THREADS =
      "mapreduce.input.fileinputformat.list-status.num-threads";
   public static final int DEFAULT_LIST_STATUS_NUM_THREADS = 1;
  
  //计算切片文件的逻辑大小
  long splitSize = computeSplitSize(blockSize, minSize, maxSize);
  protected long computeSplitSize(long blockSize, long minSize,
                                  long maxSize) {
    return Math.max(minSize, Math.min(maxSize, blockSize));
  }
  
  private static final double SPLIT_SLOP = 1.1;   // 10% slop
  //判断剩余文件与切片大小的比是否为1.1.
  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;
    }