Ejemplo n.º 1
0
    /**
     * Produce splits such that each is no greater than the quotient of the total size and the
     * number of splits requested.
     *
     * @param job The handle to the JobConf object
     * @param numSplits Number of splits requested
     */
    public InputSplit[] getSplits(JobConf job, int numSplits) throws IOException {
      int cnfiles = job.getInt(SRC_COUNT_LABEL, -1);
      long cbsize = job.getLong(TOTAL_SIZE_LABEL, -1);
      String srcfilelist = job.get(SRC_LIST_LABEL, "");
      if (cnfiles < 0 || cbsize < 0 || "".equals(srcfilelist)) {
        throw new RuntimeException(
            "Invalid metadata: #files("
                + cnfiles
                + ") total_size("
                + cbsize
                + ") listuri("
                + srcfilelist
                + ")");
      }
      Path src = new Path(srcfilelist);
      FileSystem fs = src.getFileSystem(job);
      FileStatus srcst = fs.getFileStatus(src);

      ArrayList<FileSplit> splits = new ArrayList<FileSplit>(numSplits);
      LongWritable key = new LongWritable();
      FilePair value = new FilePair();
      final long targetsize = cbsize / numSplits;
      long pos = 0L;
      long last = 0L;
      long acc = 0L;
      long cbrem = srcst.getLen();
      SequenceFile.Reader sl = null;
      try {
        sl = new SequenceFile.Reader(fs, src, job);
        for (; sl.next(key, value); last = sl.getPosition()) {
          // if adding this split would put this split past the target size,
          // cut the last split and put this next file in the next split.
          if (acc + key.get() > targetsize && acc != 0) {
            long splitsize = last - pos;
            splits.add(new FileSplit(src, pos, splitsize, (String[]) null));
            cbrem -= splitsize;
            pos = last;
            acc = 0L;
          }
          acc += key.get();
        }
      } finally {
        checkAndClose(sl);
      }
      if (cbrem != 0) {
        splits.add(new FileSplit(src, pos, cbrem, (String[]) null));
      }

      return splits.toArray(new FileSplit[splits.size()]);
    }
Ejemplo n.º 2
0
  /**
   * A TaskTracker wants to know the physical locations of completed, but not yet closed, tasks.
   * This exists so the reduce task thread can locate map task outputs.
   */
  public synchronized MapOutputLocation[] locateMapOutputs(
      String taskId, String[][] mapTasksNeeded) {
    ArrayList v = new ArrayList();
    for (int i = 0; i < mapTasksNeeded.length; i++) {
      for (int j = 0; j < mapTasksNeeded[i].length; j++) {
        TaskInProgress tip = (TaskInProgress) taskidToTIPMap.get(mapTasksNeeded[i][j]);
        if (tip != null && tip.isComplete(mapTasksNeeded[i][j])) {
          String trackerId = (String) taskidToTrackerMap.get(mapTasksNeeded[i][j]);
          TaskTrackerStatus tracker;
          synchronized (taskTrackers) {
            tracker = (TaskTrackerStatus) taskTrackers.get(trackerId);
          }
          v.add(new MapOutputLocation(mapTasksNeeded[i][j], tracker.getHost(), tracker.getPort()));
          break;
        }
      }
    }
    // randomly shuffle results to load-balance map output requests
    Collections.shuffle(v);

    return (MapOutputLocation[]) v.toArray(new MapOutputLocation[v.size()]);
  }