Using Blocks Correlations to Improve the I/O Performance of Large Network Storage System

  • ChangSheng Xie
  • Zhen Zhao
  • Jian Liu
  • Wei Wu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3759)


In the large network storage system, the operation of continuously reading discrete small blocks severely impacts the I/O performance. To solve this problem, this paper designs and implements a system prototype, which implements precise prefetch and regulates the data distribution according the small blocks correlations, mined by a novel heuristic algorithm between the file system and block device. The system performance can be improved evenly and continuously without interruption and sudden state transitions. Furthermore, compared with other algorithms, this heuristic algorithm thinks about both the locality and the globality of the correlations. Through the experiments, it has been proved that the prototype and the algorithm are effective and the system I/O performance can be enhanced distinctly. Furthermore, the prototype can be used universally by not modifying the file system and the storage devices.


Heuristic Algorithm File System Storage Node Data Layout Read Request 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Zhou, K.E., Zhang, J.-L.: Cache pfefetching adaptive policy based on access pattern. In: Proceedings of the first International Conference on machine leaning and cybernetics, Beijing, November 4-5 (2002)Google Scholar
  2. 2.
    Ayres, J., Gehrke, J.E., Yiu, T., Flan nick, J.: Sequential pattern mining using bitmaps. In: Proc. 2002 ACM SIGKDD Int. Conf. Knowledge Discovery in Databases (KDD 2002), Edmonton, Canada, pp. 429–435 (July 2002)Google Scholar
  3. 3.
    Hu, Y., Yang, Q.: DCD—Disk Caching Disk: A New Approach for Boosting I/O Performance. In: Proceedings of the 23td international Symposium on computer Architecture, pp. 169–178 (May 1996)Google Scholar
  4. 4.
    Brown, A.D., Mowry, T.C., Krieger, O.: Compiler-based I/O prefetching for out-of-core applications. ACM Transactions on Computer Systems 19(2), 111–170 (2001)CrossRefGoogle Scholar
  5. 5.
    Agrawal, R., Srikant, R.: Mining sequential patterns. In: Eleventh International Conference on Data Engineering (1995)Google Scholar
  6. 6.
    Ganger, G.R., Soules, C.A.N.: Soft Updates: A Solution to the Metadata Update Problem in File Systems. ACM Transactions on Computer Systems ( May 2000)Google Scholar
  7. 7.
    Soules, C.A.N., Goodson, G.R., Strunk, J.D., Ganger, G.R.: Metadata Efficiency in Versioning File Systems. In: 2nd USENIX Conference on File and Storage Technologies, San Francisco, CA, March 31 - April 2 (2003)Google Scholar
  8. 8.
    Schindler, J., Griffin, J., Lumb, C., Ganger, G.: Track-aligned extents: matching access patterns to disk drive characteristics. In: Proceedings of the First USENIX Conference on File and Storage Technologies (2002)Google Scholar
  9. 9.
    Seifert, A., Scholl, M.H.: A multi-version cache replacement and prefetching policy for hybrid data delivery environments. In: 28th International Conference on Very Large Data Bases, VLDB (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • ChangSheng Xie
    • 1
  • Zhen Zhao
    • 1
  • Jian Liu
    • 1
  • Wei Wu
    • 1
  1. 1.National Storage System Laboratory, College of Computer Science & TechnologyHuazhong University of Science & TechnologyHuBei, WuHan

Personalised recommendations