Cluster Computing

, Volume 7, Issue 2, pp 141–150 | Cite as

The MOSIX Direct File System Access Method for Supporting Scalable Cluster File Systems

  • Lior Amar
  • Amnon Barak
  • Amnon Shiloh


MOSIX is a cluster management system that supports preemptive process migration. This paper presents the MOSIX Direct File System Access (DFSA), a provision that can improve the performance of cluster file systems by allowing a migrated process to directly access files in its current location. This capability, when combined with an appropriate file system, could substantially increase the I/O performance and reduce the network congestion by migrating an I/O intensive process to a file server rather than the traditional way of bringing the file's data to the process. DFSA is suitable for clusters that manage a pool of shared disks among multiple machines. With DFSA, it is possible to migrate parallel processes from a client node to file servers for parallel access to different files. Any consistent file system can be adjusted to work with DFSA. To test its performance, we developed the MOSIX File-System (MFS) which allows consistent parallel operations on different files. The paper describes DFSA and presents the performance of MFS with and without DFSA.

cluster computing cluster file systems consistent file system massive parallel I/O 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    AFS, (2003).Google Scholar
  2. [2]
    L. Amar, A. Barak and A. Shiloh, The MOSIX parallel I/O system for scalable I/O performance, in: Proc. of the 14th International Conference Parallel and Distributed Computing and Systems (PDCS 2002), Cambridge, MA (November 2002) pp. 495–500.Google Scholar
  3. [3]
    K. Amiri, D. Petrou, G.R. Ganger and G.A. Gibson, Dynamic function placement for data-intensive cluster computing, in: Proc. of the USENIX Annual Technical Conference, San Diego, CA (June 2000) pp. 307–322.Google Scholar
  4. [4]
    T.E. Anderson, M.D. Dahlin, J.M. Neefe, D.A. Patterson, D.S. Roselli and R.Y. Wang, Serverless network file systems, ACM Transactions on Computer Systems 14(1) (1996) 41–79.Google Scholar
  5. [5]
    A. Barak and A. Braverman, Memory ushering in a scalable computing cluster, Journal of Microprocessors and Microsystems 22(3-4) (1998) 175–182.Google Scholar
  6. [6]
    A. Barak and O. La'adan, TheMOSIX multicomputer operating system for high performance cluster computing, Future Generation Computer Systems 12 (1997/1998) 361–372.Google Scholar
  7. [7]
    M. Beynon, C. Chang, U. Catalyurek, T. Kurc, A. Sussman, H. Andrade, R. Ferreira and J. Saltz, Processing large-scale multidimensional data in parallel and distributed environments, Parallel Computing 28(5) (2002) 827–859.Google Scholar
  8. [8]
    Bonnie, (2003).Google Scholar
  9. [9]
    Y. Cho, M. Winslett, M. Subramaniam, Y. Chen, S. Kuo and K.E. Seamons, Exploiting local data in parallel array I/O on a practical network of workstations, in: Proc. 5th Workshop on I/O in Parallel and Distributed Systems, San Jose, CA (1997) pp. 1–13.Google Scholar
  10. [10]
    Coda, (2003).Google Scholar
  11. [11]
    CXFS, (2003).Google Scholar
  12. [12]
    A. Geist, A. Beguelin, J. Dongarra, W. Jiang, R. Manchek and V. Sunderam, PVM: Parallel Virtual Machine (MIT Press, 1994).Google Scholar
  13. [13]
    Global File System (GFS), (2003).Google Scholar
  14. [14]
    M. Harchol-Balter and A. Downey, Exploiting process lifetime distributions for dynamic load balancing, ACM Transactions on Computer Systems 15(3) (1997) 253–285.Google Scholar
  15. [15]
    J. Katcher, PostMark: A new file system benchmark, http://www. (2003).Google Scholar
  16. [16]
    A. Keren and A. Barak, Opportunity cost algorithms for reduction of I/O and interprocess communication overhead in a computing cluster, IEEE Transactions on Parallel and Distributed Systems 14(1) (2003) 39–50.Google Scholar
  17. [17]
    MOSIX, (2003).Google Scholar
  18. [18]
    NFS version 3 protocol specification, (2003).Google Scholar
  19. [19]
    P. Pacheco, Parallel Programming with MPI (Morgan Kaufmann, 1996).Google Scholar
  20. [20]
    Polyserve Matrix Server, (2003).Google Scholar
  21. [21]
    F. Schmuck and R. Haskin, GPFS: A shared-disk file system for large computing clusters, in: Proc. of the USENIX Conference on File and Storage Technologies (FAST '02), Monterey, CA (January 2002) pp. 232–244.Google Scholar

Copyright information

© Kluwer Academic Publishers 2004

Authors and Affiliations

  • Lior Amar
    • 1
  • Amnon Barak
    • 1
  • Amnon Shiloh
    • 1
  1. 1.Institute of Computer ScienceThe Hebrew University of JerusalemJerusalemIsrael

Personalised recommendations