A Content-Based Load Balancing Algorithm for Metadata Servers in Cluster File Systems

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3758)


A metadata service is one of the important factors to affect the performance of cluster file systems. We propose a content-based load balancing algorithm that dynamically distributes client requests to appropriate metadata servers based on the types of metadata operations. By replicating metadata and logging update messages in each server rather than moving metadata across servers, we significantly reduce the response time and evenly distribute client requests among metadata servers.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    SPEC, SFS 3.0 Documentation Version 1.0, Standard Performance Evaluation Corporation (2001)Google Scholar
  2. 2.
    Corbett, P.F., et al.: The vesta parallel file system. ACM Transactions on Computer Systems (TOCS) 14(3), 225–264 (1996)CrossRefGoogle Scholar
  3. 3.
    Brandt, S.A., et al.: Efficient Metadata Management in Large Distributed Storage Systems. In: Proceedings of the 11th IEEE NASA Goddard Conference on Mass Storage Systems and Technologies (April 2003)Google Scholar
  4. 4.
    Braam, P.J., et al.: The Lustre Storage Architecture, Cluster File Architecture. Cluster File System. Inc (March 2003)Google Scholar
  5. 5.
    Xiong, J., et al.: Design and Performance of the Dawning Cluster File System. In: IEEE International Conference on Cluster Computing(Cluster 2003) (December 2003)Google Scholar
  6. 6.
    Bourke, T.: Server Load Balancing. O’Reilly and Associates, Sebastopol (2001)Google Scholar
  7. 7.
    Bovet, D.P., et al.: Understanding the Linux Kernel. O’Reilly and Associates, Sebastopol (2003)Google Scholar
  8. 8.

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  1. 1.Department of Computer Science and, Interdisciplinary Program of Integrated BiotechnologySogang UniversitySeoulKorea

Personalised recommendations