Conductor: Support for Autonomous Configuration of Storage Systems

  • Zsolt Németh
  • Michail D. Flouris
  • Renaud Lachaize
  • Angelos Bilas


Scalable storage systems are expected to scale to large numbers of physical storage devices and to service diverse applications without incuring high management costs. New storage virtualization architectures and techniques that are currently being proposed, aim at addressing these needs by providing the ability to configure storage systems to meet resource constraints and application requirements. However, this flexibility leads to a large number of options when configuring storage systems either statically or dynamically.

In this work we examine how this process can be automated. We present Conductor, a rule-based production system that is able to evaluate alternatives and minimize system cost, based on certain criteria. Conductor starts from a set of system resources and a set of application requirements and proposes specific system configurations that meet application requirements while minimizing resource costs. It captures human expertise in the form of rules to generate and evaluate configuration alternatives. In this work we focus on static configuration issues and examine various approaches for reducing complexity within a large configuration space. Our techniques manage to satisfy practical time and resource constraints.


distributed storage architecture virtualization rule based management 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Gartner Group. Total Cost of Storage Ownership — A User-oriented Approach. September 2000.Google Scholar
  2. [2]
    E. Anderson et al. Ergastulum: Quickly Finding Near-Optimal Storage System Designs. HP Labs SSP technical report HPL-SSP-2001-05 (2002)Google Scholar
  3. [3]
    E. Anderson et al. Selecting RAID Levels for Disk Arrays. Proc. of the USENIX FAST Conference, January 28–30, 2002, Monterey, CA, USA.Google Scholar
  4. [4]
    C Language Integrated Production System (CLIPS) and also CLIPS Reference Manual. Vol. 1, Version 6.24, 15 June 2006Google Scholar
  5. [5]
    M.D. Flouris, A. Bilas. Violin: A Framework for extensible Block-level Storage. Proc. of the 22nd IEEE / 13th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST 2005) April 2005, Monterey, CA, USA. IEEE Computer Society.Google Scholar
  6. [6]
    M. Flouris, R. Lachaize, and A. Bilas. Violin: a Framework for Extensible Block-Level Storage. Book on Knowledge and Data Management in Grids, CoreGRID series, Springer Verlag, 3, 2006.Google Scholar
  7. [7]
    D. Klahr, P. Langley, R. Neches (eds.): Production System Models of Learning and Development. MIT Press, 1987.Google Scholar
  8. [8]
    W. Mettrey. A Comparative Evaluation of Expert System Tools. Computer 24,2 (Feb. 1991), pp. 19–31.CrossRefGoogle Scholar
  9. [9]
    E. Riedel. Storage Systems. Not Just a Bunch of Disks Anymore. Queue, June 2003, ACM, pp. 32–41.Google Scholar
  10. [10]
    E. Thereska et al. Informed data distribution selection in a self-predicting storage system. Proc. of the International Conference on Autonomic Computing, ICAC-06, Dublin, Ireland, June 2006.Google Scholar
  11. [11]
    S. Uttamchandani et al. Polus: Growing Storage QoS Management Beyond a “Four-year Old Kid”. Proc. of the USENIX FAST’ 04 Conference, March 2004, San Francisco, CA, USA.Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • Zsolt Németh
    • 1
  • Michail D. Flouris
    • 2
  • Renaud Lachaize
    • 3
    • 4
  • Angelos Bilas
    • 3
    • 4
  1. 1.MTA SZTAKI Computer and Automation Research InstituteBudapestHungary
  2. 2.Department of Computer ScienceUniversity of TorontoTorontoCanada
  3. 3.Institute of Computer Science (ICS)Foundation for Research and Technology - HellasHeraklion, GRGreece
  4. 4.Dept. of Computer ScienceUniv. of CreteHeraklion, GRGreece

Personalised recommendations