Modelling Zoned RAID Systems Using Fork-Join Queueing Simulation

  • Abigail S. Lebrecht
  • Nicholas J. Dingle
  • William J. Knottenbelt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5652)


RAID systems are ubiquitously deployed in storage environments, both as standalone storage solutions and as fundamental components of virtualised storage platforms. Accurate models of their performance are crucial to delivering storage infrastructures that meet given quality of service requirements. To this end, this paper presents a flexible fork-join queueing simulation model of RAID systems that are comprised of zoned disk drives and which operate under RAID levels 01 or 5. The simulator takes as input I/O workloads that are heterogeneous in terms of request size and that exhibit burstiness, and its primary output metric is I/O request response time distribution. We also study the effects of heavy workload, taking into account the request-reordering optimisations employed by modern disk drives. All simulation results are validated against device measurements.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Patterson, D.A., Gibson, G., Katz, R.H.: A case for redundant arrays of inexpensive disks (RAID). In: Proc. International Conference on Management of Data (SIGMOD) (1988)Google Scholar
  2. 2.
    Bucy, J.S., Ganger, G.R.: Contributors: The DiskSim Simulation Environment Version 3.0 Reference Manual. School of Computer Science, Carnegie Mellon University. 3.0 edn. (January 2003)Google Scholar
  3. 3.
    Chen, P.M., Lee, E.K.: Striping in a RAID level 5 disk array. SIGMETRICS Performance Evaluation Review 23(1), 136–145 (1995)CrossRefGoogle Scholar
  4. 4.
    Lebrecht, A.S., Dingle, N.J., Knottenbelt, W.J.: A response time distribution model for zoned RAID. In: Al-Begain, K., Heindl, A., Telek, M. (eds.) ASMTA 2008. LNCS, vol. 5055, pp. 144–157. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  5. 5.
    Lee, E.K.: Performance Modeling and Analysis of Disk Arrays. PhD thesis, University of California at Berkeley (1993)Google Scholar
  6. 6.
    Chen, S., Towsley, D.: A performance evaluation of RAID architectures. IEEE Transactions on Computers 45(10), 1116–1130 (1996)CrossRefMATHGoogle Scholar
  7. 7.
    Harrison, P.G., Zertal, S.: Queueing models of RAID systems with maxima of waiting times. Performance Evaluation 64(7-8), 664–689 (2007)CrossRefGoogle Scholar
  8. 8.
    Varki, E.: Response time analysis of parallel computer and storage systems. IEEE Transactions on Parallel and Distributed Systems 12(11), 1146–1161 (2001)CrossRefGoogle Scholar
  9. 9.
    Varki, E., Merchant, A., Xu, J., Qiu, X.: Issues and challenges in the performance analysis of real disk arrays. IEEE Transactions on Parallel and Distributed Systems 15(6), 559–574 (2004)CrossRefGoogle Scholar
  10. 10.
    Lebrecht, A.S., Dingle, N.J., Knottenbelt, W.J.: Modelling and validation of response times in zoned RAID. In: 16th IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS) (September 2008)Google Scholar
  11. 11.
    Lebrecht, A.S., Dingle, N.J., Knottenbelt, W.J.: Validation of large zoned RAID systems. In: 24th UK Performance Engineering Workshop (UKPEW), July 2008, pp. 246–261 (2008)Google Scholar
  12. 12.
    Wan, F., Dingle, N.J., Knottenbelt, W.J., Lebrecht, A.S.: Simulation and modelling of RAID 0 system performance. In: 22nd Annual European Simulation and Modelling Conference (ESM), September 2008, pp. 145–149 (2008)Google Scholar
  13. 13.
    Field, A.J.: JINQS: An Extensible Library for Simulating Multiclass Queueing Networks. Imperial College London (August 2006)Google Scholar
  14. 14.
    Zertal, S., Harrison, P.G.: Multi-RAID queueing model with zoned disks. In: High Performance Computing and Simulation Conference (HPCS) (June 2007)Google Scholar
  15. 15.
    Wikipedia: Standard RAID levels (April 2009),
  16. 16.
    Gomez, M., Santonja, V.: Analysis of self-similarity in I/O workload using structural modeling. In: Proc. 7th International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS), October 1999, pp. 234–243 (1999)Google Scholar
  17. 17.
    Gomez, M., Santonja, V.: Characterizing temporal locality in I/O workload. In: Proc. International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS) (2002)Google Scholar
  18. 18.
    Wang, M., Ailamaki, A., Faloutsos, C.: Capturing the spatio-temporal behavior of real traffic data. Performance Evaluation 49(1-4), 147–163 (2002)CrossRefMATHGoogle Scholar
  19. 19.
    Riska, A., Riedel, E.: Disk drive level workload characterization. In: Proc. USENIX 2006 Annual Technical Conference (ATEC), Boston, MA (2006)Google Scholar
  20. 20.
    Ruemmler, C., Wilkes, J.: Unix disk access patterns. In: Proc. Usenix Winter Conference, San Diego, CA, pp. 405–420 (1993)Google Scholar
  21. 21.
    Shriver, E., Merchant, A., Wilkes, J.: An analytic behavior model for disk drives with readahead caches and request reordering. In: Proc. ACM SIGMETRICS, pp. 182–191 (1998)Google Scholar
  22. 22.
    Jacobson, D.M., Wilkes, J.: Disk scheduling algorithms based on rotational position. Technical Report HPL-CSP-91-7rev1, HP Laboratories (1991)Google Scholar
  23. 23.
    Seltzer, M., Chen, P., Ousterhout, J.: Disk Scheduling Revisited. In: Proc. USENIX Winter Technical Conference, USENIX Association, pp. 313–324 (1990)Google Scholar
  24. 24.
    Hsu, W.W., Smith, A.J.: The performance impact of I/O optimizations and disk improvements. IBM Journal of Research and Development 48(2), 255–289 (2004)CrossRefGoogle Scholar
  25. 25.

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Abigail S. Lebrecht
    • 1
  • Nicholas J. Dingle
    • 1
  • William J. Knottenbelt
    • 1
  1. 1.Department of ComputingImperial College LondonUnited Kingdom

Personalised recommendations