General Queueing Network Models with Variable Concurrent Programming Structures and Synchronisation

  • Demetres D. Kouvatsos
  • Andreas Skliros
Conference paper
Part of the Workshops in Computing book series (WORKSHOPS COMP.)

Abstract

A significant computational gain can be achieved through concurrent programming by exploiting parallel and distributed processing capabilities of current computer system architectures. The performance evaluation and quantitative analysis of such systems have become important due to the multiplicity of the component parts and the complexity of their functioning. In this paper an approximate method is developed for the analysis of general queueing network models of computer systems with variable concurrency and synchronisation structures. It is based on the maximum entropy algorithm and the notion of surrogate delays. Numerical examples illustrate the capability of the proposed algorithm in comparison to simulation.

Keywords

Entropy Radar Expense Convolution 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Ben-Ari M. Principles of concurrent and distributed programming. Prentice Hall, Englewood Cliff, N.J., 1990.MATHGoogle Scholar
  2. [2]
    Whiddett D. Concurrent programming for software engineers. Ellis Horwood Ltd, Chichester, 1987.Google Scholar
  3. [3]
    Peterson J. and Bulgren N. Studies in Markov models of computer systems. Proc. ACM Annual Conf., 1975, pp 102–107.Google Scholar
  4. [4]
    Price T.G. Models of multiprogrammed computer systems with I/O buffering. Proc. 4th Texas Conf. Comp. Syst., Univ. Texas, 1975.Google Scholar
  5. [5]
    Mackawa M. and Boyd D.L. Two models of task overlap within jobs of multiprocessing multiprogramming systems. Proc. Int. Conf. Parallel Processing, 1976, pp 83–91.Google Scholar
  6. [6]
    Towsley D., Chandy K.M. and Browne J.C. Models for parallel processing with programs: Applications to CPU:I/0 and 1/0:1/0 Overlap. Com. ACM, 1978, 21, pp 821–831.CrossRefGoogle Scholar
  7. [7]
    Herzog U., Hoffman W. and Kleinoder W. Performance Modelling and Evaluation for hierarchical organised multiprocessor computer systems. Proc. Int. Conf. Parallel Processing, 1979, pp 103–114.Google Scholar
  8. [8]
    Bard Y. Some extension to multiclass queueing network analysis. Proc. 4th Int. Symp. Model. & Perfor. Eval. Comp. Syst., vol 1,1979.Google Scholar
  9. [9]
    Sauer C.H. and Chandi K.M. Computer systems performance modelling. Prentice Hall, 1981.Google Scholar
  10. [10]
    Heidelberger P. and Trivedi K.S. Analytic queueing models for programs with internal concurrency. IEEE Trans. Comp., 1983, C-32, pp 73–82.MATHCrossRefGoogle Scholar
  11. [11]
    Thomaisan A. and Bay P.F. Analytic queueing network models for parallel processing of task systems. IEEE Trans. Comp., 1986, C-35, pp 1045–1054.CrossRefGoogle Scholar
  12. [12]
    Peng D. and Shin K.G. Modelling of concurrent task execution in distributed systems for real-time control. IEE Trans. Comp., 1987, C-36, pp 500–516.CrossRefGoogle Scholar
  13. [13]
    Skliros A.P. and Kouvatsos D.D. General queueing network models with job concurrency and synchronisation. Proc. 5th UK Comp and Telecom. Perf. Eng. Workshop, 1989, Univ. Edinburgh.Google Scholar
  14. [14]
    Kouvatsos D.D. and Skliros A.P. General queueing network models of parallel task processing computer systems: A comparative study. Proc. 6th UK Comp and Telecom. Perf. Eng. Workshop, 1990, Univ. Bradford.Google Scholar
  15. [15]
    Kouvatsos D.D. A universal maximum entropy algorithm for the analysis of the general closed networks. In: Hesagawa T. et al (eds) Computer Modelling and Performance Evaluation, North Holland, Amsterdam, 1986, pp 113–124.Google Scholar
  16. [16]
    Jacobson P.A. and Lazowska E.D. Analyzing queueing networks with simultaneous resource possession. Com. ACM, 1981, pp 142–151Google Scholar
  17. [17]
    U.S. Department of Defence. Programming language Ada: Reference manual, vol. 106, Lecture notes in Comp. Sci., Springer-Verlag 1981.Google Scholar
  18. [18]
    Kouvatsos D.D. and Tabet-Aouel N.M. Product-form approximations for an extended class of general closed queueing networks. In: King P.J.B. et al (eds), Performance ‘90, North-Holland, Amsterdam, 1990, pp301–315.Google Scholar
  19. [19]
    Georgatsos P.H. Modelling and analysis of computer communication networks with random or semidynamic routing, PhD Thesis, Univ. Bradford, 1989Google Scholar
  20. [20]
    Veran M. and Potier D. A portable environment for queueing network modelling. In: Potier D. (ed), Modelling techniques and tools for performance analysis, North-Holland, Amsterdam, 1985, pp 25–63.Google Scholar

Copyright information

© Springer-Verlag London 1992

Authors and Affiliations

  • Demetres D. Kouvatsos
    • 1
  • Andreas Skliros
    • 1
  1. 1.Computer Systems Modelling Research GroupUniversity of BradfordBradfordUK

Personalised recommendations