Performance analysis of interactive systems

  • Yonathan Bard
Session 2: Managing Interactive Systems
Part of the Lecture Notes in Computer Science book series (LNCS, volume 49)


Many topics are covered by the science (art?) of system performance analysis. Among these are measurement of existing systems, tuning, performance evaluation, design of control algorithms, system modeling, workload characterization, and performance prediction. After giving a brief summary of these topics, the paper will concentrate on the last three. It will describe how existing workloads can be measured and analyzed routinely so as to produce the inputs required by analytic system models. These models employ queueing network formulations which allow the workload to consist of several user classes with different characteristics. Such models have been validated successfully against real systems, but some problems, particularly relating to paging in virtual memory systems, have so far not received definitive solutions.


Service Time Distribution Main Storage Page Fault Secondary Storage Queue Network Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Y. Bard, Performance criteria and measurement for a time-sharing system, IBM Systems Journal 10, 193–216 (1971).Google Scholar
  2. 2.
    W. Buchholz, A synthetic job for measuring system performance, IBM Systems Journal 8, 290–298 (1969).Google Scholar
  3. 3.
    P.A. Hamilton and B.W. Kernigan, Synthetically generated performance test loads for operating systems, 1-st Annual Symposium on Measurement and Evaluation, SIGME, Palo Alto, 121–126 (1973).Google Scholar
  4. 4.
    P.J. Denning, The working set model for program behavior, Communications of the ACM 11, 323–333 (1968).Google Scholar
  5. 5.
    P.J. Denning and S.C. Schwartz, Properties of the working set model, Communications of the ACM 15, 191–198 (1972).Google Scholar
  6. 6.
    R.P. Parmelee, T.I. Peterson, C.C. Tillman, and D.J. Hatfield, Virtual storage and virtual machine concepts, IBM Systems Journal 11, 99–130 (1972).Google Scholar
  7. 7.
    Y. Bard, Application of the page survival index (PSI) to virtual memory system performance, IBM J. Res. Develop. 19, 212–220 (1975).Google Scholar
  8. 8.
    J.R. Jackson, Jobshop-like queueing systems, Management Science 10, 131–142 (1963).Google Scholar
  9. 9.
    W.J. Gordon and G.F. Newell, Closed queueing systems with exponential servers, Operations Research 15, 254–265 (1967).Google Scholar
  10. 10.
    J. Buzen, Analysis of system bottlenecks using a queueing network model, ACM Workshop on System Performance Evaluation, SIGOPS, Cambridge, Mass. 82–102 (1971).Google Scholar
  11. 11.
    F. Baskett, K.M. Chandy, R.R. Muntz, and F.G. Palacios, Open, closed, and mixed networks of queues with different classes of customers, Journal of the ACM 22, 248–260 (1975).Google Scholar
  12. 12.
    M. Reiser and H. Kobayashi, Queueing networks with multiple closed chains: Theory and computational algorithms, IBM J. Res. Develop. 19, 283–294 (1975).Google Scholar
  13. 13.
    H. Kobayashi and M. Reiser, On generalization of job routing behavior in a queueing network model, Research Report RC-5679, IBM, Yorktown Heights (1975).Google Scholar
  14. 14.
    H. Kobayashi, Application of the diffusion approximation to queueing networks, Journal of the ACM 21, 316–328 (1974).Google Scholar
  15. 15.
    K.M. Chandy, U. Herzog, and L. Woo, Approximate analysis of general queueing networks, IBM J. Res. Develop. 19, 43–49 (1975).Google Scholar
  16. 16.
    C.H. Sauer and K.M. Chandy, Approximate analysis of central server models, IBM J. Res. Develop. 19, 301–313 (1975).Google Scholar
  17. 17.
    J.P. Buzen, Fundamental laws of system performance, International Symposium on Computer Performance, Modeling, Measurement, and Evaluation, Cambridge, Mass., 200–210 (1976).Google Scholar
  18. 18.
    IBM Virtual Machine Facility/370, Introduction, Form No. GC20-1800, IBM Data Processing Division, White Plains, N.Y. (1972).Google Scholar
  19. 19.
    Y. Bard, A characterization of VM/370 workloads, Second International Workshop on Modeling and Performance Evaluation of Computer Systems, Stresa (1976).Google Scholar
  20. 20.
    M. Parent and D. Potier, A note on the influence of program loading on the page fault rate, Rapport de Recherche No. 159, IRIA, Rocquencourt (1976).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1977

Authors and Affiliations

  • Yonathan Bard
    • 1
  1. 1.IBM Cambridge Scientific CenterCambridge

Personalised recommendations