Interval based workload characterization for distributed systems

  • M. Braun
  • G. Kotsis
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1245)


In this paper we analyze a graph model representing the coarse grain dependency and communication structure of a distributed application. The model is called Timed Structural Parallelism Graph (TSPG). Nodes represent program components, arcs represent dependencies among components. This workload model differs from well known task graphs in two ways: (1) arcs can either have dependence or activation semantics and (2) timing parameters associated to arcs and nodes are given as intervals. Besides describing this new workload model, we sketch the issues and problems in corresponding evaluation techniques. In particular, we investigate techniques for estimating the total execution time and for deriving potential parallelism profiles. The proposed techniques are illustrated by example.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [BHK96]
    Markus Braun, Guenter Haring, and Gabriele Kotsis. Deriving parallelism profiles from structural parallelism graphs. In Proc. of the TDP'96, 1996.Google Scholar
  2. [CHK+95]
    Maria Calzarossa, Guenter Haring, Gabriele Kotsis, Alessandro Merlo, and Daniele Tessera. A hierarchical approach to workload characterization for parallel systems. In B. Hertzberger and G. Serazzi, Ed., High Performance Computing and Networking, LNCS vol. 919, pages 102–109, 1995.Google Scholar
  3. [CS93]
    Maria Calzarossa and Guiseppe Serazzi. Workload characterization: A survey. Proc. of the IEEE, 81(8):1136–1150, August 1993.CrossRefGoogle Scholar
  4. [HM92]
    Franz Hartleb and Vassilis Mertsiotakis. Bounds for the mean runtime of parallel programs. In Rob Pooley and Jane Hillston, Eds., Proc. of the 6th Int. Conf. on Modelling Techniques and Tools for Computer Performance Evaluation, pages 197–210, 1992.Google Scholar
  5. [LKMH96]
    Johannes Lüthi, Gabriele Kotsis, Shikharesh Majumdar, and Günter Haring. Bounds-based performance analysis for distributed systems with variabilities and uncertainties in workload. In Proc. of DAPSYS'96, pages 51–58, Hungarian Academy of Sciences Report KFKI-1996-09/M,N, October 1996.Google Scholar
  6. [MR95]
    Shikharesh Majumdar and Revathy Ramadoss. Interval-based performance analysis of computing systems. In Patrick Dowd and Erol Gelenbe, Eds. Proc. MASCOTS 95, pages 345–351. IEEE CS Press, Jan. 1995.Google Scholar
  7. [ST86]
    Robin A. Sahner and Kishor S. Trivedi. SHARPE: Symbolic Hierarchical Automated Reliability and Performance Evaluator — Introduction and Guide for Users. Gould CSD, Urbana, 1101 E. University, Urbana, IL 61801, Sep. 1986.Google Scholar
  8. [vdA94]
    W. M. P. van der Aalst. Using interval timed coloured petri nets to calculate performance bounds. available upon request from, 1994.Google Scholar
  9. [WMN91]
    C. Murray Woodside, Shikharesh Majumdar, and J. E. Neilson. Interval arithmetic for computing performance guarantees in client-server software. In F. Dehne, F. Fiala, and W. W. Koczkodaj, Eds. LNCS 497: Proc. ICCI '91, pages 535–546, Berlin, et al., 1991. Springer-Verlag.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • M. Braun
    • 1
  • G. Kotsis
    • 1
  1. 1.Institut für Angewandte Informatik und InformationssystemeUniversität WienViennaAustria

Personalised recommendations