Use of a Levy Distribution for Modeling Best Case Execution Time Variation

  • Jonathan C. Beard
  • Roger D. Chamberlain
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8721)

Abstract

Minor variations in execution time can lead to out-sized effects on the behavior of an application as a whole. There are many sources of such variation within modern multi-core computer systems. For an otherwise deterministic application, we would expect the execution time variation to be non-existent (effectively zero). Unfortunately, this expectation is in error. For instance, variance in the realized execution time tends to increase as the number of processes per compute core increases. Recognizing that characterizing the exact variation or the maximal variation might be a futile task, we take a different approach, focusing instead on the best case variation. We propose a modified (truncated) Levy distribution to characterize this variation. Using empirical sampling we also derive a model to parametrize this distribution that doesn’t require expensive distribution fitting, relying only on known parameters of the system. The distributional assumptions and parametrization model are evaluated on multi-core systems with the common Linux completely fair scheduler.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Abramowitz, M., Stegun, I.A.: Handbook of Mathematical Functions: with Formulas, Graphs, and Mathematical Tables. Courier Dover Publications (2012)Google Scholar
  2. 2.
    Anderson, T.W., Darling, D.A.: Asymptotic theory of certain “goodness of fit” criteria based on stochastic processes. The Annals of Mathematical Statistics, 193–212 (1952)Google Scholar
  3. 3.
    Bryant, R., O’Hallaron, D.R.: Computer Systems: A Programmer’s Perspective. Prentice Hall (2003)Google Scholar
  4. 4.
    Chakravarty, I., Roy, J., Laha, R.: Handbook of Methods of Applied Statistics. McGraw-Hill (1967)Google Scholar
  5. 5.
    Edgar, S., Burns, A.: Statistical analysis of WCET for scheduling. In: Proc. of 22nd IEEE Real-Time Systems Symposium, pp. 215–224 (2001)Google Scholar
  6. 6.
    Engblom, J., Ermedahl, A.: Pipeline timing analysis using a trace-driven simulator. In: Proc. of 6th Int’l Conf. on Real-Time Computing Systems and Applications, pp. 88–95 (1999)Google Scholar
  7. 7.
    Jain, R.: The Art of Computer Systems Performance Analysis. John Wiley & Sons (1991)Google Scholar
  8. 8.
    Kullback, S., Leibler, R.A.: On information and sufficiency. The Annals of Mathematical Statistics, 79–86 (1951)Google Scholar
  9. 9.
    Li, T., Baumberger, D., Hahn, S.: Efficient and scalable multiprocessor fair scheduling using distributed weighted round-robin. ACM SIGPLAN Notices 44(4), 65 (2009)CrossRefGoogle Scholar
  10. 10.
    Mazouz, A., Touati, S.A.A., Barthou, D.: Study of variations of native program execution times on multi-core architectures. In: Proc. of Int’l Conf. on Complex, Intelligent and Software Intensive Systems, pp. 919–924 (2010)Google Scholar
  11. 11.
    Nolan, J.: Stable Distributions: Models for Heavy-tailed Data. Birkhauser (2003)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Jonathan C. Beard
    • 1
  • Roger D. Chamberlain
    • 1
  1. 1.Dept. of Computer Science and EngineeringWashington University in St. LouisSt. LouisUSA

Personalised recommendations