Parallel Computer Workload Modeling with Markov Chains

  • Baiyi Song
  • Carsten Ernemann
  • Ramin Yahyapour
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3277)


In order to evaluate different scheduling strategies for parallel computers, simulations are often executed. As the scheduling quality highly depends on the workload that is served on the parallel machine, a representative workload model is required. Common approaches such as using a probability distribution model can capture the static feature of real workloads, but they do not consider the temporal relation in the traces. In this paper, a workload model is presented which uses Markov chains for modeling job parameters. In order to consider the interdependence of individual parameters without requiring large scale Markov chains, a novel method for transforming the states in different Markov chains is presented. The results show that the model yields closer results to the real workloads than other common approaches.


Markov Chain Schedule Algorithm Markov Chain Model Transformation Path Workload Modeling 
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.
    Aida, K.: Effect of Job Size Characteristics on Job Scheduling Performance. In: Feitelson, D.G., Rudolph, L. (eds.) IPDPS-WS 2000 and JSSPP 2000. LNCS, vol. 1911, pp. 1–17. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  2. 2.
    Box, G.E.P., Jenkins, G.M.: Time Series Analysis. Holden Day Publishing (1976) ISBN:0-8162-1104-3Google Scholar
  3. 3.
    Cirne, W., Berman, F.: A Comprehensive Model of the Supercomputer Workload. In: 4th Workshop on Workload Characterization (December 2001)Google Scholar
  4. 4.
    Cirne, W., Berman, F.: A Model for Moldable Supercomputer Jobs. In: Proceedings of the IPDPS 2001 - International Parallel and Distributed Processing Symposium (April 2001)Google Scholar
  5. 5.
    Connor, J.T., Martin, R.D., Atlas, L.E.: Recurrent Neural Networks and Robust Time Series Prediction. IEEE Transactions on Neural Networks 5(2), 240–254 (1994)CrossRefGoogle Scholar
  6. 6.
    Downey, A.B.: A Parallel Workload Model and its Implications for Processor Allocation. Technical Report CSD-96-922, University of California, Berkeley (November 1996)Google Scholar
  7. 7.
    Downey, A.B., Feitelson, D.G.: The Elusive Goal of Workload Characterization. ACM SIGMETRICS Performance Evaluation Review 26(4), 14–29 (1999)CrossRefGoogle Scholar
  8. 8.
    Dugad, R.: A Tutorial on Hidden Markov Models and Selected Apllications in Speech Recognition. In: Waibel, A., Lee, K.-F. (eds.) Readings in Speech Recognition, pp. 267–296. Kaufmann, San Mateo (1990)Google Scholar
  9. 9.
    Ernemann, C., Hamscher, V., Schwiegelshohn, U., Streit, A., Yahyapour, R.: Enhanced Algorithms for Multi-Site Scheduling. In: Parashar, M. (ed.) GRID 2002. LNCS, vol. 2536, pp. 219–231. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  10. 10.
    Ernemann, C., Hamscher, V., Schwiegelshohn, U., Streit, A., Yahyapour, R.: On Advantages of Grid Computing for Parallel Job Scheduling. In: Proceedings of the 2nd IEEE/ACM International Symposium on Cluster Computing and the Grid, Berlin, May 2002, IEEE Press, Los Alamitos (2002)Google Scholar
  11. 11.
    Ernemann, C., Hamscher, V., Streit, A., Yahyapour, R.: On Effects of Machine Configurations on Parallel Job Scheduling in Computational Grids. In: International Conference on Architecture of Computing Systems, ARCS, Karlsruhe, April 2002, pp. 169–179. VDE (2002)Google Scholar
  12. 12.
    Ernemann, C., Hamscher, V., Yahyapour, R.: Economic Scheduling in Grid Computing. In: Feitelson, D.G., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2002. LNCS, vol. 2537, pp. 128–152. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  13. 13.
    Ernemann, C., Song, B., Yahyapour, R.: Scaling of Workload Traces. In: Feitelson, D.G., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2003. LNCS, vol. 2862, pp. 166–183. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  14. 14.
    Ernemann, C., Yahyapour, R.: Grid Resource Management - State of the Art and Future Trends. In: Applying Economic Scheduling Methods to Grid Environments, pp. 491–506. Kluwer Academic Publishers, Dordrecht (2003)Google Scholar
  15. 15.
    Feitelson, D.G.: Packing Schemes for Gang Scheduling. In: Feitelson, D.G., Rudolph, L. (eds.) IPPS-WS 1996 and JSSPP 1996. LNCS, vol. 1162, pp. 89–110. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  16. 16.
    Feitelson, D.G.: Workload Modeling for Performance Evaluation. In: Calzarossa, M.C., Tucci, S. (eds.) Performance 2002. LNCS, vol. 2459, pp. 114–141. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  17. 17.
    Feitelson, D.G., Rudolph, L., Schwiegelshohn, U., Sevcik, K.C., Wong, P.: Theory and practice in parallel job scheduling. In: Feitelson, D.G., Rudolph, L. (eds.) IPPS-WS 1997 and JSSPP 1997. LNCS, vol. 1291, pp. 1–34. Springer, Heidelberg (1997)Google Scholar
  18. 18.
    Hotovy, S.: Workload Evolution on the Cornell Theory Center IBM SP2. In: Feitelson, D.G., Rudolph, L. (eds.) IPPS-WS 1996 and JSSPP 1996. LNCS, vol. 1162, pp. 27–40. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  19. 19.
    Ihaka, R., Gentleman, R.: R: A Language for Data Analysis and Graphics. Journal of Computational and Graphical Statistics 5(3), 299–314 (1996)CrossRefGoogle Scholar
  20. 20.
    Jann, J., Pattnaik, P., Franke, H., Wang, F., Skovira, J., Riodan, J.: Modeling of Workload in MPPs. In: Feitelson, D.G., Rudolph, L. (eds.) IPPS-WS 1997 and JSSPP 1997. LNCS, vol. 1291, pp. 94–116. Springer, Heidelberg (1997)Google Scholar
  21. 21.
    Jenkins, J.H.: Stationary joint distributions arising in the analysis of the M/G/1 queue by the method of the imbedded Markov chain. Journal of Applied Physics 3, 512–520 (1966)zbMATHMathSciNetGoogle Scholar
  22. 22.
    Lilliefors, H.: On the Kolmogorov-Smirnov Test for the Exponential Distribution with Mean Unknown. Journal of the American Statistical Association 64, 387–389 (1969)CrossRefGoogle Scholar
  23. 23.
    Lo, V., Mache, J., Windisch, K.: A comparative study of real workload traces and synthetic workload models for parallel job scheduling. In: Feitelson, D.G., Rudolph, L. (eds.) IPPS-WS 1998, SPDP-WS 1998, and JSSPP 1998. LNCS, vol. 1459, pp. 25–46. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  24. 24.
    Lublin, U., Feitelson, D.G.: The Workload on Parallel Supercomputers: Modeling the Characteristics of Rigid Jobs. Journal of Parallel and Distributed Computing 63(11), 1105–1122 (2003)zbMATHCrossRefGoogle Scholar
  25. 25.
    Mache, J., Lo, V., Windisch, K.: Minimizing message-passing contention in fragmentation-free processor allocation. In: Proceedings of the 10th International Conference on Parallel and Distributed Computing Systems (1997)Google Scholar
  26. 26.
    Nefian, A.V., Hayes, M.H.: Face recognition using an embedded HMM. In: Proceedings of the IEEE Conference on Audio and Video-based Biometric Person Authentication, pp. 19–24 (1999)Google Scholar
  27. 27.
    Bahl, L.R., Jelinek, F., Mercer, R.L.: A maximum likelihood approach to continuous speech recognition. In: IEEE Transactions on Pattern Analysis and Machine Intelligenc PAMI-5, pp. 179–190 (1983); Reprinted in Waibel, Lee, pp. 308–319 (1990)Google Scholar
  28. 28.
    Rosti, E., Smirni, E., Dowdy, L.W., Serazzi, G., Carlson, B.M.: Robust Partitioning Policies of Multiprocessor Systems. Performance Evaluation Journal, Special Issue on Parallel Systems 19(2-3), 141–165 (1994)Google Scholar
  29. 29.
    Subhlok, J., Gross, T., Suzuoka, T.: Impact of Job Mix on Optimizations for Space Sharing Schedulers. In: Proceedings of the 1996 ACM/IEEE conference on Supercomputing (1996)Google Scholar
  30. 30.
    Parallel Workloads Archive (July 2004),
  31. 31.
    Temujin, G., Van Hulle, M.M.: Separation of Acoustic Signals Using Self-organizing Neural Networks. In: Proceedings IEEE Neural Network for Signal Processing Workshop 1999, Madison, WI, USA, pp. 324–332 (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Baiyi Song
    • 1
  • Carsten Ernemann
    • 1
  • Ramin Yahyapour
    • 1
  1. 1.Computer Engineering InstituteUniversity DortmundDortmundGermany

Personalised recommendations