Adaptive Scheduling for QoS Virtual Machines under Different Resource Allocation – Performance Effects and Predictability

  • Angela C. Sodan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5798)

Abstract

Virtual machines have become an important approach to provide performance isolation and performance guarantees (QoS) on cluster servers and on many-core SMP servers. Many-core CPUs are a current trend in CPU design and require jobs to be parallel for exploitation of the performance potential. Very promising for batch job scheduling with virtual machines on both cluster servers and many-core SMP servers is adaptive scheduling which can adjust sizes of parallel jobs to consider different load situations and different resource availability. Then, the resource allocation and resource partitioning can be determined at virtual-machine level and be propagated down to the job sizes. The paper investigates job re-sizing and virtual-machine resizing, and the effects which the efficiency curve of the jobs has on the resulting performance. Additionally, the paper presents a simple, yet effective queuing-model approach for predicting performance under different resource allocation.

Keywords

adaptive job scheduling molding utilization prediction queuing model 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Barsanti, L., Sodan, A.C.: Adaptive Job Scheduling via Predictive Job Resource Allocation. In: Frachtenberg, E., Schwiegelshohn, U. (eds.) JSSPP 2006. LNCS, vol. 4376, pp. 115–140. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  2. 2.
    Chiang, S.-H., Vernon, M.K.: Dynamic vs. Static Quantum-Based Parallel Processor Allocation. In: Feitelson, D.G., Rudolph, L. (eds.) IPPS-WS 1996 and JSSPP 1996. LNCS, vol. 1162, pp. 200–223. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  3. 3.
    Cirne, W., Berman, F.: When the Herd is Smart-Aggregate Behavior in the selection of Job Request. IEEE Trans. on Par. and Distr. Systems 14(2), 181–192 (2003)Google Scholar
  4. 4.
    Downey, A.: A Model for Speedup of Parallel Programs. Technical Report CSD-97-933, Univ. of California Berkeley (January 1997)Google Scholar
  5. 5.
    Esbaugh, B., Sodan, A.C.: Coarse-Grain Time Slicing with Resource-Share Control in Parallel-Job Scheduling. In: Perrott, R., Chapman, B.M., Subhlok, J., de Mello, R.F., Yang, L.T. (eds.) HPCC 2007. LNCS, vol. 4782, pp. 30–43. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  6. 6.
    Feitelson, D.G., Rudolph, L., Schwiegelsohn, U., Sevcik, K.C., Parsons, W.: 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
  7. 7.
    Feitelson Workload Archive, http://www.cs.huji.ac.il/labs/parallel/workload/logs.html (last retrieved January 2008)
  8. 8.
    Foster, I., Tuecke, S.: The Different Faces of IT as Service. ACM Queue, 27–34 (July/August 2005)Google Scholar
  9. 9.
    Ghosal, D., Serazzi, G., Tripathi, S.K.: The Processor Working Set and Its Use in Scheduling Multiprocessor Systems. IEEE Trans. Software Engineering 17(5), 443–453 (1991)CrossRefGoogle Scholar
  10. 10.
    Lublin, U., Feitelson, D.G.: The Workload on Parallel Supercomputers-Modelling the Characteristics of Rigid Jobs. Journal of Parallel and Distributed Computing 63(11), 1105–1122 (2003)MATHCrossRefGoogle Scholar
  11. 11.
    Machina, J., Sodan, A.C.: Predicting Cache Needs and Cache Sensitivity for Applications in Cloud Computing on CMP Servers with Configurable Caches. In: Workshop on System Management Techniques, Processes, and Services (SMTPS) of IPDPS, Proc. IPDPS, Rome, Italy. IEEE, Los Alamitos (2009)Google Scholar
  12. 12.
    McCann, C., Zahorjan, J.: Processor Allocation Policies for Message Passing Parallel Computers. In: Proc. SIGMETRICS Conf. Measurement & Modeling of Computer Systems, May 1994, pp. 208–219 (1994)Google Scholar
  13. 13.
    Naik, V.K., Setia, S.K., Squillante, M.K.: Processor Allocation in Multiprogrammed Distributed-Memory Parallel Computer Systems. Journal of Parallel and Distributed Computing 46(1), 28–47 (1997)CrossRefGoogle Scholar
  14. 14.
    Parsons, E.W., Sevcik, K.C.: Implementing Multiprocessor Scheduling Disciplines. In: Feitelson, D.G., Rudolph, L. (eds.) IPPS-WS 1997 and JSSPP 1997. LNCS, vol. 1291, pp. 166–192. Springer, Heidelberg (1997)Google Scholar
  15. 15.
    Rosti, E., Smirni, E., Serazzi, G., Dowdy, L.W.: Analysis of Non-Work-Conserving Processor Partitioning Policies. In: Feitelson, D.G., Rudolph, L. (eds.) IPPS-WS 1995 and JSSPP 1995. LNCS, vol. 949, pp. 165–181. Springer, Heidelberg (1995)Google Scholar
  16. 16.
    Sevcik, K.C.: Characterization of Parallelism in Applications and Their Use in Scheduling. Performance Evaluation Review 17, 171–180 (1989)CrossRefGoogle Scholar
  17. 17.
    Sodan, A.C., Machina, J., Deshmeh, A., Macnaughton, K., Esbaugh, B.: Parallelism in Multithreaded and Multicore CPUs. Conditionally accepted for IEEE ComputerGoogle Scholar
  18. 18.
    Sodan, A.C.: Dynamic Job Scheduling for Computational Grids. In: Grid Computing Research Progress. Nova Science Publisher, Inc., Hauppauge (2008)Google Scholar
  19. 19.
    Sodan, A.C.: Autonomic Share Allocation and Bounded Prediction of Response Times in Parallel Job Scheduling for Grids. In: Workshop on Adaptive Grid Computing (NCA-AGC), Proc. IEEE Int. Symp. on Network Computing and Applications (NCA), Cambridge, Mass., July 2008, pp. 307–314 (2008)Google Scholar
  20. 20.
    Sodan, A.: Service Control and Service Prediction with the Preemptive Parallel Job Scheduler Scojo-PECT. Submitted to journalGoogle Scholar
  21. 21.
    Sodan, A.C., Lan, L.: LOMARC Lookahead Matchmaking for Multiresource Coscheduling on Hyperthreaded CPUs. IEEE Trans. on Parallel and Distributed Systems 17(11), 1360–1375 (2006)CrossRefGoogle Scholar
  22. 22.
    Sodan, A.C., Huang, X.: Adaptive Time/Space Sharing for Workload Adaptation and Fragmentation Reduction. IJHPCN 4(5/6), 256–269 (2006)CrossRefGoogle Scholar
  23. 23.
    Srinivasan, S., Subramani, V., Kettimuthu, R., Holenarsipur, P., Sadayappan, P.: Effective Selection of Partition Sizes for Moldable Scheduling of Parallel Jobs. In: Sahni, S.K., Prasanna, V.K., Shukla, U. (eds.) HiPC 2002. LNCS, vol. 2552, pp. 174–183. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  24. 24.
    Sutter, H.: The Free Lunch is Over-A Fundamental Turn Toward Concurrency in Software. Dr. Dobb’s Journal 30(3) (March 2005)Google Scholar
  25. 25.
    Weinberg, J., Snavely, A.: Symbiotic Space-Sharing on SDSC’s DataStar System. In: Frachtenberg, E., Schwiegelshohn, U. (eds.) JSSPP 2006. LNCS, vol. 4376, pp. 192–209. Springer, Heidelberg (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Angela C. Sodan
    • 1
  1. 1.University of WindsorWindsorCanada

Personalised recommendations