Deadline and energy constrained dynamic resource allocation in a heterogeneous computing environment

Abstract

Energy-efficient resource allocation within clusters and data centers is important because of the growing cost of energy. We study the problem of energy-constrained dynamic allocation of tasks to a heterogeneous cluster computing environment. Our goal is to complete as many tasks by their individual deadlines and within the system energy constraint as possible given that task execution times are uncertain and the system is oversubscribed at times. We use Dynamic Voltage and Frequency Scaling (DVFS) to balance the energy consumption and execution time of each task. We design and evaluate (via simulation) a set of heuristics and filtering mechanisms for making allocations in our system. We show that the appropriate choice of filtering mechanisms improves performance more than the choice of heuristic (among the heuristics we tested).

This is a preview of subscription content, access via your institution.

References

  1. 1.

    Advanced configuration and power interface specification (2010). http://www.acpi.info/DOWNLOADS/ACPIspec40a.pdf. Accessed 2 Mar 2011

  2. 2.

    Advanced Micro Devices (2010) AMD Family 10h Desktop Processor Power and Thermal Data Sheet. http://support.amd.com/us/Processor_TechDocs/43375.pdf. Accessed 2 Mar 2011

  3. 3.

    Advanced Micro Devices (2010) AMD PowerNow! Technology. http://www.amd.com/us/products/technologies/amd-powernow-technology/Pages/amd-powernow-technology.aspx. Accessed 2 Mar 2011

  4. 4.

    Advanced Micro Devices (2010) BIOS and Kernel Developer’s Guide (BKDG) for Family 10h Processors. http://support.amd.com/us/Processor_TechDocs/31116.pdf. Accessed 2 Mar 2011

  5. 5.

    Ali S, Maciejewski AA, Siegel HJ (2008) Perspectives on robust resource allocation for heterogeneous parallel systems. In: Handbook of parallel computing: models, algorithms, and applications. Chapman & Hall/CRC Press, Boca Raton, pp 41-1–41-30

    Google Scholar 

  6. 6.

    Ali S, Maciejewski AA, Siegel HJ, Kim JK (2004) Measuring the robustness of a resource allocation. IEEE Trans Parallel Distrib Syst 15(7):630–641

    Article  Google Scholar 

  7. 7.

    Ali S, Siegel HJ, Maheswaran M, Hensgen D (2000) Representing task and machine heterogeneities for heterogeneous computing systems. Tamkang J Sci Eng, Special 50th Anniversary Issue 3(3):195–207.

    Google Scholar 

  8. 8.

    Apodaca J, Young D, Briceño L, Smith J, Pasricha S, Maciejewski AA, Siegel HJ, Bahirat S, Khemka B, Ramirez A, Zou Y (2011) Stochastically robust static resource allocation for energy minimization with a makespan constraint in a heterogeneous computing environment. In: 9th ACS/IEEE international conference on computer systems and applications (AICCSA ’11)

    Google Scholar 

  9. 9.

    Aydin H, Melhem R, Mosse D, Mejia-Alvarez P (2001) Dynamic and aggressive scheduling techniques for power-aware real-time systems. In: 22nd IEEE real-time systems symposium (RTSS ’01), pp 95–105

    Google Scholar 

  10. 10.

    Barbosa J, Moreira B (2009) Dynamic job scheduling on heterogeneous clusters. In: 8th international symposium on parallel and distributed computing (ISPDC ’09), pp 3–10

    Google Scholar 

  11. 11.

    Bohrer P, Elnozahy EN, Keller T, Kistler M, Lefurgy C, McDowell C, Rajamony R (2002) The case for power management in web servers. In: Power aware computing. Kluwer Academic, Norwell, pp 261–289

    Google Scholar 

  12. 12.

    Briceño L, Siegel HJ, Maciejewski AA, Oltikar M, Brateman J, White J, Martin J, Knapp K (2011) Heuristics for robust resource allocation of satellite weather data processing on a heterogeneous parallel system. IEEE Trans Parallel Distrib Syst 22(11):1780–1787

    Article  Google Scholar 

  13. 13.

    Briceño LD, Khemka B, Siegel HJ, Maciejewski AA, Groer C, Koenig G, Okonski G, Poole S (2011) Time utility functions for modeling and evaluating resource allocations in a heterogeneous computing system. In: 20th heterogeneity in computing workshop (HCW ’11), pp 1–14

    Google Scholar 

  14. 14.

    CSU Information Science and Technology Center (2011) ISTeC Cray High Performance Computing (HPC) System. http://istec.colostate.edu/istec_cray. Accessed 15 June 2011

  15. 15.

    Intel Corporation (2010) Frequently asked questions for Intel SpeedStep Technology. http://www.intel.com/support/processors/sb/CS-028855.htm. Accessed 2 Mar 2011

  16. 16.

    Iosup A, Epema D (2010) Grid workloads. IEEE Internet Comput 15(2):19–26

    Article  Google Scholar 

  17. 17.

    Kim JK, Siegel HJ, Maciejewski AA, Eigenmann R (2008) Dynamic resource management in energy constrained heterogeneous computing systems using voltage scaling. IEEE Trans Parallel Distrib Syst 19(11):1445–1457

    Article  Google Scholar 

  18. 18.

    Kim KH, Buyya R, Kim J (2007) Power aware scheduling of bag-of-tasks applications with deadline constraints on dvs-enabled clusters. In: 7th IEEE/ACM international symposium on cluster computing and the grid (CCGrid ’05), pp 541–548

    Google Scholar 

  19. 19.

    Koomey JG (2007) Estimating total power consumption by servers in the US and the world. Tech rep, Lawrence Berkeley National Laboratory. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.87.5562&rep=rep1&type=pdf

  20. 20.

    Koomey JG, Belady C, Patterson M, Santos A, Lange KD (2009) Assessing trends over time in performance, costs, and energy use for servers. Tech rep, Lawrence Berkeley National Laboratory, Stanford University, Microsoft Corporation, and Intel Corporation. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.87.5562&rep=rep1&type=pdf. Accessed 2 Mar 2011

  21. 21.

    Leon-Garcia A (1989) Probability & random processes for electrical engineering. Addison-Wesley, Reading

    Google Scholar 

  22. 22.

    Li C, Bettati R, Zhao W (1998) Response time analysis for distributed real-time systems with bursty job arrivals. In: 1998 international conference on parallel processing (ICPP ’98), pp 432–440

    Google Scholar 

  23. 23.

    Li YA, Antonio JK, Siegel HJ, Tan M, Watson DW (1997) Determining the execution time distribution for a data parallel program in a heterogeneous computing environment. J Parallel Distrib Comput 44(1):35–52

    Article  Google Scholar 

  24. 24.

    Maheswaran M, Ali S, Siegel HJ, Hensgen D, Freund RF (1999) Dynamic mapping of a class of independent tasks onto heterogeneous computing systems. J Parallel Distrib Comput 59(2):107–121

    Article  Google Scholar 

  25. 25.

    Phillips CL, Parr JM, Riskin EA (2003) Signals, systems, and transforms. Pearson Education, Upper Saddle River

    Google Scholar 

  26. 26.

    Smith J, Apodaca J, Maciejewski AA, Siegel HJ (2010) Batch mode stochastic-based robust dynamic resource allocation in a heterogeneous computing system. In: 2010 international conference on parallel and distributed processing techniques and applications (PDPTA ’10), pp 263–269

    Google Scholar 

  27. 27.

    Smith J, Chong EKP, Maciejewski AA, Siegel HJ (2009) Stochastic-based robust dynamic resource allocation in a heterogeneous computing system. In: 38th international conference on parallel processing (ICPP ’09)

    Google Scholar 

  28. 28.

    Smith J, Siegel HJ, Maciejewski AA (2009) Robust resource allocation in heterogeneous parallel and distributed computing systems. In: Wah BW (ed) Wiley encyclopedia of computer science and engineering, vol 4. Wiley, Hoboken, pp 2461–2470

    Google Scholar 

  29. 29.

    Wasserman L (2005) All of statistics: a concise course in statistical inference. Springer, New York

    Google Scholar 

  30. 30.

    Xian C, Lu YH, Li Z (2008) Dynamic voltage scaling for multitasking real-time systems with uncertain execution time. IEEE Trans Comput-Aided Des Integr Circuits Syst 27(8):1467–1478

    Article  Google Scholar 

  31. 31.

    Young D, Apodaca J, Briceño L, Smith J, Pasricha S, Maciejewski AA, Siegel HJ, Bahirat S, Khemka B, Ramirez A, Zou Y (2011) Energy-constrained dynamic resource allocation in a heterogeneous computing environment. In: 4th international workshop on parallel programming models and systems software for high-end computing (P2S2 ’11)

    Google Scholar 

  32. 32.

    Yu H, Veeravalli B, Ha Y (2008) Dynamic scheduling of imprecise-computation tasks in maximizing QoS under energy constraints for embedded systems. In: 2008 Asia and South Pacific design automation conference (ASPDAC ’08), pp 452–455

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to B. Dalton Young.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Young, B.D., Apodaca, J., Briceño, L.D. et al. Deadline and energy constrained dynamic resource allocation in a heterogeneous computing environment. J Supercomput 63, 326–347 (2013). https://doi.org/10.1007/s11227-012-0740-7

Download citation

Keywords

  • Dynamic resource allocation
  • Heterogeneous computing
  • Power aware computing