Skip to main content

Extending goal-oriented parallel computer job scheduling policies to heterogeneous systems

Abstract

Several existing parallel computer systems partition their system resources or consist of systems from different geographical locations. This work is focusing on extending the original goal-oriented parallel computer job scheduling policies to cover such systems. The goal-oriented parallel computer job scheduling policies are proposed recently to handle conflicting objectives by utilizing a combinatorial search technique to find the most compromise schedule within a time limit. In this paper, some modifications to the original goal-oriented parallel computer job scheduling policy design are proposed and evaluated. The proposed policy is evaluated against basic priority backfilling techniques widely used in the field. Both homogeneous and heterogeneous parallel computer systems in terms of the computing power are evaluated. And, the design decision on the partition selection heuristic is also evaluated in this study. The experimental results show that the proposed policy produces good scheduling performances even when inaccurate runtime information is used.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

References

  1. 1.

    Chiang S-H, Vasupongayya S (2008) Design and potential performance of goal-oriented job scheduling policies for parallel computer workloads. IEEE Trans Parallel Distrib Syst 19(12):1642–1656

    Article  Google Scholar 

  2. 2.

    Lifka D (1995) The ANL/IBM SP scheduling system. In: Proceedings of the workshop on job scheduling strategies for parallel processing. Springer, London, pp 295–303

    Chapter  Google Scholar 

  3. 3.

    Vasupongayya S, Chiang S-H, Massey B (2005) Search-based job scheduling for parallel computer workloads. In: Proceeding of the IEEE cluster, Boston, MA

    Google Scholar 

  4. 4.

    Vasupongayya S (2009) Achieving fair share objectives via goal-oriented parallel computer job scheduling policies. World Acad Sci, Eng Technol 60:747–753

    Google Scholar 

  5. 5.

    Walsh T (1997) Depth-bounded discrepancy search. In: Proceedings of the fifteenth international joint conference on artificial intelligence. Morgan Kaufmann, San Mateo, pp 1388–1393

    Google Scholar 

  6. 6.

    Prasitsupparote A, Vasupongayya S (2010) Impact of multi-partition systems on goal-oriented parallel computer job scheduling policies. In: Proc of JCSSE2010, Bangkok, Thailand

    Google Scholar 

  7. 7.

    OpenPBS. Available at: http://doesciencegrid.org/public/pbs/ [6 January 2013]

  8. 8.

    Platform LSF. Available at: http://www-03.ibm.com/systems/technicalcomputing/platformcomputing/products/lsf/ [6 January 2013]

  9. 9.

    Park K, Kang C, Kim S (2012) Hybrid job scheduling mechanism using a backfill-based multi-queue strategy in distributed grid computing. Int J Comput Sci Netw Secur 12(9):39–48

    Google Scholar 

  10. 10.

    Jackson D, Snell Q, Clement M (2001) Core algorithms of the MAUI scheduler. In: Proceeding of the workshop on job scheduling strategies for parallel processing. Springer, London, pp 87–102

    Chapter  Google Scholar 

  11. 11.

    Kannan S, Roberts M, Mayes P, Brelsford D, Skovira J (2001) Workload management with LoadLeveler. Technical report, IBM Redbook

  12. 12.

    Liu X, Chen B, Qiu X, Cai Y, Huang K (2012) Scheduling parallel jobs using migration and consolidation in the cloud. Math Probl Eng 2012:695757. doi:10.1155/2012/695757

    Google Scholar 

  13. 13.

    Moab. Available at: https://computing.llnl.gov/tutorials/moab/ [6 January 2013]

  14. 14.

    Krishnamurthy D, Alemzadeh M, Moussavi M (2011) Towards automated HPC scheduler configuration tuning. Concurr. Comput., Pract. Exp. 23(15):1723–1748

    Article  Google Scholar 

  15. 15.

    Vasupongayya S, Chiang S-H (2006) Multi-objective models for scheduling jobs on parallel computer systems. In: The 2006 IEEE cluster, Barcelona, Spain, Sep 2006

    Google Scholar 

  16. 16.

    Mualem A, Feitelson D (2001) Utilization, predictability, workloads, and user runtime estimates in scheduling the IBM SP2 with backfilling. IEEE Trans Parallel Distrib Syst 12(6):529–543

    Article  Google Scholar 

  17. 17.

    Tsafrir D, Etsion Y, Feitelson D (2007) Backfilling using system-generated predictions rather than user runtime estimates. IEEE Trans Parallel Distrib Syst 18(6):789–803

    Article  Google Scholar 

  18. 18.

    Chiang S-H, Arpaci-Dusseau A, Vernon M (2002) The impact of more accurate request runtimes on production job scheduling performance. In: Lecture notes in computer science, vol 2537, pp 103–127

    Google Scholar 

  19. 19.

    Delavar A, Aryan Y (2012) A goal-oriented workflow scheduling in heterogeneous distributed systems. Int J Comput Appl 52(8):27–33

    Google Scholar 

  20. 20.

    Chung L, Hill T, Legunsen O, Sun Z, Dsouza A, Supakkul S (2013) A goal-oriented simulation approach for obtaining good private cloud-based system architectures. J Syst Softw. Available at: http://www.sciencedirect.com/science/article/pii/S0164121212002865 [5 January 2013]

  21. 21.

    Mlynski M, Rumik P (2011) Improving efficiency of data-intensive applications in goal-oriented adaptive computer systems. Theor Appl Inf 23(1):55–72

    Google Scholar 

  22. 22.

    Hauck M, Happe J, Reussner R (2011) Towards performance prediction for cloud computing environments based on goal-oriented measurements. In: Proceedings of the 1st international conference on cloud computing and services science, pp 616–622

    Google Scholar 

  23. 23.

    Kumar D, Shae Z, Jamjoom H (2012) Scheduling batch and heterogeneous jobs with runtime elasticity in a parallel processing environment. In: Proceeding of the 26th IEEE international parallel and distributed processing symposium workshops & PhD forum, pp 65–78

    Google Scholar 

  24. 24.

    Wu J, Xu X, Zhang P, Liu C (2011) A novel multi-agent reinforcement learning approach for job scheduling in grid computing. Future Gener Comput Syst 27(5):430–439

    Article  Google Scholar 

  25. 25.

    Shmueli E, Feitelson D (2005) Backfilling with lookahead to optimize the packing of parallel jobs. J Parallel Distrib Comput 65(9):1090–1107

    MATH  Article  Google Scholar 

  26. 26.

    Talby D, Feitelson D (2005) Improving and stabilizing parallel computer performance using adaptive backfilling. In: Proceedings of the 19th IEEE international parallel and distributed processing symposium

    Google Scholar 

  27. 27.

    Guim F, Corbalan J, Labarta J (2007) Job self-scheduling policy for HPC infrastructures. In: Proceedings of the 13th international conference on job scheduling strategies for parallel processing. Springer, Berlin, pp 51–75

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to S. Vasupongayya.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Vasupongayya, S., Prasitsupparote, A. Extending goal-oriented parallel computer job scheduling policies to heterogeneous systems. J Supercomput 65, 1223–1242 (2013). https://doi.org/10.1007/s11227-013-0879-x

Download citation

Keywords

  • Backfill
  • Discrepancy-based search
  • Goal-oriented
  • Multi-partition
  • Scheduling