Advertisement

Improving QoS for Non-trivial Applications in Grid Computing

  • Omar Dakkak
  • Shahrudin Awang Nor
  • Suki Arif
  • Yousef FazeaEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1073)

Abstract

Classical scheduling mechanisms don’t satisfy the requirements for the end user, especially if the number of the jobs has increased massively in grid computing environment. To meet the expectations for non-trivial applications, the efficiency of the system has to be improved and the resources have to be ultimately utilized. Thus, backfilling technique becomes highly required due to its efficiency in exploiting the resources by filling the gaps that was created in the scheduler by short jobs. There are two well-known mechanisms, which are Extensible Argonne Scheduling System (EASY) and Conservative Backfilling (CONS). EASY is very aggressive and well uses the resources, however it causes a delay for the jobs ahead in the queue, while CONS solve this issue at the expense of system efficiency. In addition, and to further improve the scheduling quality, schedule-based approach has to be implemented. This approach provides information for the incoming job parameters and the resources capabilities; thus, the mechanism schedules the jobs in advance. This approach has shown a significant improvement compared with queue-based approach. In this paper, a new mechanism is proposed, namely Swift Gap. This mechanism implements schedule-based approach and applies multi-level scheduling method. In the first stage, the mechanism finds the right place for the newly arrival job, while in the second stage it manipulates the jobs’ positions for further optimization. Moreover, this paper introduces the completion time scheme. This scheme minimizes both start time and processing time. The evaluation has shown the significant impact of Swift Gap alongside the completion time rule compared to CONS and EASY.

Keywords

Scheduling Grid Swift Gap Completion time scheme 

References

  1. 1.
    Klusacek, D., Rudová, H.: Improving QoS in computational Grids through schedule-based approach. In: Scheduling and Planning Applications Workshop at the Eighteenth International Conference on Automated Planning and Scheduling (ICAPS 2008), Sydney, Australia (2008)Google Scholar
  2. 2.
    Azmi, Z.R.M., et al.: Scheduling grid jobs using priority rule algorithms and gap filling techniques. Int. J. Adv. Sci. Technol. 37, 61–76 (2011)Google Scholar
  3. 3.
    Sajat, M.S., et al.: A critical review on energy-efficient medium access control for wireless and mobile sensor networks. J. Telecommun. Electron. Comput. Eng. (JTEC) 8(10), 89–94 (2016)Google Scholar
  4. 4.
    Fareed, A., et al.: Channel impulse response equalization based on genetic algorithm in mode division multiplexing. J. Telecommun. Electron. Comput. Eng. (JTEC) 10(2–4), 149–154 (2018)Google Scholar
  5. 5.
    Fazea, Y.: Numerical simulation of helical structure mode-division multiplexing with nonconcentric ring vortices. Opt. Commun. 437, 303–311 (2019)CrossRefGoogle Scholar
  6. 6.
    Fazea, Y.: Mode division multiplexing and dense WDM-PON for Fiber-to-the-Home. Optik 183, 994–998 (2019)CrossRefGoogle Scholar
  7. 7.
    Fazea, Y., Alobaedy, M.M., Ibraheem, Z.T.: Performance of a direct-detection spot mode division multiplexing in multimode fiber. J. Opt. Commun. 40, 161–166 (2019)CrossRefGoogle Scholar
  8. 8.
    Fazea, Y., Amphawan, A.: 5 × 5 25 Gbit/s WDM-MDM. J. Opt. Commun. 36(4), 327–333 (2015)CrossRefGoogle Scholar
  9. 9.
    Lee, C.B.: On the user-scheduler relationship in high-performance computing (2009)Google Scholar
  10. 10.
    Dakkak, O., Nor, S.A., Arif, S.: Analyzing the QoS criteria from end user’s perspective in computational grid environment. In: TENCON 2017–2017 IEEE Region 10 Conference. IEEE (2017)Google Scholar
  11. 11.
    Klusacek, D.: Dealing with uncertainties in grids through the event-based scheduling approach. In: Fourth Doctoral Workshop on Mathematical and Engineering Methods in Computer Science (MEMICS 2008) (2008)Google Scholar
  12. 12.
    Zotkin, D., Keleher, P.J.: Job-length estimation and performance in backfilling schedulers. In: 1999 Proceedings of the Eighth International Symposium High Performance Distributed Computing. IEEE (1999)Google Scholar
  13. 13.
    Mu’alem, A.W., Feitelson, D.G.: Utilization, predictability, workloads, and user runtime estimates in scheduling the IBM SP2 with backfilling. IEEE Trans. Parallel Distrib. Syst. 12(6), 529–543 (2001)CrossRefGoogle Scholar
  14. 14.
    Lifka, D.A.: The ANL/IBM SP scheduling system. In: Workshop on Job Scheduling Strategies for Parallel Processing. Springer (1995)Google Scholar
  15. 15.
    Jackson, D., Snell, Q., Clement, M.: Core algorithms of the Maui scheduler. In: Workshop on Job Scheduling Strategies for Parallel Processing. Springer (2001)Google Scholar
  16. 16.
    Chlumsky, V., Klusácek, D., Ruda, M.: The extension of torque scheduler allowing the use of planning and optimization in grids. Comput. Sci. 13(2), 5–19 (2012)CrossRefGoogle Scholar
  17. 17.
    Glover, F., Laguna, M.: Tabu Search*. Springer (2013)Google Scholar
  18. 18.
    Dakkak, O., Nor, S.A., Arif, S.: Proposed algorithm for scheduling in computational grid using backfilling and optimization techniques. J. Telecommun. Electron. Comput. Eng. (JTEC) 8(10), 133–138 (2016)Google Scholar
  19. 19.
    Rizal, Z., et al.: Combinatorial Rules Approach to Improve Priority Rules Scheduler in Grid Computing Environment (2012)Google Scholar
  20. 20.
    Fibich, P., Matyska, L., Rudová, H.: Model of grid scheduling problem. In: Exploring Planning and Scheduling for Web Services, Grid and Autonomic Computing, pp. 17–24 (2005)Google Scholar
  21. 21.
    Xhafa, F., Abraham, A.: Computational models and heuristic methods for Grid scheduling problems. Future Gener. Comput. Syst. 26(4), 608–621 (2010)CrossRefGoogle Scholar
  22. 22.
    Gritsenko, A.V., et al.: Decomposition analysis and machine learning in a workflow-forecast approach to the task scheduling problem for high-loaded distributed systems. Mod. Appl. Sci. 9(5), 38 (2015)CrossRefGoogle Scholar
  23. 23.
    Feitelson, D.G.: Metrics for parallel job scheduling and their convergence. In: Workshop on Job Scheduling Strategies for Parallel Processing. Springer (2001)Google Scholar
  24. 24.
    Dakkak, O., et al.: From grids to clouds: recap on challenges and solutions. In: AIP Conference Proceedings. AIP Publishing (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Omar Dakkak
    • 1
  • Shahrudin Awang Nor
    • 2
  • Suki Arif
    • 2
  • Yousef Fazea
    • 2
    Email author
  1. 1.Computer Engineering Department, Faculty of EngineeringKarabük ÜniversitesiKarabükTurkey
  2. 2.InterNetWorks Research Laboratory, School of ComputingUniversiti Utara MalaysiaSintokMalaysia

Personalised recommendations