Advertisement

Workflow Scheduling in Amazon EC2

  • Juan J. Durillo
  • Radu Prodan
  • Weicheng Huang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8374)

Abstract

Workflow scheduling has been traditionally targeted to map the execution of set of tasks onto a set of resources for makespan minimization. With the increasing popularity of Cloud computing systems, the financial cost entailed for executing these tasks plays also an important role. Existing works have however combined both, makespan and cost, on a single function and no analysis of the tradeoff between both criteria has been produced. In addition, no work in the context a real commercial cloud system exists. This paper includes a comparison of two real multi-objective workflow scheduling, MOHEFT and SPEA2*, in the context of Amazon EC2. The carried experiments show that MOHEFT outperforms SPEA2*, and that the analysis of the tradeoff solutions can help in selecting good scheduling solutions.

Keywords

Cloud Computing Economic Cost Pareto Front Cloud Computing System Utility Grid 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Alexandru, I., Ostermann, S., Yigitbasi, M., Prodan, R., Fahringer, T., Epema, D.: Performance analysis of cloud computing services for many-tasks scientific computing. IEEE Transactions on Parallel and Distr. Systems 1–16 (2010)Google Scholar
  2. 2.
    Assayad, I., Girault, A., Kalla, H.: A bi-criteria scheduling heuristics for distributed embedded systems under reliability and real-time constraints. In: Intern. Conference on Dependable Systems and Networks, DSN 2004. IEEE, Firenze (2003)Google Scholar
  3. 3.
    Blaha, P., Schwarz, K., Madsen, G., Kvasnicka, D., Luitz, J.: Wien2k: An augmented plane wave plus local orbitals program for calculating crystal properties. Tech. rep., Institute of Physical and Theoretical Chemistry, TU Vienna (2001)Google Scholar
  4. 4.
    Canon, L.C.: Emmanuel: Mo-greedy: an extended beam-search approach for solving a multi-criteria scheduling problem on heterogeneous machines. Intern. Heterogeneity in Computing (2011)Google Scholar
  5. 5.
    Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast elitist multi-objective genetic algorithm: Nsga-ii. IEEE Transactions on Evol. Comp. 6, 182–197 (2000)CrossRefGoogle Scholar
  6. 6.
    Durillo, J., Fard, H., Prodan, R.: Moheft: A multi-objective lilst-based method for workflow scheduling. In: 4th IEEE Intern. Conference on Cloud Computing Technology and Science (2012)Google Scholar
  7. 7.
    Garg, R., Singh, A.K.: Reference point based multi-objective optimization to workflow grid scheduling. Int. J. Appl. Evol. Comput. 3(1), 80–99 (2012)CrossRefGoogle Scholar
  8. 8.
    Garg, S.K., Buyya, R., Siegel, H.J.: Scheduling parallel applications on utility grids: time and cost trade-off management. In: Proceedings of the Thirty-Second Australasian Conference on Computer Science, ACSC 2009, vol. 91, pp. 151–160. Australian Computer Society, Inc., Darlinghurst (2009)Google Scholar
  9. 9.
    Hakem, M., Butelle, F.: Reliability and scheduling on systems subject to failures. In: Proceedings of the 2007 Intern. Conference on Parallel Processing, ICPP 2007. IEEE Computer Society, Washington, DC (2007)Google Scholar
  10. 10.
    Hu, S.Y., Chen, J.F., Chen, T.H.: VON: a scalable peer-to-peer network for virtual environments. IEEE Network 20(4), 22–31 (2006)CrossRefGoogle Scholar
  11. 11.
    Knowles, J., Thiele, L., Zitzler, E.: A Tutorial on the Performance Assessment of Stochastic Multiobjective Optimizers. Tech. Rep. 214, Computer Engineering and Networks Laboratory (TIK), ETH Zurich (2006)Google Scholar
  12. 12.
    Mezmaz, M., Melab, N., Kessaci, Y., Lee, Y., Albi, E.G.T., Zomaya, A.Y., Tuyttens, D.: A parallel bi-objective hybrid metaheuristic for energy-aware s cheduling for cloud computing systems. Journal of Parallel and Distr. Computing (71), 1497–1508 (2011)Google Scholar
  13. 13.
    Plachetka, T.: POVRAY – Persistence of Vision Parallel Raytracer. In: Proceedings of Computer Graphics Intern. 1998, pp. 123–129 (1998)Google Scholar
  14. 14.
    Ricci, L., Carlini, E.: Distributed virtual environments: From client server to cloud and p2p architectures. In: Smari, W., Zeljkovic, V. (eds.) HPCS, pp. 8–17. IEEE (2012)Google Scholar
  15. 15.
    Sakellariou, R., Zhao, H., Tsiakkouri, E., Dikaiakos, M.D.: Scheduling workflows with budget constraints. In: Gorlatch, S., Danelutto, M. (eds.) Integrated Research in Grid Computing. CoreGrid series. Springer (2007)Google Scholar
  16. 16.
    Topcuoglu, H., Hariri, S., Wu, M.Y.: Performance-effective and low-complexity task scheduling for heterogeneous computing. IEEE Transactions on Parallel and Distr. Systems 13(3), 260–274 (2002)CrossRefGoogle Scholar
  17. 17.
    Yu, J., Kirley, M., Buyya, R.: Multi-objective planning for workflow execution on grids. In: Proceedings of the 8th IEEE/ACM Intern. Conference on Grid Computing, GRID 2007, pp. 10–17. IEEE Computer Society, Washington, DC (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Juan J. Durillo
    • 1
  • Radu Prodan
    • 1
  • Weicheng Huang
    • 2
  1. 1.Institut fur InformatikUniversity of InnsbruckAustria
  2. 2.National Center of High-performance ComputingNational Applied Research LaboratoriesTaiwan

Personalised recommendations