Advertisement

Improving Cloud Simulation Using the Monte-Carlo Method

  • Luke BertotEmail author
  • Stéphane Genaud
  • Julien Gossa
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11014)

Abstract

In the cloud computing model, cloud providers invoice clients for resource consumption. Hence, tools helping the client to budget the cost of running his application are of pre-eminent importance. However, the opaque and multi-tenant nature of clouds make task runtimes variable and hard to predict, and hamper the creation of reliable simulation tools. In this paper, we propose an improved simulation framework that takes into account this variability using the Monte-Carlo method.

We consider the execution of batch jobs on an actual platform, scheduled using typical heuristics based on the user estimates of task runtimes. We model the observed variability through simple random variables to use as inputs to the Monte-Carlo simulation. Based on this stochastic process, predictions are expressed as interval-based makespan and cost. We show that, our method can capture over 90% of the empirical observations of makespan while keeping the capture interval size below 5% of the average makespan.

References

  1. 1.
    Cai, Z., Li, Q., Li, X.: ElasticSim: a toolkit for simulating workflows with cloud resource runtime auto-scaling and stochastic task execution times. J. Grid Comput. 15(2), 257–272 (2017).  https://doi.org/10.1007/s10723-016-9390-yCrossRefGoogle Scholar
  2. 2.
    Calheiros, R.N., Ranjan, R., Beloglazov, A., De Rose, C.A., Buyya, R.: CloudSim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms. Softw.: Pract. Exp. 41(1), 23–50 (2011)Google Scholar
  3. 3.
    Canon, L., Jeannot, E.: Evaluation and optimization of the robustness of DAG schedules in heterogeneous environments. IEEE Trans. Parallel Distrib. Syst. 21(4), 532–546 (2010).  https://doi.org/10.1109/TPDS.2009.84CrossRefGoogle Scholar
  4. 4.
    Casanova, H., Giersch, A., Legrand, A., Quinson, M., Suter, F.: Versatile, scalable, and accurate simulation of distributed applications and platforms. J. Parallel Distrib. Comput. 74(10), 2899–2917 (2014).  https://doi.org/10.1016/j.jpdc.2014.06.008CrossRefGoogle Scholar
  5. 5.
    Geer, L.Y., et al.: Open mass spectrometry search algorithm. J. Proteome Res. 3(5), 958–964 (2004)CrossRefGoogle Scholar
  6. 6.
    Jacob, J.C., et al.: Montage: a grid portal and software toolkit for science-grade astronomical image mosaicking. Int. J. Comput. Sci. Eng. 4(2), 73–87 (2009)Google Scholar
  7. 7.
    Kim, I.K., Wang, W., Humphrey, M.: PICS: a public IaaS cloud simulator. In: Pu, C., Mohindra, A. (eds.) 8th IEEE International Conference on Cloud Computing, CLOUD 2015, New York City, NY, USA, 27 June–2 July 2015, pp. 211–220. IEEE Computer Society (2015).  https://doi.org/10.1109/CLOUD.2015.37
  8. 8.
    Kliazovich, D., Bouvry, P., Khan, S.U.: GreenCloud: a packet-level simulator of energy-aware cloud computing data centers. J. Supercomput. 62(3), 1263–1283 (2012)CrossRefGoogle Scholar
  9. 9.
    Leitner, P., Cito, J.: Patterns in the chaos - a study of performance variation and predictability in public IaaS clouds. ACM Trans. Internet Technol. 16(3), 15:1–15:23 (2016).  https://doi.org/10.1145/2885497CrossRefGoogle Scholar
  10. 10.
    Li, Y.A., Antonio, J.K.: Estimating the execution time distribution for a task graph in a heterogeneous computing system. In: 6th Heterogeneous Computing Workshop, HCW 1997, Geneva, Switzerland, 1 April 1997, pp. 172–184. IEEE Computer Society (1997).  https://doi.org/10.1109/HCW.1997.581419
  11. 11.
    Lim, S., Sharma, B., Nam, G., Kim, E., Das, C.R.: MDCSim: a multi-tier data center simulation, platform. In: Proceedings of the 2009 IEEE International Conference on Cluster Computing, 31 August–4 September 2009, New Orleans, Louisiana, USA, pp. 1–9. IEEE Computer Society (2009).  https://doi.org/10.1109/CLUSTR.2009.5289159
  12. 12.
    Ludwig, A., Möhring, R.H., Stork, F.: A computational study on bounding the makespan distribution in stochastic project networks. Annals OR 102(1–4), 49–64 (2001).  https://doi.org/10.1023/A:1010945830113MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Mehrotra, P., et al.: Performance evaluation of Amazon elastic compute cloud for NASA high-performance computing applications. Concurr. Comput.: Pract. Exp. 28(4), 1041–1055 (2016).  https://doi.org/10.1002/cpe.3029CrossRefGoogle Scholar
  14. 14.
    Michon, E., Gossa, J., Genaud, S., Unbekandt, L., Kherbache, V.: Schlouder: a broker for IaaS clouds. Future Gener. Comput. Syst. 69, 11–23 (2017).  https://doi.org/10.1016/j.future.2016.09.010CrossRefGoogle Scholar
  15. 15.
    Nuñez, A., Vázquez-Poletti, J.L., Caminero, A.C., Castañé, G.G., Carretero, J., Llorente, I.M.: iCanCloud: a flexible and scalable cloud infrastructure simulator. J. Grid Comput. 10(1), 185–209 (2012).  https://doi.org/10.1007/s10723-012-9208-5CrossRefGoogle Scholar
  16. 16.
    Pucher, A., Gul, E., Wolski, R., Krintz, C.: Using trustworthy simulation to engineer cloud schedulers. In: 2015 IEEE International Conference on Cloud Engineering, IC2E 2015, Tempe, AZ, USA, 9–13 March 2015, pp. 256–265 (2015).  https://doi.org/10.1109/IC2E.2015.14
  17. 17.
    van Slyke, R.M.: Monte carlo methods and the PERT problem. Oper. Res. 11(5), 839–860 (1963). http://www.jstor.org/stable/167918CrossRefGoogle Scholar
  18. 18.
    Stanisic, L., Thibault, S., Legrand, A., Videau, B., Méhaut, J.: Faithful performance prediction of a dynamic task-based runtime system for heterogeneous multi-core architectures. Concurr. Comput.: Pract. Exp. 27(16), 4075–4090 (2015).  https://doi.org/10.1002/cpe.3555CrossRefGoogle Scholar
  19. 19.
    Tang, X., Li, K., Liao, G., Fang, K., Wu, F.: A stochastic scheduling algorithm for precedence constrained tasks on grid. Future Gener. Comput. Syst. 27(8), 1083–1091 (2011).  https://doi.org/10.1016/j.future.2011.04.007CrossRefGoogle Scholar
  20. 20.
    Velho, P., Schnorr, L.M., Casanova, H., Legrand, A.: On the validity of flow-level tcp network models for grid and cloud simulations. ACM Trans. Model. Comput. Simul. 23(4), 23:1–23:26 (2013).  https://doi.org/10.1145/2517448MathSciNetCrossRefzbMATHGoogle Scholar
  21. 21.
    Zheng, W., Sakellariou, R.: Stochastic DAG scheduling using a monte carlo approach. J. Parallel Distrib. Comput. 73(12), 1673–1689 (2013).  https://doi.org/10.1016/j.jpdc.2013.07.019CrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Icube-ICPS — UMR 7357, Université de Strasbourg, CNRS Pôle APIIllkirch-GraffenstadenFrance

Personalised recommendations