Windows Azure: Resource Organization Performance Analysis

  • Marjan Gusev
  • Sasko Ristov
  • Bojana Koteska
  • Goran Velkoski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8745)


Cloud customers can scale the resources according to their needs in order to avoid application bottleneck. The scaling can be done in two ways, either by increasing the existing virtual machine instance with additional resources, or by adding an additional virtual machine instance with the same resources. Although it is expected that the costs rise proportionally to scaling, we are interested in finding out which organization offers scaling with better performance. The goal of this paper is to determine the resource organization that produces better performance for the same cost, and help the customers decide if it is better to host a web application on a more ”small” instances or less ”large” instances. The first hypothesis states that better performance is obtained by using more and smaller instances. The second hypothesis is that the obtained speedup while scaling the resources is smaller than the scaling factor. The results from the provided experiments have not proven any of the hypotheses, meaning that using less, but larger instances results with better performance and that the user gets more performances than expected by scaling the resources.


Cloud Computing Microsoft Azure Performance SaaS 


  1. 1.
    Agarwal, D., Prasad, S.K.: AzureBench: Benchmarking the storage services of the Azure cloud platform. In: Proc. of the IEEE 26th Int. Parallel and Distributed Processing Symp. Workshops & PhD Forum, IPDPSW 2012, pp. 1048–1057 (2012)Google Scholar
  2. 2.
    Brebner, P., Liu, A.: Performance and cost assessment of cloud services. In: Maximilien, E.M., Rossi, G., Yuan, S.-T., Ludwig, H., Fantinato, M. (eds.) ICSOC 2010. LNCS, vol. 6568, pp. 39–50. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  3. 3.
    Gao, J., Pattabhiraman, P., Bai, X., Tsai, W.: SaaS performance and scalability evaluation in clouds. In: 2011 IEEE 6th International Symposium on Service Oriented System Engineering (SOSE), pp. 61–71 (2011)Google Scholar
  4. 4.
    Gaster, B.: PhluffyFotos on Windows Azure (October 2012),
  5. 5.
    Gusev, M., Ristov, S.: Superlinear speedup in Windows Azure cloud. In: 2012 IEEE 1st International Conference on Cloud Networking (CLOUDNET), Paris, France, pp. 173–175 (2012)Google Scholar
  6. 6.
    Gusev, M., Ristov, S.: A superlinear speedup region for matrix multiplication. Concurrency and Computation: Practice and Experience 26(11), 1847–1868 (2013), CrossRefGoogle Scholar
  7. 7.
    Gusev, M., Ristov, S.: Resource scaling performance for cache intensive algorithms in Windows Azure. In: Zavoral, F., Jung, J.J., Badica, C. (eds.) IDC 2013. SCI, vol. 511, pp. 77–86. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  8. 8.
    Gusev, M., Ristov, S., Velkoski, G., Simjanoska, M.: Optimal resource allocation to host web services in cloud. In: Proceedings of the 2013 IEEE 6th International Conference on Cloud Computing, CLOUD 2013, CA, USA, pp. 948–949 (June 2013)Google Scholar
  9. 9.
    Gusev, P., Ristov, S., Gusev, M.: Performance analysis of SaaS ticket management systems. In: 2014 Federated Conference on Computer Science and Information Systems (FedCSIS) (SCoDiS-LaSCoG’14 Workshop) (in press, September 2014)Google Scholar
  10. 10.
    Gustafson, J.L.: Reevaluating Amdahl’s law. Communication of ACM 31(5), 532–533 (1988)CrossRefGoogle Scholar
  11. 11.
    Hill, Z., Li, J., Mao, M., Ruiz-Alvarez, A., Humphrey, M.: Early observations on the performance of Windows Azure. In: Proc. of the 19th ACM International Symposium on High Performance Distributed Computing, HPDC 2010, pp. 367–376 (2010)Google Scholar
  12. 12.
    Kondo, D., Javadi, B., Malecot, P., Cappello, F., Anderson, D.: Cost-benefit analysis of cloud computing versus desktop grids. In: IEEE International Symposium on Parallel Distributed Processing, IPDPS 2009, pp. 1–12 (2009)Google Scholar
  13. 13.
    Lu, W., Jackson, J., Ekanayake, J., Barga, R.S., Araujo, N.: Performing large science experiments on Azure: Pitfalls and solutions. In: CloudCom 2010, pp. 209–217 (2010)Google Scholar
  14. 14.
    Mao, M., Li, J., Humphrey, M.: Cloud auto-scaling with deadline and budget constraints. In: 2010 11th IEEE/ACM International Conference on Grid Computing (GRID), pp. 41–48 (2010)Google Scholar
  15. 15.
    Microsoft: Picture gallery service (April 2008),
  16. 16.
    Ostermann, S., Iosup, A., Yigitbasi, N., Prodan, R., Fahringer, T., Epema, D.: A performance analysis of EC2 cloud computing services for scientific computing. In: Avresky, D.R., Diaz, M., Bode, A., Ciciani, B., Dekel, E. (eds.) Cloud Computing. LNICST, vol. 34, pp. 115–131. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  17. 17.
    Tudoran, R., Costan, A., Antoniu, G., Bougé, L.: A performance evaluation of Azure and Nimbus clouds for scientific applications. In: Proc. of the 2nd Int. Workshop on Cloud Computing Platforms, CloudCP 2012, pp. 4:1–4:6. ACM (2012)Google Scholar
  18. 18.
    Zhang, L., Ma, X., Lu, J., Xie, T., Tillmann, N., de Halleux, P.: Environmental modeling for automated cloud application testing. IEEE Software 29(2), 30–35 (2012)CrossRefGoogle Scholar

Copyright information

© International Federation for Information Processing 2014

Authors and Affiliations

  • Marjan Gusev
    • 1
  • Sasko Ristov
    • 1
  • Bojana Koteska
    • 1
  • Goran Velkoski
    • 2
  1. 1.Faculty of Computer Science and EngineeringSs. Cyril and MethodiusSkopjeMacedonia
  2. 2.Innovation LTDSkopjeMacedonia

Personalised recommendations