A Strategy for Performance Evaluation and Modeling of Cloud Computing Services
Keywords:Performance evaluation, Cloud Computing, Containers, Virtual machines, Performance model
On-demand services and reduced costs made cloud computing a popular mechanism to provide scalable resources according to the user’s expectations. This paradigm is an important role in business and academic organizations, supporting applications and services deployed based on virtual machines and containers, two different technologies for virtualization. Cloud environments can support workloads generated by several numbers of users, that request the cloud environment to execute transactions and its performance should be evaluated and estimated in order to achieve clients satisfactions when cloud services are offered. This work proposes a performance evaluation strategy composed of a performance model and a methodology for evaluating the performance of services configured in virtual machines and containers in cloud infrastructures. The performance model for the evaluation of virtual machines and containers in cloud infrastructures is based on stochastic Petri nets. A case study in a real public cloud is presented to illustrate the feasibility of the performance evaluation strategy. The case study experiments were performed with virtual machines and containers supporting workloads related to social networks transactions.
ERL, T.; MAHMOOD, Z.; PUTTINI, R. Cloud Computing. Concepts, Techonology and Architecture. 1. ed. New Jersey, USA: Prentice Hall Press, 2013. v. 1. (The Prentice Hall Service Technology Series from Thomas Erl, v. 1).
NIST - National Institute of Standards and Technology. The NIST Definition of Cloud Computing. Online, https://csrc.nist.gov/publications/detail/sp/800-145/final.
MARINESCU, D. C. Cloud Computing: Theory and Practice. 1. ed. London, UK: Elsevier, 2017. v. 1.
JAIN, R. Art of Computer Systems Performance Analysis Techniques For Experimental Design Measurements Simulation And Modeling. 1. ed. Hoboken, USA: John Wiley & Sons, 1991. v. 1.
KOZHIRBAYEVA, Z.; SINNOTT, R. O. A performance comparison of container-based technologies for the cloud. Future. Gener. Comput. Syst., v. 68, n. 1, p. 175–182.
ARMBRUST, M. et al. Above the clouds: A Berkeley view of cloud computing. Berkelet, USA, 2010.
PAHL, C. et al. Cloud container technologies: A state-of-the-art review. IEEE Trans. Cloud Comput., v. 1, n. 1, p. 1.
ALKHANAK, R. et al. Cost-aware challenges for workflow scheduling approaches in cloud computing environments: Taxonomy and opportunities. Future Gener. Comput. Syst., v. 50, n. 1, p. 3–21, 2015.
SHIRINBAB, S.; LUNDBERG, L.; CASALICCHIO, E. Performance evaluation of container and virtual machine running cassandra workload. In: 3rd International Conference of Cloud Computing Technologies and Applications. Rabat, Morocco: IEEE, 2017. (CloudTech, v. 3), p. 1–8.
SEKAR, V. B. et al. AWS EC2 vs. Joyent’s Triton: A Comparison of Docker Container-hosting Platforms. In: 8th Workshop on Scientific Cloud Computing. washington, USA: ACM, 2017. (ScienceCloud, ’17).
BARIK, R. K. et al. Performance analysis of virtual machines and containers in cloud computing. In: International Conference on Computing, Communication and Automation. Noida, INDIA: IEEE, 2016.(ICCCA, ’16), p. 1204–1210.
FELTER, W. et al. An update performance comparison of virtual machines and linux containers. In: 2015 IEEE International Symposium on Performance Analysis of Systems and Software. Philadelphia,USA: IEEE, 2015. (ISPASS, ’15), p. 171–172.
GUPTA, B. C.; GUTTMAN, I. Statistics and Probability with Applications for Engineers and Scientists. 1. ed. Hoboken, USA: John Wiley & Sons, 2017. v. 1.
MEREDITH, M.; URGAONKAR, B. On exploiting resource diversity in the public cloud for modeling application performance. In: The Eighth International Conference on Cloud Computing, GRIDs, and Virtualization. San Francisco, USA: IEEE, 2017. (CLOUD, ’17), p. 171–172.
JOY, A. M. Performance comparison between linux containers and virtual machines. In: International Conference on Advances in Computer Engineering and Applications. Ghaziabad, India: IEEE, 2015. 15, p. 342–346.
MARSAN, M. A. et al. Modelling with Generalized Nets. 1. ed. New York, USA: John Wiley & Sons, 1994. v. 1.
DESROCHERS, A. A.; AL-JAAR, R. Y. Applications of Petri Nets in Manufacturing Systems - Modeling, Control, and performance Analysis. 1. ed. New York, USA: IEEE Control Systems Society, 19945. v. 1.
MENASCE, D.; DOWDY, L.; ALMEIDA, V. A. F. Performance by Design: Computer Capacity Planning by Example. 1. ed. New Jersey, USA: Prentice Hall, 2004. v. 1.
HIPS TOOL. Hierarchical Petri net Simulator. Online, https://sourceforge.net/projects/hips-tools/.
ARMSTRONG, T. G. et al. Linkbench: a database benchmark based on the facebook social graph. In: . New York, USA: ACM, 2013. (SIGMOD, ’13), p. 1185–1196.
Nielsen Norman Group. Response Times: The 3 Important Limits. Online, https://www.nngroup.com/articles/response-times-3- important-limits/.