Analysis of Workloads for Cloud Infrastructure Capacity Planning

  • Eva PatelEmail author
  • Dharmender Singh Kushwaha
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 847)


Workload analysis and characterization are the first steps toward effective cloud infrastructure capacity planning. Identifying workload patterns based on resource utilization not only enables informed decisions about mapping of current request to available capacity, but also serves as a meaningful indicator for future resource requirements. Of paramount concern is the optimal utilization of data center server capacity, i.e., the CPU, I/O, and memory. The compute capacity of modern servers can be further harnessed by optimal utilization of individual CPU cores. A precise CPU core-level usage monitoring and provisioning can lead to cumulative benefits of optimal CPU utilization, efficient VM placement, reduced VM migrations, and energy efficiency through lower power consumption. In this paper, we make a preliminary analysis of usage patterns of CPU cores in the case of CPU- and memory-intensive workloads on an experimental cloud setup in our laboratory. The aim is to make a comparative analysis of the utilization of individual CPU cores with that of aggregated CPU usage to explore the feasibility of incorporating a fine-grained usage detail for resource scheduling and VM provisioning. Initial experiments reveal observable differences between the utilization of individual CPU cores and that reported by aggregate CPU usage. Usage difference ranges from 1 to 29% below and between 4 and 20% above the aggregate. Incorporating such finer details can leverage the vast compute capacity of multicore servers and effective power usage.


Workload analysis Workload characterization Capacity planning Server capacity planning Workload intensity Job inter-arrival patterns Multicore scheduling 


  1. 1.
    Varia, J., Mathew, S.: Overview of Amazon Web Services. Amaz. Web Serv. (2014)Google Scholar
  2. 2.
  3. 3.
    Feitelson, D.G.: Workload modeling for computer systems performance evaluation. Cambridge University Press, Cambridge (2015)CrossRefGoogle Scholar
  4. 4.
    Mahambre, S., Kulkarni, P., Bellur, U., Chafle, G., Deshpande, D.: Workload characterization for capacity planning and performance management in IaaS cloud. In: 2012 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM), pp. 1–7 (2012)Google Scholar
  5. 5.
    Moreno, I.S., Garraghan, P., Townend, P., Xu, J.: Analysis, modeling and simulation of workload patterns in a large-scale utility cloud. IEEE Trans. Cloud Comput. 2, 208–221 (2014)CrossRefGoogle Scholar
  6. 6.
    Magalhães, D., Calheiros, R.N., Buyya, R., Gomes, D.G.: Workload modeling for resource usage analysis and simulation in cloud computing. Comput. Electr. Eng. 47, 69–81 (2015)CrossRefGoogle Scholar
  7. 7.
    Peng, J., Chen, J., Zhi, X., Qiu, M., Xie, X.: Research on application classification method in cloud computing environment. J. Supercomput. 73, 3488–3507 (2017)CrossRefGoogle Scholar
  8. 8.
    Zhang, Q., Zhani, M.F., Boutaba, R., Hellerstein, J.L.: Dynamic heterogeneity-aware resource provisioning in the cloud. IEEE Trans. Cloud Comput. 2, 14–28 (2014)CrossRefGoogle Scholar
  9. 9.
    Singh, S., Chana, I.: QRSF: QoS-aware resource scheduling framework in cloud computing. J. Supercomput. 71, 241–292 (2015)CrossRefGoogle Scholar
  10. 10.
    Orzechowski, P., Proficz, J., Krawczyk, H., Szymański, J.: Categorization of cloud workload types with clustering. In: Proceedings of the International Conference on Signal, Networks, Computing, and Systems, pp. 303–313 (2017)Google Scholar
  11. 11.
    Lozi, J.P., Lepers, B., Funston, J., Gaud, F., Quéma, V., Fedorova, A.: The Linux scheduler: a decade of wasted cores. In: Proceedings of the Eleventh European Conference on Computer Systems, p. 1 (2016)Google Scholar
  12. 12.
    Capacity Planning—Discipline for Data center decisions, Last Accessed 2018/06/10
  13. 13.
    Sokol, A.W., Hogan, M.D.: NIST Cloud Computing Standards Roadmap (2013)Google Scholar
  14. 14.
    Calzarossa, M.C., Della Vedova, M.L., Massari, L., Petcu, D., Tabash, M.I.M., Tessera, D.: Workloads in the clouds. In: Principles of Performance and Reliability Modeling and Evaluation, pp. 525–550. Springer, Berlin (2016)Google Scholar
  15. 15.
    Vajda, A.: Programming many-core chips. Springer Science & Business Media, Berlin (2011)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringMNNIT AllahabadAllahabadIndia

Personalised recommendations