Automatic Minimization of Execution Budgets of SPITS Programs in AWS

  • Nicholas T. OkitaEmail author
  • Tiago A. Coimbra
  • Charles B. Rodamilans
  • Martin Tygel
  • Edson Borin
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1171)


Cloud computing platforms offer a wide variety of computational resources with different performance specifications for different prices. In this work, we experiment how Spot instances and Availability Zones on the Amazon Web Services (AWS) could be utilized to reduce the processing budget. Not only that, but we propose instance selection algorithms in AWS to minimize the execution budget of programs implemented using the programming model Scalable Partially Idempotent Task System (SPITS). Our results show that the proposed method can identify and dynamically adjust the virtual machine types that offer the best price per performance ratio. Therefore, we conclude that our algorithms can minimize the budget given a long enough execution time, except in situations where the startup overhead caused the budget difference or in a short period execution.


Cloud-computing Auto-scaling Economics 



This work was possible thanks to the support of Petrobras, CNPq (313012/2017-2), and Fapesp (2013/08293-7). The authors also thank the High-Performance Geophysics (HPG) team for technical support.


  1. 1.
    Amazon: Amazon EC2 Reserved Instances pricing. (2019). Accessed 03 May 2019
  2. 2.
    Borin, E., Benedicto, C., Rodrigues, I.L., Pisani, F., Tygel, M., Breternitz, M.: PY-PITS: a scalable Python runtime system for the computation of partially idempotent tasks. In: 2016 International Symposium on Computer Architecture and High Performance Computing Workshops (SBAC-PADW) (2016).
  3. 3.
    Fomel, S., Kazinnik, R.: Non-hyperbolic common reflection surface. Geophys. Prospect. 61(1) (2012). Scholar
  4. 4.
    Li, Z., et al.: Spot pricing in the cloud ecosystem: a comparative investigation. J. Syst. Softw. 114, 1–9 (2016). Scholar
  5. 5.
    Okita, N., Coimbra, T., Rodamilans, C., Tygel, M., Borin, E.: Using SPITS to optimize the cost of high-performance geophysics processing on the cloud. In: First EAGE Workshop on High Performance Computing for Upstream in Latin America. EAGE Publications BV (2018).
  6. 6.
    Okita, N., Rodamilans, C., Coimbra, T., Tygel, M., Borin, E.: Otimização automática do custo de processamento de programas SPITS na AWS. In: Anais da Trilha Principal do XIX Simpósio em Sistemas Computacionais de Alto Desempenho (WSCAD 2018), pp. 196–207, SBC (2018)Google Scholar
  7. 7.
    Shastri, S., Irwin, D.: Hotspot: automated server hopping in cloud spot markets. In: Proceedings of the 2017 Symposium on Cloud Computing. ACM (2017)Google Scholar
  8. 8.
    Subramanya, S., Guo, T., Sharma, P., Irwin, D., Shenoy, P.: SpotOn: a batch computing service for the spot market. In: Proceedings of the Sixth ACM Symposium on Cloud Computing. ACM (2015)Google Scholar
  9. 9.
    Wan, J., Gui, X., Zhang, R.: Dynamic bidding in spot market for profit maximization in the public cloud. J. Supercomput. 73(10), 4245–4274 (2017). Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Nicholas T. Okita
    • 1
    Email author
  • Tiago A. Coimbra
    • 1
  • Charles B. Rodamilans
    • 1
    • 2
  • Martin Tygel
    • 1
  • Edson Borin
    • 1
    • 3
  1. 1.Center for Petroleum Studies (CEPETRO)University of Campinas (UNICAMP)CampinasBrazil
  2. 2.Computing and Informatics Department (FCI)Mackenzie Presbyterian University (MPU)São PauloBrazil
  3. 3.Institute of Computing (IC)University of Campinas (UNICAMP)CampinasBrazil

Personalised recommendations