Investigando o Impacto de Containers no Desempenho de um Workflow Científico

  • Bruno Alves UFSM
  • Andrea Charão UFSM

Resumo


A descrição de workflows científicos através de uma linguagem padrão garante, entre outras coisas, portabilidade e escalabilidade aos fluxos de trabalhos científicos. Ao encontro da portabilidade e reprodutibilidade, os contêineres representam uma forma de virtualização leve. Dessa forma, o presente trabalho propõe-se a investigar os impactos gerados pelos contêineres no desempenho de workflows científicos através da execução do workflow Hecil. A engine de workflow Toil foi utilizada para a leitura e execução do fluxo e duas estratégias conteinerizadas são utilizadas para o escalonamento das tarefas. Os resultados mostram que o controle de criação e remoção de contêineres feito pelo Toil pode representar um gargalo na execução de workflows.

Referências

Albrecht, M., Donnelly, P., Bui, P., and Thain, D. (2012). Makeow: A portable abstrac- tion for data intensive computing on clusters, clouds, and grids. In Proceedings of the

1st ACM SIGMOD Workshop on Scalable Workow Execution Engines and Technolo- gies, SWEET '12, New York, NY, USA. Association for Computing Machinery.

Chapman, B., Chilton, J., Heuer, M., Kartashov, A., Leehr, D., Ménager, H., Nedeljko- vich, M., Scales, M., Soiland-Reyes, S., and Stojanovic, L. (2016). Common Workow Language, v1.0. Specication, product of the Common Workow Language working group. http://www.commonwl.org/v1.0/.

Combe, T., Martin, A., and Di Pietro, R. (2016). To Docker or not to Docker: A security perspective. IEEE Cloud Computing, 3(5):54–62.

Dua, R., Raja, A. R., and Kakadia, D. (2014). Virtualization vs containerization to support PaaS. In 2014 IEEE International Conference on Cloud Engineering, pages 610–614.

Felter, W., Ferreira, A., Rajamony, R., and Rubio, J. (2015). An updated performance In 2015 IEEE International comparison of virtual machines and Linux containers. Symposium on Performance Analysis of Systems and Software (ISPASS), pages 171– 172.

Hung, L.-H., Hu, J., Meiss, T., Ingersoll, A., Lloyd, W., Kristiyanto, D., Xiong, Y., Sobie, E., and Yeung, K. Y. (2018). Building containerized workows using the biodepot- workow-builder (bwb). bioRxiv.

Jansen, C., Annuscheit, J., Schilling, B., Strohmenger, K., Witt, M., Bartusch, F., Herta, C., Hufnagl, P., and Krefting, D. (2020). Curious containers: A framework for com- putational reproducibility in life sciences with support for deep learning applications. Future Generation Computer Systems, 112:209 – 227.

Perez-Riverol, Y. and Moreno, P. (2019). Scalable data analysis in proteomics and meta- bolomics using biocontainers and workows engines. bioRxiv.

Preeth E N, Mulerickal, F. J. P., Paul, B., and Sastri, Y. (2015). Evaluation of Docker containers based on hardware utilization. In 2015 International Conference on Control Communication Computing India (ICCC), pages 697–700.

Stefansen, C. (2005). Smawl: A small workow language based on ccs. Technical report, Harvard Computer Science Group Technical Report TR-06-05.

Sweeney, K. M. D. and Thain, D. (2018). Efcient integration of containers into scien- tic workows. In Proceedings of the 9th Workshop on Scientic Cloud Computing, ScienceCloud'18, pages 7:1–7:6, New York, NY, USA. ACM.

van der Aalst, W. and ter Hofstede, A. (2005). Yawl: yet another workow language. Information Systems, 30(4):245 – 275.

Xavier, M. G., Neves, M. V., Rossi, F. D., Ferreto, T. C., Lange, T., and De Rose, C. A. F. (2013). Performance evaluation of container-based virtualization for high perfor- mance computing environments. In 2013 21st Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, pages 233–240.

Zheng, C. and Thain, D. (2015). Integrating containers into workows: A case study using Makeow, Work Queue, and Docker. In Proceedings of the 8th International Workshop on Virtualization Technologies in Distributed Computing, VTDC '15, pages 31–38, New York, NY, USA. ACM.
Publicado
21/10/2020
ALVES, Bruno; CHARÃO, Andrea. Investigando o Impacto de Containers no Desempenho de um Workflow Científico. In: WORKSHOP DE INICIAÇÃO CIENTÍFICA - SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 21. , 2020, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2020 . p. 117-124. DOI: https://doi.org/10.5753/wscad_estendido.2020.14097.