Avaliação Comparativa de Escalabilidade de Aplicações de Alto Desempenho em Cluster Físico e na Nuvem
Resumo
A análise de desempenho de aplicações de computação de alto desempenho (HPC) foi recentemente facilitada pelo uso de plataformas de nuvem. Os subsídios concedidos pelos fornecedores de infra-estrutura para projetos de pesquisa nas universidades também tem contribuído neste sentido. No entanto, o desempenho de aplicativos HPC depende fortemente do suporte de Entrada/Saída da plataforma, principalmente da rede de intercomunicação entre as máquinas virtuais. Neste estudo, o desempenho de aplicativos selecionados da suíte NPB NAS Parallel Benchmark e aplicações reais para o processamento de consultas geográfica foi comparado, em um cluster físico de máquinas comuns e outro cluster semelhante na nuvem Microsoft Azure. Nossos testes demonstraram um speed-up até 2,7 vezes menor na nuvem para aplicações limitadas por CPU. Apesar da qualidade superior dos processadores na nuvem, nossos testes também mostraram um tempo de execução até 3,0 vezes maior na nuvem.
Referências
Abramson, D., Jackson, J., Muthrasanallur, S., Neiger, G., Regnier, G., Sankaran, R., Schoinas, I., Uhlig, R., Vembu, B., and Wiegert, J. (2006). Intel Virtualization Technology for Directed I/O. Intel Technology Journal, Vol. 10 Is.
AMD, A. M. D. (2009). I/O Virtualization Technology (IOMMU) Specification Revision 1.26. White Paper, AMD, 1:2–11.
Bailey, D., Browning, D., Carter, R., Dagum, L., Fatoohi, R., Fineberg, S., Frederickson, P., Lasinski, T., Schreiber, R., Simon, H., and Others (1994). The NAS Parallel Benchmarks. NASA Ames Research Center: Moffett Field, CA.
Bailey, D. H., Barszcz, E., Barton, J. T., Browning, D. S., Carter, R. L., Dagum, L., Fatoohi, R. A., Frederickson, P. O., Lasinski, T. A., Schreiber, R. S., and Others (1991). The NAS parallel benchmarks. International Journal of High Performance Computing Applications, 5(3):63–73.
Barker, S. and Shenoy, P. (2010). Empirical evaluation of latency-sensitive application performance in the cloud. MMSys ’10 Proceedings of the first annual ACM SIGMM conference on Multimedia systems, pages 35–46.
Expósito, R. R., Taboada, G. L., Ramos, S., Touriño, J., and Doallo, R. (2013). Performance analysis of HPC applications in the cloud. Future Generation Computer Systems, 29(1):218–229.
Ferreira, C. H. G., Ribeiro, J. a. B., Júnior, W. D. B., Estrella, J. C., Filho, D. M. L., and Peixoto, M. L. M. (2014). Identificação de gargalos de desempenho em ambientes virtuais para uso em computação em nuvem. In Anais do WPerformance - CSBC 2014, pages 1975–1988.
Hill, Z., Li, J., Mao, M., Ruiz-Alvarez, A., and Humphrey, M. (2011). Early observations on the performance of Windows Azure. Scientific Programming, 6640(2-3):121–132.
Huber, N., von Quast, M., Hauck, M., and Kounev, S. (2011). Evaluating and Modeling Virtualization Performance Overhead for Cloud Environments. Proceedings of the 1st International Conference on Cloud Computing and Services Science (CLOSER 2011), pages 563–573.
Intel (2007). Improving Network Performance in Multi-Core Systems. White Pap. Intel Ethernet Controllers, 1:1–4.
Li, Z., OBrien, L., Cai, R., and Zhang, H. (2012). Towards a Taxonomy of Performance Evaluation of Commercial Cloud Services. In 2012 IEEE Fifth International Conference on Cloud Computing, pages 344–351. IEEE.
Luszczek, P., Meek, E., Moore, S., Terpstra, D., Weaver, V. M., and Dongarra, J. (2012). Evaluation of the HPC Challenge Benchmarks in Virtualized Environments. In Proceedings 2011 International Conference on Parallel Processing, volume 7156 of Lecture Notes in Computer Science, pages 436–445, Berlin, Heidelberg. Springer.
Mei, Y., Liu, L., Pu, X., Sivathanu, S., and Dong, X. (2013). Performance Analysis of Network I/O Workloads in Virtualized Data Centers. IEEE Transactions on Services Computing, 6(1):48–63.
Rixner, S. (2008). Network Virtualization: Breaking the Performance Barrier. Queue, 6(1):36.
Tudoran, R., Costan, A., Antoniu, G., and Bougé, L. (2012). A performance evaluation of Azure and Nimbus clouds for scientific applications. In Proceedings of the 2nd International Workshop on Cloud Computing Platforms - CloudCP ’12, pages 1–6, New York, New York, USA. ACM Press.
Walters, J. P., Chaudhary, V., Minsuk, C., Guercio, S., and Gallo, S. (2008). A comparison of virtualization technologies for HPC. In Proceedings - International Conference on Advanced Information Networking and Applications, AINA, pages 861–868.
Younge, A. J., Henschel, R., Brown, J. T., von Laszewski, G., Qiu, J., and Fox, G. C. (2011). Analysis of Virtualization Technologies for High Performance Computing Environments. In 2011 IEEE 4th International Conference on Cloud Computing, pages 9–16. IEEE.
AMD, A. M. D. (2009). I/O Virtualization Technology (IOMMU) Specification Revision 1.26. White Paper, AMD, 1:2–11.
Bailey, D., Browning, D., Carter, R., Dagum, L., Fatoohi, R., Fineberg, S., Frederickson, P., Lasinski, T., Schreiber, R., Simon, H., and Others (1994). The NAS Parallel Benchmarks. NASA Ames Research Center: Moffett Field, CA.
Bailey, D. H., Barszcz, E., Barton, J. T., Browning, D. S., Carter, R. L., Dagum, L., Fatoohi, R. A., Frederickson, P. O., Lasinski, T. A., Schreiber, R. S., and Others (1991). The NAS parallel benchmarks. International Journal of High Performance Computing Applications, 5(3):63–73.
Barker, S. and Shenoy, P. (2010). Empirical evaluation of latency-sensitive application performance in the cloud. MMSys ’10 Proceedings of the first annual ACM SIGMM conference on Multimedia systems, pages 35–46.
Expósito, R. R., Taboada, G. L., Ramos, S., Touriño, J., and Doallo, R. (2013). Performance analysis of HPC applications in the cloud. Future Generation Computer Systems, 29(1):218–229.
Ferreira, C. H. G., Ribeiro, J. a. B., Júnior, W. D. B., Estrella, J. C., Filho, D. M. L., and Peixoto, M. L. M. (2014). Identificação de gargalos de desempenho em ambientes virtuais para uso em computação em nuvem. In Anais do WPerformance - CSBC 2014, pages 1975–1988.
Hill, Z., Li, J., Mao, M., Ruiz-Alvarez, A., and Humphrey, M. (2011). Early observations on the performance of Windows Azure. Scientific Programming, 6640(2-3):121–132.
Huber, N., von Quast, M., Hauck, M., and Kounev, S. (2011). Evaluating and Modeling Virtualization Performance Overhead for Cloud Environments. Proceedings of the 1st International Conference on Cloud Computing and Services Science (CLOSER 2011), pages 563–573.
Intel (2007). Improving Network Performance in Multi-Core Systems. White Pap. Intel Ethernet Controllers, 1:1–4.
Li, Z., OBrien, L., Cai, R., and Zhang, H. (2012). Towards a Taxonomy of Performance Evaluation of Commercial Cloud Services. In 2012 IEEE Fifth International Conference on Cloud Computing, pages 344–351. IEEE.
Luszczek, P., Meek, E., Moore, S., Terpstra, D., Weaver, V. M., and Dongarra, J. (2012). Evaluation of the HPC Challenge Benchmarks in Virtualized Environments. In Proceedings 2011 International Conference on Parallel Processing, volume 7156 of Lecture Notes in Computer Science, pages 436–445, Berlin, Heidelberg. Springer.
Mei, Y., Liu, L., Pu, X., Sivathanu, S., and Dong, X. (2013). Performance Analysis of Network I/O Workloads in Virtualized Data Centers. IEEE Transactions on Services Computing, 6(1):48–63.
Rixner, S. (2008). Network Virtualization: Breaking the Performance Barrier. Queue, 6(1):36.
Tudoran, R., Costan, A., Antoniu, G., and Bougé, L. (2012). A performance evaluation of Azure and Nimbus clouds for scientific applications. In Proceedings of the 2nd International Workshop on Cloud Computing Platforms - CloudCP ’12, pages 1–6, New York, New York, USA. ACM Press.
Walters, J. P., Chaudhary, V., Minsuk, C., Guercio, S., and Gallo, S. (2008). A comparison of virtualization technologies for HPC. In Proceedings - International Conference on Advanced Information Networking and Applications, AINA, pages 861–868.
Younge, A. J., Henschel, R., Brown, J. T., von Laszewski, G., Qiu, J., and Fox, G. C. (2011). Analysis of Virtualization Technologies for High Performance Computing Environments. In 2011 IEEE 4th International Conference on Cloud Computing, pages 9–16. IEEE.
Publicado
20/07/2015
Como Citar
DE OLIVEIRA, Thiago; SILVA, Ariel; DA CUNHA, Italo; P. JÚNIOR, Paulo.
Avaliação Comparativa de Escalabilidade de Aplicações de Alto Desempenho em Cluster Físico e na Nuvem. In: WORKSHOP EM DESEMPENHO DE SISTEMAS COMPUTACIONAIS E DE COMUNICAÇÃO (WPERFORMANCE), 14. , 2015, Recife.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2015
.
p. 15-28.
ISSN 2595-6167.
DOI: https://doi.org/10.5753/wperformance.2015.10394.
