Explorando a Elasticidade Assíncrona em Nuvem para Aplicações Paralelas Iterativas

  • Vinicius Rodrigues Unisinos
  • Cristiano Costa Unisinos
  • Rodrigo Righi Unisinos
  • Diego Kreutz FCUL

Resumo


A elasticidade é sem dúvida uma das características mais marcantes da computação em nuvem. Na área de computação de alto desempenho, as iniciativas normalmente trabalham aplicações no estilo sacola-de-tarefas com necessidade de alterações no código para o tratamento da elasticidade. Nesse contexto, esse artigo apresenta o modelo de elasticidade chamado AutoElastic. AutoElastic atua em nível de middleware sobre aplicações paralelas iterativas, oferecendo provisionamento automático de recursos. Seu diferencial está no conceito de elasticidade assíncrona. Além do modelo, o presente artigo também apresenta um protótipo construído com OpenNebula e sua avaliação com uma aplicação iterativa, demonstrando ganhos em relação a tempo de até 14% e baixa intrusividade.

Referências

Baliga, J., Ayre, R., Hinton, K., and Tucker, R. (2011). Green cloud computing: Balancing energy in processing, storage, and transport. Proceedings of the IEEE, 99(1):149–167.

Beernaert, L., Matos, M., Vilaça, R., and Oliveira, R. (2012). Automatic elasticity in openstack. In Proceedings of the Workshop on Secure and Dependable Middleware for Cloud Monitoring and Management, SDMCMM ’12, pages 1–6, ACM.

Cai, B., Xu, F., Ye, F., and Zhou, W. (2012). Research and application of migrating legacy systems to the private cloud platform with cloudstack. In Automation and Logistics (ICAL), 2012 IEEE International Conference on, pages 400 –404.

Chiu, D. and Agrawal, G. (2010). Evaluating caching and storage options on the amazon web services cloud. In Grid Computing (GRID), 11th Int. Conf. on, pages 17 –24.

Dawoud, W., Takouna, I., and Meinel, C. (2011). Elastic vm for cloud resources provisioning optimization. Advances in Computing and Communications, volume 190 of Communications in Computer and Information Science, pages 431–445. Springer.

Goh, W. X. and Tan, K.-L. (2014). Elastic mapreduce execution. In Cluster, Cloud and Grid Computing (CCGrid), 2014 14th IEEE/ACM Int. Symp. on, pages 216–225.

Imai, S., Chestna, T., and Varela, C. A. (2012). Elastic scalable cloud computing using application-level migration. In Proceedings of the 2012 IEEE/ACM Fifth International Conference on Utility and Cloud Computing, UCC ’12, pages 91–98, IEEE.

Kouki, Y., Oliveira, F. A. d., Dupont, S., and Ledoux, T. (2014). A language support for cloud elasticity management. In Cluster, Cloud and Grid Computing (CCGrid), 14th Int. Symp. on, pages 206–215.

Lee, Y., Avizienis, R., Bishara, A., Xia, R., Lockhart, D., Batten, C., and Asanovic, K. (2011). Exploring the tradeoffs between programmability and efciency in dataparallel accelerators. In Comp. Arch. (ISCA), 38th Int. Symp. on, pages 129–140.

Mao, M., Li, J., and Humphrey, M. (2010). Cloud auto-scaling with deadline and budget constraints. In Grid Computing (GRID), 2010 11th IEEE Int. Conf. on, pages 41 –48.

Martin, P., Brown, A., Powley, W., and Vazquez-Poletti, J. L. (2011). Autonomic management of elastic services in the cloud. In Proc. of the 2011 IEEE Symp. on Computers and Communications, ISCC ’11, pages 135–140, IEEE.

Michon, E., Gossa, J., and Genaud, S. (2012). Free elasticity and free cpu power for scientic workloads on iaas clouds. In Parallel and Distributed Systems (ICPADS), 18th Int. Conf. on, pages 85 –92.

Mihailescu, M. and Teo, Y. M. (2012). The impact of user rationality in federated clouds. Cluster Computing and the Grid, IEEE Int. Symp. on, 0:620–627.

Milojicic, D., Llorente, I. M., and Montero, R. S. (2011). Opennebula: A cloud manage ment tool. Internet Computing, IEEE, 15(2):11 –14.

Rajan, D., Canino, A., Izaguirre, J. A., and Thain, D. (2011). Converting a high performance application to an elastic cloud application. In Proc. of the Third Int. Conf. on Cloud Computing Technology and Science, CLOUDCOM ’11, pages 383–390, IEEE.

Raveendran, A., Bicer, T., and Agrawal, G. (2011). A framework for elastic execution of existing mpi programs. In Proc. of the 2011 IEEE Int. Symp. on Parallel and Distributed Processing Workshops and PhD Forum, IPDPSW ’11, pages 940–947, IEEE.

Roloff, E., Birck, F., Diener, M., Carissimi, A., and Navaux, P. (2012). Evaluating In Cloud Computing

high performance computing on the windows azure platform. (CLOUD), 2012 IEEE 5th Int. Conf. on, pages 803–810.

Sinha, N. and Khreisat, L. (2014). Cloud computing security, data, and performance issues. In Wireless and Optical Communication Conf. (WOCC), 2014 23rd, pages 1–6.

Wen, X., Gu, G., Li, Q., Gao, Y., and Zhang, X. (2012). Comparison of open-source cloud management platforms: Openstack and opennebula. In Fuzzy Systems and Knowledge Discovery (FSKD), 2012 9th Int. Conf. on, pages 2457 –2461.

Zhang, X., Shae, Z.-Y., Zheng, S., and Jamjoom, H. (2012). Virtual machine migration In Network Operations and Management Symposium in an over-committed cloud. (NOMS), 2012 IEEE, pages 196 –203.
Publicado
08/10/2014
RODRIGUES, Vinicius; COSTA, Cristiano; RIGHI, Rodrigo; KREUTZ, Diego. Explorando a Elasticidade Assíncrona em Nuvem para Aplicações Paralelas Iterativas. In: SIMPÓSIO EM SISTEMAS COMPUTACIONAIS DE ALTO DESEMPENHO (SSCAD), 15. , 2014, São José dos Campos. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2014 . p. 63-74. DOI: https://doi.org/10.5753/wscad.2014.15000.