Identificação de gargalos de desempenho em ambientes virtuais para uso em computação em nuvem
Resumo
A computação em nuvem se apoia na virtualização para fazer a manutenção e gerência de recursos de maneira transparente aos clientes de forma a aumentar o desempenho dos servidores ou recursos físicos. O uso de virtualização permite que vários clientes tenham máquinas independentes dentro de um mesmo servidor físico trazendo benefícios de isolamento de recursos, principalmente. No entanto, dependendo da carga de trabalho imposta a uma máquina virtual, a mesma pode gerar degradações de desempenhos em outras máquinas virtuais. Sendo assim, é fundamental identificar quando essas interfer ências acontecem e como evitá-las. Nossa proposta foi utilizar três tipos básicos de carga de trabalho (memória, cpu e E/S) para verificar, dentre o Virtualizador KVM ou Xen, qual o mais adequado para as atividades da nuvem. Nós verificamos que não há um virtualizador bom e sim um virtualizador adequado para cada tipo de carga de trabalho.
Referências
Arthur Baruchi, E. T. M. (2008). Inuência do algoritmo de escalonamento credit scheduler no desempenho de rede. In Anais do XXVIII Congresso da SBC : WSO Workshop de Sistemas Operacionais. SBC.
Benevenuto, F., Ismael Jr, J., and Almeida, J. (2004). Quantitative evaluation of unstructured peer-to-peer architectures. In Proceedings of the 2004 International Workshop on Hot Topics in Peer-to-Peer Systems, HOT-P2P '04, pages 56–65, Washington, DC, USA. IEEE Computer Society.
Daniels, J. (2009). Server virtualization architecture and implementation. Crossroads, 16(1):8–12.
Head, M., Kochut, A., Schulz, C., and Shaikh, H. (2010). Virtual hypervisor: Enabling fair and economical resource partitioning in cloud environments. In Network Operations and Management Symposium (NOMS), 2010 IEEE, pages 104–111.
Jain, R. (1991). The Art of Computer Systems Performance Analysis: Techniques for Experimental Design, Measurement, Simulation, and Modeling. Wiley Professional Computing. Wiley.
Jiang, W., Zhou, Y., Cui, Y., Feng, W., Chen, Y., Shi, Y., and Wu, Q. (2009). Cfs optimizations to kvm threads on multi-core environment. In Parallel and Distributed Systems (ICPADS), 2009 15th International Conference on, pages 348–354.
Khan, A., Othman, M., Madani, S., and Khan, S. (2014). A survey of mobile cloud computing application models. Communications Surveys Tutorials, IEEE, 16(1):393– 413.
Koh, Y., Knauerhase, R., Brett, P., Bowman, M., Wen, Z., and Pu, C. (2007). An analysis of performance interference effects in virtual environments. In Performance Analysis of Systems Software, 2007. ISPASS 2007. IEEE International Symposium on, pages 200–209.
Lee, M., Krishnakumar, A. S., Krishnan, P., Singh, N., and Yajnik, S. (2010). Supporting soft real-time tasks in the xen hypervisor. SIGPLAN Not., 45(7):97–108.
Matthews, J. N., Hu, W., Hapuarachchi, M., Deshane, T., Dimatos, D., Hamilton, G., and McCabe, M. (2007). Quantifying the performance isolation properties of virtualization systems. In Experimental Computer Science on Experimental Computer Science, ecs'07, pages 5–5, Berkeley, CA, USA. USENIX Association.
Niyato, D. (2011). Optimization-based virtual machine manager for private cloud computing. In Cloud Computing Technology and Science (CloudCom), 2011 IEEE Third International Conference on, pages 99–106.
Santos, R. and Charão, A. S. (2008). Análise comparativa de desempenho do hipervisor xen: Paravirtualização versus virtualização total. Universidade Federal de Santa Maria. Brasil.
Somani, G. and Chaudhary, S. (2010). Performance isolation and scheduler behavior. In Parallel Distributed and Grid Computing (PDGC), 2010 1st International Conference on, pages 272–277.
Srinivasan, S., Raja, K., and Muthuselvan, S. (2012). Futuristic assimilation of cloud computing platforms and its services. In Emerging Trends in Electrical Engineering and Energy Management (ICETEEEM), 2012 International Conference on, pages 178– 180.
VMware (2014). What is virtualization? https://www.vmware.com/br/virtualization/virtualization-basics/what-is-virtualization. Accessed: 2014-01-30.
White, J. and Pilbeam, A. (2010). A survey of virtualization technologies with perfor mance testing. CoRR, abs/1010.3233.
Zaghloul, S. (2013). The mutual effect of virtualization and parallelism in a cloud envi ronment. In AFRICON, 2013, pages 1–5.
Zhang, Q., Cheng, L., and Boutaba, R. (2010). Cloud computing: state-of-the-art and research challenges. Journal of internet services and applications, 1(1):7–18.
Benevenuto, F., Ismael Jr, J., and Almeida, J. (2004). Quantitative evaluation of unstructured peer-to-peer architectures. In Proceedings of the 2004 International Workshop on Hot Topics in Peer-to-Peer Systems, HOT-P2P '04, pages 56–65, Washington, DC, USA. IEEE Computer Society.
Daniels, J. (2009). Server virtualization architecture and implementation. Crossroads, 16(1):8–12.
Head, M., Kochut, A., Schulz, C., and Shaikh, H. (2010). Virtual hypervisor: Enabling fair and economical resource partitioning in cloud environments. In Network Operations and Management Symposium (NOMS), 2010 IEEE, pages 104–111.
Jain, R. (1991). The Art of Computer Systems Performance Analysis: Techniques for Experimental Design, Measurement, Simulation, and Modeling. Wiley Professional Computing. Wiley.
Jiang, W., Zhou, Y., Cui, Y., Feng, W., Chen, Y., Shi, Y., and Wu, Q. (2009). Cfs optimizations to kvm threads on multi-core environment. In Parallel and Distributed Systems (ICPADS), 2009 15th International Conference on, pages 348–354.
Khan, A., Othman, M., Madani, S., and Khan, S. (2014). A survey of mobile cloud computing application models. Communications Surveys Tutorials, IEEE, 16(1):393– 413.
Koh, Y., Knauerhase, R., Brett, P., Bowman, M., Wen, Z., and Pu, C. (2007). An analysis of performance interference effects in virtual environments. In Performance Analysis of Systems Software, 2007. ISPASS 2007. IEEE International Symposium on, pages 200–209.
Lee, M., Krishnakumar, A. S., Krishnan, P., Singh, N., and Yajnik, S. (2010). Supporting soft real-time tasks in the xen hypervisor. SIGPLAN Not., 45(7):97–108.
Matthews, J. N., Hu, W., Hapuarachchi, M., Deshane, T., Dimatos, D., Hamilton, G., and McCabe, M. (2007). Quantifying the performance isolation properties of virtualization systems. In Experimental Computer Science on Experimental Computer Science, ecs'07, pages 5–5, Berkeley, CA, USA. USENIX Association.
Niyato, D. (2011). Optimization-based virtual machine manager for private cloud computing. In Cloud Computing Technology and Science (CloudCom), 2011 IEEE Third International Conference on, pages 99–106.
Santos, R. and Charão, A. S. (2008). Análise comparativa de desempenho do hipervisor xen: Paravirtualização versus virtualização total. Universidade Federal de Santa Maria. Brasil.
Somani, G. and Chaudhary, S. (2010). Performance isolation and scheduler behavior. In Parallel Distributed and Grid Computing (PDGC), 2010 1st International Conference on, pages 272–277.
Srinivasan, S., Raja, K., and Muthuselvan, S. (2012). Futuristic assimilation of cloud computing platforms and its services. In Emerging Trends in Electrical Engineering and Energy Management (ICETEEEM), 2012 International Conference on, pages 178– 180.
VMware (2014). What is virtualization? https://www.vmware.com/br/virtualization/virtualization-basics/what-is-virtualization. Accessed: 2014-01-30.
White, J. and Pilbeam, A. (2010). A survey of virtualization technologies with perfor mance testing. CoRR, abs/1010.3233.
Zaghloul, S. (2013). The mutual effect of virtualization and parallelism in a cloud envi ronment. In AFRICON, 2013, pages 1–5.
Zhang, Q., Cheng, L., and Boutaba, R. (2010). Cloud computing: state-of-the-art and research challenges. Journal of internet services and applications, 1(1):7–18.
Publicado
28/07/2014
Como Citar
FERREIRA, Carlos; RIBEIRO, João; B. JÚNIOR, Wellington; ESTRELLA, Júlio; L. FILHO, Dionísio; PEIXOTO, Maycon.
Identificação de gargalos de desempenho em ambientes virtuais para uso em computação em nuvem. In: WORKSHOP EM DESEMPENHO DE SISTEMAS COMPUTACIONAIS E DE COMUNICAÇÃO (WPERFORMANCE), 13. , 2014, Brasília.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2014
.
p. 164-177.
ISSN 2595-6167.
