Modelos para avaliação de disponibilidade orientada a capacidade de uma nuvem privada

Authors

DOI:

https://doi.org/10.22456/2175-2745.79158

Keywords:

Computer Science

Abstract

Alta disponibilidade é um dos principais requisitos das aplicações que utilizam computação em nuvem. É possível aplicar redundâncias em hardware e software para alcançar melhores níveis de disponibilidade do sistema. Porém, além da preocupação com a disponibilidade do serviço, é necessário mensurar a capacidade do sistema em lidar com a carga de trabalho apresentada. Uma métrica que pode ser utilizada para mensurar essa capacidade é a disponibilidade orientada a capacidade. A partir dessa métrica, é possível obter estimativas dos recursos computacionais disponíveis para utilização quando o sistema está em funcionamento. Esse trabalho apresenta um conjunto de modelos analíticos para avaliação de disponibilidade orientada a capacidade considerando ambientes de nuvem privada. Para verificar diferentes situações, esse trabalho apresenta seis diferentes arquiteturas de nuvem privada. Os componentes fundamentais de cada arquitetura são Front-End, PM e VMs. O conjunto de resultados apresentados compreende a avaliação de disponibilidade, avaliação de disponibilidade orientada a capacidade e análise de sensibilidade dos dos parâmetros utilizados nos modelos. A partir dos resultados é possível inferir quais componentes são mais importantes para cada uma das métricas estudadas.

Downloads

Download data is not yet available.

Author Biography

Matheus D'Eça Torquato, Instituto Federal de Alagoas (IFAL), Campus Arapiraca

Matheus Torquato received his Master Degree in Computer Science from the Federal University of Pernambuco. He received his Bachelor Degree in Computer Science from the Federal University of Alagoas. He also has a certificate in Computer Networks, received from Federal Institute of Alagoas. He already worked on building and managing of Cloud Computing Private Environments. His research interests comprise subjects like Cloud Computing, Performance and dependability Evaluation, Computer Networks and Distributed Systems. At the moment he is teaching Informatics the Federal Institute of Alagoas, Campus Arapiraca.

References

CISCO. Cisco Global Cloud Networking Survey Summary and Analysis of ResultsWorldwide Results. San Jose, USA, 2012.

IDG-ENTERPRISE. 2016 - Cloud Computing Survey - IDG Enterprise. 2016.

PHAM, C. et al. Toward a high availability cloud: Techniques and challenges. In: SWARZ, R.; KOOPMAN, P.; CUKIER, M. (Ed.). Dependable Systems and Networks Workshops (DSN-W), 2012 IEEE/IFIP 42nd International Conference on. Boston, USA: IEEE, 2012. v. 1.

HAGEN, S.; SEIBOLD, M.; KEMPER, A. Efficient verification of it change operations or: How we could have prevented. In: NOMS. Network Operations and Management Symposium. Maui, USA: IEEE, 2012. v. 1.

GRAY, J.; SIEWIOREK, D. P. High-availability computer systems. Comput., v. 24, n. 9, p. 39–48, 1991.

HEIMANN, D. I.; MITTAL, N.; TRIVEDI, K. S. Availability and reliability modeling for computer systems. In: YOVITS, M. C. (Ed.). Amsterdam, Netherlands: Elsevier, 1990, (Advances in Computers, v. 31). p. 175 – 233.

JADEJA, Y.; MODI, K. Cloud computing-concepts, architecture and challenges. In: ICCEET. Computing, Electronics and Electrical Technologies (ICCEET), 2012 International Conference on. Kumaracoil, India: IEEE, 2012. v. 1.

MARSAN, M. A. et al. Modelling with Generalized Stochastic Petri Nets. 1st. ed. New York, NY, USA: John Wiley & Sons, Inc., 1994. v. 1.

SALTELLI, A. et al. Sensitivity analysis. 1. ed. Hoboken, USA: John Wiley & Sons, 2000. v. 1. (Wiley Series in Probability and Statistics, v. 1).

SALTELLI, A. et al. Global sensitivity analysis: the primer. 1. ed. Hoboken, USA: John Wiley & Sons, 2008. v. 1.

WEBER, T. S. Toleraˆncia a falhas: conceitos e exemplos. Apostila do PPGC-INF UFGRS, v. 1, n. 1, p. 1–24, 2003.

BESERRA, D. et al. Utilizac ̧a ̃o de hardware legado para o ensino de cad. IJCAE, v. 3, n. 1, p. 17–20, 2014.

MELO, M. et al. Comparative analysis of migration- based rejuvenation schedules on cloud availability. In: LAI, L. L.; YEUNG, D. S. (Ed.). Systems, Man, and Cybernetics (SMC), 2013 IEEE International Conference on. Manchester, UK: IEEE, 2013. v. 1.

MELO, M. et al. Availability study on cloud computing environments: Live migration as a rejuvenation mechanism. In: PATARICZA, A.; CANDEA, G.; KEMPER, P. (Ed.). Dependable Systems and Networks (DSN), 2013 43rd Annual IEEE/IFIP International Conference on. Washington, USA: IEEE, 2013. v. 1.

KIM, D. S.; MACHIDA, F.; TRIVEDI, K. S. Availability modeling and analysis of a virtualized system. In: XU, S.; GAO, J.; XIANG, D. (Ed.). Dependable Computing, 2009. Shanghai, China: IEEE, 2009. v. 1.

TRIVEDI, K. S.; BOBBIO, A. Reliability and Availability Engineering: Modeling, Analysis, and Applications. 1. ed. Cambridge, UK: Cambridge University Press, 2017. v. 1.

MACIEL, P. et al. Mercury: Performance and dependability evaluation of systems with exponential, expolynomial, and general distributions. In: KIM, D. S.; KITAKAMI, M.; VARADHARAJAN, V. (Ed.). 2017 IEEE 22nd Pacific Rim International Symposium on Dependable Computing. Christchurch, New Zealand: IEEE, 2017. v. 1.

ECKHARDT, D. E. et al. An experimental evaluation of software redundancy as a strategy for improving reliability. IEEE Trans. Softw. Eng., v. 17, n. 7, p. 692–702, 1991.

MELO, C. et al. Capacity-oriented availability model for resources estimation on private cloud infrastructure. In: KIM, D. S.; KITAKAMI, M.; VARADHARAJAN, V. (Ed.). 2017 IEEE 22nd Pacific Rim International Symposium on Dependable Computing (PRDC). Christchurch, New Zealand: IEEE, 2017. v. 1.

MATOS, R. d. S. et al. Sensitivity analysis of server virtualized system availability. IEEE Trans. Rel., v. 61, n. 4, p. 994–1006, 2012.

DANTAS, J. et al. Eucalyptus-based private clouds: availability modeling and comparison to the cost of a public cloud. Computing, v. 97, n. 11, p. 1121–1140, 2015.

ATAIE, E. et al. Hierarchical stochastic models for performance, availability, and power consumption analysis of iaas clouds. IEEE TSC, v. 1, n. 1, p. 1, 2017.

CALHEIROS, R. N. et al. Cloudsim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms. Softw Pract Exp, v. 41, n. 1, p. 23–50, 2011.

LIU, B. et al. Model-based sensitivity analysis of iaas cloud availability. Future Gener Comput Syst., v. 83, n. 1, p. 1–13, 2018.

MATOS, R. et al. Redundant eucalyptus private clouds: availability modeling and sensitivity analysis. J Grid Comput., v. 15, n. 1, p. 1–22, 2017.

NURMI, D. et al. The eucalyptus open-source cloud-computing system. In: CCGRID ’09. Cluster Computing and the Grid, 2009. Washington, USA: IEEE Computer Society, 2009. v. 1.

CHANG, X. et al. Modeling and analysis of high availability techniques in a virtualized system. Comput J., v. 61, n. 2, p. 180–198, 2018.

NGUYEN, T. A.; KIM, D. S.; PARK, J. S. A comprehensive availability modeling and analysis of a virtualized servers system using stochastic reward nets. Sci. World J, v. 2014, n. 1, p. 1–1, 2014.

XU, J. et al. Availability modeling and analysis of a single-server virtualized system with rejuvenation. JSW, v. 9, n. 1, p. 129–139, 2014.

THEIN, T.; PARK, J. S. Availability analysis of application servers using software rejuvenation and virtualization. J. Comput. Sci. Tech, v. 24, n. 2, p. 339–346, 2009.

MACHIDA, F.; KIM, D. S.; TRIVEDI, K. S. Modeling system with live vm migration. Perform. Evaluation, v. 70, and analysis of software rejuvenation in a server virtualized n. 3, p. 212–230, 2013.

Downloads

Published

2018-07-17

How to Cite

Torquato, M. D., Torquato, L., & Maciel, P. (2018). Modelos para avaliação de disponibilidade orientada a capacidade de uma nuvem privada. Revista De Informática Teórica E Aplicada, 25(2), 73–84. https://doi.org/10.22456/2175-2745.79158

Issue

Section

Regular Papers