Avaliação de desempenho e problemas de envelhecimento de software em clusters de contêineres

• Ano de defesa: 2022
• Autor(a) principal: Costa, Jackson Tavares da
• Orientador(a): Matos Júnior, Rubens de Souza
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Programa de Pós-Graduação: Pós-Graduação em Ciência da Computação
• Palavras-chave em Português: Software; Cluster (Sistema de computador); Envelhecimento de software; Rejuvenescimento de software; Orquestração; Contêineres
• Palavras-chave em Inglês: Software aging; Software rejuvenation; Kubernetes; Orchestration; Containers
• Área do conhecimento CNPq: CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: https://ri.ufs.br/jspui/handle/riufs/19526

With the increase in cloud implementations of the most varied services by several companies in recent years, the demands of providers for robust, scalable and complex architectures have significantly increased, also requiring essential requirements such as reliability, performance and availability. As a result, technologies based on container virtualization have gained much prominence. On the other hand, with the significant increase in the use of containers supporting services, there is also a need for management tools to control the tasks of automating deployment, processing, scheduling and general application operations. For this purpose, Kubernetes has been the most used tool due to its efficiency in container orchestration, also in the runtime environment, in addition to its maturity and robustness. Many works in recent years have highlighted the importance of studying the phenomenon of software aging in cloud computing systems, as it is a threat to the availability and performance of the services offered. Therefore, we intend to evaluate the performance of Kubernetes, to verify possible levels of degradation or failures, in order to detect signs arising from the phenomenon of software aging and propose approaches to software rejuvenation, in order to avoid sudden interruptions in the provision of services deployed in the Kubernetes Cluster.