Serverless computing

• Autor(a) principal: Oliveira, José Miguel
• Data de Publicação: 2023
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Texto Completo: http://hdl.handle.net/10400.22/24241
• topic: Serverless; Cloud; Function; Infrastructure

Serverless computing has emerged as a new mindset when it comes to cloud computing, promising efficient resource utilization, automatic scaling, and cost optimization for a wide range of applications. This thesis explores the adoption, performance, and cost considera tions of deploying applications that use intend to use serverless functions, one of the leading Serverless types. This thesis starts by providing an overview of Serverless computing, including its key advan tages and disadvantages and the rising adoption it has gained throughout the recent years. It presents a comprehensive comparison of various Serverless platforms and discusses the unique features offered by each. After this context phase, this thesis presents a design section composed by a migration guide that allows developers to transition from a traditional application to one that takes advan tage of serverless benefits. The guide outlines best practices and step-by-step instructions, facilitating the adoption of Serverless computing in real-world scenarios. Using the previously created guide, the next section carries out a practical use case: the mi gration of complex computational logic from a traditional Java application to AWS Lambda functions. Performance evaluations are conducted, considering metrics such as the execution duration and the amount of concurrent executions. These findings are then evaluated next to the costs associated with deploying and running Java applications in a virtual machine or with a Serverless architecture. While Serverless computing is quite promising, networking issues often arise in practice, affecting the overall efficiency of Serverless applications. This thesis addresses these chal lenges, identifying the installation and migration difficulties, how to overcome them, and what are the expected limitations, while proposing potential solutions. In summary, this thesis offers valuable insights into the adoption, performance, and cost opti mization of Serverless computing for Java applications. It provides a roadmap for developers looking to take advantage of the benefits of Serverless computing in their projects.