Advanced elastic platforms for high throughput computing on container-based and serverless infrastructures

• Autores: Alfonso María Pérez González
• Directores de la Tesis: Germán Moltó Martínez (dir. tes.)
• Lectura: En la Universitat Politècnica de València ( España ) en 2020
• Idioma: español
• Tribunal Calificador de la Tesis: María Blanca Caminero Herráez (presid.), José Damián Segrelles Quilis (secret.), Juan Gutiérrez Aguado (voc.)
• Programa de doctorado: Programa de Doctorado en Informática por la Universitat Politècnica de València
• Materias:
  • Ciencias tecnológicas
• Enlaces
  • Tesis en acceso abierto en: RiuNet
• Resumen

  • The main objective of this thesis is to allow scientific users to deploy and execute highly-parallel event-driven file-processing serverless applications both in public (e.g. AWS), and in private (e.g. OpenNebula, OpenStack) cloud infrastructures. To achieve this objective, different tools and platforms are developed and integrated to provide scientific users with a way for deploying High Throughput Computing applications based on containers that can benefit from the high elasticity capabilities of the serverless environments. First, an open-source tool to deploy generic serverless workloads in the AWS public Cloud provider has been created. This tool allows the scientific users to benefit from the features of AWS Lambda (e.g. high scalability, event-driven computing) for the deployment and integration of compute-intensive applications that use the Functions as a Service (FaaS) model. Second, an event-driven file-processing high-throughput programming model has been developed to allow the users deploy generic applications as workflows of functions in serverless architectures, offering transparent data management. Third, in order to overcome the drawbacks of public serverless services such as limited execution time or computing capabilities, an open-source platform to support FaaS for compute-intensive applications in on-premises Clouds was created. The platform can be automatically deployed on multi-Clouds in order to create highly-parallel event-driven file-processing serverless applications. Finally, in order to assess and validate all the developed tools and platforms, several use cases with business and scientific backgrounds have been tested.