Reducing Execution Time in FaaS Cloud Platforms

Abstract

This article research into the significance of caching within Function-as-a-Service (FaaS) environments, exploring how caching strategies can substantially enhance performance and scalability in the realm of serverless computing. A versatile caching architecture for FaaS is introduced, tailored to accommodate different caching strategies. The architecture is implemented by extending an open-source FaaS framework, specifically Google's Functions Framework. An aspect-oriented approach is adopted to transparently specify the relevant objects that should be cached, effectively decoupling function implementation from deployment configuration. The study extensively investigates various caching mechanisms, encompassing in-process, out-of-process, and network caching, and systematically assesses their impact on response times and resource utilization. The findings underscore the trade-offs inherent in employing caching techniques, ultimately aiming to optimize FaaS performance and improve overall system efficiency.