On Realizing Stateful FaaS in Serverless Edge Networks: State Propagation

Abstract

In this paper, we address the problem of supporting chains of stateful function invocations following a Function-as-a-Service (FaaS) model in edge networks. In particular we focus on the problem of data transfer, which can be a performance bottleneck due to the limited speed of communication links in some edge scenarios, such as wide-area Internet of Things (IoT) networks, and we propose three different solutions: a pure FaaS implementation, StateProp, i.e., propagation of the application state throughout the entire chain of functions, and StateLocal, i.e., a solution where the state is kept local to the workers that run functions and retrieved only as needed. We show via simulation that StateLocal, by applying the data locality principle, can significantly enhance the performance by reducing the application delay due to data transfer and keeping a lower traffic volume in the network. This study sheds light on some aspects within the unexplored area of stateful FaaS, which is very promising among the edge computing technologies and has several open research directions associated.