Engineering and Experimentally Benchmarking a Serverless Edge Computing System

TL;DR

This paper designs and experimentally benchmarks a serverless edge computing system using open-source tools, demonstrating feasibility on heterogeneous devices like Raspberry Pis with promising performance but highlighting areas for improvement.

Contribution

It presents a novel decentralized serverless edge computing architecture built with open-source software and benchmarks its performance across diverse hardware devices.

Findings

Serverless edge computing is feasible on heterogeneous devices.

Good response times and throughput on constrained devices like Raspberry Pis.

Identifies challenges in computational power assessment and network characterization.

Abstract

Thanks to the latest advances in containerization, the serverless edge computing model is becoming close to reality. Serverless at the edge is expected to enable low latency applications with fast autoscaling mechanisms, all running on heterogeneous and resource-constrained devices. In this work, we engineer and experimentally benchmark a serverless edge computing system architecture. We deploy a decentralized edge computing platform for serverless applications providing processing, storage, and communication capabilities using only open-source software, running over heterogeneous resources (e.g., virtual machines, Raspberry Pis, or bare metal servers, etc). To achieve that, we provision an overlay-network based on Nebula network agnostic technology, running over private or public networks, and use K3s to provide hardware abstraction. We benchmark the system in terms of response times, throughput and scalability using different hardware devices connected through the public Internet. The results show that while serverless is feasible on heterogeneous devices showing a good performance on constrained devices, such as Raspberry Pis, the lack of support when determining computational power and network characterization leaves much room for improvement in edge environments.