WebAssembly and Unikernels: A Comparative Study for Serverless at the Edge

2025-09-11

AI Summary

High cold-start latency in serverless execution hinders ultra-low-latency requirements of Ultra-low-latency Edge Computing (UEC). Method: This paper systematically compares two lightweight execution environments—WebAssembly (via the Limes runtime built on Wasmtime) and unikernel-based MicroVMs (Firecracker)—under realistic edgeless settings integrated with the SPARE framework, conducting multi-workload experiments to quantify the trade-off between cold-start latency and execution performance. Results: Wasm achieves 3.2–8.7× faster cold starts for lightweight functions, making it highly suitable for UEC’s stringent latency constraints; Firecracker delivers superior throughput stability and lower tail latency for complex and I/O-intensive workloads. This work establishes, for the first time under UEC constraints, empirically grounded applicability boundaries between these paradigms. We open-source the Limes runtime to support evidence-based runtime selection and practical deployment in edgeless edge computing.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Multiagent Systems: Multiagent Systems under Uncertainty
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Serverless computing at the edge requires lightweight execution environments to minimize cold start latency, especially in Urgent Edge Computing (UEC). This paper compares WebAssembly and unikernel-based MicroVMs for serverless workloads. We present Limes, a WebAssembly runtime built on Wasmtime, and evaluate it against the Firecracker-based environment used in SPARE. Results show that WebAssembly offers lower cold start times for lightweight functions but suffers with complex workloads, while Firecracker provides higher, but stable, cold starts and better execution performance, particularly for I/O-heavy tasks.

Problem

• Comparing WebAssembly and unikernels for edge serverless workloads
• Evaluating cold start latency in urgent edge computing environments
• Assessing performance trade-offs between lightweight and complex functions

Innovation

• WebAssembly runtime for lightweight serverless functions
• Unikernel-based MicroVMs for stable I/O performance
• Comparative evaluation framework for edge computing