Lumos: Performance Characterization of WebAssembly as a Serverless Runtime in the Edge-Cloud Continuum

Abstract

WebAssembly has emerged as a lightweight and portable runtime to execute serverless functions, particularly in heterogeneous and resource-constrained environments such as the Edge-Cloud Continuum. However, the performance benefits versus trade-offs remain insufficiently understood. Current state-of-the-art performance characterizations either focus on isolated WebAssembly benchmarks or fail to address workload diversity, such as compute-intensive and data-intensive scenarios, in dynamic and heterogeneous environments such as the Edge-Cloud Continuum. Therefore, in this paper, we present Lumos, a performance model and benchmarking tool for characterizing serverless runtimes. Lumos identifies workload, system, and environment-level performance drivers in the Edge-Cloud Continuum. We benchmark state-of-the-art containers and the Wasm runtime in interpreted mode and with ahead-of-time compilation. Our performance characterization shows that AoT-compiled Wasm images are up to 30x smaller and decrease cold-start latency by up to 16% compared to containers, while interpreted Wasm suffers 30-55x higher warm latency and 7-10x I/O-serialization overhead.