Serverless computing cuts power use on tiny computers by up to half
Energy-Proportional Serverless Computing on SBC Clusters
Distributed, Parallel, and Cluster Computing
Summary
Serverless computing runs code only when needed, but the servers it uses still consume a lot of power even when idle. The authors show that by turning off entire small computers when not in use and turning them back on when needed, power use can drop significantly without slowing down most requests. They built a system on small single-board computers that does this, cutting power by about 40-47% in typical workloads. The trade-off is that some requests might wait about a minute if all computers are off and need to boot up.
What this means in practice
- •For cloud infrastructure engineers: Optimize power use in serverless clusters by powering off idle physical nodes to reduce energy costs without affecting median request speed.
- •For edge computing operators: Run serverless functions efficiently on clusters of low-power devices by managing node power states based on workload bursts.
Authors
Yuliya Sasinskaya, Natalie Carl, Niklas Kowallik, David Bermbach
Abstract
Serverless computing promises to run code only on demand, yet the servers beneath it draw most of their power while idle, so energy consumption does not scale to zero with the workload. We show that the statelessness of serverless functions makes it possible to extend scale-to-zero from function instances to physical nodes, enabling energy proportionality. Our platform, built on tinyFaaS for clusters of single-board computers, treats node power state as part of worker selection, powering workers off when idle and back on under load. On a physical cluster, our approach reduces mean power draw by 39.6 % on a bursty, trace-based workload and by 46.7 % on a sparse one, without a detectable change in median latency on the bursty workload. The cost lands in the tail, where invocations that arrive while all workers are off wait about a minute for a node to boot. Under continuous load, the platform behaves like an always-on cluster.