Ermes integrates stateful functions to cut edge computing delays
Ermes: a Stateful Serverless Platform for the Edge-to-Cloud Continuum
Distributed, Parallel, and Cluster Computing
Summary
Edge computing aims to run apps closer to users to reduce delays, but many current cloud functions don't store data locally, causing slowdowns. The authors propose Ermes, which keeps both app code and data together across edge and cloud devices to reduce wait times. Ermes lets developers choose how strictly data stays consistent depending on needs, improving performance. Tests show Ermes lowers latency as more users connect and move around.
What this means in practice
- •For edge system developers: Build edge-to-cloud apps that manage state locally to reduce delays for users on mobile or distributed networks.
- •For mobile network operators: Deploy low-latency services by placing both app state and compute closer to mobile clients, improving user experience during movement.
Authors
Matteo Cenzato, Dario d'Abate, Arianna Dragoni, Giacomo Orsenigo, Luca Tosetti, Matteo Briscini, Alessandro Margara
Abstract
Function-as-a-Service (FaaS) is a widely adopted paradigm to simplify application deployment across the edge-to-cloud continuum. However, its stateless nature forces functions to retrieve their state from external, typically cloud-centric, data stores, reintroducing the very latency that edge computing aims to eliminate. This issue is further exacerbated by location-agnostic schedulers and rigid, one-size-fits-all consistency models that fail to capture the diverse requirements of edge applications. In this paper, we propose Ermes, a distributed platform that natively integrates state management into the FaaS paradigm, enabling the joint distribution of computational workloads and application state across the edge-to-cloud continuum. Ermes organizes application state into logical units, termed collections, and employs a distributed coordination algorithm that jointly maps collections and functions onto the available nodes seeking to minimize the latency perceived by the clients. In addition, it supports fine-grained replication and per-collection consistency levels, ranging from sequential to eventual consistency, leaving developers the choice of how to resolve the trade-off between consistency and performance. The experimental evaluation shows that Ermes quickly turns remote state accesses into local ones and sustains low latency as the workload grows, and as clients move across the edge.