Function and data placement reduces client delay at edge cloud nodes
Replication-Aware Placement of Functions and Data in the Edge-Cloud Continuum
Distributed, Parallel, and Cluster Computing
Summary
Cloud computing often runs small tasks called functions separately from their stored information, which can slow things down if not placed well. The authors study how to best schedule these functions and place their data to make things faster for users, while handling copies of data that need different rules for consistency. They create a mathematical model to find the best solution, but since it gets very complex with many nodes, they also design a faster method that finds nearly the best placement efficiently. Their quick method is practical for adjusting cloud systems over time to keep user experiences smooth.
What this means in practice
- •For cloud infrastructure teams: Improve response times by optimally placing functions and their data in edge-cloud systems with varying consistency needs.
- •For content delivery network engineers: Use a fast greedy method to efficiently decide where to replicate data and run serverless functions near users for low latency.
Authors
Dario d'Abate, Matteo Cenzato, Matteo Briscini, Arianna Dragoni, Alessandro Margara
Abstract
Function-as-a-Service (FaaS) has emerged as the prominent programming model for the edge-cloud continuum. FaaS inherently decouples stateless functions from their persistent state. We study how to jointly schedule functions and place data to minimize client latency, considering data replication under heterogeneous consistency requirements. We introduce a Binary Linear Programming (BLP) model to compute optimal placements, establishing a rigorous theoretical baseline. Since the BLP scales cubically with the infrastructure nodes, we propose a topology-aware greedy heuristic that efficiently approximates the optimal solution. Our evaluation shows that the heuristic achieves near-optimal placement quality at a fraction of the computational cost, making it suitable for periodic system reconfigurations.