AARC: Automated Affinity-aware Resource Configuration for Serverless Workflows

2025-02-28

AI Summary

To address inefficient resource provisioning caused by the strong CPU–memory coupling in serverless workflows, this paper proposes the first affinity-aware automated resource decoupling framework. The method integrates graph-centric scheduling with priority-based configuration coordination, leveraging graph analysis, critical-path identification, and SLO-driven dynamic search to achieve fine-grained, adaptive CPU/memory decoupling at the workflow level. Unlike prior approaches, our framework significantly reduces search time by 85.8%–89.6% while cutting runtime cost by 49.6%–61.7%, all while strictly satisfying end-to-end service-level objectives (SLOs). This represents the first systematic solution enabling independent, workload-aware allocation of CPU and memory resources in serverless orchestration—thereby breaking the rigid resource bundling imposed by current FaaS platforms.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Machine Learning: Hardware-aware ML

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Serverless computing is increasingly adopted for its ability to manage complex, event-driven workloads without the need for infrastructure provisioning. However, traditional resource allocation in serverless platforms couples CPU and memory, which may not be optimal for all functions. Existing decoupling approaches, while offering some flexibility, are not designed to handle the vast configuration space and complexity of serverless workflows. In this paper, we propose AARC, an innovative, automated framework that decouples CPU and memory resources to provide more flexible and efficient provisioning for serverless workloads. AARC is composed of two key components: Graph-Centric Scheduler, which identifies critical paths in workflows, and Priority Configurator, which applies priority scheduling techniques to optimize resource allocation. Our experimental evaluation demonstrates that AARC achieves substantial improvements over state-of-the-art methods, with total search time reductions of 85.8% and 89.6%, and cost savings of 49.6% and 61.7%, respectively, while maintaining SLO compliance.

Problem

• Decouples CPU and memory in serverless workflows
• Optimizes resource allocation for complex workflows
• Reduces search time and cost while maintaining SLO

Innovation

• Decouples CPU and memory resources
• Uses Graph-Centric Scheduler for workflows
• Applies Priority Configurator for optimization