RAPID: Enabling Fast Online Policy Learning in Dynamic Public Cloud Environments

• Published in: arXiv.org
• Main Authors: Penney, Drew, Li, Bin, Chen, Lizhong, Sydir, Jaroslaw J, Drewek-Ossowicka, Anna, Illikkal, Ramesh, Tai, Charlie, Iyer, Ravi, Herdrich, Andrew
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 04.09.2023
• Subjects: Cloud computing; Computer Science - Distributed, Parallel, and Cluster Computing; Computer Science - Learning; Computer Science - Systems and Control; Distance learning; Internet resources; Quality of service; Resource allocation; Resource utilization; Workload; Workloads
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.2304.04797

Resource sharing between multiple workloads has become a prominent practice among cloud service providers, motivated by demand for improved resource utilization and reduced cost of ownership. Effective resource sharing, however, remains an open challenge due to the adverse effects that resource contention can have on high-priority, user-facing workloads with strict Quality of Service (QoS) requirements. Although recent approaches have demonstrated promising results, those works remain largely impractical in public cloud environments since workloads are not known in advance and may only run for a brief period, thus prohibiting offline learning and significantly hindering online learning. In this paper, we propose RAPID, a novel framework for fast, fully-online resource allocation policy learning in highly dynamic operating environments. RAPID leverages lightweight QoS predictions, enabled by domain-knowledge-inspired techniques for sample efficiency and bias reduction, to decouple control from conventional feedback sources and guide policy learning at a rate orders of magnitude faster than prior work. Evaluation on a real-world server platform with representative cloud workloads confirms that RAPID can learn stable resource allocation policies in minutes, as compared with hours in prior state-of-the-art, while improving QoS by 9.0x and increasing best-effort workload performance by 19-43%.