Mixture-of-Schedulers: An Adaptive Scheduling Agent as a Learned Router for Expert Policies

TL;DR

This paper introduces ASA, an adaptive scheduling framework that dynamically selects the best scheduler for workloads, significantly improving performance over static policies by using machine learning and workload recognition.

Contribution

It presents a novel, lightweight framework that combines offline training of a universal workload model with runtime adaptive scheduler selection, enabling rapid adaptation to new hardware without retraining.

Findings

ASA outperforms default Linux scheduler in 86.4% of scenarios.

ASA's scheduler choices are near-optimal in 78.6% of cases.

The approach demonstrates practical benefits for diverse workloads.

Abstract

Modern operating system schedulers employ a single, static policy, which struggles to deliver optimal performance across the diverse and dynamic workloads of contemporary systems. This "one-policy-fits-all" approach leads to significant compromises in fairness, throughput, and latency, particularly with the rise of heterogeneous hardware and varied application architectures. This paper proposes a new paradigm: dynamically selecting the optimal policy from a portfolio of specialized schedulers rather than designing a single, monolithic one. We present the Adaptive Scheduling Agent (ASA), a lightweight framework that intelligently matches workloads to the most suitable "expert" scheduling policy at runtime. ASA's core is a novel, low-overhead offline/online approach. First, an offline process trains a universal, hardware-agnostic machine learning model to recognize abstract workload patterns from system behaviors. Second, at runtime, ASA continually processes the model's predictions using a time-weighted probability voting algorithm to identify the workload, then makes a scheduling decision by consulting a pre-configured, machine-specific mapping table to switch to the optimal scheduler via Linux's sched_ext framework. This decoupled architecture allows ASA to adapt to new hardware platforms rapidly without expensive retraining of the core recognition model. Our evaluation, based on a novel benchmark focused on user-experience metrics, demonstrates that ASA consistently outperforms the default Linux scheduler (EEVDF), achieving superior results in 86.4% of test scenarios. Furthermore, ASA's selections are near-optimal, ranking among the top three schedulers in 78.6% of all scenarios. This validates our approach as a practical path toward more intelligent, adaptive, and responsive operating system schedulers.