Serverless platform driven CPU loadbalancing

2026-08-06

AI Summary

This work addresses the challenge that existing serverless platforms, despite having global visibility into functions and resources, are constrained by general-purpose OS schedulers and thus struggle to simultaneously optimize energy efficiency and low latency. The paper proposes the first CPU scheduling framework driven by the serverless control plane, leveraging Linux’s SchedExt (SCX) to implement a custom scheduler that partially delegates scheduling decisions to the control plane. It dynamically partitions configurable scheduling domains based on function invocation patterns and employs intra-domain single-queue load balancing combined with virtual-time-based prioritization. Experimental results demonstrate that, under an eight-domain configuration, the system reduces energy consumption by 15% with only a 5% increase in invocation cost, while achieving up to 50% lower request latency compared to CFS under high load.

Abstract

Serverless platforms maintain a global view of function invocations and resource utilization, yet existing systems largely restrict CPU scheduling decisions to the operating system scheduler. This paper presents a serverless platform-driven CPU load balancing framework that enables the control plane to directly influence CPU scheduling through a custom Linux scheduler built on SchedExt(SCX). The proposed scheduler introduces configurable scheduling domains and a shared interface that allows the control plane to assign functions to domains based on their historical inter-arrival times. Within each domain, a single-queue load-balancing strategy combined with a virtual-time prioritization policy improves task placement while reducing interference from busy-polling tasks. Results show that an eight-domain configuration achieves the best trade-off, reducing system energy consumption by approximately 15% while increasing invocation cost by only 5%. Under heavily loaded workloads, the proposed scheduler also reduces request latency by up to 50% compared to the default Linux Completely Fair Scheduler (CFS). These results demonstrate that exposing CPU scheduling decisions to the serverless control plane can improve both energy efficiency and workload performance while preserving scheduling flexibility.

Problem

• serverless
• CPU load balancing
• scheduling
• energy efficiency
• latency

Innovation

• serverless
• CPU load balancing
• SchedExt
• scheduling domains
• virtual-time prioritization