Work

DynaSPLIT: Strong tail-optimal scheduling for the M/G/n with heavy-tailed job sizes

Year: 2026

Type: preprint

Abstract: We study the asymptotic response time tail in the M/G/n queue with heavy-tailed (regularly varying) job sizes. For this setting, strongly tail optimal policies are known only at lower load, where n-1 servers suffice for stability. At higher load, the tail optimal scheduling has been open. This paper presents DynaSPLIT, the first strongly tail optimal policy at high load. Together with prior work, this result shows that strong tail optimality is achievable across the entire stability region of the M/G/n with heavy-tailed job sizes.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.17329

Authors: Li, Zhouzi, Harchol-Balter, Mor, Scheller-Wolf, Alan

Institution: Carnegie Mellon University

Language: English

Topic: Advanced Queuing Theory Analysis

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: green

Funders: National Science Foundation, Division of Civil, Mechanical and Manufacturing Innovation

Awards: Collaborative Research: CIF: Medium: Towards optimal scheduling for parallelizable machine learning training workloads, Collaborative Research: III: Small: High-Performance Scheduling for Modern Database Systems, New Approaches to Multiserver Scheduling

OpenAlex ID: W7221820991

Cites: 2

Cited by:

Related to: 10