Priority-BF: A Task Manager for Priority-Based Scheduling

Ana Gainaru, Scott Klasky, Guillaume Pallez

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The increasing demand for computational resources, particularly in High-Performance Computing environments, necessitates to rethink how we handle job scheduling strategies. This work addresses the challenge of managing concurrent jobs with differing priorities on overloaded parallel systems, where strict QoS constraints are often difficult for users to define. Our solution relies on a qualitative description of priorities and pulls from two key approaches: the Easy-BF algorithm and the Conservative Backfilling algorithms. This solution improves the response time for high-priority jobs by 50% without affecting the overall system utilization. We show its applicability in several critical scenarios such as High-Performance Computing (HPC) resource management and in-situ computing.

Original languageEnglish
Title of host publicationEuro-Par 2025
Subtitle of host publicationParallel Processing - 31st European Conference on Parallel and Distributed Processing, 2025, Proceedings
EditorsWolfgang E. Nagel, Diana Goehringer, Pedro C. Diniz
PublisherSpringer Science and Business Media Deutschland GmbH
Pages219-232
Number of pages14
ISBN (Print)9783031998539
DOIs
StatePublished - 2026
Event31st European Conference on Parallel and Distributed Processing, Euro-Par 2025 - Dresden, Germany
Duration: Apr 25 2025Apr 29 2025

Publication series

NameLecture Notes in Computer Science
Volume15900 LNCS
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference31st European Conference on Parallel and Distributed Processing, Euro-Par 2025
Country/TerritoryGermany
CityDresden
Period04/25/2504/29/25

Funding

This material is based upon work supported by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research, for Research on Next Generation Data Management under Award Number DE-FOA-00002725. This work has benefited from a national grant managed by the French National Research Agency (Agence Nationale de la Recherche) attributed to the Exa-DoST project of the NumPEx PEPR program, under the reference ANR-22-EXNU-0004. This research uses data that was generated from resources of the Argonne Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC02-06CH11357. It used resources from Oak Ridge Leadership Computing Facility, which is a DOE Office of Science User Facility supported under Contract DE-AC05-00OR22725.

Keywords

  • Backfilling algorithm
  • HPC
  • Priority execution
  • Scheduling

Fingerprint

Dive into the research topics of 'Priority-BF: A Task Manager for Priority-Based Scheduling'. Together they form a unique fingerprint.

Cite this