Article
Version 1
Preserved in Portico This version is not peer-reviewed
Analytical and Numerical Evaluation of Co-Scheduling Strategies and Their Application
Version 1
: Received: 1 September 2021 / Approved: 3 September 2021 / Online: 3 September 2021 (10:14:03 CEST)
A peer-reviewed article of this Preprint also exists.
Kuchumov, R.; Korkhov, V. Analytical and Numerical Evaluation of Co-Scheduling Strategies and Their Application. Computers 2021, 10, 122. Kuchumov, R.; Korkhov, V. Analytical and Numerical Evaluation of Co-Scheduling Strategies and Their Application. Computers 2021, 10, 122.
Abstract
Applications in high-performance computing (HPC) may not use all available computational resources, leaving some of them underutilized. By co-scheduling, i.e. running more than one application on the same computational node, it is possible to improve resource utilization and overall throughput. Some applications may have conflicting requirements on resources and co-scheduling may cause performance degradation, so it is important to take it into account in scheduling decisions. In this paper, we formalized co-scheduling problem and proposed multiple scheduling strategies to solve it: an optimal strategy, an online strategy and heuristic strategies. These strategies vary in terms of the optimality of the solution they produce and a priori information about the system they require. We showed theoretically that the online strategy provides schedules with a competitive ratio that has a constant upper limit. This allowed us to solve the co-scheduling problem using heuristic strategies that approximate this online strategy. Numerical simulations showed how heuristic strategies compare to the optimal strategy for different input systems. We proposed a method for measuring input parameters of the model in practice and evaluated this method on HPC benchmark applications. We showed high accuracy of measurement method, which allows to apply proposed scheduling strategies in scheduler implementation.
Keywords
Co-scheduling; HPC; scheduling theory; stochastic optimization
Subject
Computer Science and Mathematics, Mathematics
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment
