HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Improving Backfilling by using Machine Learning to predict Running Times

Abstract : The job management system is the HPC middleware responsible for distributing computing power to applications. While such systems generate an ever increasing amount of data, they are characterized by uncertainties on some parameters like the job running times. The question raised in this work is: To what extent is it possible/useful to take into account predictions on the job running times for improving the global scheduling? We present a comprehensive study for answering this question assuming the popular EASY backfilling policy. More precisely, we rely on some classical methods in machine learning and propose new cost functions well-adapted to the problem. Then, we assess our proposed solutions through intensive simulations using several production logs. Finally, we propose a new scheduling algorithm that outperforms the popular EASY backfilling algorithm by 28% considering the average bounded slowdown objective.
Complete list of metadata

Cited literature [22 references]  Display  Hide  Download

Contributor : Valentin Reis Connect in order to contact the contributor
Submitted on : Tuesday, October 27, 2015 - 3:33:50 PM
Last modification on : Wednesday, February 2, 2022 - 3:56:44 PM
Long-term archiving on: : Friday, April 28, 2017 - 6:34:19 AM


Files produced by the author(s)






Eric Gaussier, David Glesser, Valentin Reis, Denis Trystram. Improving Backfilling by using Machine Learning to predict Running Times. SuperComputing 2015, Nov 2015, Austin, TX, United States. ⟨10.1145/2807591.2807646⟩. ⟨hal-01221186⟩



Record views


Files downloads