How Much Does Submitting a Burst of Jobs Impact Waiting Time? An Analysis of the Jean Zay Workload Trace
Abstract
This paper examines job waiting times on the Jean Zay supercomputer at IDRIS (Institut du Développement et des Ressources en Informatique Scientifique http://www.idris.fr/), driven by the need to improve scheduling strategies for crossfacility scientific workflows. Drawing on large workload traces, we show that job waiting times are not independent of one another but are instead correlated through job bursts—batches of identical jobs submitted together, also called “flurries”. We introduce a method for quantifying the effect of these bursts on waiting times, and find a strong Pearson correlation between waiting time and a job’s rank within its burst. This correlation is above 0.8 for more than 40% of the jobs. We further derive an exact formula for the Slurm fairshare factor based on a convolution product, showing that the burst penalty operates on a much shorter timescale than fairshare itself—pointing to a distinct throttling mechanism specifically targeting bulk submissions. Once burst effects are accounted for, we use Welch’s t-test to find that partition occupancy and number of requested cores have a significant effect on waiting time, though the effect is not significant for all partitions.
Related
- Modeling inhomogeneous spatial point configurations with applications to replicated patterns in real-life waiting crowds
- Adjusting for Social Groups in Spatial Point Process Models for Waiting Pedestrian Configurations
- Finite speed of propagation and waiting time phenomena for stochastic porous media equations with nonlinear conservative noise
- An exponent-s dynamical Borel-Cantelli lemma and the waiting time problem
- Waiting time for scheduled outpatient specialist consultations by access pathway in public hospitals in Ecuador
BibTeX
@misc{garenaux2026much,
title = {{How Much Does Submitting a Burst of Jobs Impact Waiting Time? An Analysis of the Jean Zay Workload Trace}},
author = {Marius Garénaux and François Bodin},
howpublished = {HAL},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.11703},
eprint = {2610.11703},
archivePrefix = {arXiv},
url = {https://hal.science/hal-05783397v1},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - How Much Does Submitting a Burst of Jobs Impact Waiting Time? An Analysis of the Jean Zay Workload Trace
AU - Marius Garénaux
AU - François Bodin
PY - 2026
DA - 2026/10/07
PB - HAL
DO - 10.48550/arxiv.2610.11703
UR - https://hal.science/hal-05783397v1
AB - This paper examines job waiting times on the Jean Zay supercomputer at IDRIS (Institut du Développement et des Ressources en Informatique Scientifique http://www.idris.fr/), driven by the need to improve scheduling strategies for crossfacility scientific workflows. Drawing on large workload traces, we show that job waiting times are not independent of one another but are instead correlated through job bursts—batches of identical jobs submitted together, also called “flurries”. We introduce a method for quantifying the effect of these bursts on waiting times, and find a strong Pearson correlation between waiting time and a job’s rank within its burst. This correlation is above 0.8 for more than 40% of the jobs. We further derive an exact formula for the Slurm fairshare factor based on a convolution product, showing that the burst penalty operates on a much shorter timescale than fairshare itself—pointing to a distinct throttling mechanism specifically targeting bulk submissions. Once burst effects are accounted for, we use Welch’s t-test to find that partition occupancy and number of requested cores have a significant effect on waiting time, though the effect is not significant for all partitions.
ER -