Job Simulation for Large-Scale PBS-Based Clusters with the Maui Scheduler

Authors: Georg Zitzlsberer (IT4Innovations, Czech Republic; Technical University of Ostrava, Czech Republic), Branislav Jansik (IT4Innovations, Czech Republic; Technical University of Ostrava, Czech Republic), Jan Martinovic (IT4Innovations, Czech Republic; Technical University of Ostrava, Czech Republic)

Abstract: For large-scale High Performance Computing centers with a wide range of different projects and heterogeneous infrastructures, efficiency is an important consideration. Understanding how compute jobs are scheduled is necessary for improving the job scheduling strategies in order to optimize cluster utilization and job wait times. This increases the importance of a reliable simulation capability, which in turn requires accuracy and comparability with historic workloads from the cluster. Not all job schedulers have a simulation capability, including the Portable Batch System (PBS) resource manager. Hence, PBS based centers have no direct way to simulate changes and optimizations before they are applied to the production system. We propose and discuss how to run job simulations for large-scale PBS based clusters with the Maui Scheduler. For validation purposes, we use historic workloads collected at the IT4Innovations supercomputing center, and demonstrate the viability of our approach.

Best Poster Finalist (BP): no

Poster: pdf
Poster summary: PDF
Reproducibility Description Appendix: PDF


Back to Poster Archive Listing