Ms Gin Tan1, Dr Chris Hines1, Ms Sarah Walters2, Mr. Chris Schlipalius3
1Monash University, Australia, 2University of Queensland, Australia, 3The Pawsey Supercomputing Centre, Australia
Biography:
Gin Tan is the Associate Director of Monash eResearch. She began her career in both enterprise and research computing, eventually finding her true passion in high-performance computing (HPC). Over the past eight years at Monash University, Gin has been instrumental in the development and deployment of a new HPC cluster, and has since grown into a technical leadership role. She enjoys diving deep into the technical aspects of her work while also excelling at translating complex needs into practical, effective solutions.
Chris has been kicking around the sector for longer than he likes to admit, even to himself. Originally a physicist he has become a jack of all trades doing a little bit of sysadmin here, a little bit of programming there. He gets excited about seeing interesting research happen and his main aim is to make advanced computing tools accessible to all researchers without them having to become a computer nerd like him.
Sarah Walters is a Project Manager and Research Computing Systems Engineer at the University of Queensland (UQ) Research Computing Centre with a strong background in supporting research and administration of advanced computing systems. She currently specialises in enabling new uses of High Performance Computing systems, helping to meet the needs of graphical and AI applications, and delivery of innovative storage and computation projects. She is passionate about working on projects that make a difference, particularly in improving researcher outcomes, and growing national capabilities.
https://orcid.org/0009-0003-2762-3232
Chris is an experienced presenter and Storage Manager with over 25 years of experience working on managing block storage, SANs, Tape and POSIX filesystems for large data holdings at The Curtin University of Technology and The Pawsey Supercomputing Centre. He is a member of the SC25 and SCA26 Committees and has presented at and organised a number of workshops on Storage and Filesystems in Australia, USA, Germany and Singapore. He also presented at the main Spectrum Scale Usergroup at SC18 on Improving Spark work load performance with Spectrum Conductor on Spectrum Scale (for scratch).
He ran the Versity User Group in Atlanta in 2025, and in previous years the Spectrum Scale Usergroup in Singapore, and cities across Australia and was on the Spectrum Scale Usergroup worldwide organising committee and IBM Champion for 5 years.
https://orcid.org/0009-0002-4556-8524
Abstract:
As high-performance computing (HPC) evolves to meet the demands of modern science and industry, system administrators across Australasia are facing a convergence of critical challenges. The increasing complexity of heterogeneous environments, driven by specialised accelerators, tight budgets, and evolving software stacks, demands agile, scalable, and reproducible infrastructure solutions. In this context, the choice of job scheduler has become a pivotal decision point: Slurm/PBS remains mainstream for traditional HPC workloads, but Kubernetes is gaining traction for its flexibility in handling diverse, secure, and cloud native workloads. We will explore a practical comparison between Slurm/PBS and Kubernetes for scheduling, outlining trade-offs and synergies.
Compounding technical challenges is a pronounced skills shortage. Fewer junior sysadmins are entering the field with foundational command-line experience, forcing teams to consider new models of talent development, such as structured training straight from university. These pressures underscore the importance of fostering a strong, collaborative HPC sysadmin community in Australia and the broader Australasian region, one that can share knowledge, tools, and strategies for building resilient and efficient infrastructure.
This session presents real-world insights on managing configuration at scale, fast-tracking deployment with reproducibility in mind, and fostering a new generation of HPC professionals through community-led initiatives.