Parallel application I/O performance often does not meet user expectations. Additionally, slight access pattern modifications may lead to significant changes in performance due to complex interactions between hardware and software. These challenges call for sophisticated tools to capture, analyze, understand, and tune application I/O.
In this BoF at SC18, speakers will highlight recent advances in monitoring tools to help address this problem. Discussions will follow to compare best practices, identify gaps in measurement and analysis, and find ways to translate parallel I/O analysis into actionable outcomes for users, facility operators, and researchers.
- Date: Tuesday 13th November
- Time: 5:15pm – 6:45pm
- Venue: Room C155/156, Kay Bailey Hutchison Convention Center, Dallas
The event will feature a series of talks followed by a longer discussion.
- Introduction – Phil Carns, Argonne National Laboratory
- Using benchmarks to understand performance behaviour – Julian Kunkel, University of Reading
- A peek into workflow I/O – Jakob Lüttgau, German Climate Computing Center (DKRZ)
- I/O profiling in the field with Ellexus – Rosemary Francis, Ellexus
- Monitoring of I/O with Lustre – Andreas Dilger, Lustre CTO at Whamcloud/DDN
- IO Workload Throttling on Supercomputers – Si Liu, Texas Advanced Computing Center
For more on the session and the rest of the SC18 programme, visit the SC18 website.
Workshop paper to download now
Ellexus recently contributed to a global paper on how to analyse I/O, created and published in conjunction with several of the speakers.
The paper is available for download on the Cornell University Library website and will be published in Springer Lecture Notes in Computer Science (LNCS).
Get in touch if you’d like to find a time to meet with the Ellexus team at SC18.