MOSAIC: Detection and Categorization of I/O Patterns in HPC Applications
- Authors:
- Théo Jolivel, François Tessier, Julien Monniot, Guillaume Pallez
- Venue:
- PDSW 2024 (Atlanta, USA) - November 17, 2024 - Workshop Paper
- DOI:
- 10.1109/SCW63240.2024.00172
- HAL (open access):
- hal-04808300
- Keywords:
- I/O, Characterization, Analysis, Traces
- Slides:
- Animated Slides - PDF
Abstract: With the gap between computing power and I/O performance growing ever wider on HPC systems, it is becoming crucial to optimize how applications perform I/O on storage resources. To achieve this, a good understanding of application I/O behavior is an essential preliminary step. In this paper, we introduce MOSAIC, a method for categorizing applications according to their I/O behavior. We first propose an abstraction for characterizing I/O operations in terms of periodicity, temporality and metadata access. We then present a set of segmentation-based techniques for quickly and automatically detecting meaningful data access patterns. In the end, MOSAIC is able to characterize a full set of real-world I/O traces from the Blue Waters supercomputer with 92% accuracy.