2026-06-19 –, A113 (capacity 64)
Modern Linux infrastructure is relentlessly benchmarked. Yet most storage tests share a critical flaw: they measure performance on freshly formatted filesystems.
Real systems don’t live in “day zero.” They age. Free space fragments. Metadata scatters. Allocation patterns degrade. Subtle regressions often emerge only after months or years of production churn.
By relying on day-zero testing, we miss performance cliffs that surface only in aged environments.
To close this gap, we need practical ways to rapidly age a filesystem. In this lightning talk, I will break down the methods used to simulate years of filesystem fragmentation and wear in just a matter of minutes. Finally, I will introduce Filestorm, a fully working, production-ready benchmark that encapsulates these rapid-aging techniques into a single tool, and share examples of real-world regressions it has already caught in the wild.
I’m a software engineer and performance specialist with a focus on Linux systems and Python development. At Red Hat, I work on kernel performance and manage hardware lab initiatives, and I’m the creator of Filestorm, an open-source benchmark for testing filesystem performance on aged storage states — a capability that fills a longstanding gap in storage benchmarking. My background also includes machine learning projects, from developing weather nowcasting models to research in medical imaging.