Despite the increases in disk capacity and decreases in mechanicaldelays in recent years, the performance gap between magnetic disks andCPU continues to increase. To improve disk performance, operating systems and file systems must have detailed low-level information(e.g., zoning, bad-sector positions, and cache size) and high-levelinformation (e.g. expected read and write performance for differentaccess pattern) about the disks that they use. In this paper,we present Diskbench, our tool for extracting such information.Diskbench uses both interrogative and empirical methods for extractingvarious disk features. We present our extraction methods and results forseveral testbeds. From our empirical study, we conclude that intelligentdata placement and access methods can be devised to improve disk performance,by exploiting low-level disk knowledge. Diskbench has benefittedour video storage research in the implementation of Semi-preemptible IOand guaranteed real-time scheduling.