We introduce Skylight, a novel methodology that combines software and hardware techniques to reverse engineer key properties of drive-managed SMR. The software component of Skylight measures latency of controlled I/O operations to infer important properties of drive-managed SMR, including type, structure, and size of the persistent cache, type of cleaning algorithm, type of block mapping, and size of shingled bands. The hardware component of Skylight tracks drive head movements, using a high-speed camera through an observation window drilled through the cover of the drive. These observations confirm inferences from measurements, and resolve ambiguities which arise from use of performance measurements alone. We show the generality and efficacy of our techniques by running them on top of emulated and real SMR drives, discovering valuable performance-relevant details.
