TY - GEN
T1 - Skylight—a window on shingled disk operation
AU - Aghayev, Abutalib
AU - Desnoyers, Peter
N1 - Funding Information:
This work was supported by NetApp, and NSF award CNS-1149232. We thank the anonymous reviewers, Remzi Arpaci-Dusseau, Tim Feldman, and our shepherd, Kimberly Keeton, for their feedback.
PY - 2015
Y1 - 2015
N2 - We introduce Skylight, a novel methodology that combines software and hardware techniques to reverse engineer key properties of drive-managed Shingled Magnetic Recording (SMR) drives. The software part of Skylight measures the 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 bands. The hardware part of Skylight tracks drive head movements during these tests, using a high-speed camera through an observation window drilled through the cover of the drive. These observations not only confirm inferences from measurements, but resolve ambiguities that arise from the use of latency measurements alone. We show the generality and efficacy of our techniques by running them on top of three emulated and two real SMR drives, discovering valuable performance-relevant details of the behavior of the real SMR drives.
AB - We introduce Skylight, a novel methodology that combines software and hardware techniques to reverse engineer key properties of drive-managed Shingled Magnetic Recording (SMR) drives. The software part of Skylight measures the 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 bands. The hardware part of Skylight tracks drive head movements during these tests, using a high-speed camera through an observation window drilled through the cover of the drive. These observations not only confirm inferences from measurements, but resolve ambiguities that arise from the use of latency measurements alone. We show the generality and efficacy of our techniques by running them on top of three emulated and two real SMR drives, discovering valuable performance-relevant details of the behavior of the real SMR drives.
UR - http://www.scopus.com/inward/record.url?scp=85077029313&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077029313&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85077029313
T3 - Proceedings of the 13th USENIX Conference on File and Storage Technologies, FAST 2015
SP - 135
EP - 149
BT - Proceedings of the 13th USENIX Conference on File and Storage Technologies, FAST 2015
PB - USENIX Association
T2 - 13th USENIX Conference on File and Storage Technologies, FAST 2015
Y2 - 16 February 2015 through 19 February 2015
ER -