Indirection systems for shingled-recording disk drives

  • Authors:
  • Yuval Cassuto;Marco A. A. Sanvido;Cyril Guyot;David R. Hall;Zvonimir Z. Bandic

  • Affiliations:
  • Hitachi Global Storage Technologies, San Jose Research Center 3403 Yerba Buena Road San Jose, California 95135 USA;Hitachi Global Storage Technologies, San Jose Research Center 3403 Yerba Buena Road San Jose, California 95135 USA;Hitachi Global Storage Technologies, San Jose Research Center 3403 Yerba Buena Road San Jose, California 95135 USA;Hitachi Global Storage Technologies, Advanced Magnetic Recording Laboratory 3605 Hwy 52 N Rochester, Minnesota 55901 USA;Hitachi Global Storage Technologies, San Jose Research Center 3403 Yerba Buena Road San Jose, California 95135 USA

  • Venue:
  • MSST '10 Proceedings of the 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST)
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Shingled magnetic recording is a promising technology to increase the capacity of hard-disk drives with no significant cost impact. Its main drawback is that random-write access to the disk is restricted due to overlap in the layout of data tracks. For computing and storage systems to enjoy the increased capacity, it is necessary to mitigate these access restrictions, and present a storage device that serves unrestricted read/write requests with adequate performance. This paper proposes two different indirection systems to mask access restrictions and optimize performance. The first one is a diskcache based architecture that provides unrestricted access with manageable drop in performance. A second, more complex indirection system, utilizes a new storage unit called S-block. It is shown that the S-block architecture allows good sustained random-write performance, a point where the disk-cache architecture fails. The organization and algorithms of both architectures are specified in detail. Each was implemented and simulated as a discrete-event simulation, mimicking its operation on real storage devices. For the performance evaluation both synthetic workloads and traces from real workloads were used.