Loading…

Reducing Read Latency of Shingled Magnetic Recording With Severe Intertrack Interference Using Transparent Lossless Data Compression

With the distinct advantage of retaining conventional head and media, the emerging shingled recording technology improves areal storage density through intentional track overlapping that nevertheless introduces severe intertrack interference (ITI). An economically tenable option for shingled drives...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on magnetics 2013-08, Vol.49 (8), p.4761-4767
Main Authors: Venkataraman, Kalyana Sundaram, Dong, Guiqiang, Xie, Ningde, Zhang, Tong
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the distinct advantage of retaining conventional head and media, the emerging shingled recording technology improves areal storage density through intentional track overlapping that nevertheless introduces severe intertrack interference (ITI). An economically tenable option for shingled drives is to utilize a single read head. As we continue to increase its areal storage density, there will be a higher probability that a read operation demands reading multiple adjacent tracks for explicit ITI compensation. This directly results in a significant read latency penalty when using a single read head. In this work, we propose a simple design strategy to reduce such ITI-induced read latency penalty. If a sector of user data can be compressed to a certain extent, it will leave more storage space for coding redundancy and, hence, opportunistically enable the use of a stronger-than-normal error correction code (ECC). The stronger ECC can accordingly reduce the probability of reading multiple adjacent tracks for explicit ITI compensation. Beyond a simple intrasector compression, the absence of the update-in-place feature in shingled recording makes it feasible to apply lossless compression across multiple consecutive sectors. This can further improve the compression efficiency and, hence, reduce the probability of reading multiple adjacent tracks. We carried out simulations that successfully demonstrate the effectiveness of the proposed design strategies on reducing the read latency penalty caused by severe ITI in shingled recording.
ISSN:0018-9464
1941-0069
DOI:10.1109/TMAG.2013.2242086