Floating parity and data disk arrays

Abstract

A disk array is a set of disk drives (and controller) which can automatically recover data when one or more disk drives in the set fail. One method used by disk arrays to achieve high availability at lower cost than mirroring is a parity technique. This paper considers disk arrays that use the parity technique. The main drawback of such arrays is that they need four disk accesses to update a data block-two to read old data and parity, and two to write new data and parity. We describe four new methods to improve the update performance of disk arrays that use the parity technique from four accesses to three and, in some cases, to two. All our schemes sacrifice disk storage efficiency for improved update performance by relaxing the requirement that the modified data and parity blocks be written back into their original locations. Our best technique, called floating parity track, achieves much improved update performance while using only 1% more disk space than traditional arrays. © 1993 Academic Press, Inc.