Title :
STAR : An Efficient Coding Scheme for Correcting Triple Storage Node Failures
Author :
Huang, Cheng ; Xu, Lihao
Author_Institution :
One Microsoft Way, Microsoft Res., Redmond, WA
fDate :
7/1/2008 12:00:00 AM
Abstract :
Proper data placement schemes based on erasure correcting codes are one of the most important components for a highly available data storage system. For such schemes, low decoding complexity for correcting (or recovering) storage node failures is essential for practical systems. In this paper, we describe a new coding scheme, which we call the STAR code, for correcting triple storage node failures (erasures). The STAR code is an extension of the double-erasure-correcting EVENODD code and a modification of the generalized triple-erasure-correcting EVENODD code. The STAR code is an Maximum Distance Separable (MDS) code and thus is optimal in terms of node failure recovery capability for a given data redundancy. We provide detailed STAR code decoding algorithms for correcting various triple node failures. We show that the decoding complexity of the STAR code is much lower than those of existing comparable codes; thus, the STAR code is practically very meaningful for storage systems that need higher reliability.
Keywords :
computational complexity; decoding; failure analysis; storage management; STAR code; data placement scheme; data redundancy; data storage system; double-erasure-correcting EVENODD code; erasure correcting code; generalized triple-erasure-correcting EVENODD code; low decoding complexity; maximum distance separable code; triple storage node failure recovery; Availability; Data storage systems; Decoding; Error correction; File systems; Information retrieval; Information systems; Large-scale systems; Redundancy; Storage area networks; codes; error control; fault tolerance; high availability; storage systems.;
Journal_Title :
Computers, IEEE Transactions on
DOI :
10.1109/TC.2007.70830