Title :
Design and modeling of clustered RAID
Author :
Merchant, A. ; Yu, P.S.
Author_Institution :
NEC USA, Princeton, NJ, USA
Abstract :
A redundant array of independent disks (RAID) consisting of G disks provides protection against single disk failures by adding one parity block for each G-1 data blocks. In a clustered RAID, the G data/parity blocks are distributed over a cluster of C disks, C>G, thus reducing the additional load on each disk due to a single disk failure. The authors present a fast algorithm for distributing parity groups of size G over C disks. They create mappings for each parity group based on almost-random permutations. An analytical model is constructed to predict recovery time and read/write performance. The analysis shows that the clustered RAID is significantly more tolerant of disk failure than the basic RAID scheme. Both recovery time and performance degradation during recovery are substantially reduced in the clustered RAID.<>
Keywords :
fault tolerant computing; magnetic disc storage; G-1 data blocks; almost-random permutations; analytical model; clustered RAID; data/parity blocks; disk failure; mappings; modeling; performance degradation; read/write performance; recovery time; redundant array of independent disks; single disk failures; Costs; Degradation; Failure analysis; Laboratories; Mirrors; National electric code; Performance gain; Predictive models; Protection; Throughput;
Conference_Titel :
Fault-Tolerant Computing, 1992. FTCS-22. Digest of Papers., Twenty-Second International Symposium on
Conference_Location :
Boston, MA, USA
Print_ISBN :
0-8186-2875-8
DOI :
10.1109/FTCS.1992.243606