Parity logging overcoming the small write problem in redundant disk arrays

摘要: Parity encoded redundant disk arrays provide highly reliable, cost effective secondary storage with high performance for read accesses and large write accesses. Their on small writes, however, is much worse than mirrored disks—the traditional, but expensive organization storage. Unfortunately, writes are a substantial portion of the I/O workload many important, demanding applications such as on-line transaction processing. This paper presents parity logging, novel solution to problem arrays. logging applies journalling techniques substantially reduce writes. We detailed analysis competing schemes—mirroring, floating storage, RAID level 5— verify these models by simulation. provides competitive mirroring, best alternative single failure tolerating array organizations. However, its overhead close minimum offered 5. Finally, can exploit data caching more effectively all three approaches.