Matrix-Stripe-Cache-Based Contiguity Transform for Fragmented Writes in RAID-5

Abstract

Given that contiguous reads and writes between a cache and a disk outperform fragmented reads and writes, fragmented reads and writes are forcefully transformed into contiguous reads and writes via a proposed matrix stripe cachebased contiguity transform (MSC-CT) method, which employs a rule of consistency for data integrity at the block level, and a rule of performance that ensures no performance degradation. MSC-CT performs for reads and writes, both of which are produced by write requests from a host, as a write request from a host employs reads for parity-update and writes to disks in a RAID-5 array. MSC-CT is compatible with existing disk technologies. The proposed implementation in a Linux kernel delivers a peak throughput that is 3.2 times higher than a case without MSC-CT on representative workloads. The results demonstrate that MSC-CT is extremely simple to implement, has low overhead, and is ideally suited for RAID controllers not only for random writes but also for sequential writes in various realistic scenarios.

A Fast Parity Resynchronization Scheme for Small and Mid-sized RAIDs

“…LORE는 여러 선행 연구문서에 소개 되었다 [17], [18], [19]. 이 레이드 드라이버는 Multiple Device (MD) [20]와 같은 소프트웨어 레이드이며, 리눅스 커 널 2.6.35 x86_64에서 구현되었다.…”

An Asynchronous Striping-Aware Readahead Framework for Disk Arrays in Linux

“…Other studies on disk arrays have focused on reliability [17]- [19] of redundant disk arrays of independent disks (RAID), performance by devising variants [20]- [22] of RAID, cache [6], [14], [23], [24], data deduplication [25], [26], and storage virtualization [27]. The present paper deals with the very significant problem that performance degradation occurs if sequential prefetching is incorporated with striped disk arrays such as RAID-0, RAID-5, RAID-6, RAID-10, and RAID-50 that exploit striped data placement.…”

Arrangement of multi-dimensional scalable video data for heterogeneous clients

“…However, the independency of disks is more important than their parallelism for concurrent reads of large numbers of processes in striped disk arrays, whereas parallelism is only significant when the number of concurrent accesses is roughly less than the number of member disks [2,3].…”