Performance of Two-Disk Failure-Tolerant Disk Arrays

Thomasian, Alexander; Fu, Gang; Han, Chunqi

doi:10.1109/tc.2007.1041

Cited by 45 publications

(62 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With RAID reconstruction, disk arrays either run in a degraded (not yielding to other I/O requests) or polite mode. In a degraded mode, busy disk arrays suffer a substantial performance hit when crippled with multiple failed disks [29,22]. This degradation is even more significant on parallel file systems, as files are striped over multiple disk arrays and large sequential accesses are common.…”

Section: Related Workmentioning

confidence: 99%

Improving the availability of supercomputer job input data using temporal replication

Wang

Zhang

et al. 2009

Comp. Sci. Res. Dev.

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Improving the availability of supercomputer job input data using temporal replication

Wang

Zhang

et al. 2009

Comp. Sci. Res. Dev.

View full text Add to dashboard Cite

show abstract

“…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.…”

Section: Prefetching Problem In Striped Arraysmentioning

confidence: 99%

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

Baek

2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYDisk arrays and prefetching schemes are used to mitigate the performance gap between main memory and disks. This paper presents a new problem that arises if prefetching schemes that are widely used in operation systems are applied to disk arrays. The key point of the problem is that block address space from the viewpoint of the host is contiguous but from that of the disk array it is discontiguous and thus more disk accesses than expected are required. This paper presents two ways to resolve the problem that arises from the Linux readahead framework. The proposed scheme prevents a readahead window from being split into multiple requests from the viewpoint of the disk array but not from the viewpoint of the host thereby reducing disk head movements. In addition, it outperforms the prior work by adopting an asynchronous solution, improving performance for fragmented files, eliminating readahead size restriction, and improving disk parallelism. We implemented the proposed scheme and integrated it with Linux. Our experiment shows that the solution significantly improved the original Linux readahead framework when a storage server processes multiple concurrent requests.

show abstract

“…Processing reads and writes of data and parity blocks as separate requests, with the XOR carried out at the Disk Array Controller (DAC), provides higher data integrity, but increases disk utilization [25]. In effect we have two fork-join requests, firstly to read data and parity blocks and secondly to write them.…”

Section: Raid5 Rotated Parity Arraymentioning

confidence: 99%

“…The three differ in their computational complexity (number of XORs) [5,8,28]. The performance of 2DFT arrays from the viewpoint of disk accesses is analyzed in [21,25]. The load increase in RAID6 is three-fold for two disk failures when all disk requests are reads.…”

Section: Raid5 Rotated Parity Arraymentioning

confidence: 99%

RAID level selection for heterogeneous disk arrays

Thomasian¹,

2010

Cluster Comput

Self Cite

View full text Add to dashboard Cite

Heterogeneous Disk Arrays (HDAs) allow resource sharing of their hardware by multiple RAID levels. RAID1 (mirrored disks) and RAID5 (distributed parity arrays) are the two RAID levels considered in this study. They are both single disk failure tolerant (1DFT), but differ significantly in their efficiency in processing database workloads. The goal of the study is to maximize the number of Virtual Array (VA) allocations in HDA. We develop an analysis to estimate the load per VA based on a few parameters: the fraction of accesses to small versus large blocks and the fraction of updates versus reads. A VA is allocated according to the RAID level, which minimizes the anticipated load based on input parameters. Operation in normal and degraded mode is considered for comparison purposes, but in fact allocations are carried out using the higher load in degraded mode to ensure that single disk failures will not result in overload. We report on parametric studies to gain insight into circumstances leading to a RAID1 or RAID5 classification. An allocation experiment with a synthetic workload is used to demonstrate the superiority of HDA with respect to purely RAID1 or RAID5 disk arrays. This analytic study can be extended to 2DFT arrays, namely RAID6 versus 3-way replication.

show abstract

Performance of Two-Disk Failure-Tolerant Disk Arrays

Cited by 45 publications

References 29 publications

Improving the availability of supercomputer job input data using temporal replication

Improving the availability of supercomputer job input data using temporal replication

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

RAID level selection for heterogeneous disk arrays

Contact Info

Product

Resources

About