2014
DOI: 10.1145/2560013
|View full text |Cite
|
Sign up to set email alerts
|

Sector-Disk (SD) Erasure Codes for Mixed Failure Modes in RAID Systems

Abstract: Traditionally, when storage systems employ erasure codes, they are designed to tolerate the failures of entire disks. However, the most common types of failures are latent sector failures, which only affect individual disk sectors, and block failures which arise through wear on SSD's. This paper introduces SD codes, which are designed to tolerate combinations of disk and sector failures. As such, they consume far less storage resources than traditional erasure codes. We specify the codes with enough detail for… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
76
0

Year Published

2014
2014
2021
2021

Publication Types

Select...
4
2
2

Relationship

1
7

Authors

Journals

citations
Cited by 68 publications
(76 citation statements)
references
References 27 publications
0
76
0
Order By: Relevance
“…However, these codes have to dedicate two or more drives to redundancy. To improve space efficiency, a series of strong erasure codes were developed to recover drive failures and sector faults simultaneously, such as PMDS codes in [7], SD codes in [8] and STAIR codes in [9]. However, these three codes have a significant update penalty and are only appropriate for storage systems that have limited updates.…”
Section: Related Researchmentioning
confidence: 99%
See 1 more Smart Citation
“…However, these codes have to dedicate two or more drives to redundancy. To improve space efficiency, a series of strong erasure codes were developed to recover drive failures and sector faults simultaneously, such as PMDS codes in [7], SD codes in [8] and STAIR codes in [9]. However, these three codes have a significant update penalty and are only appropriate for storage systems that have limited updates.…”
Section: Related Researchmentioning
confidence: 99%
“…The RAID-6 scheme is based on the array codes in [6]. The parameters of SD-codes in [8] are n ¼ 8, m ¼ 1, s ¼ 3, r ¼ 4. The ASPC scheme is the lifespan-aware adaptive SPC scheme and its stripe size changes from 256 to 8 [13].…”
Section: Reliability Analysismentioning
confidence: 99%
“…Constructions of (1;2) SD codes were given in [1] and of (2;2) codes in [3]. These constructions are also summarized in [11] and the construction of (3;2) SD codes was verified for all r, n in GF(2 8 ) and for r, n 24 in GF(2 16 ). Hence, our results generalize those constructions.…”
Section: Pmds and Sdmentioning
confidence: 99%
“…Normally, these arrays are protected using the well known architectures known as Redundant Arrays of Independent Disks (RAID) [5]. Recent work has explored two types of erasure codes that extend RAID and are tailored for these scenarios: Partial-MDS (PMDS) codes and Sector-Disk (SD) codes [2], [3], [11], [12].…”
Section: Introductionmentioning
confidence: 99%
“…However, it remains a hard work on large scale system. The newly proposed the sector-disk codes [14,15], and Stair code [16] still facing the hard problem of high computational complexity in Galois field.…”
Section: Introductionmentioning
confidence: 99%