STAR : An Efficient Coding Scheme for Correcting Triple Storage Node Failures

Huang, Cheng; Xu, Lizhong

doi:10.1109/tc.2007.70830

Cited by 224 publications

(158 citation statements)

References 33 publications

Supporting

Mentioning

156

Contrasting

Unclassified

Order By: Relevance

“…All failures occurred in the data array portion is most difficult to recover, so assuming all failures occur in the data array portion. The core idea of this method is to find valid decoding chains to recover the loss elements on failure nodes, which is similar to the Zig-Zag decoding method [8] but a more concise valid decoding chains searching algorithm.…”

Section: Basic Encoding and Decoding Methodsmentioning

confidence: 99%

“…In the case of m is 8, Figure 5 shows the amount of XOR operations required to store a 100M file when f is from 2 to 50. It is not difficult to see from this figure, the required binary XOR operations to store a 100M file is less than 8 10 13 even when the fault tolerant ability is as high as 50, and all of these operations can be completed by a most common computing node soon. …”

Section: Operational Workloadmentioning

confidence: 99%

“…According to the storage efficiency, array codes can be subdivided into MDS codes and non MDS codes. Among them, 2 fault tolerance codes such as EVENODD codes [6] and X codes [7] , 3 fault tolerance codes such as Star codes [8] and extended X codes [9] are all typical MDS array codes. However, the research work of MDS array codes with higher fault tolerance has not made a breakthrough.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Research on Fault Tolerance Enhancement of Array Erasure Codes

2017

View full text Add to dashboard Cite

Abstract. Array erasure coding technology is one of the most desirable methods to enhance the reliability of storage systems, but fault tolerance is always the bottleneck to the use of array codes. There are several improvement schemes for fault tolerance of array codes now, such as graph theory method, hybrid layout method, and so on. But improvement of the fault tolerance is pretty small, and always cost too much. In view of this, the paper presents a new method to improve fault tolerant ability of array erasure codes. The new method has a highly computing efficiency because all calculations are binary XOR operations, and it is convenient to implement because of its simple construction. Using this new method, we can model a horizontal array code with the optimal updating expenses. Although MDS array codes cannot be modeled by the new method, but storage efficiency can be improved by increasing the strip size. The most important contribution of this paper is that, this new method can construct an array erasure code which has the unconstrained fault tolerant ability in theory.

show abstract

Section: Basic Encoding and Decoding Methodsmentioning

confidence: 99%

Section: Operational Workloadmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Research on Fault Tolerance Enhancement of Array Erasure Codes

2017

View full text Add to dashboard Cite

show abstract

“…Other parity-based redundancy schemes included STAR, HoVer, GRID, and Bˆ, the latter of which typified the tendency of such approaches to focus on the data layout pattern, independent of the number of underlying devices [13,14,18,29]. Typically, these data layouts were subsequently declustered data across homogenous, uniform, devices, and the majority could be classified as variations of low-density parity-codes similar to those used for erasure coding in the communications domain, such as the Luby LT codes, and their Tornado and Raptor variants [16,17,28].…”

Section: Previous Workmentioning

confidence: 99%

Using shared parity disks to improve the reliability of RAID arrays

Pâris

Amer

2009

2009 IEEE 28th International Performance Computing and Communications Conference

View full text Add to dashboard Cite

Abstract-We propose to increase the reliability of RAID level 5 arrays used for storing archival data. First, we identify groups of two or three identical RAID arrays. Second, we add to each group a shared parity disk containing the diagonal parities of their arrays. We show that the new organization can tolerate all double disk failures and between 75 and 89 percent of triple disk failures without incurring any data loss. As a result, the additional parity disk increases the mean time to data loss of the arrays in the group it protects by at least 14,000 percent.

show abstract

“…Because of this storage efficiency, MDS codes are highly favorable, and a lot of research has been done to construct them. Examples of MDS codes are the well known Reed Solomon codes, EVENODD [1], [2], B-code [24], X-code [25], RDP [7], and STAR-code [9]. It is evident that in the case of r erasures, one needs to communicate all the surviving information during the repair process.…”

Section: Introductionmentioning

confidence: 99%

Access Versus Bandwidth in Codes for Storage

Tamo

Wang

Bruck

2014

IEEE Trans. Inform. Theory

View full text Add to dashboard Cite

Maximum distance separable (MDS) codes are widely used in storage systems to protect against disk (node) failures. A node is said to have capacity l over some field F, if it can store that amount of symbols of the field. An (n, k, l) MDS code uses n nodes of capacity l to store k information nodes. The MDS property guarantees the resiliency to any n − k node failures. An optimal bandwidth (resp. optimal access) MDS code communicates (resp. accesses) the minimum amount of data during the repair process of a single failed node. It was shown that this amount equals a fraction of 1/(n − k) of data stored in each node. In previous optimal bandwidth constructions, l scaled polynomially with k in codes with asymptotic rate < 1. Moreover, in constructions with a constant number of parities, i.e. rate approaches 1, l is scaled exponentially w.r.t. k. In this paper, we focus on the later case of constant number of parities n − k = r, and ask the following question: Given the capacity of a node l what is the largest number of information disks k in an optimal bandwidth (resp. access) (k + r, k, l) MDS code. We give an upper bound for the general case, and two tight bounds in the special cases of two important families of codes. Moreover, the bounds show that in some cases optimal-bandwidth code has larger k than optimal-access code, and therefore these two measures are not equivalent.

show abstract

STAR : An Efficient Coding Scheme for Correcting Triple Storage Node Failures

Cited by 224 publications

References 33 publications

Research on Fault Tolerance Enhancement of Array Erasure Codes

Research on Fault Tolerance Enhancement of Array Erasure Codes

Using shared parity disks to improve the reliability of RAID arrays

Access Versus Bandwidth in Codes for Storage

Contact Info

Product

Resources

About