Replicated erasure codes for storage and repair-traffic efficiency

Friedman, Roy; Kan‐Tor, Yoav; Kantor, Amir

doi:10.1109/p2p.2014.6934310

Cited by 18 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The amount of storage affects the number of chunk erasures in the system and the repair degree indicates the number of chunks sent in order to repair one erased chunk. Therefore, a repair efficient scheme must minimize both [13].…”

Section: Resultsmentioning

confidence: 99%

Efficient Data Administration

Mishra¹,

Patel²,

Pateriya³

2016

IJCA

View full text Add to dashboard Cite

Cloud Computing is a novel computing paradigm which is recognized as an arbitrary to traditional reference technology right to its intrinsic resource-sharing and low-maintenance characteristics. One of the virtually fundamental services offered by CSPs (Cloud Service Providers) is cloud storage. To increasing reliability and efficiency of data storage in the cloud the technique used is replication but its drawback is data loss and higher space consumption. One way to increase the data reliability and reducing the storage space in the cloud is Erasure Coding. In Erasure Coding, the data is fragmented and further encoded mutually into data pieces and stored in different locations. The arbitrary benefit of the Erasure Coding is that the corrupted data can be absolutely reconstructed into separate information. Erasure code comprises of two coding techniques regenerating code and locally repairable code. Regenerating Code is used for balancing storage space and its bandwidth. The Locally repairable code is the technique used to overcome the Disk I/O overhead in the Cloud Storage. But applying erasure code in cloud storage increases access time. So this paper explored the storage space efficiency of erasure codes and the repair traffic efficiency of replication. As a new area of research in replication and erasure coding technique can be combined using for data storage in the cloud for enhancing its overall efficiency.

show abstract

Section: Resultsmentioning

confidence: 99%

Efficient Data Administration

Mishra¹,

Patel²,

Pateriya³

2016

IJCA

View full text Add to dashboard Cite

show abstract

“…In other words, DRESS codes enjoy the repair efficiency of the replication scheme, and are suitable for high-churn environments with frequent node joins/leaves (e.g., peer-to-peer distributed storage systems). Friedman et al [34] evaluated the efficiency of DRESS codes in practical peer-to-peer environments, and showed that the concatenated scheme can achieve better features than each of the methods separately. Moreover, Itani et al [35], [36] investigated the optimal repair cost of DRESS code based data storage systems, where they proposed efficient genetic algorithms for the single node failure and multiple node failure scenarios respectively.…”

Section: B Dress Code and Fractional Repetition Codementioning

confidence: 99%

On the Duality and File Size Hierarchy of Fractional Repetition Codes

Zhu

Shum

2018

The Computer Journal

View full text Add to dashboard Cite

Distributed storage systems that deploy erasure codes can provide better features such as lower storage overhead and higher data reliability. In this paper, we focus on fractional repetition (FR) codes, which are a class of storage codes characterized by the features of uncoded exact repair and minimum repair bandwidth. We study the duality of FR codes, and investigate the relationship between the supported file size of an FR code and its dual code. Based on the established relationship, we derive an improved dual bound on the supported file size of FR codes. We further show that FR codes constructed from t-designs are optimal when the size of the stored file is sufficiently large. Moreover, we present the tensor product technique for combining FR codes, and elaborate on the file size hierarchy of resulting codes.

show abstract

“…In order to avoid the above dichotomy and offer a more flexible design, replicated erasure codes have been proposed [8]. In the latter, each of the p + q chunks may be replicated r times.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, we investigate the fundamental problem of expected data persistency of replicated erasure codes when the storage nodes permanently leave the system and erase their locally stored data. This study is related and motivated by the work of [8]. Namely, the general family of redundancy schemes for distributed storage systems, called replicated erasure codes was introduced in [8].…”

Section: Introductionmentioning

confidence: 99%