Multi-Rack Regenerating Codes for Hierarchical Distributed Storage Systems

Qu, Shan; Liu, Yu; Zhang, Jinbei; Cao, Haiwen; Wang, Xinbing

doi:10.1109/icc.2018.8422112

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A rack-aware setting that also considers local recovery from node failures are codes for multi-rack distributed storage [27], [28]. There, a small number of nodes can be repaired/regenerated locally and failure patterns for which this is not possible are repaired by contacting other racks in addition to the surviving local nodes.…”

Section: Introductionmentioning

confidence: 99%

“…Similar to RRCs, it is assumed that the contacted helper racks can process the data of the nodes within the rack and that the communication between racks is more costly than within a rack. Along with an information-theoretic bound, [28] presents a construction for the case of a efficient local repair of a single node failure. The minimization of the cross-rack repair bandwidth is stated as an open problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Partial MDS Codes with Regeneration

Holzbaur¹,

Puchinger²,

Yaakobi³

et al. 2020

Preprint

View full text Add to dashboard Cite

Partial MDS (PMDS) and sector-disk (SD) codes are classes of erasure correcting codes that combine locality with strong erasure correction capabilities. We construct PMDS and SD codes where each local code is a bandwidth-optimal regenerating MDS code. In the event of a node failure, these codes reduce both, the number of servers that have to be contacted as well as the amount of network traffic required for the repair process. The constructions require significantly smaller field size than the only other construction known in literature. Further, we present a PMDS code construction that allows for efficient repair for patterns of node failures that exceed the local erasure correction capability of the code and thereby invoke repair across different local groups.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%