Expandable Fractional Repetition Codes for Distributed Storage Systems

Authors

Image provided by Bing Zhu
Bing
Zhu
Central South University
Profile
Shigeng
Zhang
Central South University
Profile
Weiping
Wang
Central South University

Abstract

Modern distributed storage systems are increasingly implementing erasure codes to obtain better storage performance. In such systems, it is desirable to regenerate a failed storage node in a cost-effective manner since node failures occur frequently in real-world storage networks. Fractional repetition (FR) codes are a special class of regenerating codes that enable efficient recovery of failed storage nodes. In this paper, we introduce expandable FR codes, wherein both the number of storage nodes and the capacity of each node in the storage systems can be readily expanded. We present explicit constructions of expandable FR codes by applying two families of combinatorial structures called embeddable quasi-residual designs and extendible t-designs. Moreover, we study the property of constructed codes for some special scenarios.

Paper Manuscript