On the Effectiveness of Recoding-based Repair in Network Coded Distributed Storage

Linear network coding Erasure Distributed data store Erasure code
DOI: 10.3311/ppee.9377 Publication Date: 2017-01-31T17:06:03Z
ABSTRACT
High capacity storage systems distribute files across several devices (nodes) and apply an erasure code to meet availability reliability requirements. Since can lose network connectivity or fail permanently, a dynamic repair mechanism must be put in place. In such cases new recovery node gets connected given subset of the operating nodes receives part stored data. The objective this paper is investigate data survival for Random Linear Network Coding (RLNC) as function topology communication overhead, defined by number connections transmitted packets node, respectively. includes two main contributions. First, sufficient set conditions quasi-infinite longevity derived. Second, comparison using experimental results shows that RLNC up 50% more effective than traditional codes like Reed-Solomon.
SUPPLEMENTAL MATERIAL
Coming soon ....
REFERENCES (0)
CITATIONS (2)
EXTERNAL LINKS
PlumX Metrics
RECOMMENDATIONS
FAIR ASSESSMENT
Coming soon ....
JUPYTER LAB
Coming soon ....