Paper Info
Title
Practical Single Node Failure Recovery Using Fractional Repetition Codes In Data Centers
Abstract
Node failures in distributed storage systems are becoming a critical issue, and many erasure codes are designed to handle such failures. The purpose of this paper is to evaluate fractional repetition (FR) codes, a class of regenerating codes for distributed storage systems, as a practical solution. FR codes consist of a concatenation of an outer maximum distance separable (MDS) code and an inner fractional repetition code that splits the data into several blocks and stores multiple replicas of each on different nodes in the system. We model the problem as an integer linear programming problem that uses modified versions of the fractional repetition code by allowing different block sizes, and minimizes the recovery cost of all single node failure scenarios. The contribution of this work is three fold: We generate an optimized block distribution schema that minimizes the total system repair cost in a data center and we present a full recovery plan for the system. In addition, we account for new-comer blocks and allocate them to nodes with minimal computations and without changing the original optimal schema. This makes our work practical to apply. Hence, a practical solution for node failures is presented by using a self-designed genetic algorithm that searches within the feasible solution space. We show that our results are close to optimal.
Year
DOI
Venue
2016
10.1109/AINA.2016.36
IEEE 30TH INTERNATIONAL CONFERENCE ON ADVANCED INFORMATION NETWORKING AND APPLICATIONS IEEE AINA 2016
Keywords
Field
DocType
distributed storage systems, FR codes, failure recovery, genetic algorithms
Repetition code,Computer science,Distributed data store,Computer network,Algorithm,Integer programming,Bandwidth (signal processing),Concatenation,Linear code,Erasure code,Genetic algorithm,Distributed computing
Conference
ISSN
Citations 
PageRank 
1550-445X
1
0.37
References 
Authors
9
3
Name
Order
Citations
PageRank
May Itani141.09
sanaa sharafeddine214523.26
Islam Elkabbani320.71