The Community for Technology Leaders
2013 43rd Annual IEEE/IFIP Conference on Dependable Systems and Networks Workshop (DSN-W) (2013)
Budapest, Hungary
June 24, 2013 to June 27, 2013
ISSN: 2325-6648
ISBN: 978-1-4799-0181-4
pp: 1-7
Chris X. Cai , Department of Computer Science, University of Illinois at Urbana-Champaign, USA
Cristina L. Abad , Department of Computer Science, University of Illinois at Urbana-Champaign, USA
Roy H. Campbell , Department of Computer Science, University of Illinois at Urbana-Champaign, USA
ABSTRACT
Distributed storage systems often use replication for improved availability, performance and scalability. In this paper, we consider the case of using file replication to improve the availability of different classes of files, where some classes are more “important” than others and more replicas are created for them to achieve improved availability. The question we attempt to answer is: given a fixed storage budget for storing replicas, what is the number of replicas of each file class to create to maximize the (weighted) overall availability of files? We present our work towards a replica number computation algorithm that takes into account a storage budget, a configurable maximum expected percentage of failed nodes, and weights for different file classes. Simulation results show that our algorithm is able to improve the availability of the prioritized files with higher weights, has a low computation time and can utilize storage space efficiently when total storage space scales to a large size.
INDEX TERMS
budget, storage system, replication, availability, optimization
CITATION

C. X. Cai, C. L. Abad and R. H. Campbell, "Storage-efficient data replica number computation for multi-level priority data in distributed storage systems," 2013 43rd Annual IEEE/IFIP Conference on Dependable Systems and Networks Workshop (DSN-W), Budapest, Hungary, 2013, pp. 1-7.
doi:10.1109/DSNW.2013.6615512
91 ms
(Ver 3.3 (11022016))