Reliability Study of Coding Schemes for Wide-Area Distributed Storage Systems

Author

Peter, Kathrin

Author_Institution

Comput. Sci. Res., Zuse Inst. Berlin (TIB), Berlin, Germany

fYear

2011

fDate

9-11 Feb. 2011

Firstpage

19

Lastpage

23

Abstract

Distributed storage systems comprise a large number of commodity hardware distributed across several data centers. Even in the presence of failures (permanent failures) the system should provide reliable storage. While replication has advantages because of its simplicity there exist coding techniques that provide adaptable reliability properties with an optimal redundancy ratio at the same time e.g. MDS (maximum distance separable) erasure codes. The coding and distribution scheme influences the prospective storage reliability. In this paper we present reliability models for erasure coding and replication techniques especially for their application in wide-area storage systems. Furthermore we utilize these models to quantify the reliability properties of concrete data storage scenarios.

Keywords

computer centres; distributed processing; fault tolerant computing; forward error correction; redundancy; software reliability; storage management; system recovery; MDS erasure code; coding technique; commodity hardware; data center; maximum distance separability; optimal redundancy ratio; storage reliability; system failure; wide area distributed storage system; Data models; Encoding; Maintenance engineering; Markov processes; Redundancy; Servers; distributed data storage; erasure codes; reliability;

fLanguage

English

Publisher

ieee

Conference_Titel

Parallel, Distributed and Network-Based Processing (PDP), 2011 19th Euromicro International Conference on

Conference_Location

Ayia Napa

ISSN

1066-6192

Print_ISBN

978-1-4244-9682-2

Type

conf

DOI

10.1109/PDP.2011.70

Filename

5738977