Distributed Data Replenishment

Author

Nguyen, Kien ; Nguyen, Thinh ; Kovchegov, Yevgeniy ; Le, Viet

Author_Institution

EdgeCast, Inc., Santa Monica, CA, USA

Volume

24

Issue

2

fYear

2013

fDate

Feb. 2013

Firstpage

275

Lastpage

287

Abstract

We propose a distributed data replenishment mechanism for some distributed peer-to-peer-based storage systems that automates the process of maintaining a sufficient level of data redundancy to ensure the availability of data in presence of peer departures and failures. The dynamics of peers entering and leaving the network are modeled as a stochastic process. A novel analytical time-backward technique is proposed to bound the expected time for a piece of data to remain in P2P systems. Both theoretical and simulation results are in agreement, indicating that the data replenishment via random linear network coding (RLNC) outperforms other popular strategies. Specifically, we show that the expected time for a piece of data to remain in a P2P system, the longer the better, is exponential in the number of peers used to store the data for the RLNC-based strategy, while they are quadratic for other strategies.

Keywords

data handling; failure analysis; peer-to-peer computing; stochastic processes; storage management; P2P system; RLNC-based strategy; analytical time-backward technique; data availability; data redundancy; data storage; distributed data replenishment; distributed peer-to-peer-based storage system; entering peers; failure; leaving peers; peer departure; random linear network coding; stochastic process; Bandwidth; Distributed databases; Games; Maintenance engineering; Network coding; Peer to peer computing; Redundancy; Stochastic process; absorption time; distributed storage; network coding;

fLanguage

English

Journal_Title

Parallel and Distributed Systems, IEEE Transactions on

Publisher

ieee

ISSN

1045-9219

Type

jour

DOI

10.1109/TPDS.2012.115

Filename

6178245