DocumentCode
23069
Title
Two Blocks Are Enough: On the Feasibility of Using Network Coding to Ameliorate the Content Availability of BitTorrent Swarms
Author
Qing-Chao Cai ; Kwok-Tung Lo
Author_Institution
Dept. of Electron. & Inf. Eng., Hong Kong Polytech. Univ., Kowloon, China
Volume
24
Issue
8
fYear
2013
fDate
Aug. 2013
Firstpage
1682
Lastpage
1694
Abstract
In this paper, we conduct an in-depth study on the feasibility of using network coding to ameliorate the content availability of BitTorrent swarms. We first perform mathematical analysis on the potential improvement in the content availability and bandwidth utilization induced by two existing network coding schemes. It is found that these two coding schemes either incur a very high coding complexity and disk operation overhead or cannot effectively leverage the potential of improving the content availability. In this regard, we propose a simple sparse network coding scheme in which both the drawbacks mentioned before are precluded. To accommodate the proposed coding scheme into BitTorrent, a new block scheduling algorithm is also developed based on the original rarest-first block scheduling policy of BitTorrent. Through extensive simulations and performance evaluations, we show that the proposed coding scheme is very effective in terms of improving the content availability of BitTorrent swarms when compared with some existing methods.
Keywords
computer network reliability; mathematical analysis; network coding; peer-to-peer computing; scheduling; BitTorrent swarms; bandwidth utilization; block scheduling algorithm; coding complexity; content availability; disk operation overhead; mathematical analysis; peer-to-peer networks; rarest-first block scheduling policy; sparse network coding scheme; Availability; Bandwidth; Complexity theory; Encoding; Network coding; Peer to peer computing; Vectors; Availability; Bandwidth; BitTorrent; Complexity theory; Encoding; Network coding; Peer to peer computing; Peer-to-peer networks; Vectors; network coding; performance analysis;
fLanguage
English
Journal_Title
Parallel and Distributed Systems, IEEE Transactions on
Publisher
ieee
ISSN
1045-9219
Type
jour
DOI
10.1109/TPDS.2012.211
Filename
6235956
Link To Document