Towards a peer-to-peer bandwidth marketplace

M. Capota; J.A. Pouwelse; D.H.J. Epema

doi:10.1007/978-3-642-45249-9_20

Towards a peer-to-peer bandwidth marketplace

M. Capota, J.A. Pouwelse, D.H.J. Epema

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

4 Citations (Scopus)

1 Downloads (Pure)

Abstract

Peer-to-peer systems are a popular means of transferring files over the Internet, accounting for a third of the upload bandwidth of end users as of 2013. However, recent studies have highlighted that peer-to-peer systems are affected by a lack of balance between the supply and demand of bandwidth. This imbalance stems from the skewed popularity distribution of the files transfered in the system; newly released files may exhibit an undersupply of bandwidth while older ones may exhibit oversupply. In this work, we introduce a bandwidth marketplace for peers, with the aim of aligning supply and demand without the need for human intervention. Peers constantly monitor their performance and gossip with each other about undersupplied files. Peers with idle upload bandwidth that learn about an undersupplied file can autonomously start a special help mode download, with the goal of supplying as much upload bandwidth as possible to the other peers. We present an analytical model of help mode downloading and derive from it bounds for the performance of helper peers. Furthermore, we evaluate a recent existing implementation of help mode in Libtorrent, a popular BitTorrent library. Our tests show that Libtorrent help mode is effective at alleviating undersupply, although its performance relative to our model can be improved.

Original language	English
Title of host publication	Distributed Computing and Networking (15th International Conference, ICDCN 2014, Coimbatore, India, January 4-7, 2014. Proceedings)
Editors	M. Chatterjee, J.N. Cao, K. Kothapalli, S. Rajsbaum
Place of Publication	Berlin
Publisher	Springer
Pages	302-316
ISBN (Print)	978-3-642-45248-2
DOIs	https://doi.org/10.1007/978-3-642-45249-9_20
Publication status	Published - 2014
Event	conference; 15th International Conference on Distributed Computing and Networking; 2014-01-04; 2014-01-07 - Duration: 4 Jan 2014 → 7 Jan 2014

Publication series

Name	Lecture Notes in Computer Science
Volume	8314
ISSN (Print)	0302-9743

Conference

Conference	conference; 15th International Conference on Distributed Computing and Networking; 2014-01-04; 2014-01-07
Period	4/01/14 → 7/01/14
Other	15th International Conference on Distributed Computing and Networking

Access to Document

10.1007/978-3-642-45249-9_20

Cite this

Capota, M., Pouwelse, J. A., & Epema, D. H. J. (2014). Towards a peer-to-peer bandwidth marketplace. In M. Chatterjee, J. N. Cao, K. Kothapalli, & S. Rajsbaum (Eds.), Distributed Computing and Networking (15th International Conference, ICDCN 2014, Coimbatore, India, January 4-7, 2014. Proceedings) (pp. 302-316). (Lecture Notes in Computer Science; Vol. 8314). Springer. https://doi.org/10.1007/978-3-642-45249-9_20

@inproceedings{61c8e9863254486b935ed03e9cb8e3e0,

title = "Towards a peer-to-peer bandwidth marketplace",

abstract = "Peer-to-peer systems are a popular means of transferring files over the Internet, accounting for a third of the upload bandwidth of end users as of 2013. However, recent studies have highlighted that peer-to-peer systems are affected by a lack of balance between the supply and demand of bandwidth. This imbalance stems from the skewed popularity distribution of the files transfered in the system; newly released files may exhibit an undersupply of bandwidth while older ones may exhibit oversupply. In this work, we introduce a bandwidth marketplace for peers, with the aim of aligning supply and demand without the need for human intervention. Peers constantly monitor their performance and gossip with each other about undersupplied files. Peers with idle upload bandwidth that learn about an undersupplied file can autonomously start a special help mode download, with the goal of supplying as much upload bandwidth as possible to the other peers. We present an analytical model of help mode downloading and derive from it bounds for the performance of helper peers. Furthermore, we evaluate a recent existing implementation of help mode in Libtorrent, a popular BitTorrent library. Our tests show that Libtorrent help mode is effective at alleviating undersupply, although its performance relative to our model can be improved.",

author = "M. Capota and J.A. Pouwelse and D.H.J. Epema",

year = "2014",

doi = "10.1007/978-3-642-45249-9_20",

language = "English",

isbn = "978-3-642-45248-2",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "302--316",

editor = "M. Chatterjee and J.N. Cao and K. Kothapalli and S. Rajsbaum",

booktitle = "Distributed Computing and Networking (15th International Conference, ICDCN 2014, Coimbatore, India, January 4-7, 2014. Proceedings)",

address = "Germany",

note = "conference; 15th International Conference on Distributed Computing and Networking; 2014-01-04; 2014-01-07 ; Conference date: 04-01-2014 Through 07-01-2014",

}

Capota, M, Pouwelse, JA & Epema, DHJ 2014, Towards a peer-to-peer bandwidth marketplace. in M Chatterjee, JN Cao, K Kothapalli & S Rajsbaum (eds), Distributed Computing and Networking (15th International Conference, ICDCN 2014, Coimbatore, India, January 4-7, 2014. Proceedings). Lecture Notes in Computer Science, vol. 8314, Springer, Berlin, pp. 302-316, conference; 15th International Conference on Distributed Computing and Networking; 2014-01-04; 2014-01-07, 4/01/14. https://doi.org/10.1007/978-3-642-45249-9_20

Towards a peer-to-peer bandwidth marketplace. / Capota, M.; Pouwelse, J.A.; Epema, D.H.J.
Distributed Computing and Networking (15th International Conference, ICDCN 2014, Coimbatore, India, January 4-7, 2014. Proceedings). ed. / M. Chatterjee; J.N. Cao; K. Kothapalli; S. Rajsbaum. Berlin: Springer, 2014. p. 302-316 (Lecture Notes in Computer Science; Vol. 8314).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Towards a peer-to-peer bandwidth marketplace

AU - Capota, M.

AU - Pouwelse, J.A.

AU - Epema, D.H.J.

PY - 2014

Y1 - 2014

N2 - Peer-to-peer systems are a popular means of transferring files over the Internet, accounting for a third of the upload bandwidth of end users as of 2013. However, recent studies have highlighted that peer-to-peer systems are affected by a lack of balance between the supply and demand of bandwidth. This imbalance stems from the skewed popularity distribution of the files transfered in the system; newly released files may exhibit an undersupply of bandwidth while older ones may exhibit oversupply. In this work, we introduce a bandwidth marketplace for peers, with the aim of aligning supply and demand without the need for human intervention. Peers constantly monitor their performance and gossip with each other about undersupplied files. Peers with idle upload bandwidth that learn about an undersupplied file can autonomously start a special help mode download, with the goal of supplying as much upload bandwidth as possible to the other peers. We present an analytical model of help mode downloading and derive from it bounds for the performance of helper peers. Furthermore, we evaluate a recent existing implementation of help mode in Libtorrent, a popular BitTorrent library. Our tests show that Libtorrent help mode is effective at alleviating undersupply, although its performance relative to our model can be improved.

AB - Peer-to-peer systems are a popular means of transferring files over the Internet, accounting for a third of the upload bandwidth of end users as of 2013. However, recent studies have highlighted that peer-to-peer systems are affected by a lack of balance between the supply and demand of bandwidth. This imbalance stems from the skewed popularity distribution of the files transfered in the system; newly released files may exhibit an undersupply of bandwidth while older ones may exhibit oversupply. In this work, we introduce a bandwidth marketplace for peers, with the aim of aligning supply and demand without the need for human intervention. Peers constantly monitor their performance and gossip with each other about undersupplied files. Peers with idle upload bandwidth that learn about an undersupplied file can autonomously start a special help mode download, with the goal of supplying as much upload bandwidth as possible to the other peers. We present an analytical model of help mode downloading and derive from it bounds for the performance of helper peers. Furthermore, we evaluate a recent existing implementation of help mode in Libtorrent, a popular BitTorrent library. Our tests show that Libtorrent help mode is effective at alleviating undersupply, although its performance relative to our model can be improved.

U2 - 10.1007/978-3-642-45249-9_20

DO - 10.1007/978-3-642-45249-9_20

M3 - Conference contribution

SN - 978-3-642-45248-2

T3 - Lecture Notes in Computer Science

SP - 302

EP - 316

BT - Distributed Computing and Networking (15th International Conference, ICDCN 2014, Coimbatore, India, January 4-7, 2014. Proceedings)

A2 - Chatterjee, M.

A2 - Cao, J.N.

A2 - Kothapalli, K.

A2 - Rajsbaum, S.

PB - Springer

CY - Berlin

T2 - conference; 15th International Conference on Distributed Computing and Networking; 2014-01-04; 2014-01-07

Y2 - 4 January 2014 through 7 January 2014

ER -

Capota M, Pouwelse JA, Epema DHJ. Towards a peer-to-peer bandwidth marketplace. In Chatterjee M, Cao JN, Kothapalli K, Rajsbaum S, editors, Distributed Computing and Networking (15th International Conference, ICDCN 2014, Coimbatore, India, January 4-7, 2014. Proceedings). Berlin: Springer. 2014. p. 302-316. (Lecture Notes in Computer Science). doi: 10.1007/978-3-642-45249-9_20

Towards a peer-to-peer bandwidth marketplace

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this