Using Torrent Inflation to Efficiently Serve the Long Tail in Peer-assisted Content Delivery Systems

Select |


Carlsson, Niklas; Eager, Derek; Mahanti, Anirban


Conference Material

IFIP Networking 200X (Networking 200X)

Chennai, INDIA

pp. 1-14

A peer-assisted content delivery system uses the upload bandwidth of its clients to assist in delivery of popular content. In peer-assisted systems using a BitTorrent-like protocol, a content delivery server seeds the offered files, and active torrents form when multiple clients make closely-spaced requests for the same content. Scalability is achieved in the sense of being able to accommodate arbitrarily high request rates for individual files. Scalability with respect to the number of files, however, may be much more difficult to achieve, owing to a ``long tail'' of lukewarm or cold files for which the server may need to assume most or all of the delivery cost. This paper first addresses the question of how best to allocate server resources among multiple active torrents. We then propose new content delivery policies that use some of the available upload bandwidth from currently downloading clients to ``inflate'' torrents for files that would otherwise require substantial server bandwidth. Our performance results show that, in many cases, torrent inflation enables the ``long tail'' to be served with greatly improved efficiency. Finally, a new ``taxation'' policy is proposed in which some fraction of peer upload bandwidth is prioritized for use in other torrents. The proposed policy is shown to yield large reductions in download times for lukewarm/cold files, when sufficient ``tax'' bandwidth is available, at the cost of modestly increased download times for clients downloading popular files.



Carlsson, Niklas; Eager, Derek; Mahanti, Anirban. Using Torrent Inflation to Efficiently Serve the Long Tail in Peer-assisted Content Delivery Systems.[Conference Material]. Springer; 2011-05-10. <a href="" target="_blank"></a>

Loading citation data...

Citation counts
(Requires subscription to view)