Experimental Assessment of BitTorrent Completion Time in Heterogeneous TCP/uTP Swarms

  • Claudio Testa
  • Dario Rossi
  • Ashwin Rao
  • Arnaud Legout
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7189)

Abstract

BitTorrent, one of the most widespread used P2P application for file-sharing, recently got rid of TCP by introducing an application-level congestion control protocol named uTP. The aim of this new protocol is to efficiently use the available link capacity, while minimizing its interference with the rest of user traffic (e.g., Web, VoIP and gaming) sharing the same access bottleneck.

In this paper we perform an experimental study of the impact of uTP on the torrent completion time, the metric that better captures the user experience. We run BitTorrent applications in a flash crowd scenario over a dedicated cluster platform, under both homogeneous and heterogeneous swarm population. Experiments show that an all-uTP swarms have shorter torrent download time with respect to all-TCP swarms. Interestingly, at the same time, we observe that even shorter completion times can be achieved under mixtures of TCP and uTP traffic, as in the default BitTorrent settings.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Alcock, S., Nelson, R.: Application flow control in youtube video streams. ACM SIGCOMM Computer Communication Review 41(2), 24–30 (2011)CrossRefGoogle Scholar
  2. 2.
    Bonfiglio, D., Mellia, M., Meo, M., Rossi, D.: Detailed analysis of skype traffic. IEEE Transaction on Multimedia 11(1), 117–127 (2009)CrossRefGoogle Scholar
  3. 3.
    Shalunov, S.e.a.: Low Extra Delay Background Transport (LEDBAT). IETF Draft (October 2010)Google Scholar
  4. 4.
    Norberg, A.: BitTorrent Enhancement Proposals on μTorrent transport protocol (2009), http://www.bittorrent.org/beps/bep_0029.html
  5. 5.
    IETF: LEDBAT Working Group Charter, http://datatracker.ietf.org/wg/ledbat/charter/
  6. 6.
    Schneider, J., Wagner, J., Winter, R., Kolbe, H.: Out of my Way – Evaluating Low Extra Delay Background Transport in an ADSL Acciess Network. In: 22nd International Teletraffic Congress (ITC22), Amsterdam, The Netherlands (September 2010)Google Scholar
  7. 7.
    Rossi, D., Testa, C., Valenti, S.: Yes, We LEDBAT: Playing with the New BitTorrent Congestion Control Algorithm. In: Krishnamurthy, A., Plattner, B. (eds.) PAM 2010. LNCS, vol. 6032, pp. 31–40. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  8. 8.
    Morris, S.: μTorrent release 1.9 alpha 13485 (December 2008), http://forum.utorrent.com/viewtopic.php?pid=379206#p379206
  9. 9.
    Testa, C., Rossi, D.: The impact of utp on bittorrent completion time. In: 11th IEEE International Conference on Peer-to-Peer Computing (P2P), Kyoto, Japan (2011)Google Scholar
  10. 10.
  11. 11.
    Venkataramani, A., Kokku, R., Dahlin, M.: TCP Nice: A mechanism for background transfers. In: 8th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2002), Boston, MA (December 2002)Google Scholar
  12. 12.
    Kuzmanovic, A., Knightly, E.: TCP-LP: low-priority service via end-point congestion control. IEEE/ACM Transactions on Networking (TON) 14(4), 752 (2006)Google Scholar
  13. 13.
    Liu, S., Vojnovic, M., Gunawardena, D.: 4cp: Competitive and considerate congestion control protocol. In: ACM SIGCOMM, Pisa, Italy (September 2006)Google Scholar
  14. 14.
    Qiu, D., Srikant, R.: Modeling and performance analysis of BitTorrent-like peer-to-peer networks. ACM SIGCOMM Comp. Comm. Rev. 34(4), 367–378 (2004)CrossRefGoogle Scholar
  15. 15.
    Rao, A., Legout, A., Dabbous, W.: Can realistic bittorrent experiments be performed on clusters? In: 10th IEEE International Conference on Peer-to-Peer Computing (P2P), pp. 1–10 (August 2010)Google Scholar
  16. 16.
    Legout, A., Liogkas, N., Kohler, E., Zhang, L.: Clustering and sharing incentives in bittorrent systems. In: Proc. of ACM SIGMETRICS 2007, San Diego, CA, USA (June 2007)Google Scholar
  17. 17.
    Cohen, B., Norberg, A.: Correcting for clock drift in uTP and LEDBAT. Invited talk at 9th USENIX International Workshop on Peer-to-Peer Systems (IPTPS 2010), San Jose, CA (April 2010)Google Scholar
  18. 18.
    Rossi, D., Testa, C., Valenti, S., Muscariello, L.: LEDBAT: the new BitTorrent congestion control protocol. In: 19th IEEE International Conference on Computer Communications and Networks (ICCCN 2010), Zurich, Switzerland (August 2010)Google Scholar
  19. 19.
    Carofiglio, G., Muscariello, L., Rossi, D., Valenti, S.: The quest for LEDBAT fairness. In: IEEE Global Communication (GLOBECOM 2010), Miami, FL (December 2010)Google Scholar
  20. 20.
    Carofiglio, G., Muscariello, L., Rossi, D., Testa, C.: A hands-on Assessment of Transport Protocols with Lower than Best Effort Priority. In: 35th IEEE Local Computer Network (LCN 2010), Denver, CO (October 2010)Google Scholar
  21. 21.
    Bhooma, P.: Measurements using the LEDBAT implementation for MAX OS X, http://www.ietf.org/mail-archive/web/ledbat/current/msg00532.html
  22. 22.
    Abu, A., Gordon, S.: A Dynamic Algorithm for Stabilising LEDBAT Congestion Window. In: 2nd IEEE International Conference on Computer and Network Technology (ICCNT 2010), Bangkok, Thailand (April 2010)Google Scholar
  23. 23.
  24. 24.
    Mogul, J.C.: Tcp offload is a dumb idea whose time has come. In: 9th Conference on Hot Topics in Operating Systems, vol. 9, p. 5. USENIX Association, Berkeley (2003)Google Scholar
  25. 25.
    Akella, A., Seshan, S., Shaikh, A.: An empirical evaluation of wide-area internet bottlenecks. In: Proc. of the 3rd ACM SIGCOMM Conference on Internet Measurement (IMC 2003), Miami, FL, USA (October 2003)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2012

Authors and Affiliations

  • Claudio Testa
    • 1
  • Dario Rossi
    • 1
  • Ashwin Rao
    • 2
  • Arnaud Legout
    • 2
  1. 1.Telecom ParisTechParisFrance
  2. 2.INRIA PlaneteSophia AntipolisFrance

Personalised recommendations