Fast Available Bandwidth Sampling for ADSL Links: Rethinking the Estimation for Larger-Scale Measurements

  • Daniele Croce
  • Taoufik En-Najjary
  • Guillaume Urvoy-Keller
  • Ernst W. Biersack
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5448)

Abstract

Most existing tools for measuring the end-to-end available bandwidth require access to both end-hosts of the measured path, which severely restricts their usability. Few tools have been developed to overcome this limitation, but all of them focus on achieving high precision and are not suitable for large campaigns. In this paper we develop FAB-Probe, a tool aimed at characterizing the available bandwidth of a large number of paths, adapting it particularly for ADSL settings. FAB-Probe is an evolution of ABwProbe, a tool that estimates the available bandwidth in non-cooperative ADSL environments. Analyzing carefully the needs of such a characterization tool, we optimize and rethink ABwProbe for larger-scale measurements. The validation of FAB-Probe is obtained both “in-lab”, with ADSL hosts under our control, as well as under real traffic conditions, with the help of an ISP. Finally, as a proof of concept, we analyze the available bandwidth of over 1300 hosts participating to the KAD DHT used by eMule, periodically monitoring some static peers for over ten days.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Croce, D., En-Najjary, T., Urvoy-Keller, G., Biersack, E.: Capacity Estimation of ADSL links. In: CoNEXT (December 2008)Google Scholar
  2. 2.
    Croce, D., En-Najjary, T., Urvoy-Keller, G., Biersack, E.: Non-cooperative Available Bandwidth Estimation towards ADSL links. In: Proc. Global Internet Symposium 2008 (April 2008)Google Scholar
  3. 3.
    Dischinger, M., Haeberlen, A., Gummadi, K.P., Saroiu, S.: Characterizing residential broadband networks. In: IMC (October 2007)Google Scholar
  4. 4.
    Dovrolis, C., Jain, M.: End-to-end available bandwidth: Measurement methodology, dynamics, and relation with TCP throughput. In: SIGCOMM, Pittsburgh, USA (August 2002)Google Scholar
  5. 5.
    The FAB-Probe Project website, http://www.eurecom.fr/~btroup/fabprobe.html
  6. 6.
    Haeberlen, A., Dischinger, M., Gummadi, K.P., Saroiu, S.: Monarch: A tool to emulate transport protocol flows over the internet at large. In: IMC (October 2006)Google Scholar
  7. 7.
    Hu, N., Li, L.E., Mao, Z.M., Steenkiste, P., Wang, J.: Locating internet bottlenecks: algorithms, measurements, and implications. In: SIGCOMM, Portland, USA (2004)Google Scholar
  8. 8.
    Lao, L., Dovrolis, C., Sanadidi, M.Y.: The probe gap model can underestimate the available bandwidth of multihop paths. Computer Communication Review 36(5), 29–34 (2006)CrossRefGoogle Scholar
  9. 9.
    Maymounkov, P., Mazieres, D.: Kademlia: A peer-to-peer information system based on the XOR metric. In: Druschel, P., Kaashoek, M.F., Rowstron, A. (eds.) IPTPS 2002. LNCS, vol. 2429, p. 53. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  10. 10.
    OECD. OECD broadband statistics (June 2007), http://www.oecd.org/sti/ict/broadband
  11. 11.
    Saroiu, S., Gummadi, P.K., Gribble, S.D.: Sprobe: A fast technique for measuring bottleneck bandwidth in uncooperative environments (2002), http://sprobe.cs.washinton.edu
  12. 12.
    Steiner, M., En-Najjary, T., Biersack, E.W.: A Global View of KAD. In: IMC (2007)Google Scholar
  13. 13.
    Windsor, L.: Oaks Group. Annual market outlook report (2006)Google Scholar
  14. 14.
    Zaragoza, D., Belo, C.: Experimental validation of the on-off packet-level model for ip traffic. Comput. Commun. 30(5), 975–989 (2007)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Daniele Croce
    • 1
  • Taoufik En-Najjary
    • 1
  • Guillaume Urvoy-Keller
    • 1
  • Ernst W. Biersack
    • 1
  1. 1.EURECOM, Sophia AntipolisFrance

Personalised recommendations