Characterizing Bufferbloat and Its Impact at End-Hosts

  • Stéphane Wustner
  • Renata Teixeira
  • Jaideep Chandrashekar
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8406)


While buffers on forwarding devices are required to handle bursty Internet traffic, overly large or badly sized buffers can interact with TCP in undesirable ways. This phenomenon is well understood and is often called “bufferbloat”. Although a number of previous studies have shown that buffering (particularly, in home) can delay packets by as much as a few seconds in the worst case, there is less empirical evidence of tangible impacts on end-users. In this paper, we develop a modified algorithm that can detect bufferbloat at individual end-hosts based on passive observations of traffic. We then apply this algorithm on packet traces collected at 55 end-hosts, and across different network environments. Our results show that 45 out of the 55 users we study experience bufferbloat at least once, 40% of these users experience bufferbloat more than once per hour. In 90% of cases, buffering more than doubles RTTs, but RTTs during bufferbloat are rarely over one second. We also show that web and interactive applications, which are particularly sensitive to delay, are the applications most often affected by bufferbloat.


Sojourn Time Network Environment Additional Delay Interactive Application Active Queue Management 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Kreibich, C., Weaver, N., Nechaev, B., Paxson, V.: Netalyzr: illuminating the edge network. In: Proceedings of the 10th ACM SIGCOMM Conference on Internet Measurement, IMC 2010, pp. 246–259. ACM, New York (2010), Google Scholar
  2. 2.
    Gettys, J., Nichols, K.: Bufferbloat: dark buffers in the internet. Commun. ACM 55(1), 57–65 (2012), CrossRefGoogle Scholar
  3. 3.
    Nichols, K., Jacobson, V.: Controlling queue delay. Queue 10(5), 20:20–20:34 (2012), Google Scholar
  4. 4.
    Sundaresan, S., de Donato, W., Feamster, N., Teixeira, R., Crawford, S., Pescapè, A.: Broadband internet performance: A view from the gateway. SIGCOMM Comput. Commun. Rev. 41(4), 134–145 (2011), CrossRefGoogle Scholar
  5. 5.
    DiCioccio, L., Teixeira, R., May, M., Kreibich, C.: Probe and pray: Using UPnP for home network measurements. In: Taft, N., Ricciato, F. (eds.) PAM 2012. LNCS, vol. 7192, pp. 96–105. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  6. 6.
    Chirichella, C., Rossi, D.: To the moon and back: are internet bufferbloat delays really that large? In: TMA (2013)Google Scholar
  7. 7.
    Allman, M.: Comments on bufferbloat. SIGCOMM Comput. Commun. Rev. 43(1), 30–37 (2012), CrossRefGoogle Scholar
  8. 8.
    Ghobadi, M., Cheng, Y., Jain, A., Mathis, M.: Trickle: rate limiting youtube video streaming. In: Proceedings of the 2012 USENIX Conference on Annual Technical Conference, USENIX ATC 2012, p. 17. USENIX Association, Berkeley (2012), Google Scholar
  9. 9.
    Jiang, H., Wang, Y., Lee, K., Rhee, I.: Tackling bufferbloat in 3g/4g networks. In: Proceedings of the 2012 ACM Conference on Internet Measurement Conference, IMC 2012, pp. 329–342. ACM, New York (2012), CrossRefGoogle Scholar
  10. 10.
    Joumblatt, D., Teixeira, R., Chandrashekar, J., Taft, N.: Hostview: annotating end-host performance measurements with user feedback. SIGMETRICS Perform. Eval. Rev. 38(3), 43–48 (2011), CrossRefGoogle Scholar
  11. 11.
    Ostermann, S.: tcptrace,
  12. 12.
    Gringoli, F., Salgarelli, L., Dusi, M., Cascarano, N., Risso, F., Claffy, K.C.: Gt: picking up the truth from the ground for internet traffic. SIGCOMM Comput. Commun. Rev. 39(5), 12–18 (2009), CrossRefGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 2014

Authors and Affiliations

  • Stéphane Wustner
    • 1
    • 2
  • Renata Teixeira
    • 3
  • Jaideep Chandrashekar
    • 2
  1. 1.UPMC Sorbonne UniversitiesParisFrance
  2. 2.TechnicolorParisFrance
  3. 3.InriaFrance

Personalised recommendations