ABSTRACT
We consider unicast equation-based rate control, where a source estimates the loss event ratio $p$, and, primarily at loss events, adjusts its send rate to $f(p)$. Function $f$ is assumed to represent the loss-throughput relation that TCP would experience. When no loss occurs, the rate may also be increased according to some additional mechanism. We assume that the loss event interval estimator is non-biased. If the loss process is deterministic, the control is TCP-friendly in the long-run, i.e, the average throughput does not exceed that of TCP. If, in contrast, losses are random, it is a priori not clear whether this holds, due to the non-linearity of $f$, and a phenomenon similar to Feller's paradox. Our goal is to identify the key factors that drive whether, and how far, the control is TCP friendly (in the long run). As TCP and our source may experience different loss event intervals, we distinguish between TCP-friendliness and conservativeness (throughput does not exceed $f(p)$). We give a representation of the long term throughput, and derive that conservativeness is primarily influenced by various convexity properties of $f$, the variability of loss events, and the correlation structure of the loss process. In many cases, these factors lead to conservativeness, but we show reasonable experiments where the control is clearly non-conservative. However, our analysis also suggests that our source should experience a higher loss event ratio than TCP, which would make non-TCP friendliness less likely. Our findings provide guidelines that help understand when an equation base control is indeed TCP-friendly in the long-run, and in some cases, excessively so. The effects of round trip time and its variations are not included in this study.
- Francois Baccelli and Pierre Brémaud. Elements of Queueing Theory, volume 26. Applications of Mathematics, Springer-Verlag, 1991.Google Scholar
- Deepak Bansal, Hari Balakrishnan, Sally Floyd, and Scott Shenker. Dynamic Behavior of Slowly-responsive Congestion Control Algorithms. In Proc. of ACM Sigcomm'01, San Diego, California, USA, August 2001. Google ScholarDigital Library
- C. Barakat. TCP/IP Modeling and Validation. IEEE Network, 15(3):38--47, May-June 2001. Google ScholarDigital Library
- C. Boutremans and J.-Y. Le Boudec. Adaptive Delay Aware Error Control for Internet Telephony. In Proc. of 2nd IP-Telephony Workshop, pages 81--92, Columbia University, New York, April 2001.Google Scholar
- Neal Cardwell, Stefan Savage, and Thomas Anderson. Modeling TCP Latency. In Proc. of the IEEE INFOCOM'2000, Tel-Aviv, Israel, March 2000.Google Scholar
- William Feller. An Introduction to Probablity Theory and Its Applications, volume 2. John-Wiley & Sons, 2 edition, 1966.Google Scholar
- Sally Floyd. Best Control Principles, September 2000. rfc-2914, www.ietf.org.Google Scholar
- Sally Floyd and Kevin Fall. Promoting the Use of End-to-end Congestion Control in the Internet. IEEE/ACM Trans. on Networking, 7(4):458--472, August 1999. Google ScholarDigital Library
- Sally Floyd, Mark Handley, Jitendra Padhye, and J. Widmer. Equation-based Congestion Control for Unicast Applications. In Proc. of the Sigcomm'00, pages 43--56, 2000. Google ScholarDigital Library
- Mark Handley, Jitendra Padhye, Sally Floyd, and J. Widmer. TCP Friendly Rate Control (TFRC) Protocol Specification, IETF internet-draft, July 2001. http://search.ietf.org/internet-drafts/draft-ietf-tsvwg-tfrc-02.txt. Google ScholarDigital Library
- Jamshid Mahdavi and Sally Floyd. TCP-Friendly Unicast Rate-based Flow Control. Technical note sent to end-2-end interest mailing list, http://www.psc.edu/networking/papers/tcp friendly.html, January 1997.Google Scholar
- Matthew Mathis, Jeffrey Semke, Jamshid Mahdavi, and Teunis Ott. The Macroscopic Behavior of the TCP Congestion Avoidance Algorithm. Computer Communication Review, 27(3), July 1997. Google ScholarDigital Library
- Jitendra Padhye, Victor Firoiu, Don Towsley, and Jim Kurose. Modeling TCP Reno Performance: A Simple Model and its Empirical Validation. IEEE/ACM Trans. on Networking, 8(2):133--145, 2000. Google ScholarDigital Library
- Vern Paxson. End-to-end Internet Packet Dynamics. IEEE/ACM Trans. on Networking, pages 277--292, June 1999. Google ScholarDigital Library
- Salamatian M. R. and Vaton S. Hidden Markov Modeling for Network Communication Channels. In Proceedings of ACM Sigmetrics / Performance 200, Cambridge, Massachusetts, USA, June 2001. Google ScholarDigital Library
- Rockafellar R. T. Convex Analysis. Princeton University Press, Princeton, 1970.Google Scholar
- Milan VojnoviΕ and Jean-Yves Le Boudec. Some Observations on Equation-based Rate Control. In Proc. of ITC-17, pages 173--184, Salvador, Bahia, Brazil, Dec. 2001.Google Scholar
- J. Widmer, R. Denda, and M. Mauve. A Survey on TCP-Friendly Congestion Control. IEEE Network, 15(3):28--37, May-June 2001. Google ScholarDigital Library
- Y. Richard Yang, Min Sik Kim, and Simon S. Lam. Transient Behaviors of TCP-Friendly Congestion Control Protocols. In Proc. of IEEE Infocom'2001, March 2001.Google ScholarCross Ref
- Yin Zhang, Nick Duffield, Vern Paxson, and Scott Shenker. On the Constancy of Internet Path Properties. In Proc. of ACM Sigcomm Internet Measurement Workshop, Nov. 2001. Google ScholarDigital Library
Index Terms
- On the long-run behavior of equation-based rate control
Recommendations
On the long-run behavior of equation-based rate control
Proceedings of the 2002 SIGCOMM conferenceWe consider unicast equation-based rate control, where a source estimates the loss event ratio $p$, and, primarily at loss events, adjusts its send rate to $f(p)$. Function $f$ is assumed to represent the loss-throughput relation that TCP would ...
On the long-run behavior of equation-based rate control
We consider unicast equation-based rate control, where, at some points in time, a source adjusts its rate to f(p, r). Here p is an on-line estimate of the loss-event rate, r, of the mean round-trip time, both as observed by this source, and f is a TCP ...
Limitations of equation-based congestion control
SIGCOMM '05: Proceedings of the 2005 conference on Applications, technologies, architectures, and protocols for computer communicationsWe study limitations of an equation-based congestion control protocol, called TFRC (TCP Friendly Rate Control). It examines how the three main factors that determine TFRC throughput, namely, the TCP friendly equation, loss event rate estimation and ...
Comments