Abstract
The set of TCP congestion control algorithms associated with TCP/Reno (e.g., slow-start and congestion avoidance) have been crucial to ensuring the stability of the Internet. Algorithms such as TCP/NewReno (which has been deployed) and TCP/Vegas (which has not been deployed) represent incrementally deployable enhancements to TCP as they have been shown to improve a TCP connection's throughput without degrading performance to competing flows. Our research focuses on delay-based congestion avoidance algorithms (DCA), like TCP/Vegas, which attempt to utilize the congestion information contained in packet round-trip time (RTT) samples. Through measurement and simulation, we show evidence suggesting that a single deployment of DCA (i.e., a TCP connection enhanced with a DCA algorithm) is not a viable enhancement to TCP over high-speed paths. We define several performance metrics that quantify the level of correlation between packet loss and RTT. Based on our measurement analysis we find that although there is useful congestion information contained within RTT samples, the level of correlation between an increase in RTT and packet loss is not strong enough to allow a TCP/Sender to reliably improve throughput. While DCA is able to reduce the packet loss rate experienced by a connection, in its attempts to avoid packet loss, the algorithm will react unnecessarily to RTT variation that is not associated with packet loss. The result is degraded throughput as compared to a similar flow that does not support DCA.
- {1} V. Jacobson, "Congestion avoidance and control," in Proc. ACM SIGCOMM, 1988, pp. 314-329. Google Scholar
- {2} V. Jacobson, C. Leres, and S. McCanne. (1989, June) tcpdump. {Online}. Available: ftp://ftp.ee.lbl.govGoogle Scholar
- {3} M. Allman, V. Paxson, and W. Stevens, "TCP congestion control," IETF, RFC 2581, Apr. 1999. Google Scholar
- {4} S. Floyd, "A report on some recent developments in TCP congestion control," IEEE Commun. Mag., vol. 39, pp. 84-90, Apr. 2001. Google Scholar
- {5} M. Mathis, J. Mahdavi, S. Floyd, and A. Romanow, "TCP selective acknowledgment options," Network Working Group, RFC 2018, Apr. 1996. Google Scholar
- {6} M. Allman and S. Floyd. (2000, Aug.) Enhancing TCP's loss recovery using limited transmit. IETF. Internet Draft. {Online}. Available: draft-ietf-tsvwg-limited-xmit-00.txt Google Scholar
- {7} R. Jain, "A delay-based approach for congestion avoidance in interconnected heterogeneous computer networks," Comput. Commun. Rev., vol. 19, no. 5, pp. 56-71, Oct. 1989. Google Scholar
- {8} L. S. Brakmo, S. W. O'Malley, and L. L. Peterson, "TCP Vegas: New techniques for congestion detection and avoidance," in Proc. ACM SIGCOMM, Aug. 1994, pp. 24-35. Google Scholar
- {9} Z. Wang and J. Crowcroft, "Eliminating periodic packet losses in the 4.3-Tahoe BSD TCP congestion control algorithm," Comput. Commun. Rev., vol. 22, no. 2, pp. 9-16, Apr. 1992. Google Scholar
- {10} U. Hengartner, J. Bolliger, and T. Gross, "TCP Vegas revisited," in Proc. IEEE INFOCOM, Mar. 2000, pp. 1546-1555.Google Scholar
- {11} S. Low, L. Peterson, and L. Wang, "Understanding TCP Vegas: Aduality model," J. ACM, vol. 49, no. 2, pp. 207-235, Mar. 2002. Google Scholar
- {12} J. Mo et al., "Analysis and comparison of TCP/Reno and Vegas," in Proc. IEEE INFOCOM, 1999, pp. 1556-1563.Google Scholar
- {13} D. Bansal, H. Balakrishnan, S. Floyd, and S. Shenker, "Dynamic behavior of slowly-responsive congestion control algorithms," in Proc. ACM SIGCOMM, Aug. 2001, pp. 263-274. Google Scholar
- {14} K. Claffy, G. Miller, and K. Thompson, "The nature of the beast: Recent traffic measurements from an internet backbone," in Proc. INET Conf., 1998, {Online.} Available: http://www.isoc.org/inet98/proceedings/6g/6g_3.htm.Google Scholar
- {15} W. Fang and L. Peterson, "Inter-AS traffic patterns and their implications," in Proc. IEEE GLOBECOM, 1999, pp. 1859-1868.Google Scholar
- {16} K. Thompson, G. Miller, and R. Wilder, "Wide area internet traffic patterns and characteristics," IEEE Network, vol. 11, pp. 10-23, Nov. 1997. Google Scholar
- {17} C. Fraleigh, S. Moon, B. Lyles, C. Cotton, M. Khan, D. Moll, R. Rockwell, T. Seely, and C. Diot, "Packet-level traffic measurements from the Sprint IP backbone," IEEE Network, to be published. Google Scholar
- {18} J. Padhye et al., "Modeling TCP throughput: A simple model and its empirical validation," in Proc. ACM SIGCOMM, 1998, pp. 303-314. Google Scholar
- {19} J. Martin, "RTT-based congestion avoidance for high speed TCP Internet connections," Ph.D. dissertation, North Carolina State Univ., Raleigh, Dec. 1999. Google Scholar
- {20} The Network Simulator. Univ. California, Berkeley, CA. {Online}. Available: http://www-mash.cs.Berkeley.EDU/ns/Google Scholar
- {21} J. Ahn, P. Danzig, Z. Liu, and L. Yan, "Evaluation of TCP Vegas: Emulation and experiment," in Proc. ACM SIGCOMM, 1995, pp. 185-195. Google Scholar
- {22} J. Bolot, "End-to-end packet delay and loss behavior in the Internet," in Proc. ACM SIGCOMM, 1993, pp. 289-298. Google Scholar
- {23} S. Moon, J. Kurose, and D. Towsley, "Correlation of packet delay and loss in the Internet," Dept. Comput. Sci., Univ. Massachusetts, Amherst, Tech. Rep. 98-11, 1998. Google Scholar
- {24} V. Paxson, "End-to-end internet packet dynamics," IEEE/ACM Trans. Networking, vol. 7, pp. 277-292, June 1999. Google Scholar
- {25} M. Yajnik, S. Moon, J. Kurose, and D. Towsley, "Measurement and modeling of the temporal dependence in packet loss," in Proc. IEEE INFOCOM, Mar. 1999, pp. 345-352.Google Scholar
- {26} V. Paxson, "Measurements and analysis of end-to-end Internet dynamics," Ph.D. dissertation, Univ. California, Berkeley, CA, 1997. Google Scholar
- {27} Y. Zhang, N. Duffield, V. Paxson, and S. Shenker, "On the constancy of internet path properties," in Proc. ACM SIGCOMM Internet Measurement Workshop (IMW2001), Nov. 2001, pp. 197-211. Google Scholar
- {28} D. Loguinov and H. Radha, "Large-scale experimental study of internet performance using video traffic," Comput. Commun. Rev., vol. 32, no. 1, pp. 7-19, Jan. 2002. Google Scholar
- {29} W. Leland et al., "On the self-similar nature of Ethernet traffic," IEEE Trans. Networking, vol. 2, pp. 1-15, Feb. 1994. Google Scholar
- {30} S. Floyd, M. Handley, J. Padhye, and J. Widmer, "Equation-based congestion control for unicast applications," in Proc. ACM SIGCOMM, Aug. 2000, pp. 43-56. Google Scholar
- {31} S. Cen, C. Pu, and J. Walpole, "Flow and congestion control for internet streaming applications," in Proc. Multimedia Computing and Networking, Jan. 1998, pp. 250-264.Google Scholar
- {32} R. Rejaie, M. Handley, and D. Estrin, "RAP: An end-to-end rate-based congestion control mechanism for realtime streams in the Internet," in Proc. IEEE INFOCOM, 1999, pp. 1337-1345.Google Scholar
- {33} P. Hurley et al., "ABE: Providing a low-delay service within best effort," IEEE Network, vol. 15, pp. 60-69, May/June 2001. Google Scholar
- {34} R. Miles. ttcp measurement tool. The FreeBSD Project. {Online}. Available: http://www.freebsd.org/portsGoogle Scholar
- {35} S. Bortzmeyer. (2002, Oct.) Echoping measurement tool. {Online}. Available: http://echoping.sourceforge.netGoogle Scholar
- {36} V. Paxson and M. Allman, "Computing TCP's retransmission timer," Network Working Group, RFC 2988, Nov. 2000. Google Scholar
- {37} S. Shenker, L. Zhang, and D. Clark, "Some observations on the dynamics of a congestion control algorithm," in Proc. ACM SIGCOMM, 1990, pp. 30-39.Google Scholar
- {38} S. Floyd and K. Ramakrishnan. (1999, Jan.) A Proposal to add explicit congestion notification to IP. Experimental RFC 2481. Info. Sci. Inst., Los Angeles, CA. {Online}. Available: ftp://ftp.isi.edu/in-notes/rfc2481.txt Google Scholar
- {39} M. Goyal, R. Guerin, and R. Rajan, "Predicting TCP throughput from noninvasive network sampling," in Proc. IEEE INFOCOM, June 2002, pp. 180-189.Google Scholar
- {40} P. Barford and M. Crovella, "Generating representative web workloads for network and server performance evaluation," in ACM SIGMETRICS, July 1998, pp. 151-160. Google Scholar
- {41} S. Floyd and V. Paxson, "Difficulties in simulating the internet," IEEE/ACM Trans. Networking, vol. 9, pp. 392-403, Aug. 2001. Google Scholar
Index Terms
- Delay-based congestion avoidance for TCP
Recommendations
Performance evaluation of Westwood+ TCP congestion control
Internet performance symposium (IPS 2002)Westwood+ TCP is a sender-side only modification of the classic Tahoe/Reno TCP that has been recently proposed to improve fairness and efficiency of TCP. The key idea of Westwood+ TCP is to perform an end-to-end estimate of the bandwidth available for a ...
Delay-based TCP congestion avoidance: A network calculus interpretation and performance improvements
In delay-based TCP congestion avoidance mechanisms, a source adjusts its window size to adapt to changes in network conditions as measured through changing queueing delays. Although network calculus (NC) has been used to study window flow control and ...
TCP congestion avoidance algorithm identification
The Internet has recently been evolving from homogeneous congestion control to heterogeneous congestion control. Several years ago, Internet traffic was mainly controlled by the traditional RENO, whereas it is now controlled by multiple different TCP ...
Comments