Matthew Mathis
ABSTRACT
We have developed a Forward Acknowledgment (FACK) congestion control algorithm which addresses many of the performance problems recently observed in the Internet. The FACK algorithm is based on first principles of congestion control and is designed to be used with the proposed TCP SACK option. By decoupling congestion control from other algorithms such as data recovery, it attains more precise control over the data flow in the network. We introduce two additional algorithms to improve the behavior in specific situations. Through simulations we compare FACK to both Reno and Reno with SACK. Finally, we consider the potential performance and impact of FACK in the Internet.
- Bal96.Hari Balakrishnan, March 1996. Presentation to the IETF TCP-LW working group.]]Google Scholar
- BOP94.Lawrence S. Brakmo, Sean W. O'Malley, and Larry L. Peterson. TCP Vegas: New Techniques for COngestion Detection and Avoidance. Proceedings of A CM SlGCOMM '9~, August 1994.]] Google ScholarDigital Library
- Bra89.R. Braden. Requirements for Internet Hosts- Communication Layers, October 1989. Request for Comments 1122.]] Google ScholarDigital Library
- CLZ87.D.D. Clark, M. L. Lambert, and L. Zhang. NETBLT: a high throughput transport protocol. Computer Communications Review, 17(5):353-359, 1987.]] Google ScholarDigital Library
- DJ91.Peter B. Danzig and Sugih Jamin. tcplib: A library of TCP/IP traffic characteristics. Technical Report TR-SYS-91- 01, USC Networking and Distributed Systems Laboratory, October 1991. Obtain via: ftp://cat arina.usc, edu/pub/j amin / t cplib.]]Google Scholar
- DLY95.Peter B. Danzig, Zhen Liu, and Limim Yan. An Evaluation of TCP Vegas by Live Emulation. A CM SIGMetrics '95, 1995.]]Google Scholar
- FF96.Kevin Fall and Sally Floyd. Comparisons of Tahoe, Reno and Sack TCP, May 1996. Submitted to CCR, Obtain via ftp://ft p. ee.lbl, gov /papers / sacks_ v 2 .ps. Z.]]Google Scholar
- FJ91.Sally Floyd and Van Jacobson. Traffic Phase Effects in Packet-Switched Gateways. Computer Communications Review, 21(2), April 1991.]] Google ScholarDigital Library
- FJ92.Sally Floyd and Van Jacobson. On Traffic Phase Effects in Packet-Switched Gateways. Internetworking: Research and Experience, 3(3):115- 156, September 1992.]]Google Scholar
- FJ93.Sally Floyd and Van Jacobson. Random Early Detection Gateways for Congestion Avoidance. IEEE/A CM Transactions on Networking, August 1993.]] Google ScholarDigital Library
- Flo92.Sally Floyd, February 1992. Private Communication.]]Google Scholar
- Flo95.Sally Floyd. TCP and Successive Fast Retransmits, February 1995. Obtain via ftp://ft p. ee.lbl, gov/papers / fast ret rans.ps.]]Google Scholar
- Hoe95.Janey C. Hoe. Startup Dynamics of TCP's Congestion Control and Avoidance Schemes. Master's thesis, Massachusetts Institute of Technology, June 1995.]]Google Scholar
- Hoe96.Janey C. Hoe. Improving the Start-up Behavior of a Congestion Control Scheme for TCP. Proceedings of A CM SIGCOMM '96, August 1996.]] Google ScholarDigital Library
- ipp96.Charter of the Benchmarking Working Group (BMWG) of the IETF, 1996. Obtain via: ht tp://www.iet f. cnri.rest on. va.us/ht ml. chart ers / bmwg-charter.html.]]Google Scholar
- Jac88.Van Jacobson. Congestion Avoidance and Control. Proceedings of A CM SIGCOMM '88, August 1988.]] Google ScholarDigital Library
- Jac90.Van L. Jacobson. Fast Retransmit. Message to the end2end-interest mailing list, April 1990.]]Google Scholar
- Jac95.Van Jacobson, July 1995. Private Communication.]]Google Scholar
- JB88.V. Jacobson and R. Braden. TCP extensions for long-delay paths, October 1988. Request for Comments 1072.]] Google ScholarDigital Library
- JBB92.V. Jacobson, R. Braden, and D. Borman. TCP Extensions for High Performance, May 1992. Request for Comments 1323.]] Google ScholarDigital Library
- Kar95.Phil Karn, December 1995. Private Communication.]]Google Scholar
- Mat.Matthew Mathis. Internet Performance and IP Provider Metrics information page. ht tp://www.psc.edu / ~ mathis/ipp m/.]]Google Scholar
- Mat94.Matthew B. Mathis. Windowed Ping: An IP Layer Performance Diagnostic. In Proceedings of INET'9j/JENC5, volume 2, Prague, Czech Republic, June 1994.]] Google ScholarDigital Library
- Mat95.Matthew Mathis. Source code for the TReno package, 1995. Obtain via: ftp://ft p.psc, edu/pub/net_tools / t reno. shar.]]Google Scholar
- Mat96.Matthew Mathis. Diagnosing Internet Congestion with a Transport Layer Performance Tool. In Proceedings of INET'96, Montreal, Quebec, June 1996.]]Google Scholar
- MF.S. McCanne and S. Floyd. ns-LBNL Network Simulator. Obtain via: http://wwwnrg.ee.lbl.gov/ns/.]]Google Scholar
- MMFR96.Matthew Mathis, Jamshid Mahdavi, Sally Floyd, and Allyn Romanow. TCP Selective Acknowledgement Options, May 1996. Internet Draft ("work in progress") draft-ietf-tcplw-sack- 02.txt, Expires: 29/7/96.]] Google ScholarDigital Library
- Mog92.Jeff C. Mogul. Observing TCP Dynamics in Real Networks. Proceedings of A CM SIGCOMM '92, pages 305-317, October 1992.]] Google ScholarDigital Library
- Pos81.J. Postel. Transmission Control Protocol, September 1981. Request for Comments 793.]]Google Scholar
- Ste94.W. Stevens. TCP/IP Illustrated, volume 1. Addison-Wesley, Reading MA, 1994.]]Google Scholar
- Ste96.W. Richard Stevens. TCP Slow Start, Congestion Avoidance, Fast Retransmit, and Fast Recovery Algorithms, March 1996. Currently an Internet Draft: draft-stevens-tcpca-spec-01.txt.]] Google ScholarDigital Library
- tcp95.Minutes of the tcpfix meeting at the 34th IETF, in Dallas TX, December 1995. Obtain via: ht tp://www.iet f. cnri.rest on. va.us / proceedings / 95dec / tsv / t cplw.ht ml.]]Google Scholar
- ZSC91.Lixia Zhang, Scott Shenker, and David D. Clark. Observations on the Dynamics of a Congestion Control Algorithm: The Effects of Two- Way Traffic. Proceedings of A CM SIGCOMM '91, pages 133-148, 1991.]] Google ScholarDigital Library
Index Terms
- Forward acknowledgement: refining TCP congestion control
Recommendations
Forward acknowledgement: refining TCP congestion control
We have developed a Forward Acknowledgment (FACK) congestion control algorithm which addresses many of the performance problems recently observed in the Internet. The FACK algorithm is based on first principles of congestion control and is designed to ...
An enhancement of TCP Veno with forward acknowledgement
One sender-side TCP enhancement, called TCP Veno, was recently proposed to mainly eliminate TCP performance suffering in the wireless environments. Although TCP Veno shows remarkable performance improvement over legacy TCP, namely TCP Reno, Veno has not ...
Comments