research-article

Proportional rate reduction for TCP

Authors:

Nandita Dukkipati,

Yuchung Cheng, and

Monia GhobadiAuthors Info & Claims

IMC '11: Proceedings of the 2011 ACM SIGCOMM conference on Internet measurement conference

November 2011

Pages 155 - 170

https://doi.org/10.1145/2068816.2068832

Published: 02 November 2011 Publication History

Abstract

Packet losses increase latency for Web users. Fast recovery is a key mechanism for TCP to recover from packet losses. In this paper, we explore some of the weaknesses of the standard algorithm described in RFC 3517 and the non-standard algorithms implemented in Linux. We find that these algorithms deviate from their intended behavior in the real world due to the combined effect of short flows, application stalls, burst losses, acknowledgment (ACK) loss and reordering, and stretch ACKs. Linux suffers from excessive congestion window reductions while RFC 3517 transmits large bursts under high losses, both of which harm the rest of the flow and increase Web latency.

Our primary contribution is a new design to control transmission in fast recovery called proportional rate reduction (PRR). PRR recovers from losses quickly, smoothly and accurately by pacing out retransmissions across received ACKs. In addition to PRR, we evaluate the TCP early retransmit (ER) algorithm which lowers the duplicate acknowledgment threshold for short transfers, and show that delaying early retransmissions for a short interval is effective in avoiding spurious retransmissions in the presence of a small degree of reordering. PRR and ER reduce the TCP latency of connections experiencing losses by 3-10% depending on the response size. Based on our instrumentation on Google Web and YouTube servers in U.S. and India, we also present key statistics on the nature of TCP retransmissions.

References

[1]

State of the internet, 2010. http://www.akamai.com/stateoftheinternet/.

[2]

Allman, M., Avrachenkov, K., Ayesta, U., Blanton, J., and Hurtig, P. Early retransmit for TCP and SCTP, May 2010. RFC 5827.

[3]

Allman, M., Balakrishnan, H., and Floyd, S. Enhancing TCP's loss recovery using limited transmit, January 2001. RFC 3042.

Digital Library

[4]

Allman, M., Paxson, V., and Blanton, E. TCP congestion control, September 2009. RFC 5681.

[5]

Balakrishnan, H., Padmanabhan, V. N., Seshan, S., Stemm, M., and Katz, R. H. TCP behavior of a busy internet server: Analysis and improvements. In Proc. of INFOCOMM (1998).

[6]

Bennet, J. C., Patridge, C., and Shectman, N. Packet reordering is not pathological network behavior. IEEE/ACM Trans. on Networking (December 1999).

Digital Library

[7]

Blanton, E., and Allman, M. Using TCP DSACKs and SCTP duplicate TSNs to detect spurious retransmissions, February 2004. RFC 3708.

[8]

Blanton, E., Allman, M., Fall, K., and Wang, L. A conservative SACK-based loss recovery algorithm for TCP, 2003. RFC 3517.

Digital Library

[9]

Floyd, S., Mahdavi, J., Mathis, M., and Podolsky, M. An extension to the SACK option for TCP, July 2000. RFC 2883.

[10]

Ha, S., Rhee, I., and Xu, L. CUBIC: a new TCP-friendly high-speed TCP variant. SIGOPS Oper. Syst. Rev. 42 (July 2008), 64--74.

Digital Library

[11]

Hoe, J. Improving the start-up behavior of a congestion control scheme for TCP. SIGCOMM Comput. Commun. Rev. (August 1996).

Digital Library

[12]

Lin, D., and Kung, H. TCP fast recovery strategies: Analysis and improvements. In Proc. of INFOCOMM (1998).

[13]

Ludwig, R., and Katz, R. H. The eifel algorithm: Making TCP robust against spurious retransmissions. (ACM) Computer Communication Review 30 (January 2000).

Digital Library

[14]

Ludwig, R., and Meyer, M. The eifel detection algorithm for TCP, April 2003. RFC 3522.

Digital Library

[15]

Mathis, M., Dukkipati, N., and Cheng, Y. Proportional rate reduction for TCP, March 2011. Work in progress, draft-mathis-tcpm-proportional-rate-reduction-00.txt.

[16]

Mathis, M., and Mahdavi, J. Forward acknowledgment: refining TCP congestion control. SIGCOMM Comput. Commun. Rev. 26 (August 1996), 281--291.

Digital Library

[17]

Mathis, M., and Mahdavi, J. TCP rate-halving with bounding parameters, December 1997. http://www.psc.edu/networking/papers/ FACKnotes/current/.

[18]

Mathis, M., Mahdavi, J., Floyd, S., and Romanow, A. TCP selective acknowledgement options, October 1996. RFC 2018.

Digital Library

[19]

Mathis, M., Semke, J., Mahdavi, J., and Lahey, K. The rate-halving algorithm for TCP congestion control, June 1999. draft-mathis-tcp-ratehalving-00.txt, http://www.psc.edu/networking/ftp/papers/draft-ratehalving.txt.

[20]

Petlund, A., Evensen, K., Griwodz, C., and Halvorsen, P. TCP enhancements for interactive thin-stream applications. In NOSSDAV (2008).

Digital Library

[21]

Ramachandran, S. Web metrics: Size and number of resources. http://code.google.com/speed/articles/web-metrics.html.

[22]

Rewaskar, S., Kaur, J., and Smith, F. D. A performance study of loss detection/recovery in real-world TCP implementations. In Proc. of ICNP (2007).

[23]

Sarolahti, P., and Kuznetsov, A. Congestion control in linux tcp. In Proceedings of USENIX (2002), Springer, pp. 49--62.

Digital Library

[24]

Scheffenegger, R. Improving SACK-based loss recovery for TCP, November 2010. Work in progress, draft-scheffenegger-tcpm-sack-loss-recovery-00.txt.

[25]

Schurman, E., and Brutlag, J. The user and business impact of server delays, additional bytes, and HTTP chunking in web search. http://velocityconf.com/velocity2009/\ public/schedule/detail/8523.

[26]

Sun, P., Yu, M., Freedman, M. J., and Rexford, J. Identifying performance bottlenecks in CDNs through TCP-level monitoring. In SIGCOMM Workshop on Measurements Up the Stack (August 2011).

Digital Library

[27]

Touch, J. TCP control block interdependence, April 1997. RFC 2140.

Digital Library

[28]

Yang, P., Luo, W., Xu, L., Deogun, J., and Lu, Y. TCP congestion avoidance algorithm identification. In Proc. of ICDCS (June 2011).

Digital Library

[29]

Yang, Y., and Lam, S. General aimd congestion control. Proc. International Conference on Network Protocols. (November 2000).

Digital Library

Cited By

Brahmakshatriya ARinard CGhobadi MAmarasinghe S(2024)NetBlocks: Staging Layouts for High-Performance Custom Host Network StacksProceedings of the ACM on Programming Languages10.1145/36563968:PLDI(467-491)Online publication date: 20-Jun-2024
https://dl.acm.org/doi/10.1145/3656396
Lee JKim MSong WKim YKim DHong JPark J(2024)Rescuing QUIC Flows From Countermeasures Against UDP Flooding AttacksProceedings of the 39th ACM/SIGAPP Symposium on Applied Computing10.1145/3605098.3635885(1072-1080)Online publication date: 8-Apr-2024
https://dl.acm.org/doi/10.1145/3605098.3635885
Yang WLiu YTian CJiang JGuo L(2023)Gemini: Divide-and-Conquer for Practical Learning-Based Internet Congestion ControlIEEE INFOCOM 2023 - IEEE Conference on Computer Communications10.1109/INFOCOM53939.2023.10229069(1-10)Online publication date: 17-May-2023
https://doi.org/10.1109/INFOCOM53939.2023.10229069
Show More Cited By

Index Terms

Proportional rate reduction for TCP
1. Networks
  1. Network protocols

Recommendations

Techniques for Enhancing TCP Performance in Wireless Networks
ICDCSW '12: Proceedings of the 2012 32nd International Conference on Distributed Computing Systems Workshops

Transmission Control Protocol (TCP) carries the maximum Internet traffic, so performance of TCP largely affects the performance of Internet. However, end-to-end throughput in TCP degrades notably when operated in wireless networks, since random packet ...
Read More
TCP over optical burst-switched networks with controlled burst retransmission

For optical burst-switched (OBS) networks in which TCP is implemented at a higher layer, the loss of bursts can lead to serious degradation of TCP performance. Due to the bufferless nature of OBS, random burst losses may occur, even at low traffic ...
Read More
Performance of TCP over ATM with time-varying available bandwidth

While both ABR and UBR services can be used to support data traffic in ATM, many ATM switch vendors consider UBR to be more attractive because of its low implementation cost in comparison with ABR. In this paper, we present a simulation study on the ...
Read More

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

IMC '11: Proceedings of the 2011 ACM SIGCOMM conference on Internet measurement conference

November 2011

612 pages

ISBN:9781450310130

DOI:10.1145/2068816

Program Chairs:
Patrick Thiran
EPFL, Switzerland
,
Walter Willinger
AT&T Labs-Research, USA

Copyright © 2011 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

In-Cooperation

USENIX Assoc: USENIX Assoc

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 02 November 2011

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

IMC '11

Sponsor:

IMC '11: Internet Measurement Conference

November 2 - 4, 2011

Berlin, Germany

Acceptance Rates

Overall Acceptance Rate 277 of 1,083 submissions, 26%

Upcoming Conference

IMC '24

Sponsor:
sigcomm
sigcomm

ACM Internet Measurement Conference

November 4 - 6, 2024

Madrid , AA , Spain

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

31
Total Citations
View Citations
448
Total Downloads

Downloads (Last 12 months)22
Downloads (Last 6 weeks)4

Other Metrics

View Author Metrics

Citations

Cited By

Brahmakshatriya ARinard CGhobadi MAmarasinghe S(2024)NetBlocks: Staging Layouts for High-Performance Custom Host Network StacksProceedings of the ACM on Programming Languages10.1145/36563968:PLDI(467-491)Online publication date: 20-Jun-2024
https://dl.acm.org/doi/10.1145/3656396
Lee JKim MSong WKim YKim DHong JPark J(2024)Rescuing QUIC Flows From Countermeasures Against UDP Flooding AttacksProceedings of the 39th ACM/SIGAPP Symposium on Applied Computing10.1145/3605098.3635885(1072-1080)Online publication date: 8-Apr-2024
https://dl.acm.org/doi/10.1145/3605098.3635885
Yang WLiu YTian CJiang JGuo L(2023)Gemini: Divide-and-Conquer for Practical Learning-Based Internet Congestion ControlIEEE INFOCOM 2023 - IEEE Conference on Computer Communications10.1109/INFOCOM53939.2023.10229069(1-10)Online publication date: 17-May-2023
https://doi.org/10.1109/INFOCOM53939.2023.10229069
Spang BArslan SMcKeown N(2021)Updating the theory of buffer sizingPerformance Evaluation10.1016/j.peva.2021.102232151:COnline publication date: 1-Nov-2021
https://dl.acm.org/doi/10.1016/j.peva.2021.102232
Liu KZha ZWan WAggarwal VFu BChen M(2020)Optimizing TCP Loss Recovery Performance Over Mobile Data NetworksIEEE Transactions on Mobile Computing10.1109/TMC.2019.290988819:6(1401-1419)Online publication date: 1-Jun-2020
https://doi.org/10.1109/TMC.2019.2909888
Shen YLiu KGuo ZZhang WZhang GAggarwal VChen M(2020)Freeway: An Order-less User-space Framework for Non-real-time Applications2020 IEEE 22nd International Conference on High Performance Computing and Communications; IEEE 18th International Conference on Smart City; IEEE 6th International Conference on Data Science and Systems (HPCC/SmartCity/DSS)10.1109/HPCC-SmartCity-DSS50907.2020.00056(457-464)Online publication date: Dec-2020
https://doi.org/10.1109/HPCC-SmartCity-DSS50907.2020.00056
Bianchi GWelzl MTulumello AGringoli FBelocchi GFaltelli MPontarelli S(2019)XTRA: Towards Portable Transport Layer FunctionsIEEE Transactions on Network and Service Management10.1109/TNSM.2019.294846716:4(1507-1521)Online publication date: Dec-2019
https://doi.org/10.1109/TNSM.2019.2948467
KONDO TYOSHIHARA SKANEKO KTERAOKA F(2018)ZINK: An Efficient Information Centric Networking Utilizing Layered Network ArchitectureIEICE Transactions on Communications10.1587/transcom.2017EBP3348E101.B:8(1853-1865)Online publication date: 1-Aug-2018
https://doi.org/10.1587/transcom.2017EBP3348
Mittal VJain VTahiliani MGamess ESaucez DTahiliani M(2018)Proportional rate reduction for ns-3 TCPProceedings of the 2018 Workshop on ns-310.1145/3199902.3199910(9-15)Online publication date: 13-Jun-2018
https://dl.acm.org/doi/10.1145/3199902.3199910
Li FJiang XChung JClaypool M(2018)Who is the King of the Hill? Traffic Analysis over a 4G Network2018 IEEE International Conference on Communications (ICC)10.1109/ICC.2018.8422958(1-6)Online publication date: May-2018
https://doi.org/10.1109/ICC.2018.8422958
Show More Cited By

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents