Scaling TCP's Congestion Window for Small Round Trip Times

This memo explains that deploying active queue management (AQM) to counter bufferbloat will not prevent TCP from overriding the AQM and building large queues in a range of not uncommon scenarios. This is a brief paper study to explain this effect which was observed in a number of low latency testbed experiments. To keep its queue short, an AQM drops (or marks) packets to make the TCP flow(s) traversing it reduce their packet rate. Nearly all TCP implementations will not run at less than two packets per round trip time (RTT). 2pkt / RTT need not imply low bit-rate if the RTT is small. For instance, it represents 2Mb/s over a 6ms round trip. When a few TCP flows share a link, in certain scenarios, including regular broadband and data centres, no matter how much the AQM signals to the flows to keep the queue short, they will not obey, because it is impossible for them to run below this floor. The memo proposes the necessary modification to the TCP standard.

[1]  Matt Mathis Laminar TCP and the case for refactoring TCP congestion control , 2012 .

[2]  Bob Briscoe,et al.  More Accurate ECN Feedback in TCP , 2019 .

[3]  Jon Crowcroft,et al.  LEDBAT performance in sub-packet regimes , 2014, 2014 11th Annual Conference on Wireless On-demand Network Systems and Services (WONS).

[4]  Robert Tappan Morris,et al.  TCP behavior with many flows , 1997, Proceedings 1997 International Conference on Network Protocols.

[5]  Arun Venkataramani,et al.  Proceedings of the 5th Symposium on Operating Systems Design and Implementation Tcp Nice: a Mechanism for Background Transfers , 2022 .

[6]  Vern Paxson,et al.  TCP Congestion Control , 1999, RFC.

[7]  Lakshminarayanan Subramanian,et al.  TCP behavior in sub packet regimes , 2011, PERV.