4 CP : Competitive and Considerate Congestion Control Protocol

1 We present a first practical packet-level windowbased congestion controller (4CP) that implements farsighted strategy, which was introduced and shown to be optimal for sources that value large long-run average throughput and are indifferent to sporadic throughput degradations (Key-MassouliéVojnović, 2005). Following farsighted strategy, the controller distinguishes good and bad congestion phases; in the former, it aims at balancing loss probability to a target value, while in the latter it virtually sends no data. The target loss probability is adapted very slowly so that the 4CP source verifies a given (TCP) loss-throughput formula over large timescale. The send rate is reduced to (virtually) zero in a controlled manner only during bad congestion phases, and not under full control of other (TCP) transfers, as it is the case with prior low-priority service emulators. We believe that its underlying features make 4CP a good candidate for file transfer applications such as file downloading and sharing, folder and database synchronization. We demonstrate that the short-timescale throughput flexibility of 4CP can be at the benefit of competing short-run TCP transfers. In the design, we address a number of requirements, such as bad phase detection with low false positives and quick detection. Besides a new protocol design, we present new analysis results that include a sufficient condition for local stability that accounts for feedback delay, maximum achievable throughput gain of 4CP user over a competing TCP user, and obtain an estimate for the false positive probability of the bad phase detector that provides parameter setting guidelines. Our results are validated by extensive simulations and some experiments over the Internet.

[1]  H. Vincent Poor,et al.  Detection of Stochastic Processes , 1998, IEEE Trans. Inf. Theory.

[2]  C. Desoer,et al.  On the generalized Nyquist stability criterion , 1979, 1979 18th IEEE Conference on Decision and Control including the Symposium on Adaptive Processes.

[3]  Laurent Massoulié,et al.  Emulating low-priority transport at the application layer: a background transfer service , 2004, SIGMETRICS '04/Performance '04.

[4]  Donald F. Towsley,et al.  Modeling TCP throughput: a simple model and its empirical validation , 1998, SIGCOMM '98.

[5]  Dinan Gunawardena,et al.  Competitive and Considerate Congestion Control for Bulk Data Transfers , 2007, 2007 Fifteenth IEEE International Workshop on Quality of Service.

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

[7]  Frank Kelly,et al.  Rate control for communication networks: shadow prices, proportional fairness and stability , 1998, J. Oper. Res. Soc..

[8]  Ramesh Johari,et al.  End-to-end congestion control for the internet: delays and stability , 2001, TNET.

[9]  Aleksandar Kuzmanovic,et al.  TCP-LP: a distributed algorithm for low priority data transfer , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[10]  Walter L. Smith,et al.  Regenerative stochastic processes , 1955, Proceedings of the Royal Society of London. Series A. Mathematical and Physical Sciences.

[11]  Glenn Vinnicombe,et al.  ON THE STABILITY OF NETWORKS OPERATING TCP-LIKE CONGESTION CONTROL , 2002 .

[12]  Laurent Massoulié,et al.  Farsighted users harness network time-diversity , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

[13]  Klaus Wehrle,et al.  A Lower Effort Per-Domain Behavior (PDB) for Differentiated Services , 2003, RFC.

[14]  François Baccelli,et al.  AIMD, fairness and fractal scaling of TCP traffic , 2002, Proceedings.Twenty-First Annual Joint Conference of the IEEE Computer and Communications Societies.

[15]  R. Srikant,et al.  TCP-Illinois: a loss and delay-based congestion control algorithm for high-speed networks , 2006, valuetools '06.

[16]  Derong Liu The Mathematics of Internet Congestion Control , 2005, IEEE Transactions on Automatic Control.