A Markov model of TCP throughput, goodput and slow start

This paper presents a discrete-time Markov chain model for TCP, the Transmission Control Protocol for reliable transport on the Internet. The purpose is the evaluation of stationary TCP flows behavior using performance measures such as the mean throughput. The model is based on previous works which are generalized by taking into account the slow start phases that appear after each time-out recovery, whose importance is discussed.

[1]  Patrick Brown,et al.  Resource sharing of TCP connections with different round trip times , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

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

[3]  Jitendra Padhye,et al.  A Stochastic Model of TCP Reno Congestion Avoidence and Control , 1999 .

[4]  T. V. Lakshman,et al.  The performance of TCP/IP for networks with high bandwidth-delay products and random loss , 1997, TNET.

[5]  Matthew Mathis,et al.  The macroscopic behavior of the TCP congestion avoidance algorithm , 1997, CCRV.

[6]  Stefan Savage,et al.  Modeling TCP latency , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[7]  François Baccelli,et al.  TCP is max-plus linear: and what tells us on its throughput , 2000, SIGCOMM.

[8]  Eitan Altman,et al.  TCP in presence of bursty losses , 2000, SIGMETRICS '00.

[9]  Eitan Altman,et al.  A stochastic Model of TCP/IP with Stationary Ergodic Random Losses , 1999 .

[10]  W. Richard Stevens,et al.  TCP Slow Start, Congestion Avoidance, Fast Retransmit, and Fast Recovery Algorithms , 1997, RFC.

[11]  Alhussein A. Abouzeid,et al.  Stochastic modeling of TCP over lossy links , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[12]  Eitan Altman,et al.  Performance of TCP/IP: the case of two Controlled Sources , 1997 .

[13]  Chadi Barakat,et al.  A stochastic model of TCP/IP with stationary random losses , 2000, TNET.

[14]  Douglas E. Comer,et al.  Internetworking with TCP/IP, Volume 1: Principles, Protocols, and Architectures, Fourth Edition , 2000 .

[15]  Douglas Comer,et al.  Internetworking with TCP/IP , 1988 .

[16]  J. Boudec,et al.  The Fairness of Additive Increase and Multiplicative Decrease , 1998 .

[17]  G. Rubino,et al.  Sojourn times in finite Markov processes , 1989, Journal of Applied Probability.

[18]  W. Richard Stevens,et al.  TCP/IP Illustrated, Volume 1: The Protocols , 1994 .

[19]  Alhussein A. Abouzeid,et al.  Stochastic modeling of a single TCP/IP session over a random loss channel , 1999, Mobile Networks and Computing.

[20]  Eitan Altman,et al.  Performance Modeling of TCP/IP in a Wide-Area Network * , 1997 .

[21]  Anurag Kumar,et al.  Comparative performance analysis of versions of TCP in a local network with a lossy link , 1998, TNET.