Modeling TCP Throughput with Random Packet Drops

The present report deals with the modeling of the long-term throughput, a.k.a., send rate, of the Transmission Control Protocol (TCP) under the following assumptions. (i) We consider a single 'infinite source' using a network path from sender to receiver. (ii) Each TCP packet is randomly dropped with probability p; independently of previous drops or any other event/parameter. (iii) The - never changing - receiver window limits the amount of outstanding data. (iv) The receiver acknowledges every packet. (v) The TCP modeled here conforms to the publicly available standards (RFCs) as concerns congestion control. We validate and determine the limits of the different models proposed here using packet-level simulations. The contributions of the present work are the following: (a) We determine three regimes, and their conditions of applicability, depending on p: Linear law regime, square root law regime, and timeout regime. (b) As concerns the relationship between the linear and square root regimes, we give additional insights relatively to previously published work. (c) We give the exact equations governing the TCP send rate in any regime. (d) From the exact equation and under the further condition that the path is not saturated, we give and discuss approximations for the send rate of the NewReno variant of TCP. A by-product of these calculations is the distribution of the sender window, independently of any timing or saturation consideration. (e) These approximations give results that are accurate to a few percent when compared to simulation results. Detailed comparison and sources of errors between theory and simulations are also discussed.

• Publication year

  2014

• Venue

  arXiv.org

• Publication date

  2014-01-31

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1401.8173
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A Roadmap for Transmission Control Protocol (TCP) Specification Documents

  2015influential reference
• TCP Congestion Avoidance Algorithm Identification

  2011cited by this paper
• An Analytic Throughput Model for TCP NewReno

  2010cited by this paper
• TCP revisited: a fresh look at TCP in the wild

  2009cited by this paper
• Reflections on the TCP macroscopic model

  2008influential reference
• A Performance Study of Loss Detection/Recovery in Real-world TCP Implementations

  2007cited by this paper
• The PFTK-model revised

  2006cited by this paper
• The Transmission Control Protocol

  2005cited by this paper
• Measuring the evolution of transport protocols in the internet

  2005cited by this paper
• The NewReno Modification to TCP's Fast Recovery Algorithm

  2004cited by this paper
• A Markov model of TCP throughput, goodput and slow start

  2004cited by this paper
• TCP Congestion Control with Appropriate Byte Counting (ABC)

  2003cited by this paper
• TCP/IP modeling and validation

  2001influential reference
• A stochastic model of TCP/IP with stationary random losses

  2000cited by this paper
• Modeling TCP Reno performance: a simple model and its empirical validation

  2000cited by this paper
• Computing TCP's Retransmission Timer

  2000cited by this paper
• TCP Congestion Control

  1999cited by this paper
• The macroscopic behavior of the TCP congestion avoidance algorithm

  1997influential reference
• The Implementation

  1995cited by this paper
• Requirements for Internet Hosts - Communication Layers

  1989cited by this paper

• No citing papers are available for this paper.