Abstract
In this paper, we derive an approximation for throughput of TCP Compound connections under random losses. Throughput expressions for TCP Compound under a deterministic loss model exist in the literature. These are obtained assuming that the window sizes are continuous, i.e., a fluid behavior is assumed. We validate this model theoretically. We show that under the deterministic loss model, the TCP window evolution for TCP Compound is asymptotically periodic and is independent of the initial window size. We then consider the case when packets are lost randomly and independently of each other. We discuss Markov chain models to analyze performance of TCP in this scenario. We use insights from the deterministic loss model to get an appropriate scaling for the window size process and show that these scaled processes, indexed by p, the packet error rate, converge to a limit Markov chain process as p goes to 0. We show the existence and uniqueness of the stationary distribution for this limit process. Using the stationary distribution for the limit process, we obtain approximations for throughput, under random losses, for TCP Compound when packet error rates are small. We compare our results with ns2 simulations which show a good match and a better approximation than the fluid model at low p.
Similar content being viewed by others
Notes
\(\lfloor {x}\rfloor \) is the largest integer smaller than x.
References
Allman, M., Paxson, V., Stevens, W.: TCP Congestion Control. RFC 2581 (Proposed Standard) (1999)
Altman, E., Avrachenkov, K., Barakat, C.: A stochastic model of TCP/IP with stationary random losses. SIGCOMM Comput. Commun. Rev. 30(4), 231–242 (2000)
Asmussen, S.: Applied probability and queues. In: Devroye, L., Gyorfi, L., Lugosi, G. (eds.) Applications of Mathematics Stochastic Modelling and Applied Probability, vol. 51, 2nd edn. Springer, New York (2003)
Athreya, K., Lahiri, S.: Measure Theory and Probability Theory. Springer Texts in Statistics. Springer, New York (2006)
Balakrishnan, H., Padmanabhan, V.N., Seshan, S., Katz, R.H.: A comparison of mechanisms for improving TCP performance over wireless links. IEEE/ACM Trans. Netw. 5(6), 756–769 (1997)
Blanc, A., Avrachenkov, K., Collange, D., Neglia, G.: Compound TCP with Random Losses. In: Proceedings of the 8th International IFIP-TC 6 Networking Conference. NETWORKING ’09, pp. 482–494. Springer, Heidelberg (2009)
Borman, D., Scheffenegger, R., Jacobson, V.: TCP extensions for high performance. RFC 7323 (2014)
Cardwell, N., Savage, S., Anderson, T.: Modeling TCP latency. In: IEEE Infocom, pp. 1724–1751 (2000)
Chavan, S., Raina, G.: Performance of TCP with a Proportional Integral Enhanced (PIE) queue management policy. In: 2015 27th Chinese Control and Decision Conference (CCDC), pp. 1013–1018 (2015)
Dumas, V., Guillemin, F., Robert, P.: A Markovian analysis of additive-increase multiplicative-decrease algorithms. Adv. Appl. Probab. 34(1), 85–111 (2002)
Enachescu, M., Ganjali, Y., Goel, A., McKeown, N., Roughgarden, T.: Part III: routers with very small buffers. ACM SIGCOMM Comput. Commun. Rev. 35(3), 83–90 (2005)
Floyd, S.: HighSpeed TCP for Large Congestion Windows. RFC 3649 (Experimental) (2003)
Floyd, S., Henderson, T.: The NewReno Modification to TCP’s Fast Recovery Algorithm. RFC 2582 (Experimental) (1999)
Floyd, S., Henderson, T., Gurtov, A.: The NewReno Modification to TCP’s Fast Recovery Algorithm. RFC 3782 (Proposed Standard) (2004)
Gettys, J., Nichols, K.: Bufferbloat: dark buffers in the internet. Queue 9(11), 40 (2011)
Ghosh, D., Jagannathan, K., Raina, G.: Right buffer sizing matters: stability, queuing delay and traffic burstiness in compound TCP. In: 2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton 2014), pp. 1132–1139 (2014)
Gupta, A., Sharma, V.: A unified approach for analyzing persistent, non-persistent and ON–OFF TCP sessions in the internet. Perform. Eval. 63(2), 79–98 (2006)
Ha, S., Rhee, I., Xu, L.: CUBIC: a new TCP-friendly high-speed TCP variant. SIGOPS Oper. Syst. Rev. 42, 64–74 (2008)
Huston, G.: Gigabit TCP. Internet Protoc. J. 2, 64–69 (2006)
Kelly, T.: Scalable TCP: improving performance in highspeed wide area networks. SIGCOMM Comput. Commun. Rev. 33(2), 83–91 (2003)
Lakshman, T.V., Madhow, U.: The performance of TCP/IP for networks with high bandwidth-delay products and random loss. IEEE/ACM Trans. Netw. 5, 336–350 (1997)
Manjunath, S., Raina, G.: Analyses of compound TCP with random early detection (RED) queue management. In: 2015 27th Chinese Control and Decision Conference (CCDC), pp. 5334–5339 (2015)
Mathis, M., Semke, J., Mahdavi, J., Ott, T.: The macroscopic behavior of the TCP congestion avoidance algorithm. SIGCOMM Comput. Commun. Rev. 27, 67–82 (1997)
Mills, K.L., Filliben, J.J., Cho, D.Y., Schwartz, E., Genin, D.: Study of Proposed Internet Congestion Control Mechanisms. DIANE, New York (2011)
Misra, V., Gong, W.B., Towsley, D.: Fluid-based analysis of a network of AQM routers supporting TCP flows with an application to RED. ACM SIGCOMM Computer Communication Review, vol. 30, pp. 151–160. ACM, New York (2000)
Nichols, K., Jacobson, V.: Controlling queue delay. Commun. ACM 55(7), 42–50 (2012)
Padhye, J., Firoiu, V., Towsley, D.F., Kurose, J.F.: Modeling TCP reno performance: a simple model and its empirical validation. IEEE/ACM Trans. Netw. 8, 133–145 (2000)
Poojary, S., Sharma, V.: Theoretical analysis of high-speed multiple TCP connections through multiple routers. In: ICC. IEEE, Piscataway (2013)
Raina, G., Towsley, D., Wischik, D.: Part II: control theory for buffer sizing. ACM SIGCOMM Comput. Commun. Rev. 35(3), 79–82 (2005)
Shakkottai, S., Srikant, R.: How good are deterministic fluid models of internet congestion control? In: IEEE Infocom, vol. 2, pp. 497–505 (2002)
Sharma, V., Purkayastha, P.: Stability and analysis of TCP connections with RED control and exogenous traffic. Queueing Syst. Theory Appl. 48, 193–235 (2004)
Shorten, R., King, C., Wirth, F., Leith, D.: Modelling TCP congestion control dynamics in drop-tail environments. Automatica 43(3), 441–449 (2007)
Shorten, R.N., Leith, D.J.: H-TCP: TCP for high-speed and long-distance networks. In: Proceedings PFLDnet, Argonne (2004)
Talbot, D.: A Bandwidth Breakthrough. https://www.technologyreview.com/s/429722/a-bandwidth-breakthrough/. Accessed 14 Oct 2016
Tan, K., Song, J., Zhang, Q., Sridharan, M.: A compound TCP approach for high-speed and long distance networks. In: IEEE Infocom (2006)
Tweedie, R.: The existence of moments for stationary Markov chains. J. Appl. Probab. 6, 191–196 (1983)
Wei, D.X., Jin, C., Low, S.H., Hegde, S.: FAST TCP: motivation, architecture, algorithms, performance. IEEE/ACM Trans. Netw. 14(6), 1246–1259 (2006)
Wischik, D., McKeown, N.: Part I: buffer sizes for core routers. ACM SIGCOMM Comput. Commun. Rev. 35(3), 75–78 (2005)
Xu, L., Harfoush, K., Rhee, I.: Binary increase congestion control (BIC) for fast long-distance networks. In: IEEE Infocom (2004)
Yang, P., Shao, J., Luo, W., Xu, L., Deogun, J., Lu, Y.: TCP congestion avoidance algorithm identification. IEEE/ACM Trans. Netw. 22(4), 1311–1324 (2014)
Author information
Authors and Affiliations
Corresponding author
Additional information
Preliminary version of this paper was presented in the National Conference on Communications, India, 2016.
Appendix
Appendix
Proposition 8
Suppose \(\{X(p)\}\) is a family of positive random variables indexed by \(p \in I\), for some \(I \subset {\mathbb {R}}\) such that
for all y, for some \(c_1 > 0\) and \(c_2 > 0\). Then there exists \(t>0\) such that
Proof
For any \(u > 0\) and \(p > 0\),
For \(u < c_2\), \(\int _{1}^{\infty } \frac{c_1}{y^{\frac{c_2}{u}}} < \infty \). Therefore \(\sup _{u \in [0,c_2 - \epsilon ]} \sup _{p \in I} {\mathbb {E}}[\mathrm{e}^{uX(p)}] < \infty \), where \(\epsilon \) is a positive constant less than \(c_2\). For \(u<0\), \(uX(p) \le 0\) which implies \(\sup _{p \in I} {\mathbb {E}}[\mathrm{e}^{uX(p)}] \le 1\), for \(u < 0\). \(\square \)
Proposition 9
Let \(\{X_p(x), x \in {\mathbb {R}}^+\}\), be a process, for \(0< p < 1\), which converges to a limiting process X(x) uniformly in the sense that
for any finite M, and for each x, the limiting distribution, \({\mathbb {P}}(X(x) \le y) \) is continuous. Then,
for any \(f:\mathbb {R^+}\rightarrow {\mathbb {R}}\) continuous with compact support.
Proof
Consider a continuous function f with compact support [0, K]. Such a function is uniformly continuous. Therefore, given any \(\epsilon \), there exist m points \(u_0 = 0< u_1< \cdots < u_m = K\), such that
for all \(i=1,2,\cdots , m\). We have
From (35),
Similarly,
Therefore,
where \(\parallel f \parallel _{\infty } = \sup \{f(x): x \in [0,K] \}\). Since f is continuous over a compact support, it is bounded and hence \( \parallel f \parallel _{\infty } < \infty \). Therefore,
The second relation follows from the hypothesis (34). Since \(\epsilon \) is arbitrary, we get the desired result. \(\square \)
Rights and permissions
About this article
Cite this article
Poojary, S., Sharma, V. An asymptotic approximation for TCP compound. Queueing Syst 85, 211–247 (2017). https://doi.org/10.1007/s11134-016-9509-7
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11134-016-9509-7