Understanding TCP cubic performance in the cloud: A mean-field approach

Cloud networking typically leads to scenarii where a large number of TCP connections share a common bottleneck link. In this paper, we focus on the case of TCP Cubic, which is the default TCP version in the Linux kernel. TCP Cubic is designed to better utilize high bandwidth-delay product path in an IP network. To do so, Cubic modifies the linear window growth function of legacy TCP standards, e.g., New Reno, to be a cubic function. Our objective in this work is to assess the performance of TCP Cubic in a cloud setting with a large number of long-lived TCP flows.We rely on a mean-field approach leading to a fluid model to analyze the performance of Cubic. After a careful validation of the model through comparisons with ns-2, we evaluate the efficiency and fairness of Cubic as compared to that of New Reno for a set of typical cloud networking scenarii.

[1]  S. Hassayoun,et al.  Loss synchronization and router buffer sizing with high-speed versions of TCP , 2008, IEEE INFOCOM Workshops 2008.

[2]  François Baccelli,et al.  A mean-field model for multiple TCP connections through a buffer implementing RED , 2002, Perform. Evaluation.

[3]  Alberto Blanc,et al.  Comparing Some High Speed TCP Versions under Bernoulli Losses , 2009 .

[4]  Gaurav Raina,et al.  An experimental evaluation of CUBIC TCP in a small buffer regime , 2011, 2011 National Conference on Communications (NCC).

[5]  Vinod Sharma,et al.  Analytical Model for Congestion Control and Throughput with TCP CUBIC Connections , 2011, 2011 IEEE Global Telecommunications Conference - GLOBECOM 2011.

[6]  Victor C. M. Leung,et al.  A Model for Steady State Throughput of TCP CUBIC , 2010, 2010 IEEE Global Telecommunications Conference GLOBECOM 2010.

[7]  T. Kurtz.  Solutions of ordinary differential equations as limits of pure jump markov processes , 1970, Journal of Applied Probability.

[8]  Brahim Bensaou,et al.  Can high-speed networks survive with DropTail queues management? , 2007, Comput. Networks.

[9]  T. N. Vijaykumar,et al.  Deadline-aware datacenter tcp (D2TCP) , 2012, CCRV.

[10]  Qian Zhang,et al.  A Compound TCP Approach for High-Speed and Long Distance Networks , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[11]  M. Benaïm,et al.  A class of mean field interaction models for computer and communication systems , 2008, 2008 6th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks and Workshops.

[12]  Jean-Yves Le Boudec,et al.  A class of mean field interaction models for computer and communication systems , 2008, Perform. Evaluation.

[13]  Douglas J. Leith,et al.  Experimental evaluation of Cubic-TCP , 2008 .

[14]  Matti Siekkinen,et al.  Understanding the Impact of the Access Technology: The Case of Web Search Services , 2011, TMA.

[15]  Injong Rhee,et al.  Stochastic Ordering for Internet Congestion Control and its Applications , 2007, IEEE INFOCOM 2007 - 26th IEEE International Conference on Computer Communications.

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

[17]  Injong Rhee,et al.  Binary increase congestion control (BIC) for fast long-distance networks , 2004, IEEE INFOCOM 2004.

[18]  Injong Rhee,et al.  CUBIC: a new TCP-friendly high-speed TCP variant , 2008, OPSR.

[19]  Jitender S. Deogun,et al.  TCP Congestion Avoidance Algorithm Identification , 2011, 2011 31st International Conference on Distributed Computing Systems.

[20]  Nick McKeown,et al.  Part I: buffer sizes for core routers , 2005, CCRV.

[21]  David A. Maltz,et al.  Network traffic characteristics of data centers in the wild , 2010, IMC '10.