TCP Wave over Linux: A disruptive alternative to the traditional TCP window approach

Abstract TCP Wave relies on a disruptive communication paradigm based on bursts, to overcome limitations of legacy TCP with modern applications and challenging network scenarios. This protocol was already validated with appealing results via simulations. This work now presents its implementation in the Linux kernel, focusing on the adaptations needed to deal with real networking systems. A Linux implementation paves the way to validate the protocol algorithms and working principles on real communication environments, thus drawing its operational perimeter. In this regard, the most ambitious goal is to show the bright side of the burst transmission as a novel opportunity for performance optimization in the future Internet connectivity scenarios. TCP Wave performance is therefore compared with reference TCP congestion schemes currently included in the Linux kernel, namely BBR and Cubic, under a large set of network configurations. A vast gamut of performance indicators are presented and discussed, including throughput, latency, fairness, friendliness, loss management and reaction to network and traffic changes. Definitely, this paper is a manifest for the real TCP Wave implementation in Linux, which can act as reference for future works.

[1]  Cesare Roseti,et al.  Performance evaluation of TCP-based applications over DVB-RCS DAMA schemes , 2009, Int. J. Satell. Commun. Netw..

[2]  Martina Zitterbart,et al.  Experimental evaluation of BBR congestion control , 2017, 2017 IEEE 25th International Conference on Network Protocols (ICNP).

[3]  Cesare Roseti,et al.  TCP Wave estimation of the optimal operating point using ACK trains , 2018, 2018 International Symposium on Networks, Computers and Communications (ISNCC).

[4]  Cesare Roseti,et al.  TCP Wave: A new reliable transport approach for future internet , 2017, Comput. Networks.

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

[6]  Carlo Caini,et al.  TCP Hybla: a TCP enhancement for heterogeneous networks , 2004, Int. J. Satell. Commun. Netw..

[7]  Michael Welzl,et al.  An Evaluation of Tail Loss Recovery Mechanisms for TCP , 2015, CCRV.

[8]  Saneyasu Yamaguchi,et al.  Improving RTT Fairness on CUBIC TCP , 2013, 2013 First International Symposium on Computing and Networking.

[9]  Francesco Zampognaro Enabling CoDel AQM with TCP Cubic connections over satellite links , 2019, 2019 International Symposium on Advanced Electrical and Communication Technologies (ISAECT).

[10]  Raj Jain,et al.  A Quantitative Measure Of Fairness And Discrimination For Resource Allocation In Shared Computer Systems , 1998, ArXiv.

[11]  Van Jacobson,et al.  Controlling Queue Delay , 2012, ACM Queue.

[12]  N. Cardwell,et al.  Making Linux TCP Fast , 2016 .

[13]  Saverio Mascolo,et al.  Performance evaluation and comparison of Westwood+, New Reno, and Vegas TCP congestion control , 2004, CCRV.

[14]  Martina Zitterbart,et al.  TCP LoLa: Congestion Control for Low Latencies and High Throughput , 2017, 2017 IEEE 42nd Conference on Local Computer Networks (LCN).

[15]  Mo Dong,et al.  PCC: Re-architecting Congestion Control for Consistent High Performance , 2014, NSDI.

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

[17]  Cesare Roseti,et al.  Steady-state performance evaluation of Linux TCPs versus TCP wave over leaky satellite links , 2017, China Communications.

[18]  Cesare Roseti,et al.  TCP Wave Resilience to Link Changes , 2016, DCNET 2016.

[19]  Albert G. Greenberg,et al.  Data center TCP (DCTCP) , 2010, SIGCOMM '10.

[20]  Cesare Roseti,et al.  Analysis and Performance Evaluation of a Burst-Based TCP for Satellite DVB RCS Links , 2010, IEEE/ACM Transactions on Networking.

[21]  J. Tukey,et al.  Variations of Box Plots , 1978 .

[22]  Van Jacobson,et al.  BBR: Congestion-Based Congestion Control , 2016, ACM Queue.

[23]  Cesare Roseti,et al.  Evaluation of TCP wave performance applied to real HTTP traffic , 2017, 2017 International Symposium on Networks, Computers and Communications (ISNCC).

[24]  L. Peterson,et al.  TCP Vegas: new techniques for congestion detection and avoidance , 1994, SIGCOMM.