Impact of Delay Variability on LEDBAT Performance

Low Extra Delay Background Transport (LEDBAT) congestion control algorithm is designed to address the unfairness problem of TCP aggravated by applications that use multiple TCP connections for data transfer. LEDBAT operates under the assumption that the queue delay at the access router of the bottleneck link will be the primary varying contributor to end-to-end one-way delay. However this assumption will not hold if a route change occurs, which causes significant variations in the path delay. This paper analyses the impact of route changes on LEDBAT throughput and fairness. In addition to a formal description of the behaviour of LEDBAT congestion window when route changes, we present results from simulations showing the negative impact of route changes on throughput for a LEDBAT source and fairness with other sources. Importantly, our analysis shows that more work is needed to improve LEDBAT performance in the case of route changes before the novel algorithm can be considered as a suitable congestion control algorithm in the Internet.

[1]  Larry L. Peterson,et al.  TCP Vegas: End to End Congestion Avoidance on a Global Internet , 1995, IEEE J. Sel. Areas Commun..

[2]  Yang Xu,et al.  A 320-Gb/s IP router with QoS control , 2002 .

[3]  Dario Rossi,et al.  The Quest for LEDBAT Fairness , 2010, 2010 IEEE Global Telecommunications Conference GLOBECOM 2010.

[4]  Dario Rossi,et al.  Yes, We LEDBAT: Playing with the New BitTorrent Congestion Control Algorithm , 2010, PAM.

[5]  Michael Welzl,et al.  A Survey of Lower-than-Best-Effort Transport Protocols , 2011, RFC.

[6]  Anees Shaikh,et al.  An empirical evaluation of wide-area internet bottlenecks , 2003, IMC '03.

[7]  Akkihebbal L. Ananda,et al.  TCP Vegas-A: Improving the Performance of TCP Vegas , 2005, Comput. Commun..

[8]  E.W. Knightly,et al.  TCP-LP: low-priority service via end-point congestion control , 2006, IEEE/ACM Transactions on Networking.

[9]  Paul Barford,et al.  Critical path analysis of TCP transactions , 2000, Comput. Commun. Rev..

[10]  Nicolae Tapus,et al.  Performance evaluation of a Python implementation of the new LEDBAT congestion control algorithm , 2010, 2010 IEEE International Conference on Automation, Quality and Testing, Robotics (AQTR).

[11]  Bo Zhang,et al.  Measurement-Based Analysis, Modeling, and Synthesis of the Internet Delay Space , 2006, IEEE/ACM Transactions on Networking.

[12]  M. Dahlin,et al.  TCP Nice: a mechanism for background transfers , 2002, OSDI '02.

[13]  Richard J. La,et al.  Issues in TCP Vegas , 1998 .

[14]  V. Jacobson,et al.  Congestion avoidance and control , 1988, CCRV.

[15]  Dario Rossi,et al.  LEDBAT: The New BitTorrent Congestion Control Protocol , 2010, 2010 Proceedings of 19th International Conference on Computer Communications and Networks.

[16]  Amuda James Abu,et al.  A Dynamic Algorithm for Stabilising LEDBAT Congestion Window , 2010, 2010 Second International Conference on Computer and Network Technology.

[17]  Tsuyoshi Katayama,et al.  Analysis and Evaluation of Packet Delay Variance in the Internet , 2002 .

[18]  Janardhan R. Iyengar,et al.  Low Extra Delay Background Transport (LEDBAT) , 2012, RFC.

[19]  Frank Kelly,et al.  Mathematical Modelling of the Internet , 2001 .

[20]  Dario Rossi,et al.  A hands-on assessment of transport protocols with lower than best effort priority , 2010, IEEE Local Computer Network Conference.