A two-way link loss measurement approach for software-defined networks

Packet loss rate is an important consideration in the Quality of Service (QoS) measurement for a packet-switched network. The software-defined networking (SDN) technique can conveniently monitor flow statistics. However, the packet loss rate of a link or path cannot be directly measured by inquiring the statistics of an ongoing flow at the starting and ending points because it is impossible to accurately compute and control pairwise sampling moments. In this paper, we propose a two-way link-level packet loss measurement solution for software-defined networks. We solve the flow statistics sampling problem mentioned above by inquiring the statistics of a terminated probe flow. We propose a ring-based packet loss probe structure, which contains every measured directed link once and only once. The proposed probe structure effectively avoids the mutual interference between different probe flows, and thereby improves probe accuracy. The ring is implemented based on the flexible flow match capability of SDN. We further study an optimization problem of ring-based packet loss probe structure that strives to minimize the maximum delay of rings. This optimization problem is very complex, and we approximately solve it using a top-down-top graph partition method. A packet loss positioning method, based on flow statistic inquiries and the symmetry design of the probe ring, is also proposed herein.

[1]  Nick McKeown,et al.  OpenFlow: enabling innovation in campus networks , 2008, CCRV.

[2]  Cecília de A. Castro César,et al.  A network monitor and controller using only OpenFlow , 2015, 2015 Latin American Network Operations and Management Symposium (LANOMS).

[3]  Jin Cao,et al.  Network Tomography: Identifiability and Fourier Domain Estimation , 2007, IEEE INFOCOM 2007 - 26th IEEE International Conference on Computer Communications.

[4]  Guangmin Hu,et al.  Accurate and effective inference of network link loss from unicast end-to-end measurements , 2012, IET Commun..

[5]  Mathieu Bouet,et al.  Monitoring latency with OpenFlow , 2013, Proceedings of the 9th International Conference on Network and Service Management (CNSM 2013).

[6]  Vern Paxson,et al.  End-to-end Internet packet dynamics , 1997, SIGCOMM '97.

[7]  Mounir Hamdi,et al.  FlowCover: Low-cost flow monitoring scheme in software defined networks , 2014, 2014 IEEE Global Communications Conference.

[8]  Ratul Mahajan,et al.  User-level internet path diagnosis , 2003, SOSP '03.

[9]  Stefan Savage,et al.  Sting: A TCP-based Network Measurement Tool , 1999, USENIX Symposium on Internet Technologies and Systems.

[10]  Ibrahim Matta,et al.  On the origin of power laws in Internet topologies , 2000, CCRV.

[11]  Helen J. Wang,et al.  Server-based inference of Internet link lossiness , 2003, IEEE INFOCOM 2003. Twenty-second Annual Joint Conference of the IEEE Computer and Communications Societies (IEEE Cat. No.03CH37428).

[12]  Patrick Thiran,et al.  Network loss inference with second order statistics of end-to-end flows , 2007, IMC '07.

[13]  Kazuho Watanabe,et al.  Packet loss rate estimation with active and passive measurements , 2012, Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference.

[14]  Yao Zhao,et al.  Towards unbiased end-to-end network diagnosis , 2009, TNET.

[15]  Nick G. Duffield,et al.  On Passive One-Way Loss Measurements Using Sampled Flow Statistics , 2009, IEEE INFOCOM 2009.

[16]  Benjamin Teitelbaum,et al.  A One-way Active Measurement Protocol (OWAMP) , 2006, RFC.

[17]  Paul Barford,et al.  Improving accuracy in end-to-end packet loss measurement , 2005, SIGCOMM '05.