LLDP based link latency monitoring in software defined networks

Current latency monitoring approaches for Software Defined Network often use the control plane as the infrastructure to inject time-stamp data packets as probe packets to measure the network latency at a particular time, but suffer from three major issues when the network latency needs to be continuously monitored: 1) the increased control plane's overhead, 2) the feasibility of using data packets as probe packets, and 3) the increasing measurement error using OpenFlow messages to measure the time from the controller to a switch as the network scale grows. To overcome these issues, this paper proposes link latency monitoring using time-stamped Link Layer Discovery Protocol (LLDP) packets, aided by a linear calibration function to reduce errors of measuring switch-controller delays. Time-stamping LLDP packets, which are used to discover the global network topology in SDNs, does not add extra workload to the control plane and the results always reach the controller thus while avoiding measurement failures that might occur in existing approaches. Our linear calibration function can reduce the measurement error to less than 5% of the link latency measured by ping in a network with up to 30 switches and the link latency not less than 1ms.

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

[2]  Qiang Xu,et al.  Software-Defined Latency Monitoring in Data Center Networks , 2015, PAM.

[3]  Philippe Owezarski,et al.  Design and Deployment of a Passive Monitoring Infrastructure , 2001, IWDC.

[4]  Fernando A. Kuipers,et al.  OpenNetMon: Network monitoring in OpenFlow Software-Defined Networks , 2014, 2014 IEEE Network Operations and Management Symposium (NOMS).

[5]  Nick McKeown,et al.  A network in a laptop: rapid prototyping for software-defined networks , 2010, Hotnets-IX.

[6]  Sundar Balasubramaniam,et al.  Real-time monitoring of network latency in Software Defined Networks , 2015, 2015 IEEE International Conference on Advanced Networks and Telecommuncations Systems (ANTS).

[7]  Minlan Yu,et al.  Scalable flow-based networking with DIFANE , 2010, SIGCOMM 2010.

[8]  E. Chemeritskiy,et al.  On real-time delay monitoring in software-defined networks , 2014, 2014 First International Science and Technology Conference (Modern Networking Technologies) (MoNeTeC).