Lightweight Enhanced Monitoring for High-speed Networks
Résumé
In this paper, LEMON, a lightweight enhanced monitoring alg orithm based on packet sampling, is proposed. It targets a pre-assigned accuracy on bitrate estimates, for each monit ored flow at a router interface. To this end, LEMON takes into account some basic properties of the flows, which can be easil y inferred from a sampled stream, and it exploits them to dynamically adapt the monitoring time-window on a per-flow b asis. Its effectiveness has been tested using real packet traces. Experimental results show that LEMON is able to finel y tune, in real-time, the monitoring window associated to each flow and, compared to a classic fixed-scale monitoring ap proach, it is able to better satisfy the accuracy requiremen ts of bitrate estimates. Moreover, its communication overhea d can be kept low enough by choosing an appropriate aggregati on policy in the message exporting process. Finally, LEMON pro duces a low processing overhead, which can be easily sustained by currently deployed routers.