On Apr 12, 2013, at 1:59 AM, Amadine Florence wrote: > Hello! > I have to make several stress-testing OpenFlow controller to quantify its > robustness and performance. > > I must designe stress tests to implement, with the aim of measuring the > response time at different load levels and to determine the growth of > switching tables after various attacks (eg, spoofing) acting at Ethernet and > / or IP and / or TCP / UDP.
It should be pointed out that stress testing the switch component in NOX is not indicative of much. NOX is a framework for writing controllers, and the switch application hardly counts as a real controller -- real control logic is likely to have extremely different behavior. -- Murphy _______________________________________________ openflow-discuss mailing list openflow-discuss@lists.stanford.edu https://mailman.stanford.edu/mailman/listinfo/openflow-discuss
