> On Aug 31, 2016, at 10:26 PM, Kurt Jaeger <[email protected]> wrote: > > Hi! > >> Second, BFD has always been underwhelming on server platforms, >> like those that Quagga typically runs on. [...] >> I'm not aware of anyone that can do BFD in the control >> plane, and support BFD rates less than 100ms. > > ICMP round-trip can be far below 100ms (below 1ms is easy), so at least > the packet processing for BFD can be fast on a server, as well. > > Why should a server have problems with the reaction on a missing > link so that this reaction takes over 100ms ?
Because Unix isn’t a realtime OS? And ICMP echo reply processing is handled in the kernel, not user mode. So no context switches, no swapping, etc. And I said, 100m is probably achievable in Quagga, assuming the BFD patches work. Going less than 100ms is where things will get more difficult. And ICMP echo reply is only one packet per second during a typical test. Lets say you have a 50ms BFD rate (which is a typical rate). And you have 10 BGP sessions. That is 200 packets per second in BFD traffic. I’m currently working with a switch vendor that uses Linux. Their LACP implementation runs in user mode as well. They are having problems when the CPU gets swamped, they can't maintain fast LACP hello rates, to keep LAGs from flapping. And fast rate LACP is only three helos per second. > > -- > [email protected] +49 171 3101372 4 years to > go ! Tom _______________________________________________ Quagga-users mailing list [email protected] https://lists.quagga.net/mailman/listinfo/quagga-users
