Interrupts + Polling mode (similar to Linux's NAPI)
julian at elischer.org
Tue Apr 28 16:52:34 UTC 2009
Fabien Thomas wrote:
> To share my results:
> I have done at work modification to the polling code to do SMP polling
> (previously posted to this ml).
> SMP polling (dynamic group of interface binded to CPU) does not
> significantly improve the throughput (lock contention seems to be the
> cause here).
> The main advantage of polling with modern interface is not the PPS
> (which is nearly the same) but the global efficiency of the system when
> using multiple interfaces (which is the case for Firewall).
> The best configuration we have found with FreeBSD 6.3 is to do polling
> on one CPU and keep the other CPU free for other processing. In this
> configuration the whole system
> is more efficient than with interrupt where all the CPU are busy
> processing interrupt thread.
so it would (might) be worth while working out a framework
by which this could be achieved.
More information about the freebsd-net