On Wed, 2016-12-07 at 06:26 -0800, Eric Dumazet wrote: > On Wed, 2016-12-07 at 08:57 +0100, Paolo Abeni wrote: > > On Tue, 2016-12-06 at 22:47 -0800, Eric Dumazet wrote: > > > On Tue, 2016-12-06 at 19:32 -0800, Eric Dumazet wrote: > > > > A follow up patch will provide a static_key (Jump Label) since most > > > > hosts do not even use RFS. > > > > > > Speaking of static_key, it appears we now have GRO on UDP, and this > > > consumes a considerable amount of cpu cycles. > > > > > > Turning off GRO allows me to get +20 % more packets on my single UDP > > > socket. (1.2 Mpps instead of 1.0 Mpps) > > > > I see also an improvement for single flow tests disabling GRO, but on a > > smaller scale (~5% if I recall correctly). > > Was it on a NUMA host ?
I'm using a single socket host, with 12 cores/24 threads and 16 RX queues. But my data is old. I'll re-run the test on top of current net-next. Paolo
