If you tried it and it didn't improve, then I think what we have now is great.
Ethan On Tue, Jun 16, 2015 at 9:08 AM, Daniele Di Proietto <diproiet...@vmware.com> wrote: > > On 16/06/2015 09:55, "Gray, Mark D" <mark.d.g...@intel.com> wrote: > >>> >> >>> Acked-by: Ethan Jackson <et...@nicira.com> >> >>> >> >>> One question I had for a future patch. Have you considered prefetching >> >>> more packets at once? I.E. 4 at a time or something? >> >>> That's how these things are typically written, though I don't know if >>>it would >> >>> actually affect things. >> >> >> >>yeah, I was going to suggest the same thing. In most DPDK apps, we would >> >>prefetch about 3. > > I've very briefly trying to do something more sophisticated, but I didn't > manage to get any significant improvement. > > I just posted this because it's a simple 5 lines change that removes an > easy > bottleneck. > > I definitely agree that it might be worth to work more on that code in > the future to squeeze more pps. > _______________________________________________ dev mailing list dev@openvswitch.org http://openvswitch.org/mailman/listinfo/dev
