On Tue, 19 Jul 2016 15:05:37 -0700 Alexei Starovoitov <alexei.starovoi...@gmail.com> wrote:
> On Tue, Jul 19, 2016 at 12:16:57PM -0700, Brenden Blanco wrote: > > Add a sample that rewrites and forwards packets out on the same > > interface. Observed single core forwarding performance of ~10Mpps. > > > > Since the mlx4 driver under test recycles every single packet page, the > > perf output shows almost exclusively just the ring management and bpf > > program work. Slowdowns are likely occurring due to cache misses. > > long term we need to resurrect your prefetch patch. sux to leave > so much performance on the table. I will do some (more) attempts at getting prefetching working, also in a way that benefit the normal stack (when I'm back from vacation, and when net-next opens again). I think Rana is also looking into this for the mlx5 driver (based on some patches I send to her). -- Best regards, Jesper Dangaard Brouer MSc.CS, Principal Kernel Engineer at Red Hat Author of http://www.iptv-analyzer.org LinkedIn: http://www.linkedin.com/in/brouer
