On Tue, Oct 11, 2016 at 08:39:54AM +0200, Maxime Coquelin wrote: > > > On 10/11/2016 08:04 AM, Yuanhan Liu wrote: > >On Mon, Oct 10, 2016 at 04:54:39PM +0200, Maxime Coquelin wrote: > >> > >> > >>On 10/10/2016 04:42 PM, Yuanhan Liu wrote: > >>>On Mon, Oct 10, 2016 at 02:40:44PM +0200, Maxime Coquelin wrote: > >>>>>>>At that time, a packet always use 2 descs. Since indirect desc is > >>>>>>>enabled (by default) now, the assumption is not true then. What's > >>>>>>>worse, it might even slow things a bit down. That should also be > >>>>>>>part of the reason why performance is slightly worse than before. > >>>>>>> > >>>>>>> --yliu > >>>>>> > >>>>>>I'm not sure I get what you are saying > >>>>>> > >>>>>>>commit 1d41d77cf81c448c1b09e1e859bfd300e2054a98 > >>>>>>>Author: Yuanhan Liu <yuanhan.liu at linux.intel.com> > >>>>>>>Date: Mon May 2 17:46:17 2016 -0700 > >>>>>>> > >>>>>>> vhost: optimize dequeue for small packets > >>>>>>> > >>>>>>> A virtio driver normally uses at least 2 desc buffers for Tx: the > >>>>>>> first for storing the header, and the others for storing the data. > >>>>>>> > >>>>>>> Therefore, we could fetch the first data desc buf before the main > >>>>>>> loop, and do the copy first before the check of "are we done yet?". > >>>>>>> This could save one check for small packets that just have one data > >>>>>>> desc buffer and need one mbuf to store it. > >>>>>>> > >>>>>>> Signed-off-by: Yuanhan Liu <yuanhan.liu at linux.intel.com> > >>>>>>> Acked-by: Huawei Xie <huawei.xie at intel.com> > >>>>>>> Tested-by: Rich Lane <rich.lane at bigswitch.com> > >>>>>> > >>>>>>This fast-paths the 2-descriptors format but it's not active > >>>>>>for indirect descriptors. Is this what you mean? > >>>>> > >>>>>Yes. It's also not active when ANY_LAYOUT is actually turned on. > >>>>>>Should be a simple matter to apply this optimization for indirect. > >>>>> > >>>>>Might be. > >>>> > >>>>If I understand the code correctly, indirect descs also benefit from this > >>>>optimization, or am I missing something? > >>> > >>>Aha..., you are right! > >> > >>The interesting thing is that the patch I send on Thursday that removes > >>header access when no offload has been negotiated[0] seems to reduce > >>almost to zero the performance seen with indirect descriptors enabled. > > > >Didn't follow that. > > > >>I see this with 64 bytes packets using testpmd on both ends. > >> > >>When I did the patch, I would have expected the same gain with both > >>modes, whereas I measured +1% for direct and +4% for indirect. > > > >IIRC, I did a test before (remove those offload code piece), and the > >performance was basically the same before and after that. Well, there > >might be some small difference, say 1% as you said. But the result has > >never been steady. > > > >Anyway, I think your patch is good to have: I just didn't see v2. > > I waited to gather some comments/feedback before sending the v2. > I'll send it today or tomorrow.
Interesting, I saw a deadlock then: I haven't looked at the code carefully once you said there is a v2, thus I'm waiting for it. However, you are waitting for my review. :) Anyway, I will take time to look at it shortly. --yliu