> -----Original Message----- > From: Jason Wang [mailto:jasow...@redhat.com] > Sent: Thursday, March 1, 2018 9:18 PM > To: Zhang, Qi Z <qi.z.zh...@intel.com> > Cc: Karlsson, Magnus <magnus.karls...@intel.com>; Topel, Bjorn > <bjorn.to...@intel.com>; dev@dpdk.org > Subject: Re: [dpdk-dev] [RFC 0/7] PMD driver for AF_XDP > > > > On 2018年03月01日 20:56, Zhang, Qi Z wrote: > >>>>>> BTW, performance test shows our PMD can reach 94%~98% of the > >>>>>> orignal benchmark when share memory is enabled. > >>>>> Hi: > >>>>> > >>>>> Looks like zero copy is not used in this series. Any plan to support > that? > >>>> Zero copy is enabled in patch 5, if a mempool passed check_mempool, > >>>> it will be registered to af_xdp socket. > >>>> so there will be no memcpy between mbuf and af_xdp. > >> Aha, I see. So the zerocopy was limited to some specific use case. > >> And if I understand it correctly, zc mode could not be used for VM. > > I think except the limitation for mempool layout, zerocopy is transparent > to DPDK application, only difference is performance. > > Sorry, I may not get your point, if you could explain more about the VM > usage. > > > > Regards > > Qi > > No problem, so the question is: > > Can zerocopy be used when using testpmd to foward packets between > vhost-user and AF_XDP socket?
I'm not very familiar with vhost-user, but I guess the answer should be same as the case for forward packet between vhost-user and i40e, (if vhost-user does not have any special requirement for mempool that conflict with af_xdp ZC's requirement) Regards Qi > > Thanks
