> -----Original Message----- > From: Stefan Hajnoczi [mailto:stefa...@gmail.com] > Sent: Thursday, January 25, 2018 10:22 PM > To: Bie, Tiwei <tiwei....@intel.com> > Cc: qemu-devel@nongnu.org; virtio-...@lists.oasis-open.org; > m...@redhat.com; alex.william...@redhat.com; jasow...@redhat.com; > pbonz...@redhat.com; stefa...@redhat.com; Tan, Jianfeng > <jianfeng....@intel.com>; Liang, Cunming <cunming.li...@intel.com>; > Wang, Xiao W <xiao.w.w...@intel.com>; Wang, Zhihong > <zhihong.w...@intel.com>; Daly, Dan <dan.d...@intel.com> > Subject: Re: [Qemu-devel] [PATCH v1 0/6] Extend vhost-user to support > VFIO based accelerators > > On Thu, Jan 25, 2018 at 12:03:22PM +0800, Tiwei Bie wrote: > > Why extend vhost-user for vDPA > > ============================== > > > > We have already implemented various virtual switches (e.g. OVS-DPDK) > > based on vhost-user for VMs in the Cloud. They are purely software > > running on CPU cores. When we have accelerators for such NFVi > > applications, it's ideal if the applications could keep using the > > original interface (i.e. vhost-user netdev) with QEMU, and > > infrastructure is able to decide when and how to switch between CPU > > and > accelerators within the interface. > > And the switching (i.e. switch between CPU and accelerators) can be > > done flexibly and quickly inside the applications. > > > > More details about this can be found from the Cunming's discussions > > on the RFC patch set. > > > > The previous links: > > RFC: > > http://lists.nongnu.org/archive/html/qemu-devel/2017-12/msg04844.htm > > l > > Is vDPA also useful in the simpler use case where there is no NFVi > application? There're separate patches to have non-DPDK vDPA(aka. vhost-vfio, a new vhost backend proposed) support, which is the scope of stage-II as we mentioned in community call. Stay tuned for the RFC patch. Main idea is that the virtio compatible device driver register as a mdev to talk with qemu vhost-vfio.
> > In other words, you have virtio-net inside the guest and vhost-net on the > host. > You'd like to accelerate the virtio-net NIC using the hardware's vDPA support. > > DPDK requires dedicated logical cores and hugepages. Those resources > will not be used (wasted) if you just want to enable vDPA but have no > DPDK packet processing application. > > How can this use case be supported without wasting resources? > > Stefan
