From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tiwei Bie Subject: Re: [PATCH 1/5] net/virtio: fix vector Rx break caused by rxq flushing Date: Fri, 8 Dec 2017 10:30:34 +0800 Message-ID: <20171208023034.4f5u3fujmupraaia@debian-xvivbkq> References: <20171207053059.19487-1-tiwei.bie@intel.com> <20171207053059.19487-2-tiwei.bie@intel.com> <9407e2ce-8b2b-9a9d-a493-1757609184a9@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Cc: yliu@fridaylinux.org, maxime.coquelin@redhat.com, dev@dpdk.org, antonio.fischetti@intel.com, stable@dpdk.org, "Kavanagh, Mark B" To: Kevin Traynor Return-path: Content-Disposition: inline In-Reply-To: <9407e2ce-8b2b-9a9d-a493-1757609184a9@redhat.com> List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" On Thu, Dec 07, 2017 at 04:00:57PM +0000, Kevin Traynor wrote: > On 12/07/2017 05:30 AM, Tiwei Bie wrote: > > The vector Rx will be broken if backend has consumed all > > the descs in the avail ring before the device is started. > > Because in current implementation, vector Rx will return > > immediately without refilling the avail ring if the used > > ring is empty. So we have to refill the avail ring after > > flushing the elements in the used ring for vector Rx. > > > > Besides, vector Rx has a different ring layout assumption > > and mbuf management. So we need to handle it differently. > > > > Hi Tiwei, does the issue only occur with the vector rx? How about if the > simple rx is used because VIRTIO_NET_F_MRG_RXBUF is set? Hi Kevin, Yes, you are right! The issue only occurs with the vector Rx. The vector Rx (i.e. the simple Rx) won't be used if VIRTIO_NET_F_MRG_RXBUF is set. Best regards, Tiwei Bie