From mboxrd@z Thu Jan 1 00:00:00 1970 From: Vivek Goyal Subject: Re: virtq questions Date: Wed, 2 Oct 2019 09:27:34 -0400 Message-ID: <20191002132734.GA6972@redhat.com> References: Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: virtualization-bounces@lists.linux-foundation.org Errors-To: virtualization-bounces@lists.linux-foundation.org To: Miklos Szeredi Cc: "Dr. David Alan Gilbert" , Stefan Hajnoczi , virtualization@lists.linux-foundation.org List-Id: virtualization@lists.linuxfoundation.org On Wed, Oct 02, 2019 at 09:40:11AM +0200, Miklos Szeredi wrote: > Looking at the ugly retry logic in virtiofs and have some questions. Hi Miklos, What are you thinking w.r.t cleanup of retry logic. As of now we put requests in a list and retry later with the help of a worker. Other option will probably be block the submitter if queue is full. Make it sleep, wake up after a while and retry submission. > First one is, where do these features come from: > > VIRTIO_F_RING_PACKED > VIRTIO_RING_F_INDIRECT_DESC Looks like these feature bits are supposed to be advertised by the device if device supports these capabilities. I see in qemu code that bunch of drivers are advertisig this capability. (virtio_scsi, virtio_blk etc). > > I see that in virtiofs "packed" is off and "indirect" is on. Is this > guaranteed? I can't find specifying any feature bits in vhost-user-fs.c. So we probably are getting a default value. Thanks Vivek