On Thu, May 28, 2015 at 3:05 PM, Fam Zheng <f...@redhat.com> wrote: > On Thu, 05/28 13:19, Paolo Bonzini wrote: >> >> >> On 28/05/2015 13:11, Fam Zheng wrote: >> > > Whoever uses ioeventfd needs to implement pause/resume, yes---not just >> > > dataplane, also "regular" virtio-blk/virtio-scsi. >> > > >> > > However, everyone else should be okay, because the bottom half runs >> > > immediately and the big QEMU lock is not released in the meanwhile. So >> > > the CPUs have no occasion to run. This needs a comment! >> > >> > I'm not sure. It seems timer callbacks also do I/O, for example >> > nvme_process_sq(). >> >> Right, that's also true for USB devices. :( >> >> Perhaps we can skip block_job_defer_to_main_loop if not necessary >> (bs->aio_context == qemu_get_aio_context()). > > I think so. It will make dataplane even more specialized but that seems the > only way to fix the problem at the moment. > > Fam >
Sorry for a potential thread hijack, but I`m curious about the reasons to not making advertised queue depth for non-passthrough backends an independent tunable, is there any concerns behind that?
