On Wed, May 19, 2010 at 10:06 AM, Avi Kivity <avi@xxxxxxxxxx> wrote: >> In the cache=writeback case the virtio-blk guest driver does: >> >> blk_queue_ordered(q, QUEUE_ORDERED_DRAIN_FLUSH, ...) >> > > I don't follow. What's the implication? I was wondering whether the queue is incorrectly set to a mode where overlapping write requests aren't being ordered. Anyway, Christoph says overlapping write requests can be issued so my theory is broken. > btw I really dislike how the cache attribute (which I see as a pure host > choice) is exposed to the guest. It means we can't change caching mode on > the fly (for example after live migration), or that changing caching mode > during a restart may expose a previously hidden guest bug. Christoph has mentioned wanting to make the write cache switchable from inside the guest. Stefan -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
