On Thu, Aug 15, 2019 at 6:34 PM Ming Lei <tom.leiming@xxxxxxxxx> wrote: > If nothing will change, why does the userspace bother to send > SET_STATUS? We don't change transfer, but we do change the offset and sizelimit. In our specific case, we know there won't be any I/O from userspace at this point; so from that point of view the freeze wouldn't be necessary. But I'm not sure how we can make loop aware of that in a safe way. Ideally we'd just have a way of completely configuring a loop device before starting the block request queue, but that seems like a pretty big change. Martijn > > > Thanks, > Ming Lei
