On Tue, 2018-08-07 at 13:19 +0100, Daniel P. Berrangé wrote: > On Mon, Aug 06, 2018 at 11:38:06AM +0200, Andrea Bolognani wrote: > > I wonder how to handle architectures where QEMU never declared a > > default machine type, such as aarch64 and riscv64, though: I think > > it would make sense to prefer the virt machine type there, but I'm > > not entirely sure that wouldn't cause any breakages either... > > Existing libvirt behaviour is that we'll pick the first reported machine > type, so we have to preserve that. Right, makes sense. I guess with aarch64/virt first and x86_64/q35 now it won't take too long for applications to figure out they should specify the machine type explicitly rather than leaving that up to libvirt :) -- Andrea Bolognani / Red Hat / Virtualization -- libvir-list mailing list libvir-list@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/libvir-list
