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