Re: [Qemu-devel] Better qemu/kvm defaults (was Re: [RFC PATCH 0/4] Gang scheduling in CFS)

[Dor Laor]

On 01/04/2012 12:45 AM, Anthony Liguori wrote:
> > > When using 'guests-pick', we initially present the most compatible
> > > network model (rtl8139, for instance). We would provide a paravirtual
> > > channel (guest-agent?) that could be used to enumerate which models were
> > > available and let guest decide which model to use for the next reboot.
> > > You could also enable immediate switch over using hot plug.
> >
> > If guest uses an agent, it probably has virtio-serial driver and it
> > indicates it
> > has other virtio ones, otherwise, the agent won't fly
>
> Right, but I still you want the ability for the guest to indicate that
> it would like to use virtio drivers or not.

It would probably require a PCI 4.0 edition...

> If you think about it, it makes no sense to choose which type of device
> gets used in the hypervisor.  In an ideal world, the guest would just
> figure out what it wants to see and get that.
>
> The same is probably true about most device model properties.  rtc clock
> slew policy is another good example.  Instead of trying to figure out
> what the guest type is, we should just let the guest request device
> model settings like that.

The poor guest only wanted to have a real time clock that works w/ fine 
grain time stamps. It was x86 vendors w/ the help of few programmers who 
kept addition various ideas like tsc, hpet, constant_tsc, non stop tsc, 
really really non stop tsc + timer,...

Cheers,
Dor