Re: [Qemu-devel] [PATCH][RFC] Split non-TCG bits out of exec.c

[Anthony Liguori <anthony@codemonkey.ws>]

Jamie Lokier wrote:
> Also, an earlier thread pointed out that loops doing a lot of MMIO are
> _slower_ with KVM than without - this manifested as very slow VGA
> output for some guests.  Having KVM pass control to TCG for short runs
> of guest instructions which do MMIO, or other instructions which need
> to be emulated, would accelerate KVM in this respect.
>   

Note, the devil is in the details here.

An MMIO exit to userspace typically costs around 6k cycles.  On the 
other hand, a TB translation tends to average closer to 300k often times 
reaching much higher.  This with was with dyngen so TCG may be more or 
less expensive.

An in-kernel MMIO exit on the other hand will cost around 3k cycles.  
MMIO coalescing is pretty efficient because it effectively reduces the 
cost of a exit by half.

To make up the cost of TCG translation for just one TB, you need to have 
a tight loop of at least 50 iterations.  We can handle rep instructions 
with a single exit in KVM so this needs to be an actual MMIO loop, not a 
rep loop.

If you also consider all the potential locking issues with SMP guests, I 
think it's pretty likely that there are few cases where dropping to TCG 
is going to be a net performance win.

Regards,

Anthony Liguori

> -- Jamie
> --
> To unsubscribe from this list: send the line "unsubscribe kvm" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>