Re: [PATCH v3 0/2] kvm: level irqfd and new eoifd

[Avi Kivity <avi@redhat.com>]

On 07/11/2012 10:57 PM, Alex Williamson wrote:
>> 
>> > We still have classic KVM device assignment to provide fast-path INTx.
>> > But if we want to replace it midterm, I think it's necessary for VFIO to
>> > be able to provide such a path as well.
>> 
>> I would like VFIO to have no regressions vs. kvm device assignment,
>> except perhaps in uncommon corner cases.  So I agree.
> 
> I ran a few TCP_RR netperf tests forcing a 1Gb tg3 nic to use INTx.
> Without irqchip support vfio gets a bit more than 60% of KVM device
> assignment.  That's a little bit of an unfair comparison since it's more
> than just the I/O path.  With the proposed interfaces here, enabling
> irqchip, vfio is within 10% of KVM device assignment for INTx.  For MSI,
> I can actually make vfio come out more than 30% better than KVM device
> assignment if I send the eventfd from the hard irq handler.  Using a
> threaded handler as the code currently does, vfio is still behind KVM.
> It's hard to beat a direct call chain.

We can have a direct call chain with vfio too, using a custom eventfd
poll function, no?  Assuming we set up a fast path for unicast msi.

> For more devices, one that seems common among the non-enterprise users
> are TV capture cards, like the old PVR-250/350 devices.  These don't
> support MSI.  Thanks,

That doesn't mean they require an interrupt rate that warrants a fast
path.  But I guess that some combination of old guests or old hardware
will want it.

-- 
error compiling committee.c: too many arguments to function