[Qemu-devel] RE: [RFC] Moving the kvm ioapic, pic, and pit back to userspace

[Dong, Eddie]

>> A VF interrupt usually happens in 4-8KHZ. How about the virtio?
>> I assume virtio will be widely used together w/ leagcy guest with
>> INTx mode. 
>> 
> 
> True, but in time it will be replaced by MSI.
> 
> Note without vhost virtio is also in userspace, so there are lots of
> exits anyway for the status register.

Few months ago, we noticed the interrupt frequency of PV I/O in previous 
solution is almost same with physical NIC interrupt which ticks in ~4KHZ. Each 
PV I/O frontend driver (or its interrupt source) has similar interrupt 
frequency which means Nx more interrupt. I guess virtio is in similar situation.

We then did an optimization for PV IO to mitigate the interrupt to guest by 
setting interrupt throttle in backend side, because native NIC also does in 
that way -- so called ITR register in Intel NIC. We can see 30-90% CPU 
utilization saving depending on how many frontend driver interrupt is employed. 
Not sure if it is adopted in vhost side.

One drawback of course is the latency, but it is mostly tolerable if it is 
reduced to ~1KHZ. 

Thx, Eddie