Re: [RFC] Paravirt timer for KVM

[Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>]

Glauber de Oliveira Costa wrote:
> On 10/15/07, Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org> wrote:
>   
>> If we want to make the clocksource useful for Windows we need to go
>> through the apic as that will allow the TPR to mask the interrupt when
>> Windows isn't ready to receive it.  However I don't know whether it is
>> possible to integrate a paravirt clocksource into Windows.
>>     
>
> My politically-correct side told me to say that the solution that
> works also in Windows is the best one ;-)
>
>   

In this case, I'm not at all sure Windows can benefit from a paravirt
timesource, so it might be better to concentrate on Linux. I'll ask the
Windows people here.

>> For Linux, we might as well go further and provide a completely
>> paravirtualized irqchip instead of trying to integrate a paravirtualized
>> clocksource into a fullyvirtualized irqchip.
>>
>>     
>
> Yes, definitely. In your opinion, what's the size of the gap between
> the "we can", and the "we should" here?
>   

At present the APIC requires an exit for each level-triggered interrupt.
We could reduce the number of exits to zero given sufficient cleverness.
This would be beneficial to non-streaming I/O workloads.

So yes, I think it's worthwhile.

-- 
Do not meddle in the internals of kernels, for they are subtle and quick to panic.


-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems?  Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >> http://get.splunk.com/