Re: wrapping (some) ipis in arch/x86/

[christos%astron.com@localhost (Christos Zoulas)]

In article 
<CAEmhiu6BWw4dMRekus-PsdjsGTaiNGPKkkTHn88roZ43i0EnCA%mail.gmail.com@localhost>,
Cherry G. Mathew <cherry.g.mathew%gmail.com@localhost> wrote:
>On 13 August 2011 11:45, Christos Zoulas <christos%astron.com@localhost> wrote:
>> In article
><CAEmhiu7cetkMHgK=F1fzt2R9KTb8q0csyEA=1-m+-VWEJDnMFA%mail.gmail.com@localhost>,
>> Cherry G. Mathew <cherry.g.mathew%gmail.com@localhost> wrote:
>>>On 13 August 2011 11:26, Christos Zoulas <christos%astron.com@localhost> 
>>>wrote:
>>>> In article <8762m4qlm8.fsf%zyx.in@localhost>, Cherry G. Mathew 
>>>>  <cherry%zyx.in@localhost> wrote:
>>>>>ftp://ftp.netbsd.org/pub/NetBSD/misc/cherry/tmp/wrap_ipi.diff
>>>>>
>>>>>Hi,
>>>>>
>>>>>I'd like to ask peoples' opinions about the above patch. This would
>>>>>remove a couple of #ifdef XEN/#endif pairs I had to introduce
>>>>>lately.
>>>>
>>>> If those are performance critical, perhaps they should be inlined?
>>>
>>>
>>>I don't think they are - the first is a HALT ipi and the second
>>>"kicks" other sleeping CPUS via cpu_needs_resched()
>>
>> So the first one isn't, but how often is the second one called?
>>
>
>Once per tick at worst.

Then, I guess it is ok.

christos