Re: Heads up: moving some uvmexp stat to being per-cpu

[Jean-Yves Migeon <jeanyves.migeon%free.fr@localhost>]

On 15.12.2010 19:43, Matt Thomas wrote:
> 
> On Dec 15, 2010, at 1:53 AM, Jean-Yves Migeon wrote:
> 
>>>> On Wed, Dec 15, 2010 at 1:49 PM, Matt Thomas 
>>>> <matt%3am-software.com@localhost> wrote:
>>>>> The diffs are at http://www.netbsd.org/uvmexp-diff.txt
>>
>> Purely cosmetic comments:
>> - why are most of the cpu_nsoft count commented out?
> 
> Because we were counting ASTs as soft interrupts but they aren't.
> kern_softint.c already counts soft interrupts.

Alright, thanks for the explanation :) Are you going to add another
counter for ASTs or leave the commented code as-is?

> I updated the patch at http://www.netbsd.org/~matt/uvmexp-diff.txt
> 
> Thanks for the comments.  On to round 2!


-- 
Jean-Yves Migeon
jeanyves.migeon%free.fr@localhost