Linux compatible setaffinity.

[Jeff Roberson]

On Tue, 25 Dec 2007, David Xu wrote:

> Brian McGinty wrote:
>> On Dec 23, 2007 5:44 PM, David Xu <davidxu at freebsd.org> wrote:
>>> Robert Watson wrote:
>>>> On Fri, 21 Dec 2007, David Xu wrote:
>>>> 
>>>>> I don't say no to these interfaces, but there is a need to tell user
>>>>> which cpus are sharing cache, or memory distance is closest enough,
>>>>> and which cpus are servicing interrupts, e.g, network interrupt and
>>>>> disks etc, etc, otherwise, blindly setting cpu affinity mask only can
>>>>> shoot itself in the foot.
>>>> While the Mac OS X API is pretty Mach-specific, it's worth taking a look
>>>> at their recently-announced affinity API:
>>>> 
>>>> http://developer.apple.com/releasenotes/Performance/RN-AffinityAPI/index.html
>>>> 
>>>> 
>>>> Robert N M Watson
>>>> Computer Laboratory
>>>> University of Cambridge
>>>> 
>>> 
>>> I like the interfaces, it is more flexible.
>> 
>> I agree. May I as k what's being planned? It's Jeffs' call finally I think.
>> 
>> Brian.
>
> I don't have plan. ;-) If I understand it correctly, it is a hint to
> scheduler, it is better describing thread relationship, while Jeff's
> interface is a hard cpu binding interface, it is still needed in some 
> circumstance.

Yes, I don't think they're exclusive.

However, the system scheduler makes some observations about what threads 
might be best placed near each other.  I have plans to make ULE even 
smarter in this regard so that the application developers would almost 
never need to hint it.  I think these kinds of hints are not often correct 
or very useful anyway.

Thanks,
Jeff

>
> Regards,
>
> _______________________________________________
> freebsd-arch at freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-arch
> To unsubscribe, send any mail to "freebsd-arch-unsubscribe at freebsd.org"
>