Re: [PATCH 3/7] idle, thermal, acpi: Remove home grown idle implementations

[Jacob Pan <jacob.jun.pan@linux.intel.com>]

On Wed, 20 Nov 2013 20:38:03 +0100 (CET)
Thomas Gleixner <tglx@linutronix.de> wrote:

> On Wed, 20 Nov 2013, Arjan van de Ven wrote:
> > 
> > but for powerclamp to work, it needs to inject a deep idle....  I'm
> > very ok using generic abstractions for that, but the abstraction
> > needs to then include a "don't be nice about picking shallow C
> > states for performance reasons, just pick something very deep"
> > parameter.
> 
> And that's what you should have done in the first place. Make the
> generic code take a parameter to indicate that. Or tell the scheduler
> to throttle the machine and go deep idle. That would also be helpful
> to others who might need some similar thing.
> 
I thought about that. Since the generic code is in performance critical
path and idle injection is a rare case. Then the question is do we
want sacrifice the 99% for %1 usage?

> No, you went with the worst design:
> 
>     - Hack it into some random driver
>     - Export random core interfaces so it's harder to change them
>     - Let others deal with the fallout
> 
> I'm cleaning up that kind of mess for more than 9 years now and I'm
> really disappointed that you went over to the "who cares, works for
> me" camp.
> 
> I can lively remember our discussions when we were cleaning up the
> whole timer mess together in order to make NOHZ actually useful. Your
> cursing about such code was definitely impressive back then.
> 
> Thanks,
> 
> 	tglx
> 
> 
> 
> 

[Jacob Pan]