On Wed, 20 Nov 2013 20:38:03 +0100 (CET) Thomas Gleixner <[email protected]> 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] -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
