Re: Scheduler regression: Too frequent timer interrupts(?)

[Pavel Machek <pavel@ucw.cz>]

On Fri 2009-04-17 17:28:57, Peter Zijlstra wrote:
> On Fri, 2009-04-17 at 11:04 -0400, Christoph Lameter wrote:
> > On Fri, 17 Apr 2009, Peter Zijlstra wrote:
> > 
> > > And a random 1us cutoff, is well, random.
> > 
> > Its got to be somewhere.
> 
> No it doesn't, a cutoff is useless. If I steal cputime at units below
> the cutoff I can, in the limit, steal up to 100% cpu time and you'd not
> notice.

Are you sure cutoff is useless?

Irq entry/exit is sure to take > 1usec, right?

> > > So 5 <1us interruption are not at all accounted, whereas a single 1>us
> > > interruption is. I'd rather get rid of those 5 than try and shave a bit
> > > of the one, if you get what I mean.
> > 
> > Ok. We can set the threshold lower and see how that goes.
> 
> Pointless. See above.

I'd say that taking interrupt and returning in below 1000nsec is
impossible, even on very fast hw.

									Pavel
-- 
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html