Re: [PATCH] sched/loadavg: Avoid loadavg spikes caused by delayed NO_HZ accounting

[Frederic Weisbecker]

On Wed, Feb 15, 2017 at 04:16:19PM +0000, Matt Fleming wrote:
> On Wed, 15 Feb, at 04:12:11PM, Frederic Weisbecker wrote:
> > On Wed, Feb 08, 2017 at 01:29:24PM +0000, Matt Fleming wrote:
> > > The calculation for the next sample window when exiting NOH_HZ idle
> > > does not handle the fact that we may not have reached the next sample
> > > window yet
> > 
> > That sentence is hard to parse, it took me some time to figure out that
> > those two "next sample window" may not refer to the same thing.
>  
> Yeah, it's not the most lucid thing I've ever written.
> 
> > Maybe it would be clearer with something along the lines of:
> > 
> > "The calculation for the next sample window when exiting NO_HZ
> >  does not handle the fact that we may not have crossed any sample
> >  window during the NO_HZ period."
>  
> Umm... this isn't the problem. In fact, it's the opposite.
> 
> The problem is that if we *did* cross a sample window while in NO_HZ,
> then when we exit the pending window may be far enough into the future
> that all we need to do is update this_rq->calc_load_update.

Ah right. Well, see the problem statement wasn't clear to me ;-)

> 
> > > If we wake from NO_HZ idle after the pending this_rq->calc_load_update
> > > window time when we want idle but before the next sample window
> > 
> > That too was hard to understand. How about:
> > 
> > "If we enter in NO_HZ mode after a pending this_rq->calc_load_update
> >  and we exit from NO_HZ mode before the forthcoming sample window, ..."
>  
> You've got this backwards again. We enter NO_HZ before the pending
> window, not after.

Right.