Re: [PATCH] timers/nohz: introduce nohz_full_aggressive

[Andrea Righi]

On Wed, May 10, 2023 at 11:03:07AM +0200, Anna-Maria Behnsen wrote:
> On Sun, 7 May 2023, Andrea Righi wrote:
> 
> > On Sun, May 07, 2023 at 10:08:52AM -0400, Steven Rostedt wrote:
> > > 
> > > [ Added Anna-Maria who is doing some timer work as well ]
> > > 
> > > On Sun,  7 May 2023 11:07:00 +0200
> > > Andrea Righi <andrea.righi@xxxxxxxxxxxxx> wrote:
> > > 
> > > Now, I think what is really happening here is that you are somewhat
> > > simulating the results that Anna-Maria has indirectly. That is, you
> > > just prevent an idle CPU from waking up to handle interrupts when not
> > > needed.
> > > 
> > > Anna-Maria,
> > > 
> > > Do you have some patches that Andrea could test with?
> > > 
> > > Thanks,
> > > 
> > > -- Steve
> > 
> > Thanks for looking at this (and I'm happy to help Anna-Maria with any
> > test).
> 
> I posted v6 of the queue - but forgot to add you to cc list. Here is the
> current version:
> 
>   https://lore.kernel.org/lkml/20230510072817.116056-1-anna-maria@xxxxxxxxxxxxx/
> 
> I have to mention, that there is still the issue with the fair scheduler
> which wakes up the CPU where the process_timeout() timer was enqueued,
> because it assumes that context is still cache hot.
> 
> Thanks,
> 
> 	Anna-Maria

OK, will take a look, thanks!

-Andrea