Re: [PATCH V2 0/3] Introduce Thermal Pressure

From: Ingo Molnar <mingo@kernel.org>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Thara Gopinath <thara.gopinath@linaro.org>,
	mingo@redhat.com, rui.zhang@intel.com,
	linux-kernel@vger.kernel.org, amit.kachhap@gmail.com,
	viresh.kumar@linaro.org, javi.merino@kernel.org,
	edubezval@gmail.com, daniel.lezcano@linaro.org,
	vincent.guittot@linaro.org, nicolas.dechesne@linaro.org,
	bjorn.andersson@linaro.org, dietmar.eggemann@arm.com,
	Quentin Perret <quentin.perret@arm.com>,
	"Rafael J. Wysocki" <rjw@rjwysocki.net>
Subject: Re: [PATCH V2 0/3] Introduce Thermal Pressure
Date: Thu, 25 Apr 2019 19:44:25 +0200	[thread overview]
Message-ID: <20190425174425.GA121124@gmail.com> (raw)
In-Reply-To: <20190425173333.GA4081@gmail.com>

* Ingo Molnar <mingo@kernel.org> wrote:

> 
> * Peter Zijlstra <peterz@infradead.org> wrote:
> 
> > On Wed, Apr 17, 2019 at 08:29:32PM +0200, Ingo Molnar wrote:
> > > Assuming PeterZ & Rafael & Quentin doesn't hate the whole thermal load 
> > > tracking approach. 
> > 
> > I seem to remember competing proposals, and have forgotten everything
> > about them; the cover letter also didn't have references to them or
> > mention them in any way.
> > 
> > As to the averaging and period, I personally prefer a PELT signal with
> > the windows lined up, if that really is too short a window, then a PELT
> > like signal with a natural multiple of the PELT period would make sense,
> > such that the windows still line up nicely.
> > 
> > Mixing different averaging methods and non-aligned windows just makes me
> > uncomfortable.
> 
> Yeah, so the problem with PELT is that while it nicely approximates 
> variable-period decay calculations with plain additions, shifts and table 
> lookups (i.e. accelerates pow()), AFAICS the most important decay 
> parameter is fixed: the speed of decay, the dampening factor, which is 
> fixed at 32:
> 
>   Documentation/scheduler/sched-pelt.c
> 
>   #define HALFLIFE 32
> 
> Right?
> 
> Thara's numbers suggest that there's high sensitivity to the speed of 
> decay. By using PELT we'd be using whatever averaging speed there is 
> within PELT.
> 
> Now we could make that parametric of course, but that would both 
> complicate the PELT lookup code (one more dimension) and would negatively 
> affect code generation in a number of places.

I missed the other solution, which is what you suggested: by 
increasing/reducing the PELT window size we can effectively shift decay 
speed and use just a single lookup table.

I.e. instead of the fixed period size of 1024 in accumulate_sum(), use 
decay_load() directly but use a different (longer) window size from 1024 
usecs to calculate 'periods', and make it a multiple of 1024.

This might just work out right: with a half-life of 32 the fastest decay 
speed should be around ~20 msecs (?) - and Thara's numbers so far suggest 
that the sweet spot averaging is significantly longer, at a couple of 
hundred millisecs.

Thanks,

	Ingo