Re: [RFC PATCH 1/7] sched/pelt: Add a new function to approximate the future util_avg value

From: Qais Yousef <qyousef@layalina.io>
To: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Ingo Molnar <mingo@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	"Rafael J. Wysocki" <rafael@kernel.org>,
	Viresh Kumar <viresh.kumar@linaro.org>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
	Lukasz Luba <lukasz.luba@arm.com>
Subject: Re: [RFC PATCH 1/7] sched/pelt: Add a new function to approximate the future util_avg value
Date: Sat, 16 Sep 2023 20:49:23 +0100	[thread overview]
Message-ID: <20230916194923.4sijts6a56jxbava@airbuntu> (raw)
In-Reply-To: <45548b21-280e-7f94-0b53-f2dcab6ccb5e@arm.com>

On 09/13/23 19:22, Dietmar Eggemann wrote:
> On 10/09/2023 21:58, Qais Yousef wrote:
> > On 09/07/23 13:12, Dietmar Eggemann wrote:
> >> On 06/09/2023 23:19, Qais Yousef wrote:
> >>> On 09/06/23 14:56, Dietmar Eggemann wrote:
> >>>> On 28/08/2023 01:31, Qais Yousef wrote:
> 
> [...]
> 
> >> Another thing ... I guess if you call accumulate_sum with delta the PELT
> >> machinery assumes `delta = now - sa->last_update_time` which means you
> >> would have to use `clock_pelt + TICK_USEC` as delta.
> > 
> > Right.
> > 
> > The way I understood it is that at TICK we should do update_load_avg() which
> > would call __update_load_sum() which uses
> > 
> > 	delta = now - sa->last_update_time
> > 
> > which passes this delta to accumulate_sum()
> > 
> > I can see we are not very accurate since there will be a small additional time
> > besides TICK_USEC that we are not accounting for. But I can't see how this can
> > cause a big error.
> > 
> > 	predicted (assumed) tick time/delta
> > 
> > 		sa->last_update_time = now
> > 		tick_time = TICK_USEC + now
> > 
> > 		delta = tick_time - sa->last_update_time
> > 		delta = TICK_USEC + now - now
> > 		delta = TICK_USEC
> > 
> > 	but actual tick time/delta
> > 
> > 		sa->last_update_time = now - x
> > 		tick_time = TICK_USEC + now
> > 
> > 		delta = tick_time - sa->last_update_time
> > 		delta = TICK_USEC + now - (now - x)
> > 		delta = TICK_USEC + x
> > 
> > So the delta I am using might be slightly shorter than it should be.
> > 
> > IIUC, what you're saying that the `x` in my equation above is clock_pelt,
> > right?
> 
> No, I was wrong here. Calling accumulate_sum with `delta = TICK_USEC` is
> fine.
> 
> accumulate_sum() will accrue `sa->util.sum` and ___update_load_avg()
> will then adjust `sa->util_avg` accordingly.
> 
> delta should be 4000 on Arm64 boards so you will cross period
> boundaries. In case `delta < 1024` you might want to not call
> ___update_load_avg() to be in pair with __update_load_avg_cfs_rq().

You mean *not* call, or actually *do* call ___update_load_avg() if delta
< 1024? I am certainly not calling it now and I think you're suggesting to
actually call it when period is less than 1024.

This area is not my strength, so I do sure appreciate any suggestion to make it
better! :-) I will look into that for next version.

Many thanks!

--
Qais Yousef