Re: [RFC PATCH] sched/fair: Fix impossible migrate_util scenario in load balance

[Qais Yousef <qyousef@layalina.io>]

On 07/24/23 19:54, Dietmar Eggemann wrote:
> On 24/07/2023 18:10, Qais Yousef wrote:
> > On 07/24/23 14:58, Dietmar Eggemann wrote:
> >> On 22/07/2023 00:04, Qais Yousef wrote:
> >>> On 07/21/23 15:52, Vincent Guittot wrote:
> >>>> Le vendredi 21 juil. 2023 à 11:57:11 (+0100), Qais Yousef a écrit :
> >>>>> On 07/20/23 14:31, Vincent Guittot wrote:
> 
> [...]
> 
> > So I actually moved everything to a single cluster and this indeed solves the
> > lb() issue. But then when I tried to look at DT mainline I saw that the DTs
> > still define separate cluster for each uArch, and this got me confused whether
> > I did the right thing or not. And made me wonder whether the fix is to change
> > DT or port Sudeep's/Ionela's patch?
> 
> IMHO, you have to change DT.
> 
> > I did some digging and I think the DT, like the ones in mainline by the look of
> > it, stayed the way it was historically defined.
> 
> This would be a "mistake" for Arm DynamIQ based systems. We use QC RB5
> in our testing and this board schedules only within a MC sched domain (I
> guess it's: arch/arm64/boot/dts/qcom/qrb5165-rb5.dts -> sm8250.dtsi)

I did find some qcom platforms that define a single cluster after I sent my
email. Not sure if the ones I've looked at were having wrong definitions or
not.

Anyway, hope this discussion will enlighten others too ;-)


Cheers

--
Qais Yousef