Messages in this thread | | | Date | Wed, 9 Nov 2022 11:43:58 +0100 | Subject | Re: [PATCH v2 9/9] sched/fair: Consider capacity inversion in util_fits_cpu() | From | Dietmar Eggemann <> |
| |
- Qais Yousef <qais.yousef@arm.com>
On 05/11/2022 21:41, Qais Yousef wrote: > On 11/04/22 17:35, Valentin Schneider wrote: >> On 04/08/22 15:36, Qais Yousef wrote:
[...]
>> IIUC the rq->cpu_capacity_inverted computation in update_cpu_capacity() can be >> summarised as: >> >> - If there is a PD with equal cap_orig, but higher effective (orig - thermal) >> capacity >> OR >> there is a PD with pd_cap_orig > cpu_effective_cap: >> rq->cpu_capacity_inverted = capacity_orig - thermal_load_avg(rq) >> >> - Else: >> rq->cpu_capacity_inverted = 0 >> >> Then, the code above uses either rq->cpu_capacity_inverted if it is >> non-zero, otherwise: >> >> capacity_orig - arch_scale_thermal_pressure(cpu); >> >> Why use average thermal pressure in one case, and use instantaneous >> thermal pressure in the other? > > There was a big debate on [1] about using avg vs instantaneous. > > I used avg for detecting inversion to be consistent with using average in in > scale_rt_capacity(). I didn't want the inversion state to be flipping too > quickly too. > > I used the instantaneous in the other check based on that discussion. It seemed > using the average is hurtful when for example the medium drops an OPP and by > not reacting quickly at wake up we lose the chance to place it on a big; which > if my memory didn't fail me is what Xuewen was seeing. > > [1] https://lore.kernel.org/lkml/24631a27-42d9-229f-d9b0-040ac993b749@arm.com/ > >> >> Can't we get rid of rq->cpu_capacity_inverted and replace this whole thing >> with an unconditional >> >> capacity_orig_thermal = capacity_orig_of(cpu) - thermal_load_avg(cpu_rq(cpu)); >> >> ? > > I can't see how we end up with equivalent behavior then. Or address the > concerns raised by Xuewen and Lukasz on the RT thread in regards to avg vs > instantaneous. > > Specifically, if we don't use the new rq->cpu_capacity_inverted we can't handle > the case where the task is requesting to run at maximum performance but a small > drop in thermal pressure means it won't fit anywhere. That PD is the best fit > until it hits an inversion. > > Originally I wanted to defer handling thermal pressure into a different series. > But Vincent thought it's better to handle it now. We want more data points from > more systems tbh. But I think what we have now is still a good improvement over > what we had before.
I can't see the rationale in using:
!inversion: `cap_orig - instantaneous thermal pressure`
inversion: `cap_orig - PELT thermal pressure`
I can see that there was a lot of discussion on this topic but hardly any agreement IMHO.
AFAICS, the 2 capacity inversion patches just appeared in v2 and haven't seen any review yet I'm afraid.
[...]
| |