Re: [PATCH] sched/fair: Fix negative energy delta in find_energy_efficient_cpu()

From: Pierre Gondois
Date: Fri Apr 30 2021 - 04:33:45 EST

Hi Quentin,

I sent a v2 yesterday. This is just to answer your question:
Not that I disagree with the approach, just being curious: do we know
how much this is helping in practice to reduce the window by moving the
compute_energy() calls down here?
I don't have any numbers. However, moving the computation of base_energy_pd

after looping over the CPUs of a performance domain allows to skip this computation

if no CPU is available in the performance domain. This should justify moving the

compute_energy() call.