Messages in this thread | | | Date | Thu, 21 Dec 2017 14:45:02 +0530 | From | Viresh Kumar <> | Subject | Re: [PATCH v3 0/6] cpufreq: schedutil: fixes for flags updates |
| |
On 20-12-17, 16:43, Peter Zijlstra wrote: > The below makes more sense to me too; hmm? > > @@ -335,12 +335,11 @@ static unsigned int sugov_next_freq_shar > > j_max = j_sg_cpu->max; > j_util = sugov_aggregate_util(j_sg_cpu); > + sugov_iowait_boost(j_sg_cpu, &util, &max); > if (j_util * max > j_max * util) { > util = j_util; > max = j_max; > } > - > - sugov_iowait_boost(j_sg_cpu, &util, &max);
Sorry if I am being a fool here, I had 3 different interpretations of the results after this change in the last 15 minutes. It was confusing for somehow..
Why do you think above change matters ? I think nothing changed after this diff at all.
We have three different values here:
util/max, j_util/j_max, and j_boost_util/j_boost_max.
And we are trying to find the max among them and changing the order of comparisons doesn't change anything.
Am I reading the code correctly ?
-- viresh
| |