On Tue, Jul 18, 2017 at 10:37 PM, Viresh Kumar <viresh.ku...@linaro.org> wrote:
> On 18-07-17, 15:02, Juri Lelli wrote:
>> Mmm, seems to make sense to me. :/
>>
>> Would the following work (on top of Joel's v5)? Rationale being that
>> only in sugov_set_iowait_boost we might bump freq up (if no iowait_boost
>> was set) or start from policy->min. In sugov_iowait_boost (consumer)
>> instead we do the decay (if no boosting was pending).
>>
>> ---
>> kernel/sched/cpufreq_schedutil.c | 29 +++++++++++++++++++----------
>> 1 file changed, 19 insertions(+), 10 deletions(-)
>>
>> diff --git a/kernel/sched/cpufreq_schedutil.c
>> b/kernel/sched/cpufreq_schedutil.c
>> index 46b2479641cc..b270563c15a5 100644
>> --- a/kernel/sched/cpufreq_schedutil.c
>> +++ b/kernel/sched/cpufreq_schedutil.c
>> @@ -171,8 +171,14 @@ static void sugov_set_iowait_boost(struct sugov_cpu
>> *sg_cpu, u64 time,
>> {
>> if (flags & SCHED_CPUFREQ_IOWAIT) {
>> sg_cpu->iowait_boost_pending = true;
>> - sg_cpu->iowait_boost = max(sg_cpu->iowait_boost,
>> - sg_cpu->sg_policy->policy->min);
>> + if (sg_cpu->iowait_boost) {
>> + /* Bump up 2*current_boost until hitting max */
>> + sg_cpu->iowait_boost = max(sg_cpu->iowait_boost << 1,
>> + sg_cpu->iowait_boost_max);
>
> And we are back at where we started :)
>
> This wouldn't work because sugov_set_iowait_boost() gets called a lot.
> Maybe 10 times within a rate_limit_us period.
>
> The thumb rule is, never double/half the boost from
> sugov_set_iowait_boost() :)
Ok so tomorrow I'll post something slightly different. In
sugov_iowait_boost, if the flag is set and current iowait_boost < min,
then set it to min, otherwise double it. If the flag is not set, halve
it. And both these would be done, *before* consuming the boost (as in
Viresh's last patch). I think that's reasonable and handles all cases.
Hopefully that will put it to rest, let me know if any objections.
thanks,
-Joel
