Re: [PATCH linux-next] sched/psi: Avoid update triggers and rtpoll_total when it is unnecessary

[Suren Baghdasaryan]

On Thu, Sep 14, 2023 at 2:10 AM <yang.yang29@xxxxxxxxxx> wrote:
>
> Update_total in update_triggers() is also only used by psi_rtpoll_work().
> And when changed_states & group->rtpoll_states is true, update_total
> should also be true, so try to delete update_total, please see below:


Ok, sorry for the delay. I wanted to check for any side-effects and
recheck the whole logic since the code has changed quite a bit since
it was introduced...
I think this optimization is safe and won't have side-effects, however
I haven't tested it yet. One small comment above and when you post the
V2 please include peterz@xxxxxxxxxxxxx. Peter is hosting PSI in his
tree, so he is the maintainer you absolutely need :)

>
> ---
>  kernel/sched/psi.c | 24 +++++++-----------------
>  1 file changed, 7 insertions(+), 17 deletions(-)
>
> diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
> index 81fca77397f6..744ba8b4e029 100644
> --- a/kernel/sched/psi.c
> +++ b/kernel/sched/psi.c
> @@ -434,14 +434,13 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value)
>         return growth;
>  }
>
> -static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total,
> +static void update_triggers(struct psi_group *group, u64 now,
>                                                    enum psi_aggregators aggregator)
>  {
>         struct psi_trigger *t;
>         u64 *total = group->total[aggregator];
>         struct list_head *triggers;
>         u64 *aggregator_total;
> -       *update_total = false;
>
>         if (aggregator == PSI_AVGS) {
>                 triggers = &group->avg_triggers;
> @@ -471,14 +470,6 @@ static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total,
>                  * events without dropping any).
>                  */
>                 if (new_stall) {
> -                       /*
> -                        * Multiple triggers might be looking at the same state,
> -                        * remember to update group->polling_total[] once we've
> -                        * been through all of them. Also remember to extend the
> -                        * polling time if we see new stall activity.
> -                        */
> -                       *update_total = true;
> -
>                         /* Calculate growth since last update */
>                         growth = window_update(&t->win, now, total[t->state]);
>                         if (!t->pending_event) {
> @@ -499,8 +490,6 @@ static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total,
>                 /* Reset threshold breach flag once event got generated */
>                 t->pending_event = false;
>         }
> -
> -       return now + group->rtpoll_min_period;
>  }
>
>  static u64 update_averages(struct psi_group *group, u64 now)
> @@ -561,7 +550,6 @@ static void psi_avgs_work(struct work_struct *work)
>         struct delayed_work *dwork;
>         struct psi_group *group;
>         u32 changed_states;
> -       bool update_total;
>         u64 now;
>
>         dwork = to_delayed_work(work);
> @@ -580,7 +568,7 @@ static void psi_avgs_work(struct work_struct *work)
>          * go - see calc_avgs() and missed_periods.
>          */
>         if (now >= group->avg_next_update) {
> -               update_triggers(group, now, &update_total, PSI_AVGS);
> +               update_triggers(group, now, PSI_AVGS);
>                 group->avg_next_update = update_averages(group, now);
>         }
>
> @@ -636,7 +624,6 @@ static void psi_rtpoll_work(struct psi_group *group)
>  {
>         bool force_reschedule = false;
>         u32 changed_states;
> -       bool update_total;
>         u64 now;
>
>         mutex_lock(&group->rtpoll_trigger_lock);
> @@ -702,10 +689,13 @@ static void psi_rtpoll_work(struct psi_group *group)
>         }
>
>         if (now >= group->rtpoll_next_update) {
> -               group->rtpoll_next_update = update_triggers(group, now, &update_total, PSI_POLL);
> -               if (update_total)
> +               group->rtpoll_next_update = now + group->rtpoll_min_period;

It's not technically wrong and does not have side-effects today but to
be safe, please update group->rtpoll_next_update *after* you call
update_triggers() and update group->rtpoll_total. This will prevent
bugs if update_triggers() uses group->rtpoll_next_update in the future
and I think it makes more sense to set the next update time after we
finished the current update. So, the code should look something like:

        if (now >= group->rtpoll_next_update) {
                if (changed_states & group->rtpoll_states) {
                        update_triggers(group, now, PSI_POLL);
                        memcpy(group->rtpoll_total, group->total[PSI_POLL],
                                sizeof(group->rtpoll_total));
                }
                group->rtpoll_next_update = now + group->rtpoll_min_period;
        }

Thanks,
Suren.

> +
> +               if (changed_states & group->rtpoll_states) {
> +                       update_triggers(group, now, PSI_POLL);
>                         memcpy(group->rtpoll_total, group->total[PSI_POLL],
>                                    sizeof(group->rtpoll_total));
> +               }
>         }
>
>         psi_schedule_rtpoll_work(group,
> --
> 2.25.1