Re: [PATCH v3] sched,fair: skip newidle_balance if a wakeup is pending

[Vincent Guittot]

On Wed, 21 Apr 2021 at 19:27, Vincent Guittot
<vincent.guittot@xxxxxxxxxx> wrote:
>
> Hi Rik,
>
> On Tue, 20 Apr 2021 at 18:07, Rik van Riel <riel@xxxxxxxxxxx> wrote:
> >
> > The try_to_wake_up function has an optimization where it can queue
> > a task for wakeup on its previous CPU, if the task is still in the
> > middle of going to sleep inside schedule().
> >
> > Once schedule() re-enables IRQs, the task will be woken up with an
> > IPI, and placed back on the runqueue.
> >
> > If we have such a wakeup pending, there is no need to search other
> > CPUs for runnable tasks. Just skip (or bail out early from) newidle
> > balancing, and run the just woken up task.
> >
> > For a memcache like workload test, this reduces total CPU use by
> > about 2%, proportionally split between user and system time,
> > and p99 and p95 application response time by 10% on average.
> > The schedstats run_delay number shows a similar improvement.
> >
> > Signed-off-by: Rik van Riel <riel@xxxxxxxxxxx>
> > ---
> >  kernel/sched/fair.c | 18 ++++++++++++++++--
> >  1 file changed, 16 insertions(+), 2 deletions(-)
> >
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index 69680158963f..fd80175c3b3e 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@ -10594,6 +10594,14 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
> >         u64 curr_cost = 0;
> >
> >         update_misfit_status(NULL, this_rq);
> > +
> > +       /*
> > +        * There is a task waiting to run. No need to search for one.
> > +        * Return 0; the task will be enqueued when switching to idle.
> > +        */
> > +       if (this_rq->ttwu_pending)
> > +               return 0;
> > +
> >         /*
> >          * We must set idle_stamp _before_ calling idle_balance(), such that we
> >          * measure the duration of idle_balance() as idle time.
> > @@ -10661,7 +10669,8 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
> >                  * Stop searching for tasks to pull if there are
> >                  * now runnable tasks on this rq.
> >                  */
> > -               if (pulled_task || this_rq->nr_running > 0)
> > +               if (pulled_task || this_rq->nr_running > 0 ||
> > +                   this_rq->ttwu_pending)
> >                         break;
> >         }
> >         rcu_read_unlock();
> > @@ -10688,7 +10697,12 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
> >         if (this_rq->nr_running != this_rq->cfs.h_nr_running)
> >                 pulled_task = -1;
> >
> > -       if (pulled_task)
> > +       /*
> > +        * If we are no longer idle, do not let the time spent here pull
> > +        * down this_rq->avg_idle. That could lead to newidle_balance not
> > +        * doing enough work, and the CPU actually going idle.
> > +        */
> > +       if (pulled_task || this_rq->ttwu_pending)
>
> I'm still running some benchmarks to evaluate the impact of your patch
> and more especially the line above which clears this_rq->idle_stamp
> and skips the time spent in newidle_balance from being accounted for
> in avg_idle. I have some results which  show some regression because
> of this test especially with hackbench.
> On large system, the time spent in newidle_balance can be significant
> and we can't ignore it just because this_rq->ttwu_pending is set while
> looping the domains because without newidle_balance the idle time
> would have been large and we end up screwing up the metric

I confirmed that the line above generate hackbench regression on my
large arm64 system (2 * 112 CPUs)
I'm testing hackbench with various number of group : 1, 2, 4, 16, 32,
64, 128, 256 but I have only put the 2 results which significantly
regress. The other ones are in the +/-1% variation range

hackbench -g $group

group    v5.12-rc8+tip    w/ this patch          w/ this patch without
the line above
64       2.862(+/- 9%)    2.952(+/-11%) -3%      2.807(+/- 7%) +2%
128      3.334(+/-10%)    3.561-+/-13%) -7%      3.181(+/- 6%) +4%



>
> >                 this_rq->idle_stamp = 0;
> >
> >         rq_repin_lock(this_rq, rf);
> > --
> > 2.25.4
> >
> >