The following commit has been merged into the sched/core branch of tip: Commit-ID: 9c9f520a14670ad59da2f700660f7601ec9e0b07 Gitweb: https://git.kernel.org/tip/9c9f520a14670ad59da2f700660f7601ec9e0b07 Author: Rik van Riel <riel@xxxxxxxxxxx> AuthorDate: Tue, 20 Apr 2021 12:07:05 -04:00 Committer: Peter Zijlstra <peterz@xxxxxxxxxxxxx> CommitterDate: Wed, 21 Apr 2021 13:55:43 +02:00 sched,fair: skip newidle_balance if a wakeup is pending 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> Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx> Link: https://lkml.kernel.org/r/20210420120705.5c705d4b@xxxxxxxxxxxxxxxxxxxx --- 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 1d75af1..83cd2bd 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -10592,6 +10592,14 @@ 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. @@ -10657,7 +10665,8 @@ 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(); @@ -10684,7 +10693,12 @@ out: if (time_after(this_rq->next_balance, next_balance)) this_rq->next_balance = next_balance; - 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) this_rq->idle_stamp = 0; else nohz_newidle_balance(this_rq);
|