The following commit has been merged into the sched/core branch of tip:
Commit-ID: 1c0482707c42960ec46b88aadd6bffca8685db11
Gitweb: https://git.kernel.org/tip/1c0482707c42960ec46b88aadd6bffca8685db11
Author: Vineeth Pillai (Google) <vineeth@xxxxxxxxxxxxxxx>
AuthorDate: Fri, 20 Oct 2023 01:40:28
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitterDate: Fri, 20 Oct 2023 09:56:21 +02:00
sched/fair: Update ->next_balance correctly during newidle balance
When newidle balancing triggers, we see that it constantly clobbers
rq->next_balance even when there is no newidle balance happening due to
the cost estimates. Due to this, we see that periodic load balance
(rebalance_domains) may trigger way more often when the CPU is going in
and out of idle at a high rate but is no really idle. Repeatedly
triggering load balance there is a bad idea as it is a heavy operation.
It also causes increases in softirq.
Another issue is ->last_balance is not updated after newidle balance
causing mistakes in the ->next_balance calculations.
Fix by updating last_balance when a newidle load balance actually
happens and then updating next_balance. This is also how it is done in
other load balance paths.
Testing shows a significant drop in softirqs when running:
$ cyclictest -i 100 -d 100 --latency=1000 -D 5 -t -m -q
... goes from ~6,000 to ~800.
Co-developed-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
Signed-off-by: Vineeth Pillai (Google) <vineeth@xxxxxxxxxxxxxxx>
Signed-off-by: Joel Fernandes (Google) <joel@xxxxxxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20231020014031.919742-3-joel@xxxxxxxxxxxxxxxxx
---
kernel/sched/fair.c | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8c486ff..393d0dc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12122,11 +12122,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
if (!READ_ONCE(this_rq->rd->overload) ||
(sd && this_rq->avg_idle < sd->max_newidle_lb_cost)) {
-
- if (sd)
- update_next_balance(sd, &next_balance);
rcu_read_unlock();
-
goto out;
}
rcu_read_unlock();
@@ -12141,8 +12137,6 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
int continue_balancing = 1;
u64 domain_cost;
- update_next_balance(sd, &next_balance);
-
if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost)
break;
@@ -12155,6 +12149,8 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
t1 = sched_clock_cpu(this_cpu);
domain_cost = t1 - t0;
update_newidle_cost(sd, domain_cost);
+ sd->last_balance = jiffies;
+ update_next_balance(sd, &next_balance);
curr_cost += domain_cost;
t0 = t1;
|