mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
* [PATCH] sched_ext: Update other_load_avgs on set_next_task_scx
@ 2026-11-22  3:33 Peng Huang
  0 siblings, 0 replies; only message in thread
From: Peng Huang @ 2026-11-22  3:33 UTC (permalink / raw)
  To: Tejun Heo, David Vernet, Andrea Righi, Changwoo Min, sched-ext
  Cc: Ingo Molnar, Peter Zijlstra, Juri Lelli, Vincent Guittot,
	Dietmar Eggemann, Steven Rostedt, Ben Segall, Mel Gorman,
	Valentin Schneider, K Prateek Nayak, Barret Rhoden, Josh Don,
	Hao Luo, linux-kernel, penghuang

When scx_switched_all() is enabled, scheduler_tick() skips
sched_balance_trigger(), so __update_blocked_others() no longer runs to
decay RT, DL, IRQ, and HW pressure load averages. Other-class load
averages then depend on scx_tick() and SCX_RQ_CAN_STOP_TICK transitions
in set_next_task_scx().

If SCX_RQ_CAN_STOP_TICK stays unchanged (e.g., remaining set across an
idle or RT interval on tickless CPUs, or remaining clear on finite-slice
switches before a tick fires or before going idle), stale RT/DL PELT
values can remain elevated when consumers such as effective_cpu_util()
or update_idle_rq_clock_pelt() read them.

Track load-average updates explicitly with @update_load_avgs in
set_next_task_scx() and refresh update_other_load_avgs() on SNT_PICK as
well as when SCX_RQ_CAN_STOP_TICK toggles.

Fixes: 22a920209ab6 ("sched_ext: Implement tickless support")
Cc: stable@vger.kernel.org
Signed-off-by: Peng Huang <penghuang@google.com>
---
 kernel/sched/ext/ext.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 10de6bd865e8..e29c9c18e1ab 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -3553,6 +3553,7 @@ static void kick_sync_wait_bal_cb(struct rq *rq);
 static void set_next_task_scx(struct rq *rq, struct task_struct *p, enum snt_e type)
 {
 	bool first = type == SNT_PICK;
+	bool update_load_avgs = first;
 	bool can_stop_tick;
 
 	/*
@@ -3619,10 +3620,6 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, enum snt_e t
 	 * @p is getting newly scheduled or got kicked after someone updated its
 	 * slice. Update SCX_RQ_CAN_STOP_TICK to reflect whether the tick can be
 	 * stopped. See scx_can_stop_tick().
-	 *
-	 * Moreover, refresh the load_avgs just when transitioning in and out of
-	 * nohz. In the future, we might want to add a mechanism to update
-	 * load_avgs periodically on tick-stopped CPUs.
 	 */
 	if (can_stop_tick) {
 		if (!(rq->scx.flags & SCX_RQ_CAN_STOP_TICK)) {
@@ -3634,13 +3631,12 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, enum snt_e t
 			 */
 			rq->scx.flags |= SCX_RQ_CAN_STOP_TICK;
 			sched_update_tick_dependency(rq);
-
-			update_other_load_avgs(rq);
+			update_load_avgs = true;
 		}
 	} else {
 		if (rq->scx.flags & SCX_RQ_CAN_STOP_TICK) {
 			rq->scx.flags &= ~SCX_RQ_CAN_STOP_TICK;
-			update_other_load_avgs(rq);
+			update_load_avgs = true;
 		}
 
 		/*
@@ -3651,6 +3647,15 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, enum snt_e t
 		if (tick_nohz_full_cpu(cpu_of(rq)))
 			tick_nohz_dep_set_cpu(cpu_of(rq), TICK_DEP_BIT_SCHED);
 	}
+
+	/*
+	 * Refresh other-class (RT/DL/IRQ/HW) load averages when picking a new
+	 * task or toggling nohz tick dependency while CFS PELT is dormant.
+	 * In the future, we might want to add a mechanism to update load_avgs
+	 * periodically on tick-stopped CPUs.
+	 */
+	if (update_load_avgs)
+		update_other_load_avgs(rq);
 }
 
 void scx_proxy_donor_start(struct rq *rq)
-- 
2.56.1.750.gf70dc682cf-goog


^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2026-11-22  3:33 UTC | newest]

Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-11-22  3:33 [PATCH] sched_ext: Update other_load_avgs on set_next_task_scx Peng Huang

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®