Skip to contentSkip to conversation

sched/pelt: Use rq_clock_task() for hw_pressure

PATCH Superseded Chen Yu 2 participants 2 messages Aug 6, 2024 Scheduler

v4 of 5 Superseded Latest is v5 →

lore
Share & tools
lore

Chen Yu

author
#0 lore raw

PATCH v4 1/1 sched/pelt: Use rq_clock_task() for hw_pressure

commit 97450eb90965 ("sched/pelt: Remove shift of thermal clock") removed the decay_shift for hw_pressure. This commit uses the sched_clock_task() in sched_tick() while it replaces the sched_clock_task() with rq_clock_pelt() in __update_blocked_others(). This could bring inconsistence. One possible scenario I can think of is in ___update_load_sum():

u64 delta = now - sa->last_update_time

'now' could be calculated by rq_clock_pelt() from __update_blocked_others(), and last_update_time was calculated by rq_clock_task() previously from sched_tick(). Usually the former chases after the latter, it cause a very large 'delta' and brings unexpected behavior.

Fixes 97450eb90965 ("sched/pelt: Remove shift of thermal clock")

---
v3->v4:
Revert to v2 to keep the clock outside of pelt functions. (Vincent Guittot)
Added comments for hw_pressure within __update_blocked_others(). (Qais Yousef)
v2>v3:
call rq_clock_task() inside update_hw_load_avg() to avoid any inconsistence in the future. (Qais Yousef)
Added comments around update_hw_load_avg(). (Qais Yousef)
v1->v2:
Added Hongyan's Reviewed-by tag.
Removed the Reported-by/Closes tags because they are not related to this fix.(Hongyan Xia)

---
 kernel/sched/fair.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/sched/fair.c +2 -1
index 9057584ec06d..5176db6ae13d 100644
@@ -9360,9 +9360,10 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
 
 	hw_pressure = arch_scale_hw_pressure(cpu_of(rq));
 
+	/* hw_pressure doesn't care about invariance */
 	decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
 		  update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
-		  update_hw_load_avg(now, rq, hw_pressure) |
+		  update_hw_load_avg(rq_clock_task(rq), rq, hw_pressure) |
 		  update_irq_load_avg(rq, 0);
 
 	if (others_have_blocked(rq))
Signature · 1 line
2.25.1
maintainer Reviewed-by on v4 1/1
#1 lore raw
Quoted 16 lines · Chen Yu

commit 97450eb90965 ("sched/pelt: Remove shift of thermal clock") removed the decay_shift for hw_pressure. This commit uses the sched_clock_task() in sched_tick() while it replaces the sched_clock_task() with rq_clock_pelt() in __update_blocked_others(). This could bring inconsistence. One possible scenario I can think of is in ___update_load_sum():

u64 delta = now - sa->last_update_time

'now' could be calculated by rq_clock_pelt() from __update_blocked_others(), and last_update_time was calculated by rq_clock_task() previously from sched_tick(). Usually the former chases after the latter, it cause a very large 'delta' and brings unexpected behavior.

Quoted 3 lines
Fixes 97450eb90965 ("sched/pelt: Remove shift of thermal clock")
Quoted 37 lines

---
v3->v4:
Revert to v2 to keep the clock outside of pelt functions. (Vincent Guittot)
Added comments for hw_pressure within __update_blocked_others(). (Qais Yousef)
v2>v3:
call rq_clock_task() inside update_hw_load_avg() to avoid any inconsistence in the future. (Qais Yousef)
Added comments around update_hw_load_avg(). (Qais Yousef)
v1->v2:
Added Hongyan's Reviewed-by tag.
Removed the Reported-by/Closes tags because they are not related to this fix.(Hongyan Xia)

---
 kernel/sched/fair.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
kernel/sched/fair.c +2 -2
index 9057584ec06d..5176db6ae13d 100644
@@ -9360,9 +9360,10 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
 
        hw_pressure = arch_scale_hw_pressure(cpu_of(rq));
 
+       /* hw_pressure doesn't care about invariance */
        decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
                  update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
-                 update_hw_load_avg(now, rq, hw_pressure) |
+                 update_hw_load_avg(rq_clock_task(rq), rq, hw_pressure) |
                  update_irq_load_avg(rq, 0);
 
        if (others_have_blocked(rq))
--

2.25.1