sched/pelt: Use rq_clock_task() for hw_pressure
PATCH v2 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.
---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 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/sched/fair.c +1 -1
@@ -9362,7 +9362,7 @@ static bool __update_blocked_others(struct rq *rq, bool *done) 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
Quoted 32 lines · Chen Yu
commit
97450eb90965("sched/pelt: Remove shift of thermal clock") removed thedecay_shiftforhw_pressure. This commit uses thesched_clock_task()insched_tick()while it replaces thesched_clock_task()withrq_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(), andlast_update_timewas calculated byrq_clock_task()previously fromsched_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")Reviewed-by Hongyan Xia <[email protected]>Signed-off-by Chen Yu <[email protected]>---
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 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)kernel/sched/fair.c +0
-0
kernel/sched/fair.c static bool __update_blocked_others(struct rq *rq, bool *done) · line 9365
Quoted 5 lines
kernel/sched/fair.c +1
-1@@ -9362,7 +9362,7 @@ static bool __update_blocked_others(struct rq *rq, bool *done) 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) |
NIT:
Wouldn't it be better to remove 'now' and call rq_clock_task() inside update_hw_load_avg()? Adding a comment on why we should use this not clock_pelt would be helpful too. hw_pressure doesn't care about invariance.
ie:
update_hw_load_avg(rq, hw_pressure)
{
}
LGTM anyway. I think this is called most of the time from idle when clock_pelt is synced with clock_task. So the impact is low, I believe.
Quoted 6 lines
kernel/sched/fair.c +0
-0update_irq_load_avg (rq,0 );if (others_have_blocked (rq))Signature · 1 line
2.25.1
Hi Qais,
thanks for taking a look,
Quoted 41 lines · Qais Yousef
Quoted 32 lines · Chen Yu
commit
97450eb90965("sched/pelt: Remove shift of thermal clock") removed thedecay_shiftforhw_pressure. This commit uses thesched_clock_task()insched_tick()while it replaces thesched_clock_task()withrq_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(), andlast_update_timewas calculated byrq_clock_task()previously fromsched_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")Reviewed-by Hongyan Xia <[email protected]>Signed-off-by Chen Yu <[email protected]>---
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 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)kernel/sched/fair.c +0
-0kernel/sched/fair.c static bool __update_blocked_others(struct rq *rq, bool *done) · line 9365
Quoted 5 lines
kernel/sched/fair.c +1
-1@@ -9362,7 +9362,7 @@ static bool __update_blocked_others(struct rq *rq, bool *done) 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) |NIT:
Quoted 4 lines
Wouldn't it be better to remove 'now' and call
rq_clock_task()insideupdate_hw_load_avg()? Adding a comment on why we should use this notclock_peltwould be helpful too.hw_pressuredoesn't care about invariance.
OK, will do in the next version.
Quoted 9 lines
ie:
update_hw_load_avg(rq, hw_pressure)
{
}LGTM anyway. I think this is called most of the time from idle when
clock_peltis synced withclock_task. So the impact is low, I believe.
Yes, when the current task is found to be idle, clock_pelt is synced with clock_task by update_rq_clock(). While a case is that, in the softirq load balance, sched_balance_softirq()->sched_balance_update_blocked_averages()->__update_blocked_others() ->update_hw_load_avg() is not always called by the idle task, and clock_pelt has not been synced with clock_task yet.
thanks,
Chenyu
Quoted 63 lines · Chen Yu
Hi Qais,
thanks for taking a look,
Quoted 41 lines · Qais Yousef
Quoted 32 lines · Chen Yu
commit
97450eb90965("sched/pelt: Remove shift of thermal clock") removed thedecay_shiftforhw_pressure. This commit uses thesched_clock_task()insched_tick()while it replaces thesched_clock_task()withrq_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(), andlast_update_timewas calculated byrq_clock_task()previously fromsched_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")Reviewed-by Hongyan Xia <[email protected]>Signed-off-by Chen Yu <[email protected]>---
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 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)kernel/sched/fair.c +0
-0kernel/sched/fair.c static bool __update_blocked_others(struct rq *rq, bool *done) · line 9365
Quoted 5 lines
kernel/sched/fair.c +1
-1@@ -9362,7 +9362,7 @@ static bool __update_blocked_others(struct rq *rq, bool *done) 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) |NIT:
Quoted 4 lines
Wouldn't it be better to remove 'now' and call
rq_clock_task()insideupdate_hw_load_avg()? Adding a comment on why we should use this notclock_peltwould be helpful too.hw_pressuredoesn't care about invariance.OK, will do in the next version.
Quoted 9 lines
ie:
update_hw_load_avg(rq, hw_pressure)
{
}LGTM anyway. I think this is called most of the time from idle when
clock_peltis synced withclock_task. So the impact is low, I believe.
Quoted 5 lines
Yes, when the current task is found to be idle,
clock_peltis synced withclock_taskbyupdate_rq_clock(). While a case is that, in the softirq load balance, sched_balance_softirq()->sched_balance_update_blocked_averages()->__update_blocked_others() ->update_hw_load_avg() is not always called by the idle task, andclock_pelthas not been synced withclock_taskyet.
Yes. I think it is less often happens from there though, that's why I said the impact is low. But yes there's a problem.