* [PATCH] sched/fair: Revise comment about lb decision matrix
@ 2022-04-03 17:59 Tao Zhou
2022-04-14 10:33 ` Dietmar Eggemann
0 siblings, 1 reply; 3+ messages in thread
From: Tao Zhou @ 2022-04-03 17:59 UTC (permalink / raw)
To: linux-kernel, tao.zhou
If busiest group type is group_misfit_task, the local
group type must be group_has_spare according to below
code in update_sd_pick_busiest():
if (sgs->group_type == group_misfit_task &&
(!capacity_greater(capacity_of(env->dst_cpu), sg->sgc->max_capacity) ||
sds->local_stat.group_type != group_has_spare))
return false;
group type imbalanced and overloaded and fully_busy are filtered in here.
misfit and asym are filtered before in update_sg_lb_stats().
So, change the decision matrix to:
busiest \ local has_spare fully_busy misfit asym imbalanced overloaded
has_spare nr_idle balanced N/A N/A balanced balanced
fully_busy nr_idle nr_idle N/A N/A balanced balanced
misfit_task force N/A N/A N/A *N/A* *N/A*
asym_packing force force N/A N/A force force
imbalanced force force N/A N/A force force
overloaded force force N/A N/A force avg_load
---
kernel/sched/fair.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5146163bfabb..5765d96202c7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9441,7 +9441,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
* busiest \ local has_spare fully_busy misfit asym imbalanced overloaded
* has_spare nr_idle balanced N/A N/A balanced balanced
* fully_busy nr_idle nr_idle N/A N/A balanced balanced
- * misfit_task force N/A N/A N/A force force
+ * misfit_task force N/A N/A N/A N/A N/A
* asym_packing force force N/A N/A force force
* imbalanced force force N/A N/A force force
* overloaded force force N/A N/A force avg_load
--
2.35.1
^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [PATCH] sched/fair: Revise comment about lb decision matrix
2022-04-03 17:59 [PATCH] sched/fair: Revise comment about lb decision matrix Tao Zhou
@ 2022-04-14 10:33 ` Dietmar Eggemann
2022-04-14 17:27 ` Tao Zhou
0 siblings, 1 reply; 3+ messages in thread
From: Dietmar Eggemann @ 2022-04-14 10:33 UTC (permalink / raw)
To: Tao Zhou, linux-kernel
On 03/04/2022 19:59, Tao Zhou wrote:
> If busiest group type is group_misfit_task, the local
> group type must be group_has_spare according to below
> code in update_sd_pick_busiest():
>
> if (sgs->group_type == group_misfit_task &&
> (!capacity_greater(capacity_of(env->dst_cpu), sg->sgc->max_capacity) ||
> sds->local_stat.group_type != group_has_spare))
> return false;
>
> group type imbalanced and overloaded and fully_busy are filtered in here.
> misfit and asym are filtered before in update_sg_lb_stats().
> So, change the decision matrix to:
>
> busiest \ local has_spare fully_busy misfit asym imbalanced overloaded
> has_spare nr_idle balanced N/A N/A balanced balanced
> fully_busy nr_idle nr_idle N/A N/A balanced balanced
> misfit_task force N/A N/A N/A *N/A* *N/A*
> asym_packing force force N/A N/A force force
> imbalanced force force N/A N/A force force
> overloaded force force N/A N/A force avg_load
> ---
> kernel/sched/fair.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 5146163bfabb..5765d96202c7 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -9441,7 +9441,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
> * busiest \ local has_spare fully_busy misfit asym imbalanced overloaded
> * has_spare nr_idle balanced N/A N/A balanced balanced
> * fully_busy nr_idle nr_idle N/A N/A balanced balanced
> - * misfit_task force N/A N/A N/A force force
> + * misfit_task force N/A N/A N/A N/A N/A
> * asym_packing force force N/A N/A force force
> * imbalanced force force N/A N/A force force
> * overloaded force force N/A N/A force avg_load
You should put people you find in `./scripts/get_maintainer.pl
kernel/sched/fair.c` on To/Cc to attract more attention.
Otherwise, LGTM.
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [PATCH] sched/fair: Revise comment about lb decision matrix
2022-04-14 10:33 ` Dietmar Eggemann
@ 2022-04-14 17:27 ` Tao Zhou
0 siblings, 0 replies; 3+ messages in thread
From: Tao Zhou @ 2022-04-14 17:27 UTC (permalink / raw)
To: Dietmar Eggemann; +Cc: linux-kernel
On Thu, Apr 14, 2022 at 12:33:06PM +0200,
Dietmar Eggemann wrote:
> On 03/04/2022 19:59, Tao Zhou wrote:
> > If busiest group type is group_misfit_task, the local
> > group type must be group_has_spare according to below
> > code in update_sd_pick_busiest():
> >
> > if (sgs->group_type == group_misfit_task &&
> > (!capacity_greater(capacity_of(env->dst_cpu), sg->sgc->max_capacity) ||
> > sds->local_stat.group_type != group_has_spare))
> > return false;
> >
> > group type imbalanced and overloaded and fully_busy are filtered in here.
> > misfit and asym are filtered before in update_sg_lb_stats().
> > So, change the decision matrix to:
> >
> > busiest \ local has_spare fully_busy misfit asym imbalanced overloaded
> > has_spare nr_idle balanced N/A N/A balanced balanced
> > fully_busy nr_idle nr_idle N/A N/A balanced balanced
> > misfit_task force N/A N/A N/A *N/A* *N/A*
> > asym_packing force force N/A N/A force force
> > imbalanced force force N/A N/A force force
> > overloaded force force N/A N/A force avg_load
> > ---
> > kernel/sched/fair.c | 2 +-
> > 1 file changed, 1 insertion(+), 1 deletion(-)
> >
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index 5146163bfabb..5765d96202c7 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@ -9441,7 +9441,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
> > * busiest \ local has_spare fully_busy misfit asym imbalanced overloaded
> > * has_spare nr_idle balanced N/A N/A balanced balanced
> > * fully_busy nr_idle nr_idle N/A N/A balanced balanced
> > - * misfit_task force N/A N/A N/A force force
> > + * misfit_task force N/A N/A N/A N/A N/A
> > * asym_packing force force N/A N/A force force
> > * imbalanced force force N/A N/A force force
> > * overloaded force force N/A N/A force avg_load
>
> You should put people you find in `./scripts/get_maintainer.pl
> kernel/sched/fair.c` on To/Cc to attract more attention.
>
> Otherwise, LGTM.
>
> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
I will send based on latest rc version..
Thanks,
Tao
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2022-04-14 17:26 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-04-03 17:59 [PATCH] sched/fair: Revise comment about lb decision matrix Tao Zhou
2022-04-14 10:33 ` Dietmar Eggemann
2022-04-14 17:27 ` Tao Zhou
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).