From: Zhaoyang Huang <[email protected]>
When a new threshold breaching stall happens after a psi event was
generated and within the window duration, the new event is not
generated because the events are rate-limited to one per window. If
after that no new stall is recorded then the event will not be
generated even after rate-limiting duration has passed. This is
happening because with no new stall, window_update will not be called
even though threshold was previously breached. To fix this, record
threshold breaching occurrence and generate the event once window
duration is passed.
Suggested-by: Suren Baghdasaryan <[email protected]>
Signed-off-by: Zhaoyang Huang <[email protected]>
---
v2: modify the logic according to Suren's suggestion
v3: update commit message
---
---
include/linux/psi_types.h | 2 ++
kernel/sched/psi.c | 38 +++++++++++++++++++++++---------------
2 files changed, 25 insertions(+), 15 deletions(-)
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 0a23300..87b694a 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -132,6 +132,8 @@ struct psi_trigger {
/* Refcounting to prevent premature destruction */
struct kref refcount;
+
+ bool threshold_breach;
};
struct psi_group {
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 1652f2b..5c67ab9 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -524,24 +524,29 @@ static u64 update_triggers(struct psi_group *group, u64 now)
*/
list_for_each_entry(t, &group->triggers, node) {
u64 growth;
+ bool trigger_stalled =
+ group->polling_total[t->state] != total[t->state];
- /* Check for stall activity */
- if (group->polling_total[t->state] == total[t->state])
- continue;
-
- /*
- * Multiple triggers might be looking at the same state,
- * remember to update group->polling_total[] once we've
- * been through all of them. Also remember to extend the
- * polling time if we see new stall activity.
- */
- new_stall = true;
-
- /* Calculate growth since last update */
- growth = window_update(&t->win, now, total[t->state]);
- if (growth < t->threshold)
+ /* Check for stall activity or a previous threshold breach */
+ if (!trigger_stalled && !t->threshold_breach)
continue;
+ if (trigger_stalled) {
+ /*
+ * Multiple triggers might be looking at the same state,
+ * remember to update group->polling_total[] once we've
+ * been through all of them. Also remember to extend the
+ * polling time if we see new stall activity.
+ */
+ new_stall = true;
+
+ /* Calculate growth since last update */
+ growth = window_update(&t->win, now, total[t->state]);
+ if (growth < t->threshold)
+ continue;
+
+ t->threshold_breach = true;
+ }
/* Limit event signaling to once per window */
if (now < t->last_event_time + t->win.size)
continue;
@@ -550,6 +555,8 @@ static u64 update_triggers(struct psi_group *group, u64 now)
if (cmpxchg(&t->event, 0, 1) == 0)
wake_up_interruptible(&t->event_wait);
t->last_event_time = now;
+ /* Reset threshold breach flag once event got generated */
+ t->threshold_breach = false;
}
if (new_stall)
@@ -1152,6 +1159,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
t->last_event_time = 0;
init_waitqueue_head(&t->event_wait);
kref_init(&t->refcount);
+ t->threshold_breach = false;
mutex_lock(&group->trigger_lock);
--
1.9.1
On Tue, Dec 21, 2021 at 4:24 PM Huangzhaoyang <[email protected]> wrote:
>
> From: Zhaoyang Huang <[email protected]>
Please remember to CC Peter.
>
> When a new threshold breaching stall happens after a psi event was
> generated and within the window duration, the new event is not
> generated because the events are rate-limited to one per window. If
> after that no new stall is recorded then the event will not be
> generated even after rate-limiting duration has passed. This is
> happening because with no new stall, window_update will not be called
> even though threshold was previously breached. To fix this, record
> threshold breaching occurrence and generate the event once window
> duration is passed.
>
> Suggested-by: Suren Baghdasaryan <[email protected]>
> Signed-off-by: Zhaoyang Huang <[email protected]>
> ---
> v2: modify the logic according to Suren's suggestion
> v3: update commit message
> ---
> ---
> include/linux/psi_types.h | 2 ++
> kernel/sched/psi.c | 38 +++++++++++++++++++++++---------------
> 2 files changed, 25 insertions(+), 15 deletions(-)
>
> diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
> index 0a23300..87b694a 100644
> --- a/include/linux/psi_types.h
> +++ b/include/linux/psi_types.h
> @@ -132,6 +132,8 @@ struct psi_trigger {
>
> /* Refcounting to prevent premature destruction */
> struct kref refcount;
> +
> + bool threshold_breach;
> };
>
> struct psi_group {
> diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
> index 1652f2b..5c67ab9 100644
> --- a/kernel/sched/psi.c
> +++ b/kernel/sched/psi.c
> @@ -524,24 +524,29 @@ static u64 update_triggers(struct psi_group *group, u64 now)
> */
> list_for_each_entry(t, &group->triggers, node) {
> u64 growth;
> + bool trigger_stalled =
> + group->polling_total[t->state] != total[t->state];
>
> - /* Check for stall activity */
> - if (group->polling_total[t->state] == total[t->state])
> - continue;
> -
> - /*
> - * Multiple triggers might be looking at the same state,
> - * remember to update group->polling_total[] once we've
> - * been through all of them. Also remember to extend the
> - * polling time if we see new stall activity.
> - */
> - new_stall = true;
> -
> - /* Calculate growth since last update */
> - growth = window_update(&t->win, now, total[t->state]);
> - if (growth < t->threshold)
> + /* Check for stall activity or a previous threshold breach */
> + if (!trigger_stalled && !t->threshold_breach)
> continue;
>
> + if (trigger_stalled) {
> + /*
> + * Multiple triggers might be looking at the same state,
> + * remember to update group->polling_total[] once we've
> + * been through all of them. Also remember to extend the
> + * polling time if we see new stall activity.
> + */
> + new_stall = true;
> +
> + /* Calculate growth since last update */
> + growth = window_update(&t->win, now, total[t->state]);
> + if (growth < t->threshold)
> + continue;
> +
> + t->threshold_breach = true;
> + }
> /* Limit event signaling to once per window */
> if (now < t->last_event_time + t->win.size)
> continue;
> @@ -550,6 +555,8 @@ static u64 update_triggers(struct psi_group *group, u64 now)
> if (cmpxchg(&t->event, 0, 1) == 0)
> wake_up_interruptible(&t->event_wait);
> t->last_event_time = now;
> + /* Reset threshold breach flag once event got generated */
> + t->threshold_breach = false;
> }
>
> if (new_stall)
> @@ -1152,6 +1159,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
> t->last_event_time = 0;
> init_waitqueue_head(&t->event_wait);
> kref_init(&t->refcount);
> + t->threshold_breach = false;
>
> mutex_lock(&group->trigger_lock);
>
> --
> 1.9.1
>
@Peter Zijlstra @Johannes Weiner
Would you please review this patch? We would like to have it be merged
ASAP. Thanks.
On Wed, Dec 22, 2021 at 8:31 AM Suren Baghdasaryan <[email protected]> wrote:
>
> On Tue, Dec 21, 2021 at 4:24 PM Huangzhaoyang <[email protected]> wrote:
> >
> > From: Zhaoyang Huang <[email protected]>
>
> Please remember to CC Peter.
>
> >
> > When a new threshold breaching stall happens after a psi event was
> > generated and within the window duration, the new event is not
> > generated because the events are rate-limited to one per window. If
> > after that no new stall is recorded then the event will not be
> > generated even after rate-limiting duration has passed. This is
> > happening because with no new stall, window_update will not be called
> > even though threshold was previously breached. To fix this, record
> > threshold breaching occurrence and generate the event once window
> > duration is passed.
> >
> > Suggested-by: Suren Baghdasaryan <[email protected]>
> > Signed-off-by: Zhaoyang Huang <[email protected]>
> > ---
> > v2: modify the logic according to Suren's suggestion
> > v3: update commit message
> > ---
> > ---
> > include/linux/psi_types.h | 2 ++
> > kernel/sched/psi.c | 38 +++++++++++++++++++++++---------------
> > 2 files changed, 25 insertions(+), 15 deletions(-)
> >
> > diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
> > index 0a23300..87b694a 100644
> > --- a/include/linux/psi_types.h
> > +++ b/include/linux/psi_types.h
> > @@ -132,6 +132,8 @@ struct psi_trigger {
> >
> > /* Refcounting to prevent premature destruction */
> > struct kref refcount;
> > +
> > + bool threshold_breach;
> > };
> >
> > struct psi_group {
> > diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
> > index 1652f2b..5c67ab9 100644
> > --- a/kernel/sched/psi.c
> > +++ b/kernel/sched/psi.c
> > @@ -524,24 +524,29 @@ static u64 update_triggers(struct psi_group *group, u64 now)
> > */
> > list_for_each_entry(t, &group->triggers, node) {
> > u64 growth;
> > + bool trigger_stalled =
> > + group->polling_total[t->state] != total[t->state];
> >
> > - /* Check for stall activity */
> > - if (group->polling_total[t->state] == total[t->state])
> > - continue;
> > -
> > - /*
> > - * Multiple triggers might be looking at the same state,
> > - * remember to update group->polling_total[] once we've
> > - * been through all of them. Also remember to extend the
> > - * polling time if we see new stall activity.
> > - */
> > - new_stall = true;
> > -
> > - /* Calculate growth since last update */
> > - growth = window_update(&t->win, now, total[t->state]);
> > - if (growth < t->threshold)
> > + /* Check for stall activity or a previous threshold breach */
> > + if (!trigger_stalled && !t->threshold_breach)
> > continue;
> >
> > + if (trigger_stalled) {
> > + /*
> > + * Multiple triggers might be looking at the same state,
> > + * remember to update group->polling_total[] once we've
> > + * been through all of them. Also remember to extend the
> > + * polling time if we see new stall activity.
> > + */
> > + new_stall = true;
> > +
> > + /* Calculate growth since last update */
> > + growth = window_update(&t->win, now, total[t->state]);
> > + if (growth < t->threshold)
> > + continue;
> > +
> > + t->threshold_breach = true;
> > + }
> > /* Limit event signaling to once per window */
> > if (now < t->last_event_time + t->win.size)
> > continue;
> > @@ -550,6 +555,8 @@ static u64 update_triggers(struct psi_group *group, u64 now)
> > if (cmpxchg(&t->event, 0, 1) == 0)
> > wake_up_interruptible(&t->event_wait);
> > t->last_event_time = now;
> > + /* Reset threshold breach flag once event got generated */
> > + t->threshold_breach = false;
> > }
> >
> > if (new_stall)
> > @@ -1152,6 +1159,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
> > t->last_event_time = 0;
> > init_waitqueue_head(&t->event_wait);
> > kref_init(&t->refcount);
> > + t->threshold_breach = false;
> >
> > mutex_lock(&group->trigger_lock);
> >
> > --
> > 1.9.1
> >
On Wed, Dec 22, 2021 at 4:50 PM Zhaoyang Huang <[email protected]> wrote:
>
> @Peter Zijlstra @Johannes Weiner
> Would you please review this patch? We would like to have it be merged
> ASAP. Thanks.
It's the holiday season, so I would not expect a quick turnaround.
>
> On Wed, Dec 22, 2021 at 8:31 AM Suren Baghdasaryan <[email protected]> wrote:
> >
> > On Tue, Dec 21, 2021 at 4:24 PM Huangzhaoyang <[email protected]> wrote:
> > >
> > > From: Zhaoyang Huang <[email protected]>
> >
> > Please remember to CC Peter.
> >
> > >
> > > When a new threshold breaching stall happens after a psi event was
> > > generated and within the window duration, the new event is not
> > > generated because the events are rate-limited to one per window. If
> > > after that no new stall is recorded then the event will not be
> > > generated even after rate-limiting duration has passed. This is
> > > happening because with no new stall, window_update will not be called
> > > even though threshold was previously breached. To fix this, record
> > > threshold breaching occurrence and generate the event once window
> > > duration is passed.
> > >
> > > Suggested-by: Suren Baghdasaryan <[email protected]>
> > > Signed-off-by: Zhaoyang Huang <[email protected]>
> > > ---
> > > v2: modify the logic according to Suren's suggestion
> > > v3: update commit message
> > > ---
> > > ---
> > > include/linux/psi_types.h | 2 ++
> > > kernel/sched/psi.c | 38 +++++++++++++++++++++++---------------
> > > 2 files changed, 25 insertions(+), 15 deletions(-)
> > >
> > > diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
> > > index 0a23300..87b694a 100644
> > > --- a/include/linux/psi_types.h
> > > +++ b/include/linux/psi_types.h
> > > @@ -132,6 +132,8 @@ struct psi_trigger {
> > >
> > > /* Refcounting to prevent premature destruction */
> > > struct kref refcount;
> > > +
> > > + bool threshold_breach;
> > > };
> > >
> > > struct psi_group {
> > > diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
> > > index 1652f2b..5c67ab9 100644
> > > --- a/kernel/sched/psi.c
> > > +++ b/kernel/sched/psi.c
> > > @@ -524,24 +524,29 @@ static u64 update_triggers(struct psi_group *group, u64 now)
> > > */
> > > list_for_each_entry(t, &group->triggers, node) {
> > > u64 growth;
> > > + bool trigger_stalled =
> > > + group->polling_total[t->state] != total[t->state];
> > >
> > > - /* Check for stall activity */
> > > - if (group->polling_total[t->state] == total[t->state])
> > > - continue;
> > > -
> > > - /*
> > > - * Multiple triggers might be looking at the same state,
> > > - * remember to update group->polling_total[] once we've
> > > - * been through all of them. Also remember to extend the
> > > - * polling time if we see new stall activity.
> > > - */
> > > - new_stall = true;
> > > -
> > > - /* Calculate growth since last update */
> > > - growth = window_update(&t->win, now, total[t->state]);
> > > - if (growth < t->threshold)
> > > + /* Check for stall activity or a previous threshold breach */
> > > + if (!trigger_stalled && !t->threshold_breach)
> > > continue;
> > >
> > > + if (trigger_stalled) {
> > > + /*
> > > + * Multiple triggers might be looking at the same state,
> > > + * remember to update group->polling_total[] once we've
> > > + * been through all of them. Also remember to extend the
> > > + * polling time if we see new stall activity.
> > > + */
> > > + new_stall = true;
> > > +
> > > + /* Calculate growth since last update */
> > > + growth = window_update(&t->win, now, total[t->state]);
> > > + if (growth < t->threshold)
> > > + continue;
> > > +
> > > + t->threshold_breach = true;
> > > + }
> > > /* Limit event signaling to once per window */
> > > if (now < t->last_event_time + t->win.size)
> > > continue;
> > > @@ -550,6 +555,8 @@ static u64 update_triggers(struct psi_group *group, u64 now)
> > > if (cmpxchg(&t->event, 0, 1) == 0)
> > > wake_up_interruptible(&t->event_wait);
> > > t->last_event_time = now;
> > > + /* Reset threshold breach flag once event got generated */
> > > + t->threshold_breach = false;
> > > }
> > >
> > > if (new_stall)
> > > @@ -1152,6 +1159,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
> > > t->last_event_time = 0;
> > > init_waitqueue_head(&t->event_wait);
> > > kref_init(&t->refcount);
> > > + t->threshold_breach = false;
> > >
> > > mutex_lock(&group->trigger_lock);
> > >
> > > --
> > > 1.9.1
> > >