Message-ID: <yaV6Pl8Nz9T25r41NdQTNSmI2lbTQ6VG0XmOoKTw77RLE0pRZAorDIQU1Cgv3XpvPpUkAPHWeJyEXwaEChcctVoxuzS_24jaMzI8-yds744=@gianis.ca>
Date: Fri, 13 Jun 2025 21:00:02 +0000
From: dhaval@...nis.ca
To: Vincent Guittot <vincent.guittot@...aro.org>
Cc: mingo@...hat.com, peterz@...radead.org, juri.lelli@...hat.com, dietmar.eggemann@....com, rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de, vschneid@...hat.com, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 2/4] sched/fair: Increase max lag clamping






On Friday, June 13th, 2025 at 7:14 AM, Vincent Guittot <vincent.guittot@...aro.org> wrote:

> 
> 
> From: Peter Zijlstra peterz@...radead.org
> 
> 
> sched_entity's lag is currently limited to the maximum between the tick
> and twice its slice. This is too short compared to the maximum custom
> slice that can be set and accumulated by other tasks.
> A task can accumulate up to its slice of negative lag while running to
> parity and the other runnable tasks can accumulate the same positive lag
> while waiting to run. This positive lag could be lost during dequeue when
> clamping it to twice task's slice if a task's slice is 100ms and others
> use a smaller value like the default 2.8ms.
> Clamp the lag of a task to the maximum slice of enqueued entities plus
> a tick as the update can be delayed to the next tick.
> 
> Signed-off-by: Peter Zijlstra (Intel) peterz@...radead.org
> 
> 
> [ Rebased and Fix max slice computation ]
> 
> Signed-off-by: Vincent Guittot vincent.guittot@...aro.org
> 
> ---
> include/linux/sched.h | 1 +
> kernel/sched/fair.c | 41 +++++++++++++++++++++++++++++++++++++----
> 2 files changed, 38 insertions(+), 4 deletions(-)
> 
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 4f78a64beb52..89855ab45c43 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -576,6 +576,7 @@ struct sched_entity {
> u64 deadline;
> u64 min_vruntime;
> u64 min_slice;
> + u64 max_slice;
> 

I am just wondering if it makes sense to maybe add a few comments here on what each of these fields are for. Maybe not this series, but if you are open to it, I will spin one up next week.

> struct list_head group_node;
> unsigned char on_rq;
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 44a09de38ddf..479b38dc307a 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -676,6 +676,8 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
> return cfs_rq->min_vruntime + avg;
> 
> }
> 
> +static inline u64 cfs_rq_max_slice(struct cfs_rq cfs_rq);
> +
> /
> * lag_i = S - s_i = w_i * (V - v_i)
> *
> @@ -689,17 +691,16 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
> * EEVDF gives the following limit for a steady state system:
> *
> * -r_max < lag < max(r_max, q)
> - *
> - * XXX could add max_slice to the augmented data to track this.
> */
> static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
> {
> + u64 max_slice = cfs_rq_max_slice(cfs_rq) + TICK_NSEC;
> s64 vlag, limit;
> 
> WARN_ON_ONCE(!se->on_rq);
> 
> 
> vlag = avg_vruntime(cfs_rq) - se->vruntime;
> 
> - limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
> 
> + limit = calc_delta_fair(max_slice, se);
> 
> se->vlag = clamp(vlag, -limit, limit);
> 

As an aside, I have a test for Theorem 1 from the paper which shows we are clamping here even in conditions I do not expect. Almost always a cgroup seems to be involved. I was out dealing with sickness last couple of weeks, so I have not debugged further.

> }
> @@ -795,6 +796,21 @@ static inline u64 cfs_rq_min_slice(struct cfs_rq *cfs_rq)
> return min_slice;
> }
> 
> +static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq)
> +{
> + struct sched_entity *root = __pick_root_entity(cfs_rq);
> + struct sched_entity *curr = cfs_rq->curr;
> 
> + u64 max_slice = 0ULL;
> +
> + if (curr && curr->on_rq)
> 
> + max_slice = curr->slice;
> 
> +
> + if (root)
> + max_slice = max(max_slice, root->max_slice);
> 
> +
> + return max_slice;
> +}
> +
> static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
> {
> return entity_before(__node_2_se(a), __node_2_se(b));
> @@ -820,6 +836,16 @@ static inline void __min_slice_update(struct sched_entity *se, struct rb_node *n
> }
> }
> 
> +static inline void __max_slice_update(struct sched_entity *se, struct rb_node *node)
> +{
> + if (node) {
> + struct sched_entity *rse = __node_2_se(node);
> +
> + if (rse->max_slice > se->max_slice)
> 
> + se->max_slice = rse->max_slice;
> 
> + }
> +}
> +
> /*
> * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
> 
> */
> @@ -827,6 +853,7 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
> {
> u64 old_min_vruntime = se->min_vruntime;
> 
> u64 old_min_slice = se->min_slice;
> 
> + u64 old_max_slice = se->max_slice;
> 
> struct rb_node *node = &se->run_node;
> 
> 
> se->min_vruntime = se->vruntime;
> 
> @@ -837,8 +864,13 @@ static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
> __min_slice_update(se, node->rb_right);
> 
> __min_slice_update(se, node->rb_left);
> 
> 
> + se->max_slice = se->slice;
> 
> + __max_slice_update(se, node->rb_right);
> 
> + __max_slice_update(se, node->rb_left);
> 
> +
> return se->min_vruntime == old_min_vruntime &&
> 
> - se->min_slice == old_min_slice;
> 
> + se->min_slice == old_min_slice &&
> 
> + se->max_slice == old_max_slice;
> 
> }
> 
> RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
> @@ -852,6 +884,7 @@ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
> avg_vruntime_add(cfs_rq, se);
> se->min_vruntime = se->vruntime;
> 
> se->min_slice = se->slice;
> 
> + se->max_slice = se->slice;
> 
> rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
> 
> __entity_less, &min_vruntime_cb);
> }

otherwise

Reviewed-by: Dhaval Giani (AMD) <dhaval@...nis.ca>

> --
> 2.43.0

Powered by blists - more mailing lists