| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAKfTPtDCDZtmc-kNthF-txf4-J8byROSbPseQ_b6W+Q0Q2W9xQ@mail.gmail.com>
Date: Wed, 23 Apr 2025 12:19:50 +0200
From: Vincent Guittot <vincent.guittot@...aro.org>
To: Peter Zijlstra <peterz@...radead.org>
Cc: mingo@...hat.com, juri.lelli@...hat.com, dietmar.eggemann@....com,
rostedt@...dmis.org, bsegall@...gle.com, mgorman@...e.de, vschneid@...hat.com,
linux-kernel@...r.kernel.org, dhaval@...nis.ca
Subject: Re: [PATCH] sched/fair: Increase max lag clamping
Hi Peter,
On Tue, 22 Apr 2025 at 12:16, Peter Zijlstra <peterz@...radead.org> wrote:
>
> On Fri, Apr 18, 2025 at 05:51:15PM +0200, Peter Zijlstra wrote:
> > On Fri, Apr 18, 2025 at 05:12:25PM +0200, Vincent Guittot wrote:
> > > sched_entity lag is currently limited to the maximum between the tick and
> > > twice the slice. This is too short compared to the maximum custom slice
> > > that can be set and accumulated by other tasks.
> > > Clamp the lag to the maximum slice that a task can set. A task A 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 task A's slice is 100ms and others
> > > use a smaller value like the default 2.8ms.
> > >
> > > Signed-off-by: Vincent Guittot <vincent.guittot@...aro.org>
> > > ---
> > > kernel/sched/fair.c | 16 +++++++++-------
> > > 1 file changed, 9 insertions(+), 7 deletions(-)
> > >
> > > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > > index a0c4cd26ee07..1c2c70decb20 100644
> > > --- a/kernel/sched/fair.c
> > > +++ b/kernel/sched/fair.c
> > > @@ -683,15 +683,17 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
> > > * is possible -- by addition/removal/reweight to the tree -- to move V around
> > > * and end up with a larger lag than we started with.
> > > *
> > > - * Limit this to either double the slice length with a minimum of TICK_NSEC
> > > - * since that is the timing granularity.
> > > - *
> > > - * EEVDF gives the following limit for a steady state system:
> > > + * Limit this to the max allowed custom slice length which is higher than the
> > > + * timing granularity (the tick) and 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.
> > > */
> >
> > Right, its that max_slice XXX there.
> >
> > I think I've actually done that patch at some point, but I'm not sure
> > where I've placed it :-)
>
> No matter, I've redone it by copy-paste from min_slice.
>
> How's something like this then?
Thanks, I will test it
>
> ---
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index f96ac1982893..9e90cd9023db 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -573,6 +573,7 @@ struct sched_entity {
> u64 deadline;
> u64 min_vruntime;
> u64 min_slice;
> + u64 max_slice;
>
> struct list_head group_node;
> unsigned char on_rq;
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 84916c865377..7c3c95f5cabd 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);
> }
> @@ -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 = min(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 +836,15 @@ 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 +852,7 @@ 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 +863,13 @@ 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 +883,7 @@ 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);
> }
Powered by blists - more mailing lists