From: Josh Don <joshdon@google.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: mingo@kernel.org, vincent.guittot@linaro.org,
linux-kernel@vger.kernel.org, juri.lelli@redhat.com,
dietmar.eggemann@arm.com, rostedt@goodmis.org,
bsegall@google.com, mgorman@suse.de, bristot@redhat.com,
corbet@lwn.net, qyousef@layalina.io, chris.hyser@oracle.com,
patrick.bellasi@matbug.net, pjt@google.com, pavel@ucw.cz,
qperret@google.com, tim.c.chen@linux.intel.com, timj@gnu.org,
kprateek.nayak@amd.com, yu.c.chen@intel.com,
youssefesmat@chromium.org, joel@joelfernandes.org, efault@gmx.de
Subject: Re: [PATCH 08/17] sched/fair: Implement an EEVDF like policy
Date: Tue, 28 Mar 2023 18:26:51 -0700 [thread overview]
Message-ID: <CABk29Nt4T67S+L9Qs1qeOUyo5gY1Qy5KuOwuCYNM74E58J81Eg@mail.gmail.com> (raw)
In-Reply-To: <20230328110354.141543852@infradead.org>
Hi Peter,
This is a really interesting proposal and in general I think the
incorporation of latency/deadline is quite a nice enhancement. We've
struggled for a while to get better latency bounds on performance
sensitive threads in the face of antagonism from overcommit.
> void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
> {
> + s64 lag, limit;
> +
> SCHED_WARN_ON(!se->on_rq);
> - se->vlag = avg_vruntime(cfs_rq) - se->vruntime;
> + lag = avg_vruntime(cfs_rq) - se->vruntime;
> +
> + limit = calc_delta_fair(max_t(u64, 2*se->slice, TICK_NSEC), se);
> + se->vlag = clamp(lag, -limit, limit);
This is for dequeue; presumably you'd want to update the vlag at
enqueue in case the average has moved again due to enqueue/dequeue of
other entities?
> +static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
> +{
> + struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
> + struct sched_entity *curr = cfs_rq->curr;
> + struct sched_entity *best = NULL;
> +
> + if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
> + curr = NULL;
> +
> + while (node) {
> + struct sched_entity *se = __node_2_se(node);
> +
> + /*
> + * If this entity is not eligible, try the left subtree.
> + */
> + if (!entity_eligible(cfs_rq, se)) {
> + node = node->rb_left;
> + continue;
> + }
> +
> + /*
> + * If this entity has an earlier deadline than the previous
> + * best, take this one. If it also has the earliest deadline
> + * of its subtree, we're done.
> + */
> + if (!best || deadline_gt(deadline, best, se)) {
> + best = se;
> + if (best->deadline == best->min_deadline)
> + break;
Isn't it possible to have a child with less vruntime (ie. rb->left)
but with the same deadline? Wouldn't it be preferable to choose the
child instead since the deadlines are equivalent but the child has
received less service time?
> + }
> +
> + /*
> + * If the earlest deadline in this subtree is in the fully
> + * eligible left half of our space, go there.
> + */
> + if (node->rb_left &&
> + __node_2_se(node->rb_left)->min_deadline == se->min_deadline) {
> + node = node->rb_left;
> + continue;
> + }
> +
> + node = node->rb_right;
> + }
> +
> + if (!best || (curr && deadline_gt(deadline, best, curr)))
> + best = curr;
> +
> + if (unlikely(!best)) {
> + struct sched_entity *left = __pick_first_entity(cfs_rq);
> + if (left) {
> + pr_err("EEVDF scheduling fail, picking leftmost\n");
> + return left;
> + }
> + }
> +
> + return best;
> +}
> +
>
> static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
> @@ -5088,19 +5307,20 @@ dequeue_entity(struct cfs_rq *cfs_rq, st
> static void
> check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
> {
> - unsigned long ideal_runtime, delta_exec;
> + unsigned long delta_exec;
> struct sched_entity *se;
> s64 delta;
>
> - /*
> - * When many tasks blow up the sched_period; it is possible that
> - * sched_slice() reports unusually large results (when many tasks are
> - * very light for example). Therefore impose a maximum.
> - */
> - ideal_runtime = min_t(u64, sched_slice(cfs_rq, curr), sysctl_sched_latency);
> + if (sched_feat(EEVDF)) {
> + if (pick_eevdf(cfs_rq) != curr)
> + goto preempt;
This could shortcircuit the loop in pick_eevdf once we find a best
that has less vruntime and sooner deadline than curr, since we know
we'll never pick curr in that case. Might help performance when we
have a large tree for this cfs_rq.
> +
> + return;
> + }
>
> delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
> - if (delta_exec > ideal_runtime) {
> + if (delta_exec > curr->slice) {
> +preempt:
> resched_curr(rq_of(cfs_rq));
> /*
> * The current task ran long enough, ensure it doesn't get
> @@ -5124,7 +5344,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq
> if (delta < 0)
> return;
>
> - if (delta > ideal_runtime)
> + if (delta > curr->slice)
> resched_curr(rq_of(cfs_rq));
> }
Best,
Josh
next prev parent reply other threads:[~2023-03-29 1:27 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-28 9:26 [PATCH 00/17] sched: EEVDF using latency-nice Peter Zijlstra
2023-03-28 9:26 ` [PATCH 01/17] sched: Introduce latency-nice as a per-task attribute Peter Zijlstra
2023-03-28 9:26 ` [PATCH 02/17] sched/fair: Add latency_offset Peter Zijlstra
2023-03-28 9:26 ` [PATCH 03/17] sched/fair: Add sched group latency support Peter Zijlstra
2023-03-28 9:26 ` [PATCH 04/17] sched/fair: Add avg_vruntime Peter Zijlstra
2023-03-28 23:57 ` Josh Don
2023-03-29 7:50 ` Peter Zijlstra
2023-04-05 19:13 ` Peter Zijlstra
2023-03-28 9:26 ` [PATCH 05/17] sched/fair: Remove START_DEBIT Peter Zijlstra
2023-03-28 9:26 ` [PATCH 06/17] sched/fair: Add lag based placement Peter Zijlstra
2023-04-03 9:18 ` Chen Yu
2023-04-05 9:47 ` Peter Zijlstra
2023-04-06 3:03 ` Chen Yu
2023-04-13 15:42 ` Chen Yu
2023-04-13 15:55 ` Chen Yu
2023-03-28 9:26 ` [PATCH 07/17] rbtree: Add rb_add_augmented_cached() helper Peter Zijlstra
2023-03-28 9:26 ` [PATCH 08/17] sched/fair: Implement an EEVDF like policy Peter Zijlstra
2023-03-29 1:26 ` Josh Don [this message]
2023-03-29 8:02 ` Peter Zijlstra
2023-03-29 8:06 ` Peter Zijlstra
2023-03-29 8:22 ` Peter Zijlstra
2023-03-29 18:48 ` Josh Don
2023-03-29 8:12 ` Peter Zijlstra
2023-03-29 18:54 ` Josh Don
2023-03-29 8:18 ` Peter Zijlstra
2023-03-29 14:35 ` Vincent Guittot
2023-03-30 8:01 ` Peter Zijlstra
2023-03-30 17:05 ` Vincent Guittot
2023-04-04 12:00 ` Peter Zijlstra
2023-03-28 9:26 ` [PATCH 09/17] sched: Commit to lag based placement Peter Zijlstra
2023-03-28 9:26 ` [PATCH 10/17] sched/smp: Use lag to simplify cross-runqueue placement Peter Zijlstra
2023-03-28 9:26 ` [PATCH 11/17] sched: Commit to EEVDF Peter Zijlstra
2023-03-28 9:26 ` [PATCH 12/17] sched/debug: Rename min_granularity to base_slice Peter Zijlstra
2023-03-28 9:26 ` [PATCH 13/17] sched: Merge latency_offset into slice Peter Zijlstra
2023-03-28 9:26 ` [PATCH 14/17] sched/eevdf: Better handle mixed slice length Peter Zijlstra
2023-03-31 15:26 ` Vincent Guittot
2023-04-04 9:29 ` Peter Zijlstra
2023-04-04 13:50 ` Joel Fernandes
2023-04-05 5:41 ` Mike Galbraith
2023-04-05 8:35 ` Peter Zijlstra
2023-04-05 20:05 ` Joel Fernandes
2023-04-14 11:18 ` Phil Auld
2023-04-16 5:10 ` Joel Fernandes
[not found] ` <20230401232355.336-1-hdanton@sina.com>
2023-04-02 2:40 ` Mike Galbraith
2023-03-28 9:26 ` [PATCH 15/17] [RFC] sched/eevdf: Sleeper bonus Peter Zijlstra
2023-03-29 9:10 ` Mike Galbraith
2023-03-28 9:26 ` [PATCH 16/17] [RFC] sched/eevdf: Minimal vavg option Peter Zijlstra
2023-03-28 9:26 ` [PATCH 17/17] [DEBUG] sched/eevdf: Debug / validation crud Peter Zijlstra
2023-04-03 7:42 ` [PATCH 00/17] sched: EEVDF using latency-nice Shrikanth Hegde
2023-04-10 3:13 ` David Vernet
2023-04-11 2:09 ` David Vernet
[not found] ` <20230410082307.1327-1-hdanton@sina.com>
2023-04-11 10:15 ` Mike Galbraith
[not found] ` <20230411133333.1790-1-hdanton@sina.com>
2023-04-11 14:56 ` Mike Galbraith
[not found] ` <20230412025042.1413-1-hdanton@sina.com>
2023-04-12 4:05 ` Mike Galbraith
2023-04-25 12:32 ` Phil Auld
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CABk29Nt4T67S+L9Qs1qeOUyo5gY1Qy5KuOwuCYNM74E58J81Eg@mail.gmail.com \
--to=joshdon@google.com \
--cc=bristot@redhat.com \
--cc=bsegall@google.com \
--cc=chris.hyser@oracle.com \
--cc=corbet@lwn.net \
--cc=dietmar.eggemann@arm.com \
--cc=efault@gmx.de \
--cc=joel@joelfernandes.org \
--cc=juri.lelli@redhat.com \
--cc=kprateek.nayak@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@suse.de \
--cc=mingo@kernel.org \
--cc=patrick.bellasi@matbug.net \
--cc=pavel@ucw.cz \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=qperret@google.com \
--cc=qyousef@layalina.io \
--cc=rostedt@goodmis.org \
--cc=tim.c.chen@linux.intel.com \
--cc=timj@gnu.org \
--cc=vincent.guittot@linaro.org \
--cc=youssefesmat@chromium.org \
--cc=yu.c.chen@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).