From: Wanpeng Li <kernellwp@gmail.com>
To: Peter Zijlstra <peterz@infradead.org>,
Ingo Molnar <mingo@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Paolo Bonzini <pbonzini@redhat.com>,
Sean Christopherson <seanjc@google.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>,
Christian Borntraeger <borntraeger@linux.ibm.com>,
Steven Rostedt <rostedt@goodmis.org>,
Vincent Guittot <vincent.guittot@linaro.org>,
Juri Lelli <juri.lelli@redhat.com>,
linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
Wanpeng Li <wanpengli@tencent.com>,
Richie Buturla <richie@linux.ibm.com>
Subject: [PATCH v3 02/10] sched/fair: Credit a persistent, queue-depth-scaled vlag margin
Date: Fri, 12 Jun 2026 09:33:47 +0800 [thread overview]
Message-ID: <20260612013355.59231-3-kernellwp@gmail.com> (raw)
In-Reply-To: <20260612013355.59231-1-kernellwp@gmail.com>
From: Wanpeng Li <wanpengli@tencent.com>
Crediting only up to vlag = 0 makes the buddy eligible for a single
pick_eevdf() pass. The next update_curr() can push it below zero again
before PICK_BUDDY consumes the hint.
Credit to a bounded positive-vlag margin instead, so the buddy stays
eligible across several scheduling decisions. Scale the margin with
runqueue depth, because deeper runqueues dilute eligibility faster, and
clamp it to entity_lag()'s legal positive-lag bound to preserve EEVDF
fairness.
The helper is not called in this change; there is no functional change.
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
---
kernel/sched/fair.c | 58 ++++++++++++++++++++++++++++++++++++---------
1 file changed, 47 insertions(+), 11 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e7f5ea25fdae..c6502db62cd3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9342,21 +9342,45 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct t
}
/*
- * eevdf_credit_entity_vlag - credit a nominated next-buddy to eligibility
+ * Positive-vlag target margin for a credited buddy, scaled by runqueue
+ * depth so it stays eligible across several picks. The caller clamps it to
+ * entity_lag()'s legal bound, so EEVDF fairness is preserved.
+ */
+static u64 __maybe_unused
+eevdf_persistent_margin(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ u64 base = sysctl_sched_base_slice;
+ unsigned int n = cfs_rq->h_nr_queued;
+ u64 raw;
+
+ if (n <= 4)
+ raw = base * 4;
+ else if (n <= 8)
+ raw = base * 6;
+ else if (n <= 16)
+ raw = base * 8;
+ else
+ raw = base * 12;
+
+ return calc_delta_fair(raw, se);
+}
+
+/*
+ * eevdf_credit_entity_vlag - credit bounded vlag to a nominated next-buddy
*
* Advance @se (already nominated by set_next_buddy(), so cfs_rq->next == se)
- * just enough negative vlag to reach the eligibility boundary (vlag = 0) so
- * pick_eevdf()'s PICK_BUDDY branch returns it. cfs_rq->curr is shifted in
- * place (off-tree, carrying any vprot window). Queued entities are left
- * unchanged.
+ * to a bounded positive-vlag margin so pick_eevdf()'s PICK_BUDDY branch
+ * keeps returning it across several picks, without exceeding entity_lag()'s
+ * legal bound. cfs_rq->curr is shifted in place (off-tree, carrying any
+ * vprot window). Queued entities are left unchanged.
*
- * Idempotent: a no-op once @se is already eligible. Caller must hold
+ * Idempotent once @se holds the margin. Caller must hold
* rq_of(cfs_rq)->lock with rq_clock up to date.
*/
static void __maybe_unused
eevdf_credit_entity_vlag(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- u64 avruntime, credit;
+ u64 avruntime, credit, want, margin, max_slice, lag_limit;
s64 vlag;
/* Callers gate this helper with YIELD_TO_LAG_CREDIT. */
@@ -9371,11 +9395,23 @@ eevdf_credit_entity_vlag(struct cfs_rq *cfs_rq, struct sched_entity *se)
avruntime = avg_vruntime(cfs_rq);
vlag = entity_lag(cfs_rq, se, avruntime);
- /* Already eligible: nothing to do. */
- if (vlag >= 0)
- return;
+ /* Clamp the margin to entity_lag()'s bound so place_entity() keeps it. */
+ max_slice = cfs_rq_max_slice(cfs_rq) + TICK_NSEC;
+ lag_limit = calc_delta_fair(max_slice, se);
+ margin = eevdf_persistent_margin(cfs_rq, se);
+ if (lag_limit && margin > lag_limit)
+ margin = lag_limit;
+ if (vlag >= 0) {
+ if ((u64)vlag >= margin)
+ return;
+ want = margin - (u64)vlag;
+ } else {
+ want = margin + (u64)(-vlag);
+ }
- credit = (u64)(-vlag);
+ credit = want;
+ if (!credit)
+ return;
if (cfs_rq->curr == se) {
/* curr is off-tree: in-place shift, carrying any vprot window. */
--
2.43.0
next prev parent reply other threads:[~2026-06-12 1:34 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-06-12 1:33 [PATCH v3 00/10] sched/fair, KVM: Semantics-aware directed yield for oversubscribed KVM Wanpeng Li
2026-06-12 1:33 ` [PATCH v3 01/10] sched/fair: Add EEVDF lag credit primitive for nominated next-buddy Wanpeng Li
2026-06-12 1:49 ` sashiko-bot
2026-06-12 5:34 ` K Prateek Nayak
2026-06-12 1:33 ` Wanpeng Li [this message]
2026-06-12 1:53 ` [PATCH v3 02/10] sched/fair: Credit a persistent, queue-depth-scaled vlag margin sashiko-bot
2026-06-12 6:07 ` K Prateek Nayak
2026-06-12 1:33 ` [PATCH v3 03/10] sched/fair: Credit queued next-buddy via canonical requeue Wanpeng Li
2026-06-12 1:55 ` sashiko-bot
2026-06-12 1:33 ` [PATCH v3 04/10] sched/fair: Credit nominated next-buddy in yield_to_task_fair() Wanpeng Li
2026-06-12 1:54 ` sashiko-bot
2026-06-12 1:33 ` [PATCH v3 05/10] sched/fair: Force a local resched on yield_to() so the buddy is picked Wanpeng Li
2026-06-12 1:50 ` sashiko-bot
2026-06-12 1:33 ` [PATCH v3 06/10] KVM: x86: Add IPI tracking infrastructure for directed yield Wanpeng Li
2026-06-12 1:33 ` [PATCH v3 07/10] KVM: x86/lapic: Track unicast fixed IPI delivery Wanpeng Li
2026-06-12 1:33 ` [PATCH v3 08/10] KVM: x86/lapic: Clear IPI tracking on matching-vector EOI Wanpeng Li
2026-06-12 3:46 ` sashiko-bot
2026-06-12 1:33 ` [PATCH v3 09/10] KVM: Add IPI-aware directed-yield candidate selection Wanpeng Li
2026-06-12 1:48 ` sashiko-bot
2026-06-12 1:33 ` [PATCH v3 10/10] KVM: Add relaxed preempted-only fallback for directed yield Wanpeng Li
2026-06-12 5:17 ` [PATCH v3 00/10] sched/fair, KVM: Semantics-aware directed yield for oversubscribed KVM K Prateek Nayak
2026-06-12 9:43 ` Shrikanth Hegde
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=20260612013355.59231-3-kernellwp@gmail.com \
--to=kernellwp@gmail.com \
--cc=borntraeger@linux.ibm.com \
--cc=juri.lelli@redhat.com \
--cc=kprateek.nayak@amd.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=richie@linux.ibm.com \
--cc=rostedt@goodmis.org \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=vincent.guittot@linaro.org \
--cc=wanpengli@tencent.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