From: "tip-bot2 for Vincent Guittot" <tip-bot2@linutronix.de>
To: linux-tip-commits@vger.kernel.org
Cc: Vincent Guittot <vincent.guittot@linaro.org>,
"Peter Zijlstra (Intel)" <peterz@infradead.org>,
K Prateek Nayak <kprateek.nayak@amd.com>,
x86@kernel.org, linux-kernel@vger.kernel.org
Subject: [tip: sched/core] sched/eevdf: Speedup short slice task scheduling
Date: Tue, 30 Jun 2026 09:03:39 -0000 [thread overview]
Message-ID: <178281021944.3843924.13242155820515469077.tip-bot2@tip-bot2> (raw)
In-Reply-To: <20260624151229.1710703-7-vincent.guittot@linaro.org>
The following commit has been merged into the sched/core branch of tip:
Commit-ID: 0d1e7a2bab35dbc898e8a6aa29fd074dafbbccda
Gitweb: https://git.kernel.org/tip/0d1e7a2bab35dbc898e8a6aa29fd074dafbbccda
Author: Vincent Guittot <vincent.guittot@linaro.org>
AuthorDate: Wed, 24 Jun 2026 17:12:29 +02:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Tue, 30 Jun 2026 10:56:55 +02:00
sched/eevdf: Speedup short slice task scheduling
When a task with a shorter slice is enqueued, we protect the running
task which has a longer slice until it becomes ineligible instead of a
full slice in order to speedup the switch to other tasks until the task
with the shortest slice is scheduled. This helps to the task to not wait
too many full slices before running.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://patch.msgid.link/20260624151229.1710703-7-vincent.guittot@linaro.org
---
kernel/sched/fair.c | 71 ++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 69 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2547a97..c575910 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -777,6 +777,67 @@ u64 avg_vruntime(struct cfs_rq *cfs_rq)
return cfs_rq->zero_vruntime;
}
+/*
+ * \Sum (v_i - v0)*w_i
+ * V = ------------------- + v0
+ * \Sum w_i
+ *
+ * Let W = \Sum w_i, and move v_j such that 'v_j == V', thus:
+ *
+ * V = 1/W * {(v_j - v0)*w_j + \Sum_i!=j (v_i - v0)*w_i} + v0
+ *
+ * v_j = 1/W * {(v_j - v0)*w_j + \Sum_i!=j (v_i - v0)*w_i} + v0
+ *
+ * v_j = 1/W * (v_j - v0)*w_j + 1/W * \Sum_i!=j (v_i - v0)*w_i + v0
+ *
+ * v_j - 1/W * (v_j - v0)*w_j = 1/W * \Sum_i!=j (v_i - v0)*w_i + v0
+ *
+ * v_j*W - (v_j - v0)*w_j = \Sum_i!=j (v_i - v0)*w_i + v0*W
+ *
+ * v_j*(W - w_j) + v0*w_j = \Sum_i!=j (v_i - v0)*w_i + v0*W
+ *
+ * v_j*(W - w_j) = \Sum_i!=j (v_i - v0)*w_i + v0*(W - w_j)
+ *
+ * \Sum_i!=j (v_i - v0)*w_i
+ * v_j = ------------------------ + v0
+ * W - w_j
+ *
+ * When v_j happens to be curr, then '\Sum_i!=j (v_i - v0)*w_i'
+ * is cfs_rq->sum_w_runtime, and 'W - w_j' is cfs_rq->sum_weight, since curr
+ * is not included in the sum.
+ */
+static u64 ineligible_vruntime(struct cfs_rq *cfs_rq)
+{
+ struct sched_entity *curr = cfs_rq->curr;
+ long weight = cfs_rq->sum_weight;
+ s64 delta = 0;
+
+ if (curr && !curr->on_rq)
+ curr = NULL;
+
+ /*
+ * This is called from set_next_task_fair(.first=true) /
+ * set_protect_slice() so curr had better be set and on_rq.
+ */
+ WARN_ON_ONCE(!curr);
+
+ if (weight) {
+ s64 runtime = cfs_rq->sum_w_vruntime;
+
+ /*
+ * Do not add @curr to obtain the effective '- w_j' terms.
+ */
+
+ /* sign flips effective floor / ceiling */
+ if (runtime < 0)
+ runtime -= (weight - 1);
+
+ delta = div64_long(runtime, weight);
+ }
+
+ return cfs_rq->zero_vruntime + delta + 1;
+}
+
static inline u64 cfs_rq_max_slice(struct cfs_rq *cfs_rq);
/*
@@ -1058,8 +1119,14 @@ static inline void set_protect_slice(struct cfs_rq *cfs_rq, struct sched_entity
slice = cfs_rq_min_slice(cfs_rq);
slice = min(slice, se->slice);
- if (slice != se->slice)
- vprot = min_vruntime(vprot, se->vruntime + calc_delta_fair(slice, se));
+
+ /* If there are shorter slices than se's one */
+ if (slice != se->slice) {
+ if (sched_feat(PREEMPT_SHORT))
+ vprot = min_vruntime(vprot, ineligible_vruntime(cfs_rq));
+ else
+ vprot = min_vruntime(vprot, se->vruntime + calc_delta_fair(slice, se));
+ }
se->vprot = vprot;
}
prev parent reply other threads:[~2026-06-30 9:03 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-06-24 15:12 [PATCH 0/6 v3] sched/eevdf: Improve scheduling latency of short slice task Vincent Guittot
2026-06-24 15:12 ` [PATCH 1/6 v3] sched/fair: Set next buddy for preempt short Vincent Guittot
2026-06-25 6:24 ` K Prateek Nayak
2026-06-25 12:40 ` Vincent Guittot
2026-06-25 12:43 ` Peter Zijlstra
2026-06-26 6:54 ` Peter Zijlstra
2026-06-26 7:02 ` Vincent Guittot
2026-06-26 8:08 ` Peter Zijlstra
2026-06-26 8:55 ` Vincent Guittot
2026-06-30 9:03 ` [tip: sched/core] " tip-bot2 for Vincent Guittot
2026-06-24 15:12 ` [PATCH 2/6 v3] sched/eevdf: Take into account current's lag when updating slice protection Vincent Guittot
2026-06-30 9:03 ` [tip: sched/core] " tip-bot2 for Vincent Guittot
2026-06-24 15:12 ` [PATCH 3/6 v3] sched/eevdf: Update slice protection even when resched is already set Vincent Guittot
2026-06-26 7:21 ` Peter Zijlstra
2026-06-26 7:46 ` Peter Zijlstra
2026-06-30 9:03 ` [tip: sched/core] sched/core: Fix inter-class wakeup_preempt() tip-bot2 for Peter Zijlstra
2026-06-30 9:03 ` [tip: sched/core] sched/eevdf: Update slice protection even when resched is already set tip-bot2 for Vincent Guittot
2026-06-24 15:12 ` [PATCH 4/6 v3] sched/eevdf: Cancel slice protection if short slice task is eligible Vincent Guittot
2026-06-25 6:00 ` K Prateek Nayak
2026-06-25 12:40 ` Vincent Guittot
2026-06-26 5:51 ` Shubhang Kaushik
2026-06-26 7:39 ` Vincent Guittot
2026-06-30 9:03 ` [tip: sched/core] " tip-bot2 for Vincent Guittot
2026-06-24 15:12 ` [PATCH 5/6 v3] sched/eevdf: Always update slice protection Vincent Guittot
2026-06-30 9:03 ` [tip: sched/core] " tip-bot2 for Vincent Guittot
2026-06-24 15:12 ` [PATCH 6/6 v3] sched/eevdf: Speedup short slice task scheduling Vincent Guittot
2026-06-25 7:37 ` K Prateek Nayak
2026-06-25 8:37 ` Peter Zijlstra
2026-06-25 10:09 ` Peter Zijlstra
2026-06-25 12:57 ` Vincent Guittot
2026-06-25 12:59 ` Vincent Guittot
2026-06-25 22:28 ` Peter Zijlstra
2026-06-26 3:57 ` K Prateek Nayak
2026-06-26 6:41 ` Peter Zijlstra
2026-06-26 7:05 ` Vincent Guittot
2026-06-26 7:18 ` Peter Zijlstra
2026-06-26 7:54 ` Peter Zijlstra
2026-06-26 8:55 ` Vincent Guittot
2026-06-26 13:55 ` Vincent Guittot
2026-06-29 14:25 ` Vincent Guittot
2026-06-25 14:55 ` Vincent Guittot
2026-06-25 12:51 ` Vincent Guittot
2026-06-25 8:33 ` Peter Zijlstra
2026-06-30 9:03 ` tip-bot2 for Vincent Guittot [this message]
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=178281021944.3843924.13242155820515469077.tip-bot2@tip-bot2 \
--to=tip-bot2@linutronix.de \
--cc=kprateek.nayak@amd.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=vincent.guittot@linaro.org \
--cc=x86@kernel.org \
/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
all inboxes | Powered by JetHome®