From: Peter Zijlstra <peterz@infradead.org>
To: mingo@kernel.org, vincent.guittot@linaro.org,
dietmar.eggemann@arm.com, juri.lelli@redhat.com,
rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de
Cc: linux-kernel@vger.kernel.org, qperret@google.com,
valentin.schneider@arm.com, qais.yousef@arm.com,
ktkhai@virtuozzo.com, peterz@infradead.org
Subject: [PATCH 4/7] sched: Optimize pick_next_task()
Date: Fri, 08 Nov 2019 14:15:57 +0100 [thread overview]
Message-ID: <20191108131909.603037345@infradead.org> (raw)
In-Reply-To: 20191108131553.027892369@infradead.org
Ever since we moved the sched_class defenitions into their own files,
the constant expression {fair,idle}_sched_class.pick_next_task() is
not in fact a compile time constant anymore and results in an indirect
call (barring LTO).
Fix that by exposing pick_next_task_{fair,idle}() directly, this gets
rid of the indirect call (and RETPOLINE) on the fast path.
Also remove the unlikely() from the idle case, it is in fact /the/ way
we select idle -- and that is a very common thing to do.
Performance for will-it-scale/sched_yield improves by 2% (as reported
by 0-day).
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
kernel/sched/core.c | 6 +++---
kernel/sched/fair.c | 2 +-
kernel/sched/idle.c | 2 +-
kernel/sched/sched.h | 3 +++
4 files changed, 8 insertions(+), 5 deletions(-)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3917,14 +3917,14 @@ pick_next_task(struct rq *rq, struct tas
prev->sched_class == &fair_sched_class) &&
rq->nr_running == rq->cfs.h_nr_running)) {
- p = fair_sched_class.pick_next_task(rq, prev, rf);
+ p = pick_next_task_fair(rq, prev, rf);
if (unlikely(p == RETRY_TASK))
goto restart;
/* Assumes fair_sched_class->next == idle_sched_class */
- if (unlikely(!p)) {
+ if (!p) {
put_prev_task(rq, prev);
- p = idle_sched_class.pick_next_task(rq, NULL, NULL);
+ p = pick_next_task_idle(rq, NULL, NULL);
}
return p;
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6599,7 +6599,7 @@ static void check_preempt_wakeup(struct
set_last_buddy(se);
}
-static struct task_struct *
+struct task_struct *
pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct cfs_rq *cfs_rq = &rq->cfs;
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -391,7 +391,7 @@ static void set_next_task_idle(struct rq
schedstat_inc(rq->sched_goidle);
}
-static struct task_struct *
+struct task_struct *
pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
struct task_struct *next = rq->idle;
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1821,6 +1821,9 @@ static inline bool sched_fair_runnable(s
return rq->cfs.nr_running > 0;
}
+extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
+extern struct task_struct *pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
+
#ifdef CONFIG_SMP
extern void update_group_capacity(struct sched_domain *sd, int cpu);
next prev parent reply other threads:[~2019-11-08 13:21 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-08 13:15 [PATCH 0/7] scheduler patches Peter Zijlstra
2019-11-08 13:15 ` [PATCH 1/7] sched: Fix pick_next_task() vs change pattern race Peter Zijlstra
2019-11-08 14:28 ` Quentin Perret
2019-11-08 16:05 ` Valentin Schneider
2019-11-08 20:49 ` Peter Zijlstra
2019-11-08 17:03 ` Qais Yousef
2019-11-08 13:15 ` [PATCH 2/7] sched/fair: Better document newidle_balance() Peter Zijlstra
2019-11-11 9:32 ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2019-11-08 13:15 ` [PATCH 3/7] sched: Make pick_next_task_idle() more consistent Peter Zijlstra
2019-11-11 9:32 ` [tip: sched/core] sched/core: " tip-bot2 for Peter Zijlstra
2019-11-08 13:15 ` Peter Zijlstra [this message]
2019-11-08 14:33 ` [PATCH 4/7] sched: Optimize pick_next_task() Quentin Perret
2019-11-08 16:46 ` Vincent Guittot
2019-11-08 20:46 ` Peter Zijlstra
2019-11-11 9:32 ` [tip: sched/core] sched/core: " tip-bot2 for Peter Zijlstra
2019-11-08 13:15 ` [PATCH 5/7] sched: Simplify sched_class::pick_next_task() Peter Zijlstra
2019-11-11 9:32 ` [tip: sched/core] sched/core: " tip-bot2 for Peter Zijlstra
2019-11-08 13:15 ` [PATCH 6/7] sched/fair: Use mul_u32_u32() Peter Zijlstra
2019-11-11 9:32 ` [tip: sched/core] " tip-bot2 for Peter Zijlstra
2019-11-08 13:16 ` [PATCH 7/7] sched: Further clarify sched_class::set_next_task() Peter Zijlstra
2019-11-11 9:32 ` [tip: sched/core] sched/core: " tip-bot2 for Peter Zijlstra
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=20191108131909.603037345@infradead.org \
--to=peterz@infradead.org \
--cc=bsegall@google.com \
--cc=dietmar.eggemann@arm.com \
--cc=juri.lelli@redhat.com \
--cc=ktkhai@virtuozzo.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@suse.de \
--cc=mingo@kernel.org \
--cc=qais.yousef@arm.com \
--cc=qperret@google.com \
--cc=rostedt@goodmis.org \
--cc=valentin.schneider@arm.com \
--cc=vincent.guittot@linaro.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;
as well as URLs for NNTP newsgroup(s).