From: Mel Gorman <mgorman@techsingularity.net>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Jirka Hladky <jhladky@redhat.com>, Ingo Molnar <mingo@kernel.org>,
Vincent Guittot <vincent.guittot@linaro.org>,
valentin.schneider@arm.com, Hillf Danton <hdanton@sina.com>,
Rik van Riel <riel@surriel.com>,
LKML <linux-kernel@vger.kernel.org>,
Mel Gorman <mgorman@techsingularity.net>
Subject: [PATCH 1/2] sched: Optimize ttwu() spinning on p->on_cpu
Date: Sun, 24 May 2020 21:29:55 +0100 [thread overview]
Message-ID: <20200524202956.27665-2-mgorman@techsingularity.net> (raw)
In-Reply-To: <20200524202956.27665-1-mgorman@techsingularity.net>
From: Peter Zijlstra <peterz@infradead.org>
Both Rik and Mel reported seeing ttwu() spend significant time on:
smp_cond_load_acquire(&p->on_cpu, !VAL);
Attempt to avoid this by queueing the wakeup on the CPU that owns the
p->on_cpu value. This will then allow the ttwu() to complete without
further waiting.
Since we run schedule() with interrupts disabled, the IPI is
guaranteed to happen after p->on_cpu is cleared, this is what makes it
safe to queue early.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
---
kernel/sched/core.c | 52 +++++++++++++++++++++++++++------------------
1 file changed, 31 insertions(+), 21 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9a2fbf98fd6f..987b8ecf2ee9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2330,7 +2330,7 @@ void scheduler_ipi(void)
irq_exit();
}
-static void ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags)
+static void __ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags)
{
struct rq *rq = cpu_rq(cpu);
@@ -2372,6 +2372,17 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
{
return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
}
+
+static bool ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags)
+{
+ if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
+ sched_clock_cpu(cpu); /* Sync clocks across CPUs */
+ __ttwu_queue_remote(p, cpu, wake_flags);
+ return true;
+ }
+
+ return false;
+}
#endif /* CONFIG_SMP */
static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
@@ -2380,11 +2391,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
struct rq_flags rf;
#if defined(CONFIG_SMP)
- if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
- sched_clock_cpu(cpu); /* Sync clocks across CPUs */
- ttwu_queue_remote(p, cpu, wake_flags);
+ if (ttwu_queue_remote(p, cpu, wake_flags))
return;
- }
#endif
rq_lock(rq, &rf);
@@ -2566,7 +2574,15 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
if (p->on_rq && ttwu_remote(p, wake_flags))
goto unlock;
+ if (p->in_iowait) {
+ delayacct_blkio_end(p);
+ atomic_dec(&task_rq(p)->nr_iowait);
+ }
+
#ifdef CONFIG_SMP
+ p->sched_contributes_to_load = !!task_contributes_to_load(p);
+ p->state = TASK_WAKING;
+
/*
* Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
* possible to, falsely, observe p->on_cpu == 0.
@@ -2588,6 +2604,16 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
*/
smp_rmb();
+ /*
+ * If the owning (remote) CPU is still in the middle of schedule() with
+ * this task as prev, considering queueing p on the remote CPUs wake_list
+ * which potentially sends an IPI instead of spinning on p->on_cpu to
+ * let the waker make forward progress. This is safe because IRQs are
+ * disabled and the IPI will deliver after on_cpu is cleared.
+ */
+ if (READ_ONCE(p->on_cpu) && ttwu_queue_remote(p, cpu, wake_flags))
+ goto unlock;
+
/*
* If the owning (remote) CPU is still in the middle of schedule() with
* this task as prev, wait until its done referencing the task.
@@ -2599,28 +2625,12 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
*/
smp_cond_load_acquire(&p->on_cpu, !VAL);
- p->sched_contributes_to_load = !!task_contributes_to_load(p);
- p->state = TASK_WAKING;
-
- if (p->in_iowait) {
- delayacct_blkio_end(p);
- atomic_dec(&task_rq(p)->nr_iowait);
- }
-
cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
if (task_cpu(p) != cpu) {
wake_flags |= WF_MIGRATED;
psi_ttwu_dequeue(p);
set_task_cpu(p, cpu);
}
-
-#else /* CONFIG_SMP */
-
- if (p->in_iowait) {
- delayacct_blkio_end(p);
- atomic_dec(&task_rq(p)->nr_iowait);
- }
-
#endif /* CONFIG_SMP */
ttwu_queue(p, cpu, wake_flags);
--
2.26.1
next prev parent reply other threads:[~2020-05-24 20:30 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-24 20:29 [PATCH 0/2] Optimise try_to_wake_up() when wakee is descheduling Mel Gorman
2020-05-24 20:29 ` Mel Gorman [this message]
2020-05-25 5:26 ` [tip: sched/core] sched/core: Optimize ttwu() spinning on p->on_cpu tip-bot2 for Peter Zijlstra
2020-05-24 20:29 ` [PATCH 2/2] sched: Offload wakee task activation if it the wakee is descheduling Mel Gorman
2020-05-25 5:26 ` [tip: sched/core] sched/core: " tip-bot2 for Mel Gorman
2020-05-27 10:10 ` [PATCH 2/2] sched: " Pavan Kondeti
2020-05-25 5:26 ` [PATCH 0/2] Optimise try_to_wake_up() when " Ingo Molnar
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=20200524202956.27665-2-mgorman@techsingularity.net \
--to=mgorman@techsingularity.net \
--cc=hdanton@sina.com \
--cc=jhladky@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=riel@surriel.com \
--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).