From: tip-bot for Peter Zijlstra <a.p.zijlstra@chello.nl>
To: linux-tip-commits@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, hpa@zytor.com, mingo@redhat.com,
torvalds@linux-foundation.org, a.p.zijlstra@chello.nl,
efault@gmx.de, npiggin@kernel.dk, akpm@linux-foundation.org,
tglx@linutronix.de, frank.rowand@am.sony.com, mingo@elte.hu
Subject: [tip:sched/locking] sched: Move the second half of ttwu() to the remote cpu
Date: Thu, 14 Apr 2011 08:39:51 GMT [thread overview]
Message-ID: <tip-317f394160e9beb97d19a84c39b7e5eb3d7815a8@git.kernel.org> (raw)
In-Reply-To: <20110405152729.515897185@chello.nl>
Commit-ID: 317f394160e9beb97d19a84c39b7e5eb3d7815a8
Gitweb: http://git.kernel.org/tip/317f394160e9beb97d19a84c39b7e5eb3d7815a8
Author: Peter Zijlstra <a.p.zijlstra@chello.nl>
AuthorDate: Tue, 5 Apr 2011 17:23:58 +0200
Committer: Ingo Molnar <mingo@elte.hu>
CommitDate: Thu, 14 Apr 2011 08:52:41 +0200
sched: Move the second half of ttwu() to the remote cpu
Now that we've removed the rq->lock requirement from the first part of
ttwu() and can compute placement without holding any rq->lock, ensure
we execute the second half of ttwu() on the actual cpu we want the
task to run on.
This avoids having to take rq->lock and doing the task enqueue
remotely, saving lots on cacheline transfers.
As measured using: http://oss.oracle.com/~mason/sembench.c
$ for i in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor ; do echo performance > $i; done
$ echo 4096 32000 64 128 > /proc/sys/kernel/sem
$ ./sembench -t 2048 -w 1900 -o 0
unpatched: run time 30 seconds 647278 worker burns per second
patched: run time 30 seconds 816715 worker burns per second
Reviewed-by: Frank Rowand <frank.rowand@am.sony.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Nick Piggin <npiggin@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110405152729.515897185@chello.nl
---
include/linux/sched.h | 3 +-
init/Kconfig | 5 ++++
kernel/sched.c | 56 +++++++++++++++++++++++++++++++++++++++++++++++
kernel/sched_features.h | 6 +++++
4 files changed, 69 insertions(+), 1 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 25c5031..e09dafa 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1203,6 +1203,7 @@ struct task_struct {
int lock_depth; /* BKL lock depth */
#ifdef CONFIG_SMP
+ struct task_struct *wake_entry;
int on_cpu;
#endif
int on_rq;
@@ -2192,7 +2193,7 @@ extern void set_task_comm(struct task_struct *tsk, char *from);
extern char *get_task_comm(char *to, struct task_struct *tsk);
#ifdef CONFIG_SMP
-static inline void scheduler_ipi(void) { }
+void scheduler_ipi(void);
extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
#else
static inline void scheduler_ipi(void) { }
diff --git a/init/Kconfig b/init/Kconfig
index 56240e7..32745bf 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -827,6 +827,11 @@ config SCHED_AUTOGROUP
desktop applications. Task group autogeneration is currently based
upon task session.
+config SCHED_TTWU_QUEUE
+ bool
+ depends on !SPARC32
+ default y
+
config MM_OWNER
bool
diff --git a/kernel/sched.c b/kernel/sched.c
index 7d8b85f..9e3ede1 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -556,6 +556,10 @@ struct rq {
unsigned int ttwu_count;
unsigned int ttwu_local;
#endif
+
+#ifdef CONFIG_SMP
+ struct task_struct *wake_list;
+#endif
};
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
@@ -2516,10 +2520,61 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
return ret;
}
+#ifdef CONFIG_SMP
+static void sched_ttwu_pending(void)
+{
+ struct rq *rq = this_rq();
+ struct task_struct *list = xchg(&rq->wake_list, NULL);
+
+ if (!list)
+ return;
+
+ raw_spin_lock(&rq->lock);
+
+ while (list) {
+ struct task_struct *p = list;
+ list = list->wake_entry;
+ ttwu_do_activate(rq, p, 0);
+ }
+
+ raw_spin_unlock(&rq->lock);
+}
+
+void scheduler_ipi(void)
+{
+ sched_ttwu_pending();
+}
+
+static void ttwu_queue_remote(struct task_struct *p, int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ struct task_struct *next = rq->wake_list;
+
+ for (;;) {
+ struct task_struct *old = next;
+
+ p->wake_entry = next;
+ next = cmpxchg(&rq->wake_list, old, p);
+ if (next == old)
+ break;
+ }
+
+ if (!next)
+ smp_send_reschedule(cpu);
+}
+#endif
+
static void ttwu_queue(struct task_struct *p, int cpu)
{
struct rq *rq = cpu_rq(cpu);
+#if defined(CONFIG_SMP) && defined(CONFIG_SCHED_TTWU_QUEUE)
+ if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) {
+ ttwu_queue_remote(p, cpu);
+ return;
+ }
+#endif
+
raw_spin_lock(&rq->lock);
ttwu_do_activate(rq, p, 0);
raw_spin_unlock(&rq->lock);
@@ -6331,6 +6386,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
#ifdef CONFIG_HOTPLUG_CPU
case CPU_DYING:
+ sched_ttwu_pending();
/* Update our root-domain */
raw_spin_lock_irqsave(&rq->lock, flags);
if (rq->rd) {
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 68e69ac..be40f73 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -64,3 +64,9 @@ SCHED_FEAT(OWNER_SPIN, 1)
* Decrement CPU power based on irq activity
*/
SCHED_FEAT(NONIRQ_POWER, 1)
+
+/*
+ * Queue remote wakeups on the target CPU and process them
+ * using the scheduler IPI. Reduces rq->lock contention/bounces.
+ */
+SCHED_FEAT(TTWU_QUEUE, 1)
next prev parent reply other threads:[~2011-04-14 8:40 UTC|newest]
Thread overview: 152+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-04-05 15:23 [PATCH 00/21] sched: Reduce runqueue lock contention -v6 Peter Zijlstra
2011-04-05 15:23 ` [PATCH 01/21] sched: Provide scheduler_ipi() callback in response to smp_send_reschedule() Peter Zijlstra
2011-04-13 21:15 ` Tony Luck
2011-04-13 21:38 ` Peter Zijlstra
2011-04-14 8:31 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 02/21] sched: Always provide p->on_cpu Peter Zijlstra
2011-04-14 8:31 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 03/21] mutex: Use p->on_cpu for the adaptive spin Peter Zijlstra
2011-04-14 8:32 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 04/21] sched: Change the ttwu success details Peter Zijlstra
2011-04-13 9:23 ` Peter Zijlstra
2011-04-13 10:48 ` Peter Zijlstra
2011-04-13 11:06 ` Peter Zijlstra
2011-04-13 18:39 ` Tejun Heo
2011-04-13 19:11 ` Peter Zijlstra
2011-04-14 8:32 ` [tip:sched/locking] sched: Change the ttwu() " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 05/21] sched: Clean up ttwu stats Peter Zijlstra
2011-04-14 8:33 ` [tip:sched/locking] sched: Clean up ttwu() stats tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 06/21] sched: Provide p->on_rq Peter Zijlstra
2011-04-14 8:33 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 07/21] sched: Serialize p->cpus_allowed and ttwu() using p->pi_lock Peter Zijlstra
2011-04-14 8:34 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 08/21] sched: Drop the rq argument to sched_class::select_task_rq() Peter Zijlstra
2011-04-14 8:34 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 09/21] sched: Remove rq argument to sched_class::task_waking() Peter Zijlstra
2011-04-14 8:35 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 10/21] sched: Deal with non-atomic min_vruntime reads on 32bits Peter Zijlstra
2011-04-14 8:35 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 11/21] sched: Delay task_contributes_to_load() Peter Zijlstra
2011-04-14 8:35 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 12/21] sched: Also serialize ttwu_local() with p->pi_lock Peter Zijlstra
2011-04-14 8:36 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 13/21] sched: Add p->pi_lock to task_rq_lock() Peter Zijlstra
2011-04-14 8:36 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-06-01 13:58 ` Arne Jansen
2011-06-01 16:35 ` Peter Zijlstra
2011-06-01 17:20 ` Arne Jansen
2011-06-01 18:09 ` Peter Zijlstra
2011-06-01 18:44 ` Peter Zijlstra
2011-06-01 19:30 ` Arne Jansen
2011-06-01 21:09 ` Linus Torvalds
2011-06-03 9:15 ` Peter Zijlstra
2011-06-03 10:02 ` Arne Jansen
2011-06-03 10:30 ` Peter Zijlstra
2011-06-03 11:52 ` Arne Jansen
2011-06-05 8:17 ` Ingo Molnar
2011-06-05 8:53 ` Arne Jansen
2011-06-05 9:41 ` Ingo Molnar
2011-06-05 9:45 ` Ingo Molnar
2011-06-05 9:43 ` Arne Jansen
2011-06-05 9:55 ` Ingo Molnar
2011-06-05 10:22 ` Arne Jansen
2011-06-05 11:01 ` Ingo Molnar
2011-06-05 11:19 ` [debug patch] printk: Add a printk killswitch to robustify NMI watchdog messages Ingo Molnar
2011-06-05 11:36 ` Ingo Molnar
2011-06-05 11:57 ` Arne Jansen
2011-06-05 13:39 ` Ingo Molnar
2011-06-05 13:54 ` Arne Jansen
2011-06-05 14:06 ` Ingo Molnar
2011-06-05 14:45 ` Arne Jansen
2011-06-05 14:10 ` Ingo Molnar
2011-06-05 14:31 ` Arne Jansen
2011-06-05 15:13 ` Ingo Molnar
2011-06-05 15:26 ` Ingo Molnar
2011-06-05 15:32 ` Ingo Molnar
2011-06-05 16:07 ` Arne Jansen
2011-06-05 16:35 ` Arne Jansen
2011-06-05 16:50 ` Arne Jansen
2011-06-05 17:20 ` Ingo Molnar
2011-06-05 17:42 ` Arne Jansen
2011-06-05 18:59 ` Ingo Molnar
2011-06-05 19:30 ` Arne Jansen
2011-06-05 19:44 ` Ingo Molnar
2011-06-05 20:15 ` Arne Jansen
2011-06-06 6:56 ` Arne Jansen
2011-06-06 9:01 ` Peter Zijlstra
2011-06-06 9:18 ` Arne Jansen
2011-06-06 9:24 ` Peter Zijlstra
2011-06-06 9:52 ` Peter Zijlstra
2011-06-06 10:00 ` Arne Jansen
2011-06-06 10:26 ` Peter Zijlstra
2011-06-06 13:25 ` Peter Zijlstra
2011-06-06 15:04 ` Ingo Molnar
2011-06-06 15:08 ` Ingo Molnar
2011-06-06 17:44 ` Mike Galbraith
2011-06-07 5:20 ` Mike Galbraith
2011-06-06 13:10 ` Ingo Molnar
2011-06-06 13:12 ` Peter Zijlstra
2011-06-06 13:21 ` Ingo Molnar
2011-06-06 13:31 ` Peter Zijlstra
2011-06-06 7:34 ` Arne Jansen
2011-06-05 15:34 ` Arne Jansen
2011-06-06 8:38 ` Peter Zijlstra
2011-06-06 14:58 ` Ingo Molnar
2011-06-06 15:09 ` Peter Zijlstra
2011-06-06 15:47 ` Peter Zijlstra
2011-06-06 15:52 ` Ingo Molnar
2011-06-06 16:00 ` Peter Zijlstra
2011-06-06 16:08 ` Ingo Molnar
2011-06-06 16:12 ` Peter Zijlstra
2011-06-06 16:17 ` Ingo Molnar
2011-06-06 16:38 ` Arne Jansen
2011-06-06 16:45 ` Arne Jansen
2011-06-06 16:53 ` Peter Zijlstra
2011-06-06 17:07 ` Ingo Molnar
2011-06-06 17:11 ` Peter Zijlstra
2011-06-08 15:50 ` Peter Zijlstra
2011-06-08 19:17 ` Ingo Molnar
2011-06-08 19:27 ` Linus Torvalds
2011-06-08 20:32 ` Peter Zijlstra
2011-06-08 20:53 ` Linus Torvalds
2011-06-08 20:54 ` Thomas Gleixner
2011-06-08 19:45 ` Peter Zijlstra
2011-06-08 20:52 ` Ingo Molnar
2011-06-08 21:49 ` Peter Zijlstra
2011-06-08 21:57 ` Thomas Gleixner
2011-06-06 16:44 ` Peter Zijlstra
2011-06-06 16:50 ` Peter Zijlstra
2011-06-06 17:13 ` Ingo Molnar
2011-06-06 17:04 ` Peter Zijlstra
2011-06-06 17:11 ` Ingo Molnar
2011-06-06 17:57 ` Arne Jansen
2011-06-06 18:07 ` Ingo Molnar
2011-06-06 18:14 ` Arne Jansen
2011-06-06 18:19 ` Peter Zijlstra
2011-06-06 22:08 ` Ingo Molnar
2011-06-03 12:44 ` [tip:sched/locking] sched: Add p->pi_lock to task_rq_lock() Linus Torvalds
2011-06-03 13:05 ` Arne Jansen
2011-06-04 21:29 ` Linus Torvalds
2011-06-04 22:08 ` Peter Zijlstra
2011-06-04 22:50 ` Linus Torvalds
2011-06-05 6:01 ` Arne Jansen
2011-06-05 7:57 ` Mike Galbraith
2011-04-05 15:23 ` [PATCH 14/21] sched: Drop rq->lock from first part of wake_up_new_task() Peter Zijlstra
2011-04-14 8:37 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 15/21] sched: Drop rq->lock from sched_exec() Peter Zijlstra
2011-04-14 8:37 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 16/21] sched: Remove rq->lock from the first half of ttwu() Peter Zijlstra
2011-04-14 8:38 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 17/21] sched: Remove rq argument from ttwu_stat() Peter Zijlstra
2011-04-14 8:38 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 18/21] sched: Rename ttwu_post_activation Peter Zijlstra
2011-04-14 8:39 ` [tip:sched/locking] sched: Rename ttwu_post_activation() to ttwu_do_wakeup() tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 19/21] sched: Restructure ttwu some more Peter Zijlstra
2011-04-14 8:39 ` [tip:sched/locking] sched: Restructure ttwu() " tip-bot for Peter Zijlstra
2011-04-05 15:23 ` [PATCH 20/21] sched: Move the second half of ttwu() to the remote cpu Peter Zijlstra
2011-04-14 8:39 ` tip-bot for Peter Zijlstra [this message]
2011-04-05 15:23 ` [PATCH 21/21] sched: Remove need_migrate_task() Peter Zijlstra
2011-04-14 8:40 ` [tip:sched/locking] " tip-bot for Peter Zijlstra
2011-04-05 15:59 ` [PATCH 00/21] sched: Reduce runqueue lock contention -v6 Peter Zijlstra
2011-04-06 11:00 ` Peter Zijlstra
2011-04-27 16:54 ` Dave Kleikamp
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=tip-317f394160e9beb97d19a84c39b7e5eb3d7815a8@git.kernel.org \
--to=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=efault@gmx.de \
--cc=frank.rowand@am.sony.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=mingo@redhat.com \
--cc=npiggin@kernel.dk \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.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).