From: Peter Zijlstra <peterz@infradead.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>, Borislav Petkov <bp@alien8.de>,
Nikolay Ulyanitsky <lystor@gmail.com>,
Mike Galbraith <efault@gmx.de>,
linux-kernel@vger.kernel.org,
Andreas Herrmann <andreas.herrmann3@amd.com>,
Andrew Morton <akpm@linux-foundation.org>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@kernel.org>,
Suresh Siddha <suresh.b.siddha@intel.com>
Subject: Re: 20% performance drop on PostgreSQL 9.2 from kernel 3.5.3 to 3.6-rc5 on AMD chipsets - bisected
Date: Mon, 24 Sep 2012 19:44:17 +0200 [thread overview]
Message-ID: <1348508657.11847.114.camel@twins> (raw)
In-Reply-To: <1348505683.11847.111.camel@twins>
On Mon, 2012-09-24 at 18:54 +0200, Peter Zijlstra wrote:
> But let me try and come up with the list thing, I think we've
> actually got that someplace as well.
OK, I'm sure the below can be written better, but my brain is gone for
the day...
---
include/linux/sched.h | 1 +
kernel/sched/core.c | 1 +
kernel/sched/fair.c | 102 +++++++++++++++++++++++++++++++++++---------------
3 files changed, 73 insertions(+), 31 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 0beac68..d72ea68 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -888,6 +888,7 @@ struct sched_group {
atomic_t ref;
unsigned int group_weight;
+ int group_first;
struct sched_group_power *sgp;
/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b38f00e..1177eb1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5781,6 +5781,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
do {
sg->group_weight = cpumask_weight(sched_group_cpus(sg));
+ sg->group_first = cpumask_first(sched_group_cpus(sg));
sg = sg->next;
} while (sg != sd->groups);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 6b800a1..601bc38 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2634,50 +2634,90 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
*/
static int select_idle_sibling(struct task_struct *p, int target)
{
- int cpu = smp_processor_id();
- int prev_cpu = task_cpu(p);
- struct sched_domain *sd;
- struct sched_group *sg;
- int i;
+ struct sched_domain *sd_smt, *sd_llc;
+ struct sched_group *sg_smt, *sg_llc;
/*
- * If the task is going to be woken-up on this cpu and if it is
- * already idle, then it is the right target.
+ * Of the target is idle, easy peasy, we're done.
*/
- if (target == cpu && idle_cpu(cpu))
- return cpu;
+ if (idle_cpu(target))
+ return target;
/*
- * If the task is going to be woken-up on the cpu where it previously
- * ran and if it is currently idle, then it the right target.
+ * Otherwise, see if there's an idle core in the cache domain.
*/
- if (target == prev_cpu && idle_cpu(prev_cpu))
- return prev_cpu;
+ sd_llc = rcu_dereference(per_cpu(sd_llc, target));
+ sg_llc = sd_llc->groups;
+ do {
+ int candidate = -1;
+
+ sd_smt = rcu_dereference(per_cpu(sd_llc, sg_llc->group_first));
+ for_each_lower_domain(sd_smt) {
+ if (sd_smt->flags & SD_SHARE_CPUPOWER) /* aka. SMT */
+ break;
+ }
+
+ if (!sd_smt) {
+ int cpu = sg_llc->group_first; /* Assume singleton group */
+
+ if (!idle_cpu(cpu))
+ goto next_llc;
+
+ if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
+ goto next_llc;
+
+ return cpu;
+ }
+
+ sg_smt = sd_smt->groups;
+ do {
+ int cpu = sg_smt->group_first; /* Assume singleton group */
+
+ if (!idle_cpu(cpu)) /* core is not idle, skip to next core */
+ goto next_llc;
+
+ if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(p)))
+ goto next_smt;
+
+ if (candidate < 0)
+ candidate = cpu;
+
+next_smt:
+ sg_smt = sg_smt->next;
+ } while (sg_smt != sd_smt->groups);
+
+ if (candidate >= 0)
+ return candidate;
+
+next_llc:
+ sg_llc = sg_llc->next;
+ } while (sg_llc != sd_llc->groups);
/*
- * Otherwise, iterate the domains and find an elegible idle cpu.
+ * Failing that, see if there's an idle SMT sibling.
*/
- sd = rcu_dereference(per_cpu(sd_llc, target));
- for_each_lower_domain(sd) {
- sg = sd->groups;
+ sd_smt = rcu_dereference(per_cpu(sd_llc, target));
+ for_each_lower_domain(sd_smt) {
+ if (sd_smt->flags & SD_SHARE_CPUPOWER) /* aka. SMT */
+ break;
+ }
+
+ if (sd_smt) {
+ sg_smt = sd_smt->groups;
do {
- if (!cpumask_intersects(sched_group_cpus(sg),
- tsk_cpus_allowed(p)))
- goto next;
+ int cpu = sg_smt->group_first; /* Assume singleton group */
- for_each_cpu(i, sched_group_cpus(sg)) {
- if (!idle_cpu(i))
- goto next;
- }
+ if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p)) &&
+ idle_cpu(cpu))
+ return cpu;
- target = cpumask_first_and(sched_group_cpus(sg),
- tsk_cpus_allowed(p));
- goto done;
-next:
- sg = sg->next;
- } while (sg != sd->groups);
+ sg_smt = sg_smt->next;
+ } while (sg_smt != sd_smt->groups);
}
-done:
+
+ /*
+ * OK, no idle siblings of any kind, take what we started with.
+ */
return target;
}
next prev parent reply other threads:[~2012-09-24 17:45 UTC|newest]
Thread overview: 115+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-09-14 7:47 20% performance drop on PostgreSQL 9.2 from kernel 3.5.3 to 3.6-rc5 on AMD chipsets Nikolay Ulyanitsky
2012-09-14 18:40 ` Borislav Petkov
2012-09-14 18:51 ` Borislav Petkov
2012-09-14 21:27 ` 20% performance drop on PostgreSQL 9.2 from kernel 3.5.3 to 3.6-rc5 on AMD chipsets - bisected Borislav Petkov
2012-09-14 21:40 ` Peter Zijlstra
2012-09-14 21:44 ` Linus Torvalds
2012-09-14 21:56 ` Peter Zijlstra
2012-09-14 21:59 ` Peter Zijlstra
2012-09-15 3:57 ` Mike Galbraith
2012-09-14 22:01 ` Linus Torvalds
2012-09-14 22:10 ` Peter Zijlstra
2012-09-14 22:20 ` Linus Torvalds
2012-09-14 22:14 ` Borislav Petkov
2012-09-14 21:45 ` Borislav Petkov
2012-09-14 21:42 ` Linus Torvalds
2012-09-15 3:33 ` Mike Galbraith
2012-09-15 16:16 ` Andi Kleen
2012-09-15 16:36 ` Mike Galbraith
2012-09-15 17:08 ` richard -rw- weinberger
2012-09-16 4:48 ` Mike Galbraith
2012-09-15 21:32 ` Alan Cox
2012-09-16 4:35 ` Mike Galbraith
2012-09-16 19:57 ` Linus Torvalds
2012-09-17 8:08 ` Mike Galbraith
2012-09-17 10:07 ` Ingo Molnar
2012-09-17 10:47 ` Mike Galbraith
2012-09-17 14:39 ` Andi Kleen
2012-09-19 12:35 ` Mike Galbraith
2012-09-19 14:54 ` Ingo Molnar
2012-09-19 15:23 ` Mike Galbraith
2012-09-24 15:00 ` Mel Gorman
2012-09-24 15:23 ` Nikolay Ulyanitsky
2012-09-24 15:53 ` Borislav Petkov
2012-09-24 15:30 ` Peter Zijlstra
2012-09-24 15:51 ` Mike Galbraith
2012-09-24 15:52 ` Linus Torvalds
2012-09-24 16:07 ` Peter Zijlstra
2012-09-24 16:33 ` Linus Torvalds
2012-09-24 16:54 ` Peter Zijlstra
2012-09-25 12:10 ` Hillf Danton
2012-09-24 16:12 ` Peter Zijlstra
2012-09-24 16:30 ` Linus Torvalds
2012-09-24 16:52 ` Borislav Petkov
2012-09-24 16:54 ` Peter Zijlstra
2012-09-24 17:44 ` Peter Zijlstra [this message]
2012-09-25 13:23 ` Mel Gorman
2012-09-25 14:36 ` Peter Zijlstra
2012-09-24 18:26 ` Mike Galbraith
2012-09-24 19:12 ` Linus Torvalds
2012-09-24 19:20 ` Borislav Petkov
2012-09-25 1:57 ` Mike Galbraith
2012-09-25 2:11 ` Linus Torvalds
2012-09-25 2:49 ` Mike Galbraith
2012-09-25 3:10 ` Linus Torvalds
2012-09-25 3:20 ` Mike Galbraith
2012-09-25 3:32 ` Linus Torvalds
2012-09-25 3:43 ` Mike Galbraith
2012-09-25 11:58 ` Peter Zijlstra
2012-09-25 13:17 ` Borislav Petkov
2012-09-25 17:00 ` Borislav Petkov
2012-09-25 17:21 ` Linus Torvalds
2012-09-25 18:42 ` Borislav Petkov
2012-09-25 19:08 ` Linus Torvalds
2012-09-26 2:23 ` Mike Galbraith
2012-09-26 17:17 ` Borislav Petkov
2012-09-26 2:00 ` Mike Galbraith
2012-09-26 2:22 ` Linus Torvalds
2012-09-26 2:42 ` Mike Galbraith
2012-09-26 17:15 ` Borislav Petkov
2012-09-26 16:32 ` Borislav Petkov
2012-09-26 18:19 ` Linus Torvalds
2012-09-26 21:37 ` Borislav Petkov
2012-09-27 5:09 ` Mike Galbraith
2012-09-27 5:18 ` Borislav Petkov
2012-09-27 5:44 ` Mike Galbraith
2012-09-27 5:47 ` Ingo Molnar
2012-09-27 5:59 ` Ingo Molnar
2012-09-27 6:34 ` Mike Galbraith
2012-09-27 6:41 ` Ingo Molnar
2012-09-27 6:54 ` Mike Galbraith
2012-09-27 7:10 ` Ingo Molnar
2012-09-27 16:25 ` Borislav Petkov
2012-09-27 17:44 ` Linus Torvalds
2012-09-27 18:05 ` Borislav Petkov
2012-09-27 18:19 ` Linus Torvalds
2012-09-27 18:29 ` Peter Zijlstra
2012-09-27 19:24 ` Borislav Petkov
2012-09-28 3:50 ` Mike Galbraith
2012-09-28 12:30 ` Borislav Petkov
2012-09-27 19:40 ` Linus Torvalds
2012-09-28 4:13 ` Mike Galbraith
2012-09-28 8:37 ` Peter Zijlstra
2012-09-27 7:17 ` david
2012-09-27 7:55 ` Mike Galbraith
2012-09-27 10:20 ` Borislav Petkov
2012-09-27 13:38 ` Mike Galbraith
2012-09-27 16:55 ` david
2012-09-27 4:32 ` Mike Galbraith
2012-09-27 8:21 ` Peter Zijlstra
2012-09-27 16:48 ` david
2012-09-27 17:38 ` Peter Zijlstra
2012-09-27 17:45 ` david
2012-09-27 18:09 ` Peter Zijlstra
2012-09-27 18:15 ` Linus Torvalds
2012-09-27 18:24 ` Borislav Petkov
2012-09-25 1:39 ` Mike Galbraith
2012-09-25 21:11 ` Suresh Siddha
2012-09-25 4:16 ` Mike Galbraith
2012-09-15 4:11 ` Mike Galbraith
[not found] ` <CA+55aFz1A7HbMYS9o-GTS5Zm=Xx8MUD7cR05GMVo--2E34jcgQ@mail.gmail.com>
2012-09-15 4:42 ` Mike Galbraith
2012-09-15 10:44 ` Borislav Petkov
2012-09-15 14:47 ` Mike Galbraith
2012-09-15 15:18 ` Borislav Petkov
2012-09-15 16:13 ` Mike Galbraith
2012-09-15 19:44 ` Borislav Petkov
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=1348508657.11847.114.camel@twins \
--to=peterz@infradead.org \
--cc=akpm@linux-foundation.org \
--cc=andreas.herrmann3@amd.com \
--cc=bp@alien8.de \
--cc=efault@gmx.de \
--cc=linux-kernel@vger.kernel.org \
--cc=lystor@gmail.com \
--cc=mgorman@suse.de \
--cc=mingo@kernel.org \
--cc=suresh.b.siddha@intel.com \
--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).