From: Mike Galbraith <efault@gmx.de>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Dhaval Giani <dhaval@linux.vnet.ibm.com>,
Greg Smith <gsmith@gregsmith.com>,
lkml <linux-kernel@vger.kernel.org>, Ingo Molnar <mingo@elte.hu>,
Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Subject: Re: PostgreSQL pgbench performance regression in 2.6.23+
Date: Thu, 22 May 2008 15:16:49 +0200 [thread overview]
Message-ID: <1211462209.5182.1.camel@marge.simson.net> (raw)
In-Reply-To: <1211459081.29104.40.camel@twins>
On Thu, 2008-05-22 at 14:24 +0200, Peter Zijlstra wrote:
> On Thu, 2008-05-22 at 14:09 +0200, Mike Galbraith wrote:
> > On Thu, 2008-05-22 at 13:44 +0200, Peter Zijlstra wrote:
> >
> > > Humm,.. how to fix this.. we'd need to somehow detect the 1:n nature of
> > > its operation - I'm sure there are other scenarios that could benefit
> > > from this.
> >
> > Maybe simple (minded): cache waker's last non-interrupt context wakee,
> > if the wakee != cached, ignore SYNC_WAKEUP unless sync was requested at
> > call time?
>
> Yeah, something like so - or perhaps like you say cache the wakee.
>
> I picked the wake_affine() condition, because I think that is the
> biggest factor in this behaviour. You could of course also disable all
> of sync.
Works fine (modulo booboo).
-Mike
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index c86c5c5..856c2a8 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -950,6 +950,8 @@ struct sched_entity {
> u64 last_wakeup;
> u64 avg_overlap;
>
> + struct sched_entity *waker;
> +
> #ifdef CONFIG_SCHEDSTATS
> u64 wait_start;
> u64 wait_max;
> diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
> index 894a702..8971044 100644
> --- a/kernel/sched_fair.c
> +++ b/kernel/sched_fair.c
> @@ -1036,7 +1036,8 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
> * a reasonable amount of time then attract this newly
> * woken task:
> */
> - if (sync && curr->sched_class == &fair_sched_class) {
> + if (sync && curr->sched_class == &fair_sched_class &&
> + p->se.waker == curr->se->waker) {
> if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
> p->se.avg_overlap < sysctl_sched_migration_cost)
> return 1;
> @@ -1210,6 +1211,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p)
> if (unlikely(se == pse))
> return;
>
> + se->waker = pse;
> cfs_rq_of(pse)->next = pse;
>
> /*
>
>
next prev parent reply other threads:[~2008-05-22 13:17 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-05-21 17:34 PostgreSQL pgbench performance regression in 2.6.23+ Greg Smith
2008-05-22 7:10 ` Mike Galbraith
2008-05-22 8:28 ` Dhaval Giani
2008-05-22 9:05 ` Mike Galbraith
2008-05-22 10:34 ` Mike Galbraith
2008-05-22 11:25 ` Mike Galbraith
2008-05-22 11:44 ` Peter Zijlstra
2008-05-22 12:09 ` Mike Galbraith
2008-05-22 12:24 ` Peter Zijlstra
2008-05-22 13:16 ` Mike Galbraith [this message]
2008-05-23 7:13 ` Greg Smith
2008-05-23 10:00 ` Mike Galbraith
2008-05-23 10:10 ` Ingo Molnar
2008-05-23 10:15 ` Mike Galbraith
2008-05-23 23:18 ` Greg Smith
2008-05-23 23:46 ` Mike Galbraith
2008-05-24 8:08 ` Mike Galbraith
2008-05-27 0:28 ` Greg Smith
2008-05-27 5:59 ` [patch] " Mike Galbraith
2008-05-27 8:20 ` Mike Galbraith
2008-05-27 8:35 ` Mike Galbraith
2008-06-06 5:03 ` Greg Smith
2008-06-06 6:13 ` Mike Galbraith
2008-06-07 11:38 ` Mike Galbraith
2008-06-07 12:50 ` Mike Galbraith
2008-06-07 13:07 ` Peter Zijlstra
2008-06-07 14:16 ` Mike Galbraith
2008-06-07 16:16 ` Peter Zijlstra
2008-06-07 17:56 ` Mike Galbraith
2008-06-07 13:08 ` Peter Zijlstra
2008-06-07 14:54 ` [patch part 2] " Mike Galbraith
2008-06-07 16:12 ` Peter Zijlstra
2008-06-07 17:53 ` Mike Galbraith
2008-06-07 18:19 ` Mike Galbraith
2008-05-23 13:05 ` Mike Galbraith
2008-05-23 13:35 ` Mike Galbraith
-- strict thread matches above, loose matches on Subject: below --
2008-05-23 11:26 Anton Petrusevich
2008-05-23 18:46 ` Greg Smith
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=1211462209.5182.1.camel@marge.simson.net \
--to=efault@gmx.de \
--cc=dhaval@linux.vnet.ibm.com \
--cc=gsmith@gregsmith.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=peterz@infradead.org \
--cc=vatsa@linux.vnet.ibm.com \
/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