From: Ingo Molnar <mingo@elte.hu>
To: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>,
linux-kernel@vger.kernel.org,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Dhaval Giani <dhaval@linux.vnet.ibm.com>,
Dmitry Adamushko <dmitry.adamushko@gmail.com>,
Andrew Morton <akpm@linux-foundation.org>
Subject: Re: [git] CFS-devel, latest code
Date: Tue, 25 Sep 2007 13:33:06 +0200 [thread overview]
Message-ID: <20070925113306.GA19166@elte.hu> (raw)
In-Reply-To: <20070925103617.GA3426@elte.hu>
* Ingo Molnar <mingo@elte.hu> wrote:
> hm. perhaps this fixup in kernel/sched.c:set_task_cpu():
>
> p->se.vruntime -= old_rq->cfs.min_vruntime - new_rq->cfs.min_vruntime;
>
> needs to become properly group-hierarchy aware?
a quick first stab like the one below does not appear to solve the
problem.
Ingo
------------------->
Subject: sched: group scheduler SMP migration fix
From: Ingo Molnar <mingo@elte.hu>
group scheduler SMP migration fix.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
kernel/sched.c | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
Index: linux/kernel/sched.c
===================================================================
--- linux.orig/kernel/sched.c
+++ linux/kernel/sched.c
@@ -1039,7 +1039,8 @@ void set_task_cpu(struct task_struct *p,
{
int old_cpu = task_cpu(p);
struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu);
- u64 clock_offset;
+ struct sched_entity *se;
+ u64 clock_offset, voffset;
clock_offset = old_rq->clock - new_rq->clock;
@@ -1051,7 +1052,11 @@ void set_task_cpu(struct task_struct *p,
if (p->se.block_start)
p->se.block_start -= clock_offset;
#endif
- p->se.vruntime -= old_rq->cfs.min_vruntime - new_rq->cfs.min_vruntime;
+
+ se = &p->se;
+ voffset = old_rq->cfs.min_vruntime - new_rq->cfs.min_vruntime;
+ for_each_sched_entity(se)
+ se->vruntime -= voffset;
__set_task_cpu(p, new_cpu);
}
next prev parent reply other threads:[~2007-09-25 11:34 UTC|newest]
Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-09-24 21:45 [git] CFS-devel, latest code Ingo Molnar
2007-09-24 21:55 ` Andrew Morton
2007-09-24 21:59 ` Ingo Molnar
2007-09-25 0:08 ` Daniel Walker
2007-09-25 6:45 ` Ingo Molnar
2007-09-25 15:17 ` Daniel Walker
2007-09-25 6:10 ` Mike Galbraith
2007-09-25 7:35 ` Mike Galbraith
2007-09-25 8:33 ` Mike Galbraith
2007-09-25 8:53 ` Srivatsa Vaddagiri
2007-09-25 9:11 ` Srivatsa Vaddagiri
2007-09-25 9:15 ` Mike Galbraith
2007-09-25 9:12 ` Mike Galbraith
2007-09-25 9:13 ` Ingo Molnar
2007-09-25 9:17 ` Mike Galbraith
2007-09-25 9:47 ` Ingo Molnar
2007-09-25 10:02 ` Mike Galbraith
2007-09-26 8:04 ` Mike Galbraith
2007-09-28 21:46 ` Bill Davidsen
2007-09-25 9:44 ` Srivatsa Vaddagiri
2007-09-25 9:40 ` Ingo Molnar
2007-09-25 10:10 ` Ingo Molnar
2007-09-25 10:28 ` Srivatsa Vaddagiri
2007-09-25 10:36 ` Ingo Molnar
2007-09-25 11:33 ` Ingo Molnar [this message]
2007-09-25 14:48 ` Srivatsa Vaddagiri
2007-09-25 12:51 ` Srivatsa Vaddagiri
2007-09-25 13:35 ` Mike Galbraith
2007-09-25 14:07 ` Srivatsa Vaddagiri
2007-09-25 12:28 ` Mike Galbraith
2007-09-25 12:54 ` Mike Galbraith
[not found] ` <20070925131717.GM26289@linux.vnet.ibm.com>
[not found] ` <1190725693.13716.10.camel@Homer.simpson.net>
[not found] ` <20070925132528.GN26289@linux.vnet.ibm.com>
[not found] ` <1190726682.11260.1.camel@Homer.simpson.net>
[not found] ` <20070925140559.GB26310@linux.vnet.ibm.com>
[not found] ` <20070925143755.GA15594@elte.hu>
[not found] ` <20070926210737.GA8663@elte.hu>
2007-10-01 14:04 ` [RFC/PATCH] Add sysfs control to modify a user's cpu share Dhaval Giani
2007-10-01 14:44 ` Ingo Molnar
2007-10-01 15:32 ` Srivatsa Vaddagiri
2007-10-02 22:12 ` Eric St-Laurent
2007-10-03 4:09 ` Srivatsa Vaddagiri
2007-10-03 17:10 ` [RFC/PATCH -v2] " Dhaval Giani
2007-10-04 7:57 ` Ingo Molnar
2007-10-04 8:54 ` Heiko Carstens
2007-10-04 16:02 ` Bill Davidsen
2007-10-04 17:20 ` Srivatsa Vaddagiri
2007-10-04 21:32 ` Valdis.Kletnieks
2007-10-05 7:01 ` Srivatsa Vaddagiri
2007-10-09 15:12 ` [PATCH sched-devel] Generate uevents for user creation/destruction Srivatsa Vaddagiri
2007-10-10 7:42 ` Ingo Molnar
2007-10-01 16:12 ` [RFC/PATCH] Add sysfs control to modify a user's cpu share Dave Jones
2007-10-01 16:37 ` Srivatsa Vaddagiri
2007-09-25 6:50 ` [git] CFS-devel, latest code S.Çağlar Onur
2007-09-25 9:17 ` Ingo Molnar
2007-09-25 7:41 ` Andrew Morton
2007-09-25 8:43 ` Srivatsa Vaddagiri
2007-09-25 8:48 ` Andrew Morton
2007-09-25 11:00 ` Ingo Molnar
-- strict thread matches above, loose matches on Subject: below --
2007-09-25 14:44 Ingo Molnar
2007-09-25 16:04 ` Srivatsa Vaddagiri
2007-09-25 16:08 ` Srivatsa Vaddagiri
2007-09-25 21:35 Dmitry Adamushko
2007-09-27 7:56 ` Ingo Molnar
2007-09-30 19:13 Dmitry Adamushko
2007-10-01 6:11 ` Ingo Molnar
2007-09-30 19:15 Dmitry Adamushko
2007-10-01 5:53 ` Mike Galbraith
2007-10-01 5:55 ` Ingo Molnar
2007-09-30 19:18 Dmitry Adamushko
2007-10-02 19:49 Dmitry Adamushko
2007-10-02 19:59 ` Dmitry Adamushko
2007-10-03 4:15 ` Srivatsa Vaddagiri
2007-10-04 7:40 ` Ingo Molnar
2007-10-04 7:41 ` 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=20070925113306.GA19166@elte.hu \
--to=mingo@elte.hu \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=dhaval@linux.vnet.ibm.com \
--cc=dmitry.adamushko@gmail.com \
--cc=efault@gmx.de \
--cc=linux-kernel@vger.kernel.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