From: Tong Li <tong.n.li@intel.com>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>, Ingo Molnar <mingo@elte.hu>,
dimm <dmitry.adamushko@gmail.com>,
linux-kernel@vger.kernel.org,
Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Subject: Re: [git] CFS-devel, group scheduler, fixes
Date: Mon, 24 Sep 2007 09:43:17 -0700 (PDT) [thread overview]
Message-ID: <Pine.LNX.4.64.0709240935170.25564@tongli.jf.intel.com> (raw)
In-Reply-To: <20070924135158.1359013b@twins>
On Mon, 24 Sep 2007, Peter Zijlstra wrote:
> On Mon, 24 Sep 2007 13:22:14 +0200 Mike Galbraith <efault@gmx.de> wrote:
>
>> On Mon, 2007-09-24 at 12:42 +0200, Mike Galbraith wrote:
>>> On Mon, 2007-09-24 at 12:24 +0200, Peter Zijlstra wrote:
>>>
>>>> how about something like:
>>>>
>>>> s64 delta = (s64)(vruntime - min_vruntime);
>>>> if (delta > 0)
>>>> min_vruntime += delta;
>>>>
>>>> That would rid us of most of the funny conditionals there.
>>>
>>> That still left me with negative min_vruntimes. The pinned hogs didn't
>>> lock my box up, but I quickly got the below, so hastily killed it.
>>
>> Shouldn't the max() in place_entity() be the max_vruntime() that my
>> lysdexia told me it was when I looked at it earlier? ;-)
>>
>
> probably, my tree doesn't have that max anymore so I'm not sure.
>
Last time I looked, I thought the max() in place_entity() was fine and the
problem seemed to be in set_task_cpu() that was causing the negative
vruntimes:
if (likely(new_rq->cfs.min_vruntime))
p->se.vruntime -= old_rq->cfs.min_vruntime -
new_rq->cfs.min_vruntime;
I think it's fine we get rid of sync_vruntime(). I need to think more
about how to make global fairness work based on this--it seems to be more
complicated than if we had sync_vruntime().
tong
next prev parent reply other threads:[~2007-09-24 16:48 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-09-18 19:36 dimm
2007-09-18 20:16 ` Ingo Molnar
2007-09-19 6:03 ` Tong Li
2007-09-19 6:28 ` Mike Galbraith
2007-09-19 7:51 ` Mike Galbraith
2007-09-19 8:42 ` Mike Galbraith
2007-09-19 17:06 ` Tong Li
2007-09-20 4:55 ` Mike Galbraith
2007-09-20 7:15 ` Mike Galbraith
2007-09-20 7:51 ` Ingo Molnar
2007-09-20 8:11 ` Mike Galbraith
2007-09-22 3:27 ` Tong Li
2007-09-22 10:01 ` Mike Galbraith
2007-09-23 7:14 ` Mike Galbraith
2007-09-23 11:37 ` Mike Galbraith
[not found] ` <20070923115847.GA13061@elte.hu>
2007-09-23 15:53 ` [git] CFS-devel, updates Mike Galbraith
2007-09-24 6:21 ` [git] CFS-devel, group scheduler, fixes Tong Li
2007-09-24 10:10 ` Mike Galbraith
2007-09-24 10:24 ` Peter Zijlstra
2007-09-24 10:42 ` Mike Galbraith
2007-09-24 11:08 ` Peter Zijlstra
2007-09-24 11:43 ` Mike Galbraith
2007-09-24 11:22 ` Mike Galbraith
2007-09-24 11:51 ` Peter Zijlstra
2007-09-24 16:43 ` Tong Li [this message]
2007-09-20 19:48 ` Willy Tarreau
2007-09-21 2:40 ` Mike Galbraith
2007-09-21 3:11 ` Willy Tarreau
2007-09-19 19:35 ` Siddha, Suresh B
2007-09-19 20:58 ` Tong Li
2007-09-18 20:22 ` Ingo Molnar
2007-09-19 3:55 ` Srivatsa Vaddagiri
-- strict thread matches above, loose matches on Subject: below --
2007-09-18 19:56 Dmitry Adamushko
2007-09-18 20:18 ` Ingo Molnar
2007-09-18 19:46 Dmitry Adamushko
2007-09-18 20:17 ` Ingo Molnar
2007-09-15 13:06 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=Pine.LNX.4.64.0709240935170.25564@tongli.jf.intel.com \
--to=tong.n.li@intel.com \
--cc=a.p.zijlstra@chello.nl \
--cc=dmitry.adamushko@gmail.com \
--cc=efault@gmx.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--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
all inboxes | Powered by JetHome®