From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
To: Michael Wang <wangyun@linux.vnet.ibm.com>
Cc: linux-kernel@vger.kernel.org,
"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
tglx@linutronix.de
Subject: Re: [RFC 2/2] sched/fair: prefer a CPU in the "lowest" idle state
Date: Sat, 02 Feb 2013 18:50:05 +0100 [thread overview]
Message-ID: <510D51CD.6020506@linutronix.de> (raw)
In-Reply-To: <5109D313.1020409@linux.vnet.ibm.com>
On 01/31/2013 03:12 AM, Michael Wang wrote:
> I'm not sure, but just concern about this case:
>
> group 0 cpu 0 cpu 1
> least idle 4 task
>
> group 1 cpu 2 cpu 3
> 1 task 1 task
>
> The previous logical will pick group 1 and now it will take group 0, and
> that cause more imbalance, doesn't it?
That depends on load of CPU 0 + 1 vs CPU 2 + 3. If the four tasks on
CPU1 are idle then the previous code should return group 0.
If the four tasks are running at 100% each then two of them should be
migrated to CPU0 and this point the idle state does not matter :)
> May be check that state in find_idlest_cpu() will be better?
You say to move this from find_idlest_group() to find_idlest_cpu()?
> Regards,
> Michael Wang
Sebastian
next prev parent reply other threads:[~2013-02-02 17:50 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-01-30 21:19 [RFC] Consider CPU idle state while choosing a new CPU Sebastian Andrzej Siewior
2013-01-30 21:19 ` [RFC 1/2] cpuidle: trace state of the CPU Sebastian Andrzej Siewior
2013-01-31 5:21 ` Namhyung Kim
2013-02-02 17:35 ` Sebastian Andrzej Siewior
2013-01-30 21:19 ` [RFC 2/2] sched/fair: prefer a CPU in the "lowest" idle state Sebastian Andrzej Siewior
2013-01-31 2:12 ` Michael Wang
2013-01-31 5:16 ` Namhyung Kim
2013-01-31 6:39 ` Michael Wang
2013-01-31 6:58 ` Namhyung Kim
2013-01-31 7:30 ` Michael Wang
2013-01-31 7:40 ` Namhyung Kim
2013-01-31 8:24 ` Michael Wang
2013-01-31 8:45 ` Michael Wang
2013-01-31 8:57 ` Michael Wang
2013-02-01 8:53 ` Namhyung Kim
2013-02-02 17:50 ` Sebastian Andrzej Siewior [this message]
2013-02-04 3:01 ` Michael Wang
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=510D51CD.6020506@linutronix.de \
--to=bigeasy@linutronix.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rafael.j.wysocki@intel.com \
--cc=tglx@linutronix.de \
--cc=wangyun@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;
as well as URLs for NNTP newsgroup(s).