From: Peter Zijlstra <peterz@infradead.org>
To: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: mingo@elte.hu, linux-kernel@vger.kernel.org, chris@frostnet.net,
debian00@aliceadsl.fr, hpa@zytor.com,
jonathan.protzenko@gmail.com, mans@mansr.com, psastudio@mail.ru,
rjw@sisk.pl, stephan.eicher@web.de, sxxe@gmx.de,
thomas@archlinux.org, venki@google.com, wonghow@gmail.com
Subject: Re: [patch 3/3] sched: move sched_avg_update() to update_cpu_load()
Date: Mon, 16 Aug 2010 10:00:34 +0200 [thread overview]
Message-ID: <1281945634.1926.968.camel@laptop> (raw)
In-Reply-To: <20100813193911.999833492@sbsiddha-MOBL3.sc.intel.com>
On Fri, 2010-08-13 at 12:45 -0700, Suresh Siddha wrote:
> plain text document attachment (move_sched_avg_update.patch)
> Currently sched_avg_update() (which updates rt_avg stats in the rq) is getting
> called from scale_rt_power() (in the load balance context) which doesn't take
> rq->lock.
Right, but I think it doesn't need to, as its never accessed cross CPU
(except maybe for /proc/sched_debug, and who cares about that).
The (other) odd case is NO_HZ idle balancing, but there the actual CPU
won't be updating the fields, so the remote CPU doing NO_HZ idle
balancing should be good to touch it.
> Fix it by moving the sched_avg_update() to more appropriate update_cpu_load()
> where the CFS load gets updated aswell.
Right, except it breaks things a bit, at the very least you really need
that update right before reading it, otherwise you can end up with >100%
fractions, which are odd indeed ;-)
next prev parent reply other threads:[~2010-08-16 8:01 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-08-13 19:45 [patch 0/3] sched: fixes related to scaling down cpu power with RT tasks Suresh Siddha
2010-08-13 19:45 ` [patch 1/3] sched: init rt_avg stat whenever rq comes online Suresh Siddha
2010-08-16 7:47 ` Peter Zijlstra
2010-08-16 17:36 ` Suresh Siddha
2010-08-16 19:25 ` Peter Zijlstra
2010-08-17 8:51 ` Peter Zijlstra
2010-08-19 0:20 ` Suresh Siddha
2010-08-19 8:53 ` Peter Zijlstra
2010-08-20 0:03 ` Suresh Siddha
2010-08-20 8:54 ` Peter Zijlstra
2010-08-20 14:16 ` [tip:sched/urgent] x86, tsc, sched: Recompute cyc2ns_offset's during resume from sleep states tip-bot for Suresh Siddha
2010-08-13 19:45 ` [patch 2/3] sched: fix minimum power returned by update_cpu_power() Suresh Siddha
2010-08-16 7:50 ` Peter Zijlstra
2010-08-16 17:37 ` Suresh Siddha
2010-08-13 19:45 ` [patch 3/3] sched: move sched_avg_update() to update_cpu_load() Suresh Siddha
2010-08-16 8:00 ` Peter Zijlstra [this message]
2010-08-16 17:46 ` Suresh Siddha
2010-08-16 19:31 ` Peter Zijlstra
2010-08-20 0:51 ` Suresh Siddha
2010-08-20 9:25 ` Peter Zijlstra
2010-08-20 13:47 ` Peter Zijlstra
2010-08-23 20:42 ` Suresh Siddha
2010-09-09 19:45 ` [tip:sched/urgent] sched: Move " tip-bot for Suresh Siddha
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=1281945634.1926.968.camel@laptop \
--to=peterz@infradead.org \
--cc=chris@frostnet.net \
--cc=debian00@aliceadsl.fr \
--cc=hpa@zytor.com \
--cc=jonathan.protzenko@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mans@mansr.com \
--cc=mingo@elte.hu \
--cc=psastudio@mail.ru \
--cc=rjw@sisk.pl \
--cc=stephan.eicher@web.de \
--cc=suresh.b.siddha@intel.com \
--cc=sxxe@gmx.de \
--cc=thomas@archlinux.org \
--cc=venki@google.com \
--cc=wonghow@gmail.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.