From: Arjan van de Ven <arjan@linux.intel.com>
To: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Vladimir Davydov <vdavydov@parallels.com>,
Ingo Molnar <mingo@elte.hu>, Len Brown <lenb@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH] cpuidle: menu: use nr_running instead of cpuload for calculating perf mult
Date: Mon, 04 Jun 2012 06:13:42 -0700 [thread overview]
Message-ID: <4FCCB486.4040905@linux.intel.com> (raw)
In-Reply-To: <1338805967.28282.12.camel@twins>
On 6/4/2012 3:32 AM, Peter Zijlstra wrote:
> On Mon, 2012-06-04 at 14:24 +0400, Vladimir Davydov wrote:
>> rq->cpuload strongly depends on cgroup hierarchy. For example, if hundreds of
>> tasks are running inside cpu:/test cgroup, the sum of cpuload over all cpus
>> won't exceed 1024 (by default). That makes the cpuidle menu governor take wrong
>> decisions, which can negatively affect overall performance.
>>
>> To cope this, use nr_running last seen in __update_cpu_load() instead of
>> cpuload for calculating performance multiplier.
>
> What is cpuidle trying to do?
what it is doing is trying to use "cpuload" as proxy for performance
sensitivity. The higher the load, the longer the idle period (predicted)
needs to be, for cpuidle to be willing to tolerate the latency of deeper
C states.
next prev parent reply other threads:[~2012-06-04 13:13 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-06-04 10:24 [PATCH] cpuidle: menu: use nr_running instead of cpuload for calculating perf mult Vladimir Davydov
2012-06-04 10:32 ` Peter Zijlstra
2012-06-04 10:50 ` Vladimir Davydov
2012-06-04 13:13 ` Arjan van de Ven [this message]
2012-06-04 13:45 ` Peter Zijlstra
2012-06-04 13:48 ` Arjan van de Ven
2012-06-04 15:08 ` Peter Zijlstra
2012-06-04 15:14 ` Arjan van de Ven
2012-06-04 15:26 ` Peter Zijlstra
2012-06-04 15:39 ` Arjan van de Ven
2012-06-04 16:33 ` Peter Zijlstra
2012-06-04 16:53 ` Arjan van de Ven
2012-06-04 17:08 ` Vladimir Davydov
2012-06-04 17:17 ` Peter Zijlstra
2012-06-04 17:16 ` Peter Zijlstra
2012-06-04 17:25 ` Arjan van de Ven
2012-06-04 20:31 ` Peter Zijlstra
2012-06-04 20:45 ` Arjan van de Ven
2012-06-04 21:14 ` Peter Zijlstra
2012-06-04 20:40 ` Peter Zijlstra
2012-06-05 3:48 ` Mike Galbraith
2012-06-04 13:15 ` Arjan van de Ven
2012-06-04 13:19 ` Vladimir Davydov
2012-11-27 19:02 ` Vladimir Davydov
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=4FCCB486.4040905@linux.intel.com \
--to=arjan@linux.intel.com \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=lenb@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=vdavydov@parallels.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