From: Andi Kleen <andi@firstfloor.org>
To: Arjan van de Ven <arjan@infradead.org>
Cc: Andi Kleen <andi@firstfloor.org>, Matthew Wilcox <matthew@wil.cx>,
Jens Axboe <jens.axboe@oracle.com>,
linux-kernel@vger.kernel.org, "Styner,
Douglas W" <douglas.w.styner@intel.com>,
Chinang Ma <chinang.ma@intel.com>,
"Prickett, Terry O" <terry.o.prickett@intel.com>,
Matthew Wilcox <matthew.r.wilcox@intel.com>,
Eric.Moore@lsi.com, DL-MPTFusionLinux@lsi.com
Subject: Re: >10% performance degradation since 2.6.18
Date: Sat, 4 Jul 2009 01:35:05 +0200 [thread overview]
Message-ID: <20090703233505.GL2041@one.firstfloor.org> (raw)
In-Reply-To: <20090703130421.646fe5cb@infradead.org>
> ... so that you can't do power management on a per socket basis?
> hardly a good idea.
Interrupts should only happen when the socket did spent time submitting
the work for them. Typically on drivers I'm familiar with the return
MSI is tied to the CPU that did submit the work item
> just need to use a new enough irqbalance and it will spread out the
> interrupts unless your load is low enough to go into low power mode.
When that load is low then likely you won't get many interrupts
anyways.
-Andi
--
ak@linux.intel.com -- Speaking for myself only.
next prev parent reply other threads:[~2009-07-03 23:35 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-07-03 2:56 >10% performance degradation since 2.6.18 Matthew Wilcox
2009-07-03 17:04 ` Paul E. McKenney
2009-07-03 18:19 ` Andi Kleen
2009-07-03 18:54 ` Jens Axboe
2009-07-03 19:13 ` Matthew Wilcox
2009-07-03 19:22 ` Jens Axboe
2009-07-03 19:45 ` Matthew Wilcox
2009-07-03 19:54 ` Andi Kleen
2009-07-03 20:04 ` Arjan van de Ven
2009-07-03 23:35 ` Andi Kleen [this message]
2009-07-04 6:04 ` Arjan van de Ven
2009-07-04 8:44 ` Andi Kleen
2009-07-04 9:19 ` Jeff Garzik
2009-07-05 4:01 ` Herbert Xu
2009-07-05 13:09 ` Matthew Wilcox
2009-07-05 16:11 ` Herbert Xu
2009-07-06 8:38 ` Andi Kleen
2009-07-05 20:44 ` Jeff Garzik
2009-07-06 1:19 ` Herbert Xu
2009-07-06 8:45 ` Andi Kleen
2009-07-06 17:00 ` Rick Jones
2009-07-06 17:36 ` Ma, Chinang
2009-07-06 17:42 ` Matthew Wilcox
2009-07-06 17:57 ` Ma, Chinang
2009-07-06 18:05 ` Matthew Wilcox
2009-07-06 18:48 ` Ma, Chinang
2009-07-06 18:53 ` Matthew Wilcox
2009-07-06 21:16 ` Ma, Chinang
2009-07-07 8:16 ` Andi Kleen
-- strict thread matches above, loose matches on Subject: below --
2009-07-05 11:00 Daniel J Blueman
2009-07-06 21:58 ` Chetan.Loke
2009-07-07 22:05 ` Daniel J Blueman
2009-07-08 15:03 ` Chetan.Loke
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=20090703233505.GL2041@one.firstfloor.org \
--to=andi@firstfloor.org \
--cc=DL-MPTFusionLinux@lsi.com \
--cc=Eric.Moore@lsi.com \
--cc=arjan@infradead.org \
--cc=chinang.ma@intel.com \
--cc=douglas.w.styner@intel.com \
--cc=jens.axboe@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=matthew.r.wilcox@intel.com \
--cc=matthew@wil.cx \
--cc=terry.o.prickett@intel.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