From: Mike Galbraith <efault@gmx.de>
To: "Björn Steinbrink" <B.Steinbrink@gmx.de>
Cc: Arjan van de Ven <arjan@infradead.org>,
linux-kernel@vger.kernel.org, danial_thom@yahoo.com,
Linus Torvalds <torvalds@osdl.org>, Andrew Morton <akpm@osdl.org>
Subject: Re: [PATCH] i386: Fix softirq accounting with 4K stacks
Date: Mon, 26 Jun 2006 04:23:22 +0200 [thread overview]
Message-ID: <1151288602.7470.22.camel@Homer.TheSimpsons.net> (raw)
In-Reply-To: <20060625184244.GA11921@atjola.homenet>
On Sun, 2006-06-25 at 20:42 +0200, Björn Steinbrink wrote:
> I just booted with both patches applied, mine and Mike's, and that
> actually makes a difference in hardirq cpu time accounting. With my
> patch only, hi is 0 in top while the box gets a ping flood. With both
> patches, I get about 1% hi. Mike's patch causes update_process_times()
> to be called twice on UP, but that alone shouldn't change the
> percentages, right?
Yes, you definitely need to comment out the other call if you test the
SMP path on UP+IO-APIC.
> OTOH top shows "hi" as zero with 8K stacks as well unless Mike's patch
> is applied, so the results with Mike's patch are bogus (if so, why?) or
> hardirq accounting is broken in general.
Something is certainly still b0rken. I still get three different
answers to the question "what is my cpu usage" depending on
configuration. With stock UP kernel with no IO-APIC, interrupt load is
all hi. With your patch and IO-APIC, it's all si. SMP shows a mix of
both.
I like the result of using the SMP path if you have an IO-APIC best,
though I haven't verified them against a profile for accuracy. Taking a
peek at the profile confirms that it is indeed mixed, so anything
showing the load as being either hi or si has to be wrong.
-Mike
next prev parent reply other threads:[~2006-06-26 2:19 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-06-22 15:26 Measuring tools - top and interrupts Danial Thom
2006-06-22 16:19 ` Randy.Dunlap
2006-06-22 17:16 ` Bernd Eckenfels
2006-06-22 16:21 ` Erik Mouw
2006-06-22 16:58 ` Danial Thom
2006-06-22 17:31 ` Erik Mouw
2006-06-22 23:37 ` Danial Thom
2006-06-23 8:32 ` Mike Galbraith
2006-06-23 20:14 ` Danial Thom
2006-06-23 22:51 ` Mike Galbraith
2006-06-23 9:02 ` Erik Mouw
2006-06-23 17:13 ` Alistair John Strachan
2006-06-23 18:16 ` Danial Thom
2006-06-23 5:34 ` sena seneviratne
2006-06-23 20:42 ` Danial Thom
2006-06-22 17:57 ` Francois Romieu
2006-06-22 22:47 ` Danial Thom
2006-06-22 23:53 ` Francois Romieu
2006-06-23 20:34 ` Danial Thom
2006-06-23 21:19 ` Francois Romieu
2006-06-24 2:07 ` Björn Steinbrink
2006-06-24 4:39 ` sena seneviratne
2006-06-24 5:59 ` Mike Galbraith
2006-06-24 6:26 ` Mike Galbraith
2006-06-24 9:21 ` Björn Steinbrink
2006-06-24 9:51 ` Mike Galbraith
2006-06-24 11:41 ` Mike Galbraith
2006-06-24 15:40 ` Björn Steinbrink
2006-06-24 16:23 ` Mike Galbraith
2006-06-24 19:25 ` Björn Steinbrink
2006-06-25 5:06 ` Mike Galbraith
2006-06-25 11:12 ` Björn Steinbrink
2006-06-25 14:24 ` [PATCH] i386: Fix softirq accounting with 4K stacks Björn Steinbrink
2006-06-25 15:15 ` Arjan van de Ven
2006-06-25 17:44 ` Mike Galbraith
2006-06-25 17:43 ` Arjan van de Ven
2006-06-25 18:42 ` Björn Steinbrink
2006-06-26 2:23 ` Mike Galbraith [this message]
2006-06-26 3:05 ` Mike Galbraith
2006-06-26 17:58 ` Björn Steinbrink
2006-06-27 10:09 ` Mike Galbraith
2006-06-25 20:45 ` Measuring tools - top and interrupts Danial Thom
2006-06-26 2:33 ` Mike Galbraith
2006-06-30 13:41 ` Danial Thom
2006-06-30 18:03 ` Mike Galbraith
2006-06-26 22:54 [PATCH] i386: Fix softirq accounting with 4K stacks Chuck Ebbert
2006-06-27 0:57 ` Björn Steinbrink
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=1151288602.7470.22.camel@Homer.TheSimpsons.net \
--to=efault@gmx.de \
--cc=B.Steinbrink@gmx.de \
--cc=akpm@osdl.org \
--cc=arjan@infradead.org \
--cc=danial_thom@yahoo.com \
--cc=linux-kernel@vger.kernel.org \
--cc=torvalds@osdl.org \
/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).