From: Mike Galbraith <efault@gmx.de>
To: Paolo Ornati <ornati@fastwebnet.it>
Cc: Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Con Kolivas <kernel@kolivas.org>, Ingo Molnar <mingo@elte.hu>,
Nick Piggin <nickpiggin@yahoo.com.au>,
Peter Williams <pwil3058@bigpond.net.au>
Subject: Re: [SCHED] wrong priority calc - SIMPLE test case
Date: Tue, 10 Jan 2006 08:08:09 +0100 [thread overview]
Message-ID: <5.2.1.1.2.20060110062457.00c38d18@pop.gmx.net> (raw)
In-Reply-To: <20060109210035.3f6adafc@localhost>
At 09:00 PM 1/9/2006 +0100, Paolo Ornati wrote:
>On Mon, 09 Jan 2006 16:52:17 +0100
>Mike Galbraith <efault@gmx.de> wrote:
>
> > >Care to try an experiment?...
>
>Yes.
Thanks.
>With my simple proggy things improve a bit:
<snip rest of good news>
>BUT if I start more of them (3/4) I'm able to fool it.
>
>"./a.out 7000 & ./a.out 6537 & ./a.out 6347 & ./a.out 5873"
>
>2 TOP's snapshots:
>
> PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
> 5625 paolo 17 0 2392 288 228 R 31.6 0.1 0:10.74 a.out
> 5626 paolo 17 0 2392 288 228 R 28.8 0.1 0:09.16 a.out
> 5627 paolo 17 0 2392 288 228 R 22.2 0.1 0:07.59 a.out
> 5624 paolo 17 0 2392 288 228 R 17.4 0.1 0:08.67 a.out
>
> PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
> 5626 paolo 16 0 2392 288 228 R 30.1 0.1 0:39.95 a.out
> 5627 paolo 16 0 2392 288 228 R 24.1 0.1 0:34.93 a.out
> 5625 paolo 18 0 2392 288 228 R 23.5 0.1 0:37.53 a.out
> 5624 paolo 18 0 2392 288 228 R 21.9 0.1 0:37.60 a.out
> 5193 root 15 0 167m 17m 2916 S 0.2 3.5 0:09.67 X
> 5638 paolo 18 0 4952 1468 372 R 0.2 0.3 0:00.15 dd
>
>DD test (256MB): real 3m37.122s (instead of 8s)
Ok, I'll take another look. Those should be being throttled.
>REAL LIFE TEST (transcode)
>
>While running only transcode it gets priority 25:
>
> PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
> 5857 paolo 25 0 114m 18m 2424 R 90.9 3.7 0:14.28 transcode
> 5873 paolo 19 0 49860 4452 1860 S 8.6 0.9 0:01.40 tcdecode
> 5308 paolo 16 0 86796 22m 15m R 0.2 4.4 0:06.26 konsole
> 5687 paolo 16 0 98648 37m 9348 S 0.2 7.5 0:02.11 perl
> 5872 paolo 24 0 21864 1064 600 S 0.2 0.2 0:00.01 tcextract
>
>
>But if I run also the DD test, "transcode" priority start fluctuating
>and can go down to 18/19 (from time to time) interfering with DD:
19 shouldn't interfere from the cpu side, but 18 will.
> PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
> 5694 paolo 19 0 114m 18m 2424 R 75.1 3.7 0:42.29 transcode
> 5710 paolo 25 0 49856 4452 1860 R 8.0 0.9 0:04.36 tcdecode
> 5726 paolo 18 0 4952 1468 372 R 4.0 0.3 0:00.77 dd
>
>
>This seems to happen because also transcode is reading (not directly but
>through pipes) from disk so the massive disk usage of DD interferes
>with it, this leads to transcode using less CPU and getting better
>priority.
It can't be pipe waits, they're disabled in the kernel. Most likely the
credit we get for being activated without having yet been selected.
>The exact behaviour changes time to time... but seems to confirm my
>teory.
>
>I don't know how can "nicksched" keep transcode priority always to 40
>even when I'm running the DD test... I should retry and see.
>
>
>PS: yes, transcode is reading from disk, but SLOWLY... i think that a
>good read-ahead should fullfill his needs even when doing the HD
>stressing DD test, no?
Dunno.
-Mike
next prev parent reply other threads:[~2006-01-10 7:08 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-12-27 18:09 [SCHED] Totally WRONG prority calculation with specific test-case (since 2.6.10-bk12) Paolo Ornati
2005-12-27 21:48 ` Paolo Ornati
2005-12-27 23:26 ` Con Kolivas
2005-12-28 11:01 ` Paolo Ornati
2005-12-28 11:19 ` Con Kolivas
2005-12-28 11:35 ` Paolo Ornati
2005-12-28 17:23 ` Paolo Ornati
2005-12-28 17:39 ` Paolo Ornati
2005-12-30 13:52 ` [SCHED] wrong priority calc - SIMPLE test case Paolo Ornati
2005-12-31 2:06 ` Peter Williams
2005-12-31 10:34 ` Paolo Ornati
2005-12-31 10:52 ` Paolo Ornati
2005-12-31 11:12 ` Con Kolivas
2005-12-31 13:44 ` Peter Williams
2005-12-31 16:31 ` Paolo Ornati
2005-12-31 22:04 ` Peter Williams
2005-12-31 8:13 ` Mike Galbraith
2005-12-31 11:00 ` Paolo Ornati
2005-12-31 15:11 ` Paolo Ornati
2005-12-31 16:37 ` Mike Galbraith
2005-12-31 17:24 ` Paolo Ornati
2005-12-31 17:42 ` Paolo Ornati
2006-01-01 11:39 ` Paolo Ornati
2006-01-02 9:15 ` Mike Galbraith
2006-01-02 9:50 ` Paolo Ornati
2006-01-09 11:11 ` Mike Galbraith
2006-01-09 15:52 ` Mike Galbraith
2006-01-09 16:08 ` Con Kolivas
2006-01-09 18:14 ` Mike Galbraith
2006-01-09 20:00 ` Paolo Ornati
2006-01-09 20:23 ` Paolo Ornati
2006-01-10 7:08 ` Mike Galbraith [this message]
2006-01-10 12:07 ` Mike Galbraith
2006-01-10 12:56 ` Paolo Ornati
2006-01-10 13:01 ` Mike Galbraith
2006-01-10 13:53 ` Paolo Ornati
2006-01-10 15:18 ` Mike Galbraith
2006-01-13 1:13 ` Con Kolivas
2006-01-13 1:32 ` Con Kolivas
2006-01-13 10:46 ` Paolo Ornati
2006-01-13 10:51 ` Con Kolivas
2006-01-13 13:01 ` Mike Galbraith
2006-01-13 14:34 ` Con Kolivas
2006-01-13 16:15 ` Mike Galbraith
2006-01-14 2:05 ` Con Kolivas
2006-01-14 2:56 ` Mike Galbraith
2005-12-27 23:59 ` [SCHED] Totally WRONG prority calculation with specific test-case (since 2.6.10-bk12) Peter Williams
2005-12-28 10:20 ` Paolo Ornati
2005-12-28 13:38 ` Peter Williams
2005-12-28 19:45 ` Paolo Ornati
2005-12-29 3:13 ` Nick Piggin
2005-12-29 3:35 ` Peter Williams
2005-12-29 8:11 ` Nick Piggin
2006-01-27 16:57 [SCHED] wrong priority calc - SIMPLE test case Con Kolivas
2006-01-27 20:06 ` MIke Galbraith
2006-01-27 23:18 ` Con Kolivas
2006-01-28 0:01 ` Peter Williams
2006-01-28 3:43 ` MIke Galbraith
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=5.2.1.1.2.20060110062457.00c38d18@pop.gmx.net \
--to=efault@gmx.de \
--cc=kernel@kolivas.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=nickpiggin@yahoo.com.au \
--cc=ornati@fastwebnet.it \
--cc=pwil3058@bigpond.net.au \
/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).