From: Dimitrios Apostolou <jimis@gmx.net>
To: "Rafał Bilski" <rafalbilski@interia.pl>
Cc: linux-kernel@vger.kernel.org
Subject: Re: high system cpu load during intense disk i/o
Date: Tue, 7 Aug 2007 12:43:51 +0300 [thread overview]
Message-ID: <200708071243.52430.jimis@gmx.net> (raw)
In-Reply-To: <46B83560.2060107@interia.pl>
On Tuesday 07 August 2007 12:03:28 Rafał Bilski wrote:
> >> Just tested (plain curiosity).
> >> via82cxxx average result @533MHz:
> >> /dev/hda:
> >> Timing cached reads: 232 MB in 2.00 seconds = 115.93 MB/sec
> >> Timing buffered disk reads: 64 MB in 3.12 seconds = 20.54 MB/sec
> >> pata_via average result @533MHz:
> >> /dev/sda:
> >> Timing cached reads: 234 MB in 2.01 seconds = 116.27 MB/sec
> >> Timing buffered disk reads: 82 MB in 3.05 seconds = 26.92 MB/sec
> >
> > Interesting! I haven't tried libata myself on that system, I only have
> > remote access to it so I'm a bit afraid...
>
> Just change root=/dev/hda1 to append="root=/dev/sda1" in lilo.conf.
> And change fstab. If You don't change "/" then system will go into single
> user mode after reboot.
>
> > Rafal, I hope that system you run hdparm on isn't the archlinux one! Is
> > it easy to load an old kernel (even two years old) and do the same test?
> > If it is, please let me know of the results.
>
> I don't think it is possible. If I remember right kernel can't be older
> then glibc kernel headers.
> Btw. My disk is 20GB 2,5" ATA33. I wonder how 26MB/s is possible. I don't
> expect more.
Aha! So perhaps libata gives even greater performance benefit for better
drives. I'll try to get local access to my PC and try it. Thanks.
Dimitris
next prev parent reply other threads:[~2007-08-07 9:46 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-08-03 16:03 Dimitrios Apostolou
2007-08-05 16:03 ` Dimitrios Apostolou
2007-08-05 17:58 ` Rafał Bilski
2007-08-05 18:42 ` Dimitrios Apostolou
2007-08-05 20:08 ` Rafał Bilski
2007-08-06 16:14 ` Rafał Bilski
2007-08-06 19:18 ` Dimitrios Apostolou
2007-08-06 19:48 ` Alan Cox
2007-08-07 0:40 ` Dimitrios Apostolou
2007-08-07 0:37 ` Alan Cox
2007-08-07 13:15 ` Dimitrios Apostolou
2007-08-06 22:12 ` Rafał Bilski
2007-08-07 0:49 ` Dimitrios Apostolou
2007-08-07 9:03 ` Rafał Bilski
2007-08-07 9:43 ` Dimitrios Apostolou [this message]
2007-08-06 1:28 ` Andrew Morton
2007-08-06 14:20 ` Dimitrios Apostolou
2007-08-06 17:33 ` Andrew Morton
2007-08-06 19:27 ` Dimitrios Apostolou
2007-08-06 20:04 ` Dimitrios Apostolou
2007-08-06 16:09 ` Dimitrios Apostolou
2007-08-07 14:50 ` Dimitrios Apostolou
2007-08-08 19:08 ` Rafał Bilski
2007-08-09 8:17 ` Dimitrios Apostolou
2007-08-10 7:06 ` Rafał Bilski
2007-08-17 23:19 ` Dimitrios Apostolou
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=200708071243.52430.jimis@gmx.net \
--to=jimis@gmx.net \
--cc=linux-kernel@vger.kernel.org \
--cc=rafalbilski@interia.pl \
/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
all inboxes | Powered by JetHome®