mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: David Ronis <ronis@ronispc.chem.mcgill.ca>
To: Parag Warudkar <kernel-stuff@comcast.net>
Cc: david.ronis@mcgill.ca, linux-kernel@vger.kernel.org
Subject: RE: problem with 2.6.13.[0-2]
Date: Wed, 28 Sep 2005 21:37:10 -0400	[thread overview]
Message-ID: <1127957830.6261.5.camel@montroll.chem.mcgill.ca> (raw)
In-Reply-To: <Pine.WNT.4.63.0509272247550.2588@home-comp>

On Tue, 2005-09-27 at 22:55 -0400, Parag Warudkar wrote:
> 
> > DMA is on in both 2.6.12.6 and in 2.6.13.2.  Here's what hdparm
> > /dev/hda gives:
> >
> > in 2.6.12.6:
> >
> > /dev/hda:
> >  multcount    = 16 (on)
> >  IO_support   =  0 (default 16-bit)
> >  unmaskirq    =  0 (off)
> >  using_dma    =  1 (on)
> >  keepsettings =  0 (off)
> >  readonly     =  0 (off)
> >  readahead    = 256 (on)
> >  geometry     = 65535/16/63, sectors = 195371568, start = 0
> >
> > in 2.6.13.2 it's the same, except for
> >
> > multcount    =  0 (off)
> >
> > Could this be the problem, and if so, would setting multcount to on
> > fix it? (I take it hdparm -m 16 /dev/hda would do it)
> 
> I doubt if multcount will make a difference, but you can try.
> Probably next best thing to do is profile the slow kernel to find where it 
> is spending time. (pass profile=2 on kernel command line and use 
> readprofile or use oprofile).
> 
> Did you try hdparm -tT /dev/hda? It's going to be slow, thats for sure 
> from what you described but try that and then post dmesg (for both 
> kernels) and profile results - may be someone will get a clue from that.
> 
> Parag
> 
> 

Hi Parag,

Here's what I get:

In 2.6.12.6:

/dev/hda:
 Timing cached reads:   1140 MB in  2.00 seconds = 569.80 MB/sec
 Timing buffered disk reads:  102 MB in  3.02 seconds =  33.80 MB/sec

In 2.6.13.2:

/dev/hda:
 Timing cached reads:    28 MB in  2.15 seconds =  13.03 MB/sec
 Timing buffered disk reads:   14 MB in  3.30 seconds =   4.24 MB/sec

and after hdparm -m 16 /dev/hda (recall this is the default in 2.6.12.6)

/dev/hda:
 Timing cached reads:    24 MB in  2.05 seconds =  11.73 MB/sec
 Timing buffered disk reads:   36 MB in  3.11 seconds =  11.56 MB/sec

I ran thing a few times in each case and the results were close.  There
was nothing in dmesg.

David



  reply	other threads:[~2005-09-29  1:37 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-09-28  2:55 Parag Warudkar
2005-09-29  1:37 ` David Ronis [this message]
2005-09-29  6:20   ` Jean Delvare
2005-09-29 21:26     ` David Ronis
  -- strict thread matches above, loose matches on Subject: below --
2005-09-29  4:13 kernel-stuff
2005-09-25 18:24 David Ronis
     [not found] ` <20050926005531.90DF42E0018@asmx1.McGill.CA>
2005-09-27  2:34   ` David Ronis
2005-09-29 10:29 ` Bartlomiej Zolnierkiewicz
2005-09-29 21:34   ` David Ronis

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=1127957830.6261.5.camel@montroll.chem.mcgill.ca \
    --to=ronis@ronispc.chem.mcgill.ca \
    --cc=david.ronis@mcgill.ca \
    --cc=kernel-stuff@comcast.net \
    --cc=linux-kernel@vger.kernel.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

all inboxes | Powered by JetHome®