mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Steven Cole <elenstev@mesatop.com>
To: Andrew Morton <akpm@zip.com.au>
Cc: Jens Axboe <axboe@suse.de>,
	Marcelo Tosatti <marcelo@conectiva.com.br>,
	lkml <linux-kernel@vger.kernel.org>, Steven Cole <scole@lanl.gov>
Subject: Re: Linux v2.4.19-rc5
Date: 01 Aug 2002 08:45:20 -0600	[thread overview]
Message-ID: <1028213120.3085.88.camel@spc9.esa.lanl.gov> (raw)
In-Reply-To: <3D48F915.3FADA08F@zip.com.au>

On Thu, 2002-08-01 at 03:02, Andrew Morton wrote:
> Jens Axboe wrote:
> > 
> > ...
> > > Anyway, lets wait for the numbers.
> > 
> > It just 'feels' like the sort of change that might have odd side
> > effects.
> 
> It's almost impossible to get READA to do anything.  For example, in
> current 2.5, if a READA attempt is actually aborted, end_buffer_io_sync
> reports a "buffer I/O error".  Every time. And nobody has reported this.
> 
> It _is_ possible to hit this in 2.5, because of ext2_preread_inode().
> 
> Probably, also it's possible to hit it in 2.4 with hundreds of processes
> all issuing ext3 directory readahead.  But it's pretty remote.

I've never seen this on 2.4.19-rc3 and I've been beating on it pretty
hard, running dbench 128 many times.  However, 2.5 is another story.

This might not be the best thread to report this, but since the subject 
came up, I'm getting the following message with recent 2.5.x kernels
whenever I run relatively large numbers of dbench clients.  

Buffer I/O error on device sd(8,8), logical block XXXXXXX

where logical block repeats 0-6 times.  This behavior is repeatable, but
only occurs under fairly high load.  I ran dbench with increasing numbers
of clients, with the following results:

dbench clients	Buffer I/O error messages
>=48		0
52		1
56		0
64		0
80		11
96		9
112		7
128		4

This particular run was with 2.5.29 with rmap13b and slabLRU patches, but the behavior with 2.5.29-vanilla was similar.  Kernel is SMP, no preempt,
and /dev/sda8 where dbench was running was mounted ext2.
The test box is 2-way p3, SCSI, 1GB memory.

Time to go beat on -rc5 and see if anything falls out.

Steven





  parent reply	other threads:[~2002-08-01 14:44 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-08-01  6:38 Marcelo Tosatti
2002-08-01  7:49 ` Jens Axboe
2002-08-01  7:14   ` Marcelo Tosatti
2002-08-01  8:10     ` Jens Axboe
2002-08-01  9:02       ` Andrew Morton
2002-08-01  8:58         ` Jens Axboe
2002-08-01 14:45         ` Steven Cole [this message]
2002-08-01 18:57           ` Andrew Morton
2002-08-01 20:15     ` Steven Cole
2002-08-06  3:46       ` Bill Davidsen
2002-08-06  4:30         ` Andrew Morton
2002-08-06 14:07           ` Steven Cole
2002-08-06 14:20             ` Rik van Riel
2002-08-06 17:12             ` Andrew Morton
2002-08-06  5:42         ` Jens Axboe
2002-08-06  8:30           ` Adrian Bunk
2002-08-06  8:48             ` Jens Axboe
2002-08-06 10:31           ` Lincoln Dale
2002-08-06 12:59         ` Rik van Riel
2002-08-07  1:09           ` Bill Davidsen
2002-08-07  2:54             ` Steven Cole
2002-08-07 22:30               ` Bill Davidsen
2002-08-07 22:39                 ` Rik van Riel
2002-08-07 23:44                   ` Bill Davidsen
2002-08-07 23:53                     ` Rik van Riel
2002-08-09 17:46                       ` Bill Davidsen
2002-08-09 19:27                         ` Rik van Riel
2002-08-01  7:55 ` Keith Owens
2002-08-01  8:10   ` Jens Axboe
2002-08-04  6:50   ` H. Peter Anvin
2002-08-01 11:32 ` Willy TARREAU
2002-08-01 13:54   ` Alan Cox
2002-08-01 12:48     ` Willy TARREAU
2002-08-01 12:12 ` Linux v2.4.19-rc5 - APM bug Willy TARREAU
2002-08-01 13:32   ` [PANIC] APM bug with -rc4 and -rc5 Willy TARREAU
2002-08-01 14:55     ` Alan Cox
2002-08-01 13:56       ` Willy Tarreau
2002-08-01 15:24         ` Willy Tarreau
2002-08-01 16:53           ` Alan Cox
2002-08-01 16:41             ` Willy Tarreau
2002-08-01 20:35             ` [PATCH] solved APM bug with -rc5 Willy TARREAU
2002-08-01 20:52               ` Richard Gooch
2002-08-01 20:54                 ` Richard Gooch
2002-08-01 21:17                   ` Willy TARREAU
2002-08-01 22:37                     ` Alan Cox
2002-08-01 20:58                 ` Dave Jones
2002-08-01 22:16               ` Alan Cox
2002-08-01 21:07                 ` Willy Tarreau
2002-08-01 21:47                   ` Linus Torvalds
2002-08-02  0:12                 ` [PATCH] solved APM bug with -rc5 (take 2) Willy TARREAU
2002-08-02  1:47 ` [PATCH] pdc20265 problem Nick Orlov
2002-08-02  2:29   ` Nick Orlov
2002-08-02 12:27   ` Alan Cox
2002-08-02 12:52     ` Nick Orlov
2002-08-02 14:00       ` Bartlomiej Zolnierkiewicz
2002-08-02 14:45         ` Nick Orlov
2002-08-06  4:36 Linux v2.4.19-rc5 rwhron
2002-08-07  3:00 ` Bill Davidsen
2002-08-06 20:12 Peter Wong

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=1028213120.3085.88.camel@spc9.esa.lanl.gov \
    --to=elenstev@mesatop.com \
    --cc=akpm@zip.com.au \
    --cc=axboe@suse.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=marcelo@conectiva.com.br \
    --cc=scole@lanl.gov \
    /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®