All of lore.kernel.org
 help / color / mirror / Atom feed
From: Marcelo Tosatti <marcelo.tosatti@cyclades.com>
To: Chris Caputo <ccaputo@alt.net>
Cc: Linux Kernel <linux-kernel@vger.kernel.org>
Subject: Re: inode_unused list corruption in 2.4.26 - spin_lock problem?
Date: Sat, 7 Aug 2004 16:36:06 -0300	[thread overview]
Message-ID: <20040807193606.GB26893@logos.cnet> (raw)
In-Reply-To: <Pine.LNX.4.44.0408070828240.7317-100000@nacho.alt.net>

On Sat, Aug 07, 2004 at 09:00:30AM -0700, Chris Caputo wrote:
> On Thu, 5 Aug 2004, Marcelo Tosatti wrote:
> > On Wed, Aug 04, 2004 at 02:55:38PM -0700, Chris Caputo wrote:
> > > Right now the 3 tests I have running are:
> > > 
> > >  Intel SDS2 mb / dual-PIII / 3ware / 2.4.26 / irqbalance --oneshot
> > >  Intel SDS2 mb / dual-PIII / 3ware / 2.4.27-rc5 / irqbalance ongoing
> > >  Intel STL2 mb / dual-PIII / DAC960 / 2.4.26 / irqbalance ongoing
> 
> Well, I ended up getting the same crash (report below) with the non-3ware
> (STL2 based) server, so I think I can rule the 3ware driver out as being
> an instigator.  The STL2 based server took 2 days 14.5 hours to get a
> corrupted inode_unused list.
> 
> This makes the list of motherboards I have seen the problem on be:
> 
>    Intel SE7501HG2 with dual-PIV's, 4 gig of ram
>    Intel SDS2 with dual-PIII's, 4 gig of ram
>    Intel STL2 with dual-PIII's, 2 gig of ram
> 
> At present the 2.4.26 with oneshot irqbalance and the 2.4.27-rc5 with
> normal irqbalance are continuing to run without problems.  Coming up on 3
> days without issues...  I'll keep them running.
> 
> Also, I'll start running 2.4.27-rc5 on a second server (the STL2) with a
> normal irqbalance.

Chris,

Started running "dbench 10" on 2.4.27-rc6 + arjan's irqbalance 0.9 on my 
dual P4 (e7500 plumas) with Symbios 53c1030 controller and 2GB of RAM.

  parent reply	other threads:[~2004-08-07 20:31 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20040805225549.GA18420@logos.cnet>
2004-08-07 16:00 ` inode_unused list corruption in 2.4.26 - spin_lock problem? Chris Caputo
2004-08-07 18:31   ` Marcelo Tosatti
2004-08-07 19:36   ` Marcelo Tosatti [this message]
2004-06-19  0:47 Chris Caputo
2004-06-20  0:15 ` Marcelo Tosatti
2004-06-20  3:33   ` Trond Myklebust
2004-06-21  0:45     ` Marcelo Tosatti
2004-06-21 17:10       ` Trond Myklebust
2004-06-21 18:23         ` Marcelo Tosatti
2004-06-24  1:51         ` Chris Caputo
2004-06-25  7:47           ` Chris Caputo
2004-06-24  1:50   ` Chris Caputo
2004-06-25  8:04     ` Chris Caputo
2004-06-25 10:18       ` Chris Caputo
2004-06-25 12:17     ` Marcelo Tosatti
2004-07-02 20:00       ` Chris Caputo
2004-07-03  5:15         ` Arjan van de Ven
2004-07-26 17:41           ` Chris Caputo
2004-07-27 14:19             ` Marcelo Tosatti
2004-07-27 16:08               ` Chris Caputo
2004-07-29  0:25                 ` Marcelo Tosatti
2004-07-29  6:27                   ` Chris Caputo
2004-07-29  7:54                     ` Arjan van de Ven
2004-07-29 10:57                       ` Marcelo Tosatti
2004-07-29 12:21                         ` Arjan van de Ven
2004-07-29 16:22                           ` Chris Caputo
2004-07-29 16:23                             ` Arjan van de Ven
2004-08-04 15:38                               ` Chris Caputo
2004-08-04 18:47                                 ` Chris Caputo

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=20040807193606.GB26893@logos.cnet \
    --to=marcelo.tosatti@cyclades.com \
    --cc=ccaputo@alt.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.