xfs
[Top] [All Lists]

Re: kernel-smp-2.4.3-SGI_XFS_1.0.1_PR3 bug report

To: Christopher McCrory <chrismcc@xxxxxxxxxxxxxxxx>
Subject: Re: kernel-smp-2.4.3-SGI_XFS_1.0.1_PR3 bug report
From: Nathan Straz <nstraz@xxxxxxx>
Date: Fri, 6 Jul 2001 10:29:28 -0500
Cc: linux-xfs list <linux-xfs@xxxxxxxxxxx>
In-reply-to: <3B45CCB3.1090107@xxxxxxxxxxxxxxxx>
Mail-followup-to: Christopher McCrory <chrismcc@xxxxxxxxxxxxxxxx>, linux-xfs list <linux-xfs@xxxxxxxxxxx>
References: <3B45CCB3.1090107@xxxxxxxxxxxxxxxx>
Sender: owner-linux-xfs@xxxxxxxxxxx
User-agent: Mutt/1.3.18i
On Fri, Jul 06, 2001 at 07:35:31AM -0700, Christopher McCrory wrote:
> 2:  I tried kernel-smp-2.4.3-SGI_XFS_1.0.1_PR3.i686.rpm on one of my 
> production web servers running XFS.  After ~15 minutes it crashed.  I 
> got someone to go to the colo and reset it.  I watched it for a while 
> and ~15 minutes later the load started shooting through the roof (~150). 

Did you get a look at the process table before you took the machine
down?  Theorically, if some of the Apache processes hit a common
deadlock, it would keep spawning new servers which would hit the same
deadlock and the load would skyrocket like you describe.  

I don't remember if kdb is in PR3, but if you could get a back trace of
the deadlocked processes, that might be helpful.

-- 
Nate Straz                                              nstraz@xxxxxxx
sgi, inc                                           http://www.sgi.com/
Linux Test Project                                  http://ltp.sf.net/

<Prev in Thread] Current Thread [Next in Thread>