Date: Sat, 30 Apr 2005 18:20:54 +0200
From: Francois Romieu <romieu@fr.zoreil.com>
To: "Pedro Venda (SYSADM)" <pjvenda@rnl.ist.utl.pt>
Cc: linux-kernel@vger.kernel.org, rnl@rnl.ist.utl.pt
Subject: Re: ftp server crashes on heavy load: possible scheduler bug
Message-ID: <20050430162054.GA20899@electric-eye.fr.zoreil.com>
References: <200504261402.57375.pjvenda@rnl.ist.utl.pt> <20050427181609.GA21785@electric-eye.fr.zoreil.com> <200504291519.52558.pjvenda@rnl.ist.utl.pt>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <200504291519.52558.pjvenda@rnl.ist.utl.pt>
User-Agent: Mutt/1.4.1i
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 816
Lines: 21

Pedro Venda (SYSADM) <pjvenda@rnl.ist.utl.pt> :
[...]
> please note that netconsole was added AFTER some crashes to analise the crash 
> dump, so I don't think it's directly related.

I agree. See it more as 1) preempt is "interesting", 2) it is not clear that
netpoll will show what one expects when networking issues come into play
(netpoll locking had to change recently). It would be nice to narrow the
issue within the fs/block subsystem.

> keep in mind that this is a production machine.

Some may toast me but I'd avoid preempt on a production machine.

--
Ueimor
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/