Date: Sun, 16 Sep 2007 17:53:21 +0200
From: Andrea Arcangeli <andrea@suse.de>
To: Randy Dunlap <randy.dunlap@oracle.com>
Cc: linux-kernel@vger.kernel.org
Subject: Re: crashme fault
Message-ID: <20070916155320.GE6708@v2.random>
References: <20070912222151.70d1fc7d.randy.dunlap@oracle.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20070912222151.70d1fc7d.randy.dunlap@oracle.com>
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 894
Lines: 16

On Wed, Sep 12, 2007 at 10:21:51PM -0700, Randy Dunlap wrote:
> I run almost-daily kernel testing.  I haven't seen 'crashme' cause a
> kernel fault until today, and now I've seen it twice on 2.6.23-rc6-git2,

Did the room temperature change in the server room? ;) Those early
EM64T P4 core based are fast but they suck a whole lot of power. It
seems a bitflip in a cpu register. You can use cpufreq to set low
frequency (they should support it, and they shouldn't use more than
100w per core that way) to lower the temp, and see if the problem goes
away. If it's a software issue it will hopefully be still reproducible
with ~2ghz instead of 3.4ghz.
-
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/