Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 10 Jun 2005 07:38:16 -0500
From:      Doug Poland <doug@polands.org>
To:        Jeff Roberson <jroberson@chesapeake.net>
Cc:        current@freebsd.org
Subject:   Re: ULE Status.
Message-ID:  <20050610123816.GA39007@polands.org>
In-Reply-To: <20050610040141.B16943@mail.chesapeake.net>
References:  <20050604052429.T8209@mail.chesapeake.net> <20050609133749.GA68687@polands.org> <42A84CBF.9070701@altern.org> <20050609170838.GA80335@xor.obsecurity.org> <20050609171708.GC68687@polands.org> <20050609172225.GA92378@xor.obsecurity.org> <20050609173531.GE68687@polands.org> <20050610040141.B16943@mail.chesapeake.net>

next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, Jun 10, 2005 at 04:02:15AM -0400, Jeff Roberson wrote:
> On Thu, 9 Jun 2005, Doug Poland wrote:
> > On Thu, Jun 09, 2005 at 01:22:25PM -0400, Kris Kennaway wrote:
> > > On Thu, Jun 09, 2005 at 12:17:08PM -0500, Doug Poland wrote:
> > > > On Thu, Jun 09, 2005 at 01:08:39PM -0400, Kris Kennaway wrote:
> > > > > On Thu, Jun 09, 2005 at 04:05:51PM +0200, Gr?gory Nou wrote:
> > > > > > Fatal trap 12: page fault while in kernel mode
> > > > >
> > > > > No, this usually means you forgot to recompile nvidia.ko when
> > > > > you updated your kernel.
> > > > >
> > > > In my case, I'm not using the nvidia driver.  On this box, I
> > > > brought it up to 6-CURRENT from 5-STABLE via cvsup.  When I run
> > > > the GENERIC kernel with SCHED_4BSD, I don't have the fatal trap
> > > > issues.  When I'm running SCHED_ULE, hard locks are frequent.
> > >
> > > Right, yours is a different issue.  By "hard lock" you seem to
> > > mean "panic" though (your fatal trap 12)..it's important to use
> > > the right terminology to avoid confusion :-)
> > >
> > Sorry for my imprecise language.  So is this a ULE issue manifesting
> > itself with kernel panics?  Am I reporting it correctly?
> >
> 
> I think it's still not quite ready for prime time on SMP.  On UP it
> seems to be stable though.  Hopefully I can take a break from VFS this
> weekend to fix SMP again.
> 
I'll be glad to help test.  This particular SMP box is between projects
and is a good guinea pig.

-- 
Regards,
Doug



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050610123816.GA39007>