Re: 2.6.5-rc1-mm2

[Jesse Barnes <jbarnes@sgi.com>]

On Wednesday 31 March 2004 3:56 pm, Andrew Morton wrote:
> Jesse Barnes <jbarnes@sgi.com> wrote:
> > On Wednesday 31 March 2004 12:06 pm, Andrew Morton wrote:
> > > So are we to assume that this is the offending process?  That the
> > > periodic slab reaping code has screwed up?
> >
> > It looks like it.  Disabling the slab cache reaping function allows it to
> > boot again.
>
> I suspect that the reap timer is innocent and what we have is simply
> scribbled-on slab metadata.  Which means it could be anything at all.

That's what I thought too, I'm trying to track down exactly which slab is 
having problems now.

>
> One last thing: could you please stick a
>
> 	printk(KERN_EMERG "destroying slab %s\n", cachep->name);

I'm already booting up something similar...

> at the start of slab_destroy()?  That'll help narrow it down.
>
> Could you also punt me over the .config?  If I can make it happen, the
> binary search will find it.  But it probably won't happen here.

I'm using sn2_defconfig in arch/ia64/configs.

Thanks,
Jesse