Re: Huge memory takes too long time to initialize on 4TB ?

[Andrea Arcangeli <aarcange@redhat.com>]

Hi,

On Tue, May 22, 2012 at 08:38:04PM -0700, David Rientjes wrote:
> On Wed, 23 May 2012, ethan zhao wrote:
> 
> > Hi, aarcange
> > 
> >    When I boot kernel 2.6.39-100.6.1.el6uek.x86_64(actually 3.0.26)on
> > a 4TB memory machine, got following call trace,
> > That shows huge memory take too long time to initialize ? any help ?,
> > I compared the huge_memory.c code between 3.0.26 and the current
> > 3.2.x, no change.
> > 
> 
> This has nothing to do with mm/huge_memory.c, which is transparent 
> hugepages code, it's the lengthy iteration done for a very large 
> ZONE_NORMAL in setup_zone_migrate_reserve().  
> 
> This should be fixed by 938929f14cb5 ("mm: reduce the amount of work done 
> when updating min_free_kbytes") and was merged in 3.3.  Let us know if 
> there's still a problem after upgrading to either that or 3.4

I thought that was only a performance optimization, so if the oops is
generated by a timeout it can fix it, so good idea to try it. But a
timeout watchdog triggering exactly in spin_unlock sounds a bit
unlikely occurence, so I assumed too long time here meant "wait forever
because it crashed".