Re: [PATCH 2/2] SLUB: Disable debugging if it increases the minimum page order

[Mel Gorman <mel@csn.ul.ie>]

On Thu, Jun 11, 2009 at 11:49:19AM -0400, Christoph Lameter wrote:
> On Thu, 11 Jun 2009, Pekka Enberg wrote:
> 
> > My main point is that a lot of _testers_ will probably enable all SLUB
> > debugging by default because we encourage them to and it's pretty bad
> > that we end up causing order 1 allocations and oom conditions.
> 
> Other test methods (like PAGE_ALLOC debugging) also have significant side
> effects.
> 

True, but they come with huge big warnings and I agree that we don't want
to make the SL*B debug warning too drastic, particularly because SL*B
debugging is often so valuable and relatively lightweight in comparison
to some debug options.


> > So I still think we need to fix _at minimum_ the kmalloc-4096 case
> > (assuming Larry won't hit the same problem still). I see you're not
> > happy with my patch so any suggestions how to handle that?
> 
> Add a warning to Kconfig that the higher order page allocations may
> increase with debugging on for caches with object sizes near or equal to
> PAGE_SIZE?
> 

Possibly clueless suggestion here. How possible would it be to implement
something like

"With SLUB_DEBUG, enable debug on all caches unless the increased meta-data
would force the minimum order up on order due to object sizes being near or
equal the PAGE_SIZE. If SLUB_DEBUG must be enabled, specify slub_debug=A for
'All caches enable debug regardless'"

?

> Its good to run with full debugging on for even the 4k sized caches.
> Otherwise we wont be catching overruns there. But the debugging can cause
> some side effects.
> 

-- 
Mel Gorman
Part-time Phd Student                          Linux Technology Center
University of Limerick                         IBM Dublin Software Lab