On Thu, 2009-06-11 at 18:09 +0300, Pekka Enberg wrote: > On Wed, 10 Jun 2009, Pekka Enberg wrote: > > > Aha, SLUB thinks the minimum order for 4096 is 1. I guess you have > > > CONFIG_SLUB_DEBUG enabled? If yes, something like to following should > > > help. Christoph, are you okay with this patch? > > On Thu, 2009-06-11 at 10:41 -0400, Christoph Lameter wrote: > > He likely has CONFIG_SLUB_DEBUG_ON set which enables debugging and thus > > needs more than the payload for metadata. > > Yup. I suspect a lot of people who are doing _testing_ enable that. If > you're unhappy with my patch (the get_order one which shouldn't affect > that many caches anyway), any suggestions how to fix this up? It seems > that the wireless stack at least does quite a few kmalloc(4096) > allocations. I think networking rounds up allocations, but it's not wireless per se. johannes
Attachment:
signature.asc
Description: This is a digitally signed message part
