On Tue, 2009-06-30 at 11:06 +0200, Nick Piggin wrote: > > > Finally, if KMALLOC_SHIFT_SLQB_HIGH is larger than 2MB, then kmalloc_index > > > could silently run off the end of its precomputed table and return a -1 > > > index into the kmalloc slab array, which could result in corruption. Extend > > > this to allow up to 32MB (to match SLAB), and add a compile-time error in > > > the case that the table is exceeded (also like SLAB). On Tue, Jun 30, 2009 at 12:20:10PM +0300, Pekka Enberg wrote: > > I wonder if SLQB should just do page allocator pass-through for really > > big allocations? That way callers don't need to worry about whether > > they're running under SLAB/SLUB/SLOB/SQLB. On Tue, 2009-06-30 at 11:27 +0200, Nick Piggin wrote: > Well it could, OTOH it should be pretty well in line with SLAB > after this patch so I don't see much need. True. But with page allocator fall-through, we don't need to bump up slab limit to 32 MB (which is pretty damn big IMHO). Anyway, up to you, really. Pekka -- To unsubscribe from this list: send the line "unsubscribe linux-next" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
