Messages in this thread | | | Date | Wed, 5 Mar 2008 01:08:20 +0100 | From | Nick Piggin <> | Subject | Re: [rfc][patch 1/3] slub: fix small HWCACHE_ALIGN alignment |
| |
On Mon, Mar 03, 2008 at 01:32:54PM -0800, Christoph Lameter wrote: > On Mon, 3 Mar 2008, Pekka Enberg wrote: > > > Well, not my definition either but SLAB has guaranteed that for small > > objects in the past, so I think Nick has a point here. However, with > > all this back and forth, I've lost track why this matters. I suppose > > it causes regression on some workload? > > Well the guarantee can only be exploited if you would check the cacheline > sizes and the object size from the code that creates the slab cache. > Basically you would have to guestimate what the slab allocator is doing. > > So the guarantee is basically meaningless. If the object is larger than a > cacheline then this will never work.
Of course it works. It fits the object into the fewest number of cachelines possible. If you need to be accessing such objects in a random manner, then for highest performance you want to touch as few cachelines as possible.
| |