On Wed, 14 Dec 2011, Pekka Enberg wrote: > On Wed, 14 Dec 2011, Eric Dumazet wrote: > > We should try to batch things a bit, instead of doing a very small unit > > of work in slow path. > > > > We now have a very fast fastpath, but inefficient slow path. > > > > SLAB has a litle cache per cpu, we could add one to SLUB for freed > > objects, not belonging to current slab. This could avoid all these > > activate/deactivate overhead. > > Yeah, this is definitely worth looking at. We have been down this road repeatedly. Nick tried it, I tried it and neither got us to something we liked. Please consult the archives. There was a whole patch series last year that I did introducing per cpu caches which ended up in the "unified" patches. See the archives for the various attempts please. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>