On Mon, 09 May 2011 21:27:28 -0400 Rik van Riel <riel@xxxxxxxxxx> wrote: > On 05/09/2011 09:26 PM, Andrew Morton wrote: > > On Tue, 10 May 2011 02:05:17 +0200 Andi Kleen<andi@xxxxxxxxxxxxxx> wrote: > > > >>> hm, which atomic ops are those? We shouldn't need buslocked operations > >>> on UP. > >> > >> Good point. I forgot they're patched out. > >> > >> Then it's likely somewhat slower, but I doubt it's a significant > >> slowdown. Essentially it's just a few more if ()s > > > > And presumably some more instruction cachelines here and there. It'll > > be small, but 100*small == large. We can reduce the overhead to zero, > > it's a question of how ugly the end result is. > > More instruction cachelines, but fewer pointer dereferences > due to not looking up the lock all the time (if the root > anon_vma is the same). > Why would we be looking up a lock which doesn't exist? -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxxx 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>