On Tue, Oct 14, 2014 at 05:56:47PM +0200, Michal Hocko wrote: > On Mon 13-10-14 21:46:01, Johannes Weiner wrote: > > Memory is internally accounted in bytes, using spinlock-protected > > 64-bit counters, even though the smallest accounting delta is a page. > > The counter interface is also convoluted and does too many things. > > > > Introduce a new lockless word-sized page counter API, then change all > > memory accounting over to it. The translation from and to bytes then > > only happens when interfacing with userspace. > > > > The removed locking overhead is noticable when scaling beyond the > > per-cpu charge caches - on a 4-socket machine with 144-threads, the > > following test shows the performance differences of 288 memcgs > > concurrently running a page fault benchmark: > > I assume you had root.use_hierarchy = 1, right? Processes wouldn't bounce > on the same lock otherwise. Yep. That's already the default on most distros, and will be in the kernel in unified hierarchy. > > Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx> > > You have only missed MAINTAINERS... Hm, we can add it, but then again scripts/get_maintainer.pl should already do the right thing. I find myself using it with --git all the time to find the people that actually worked on the code recently, not just the ones listed in there - which might be stale information. > Acked-by: Michal Hocko <mhocko@xxxxxxx> Thank you, Michal! -- 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/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>