On Wed 30-04-14 16:25:39, Johannes Weiner wrote: > The root_mem_cgroup res_counter is never charged itself: there is no > limit at the root level anyway, and any statistics are generated on > demand by summing up the counters of all other cgroups. This was an > optimization to keep down costs on systems that don't create specific > cgroups, but with per-cpu charge caches the res_counter operations do > not even show up on in profiles anymore. Just remove it and simplify > the code.
It seems that only kmem and tcp thingy are left but those looks much harder and they are not directly related. root_mem_cgroup use also seems to be correct. I have to look at this closer and that will be no sooner than on Monday as I am off for the rest of the week. [...] -- Michal Hocko SUSE Labs -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
