On Tue 04-06-13 18:10:59, Glauber Costa wrote: > The memory we used to hold the memcg arrays is currently accounted to > the current memcg. Maybe I have missed a train but I thought that only some caches are tracked and those have to be enabled explicitly by using __GFP_KMEMCG in gfp flags. But d79923fa "sl[au]b: allocate objects from memcg cache" seems to be setting gfp unconditionally for large caches. The changelog doesn't explain why, though? This is really confusing. > But that creates a problem, because that memory can > only be freed after the last user is gone. Our only way to know which is > the last user, is to hook up to freeing time, but the fact that we still > have some in flight kmallocs will prevent freeing to happen. I believe > therefore to be just easier to account this memory as global overhead. No internal allocations for memcg can be tracked otherwise we call for a problem. How do we know that others are safe? > Signed-off-by: Glauber Costa <glommer@xxxxxxxxxx> > Cc: Johannes Weiner <hannes@xxxxxxxxxxx> > Cc: Michal Hocko <mhocko@xxxxxxx> > Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> > > --- > I noticed this while testing nuances of the shrinker patches. The > caches would basically stay present forever, even if we managed to > flush all of the actual memory being used. With this patch applied, > they would go away all right. > --- > mm/memcontrol.c | 2 ++ > 1 file changed, 2 insertions(+) > > diff --git a/mm/memcontrol.c b/mm/memcontrol.c > index 5d8b93a..aa1cbd4 100644 > --- a/mm/memcontrol.c > +++ b/mm/memcontrol.c > @@ -5642,7 +5642,9 @@ static int memcg_propagate_kmem(struct mem_cgroup *memcg) > static_key_slow_inc(&memcg_kmem_enabled_key); > > mutex_lock(&set_limit_mutex); > + memcg_stop_kmem_account(); > ret = memcg_update_cache_sizes(memcg); > + memcg_resume_kmem_account(); > mutex_unlock(&set_limit_mutex); > out: > return ret; > -- > 1.8.1.4 > > -- > 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> -- Michal Hocko SUSE Labs -- To unsubscribe from this list: send the line "unsubscribe cgroups" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
