The memory we used to hold the memcg arrays is currently accounted to the current memcg. 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. >From my last submission, Michal rightfully noted that this will break when SLUB is used and allocations are big enough, since those will bypass the cache mechanism and go directly to the page allocator. To fix this, we need an extra patch that instructs the memcg kmem page charging to check the bypass flag as well. Glauber Costa (2): memcg: also test for skip accounting at the page allocation level memcg: do not account memory used for cache creation mm/memcontrol.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) -- 1.8.2.1 -- 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>