Re: [PATCH v5 07/14] mm: Allocate kernel pages to the right memcg

On Thu, 18 Oct 2012 13:24:47 +0400
Glauber Costa [off-list ref] wrote:

On 10/18/2012 02:12 AM, Andrew Morton wrote:

quoted

On Tue, 16 Oct 2012 14:16:44 +0400
Glauber Costa [off-list ref] wrote:

quoted

When a process tries to allocate a page with the __GFP_KMEMCG flag, the
page allocator will call the corresponding memcg functions to validate
the allocation. Tasks in the root memcg can always proceed.

To avoid adding markers to the page - and a kmem flag that would
necessarily follow, as much as doing page_cgroup lookups for no reason,
whoever is marking its allocations with __GFP_KMEMCG flag is responsible
for telling the page allocator that this is such an allocation at
free_pages() time.

Well, why?  Was that the correct decision?

I don't fully understand your question. Is this the same question you
posed in patch 0, about marking some versus marking all? If so, I
believe I should have answered it there.

Yes, it's the same question.  The one which has not yet been fully answered ;)