[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20171004141620.37qojkpftpmpgmxj@node.shutemov.name>
Date: Wed, 4 Oct 2017 17:16:20 +0300
From: "Kirill A. Shutemov" <kirill@...temov.name>
To: Michal Hocko <mhocko@...nel.org>
Cc: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
Andrew Morton <akpm@...ux-foundation.org>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org, Vlastimil Babka <vbabka@...e.cz>
Subject: Re: [PATCHv3] mm: Account pud page tables
On Wed, Oct 04, 2017 at 03:48:53PM +0200, Michal Hocko wrote:
> On Mon 02-10-17 11:04:27, Kirill A. Shutemov wrote:
> > On machine with 5-level paging support a process can allocate
> > significant amount of memory and stay unnoticed by oom-killer and
> > memory cgroup. The trick is to allocate a lot of PUD page tables.
> > We don't account PUD page tables, only PMD and PTE.
> >
> > We already addressed the same issue for PMD page tables, see
> > dc6c9a35b66b ("mm: account pmd page tables to the process").
> > Introduction 5-level paging bring the same issue for PUD page tables.
> >
> > The patch expands accounting to PUD level.
>
> Can we skip the VmPUD part and reporting puds in the oom report please?
> I would like to consolidate all levels into a single counter and carying
> about one less user visible change will make it slightly easier. Or does
> anybody need this exported to the userspace?
Let me do this as a separate patch. I will also fold VmPMD into VmPTE.
--
Kirill A. Shutemov
Powered by blists - more mailing lists