From: Minchan Kim <minchan@kernel.org>
To: Michal Hocko <mhocko@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
"Kirill A. Shutemov" <kirill@shutemov.name>,
Johannes Weiner <hannes@cmpxchg.org>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: memcg uncharge page counter mismatch
Date: Thu, 3 Dec 2015 21:59:50 +0900 [thread overview]
Message-ID: <20151203125950.GA1428@bbox> (raw)
In-Reply-To: <20151203085451.GC9264@dhcp22.suse.cz>
On Thu, Dec 03, 2015 at 09:54:52AM +0100, Michal Hocko wrote:
> On Thu 03-12-15 11:10:06, Minchan Kim wrote:
> > On Thu, Dec 03, 2015 at 10:34:04AM +0900, Minchan Kim wrote:
> > > On Wed, Dec 02, 2015 at 11:16:43AM +0100, Michal Hocko wrote:
> > > > On Tue 01-12-15 22:34:55, Minchan Kim wrote:
> > > > > With new test on mmotm-2015-11-25-17-08, I saw below WARNING message
> > > > > several times. I couldn't see it with reverting new THP refcount
> > > > > redesign.
> > > >
> > > > Just a wild guess. What prevents migration/compaction from calling
> > > > split_huge_page on thp zero page? There is VM_BUG_ON but it is not clear
> > >
> > > I guess migration should work with LRU pages now but zero page couldn't
> > > stay there.
>
> Ahh, you are right. I have missed PageLRU check in isolate_migratepages_block
> pfn walker.
>
> > > > whether you run with CONFIG_DEBUG_VM enabled.
> > >
> > > I enabled VM_DEBUG_VM.
> > >
> > > >
> > > > Also, how big is the underflow?
> [...]
> > > nr_pages 293 new -324
> > > nr_pages 16 new -340
> > > nr_pages 342 new -91
> > > nr_pages 246 new -337
> > > nr_pages 15 new -352
> > > nr_pages 15 new -367
>
> They are quite large but that is not that surprising if we consider that
> we are batching many uncharges at once.
>
> > My guess is that it's related to new feature of Kirill's THP 'PageDoubleMap'
> > so a THP page could be mapped a pte but !pmd_trans_huge(*pmd) so memcg
> > precharge in move_charge should handle it?
>
> I am not familiar with the current state of THP after the rework
> unfortunately. So if I got you right then you are saying that
> pmd_trans_huge_lock fails to notice a THP so we will not charge it as
> THP and only charge one head page and then the tear down path will
> correctly recognize it as a THP and uncharge the full size, right?
Exactly.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2015-12-03 12:59 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-12-01 13:34 memcg uncharge page counter mismatch Minchan Kim
2015-12-02 10:16 ` Michal Hocko
2015-12-03 1:34 ` Minchan Kim
2015-12-03 2:10 ` Minchan Kim
2015-12-03 8:54 ` Michal Hocko
2015-12-03 12:59 ` Minchan Kim [this message]
2015-12-03 13:37 ` Michal Hocko
2015-12-03 13:43 ` Michal Hocko
2015-12-03 14:58 ` Michal Hocko
2015-12-03 15:47 ` Michal Hocko
2015-12-04 5:35 ` Minchan Kim
2015-12-04 8:52 ` Michal Hocko
2015-12-04 9:16 ` Minchan Kim
2015-12-04 9:58 ` Michal Hocko
2015-12-04 13:35 ` Minchan Kim
2015-12-04 16:01 ` Johannes Weiner
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20151203125950.GA1428@bbox \
--to=minchan@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=hannes@cmpxchg.org \
--cc=kirill@shutemov.name \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).