All of lore.kernel.org
 help / color / mirror / Atom feed
From: Dave Jones <davej@redhat.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Linux Kernel <linux-kernel@vger.kernel.org>,
	linux-mm@kvack.org,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Sasha Levin <sasha.levin@oracle.com>,
	Cyrill Gorcunov <gorcunov@gmail.com>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	Wanpeng Li <liwanp@linux.vnet.ibm.com>,
	Bob Liu <bob.liu@oracle.com>,
	Konstantin Khlebnikov <koct9i@gmail.com>
Subject: Re: bad rss-counter message in 3.14rc5
Date: Tue, 11 Mar 2014 01:07:52 -0400	[thread overview]
Message-ID: <20140311050752.GA14329@redhat.com> (raw)
In-Reply-To: <20140310220158.7e8b7f2a.akpm@linux-foundation.org>

On Mon, Mar 10, 2014 at 10:01:58PM -0700, Andrew Morton wrote:
 > On Tue, 11 Mar 2014 00:51:09 -0400 Dave Jones <davej@redhat.com> wrote:
 > 
 > > On Mon, Mar 10, 2014 at 09:46:12PM -0700, Andrew Morton wrote:
 > >  > On Mon, 10 Mar 2014 20:13:40 -0700 Andrew Morton <akpm@linux-foundation.org> wrote:
 > >  > 
 > >  > > > Anyone ? I'm hitting this trace on an almost daily basis, which is a pain
 > >  > > > while trying to reproduce a different bug..
 > >  > > 
 > >  > > Damn, I thought we'd fixed that but it seems not.  Cc's added.
 > >  > > 
 > >  > > Guys, what stops the migration target page from coming unlocked in
 > >  > > parallel with zap_pte_range()'s call to migration_entry_to_page()?
 > >  > 
 > >  > page_table_lock, sort-of.  At least, transitions of is_migration_entry()
 > >  > and page_locked() happen under ptl.
 > >  > 
 > >  > I don't see any holes in regular migration.  Do you know if this is
 > >  > reproducible with CONFIG_NUMA_BALANCING=n or CONFIG_NUMA=n?
 > > 
 > > CONFIG_NUMA_BALANCING was n already btw, so I'll do a NUMA=n run.
 > 
 > There probably isn't much point unless trinity is using
 > sys_move_pages().  Is it?

Trinity will do every syscall an arch has.

In the test case I have so far, I've narrowed it down to the vm group of syscalls
(so running with '-g vm' will do anything that I deemed 'vm'. Including.. sys_move_pages)
I'll try to narrow it down further tomorrow.

 >  If so it would be interesting to disable
 > trinity's move_pages calls and see if it still fails.
 
Ok, I'll try that first.

 > Grasping at straws here, trying to reduce the amount of code to look at :(

*nod*, it's not helped by the fact that the trace happens at process exit time
which could be considerably later after the syscall that buggers everything up
has happened.

	Dave

--
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>

WARNING: multiple messages have this Message-ID (diff)
From: Dave Jones <davej@redhat.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Linux Kernel <linux-kernel@vger.kernel.org>,
	linux-mm@kvack.org,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Sasha Levin <sasha.levin@oracle.com>,
	Cyrill Gorcunov <gorcunov@gmail.com>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	Wanpeng Li <liwanp@linux.vnet.ibm.com>,
	Bob Liu <bob.liu@oracle.com>,
	Konstantin Khlebnikov <koct9i@gmail.com>
Subject: Re: bad rss-counter message in 3.14rc5
Date: Tue, 11 Mar 2014 01:07:52 -0400	[thread overview]
Message-ID: <20140311050752.GA14329@redhat.com> (raw)
In-Reply-To: <20140310220158.7e8b7f2a.akpm@linux-foundation.org>

On Mon, Mar 10, 2014 at 10:01:58PM -0700, Andrew Morton wrote:
 > On Tue, 11 Mar 2014 00:51:09 -0400 Dave Jones <davej@redhat.com> wrote:
 > 
 > > On Mon, Mar 10, 2014 at 09:46:12PM -0700, Andrew Morton wrote:
 > >  > On Mon, 10 Mar 2014 20:13:40 -0700 Andrew Morton <akpm@linux-foundation.org> wrote:
 > >  > 
 > >  > > > Anyone ? I'm hitting this trace on an almost daily basis, which is a pain
 > >  > > > while trying to reproduce a different bug..
 > >  > > 
 > >  > > Damn, I thought we'd fixed that but it seems not.  Cc's added.
 > >  > > 
 > >  > > Guys, what stops the migration target page from coming unlocked in
 > >  > > parallel with zap_pte_range()'s call to migration_entry_to_page()?
 > >  > 
 > >  > page_table_lock, sort-of.  At least, transitions of is_migration_entry()
 > >  > and page_locked() happen under ptl.
 > >  > 
 > >  > I don't see any holes in regular migration.  Do you know if this is
 > >  > reproducible with CONFIG_NUMA_BALANCING=n or CONFIG_NUMA=n?
 > > 
 > > CONFIG_NUMA_BALANCING was n already btw, so I'll do a NUMA=n run.
 > 
 > There probably isn't much point unless trinity is using
 > sys_move_pages().  Is it?

Trinity will do every syscall an arch has.

In the test case I have so far, I've narrowed it down to the vm group of syscalls
(so running with '-g vm' will do anything that I deemed 'vm'. Including.. sys_move_pages)
I'll try to narrow it down further tomorrow.

 >  If so it would be interesting to disable
 > trinity's move_pages calls and see if it still fails.
 
Ok, I'll try that first.

 > Grasping at straws here, trying to reduce the amount of code to look at :(

*nod*, it's not helped by the fact that the trace happens at process exit time
which could be considerably later after the syscall that buggers everything up
has happened.

	Dave


  reply	other threads:[~2014-03-11  5:08 UTC|newest]

Thread overview: 82+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-03-05 17:45 bad rss-counter message in 3.14rc5 Dave Jones
2014-03-05 17:45 ` Dave Jones
2014-03-05 17:57 ` Dave Jones
2014-03-05 17:57   ` Dave Jones
2014-03-07  0:22   ` Dave Jones
2014-03-07  0:22     ` Dave Jones
2014-03-11  2:49     ` Dave Jones
2014-03-11  2:49       ` Dave Jones
2014-03-11  3:13       ` Andrew Morton
2014-03-11  3:13         ` Andrew Morton
2014-03-11  4:46         ` Andrew Morton
2014-03-11  4:46           ` Andrew Morton
2014-03-11  4:50           ` Dave Jones
2014-03-11  4:50             ` Dave Jones
2014-03-11  4:51           ` Dave Jones
2014-03-11  4:51             ` Dave Jones
2014-03-11  5:01             ` Andrew Morton
2014-03-11  5:01               ` Andrew Morton
2014-03-11  5:07               ` Dave Jones [this message]
2014-03-11  5:07                 ` Dave Jones
2014-03-11  5:30               ` Dave Jones
2014-03-11  5:30                 ` Dave Jones
2014-03-11 12:55                 ` Sasha Levin
2014-03-11 12:55                   ` Sasha Levin
2014-03-11 13:20                 ` Cyrill Gorcunov
2014-03-11 13:20                   ` Cyrill Gorcunov
2014-03-11 13:23                   ` Sasha Levin
2014-03-11 13:23                     ` Sasha Levin
2014-03-11 13:41                     ` Cyrill Gorcunov
2014-03-11 13:41                       ` Cyrill Gorcunov
2014-03-11 14:28                       ` Dave Jones
2014-03-11 14:28                         ` Dave Jones
2014-03-11 14:37                         ` Cyrill Gorcunov
2014-03-11 14:37                           ` Cyrill Gorcunov
2014-03-11 14:58                           ` Sasha Levin
2014-03-11 14:58                             ` Sasha Levin
2014-03-11 17:10                           ` Dave Jones
2014-03-11 17:10                             ` Dave Jones
2014-03-11 17:36                             ` Cyrill Gorcunov
2014-03-11 17:36                               ` Cyrill Gorcunov
2014-03-11 17:39                               ` Dave Jones
2014-03-11 17:39                                 ` Dave Jones
2014-03-14 12:27                                 ` Cyrill Gorcunov
2014-03-14 12:27                                   ` Cyrill Gorcunov
2014-03-19  0:38                                 ` Hugh Dickins
2014-03-19  0:38                                   ` Hugh Dickins
2014-03-19  1:10                                   ` Linus Torvalds
2014-03-19  1:10                                     ` Linus Torvalds
2014-03-19  2:06                                     ` Hugh Dickins
2014-03-19  2:06                                       ` Hugh Dickins
2014-03-19  2:24                                       ` Linus Torvalds
2014-03-19  2:24                                         ` Linus Torvalds
2014-03-19  2:37                                         ` Hugh Dickins
2014-03-19  2:37                                           ` Hugh Dickins
2014-03-19  2:57                                           ` Linus Torvalds
2014-03-19  2:57                                             ` Linus Torvalds
2014-03-19 11:04                                           ` Jan Kara
2014-03-19 11:04                                             ` Jan Kara
2014-03-19  1:32                                   ` Sasha Levin
2014-03-19  1:32                                     ` Sasha Levin
2014-03-19  2:06                                     ` Dave Jones
2014-03-19  2:06                                       ` Dave Jones
2014-03-19  2:11                                       ` Dave Jones
2014-03-19  2:11                                         ` Dave Jones
2014-03-19  2:19                                         ` Hugh Dickins
2014-03-19  2:19                                           ` Hugh Dickins
2014-03-19 14:52                                           ` Dave Jones
2014-03-19 14:52                                             ` Dave Jones
2014-03-20  5:00                                             ` Hugh Dickins
2014-03-20  5:00                                               ` Hugh Dickins
2014-03-20 13:51                                               ` Dave Jones
2014-03-20 13:51                                                 ` Dave Jones
2014-03-20 14:19                                                 ` Sasha Levin
2014-03-20 14:19                                                   ` Sasha Levin
2014-03-21  4:46                                                   ` Hugh Dickins
2014-03-21  4:46                                                     ` Hugh Dickins
2014-03-19  2:12                                     ` Hugh Dickins
2014-03-19  2:12                                       ` Hugh Dickins
2014-03-19  2:42                                       ` Sasha Levin
2014-03-19  2:42                                         ` Sasha Levin
2014-03-19 12:04                                   ` Cyrill Gorcunov
2014-03-19 12:04                                     ` Cyrill Gorcunov

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=20140311050752.GA14329@redhat.com \
    --to=davej@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=bob.liu@oracle.com \
    --cc=gorcunov@gmail.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=koct9i@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=liwanp@linux.vnet.ibm.com \
    --cc=sasha.levin@oracle.com \
    --cc=torvalds@linux-foundation.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.