From: Andy Lutomirski <luto@amacapital.net>
To: Michel Lespinasse <walken@google.com>
Cc: Ingo Molnar <mingo@kernel.org>, Al Viro <viro@zeniv.linux.org.uk>,
Hugh Dickins <hughd@google.com>, Jorn_Engel <joern@logfs.org>,
Rik van Riel <riel@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH 0/9] Avoid populating unbounded num of ptes with mmap_sem held
Date: Fri, 4 Jan 2013 10:16:21 -0800 [thread overview]
Message-ID: <CALCETrVGvfm2VHUaVNDg40U4dbsRmriW7GfRnfpHGihG9v1=Uw@mail.gmail.com> (raw)
In-Reply-To: <1356050997-2688-1-git-send-email-walken@google.com>
On Thu, Dec 20, 2012 at 4:49 PM, Michel Lespinasse <walken@google.com> wrote:
> We have many vma manipulation functions that are fast in the typical case,
> but can optionally be instructed to populate an unbounded number of ptes
> within the region they work on:
> - mmap with MAP_POPULATE or MAP_LOCKED flags;
> - remap_file_pages() with MAP_NONBLOCK not set or when working on a
> VM_LOCKED vma;
> - mmap_region() and all its wrappers when mlock(MCL_FUTURE) is in effect;
> - brk() when mlock(MCL_FUTURE) is in effect.
>
> Current code handles these pte operations locally, while the sourrounding
> code has to hold the mmap_sem write side since it's manipulating vmas.
> This means we're doing an unbounded amount of pte population work with
> mmap_sem held, and this causes problems as Andy Lutomirski reported
> (we've hit this at Google as well, though it's not entirely clear why
> people keep trying to use mlock(MCL_FUTURE) in the first place).
>
> I propose introducing a new mm_populate() function to do this pte
> population work after the mmap_sem has been released. mm_populate()
> does need to acquire the mmap_sem read side, but critically, it
> doesn't need to hold continuously for the entire duration of the
> operation - it can drop it whenever things take too long (such as when
> hitting disk for a file read) and re-acquire it later on.
>
I still have quite a few instances of 2-6 ms of latency due to
"call_rwsem_down_read_failed __do_page_fault do_page_fault
page_fault". Any idea why? I don't know any great way to figure out
who is holding mmap_sem at the time. Given what my code is doing, I
suspect the contention is due to mmap or munmap on a file. MCL_FUTURE
is set, and MAP_POPULATE is not set.
It could be the other thread calling mmap and getting preempted (or
otherwise calling schedule()). Grr.
--Andy
--
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:[~2013-01-04 18:16 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-12-21 0:49 Michel Lespinasse
2012-12-21 0:49 ` [PATCH 1/9] mm: make mlockall preserve flags other than VM_LOCKED in def_flags Michel Lespinasse
2012-12-22 4:25 ` Rik van Riel
2012-12-21 0:49 ` [PATCH 2/9] mm: remap_file_pages() fixes Michel Lespinasse
2013-01-03 0:31 ` Rik van Riel
2012-12-21 0:49 ` [PATCH 3/9] mm: introduce mm_populate() for populating new vmas Michel Lespinasse
2013-01-03 2:14 ` Rik van Riel
2012-12-21 0:49 ` [PATCH 4/9] mm: use mm_populate() for blocking remap_file_pages() Michel Lespinasse
2013-01-03 2:25 ` Rik van Riel
2013-03-10 18:55 ` Tommi Rantala
2013-03-11 23:03 ` Andrew Morton
2013-03-12 0:24 ` Michel Lespinasse
2013-03-12 4:23 ` Hillf Danton
2013-03-12 5:01 ` Michel Lespinasse
2013-03-12 20:47 ` Andrew Morton
2012-12-21 0:49 ` [PATCH 5/9] mm: use mm_populate() when adjusting brk with MCL_FUTURE in effect Michel Lespinasse
2013-01-03 2:56 ` Rik van Riel
2012-12-21 0:49 ` [PATCH 6/9] mm: use mm_populate() for mremap() of VM_LOCKED vmas Michel Lespinasse
2013-01-03 5:47 ` Rik van Riel
2012-12-21 0:49 ` [PATCH 7/9] mm: remove flags argument to mmap_region Michel Lespinasse
2013-01-03 5:49 ` Rik van Riel
2012-12-21 0:49 ` [PATCH 8/9] mm: directly use __mlock_vma_pages_range() in find_extend_vma() Michel Lespinasse
2013-01-03 5:50 ` Rik van Riel
2012-12-21 0:49 ` [PATCH 9/9] mm: introduce VM_POPULATE flag to better deal with racy userspace programs Michel Lespinasse
2013-01-03 6:20 ` Rik van Riel
2012-12-21 10:46 ` [PATCH 0/9] Avoid populating unbounded num of ptes with mmap_sem held Michel Lespinasse
2012-12-22 15:02 ` Greg Ungerer
2013-01-23 13:37 ` Greg Ungerer
2012-12-22 0:36 ` Andy Lutomirski
2012-12-22 0:59 ` Michel Lespinasse
2012-12-22 1:09 ` Andy Lutomirski
2012-12-22 1:59 ` Michel Lespinasse
2012-12-22 2:16 ` Andy Lutomirski
2012-12-22 9:37 ` Michel Lespinasse
2012-12-22 9:45 ` [PATCH 10/9] mm: make do_mmap_pgoff return populate as a size in bytes, not as a bool Michel Lespinasse
2013-01-03 6:21 ` Rik van Riel
2013-01-03 18:54 ` Andy Lutomirski
2013-01-03 18:56 ` [PATCH 0/9] Avoid populating unbounded num of ptes with mmap_sem held Andy Lutomirski
2013-01-04 18:16 ` Andy Lutomirski [this message]
2013-01-04 22:58 ` Michel Lespinasse
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='CALCETrVGvfm2VHUaVNDg40U4dbsRmriW7GfRnfpHGihG9v1=Uw@mail.gmail.com' \
--to=luto@amacapital.net \
--cc=akpm@linux-foundation.org \
--cc=hughd@google.com \
--cc=joern@logfs.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mingo@kernel.org \
--cc=riel@redhat.com \
--cc=viro@zeniv.linux.org.uk \
--cc=walken@google.com \
/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