From: Arjan van de Ven <arjan@infradead.org>
To: Mikulas Patocka <mpatocka@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org, agk@redhat.com, mbroz@redhat.com,
chris@arachsys.com
Subject: Re: [PATCH 2/3] Fix fsync livelock
Date: Sun, 5 Oct 2008 15:33:06 -0700 [thread overview]
Message-ID: <20081005153306.7e644c9f@infradead.org> (raw)
In-Reply-To: <Pine.LNX.4.64.0810051814060.23248@hs20-bc2-1.build.redhat.com>
On Sun, 5 Oct 2008 18:14:50 -0400 (EDT)
Mikulas Patocka <mpatocka@redhat.com> wrote:
> Fix starvation in memory management.
>
> The bug happens when one process is doing sequential buffered writes
> to a block device (or file) and another process is attempting to
> execute sync(), fsync() or direct-IO on that device (or file). This
> syncing process will wait indefinitelly, until the first writing
> process finishes.
>
> For example, run these two commands:
> dd if=/dev/zero of=/dev/sda1 bs=65536 &
> dd if=/dev/sda1 of=/dev/null bs=4096 count=1 iflag=direct
>
> The bug is caused by sequential walking of address space in
> write_cache_pages and wait_on_page_writeback_range: if some other
> process is constantly making dirty and writeback pages while these
> functions run, the functions will wait on every new page, resulting in
> indefinite wait.
are you sure?
isn't the right fix to just walk the file pages only once?
next prev parent reply other threads:[~2008-10-05 22:33 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20080911101616.GA24064@agk.fab.redhat.com>
2008-09-22 21:10 ` [PATCH] Memory management livelock Mikulas Patocka
2008-09-23 0:48 ` Andrew Morton
2008-09-23 22:34 ` Mikulas Patocka
2008-09-23 22:49 ` Andrew Morton
2008-09-23 23:11 ` Mikulas Patocka
2008-09-23 23:46 ` Andrew Morton
2008-09-24 18:50 ` Mikulas Patocka
2008-09-24 18:51 ` [PATCH 1/3] " Mikulas Patocka
2008-09-24 18:52 ` [PATCH 2/3] " Mikulas Patocka
2008-10-02 5:54 ` Andrew Morton
2008-10-05 22:11 ` RFC: one-bit mutexes (was: Re: [PATCH 2/3] Memory management livelock) Mikulas Patocka
2008-10-11 12:06 ` Nick Piggin
2008-10-20 20:14 ` Mikulas Patocka
2008-10-21 1:51 ` Nick Piggin
2008-10-05 22:14 ` [PATCH 1/3] bit mutexes Mikulas Patocka
2008-10-05 22:14 ` [PATCH 2/3] Fix fsync livelock Mikulas Patocka
2008-10-05 22:33 ` Arjan van de Ven [this message]
2008-10-05 23:02 ` Mikulas Patocka
2008-10-05 23:07 ` Arjan van de Ven
2008-10-05 23:18 ` Mikulas Patocka
2008-10-05 23:28 ` Arjan van de Ven
2008-10-06 0:01 ` Mikulas Patocka
2008-10-06 0:30 ` Arjan van de Ven
2008-10-06 3:30 ` Mikulas Patocka
2008-10-06 4:20 ` Arjan van de Ven
2008-10-06 13:00 ` Mikulas Patocka
2008-10-06 13:50 ` Arjan van de Ven
2008-10-06 20:44 ` Mikulas Patocka
2008-10-08 10:56 ` Pavel Machek
2008-10-06 2:51 ` Dave Chinner
2008-10-05 22:16 ` [PATCH 3/3] Fix fsync-vs-write misbehavior Mikulas Patocka
2008-10-09 1:12 ` [PATCH] documentation: explain memory barriers Randy Dunlap
2008-10-09 1:17 ` Chris Snook
2008-10-09 1:31 ` Andrew Morton
2008-10-09 5:51 ` Chris Snook
2008-10-09 9:58 ` Ben Hutchings
2008-10-09 21:27 ` Nick Piggin
2008-10-09 17:29 ` Nick Piggin
2008-10-09 1:50 ` Valdis.Kletnieks
2008-10-09 17:35 ` Nick Piggin
2008-10-09 6:52 ` Valdis.Kletnieks
2008-09-24 18:53 ` [PATCH 3/3] Memory management livelock Mikulas Patocka
2008-10-03 2:32 ` [PATCH] " Nick Piggin
2008-10-03 2:40 ` Andrew Morton
2008-10-03 2:59 ` Nick Piggin
2008-10-03 3:14 ` Andrew Morton
2008-10-03 3:47 ` Nick Piggin
2008-10-03 3:56 ` Andrew Morton
2008-10-03 4:07 ` Nick Piggin
2008-10-03 4:17 ` Andrew Morton
2008-10-03 4:29 ` Nick Piggin
2008-10-03 11:43 ` Mikulas Patocka
2008-10-03 12:27 ` Nick Piggin
2008-10-03 13:53 ` Mikulas Patocka
2008-10-03 2:54 ` Nick Piggin
2008-10-03 11:26 ` Mikulas Patocka
2008-10-03 12:31 ` Nick Piggin
2008-10-03 13:50 ` Mikulas Patocka
2008-10-03 14:50 ` Alasdair G Kergon
2008-10-03 14:36 ` Alasdair G Kergon
2008-10-03 15:52 ` application syncing options (was Re: [PATCH] Memory management livelock) david
2008-10-06 0:04 ` Mikulas Patocka
2008-10-06 0:19 ` david
2008-10-06 3:42 ` Mikulas Patocka
2008-10-07 3:37 ` david
2008-10-07 15:44 ` Mikulas Patocka
2008-10-07 17:16 ` david
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=20081005153306.7e644c9f@infradead.org \
--to=arjan@infradead.org \
--cc=agk@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=chris@arachsys.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mbroz@redhat.com \
--cc=mpatocka@redhat.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 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.