From: Jan Kara <jack@suse.cz>
To: Jan Engelhardt <jengelh@medozas.de>
Cc: Jan Kara <jack@suse.cz>,
Andrew Morton <akpm@linux-foundation.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
Jens Axboe <jens.axboe@oracle.com>,
Linux Kernel <linux-kernel@vger.kernel.org>,
stable@kernel.org, gregkh@suse.de
Subject: Re: Sync writeback still broken
Date: Fri, 21 Jan 2011 16:09:02 +0100 [thread overview]
Message-ID: <20110121150902.GF5302@quack.suse.cz> (raw)
In-Reply-To: <alpine.LNX.2.01.1101202344170.26671@obet.zrqbmnf.qr>
Hi,
On Thu 20-01-11 23:50:36, Jan Engelhardt wrote:
> On Friday 2010-11-05 23:03, Jan Engelhardt wrote:
> >On Friday 2010-11-05 22:33, Jan Kara wrote:
> >> OK, so at Kernel Summit we agreed to fix the issue as I originally wanted
> >>by patches
> >>http://marc.info/?l=linux-fsdevel&m=128861735213143&w=2
> >>and
> >>http://marc.info/?l=linux-fsdevel&m=128861734813131&w=2
> >>
> >> I needed one more patch to resolve the issue (attached) which I've just
> >>posted for review and possible inclusion.
> >
> >If you have a branch that has all three and is easy to fetch, I'll
> >get on it right away.
>
> I tested these now [2.6.37-rc1+yourpatches].
>
> Within the last 13 days of uptime, the following messages have
> accumulated, however the machine is still alive, so I guess it's
> fine. (I see Andrew merged the patches already, so if it becomes
> a problem again I will notice it within the next kernel releases.)
Thanks for an update :) I went through the messages bellow and there
are no signs of bdi-writeout causing any problems. Apparently your disk
is rather busy (maybe in combination with suboptiomal IO scheduling
decisions?) since I could attribute all the reports to waiting for an
IO on a buffer to finish.
Honza
> INFO: task flush-259:0:324 blocked for more than 120
> seconds.
> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
> message.
> flush-259:0 D 00000000005a3d38 0 324 2 0x18000000000
> Call Trace:
> [00000000005a39c4] do_get_write_access+0x244/0x480
> [00000000005a3d38] jbd2_journal_get_write_access+0x18/0x40
> [0000000000591278] __ext4_journal_get_write_access+0x18/0x60
> [0000000000572a94] ext4_reserve_inode_write+0x54/0xa0
> [0000000000572afc] ext4_mark_inode_dirty+0x1c/0x1e0
> [000000000058ba98] ext4_ext_insert_extent+0x718/0x17a0
> [000000000058f2d4] ext4_ext_map_blocks+0x9f4/0x12c0
> [00000000005742f4] ext4_map_blocks+0x1b4/0x240
> [0000000000576864] mpage_da_map_and_submit+0x84/0x420
> [0000000000576f5c] write_cache_pages_da+0x27c/0x3e0
> [00000000005772f8] ext4_da_writepages+0x238/0x4a0
> [00000000004cc7a4] do_writepages+0x24/0x60
> [0000000000525264] writeback_single_inode+0x84/0x240
> [00000000005258d8] writeback_sb_inodes+0x98/0x140
> [0000000000525f44] writeback_inodes_wb+0xc4/0x180
> [0000000000526294] wb_writeback+0x294/0x300
> INFO: task jbd2/sda2-8:327 blocked for more than 120 seconds.
> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
> message.
> jbd2/sda2-8 D 000000000052ce28 0 327 2 0x58000000000
> Call Trace:
> [00000000007880d4] io_schedule+0x54/0xc0
> [000000000052ce28] sync_buffer+0x48/0x60
> [000000000078895c] __wait_on_bit+0x7c/0xe0
> [0000000000788a04] out_of_line_wait_on_bit+0x44/0x60
> [00000000005a4e10] jbd2_journal_commit_transaction+0x850/0x1280
> [00000000005a87bc] kjournald2+0x9c/0x1c0
> [0000000000482b84] kthread+0x64/0x80
> [000000000042b790] kernel_thread+0x30/0x60
> [0000000000482e84] kthreadd+0xe4/0x160
> INFO: task lighttpd:3260 blocked for more than 120 seconds.
> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
> message.
> lighttpd D 000000000052ce28 0 3260 1 0x410051101000080
> Call Trace:
> [00000000007880d4] io_schedule+0x54/0xc0
> [000000000052ce28] sync_buffer+0x48/0x60
> [000000000078895c] __wait_on_bit+0x7c/0xe0
> [0000000000788a04] out_of_line_wait_on_bit+0x44/0x60
> [000000000057ba44] ext4_find_entry+0x3c4/0x520
> [000000000057c7c8] ext4_lookup+0x28/0x180
> [000000000050e5a0] d_alloc_and_lookup+0x40/0x80
> [000000000050e6dc] do_lookup+0xfc/0x160
> [0000000000510578] link_path_walk+0x6b8/0xb00
> [0000000000510aa8] path_walk+0x28/0xa0
> [0000000000510b64] do_path_lookup+0x44/0xa0
> [0000000000510f6c] user_path_at+0x2c/0x80
> [00000000005090c8] vfs_fstatat+0x28/0x80
> [000000000044390c] compat_sys_stat64+0xc/0x40
> [0000000000406114] linux_sparc_syscall32+0x34/0x40
> INFO: task rsync:2451 blocked for more than 120 seconds.
> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
> message.
> rsync D 00000000005a3d38 0 2451 2445 0x410061101000080
> Call Trace:
> [00000000005a39c4] do_get_write_access+0x244/0x480
> [00000000005a3d38] jbd2_journal_get_write_access+0x18/0x40
> [0000000000591278] __ext4_journal_get_write_access+0x18/0x60
> [0000000000572a94] ext4_reserve_inode_write+0x54/0xa0
> [0000000000572afc] ext4_mark_inode_dirty+0x1c/0x1e0
> [0000000000577844] ext4_dirty_inode+0x24/0x40
> [0000000000525b60] __mark_inode_dirty+0x20/0x200
> [0000000000519d84] file_update_time+0xc4/0x140
> [00000000004c43f4] __generic_file_aio_write+0x1f4/0x3a0
> [00000000004c45d4] generic_file_aio_write+0x34/0xc0
> [0000000000504338] do_sync_write+0x78/0xc0
> [00000000005049a8] vfs_write+0x68/0x140
> [0000000000504c4c] SyS_write+0x2c/0x60
> [0000000000406114] linux_sparc_syscall32+0x34/0x40
> INFO: task cron:4376 blocked for more than 120 seconds.
> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
> message.
> cron D 00000000004c33f8 0 4376 3244 0x210021101000080
> Call Trace:
> [00000000007880d4] io_schedule+0x54/0xc0
> [00000000004c33f8] sync_page+0x58/0x80
> [0000000000788808] __wait_on_bit_lock+0x68/0xe0
> [00000000004c3360] __lock_page+0x40/0x60
> [00000000004c4eac] __lock_page_or_retry+0x4c/0x60
> [00000000004c5108] filemap_fault+0x248/0x3c0
> [00000000004dca90] __do_fault+0x30/0x480
> [00000000004df27c] handle_mm_fault+0x13c/0x9a0
> [000000000044de4c] do_sparc64_fault+0x32c/0x7c0
> [00000000004079a8] sparc64_realfault_common+0x10/0x20
> INFO: task cron:4377 blocked for more than 120 seconds.
> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
> message.
> cron D 00000000004c33f8 0 4377 3244 0x210021101000080
> Call Trace:
> [00000000007880d4] io_schedule+0x54/0xc0
> [00000000004c33f8] sync_page+0x58/0x80
> [0000000000788808] __wait_on_bit_lock+0x68/0xe0
> [00000000004c3360] __lock_page+0x40/0x60
> [00000000004c4eac] __lock_page_or_retry+0x4c/0x60
> [00000000004c5108] filemap_fault+0x248/0x3c0
> [00000000004dca90] __do_fault+0x30/0x480
> [00000000004df27c] handle_mm_fault+0x13c/0x9a0
> [000000000044de4c] do_sparc64_fault+0x32c/0x7c0
> [00000000004079a8] sparc64_realfault_common+0x10/0x20
> INFO: task cron:4378 blocked for more than 120 seconds.
> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this
> message.
> cron D 00000000004c33f8 0 4378 3244 0x210021101000080
> Call Trace:
> [00000000007880d4] io_schedule+0x54/0xc0
> [00000000004c33f8] sync_page+0x58/0x80
> [0000000000788808] __wait_on_bit_lock+0x68/0xe0
> [00000000004c3360] __lock_page+0x40/0x60
> [00000000004c4eac] __lock_page_or_retry+0x4c/0x60
> [00000000004c5108] filemap_fault+0x248/0x3c0
> [00000000004dca90] __do_fault+0x30/0x480
> [00000000004df27c] handle_mm_fault+0x13c/0x9a0
> [000000000044de4c] do_sparc64_fault+0x32c/0x7c0
> [00000000004079a8] sparc64_realfault_common+0x10/0x20
--
Jan Kara <jack@suse.cz>
SUSE Labs, CR
next prev parent reply other threads:[~2011-01-21 15:09 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-02-12 9:16 [PATCH] writeback: Fix broken sync writeback Jens Axboe
2010-02-12 15:45 ` Linus Torvalds
2010-02-13 12:58 ` Jan Engelhardt
2010-02-15 14:49 ` Jan Kara
2010-02-15 15:41 ` Jan Engelhardt
2010-02-15 15:58 ` Jan Kara
2010-06-27 16:44 ` Jan Engelhardt
2010-10-24 23:41 ` Sync writeback still broken Jan Engelhardt
2010-10-30 0:57 ` Linus Torvalds
2010-10-30 1:16 ` Linus Torvalds
2010-10-30 1:30 ` Linus Torvalds
2010-10-30 3:18 ` Andrew Morton
2010-10-30 13:15 ` Christoph Hellwig
2010-10-31 12:24 ` Jan Kara
2010-10-31 22:40 ` Jan Kara
2010-11-05 21:33 ` Jan Kara
2010-11-05 21:34 ` Jan Kara
2010-11-05 21:41 ` Linus Torvalds
2010-11-05 22:03 ` Jan Engelhardt
2010-11-07 12:57 ` Jan Kara
2011-01-20 22:50 ` Jan Engelhardt
2011-01-21 15:09 ` Jan Kara [this message]
2010-02-15 14:17 ` [PATCH] writeback: Fix broken sync writeback Jan Kara
2010-02-16 0:05 ` Linus Torvalds
2010-02-16 23:00 ` Jan Kara
2010-02-16 23:34 ` Linus Torvalds
2010-02-17 0:01 ` Linus Torvalds
2010-02-17 1:33 ` Jan Kara
2010-02-17 1:57 ` Dave Chinner
2010-02-17 3:35 ` Linus Torvalds
2010-02-17 4:30 ` tytso
2010-02-17 5:16 ` Linus Torvalds
2010-02-22 17:29 ` Jan Kara
2010-02-22 21:01 ` tytso
2010-02-22 22:26 ` Jan Kara
2010-02-23 2:53 ` Dave Chinner
2010-02-23 3:23 ` tytso
2010-02-23 5:53 ` Dave Chinner
2010-02-24 14:56 ` Jan Kara
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=20110121150902.GF5302@quack.suse.cz \
--to=jack@suse.cz \
--cc=akpm@linux-foundation.org \
--cc=gregkh@suse.de \
--cc=jengelh@medozas.de \
--cc=jens.axboe@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=stable@kernel.org \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox