LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Jens Axboe <jens.axboe@oracle.com>
To: David Chinner <dgc@sgi.com>
Cc: Christoph Lameter <clameter@sgi.com>,
	Andrew Morton <akpm@osdl.org>,
	linux-kernel@vger.kernel.org
Subject: Re: 2.6.20-rc6-mm3
Date: Fri, 2 Feb 2007 08:31:18 +0100	[thread overview]
Message-ID: <20070202073117.GS10305@kernel.dk> (raw)
In-Reply-To: <20070202040858.GN33919298@melbourne.sgi.com>

On Fri, Feb 02 2007, David Chinner wrote:
> On Thu, Feb 01, 2007 at 08:18:57PM +0100, Jens Axboe wrote:
> > That down() probably wants a replug to precede it. Probably something
> > like:
> > 
> >         if (atomic_read(&bp->b_io_remaining))
> >                 blk_replug_current_nested();
> > 
> > for xfs_buf_wait_unpin() and xfs_buf_lock(). Does this fix it?
> 
> Jens, this patch looks like you originally removed the explicit
> unplug calls that XFS used to prevent metadata I/O hangs and now you
> are putting them back.  Correct?
> 
> Reading on from Andrew's earlier comments, shouldn't XFS have
> worked unchanged? I'm just trying to understand why you removed
> the explicit unplugs in the first place.....

It should, the problem is if someone has plugged higher up in the
hierarchy, then you do need the explicit replug to drain that before
going to sleep and waiting for IO to complete. Not very happy about that
situation, I'd prefer if that happened automagically. I'll likely change
the code to fix that, so we don't have to sprinkle
blk_replug_current_nested() and always call io_schedule() instead of
schedule(). It's just going to cause too many problems.

-- 
Jens Axboe


  reply	other threads:[~2007-02-02  7:29 UTC|newest]

Thread overview: 124+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-01-30  4:45 2.6.20-rc6-mm3 Andrew Morton
2007-01-30  4:50 ` 2.6.20-rc6-mm3 Jeff Garzik
2007-01-30  5:11   ` 2.6.20-rc6-mm3 Andrew Morton
2007-01-30  9:56     ` 2.6.20-rc6-mm3 Evgeniy Polyakov
2007-01-30  8:16 ` 2.6.20-rc6-mm3 Sunil Naidu
2007-01-30  8:32   ` 2.6.20-rc6-mm3 Andrew Morton
2007-01-30  9:06 ` 2.6.20-rc6-mm3 Olivier Galibert
2007-01-30  9:26   ` 2.6.20-rc6-mm3 Andrew Morton
2007-01-30 18:47     ` 2.6.20-rc6-mm3 Olivier Galibert
2007-01-31  7:57     ` 2.6.20-rc6-mm3 Len Brown
2007-02-01  4:25     ` 2.6.20-rc6-mm3 Len Brown
2007-01-30 22:18 ` 2.6.20-rc6-mm3 Maciej Rutecki
2007-01-30 22:27   ` 2.6.20-rc6-mm3 Andrew Morton
2007-01-31  0:55     ` 2.6.20-rc6-mm3 Karsten Wiese
2007-01-31 13:22       ` 2.6.20-rc6-mm3 Ingo Molnar
2007-01-31 14:25         ` 2.6.20-rc6-mm3 Karsten Wiese
2007-02-01  8:01           ` 2.6.20-rc6-mm3 Ingo Molnar
2007-02-01 10:44             ` 2.6.20-rc6-mm3 Karsten Wiese
2007-03-01 11:11               ` 2.6.20-rc6-mm3 Karsten Wiese
2007-02-03  0:37             ` 2.6.20-rc6-mm3 Pavel Machek
2007-02-01 13:03       ` [PATCH -mm] gtod persistent clock resume fix Thomas Gleixner
2007-01-31 11:54     ` 2.6.20-rc6-mm3 Maciej Rutecki
2007-02-01  4:10       ` 2.6.20-rc6-mm3 Len Brown
2007-02-01  4:17         ` 2.6.20-rc6-mm3 Andrew Morton
2007-01-31  1:16   ` 2.6.20-rc6-mm3 Tilman Schmidt
2007-01-31  1:25     ` 2.6.20-rc6-mm3 Andrew Morton
2007-01-31 11:38       ` 2.6.20-rc6-mm3 Tilman Schmidt
2007-01-31 12:29         ` 2.6.20-rc6-mm3 Alexey Starikovskiy
2007-01-31 16:02           ` 2.6.20-rc6-mm3 Maciej Rutecki
2007-01-31 18:28           ` 2.6.20-rc6-mm3 Tilman Schmidt
2007-01-31 21:52 ` 2.6.20-rc6-mm3 Mattia Dongili
2007-01-31 23:21   ` 2.6.20-rc6-mm3 Mattia Dongili
2007-02-01 19:04     ` 2.6.20-rc6-mm3 Ingo Molnar
2007-02-01 19:36     ` 2.6.20-rc6-mm3 Thomas Gleixner
2007-02-01 20:01       ` 2.6.20-rc6-mm3 Thomas Gleixner
2007-02-01 21:11         ` 2.6.20-rc6-mm3 Mattia Dongili
2007-02-01 22:33           ` 2.6.20-rc6-mm3 Thomas Gleixner
2007-02-02 19:18             ` dynticks + iptables almost stops the boot process [was: Re: 2.6.20-rc6-mm3] Mattia Dongili
2007-02-02 20:27               ` Thomas Gleixner
2007-02-02 20:43                 ` Mattia Dongili
2007-02-06 16:48                   ` Ingo Molnar
2007-02-06 19:28                     ` Mattia Dongili
2007-02-06 23:12                       ` Tilman Schmidt
2007-02-06 23:17                         ` Thomas Gleixner
2007-02-07  1:01                           ` Andrew Morton
2007-02-07 19:33                             ` Ingo Molnar
2007-02-01 21:37         ` 2.6.20-rc6-mm3 Mattia Dongili
2007-02-01 20:24       ` 2.6.20-rc6-mm3 Mattia Dongili
2007-02-01  0:14 ` 2.6.20-rc6-mm3 Christoph Lameter
2007-02-01  0:24   ` 2.6.20-rc6-mm3 Andrew Morton
2007-02-01  0:27     ` 2.6.20-rc6-mm3 Christoph Lameter
2007-02-01  0:36       ` 2.6.20-rc6-mm3 Andrew Morton
2007-02-01  0:38         ` 2.6.20-rc6-mm3 Christoph Lameter
2007-02-01  6:20         ` 2.6.20-rc6-mm3 David Chinner
2007-02-01  7:12           ` 2.6.20-rc6-mm3 Andrew Morton
2007-02-01 19:01             ` 2.6.20-rc6-mm3 Christoph Lameter
2007-02-01 19:18               ` 2.6.20-rc6-mm3 Jens Axboe
2007-02-01 20:18                 ` 2.6.20-rc6-mm3 Christoph Lameter
2007-02-01 20:26                   ` 2.6.20-rc6-mm3 Jens Axboe
2007-02-01 23:02                     ` 2.6.20-rc6-mm3 Christoph Lameter
2007-02-05 12:02                       ` 2.6.20-rc6-mm3 Jens Axboe
2007-02-05 12:17                         ` 2.6.20-rc6-mm3 Jens Axboe
2007-02-05 12:56                           ` 2.6.20-rc6-mm3 Jens Axboe
2007-02-05 18:20                             ` 2.6.20-rc6-mm3 Christoph Lameter
2007-02-05 18:34                               ` 2.6.20-rc6-mm3 Jens Axboe
2007-02-02  4:08                 ` 2.6.20-rc6-mm3 David Chinner
2007-02-02  7:31                   ` Jens Axboe [this message]
2007-02-01 18:24 ` 2.6.20-rc6-mm3 Cedric Le Goater
2007-02-01 19:37   ` 2.6.20-rc6-mm3 Starikovskiy, Alexey Y
2007-02-01 20:29     ` 2.6.20-rc6-mm3 Cedric Le Goater
2007-02-01 20:38       ` 2.6.20-rc6-mm3 Cedric Le Goater
2007-02-02 14:22         ` 2.6.20-rc6-mm3 Starikovskiy, Alexey Y
2007-02-02 14:47           ` 2.6.20-rc6-mm3 Cedric Le Goater
2007-02-02 14:50             ` 2.6.20-rc6-mm3 Starikovskiy, Alexey Y
2007-02-02 16:04               ` 2.6.20-rc6-mm3 Cedric Le Goater
2007-02-03  7:30                 ` 2.6.20-rc6-mm3 Cedric Le Goater
2007-02-03  7:57                   ` 2.6.20-rc6-mm3 Starikovskiy, Alexey Y
2007-02-02 17:39 ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 16:03 ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 18:36   ` 2.6.20-rc6-mm3 Thomas Gleixner
2007-02-06 18:45     ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 19:07       ` 2.6.20-rc6-mm3 Thomas Gleixner
2007-02-06 19:55         ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 20:20           ` 2.6.20-rc6-mm3 Thomas Gleixner
2007-02-06 20:40             ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 20:52               ` 2.6.20-rc6-mm3 Ingo Molnar
2007-02-06 20:56                 ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 21:09                   ` 2.6.20-rc6-mm3 Ingo Molnar
2007-02-06 21:20                     ` 2.6.20-rc6-mm3 Ingo Molnar
2007-02-06 21:23                     ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 21:41                       ` 2.6.20-rc6-mm3 Ingo Molnar
2007-02-06 21:54                         ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 22:08                           ` 2.6.20-rc6-mm3 Ingo Molnar
2007-02-06 22:42                             ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 22:56                               ` 2.6.20-rc6-mm3 Ingo Molnar
2007-02-06 23:04                                 ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 23:14                                   ` 2.6.20-rc6-mm3 Ingo Molnar
2007-02-06 23:22                                     ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 23:28                                       ` 2.6.20-rc6-mm3 Ingo Molnar
2007-02-06 23:35                                         ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 23:44                                           ` 2.6.20-rc6-mm3 Thomas Gleixner
2007-02-06 23:51                                           ` 2.6.20-rc6-mm3 Ingo Molnar
2007-02-07  2:46                                             ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 23:36                                       ` 2.6.20-rc6-mm3 Thomas Gleixner
2007-02-07  1:12                                         ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-07 14:53                                           ` 2.6.20-rc6-mm3 Thomas Gleixner
2007-02-06 23:37                                       ` 2.6.20-rc6-mm3 Ingo Molnar
2007-02-06 22:13                           ` 2.6.20-rc6-mm3 Thomas Gleixner
2007-02-06 21:43                       ` 2.6.20-rc6-mm3 Thomas Gleixner
2007-02-06 21:59                         ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 21:17               ` 2.6.20-rc6-mm3 Thomas Gleixner
2007-02-06 21:25                 ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 23:15               ` 2.6.20-rc6-mm3 Rob Landley
2007-02-06 23:28                 ` 2.6.20-rc6-mm3 Daniel Walker
2007-02-06 23:55                   ` 2.6.20-rc6-mm3 Rob Landley
2007-02-06 22:11 ` [-mm patch] #ifdef ACPI_FUTURE_USAGE acpi_os_readable() Adrian Bunk
2007-02-06 22:12 ` [RFC: -mm patch] drivers/net/atl1/: possible cleanups Adrian Bunk
2007-02-07  0:19   ` Jay Cliburn
2007-02-07  0:22     ` Jeff Garzik
2007-02-07  0:24       ` J. K. Cliburn
2007-02-07  0:24     ` Adrian Bunk
2007-02-06 22:12 ` [-mm patch] drivers/scsi/aacraid/: cleanups Adrian Bunk
2007-02-06 22:12 ` [-mm patch] make gfs2_writepages() static Adrian Bunk
2007-02-07 10:50   ` Steven Whitehouse

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=20070202073117.GS10305@kernel.dk \
    --to=jens.axboe@oracle.com \
    --cc=akpm@osdl.org \
    --cc=clameter@sgi.com \
    --cc=dgc@sgi.com \
    --cc=linux-kernel@vger.kernel.org \
    --subject='Re: 2.6.20-rc6-mm3' \
    /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

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).