public inbox for linux-xfs@vger.kernel.org
 help / color / mirror / Atom feed
From: Dave Chinner <david@fromorbit.com>
To: xfs@oss.sgi.com
Subject: [PATCH 0/8 v2] xfs: fix direct IO completion issues
Date: Tue, 14 Apr 2015 17:26:43 +1000	[thread overview]
Message-ID: <1428996411-1507-1-git-send-email-david@fromorbit.com> (raw)

Hi folks,

This is the second version of the series I first posted here:

http://oss.sgi.com/archives/xfs/2015-04/msg00097.html

I've reworked and refactored the first two patches in the series,
breaking them out into simpler, more self contained patches.

The main change from the previous version is that I dropped the
pre-allocation of the append transaction to avoid the nesting
problems it could cause.

The only other major change is that the ioend is only allocated when
a mapping is either for an unwritten region or spans EOF. hence if the
mapping is an overwrite within EOF we do not allocate an ioend, we
do not defer completion to the DIO workqueue and we do nothing in
the completion function as there is nothing to do.

Comments, thoughts?

-Dave.

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

             reply	other threads:[~2015-04-14  7:27 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-04-14  7:26 Dave Chinner [this message]
2015-04-14  7:26 ` [PATCH 1/8] xfs: factor DIO write mapping from get_blocks Dave Chinner
2015-04-14 14:23   ` Brian Foster
2015-04-14 20:06     ` Dave Chinner
2015-04-14  7:26 ` [PATCH 2/8] xfs: move DIO mapping size calculation Dave Chinner
2015-04-14 14:24   ` Brian Foster
2015-04-14  7:26 ` [PATCH 3/8] xfs: DIO needs an ioend for writes Dave Chinner
2015-04-14 14:24   ` Brian Foster
2015-04-14  7:26 ` [PATCH 4/8] xfs: handle DIO overwrite EOF update completion correctly Dave Chinner
2015-04-14 14:35   ` Brian Foster
2015-04-14 15:35     ` Brian Foster
2015-04-14 20:12     ` Dave Chinner
2015-04-14  7:26 ` [PATCH 5/8] xfs: DIO writes within EOF don't need an ioend Dave Chinner
2015-04-14 14:35   ` Brian Foster
2015-04-14 20:18     ` Dave Chinner
2015-04-14  7:26 ` [PATCH 6/8] xfs: DIO write completion size updates race Dave Chinner
2015-04-14 14:35   ` Brian Foster
2015-04-14  7:26 ` [PATCH 7/8] xfs: direct IO EOF zeroing needs to drain AIO Dave Chinner
2015-04-14 14:35   ` Brian Foster
2015-04-14  7:26 ` [PATCH 8/8] xfs: using generic_file_direct_write() is unnecessary Dave Chinner
2015-04-14 14:35   ` Brian Foster

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=1428996411-1507-1-git-send-email-david@fromorbit.com \
    --to=david@fromorbit.com \
    --cc=xfs@oss.sgi.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