From: Theodore Ts'o <tytso@mit.edu>
To: Jan Kara <jack@suse.cz>
Cc: linux-ext4@vger.kernel.org, Eryu Guan <eguan@redhat.com>,
stable@vger.kernel.org
Subject: Re: [PATCH 1/4] ext4: Fix deadlock during page writeback
Date: Mon, 4 Jul 2016 11:20:43 -0400 [thread overview]
Message-ID: <20160704152043.GA15193@thunk.org> (raw)
In-Reply-To: <20160704140012.GG5200@quack2.suse.cz>
On Mon, Jul 04, 2016 at 04:00:12PM +0200, Jan Kara wrote:
> OK, but we do all the block mappings, page locking etc. while the handle is
> started so it is not exactly a really short lived handle. The patch adds
> there a submission of a bio (we have the IO plugged so it will just add the
> bio to the list of submitted bios), unlock locked pages, drop refcount to
> ioend (unless IO is already completed, only refcount update is done, if IO
> is completed we defer any real work to workqueue anyway). So although we
> add some work which is done while the handle is still running, it is not
> that much.
Good point that the block device is plugged. Ultimately I suspect the
way to fix the scalability problem will be move to dioread nolock as
the default, and use separate transaction to map the blocks using the
uninitialized flags, and then do a separate transaction to convert
them afterwards.
- Ted
next prev parent reply other threads:[~2016-07-04 15:20 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-06-16 10:42 [PATCH 0/4] ext4: Fix deadlock during page writeback Jan Kara
2016-06-16 10:42 ` [PATCH 1/4] " Jan Kara
2016-06-30 15:05 ` Theodore Ts'o
2016-07-01 9:09 ` Jan Kara
2016-07-01 16:53 ` Theodore Ts'o
2016-07-01 17:40 ` Jan Kara
2016-07-01 21:26 ` Theodore Ts'o
2016-07-04 14:00 ` Jan Kara
2016-07-04 15:20 ` Theodore Ts'o [this message]
2016-07-04 15:47 ` Jan Kara
2016-07-05 2:43 ` Theodore Ts'o
2016-07-06 7:04 ` Jan Kara
2016-07-04 14:14 ` Theodore Ts'o
2016-07-04 15:51 ` Jan Kara
2016-07-05 3:38 ` Theodore Ts'o
2016-07-06 7:51 ` Jan Kara
2016-07-06 12:35 ` Theodore Ts'o
2016-07-06 12:52 ` Jan Kara
2016-07-06 14:27 ` Theodore Ts'o
2016-07-06 14:41 ` Jan Kara
2016-06-16 10:42 ` [PATCH 2/4] jbd2: Move lockdep instrumentation for jbd2 handles Jan Kara
2016-06-30 15:34 ` Theodore Ts'o
2016-06-16 10:42 ` [PATCH 3/4] jbd2: Move lockdep tracking to journal_s Jan Kara
2016-06-16 11:42 ` kbuild test robot
2016-06-30 15:40 ` Theodore Ts'o
2016-06-16 10:42 ` [PATCH 4/4] jbd2: Track more dependencies on transaction commit Jan Kara
2016-06-30 15:45 ` Theodore Ts'o
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=20160704152043.GA15193@thunk.org \
--to=tytso@mit.edu \
--cc=eguan@redhat.com \
--cc=jack@suse.cz \
--cc=linux-ext4@vger.kernel.org \
--cc=stable@vger.kernel.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;
as well as URLs for NNTP newsgroup(s).