From: "Theodore Ts'o" <tytso@mit.edu>
To: Christoph Hellwig <hch@lst.de>
Cc: Christian Brauner <brauner@kernel.org>, Jan Kara <jack@suse.cz>,
Carlos Maiolino <cem@kernel.org>,
Andrew Morton <akpm@linux-foundation.org>,
willy@infradead.org, dlemoal@kernel.org, hans.holmberg@wdc.com,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
linux-xfs@vger.kernel.org
Subject: Re: [PATCH 2/3] writeback: allow the file system to override MIN_WRITEBACK_PAGES
Date: Wed, 15 Oct 2025 11:13:53 -0400 [thread overview]
Message-ID: <20251015151353.GA786497@mit.edu> (raw)
In-Reply-To: <20251015062728.60104-3-hch@lst.de>
On Wed, Oct 15, 2025 at 03:27:15PM +0900, Christoph Hellwig wrote:
> The relatively low minimal writeback size of 4MiB leads means that
> written back inodes on rotational media are switched a lot. Besides
> introducing additional seeks, this also can lead to extreme file
> fragmentation on zoned devices when a lot of files are cached relative
> to the available writeback bandwidth.
>
> Add a superblock field that allows the file system to override the
> default size.
I wonder if we should bump the default; and if the concern is that
might be problematic for super slow devices (e.g., cheap USB thumb
drives), perhaps we can measure the time needed to complete the
writeback, and then dynamically adjust the value based on the apparent
write bandwidth?
We could have each file system implement something like this, but
maybe there should be a way to do this in fs generic code?
- Ted
next prev parent reply other threads:[~2025-10-15 15:14 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-15 6:27 allow file systems to increase the minimum writeback chunk size Christoph Hellwig
2025-10-15 6:27 ` [PATCH 1/3] writeback: cleanup writeback_chunk_size Christoph Hellwig
2025-10-15 7:05 ` Damien Le Moal
2025-10-15 15:48 ` Darrick J. Wong
2025-10-20 9:34 ` Jan Kara
2025-10-15 6:27 ` [PATCH 2/3] writeback: allow the file system to override MIN_WRITEBACK_PAGES Christoph Hellwig
2025-10-15 7:09 ` Damien Le Moal
2025-10-15 7:27 ` Christoph Hellwig
2025-10-15 15:13 ` Theodore Ts'o [this message]
2025-10-16 4:33 ` Christoph Hellwig
2025-10-15 15:57 ` Darrick J. Wong
2025-10-16 4:37 ` Christoph Hellwig
2025-10-15 20:49 ` Dave Chinner
2025-10-16 4:39 ` Christoph Hellwig
2025-10-16 8:23 ` Dave Chinner
2025-10-15 6:27 ` [PATCH 3/3] xfs: set s_min_writeback_pages for zoned file systems Christoph Hellwig
2025-10-15 7:10 ` Damien Le Moal
2025-10-15 16:01 ` Darrick J. Wong
2025-10-15 7:11 ` allow file systems to increase the minimum writeback chunk size Damien Le Moal
-- strict thread matches above, loose matches on Subject: below --
2025-10-17 3:45 allow file systems to increase the minimum writeback chunk size v2 Christoph Hellwig
2025-10-17 3:45 ` [PATCH 2/3] writeback: allow the file system to override MIN_WRITEBACK_PAGES Christoph Hellwig
2025-10-17 12:32 ` Jan Kara
2025-10-17 15:45 ` Darrick J. Wong
2025-10-20 9:35 ` Jan Kara
2025-10-24 14:33 ` Nirjhar Roy (IBM)
2025-10-24 15:12 ` Christoph Hellwig
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=20251015151353.GA786497@mit.edu \
--to=tytso@mit.edu \
--cc=akpm@linux-foundation.org \
--cc=brauner@kernel.org \
--cc=cem@kernel.org \
--cc=dlemoal@kernel.org \
--cc=hans.holmberg@wdc.com \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-xfs@vger.kernel.org \
--cc=willy@infradead.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).