From: Joanne Koong <joannelkoong@gmail.com>
To: miklos@szeredi.hu
Cc: djwong@kernel.org, brauner@kernel.org,
linux-fsdevel@vger.kernel.org, linux-xfs@vger.kernel.org,
bernd.schubert@fastmail.fm, kernel-team@meta.com
Subject: [PATCH v1 0/8] fuse: use iomap for buffered writes + writeback
Date: Fri, 6 Jun 2025 16:37:55 -0700 [thread overview]
Message-ID: <20250606233803.1421259-1-joannelkoong@gmail.com> (raw)
This series adds fuse iomap support for buffered writes and dirty folio
writeback. This is needed so that granular dirty tracking can be used in
fuse when large folios are enabled so that if only a few bytes in a large
folio are dirty, only a smaller portion is written out instead of the entire
folio.
In order to do so, a new iomap type, IOMAP_IN_MEM, is added that is more
generic and does not depend on the block layer. The parts of iomap buffer io
that depend on bios and CONFIG_BLOCK is moved to a separate file,
buffered-io-bio.c, in order to allow filesystems that do not have CONFIG_BLOCK
set to use IOMAP_IN_MEM buffered io.
This series was run through fstests with large folios enabled and through
some quick sanity checks on passthrough_hp with a) writing 1 GB in 1 MB chunks
and then going back and dirtying a few bytes in each chunk and b) writing 50 MB
in 1 MB chunks and going through dirtying the entire chunk for several runs.
a) showed about a 40% speedup increase with iomap support added and b) showed
roughly the same performance.
This patchset does not enable large folios yet. That will be sent out in a
separate future patchset.
Thanks,
Joanne
Joanne Koong (8):
iomap: move buffered io bio logic into separate file
iomap: add IOMAP_IN_MEM iomap type
iomap: add buffered write support for IOMAP_IN_MEM iomaps
iomap: add writepages support for IOMAP_IN_MEM iomaps
iomap: add iomap_writeback_dirty_folio()
fuse: use iomap for buffered writes
fuse: use iomap for writeback
fuse: use iomap for folio laundering
fs/fuse/Kconfig | 1 +
fs/fuse/file.c | 304 ++++++++++++---------------
fs/iomap/Makefile | 5 +-
fs/iomap/buffered-io-bio.c | 279 +++++++++++++++++++++++++
fs/iomap/buffered-io.c | 410 +++++++++----------------------------
fs/iomap/internal.h | 46 +++++
include/linux/iomap.h | 32 ++-
7 files changed, 586 insertions(+), 491 deletions(-)
create mode 100644 fs/iomap/buffered-io-bio.c
--
2.47.1
next reply other threads:[~2025-06-06 23:42 UTC|newest]
Thread overview: 70+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-06 23:37 Joanne Koong [this message]
2025-06-06 23:37 ` [PATCH v1 1/8] iomap: move buffered io bio logic into separate file Joanne Koong
2025-06-08 19:17 ` Anuj gupta
2025-06-09 4:44 ` Christoph Hellwig
2025-06-09 20:01 ` Joanne Koong
2025-06-06 23:37 ` [PATCH v1 2/8] iomap: add IOMAP_IN_MEM iomap type Joanne Koong
2025-06-09 4:45 ` Christoph Hellwig
2025-06-09 21:45 ` Joanne Koong
2025-06-10 3:39 ` Christoph Hellwig
2025-06-10 13:27 ` Christoph Hellwig
2025-06-10 20:13 ` Joanne Koong
2025-06-11 4:04 ` Christoph Hellwig
2025-06-11 6:00 ` Joanne Koong
2025-06-11 6:08 ` Christoph Hellwig
2025-06-11 18:33 ` Joanne Koong
2025-06-11 18:50 ` Darrick J. Wong
2025-06-11 23:08 ` Joanne Koong
2025-06-12 4:42 ` Christoph Hellwig
2025-06-09 16:24 ` Darrick J. Wong
2025-06-09 21:28 ` Joanne Koong
2025-06-12 3:53 ` Darrick J. Wong
2025-06-06 23:37 ` [PATCH v1 3/8] iomap: add buffered write support for IOMAP_IN_MEM iomaps Joanne Koong
2025-06-09 4:56 ` Christoph Hellwig
2025-06-09 22:45 ` Joanne Koong
2025-06-10 3:44 ` Christoph Hellwig
2025-06-09 16:38 ` Darrick J. Wong
2025-06-09 22:03 ` Joanne Koong
2025-06-12 3:54 ` Darrick J. Wong
2025-06-06 23:37 ` [PATCH v1 4/8] iomap: add writepages " Joanne Koong
2025-06-09 5:32 ` Christoph Hellwig
2025-06-09 16:57 ` Darrick J. Wong
2025-06-10 3:49 ` Christoph Hellwig
2025-06-12 3:56 ` Darrick J. Wong
2025-06-09 23:15 ` Joanne Koong
2025-06-10 3:58 ` Christoph Hellwig
2025-06-10 18:23 ` Joanne Koong
2025-06-10 18:58 ` Joanne Koong
2025-06-11 4:01 ` Christoph Hellwig
2025-06-06 23:38 ` [PATCH v1 5/8] iomap: add iomap_writeback_dirty_folio() Joanne Koong
2025-06-09 4:51 ` Christoph Hellwig
2025-06-09 17:14 ` Darrick J. Wong
2025-06-09 23:54 ` Joanne Koong
2025-06-10 3:59 ` Christoph Hellwig
2025-06-11 4:34 ` Matthew Wilcox
2025-06-18 4:47 ` does fuse need ->launder_folios, was: " Christoph Hellwig
2025-06-18 12:17 ` Jeff Layton
2025-06-20 18:15 ` Matthew Wilcox
2025-06-25 5:26 ` Joanne Koong
2025-06-25 6:26 ` Christoph Hellwig
2025-06-25 16:44 ` Joanne Koong
2025-07-01 5:41 ` Darrick J. Wong
2025-07-02 21:36 ` Joanne Koong
2025-07-02 21:47 ` Joanne Koong
2025-07-01 6:23 ` Miklos Szeredi
2025-06-09 23:30 ` Joanne Koong
2025-06-10 4:03 ` Christoph Hellwig
2025-06-06 23:38 ` [PATCH v1 6/8] fuse: use iomap for buffered writes Joanne Koong
2025-06-06 23:38 ` [PATCH v1 7/8] fuse: use iomap for writeback Joanne Koong
2025-06-08 19:20 ` Anuj gupta
2025-06-06 23:38 ` [PATCH v1 8/8] fuse: use iomap for folio laundering Joanne Koong
2025-06-08 19:12 ` [PATCH v1 0/8] fuse: use iomap for buffered writes + writeback Anuj gupta
2025-06-09 19:59 ` Joanne Koong
2025-06-14 14:22 ` Anuj gupta
2025-06-09 4:40 ` Christoph Hellwig
2025-06-09 12:38 ` Anuj gupta
2025-06-09 19:47 ` Joanne Koong
2025-06-10 4:04 ` Christoph Hellwig
2025-06-10 0:47 ` Dave Chinner
2025-06-10 4:06 ` Christoph Hellwig
2025-06-10 20:33 ` Joanne Koong
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=20250606233803.1421259-1-joannelkoong@gmail.com \
--to=joannelkoong@gmail.com \
--cc=bernd.schubert@fastmail.fm \
--cc=brauner@kernel.org \
--cc=djwong@kernel.org \
--cc=kernel-team@meta.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=miklos@szeredi.hu \
/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).