From: Chuck Lever <cel@kernel.org>
To: NeilBrown <neil@brown.name>, Jeff Layton <jlayton@kernel.org>,
Olga Kornievskaia <okorniev@redhat.com>,
Dai Ngo <dai.ngo@oracle.com>, Tom Talpey <tom@talpey.com>
Cc: <linux-nfs@vger.kernel.org>, Chuck Lever <chuck.lever@oracle.com>
Subject: [PATCH v9 00/12] NFSD: Implement NFSD_IO_DIRECT for NFS WRITE
Date: Mon, 3 Nov 2025 11:53:39 -0500 [thread overview]
Message-ID: <20251103165351.10261-1-cel@kernel.org> (raw)
From: Chuck Lever <chuck.lever@oracle.com>
Following on https://lore.kernel.org/linux-nfs/aPAci7O_XK1ljaum@kernel.org/
this series includes the patches needed to make NFSD Direct WRITE
operational.
The Documentation update is taken verbatim from Mike's Sep 3 series.
The document refers to NFSD_IO_DIRECT as working in an "uncached"
mode, but it doesn't explain how UNSTABLE works with NFSD_IO_DIRECT
(why a subsequent COMMIT is still required for durability). And IMO,
it needs a more thorough explanation of "Linux memory management's
page reclaim scalability problems". I prefer a brief root-cause
analysis here rather than a reference to a video or a benchmark
result.
I think the functional code changes come pretty close to what we've
agreed to so far, however. I dropped one R-b due to significant
mechanical changes in that patch.
Changes since v8:
* Drop "NFSD: Handle both offset and memory alignment for direct I/O"
* Include the Sep 3 version of the Documentation update
Changes since v7:
* Rebase the series on Mike's original v3 patch
* Address more review comments
* Optimize the "when can NFSD use IOCB_DIRECT" logic
* Revert the "always promote to FILE_SYNC" logic
Changes since v6:
* Patches to address review comments have been split out
* Refactored the iter initialization code
Changes since v5:
* Add a patch to make FILE_SYNC WRITEs persist timestamps
* Address some of Christoph's review comments
* The svcrdma patch has been dropped until we actually need it
Changes since v4:
* Split out refactoring nfsd_buffered_write() into a separate patch
* Expand patch description of 1/4
* Don't set IOCB_SYNC flag
Changes since v3:
* Address checkpatch.pl nits in 2/3
* Add an untested patch to mark ingress RDMA Read chunks
Chuck Lever (10):
NFSD: Make FILE_SYNC WRITEs comply with spec
NFSD: Enable return of an updated stable_how to NFS clients
NFSD: Remove specific error handling
NFSD: Remove alignment size checking
NFSD: Clean up struct nfsd_write_dio
NFSD: Introduce struct nfsd_write_dio_seg
NFSD: Simplify nfsd_iov_iter_aligned_bvec()
NFSD: Combine direct I/O feasibility check with iterator setup
NFSD: Handle kiocb->ki_flags correctly
NFSD: Refactor nfsd_vfs_write
Mike Snitzer (2):
NFSD: Implement NFSD_IO_DIRECT for NFS WRITE
NFSD: add Documentation/filesystems/nfs/nfsd-io-modes.rst
.../filesystems/nfs/nfsd-io-modes.rst | 144 +++++++++++++
fs/nfsd/debugfs.c | 1 +
fs/nfsd/nfs3proc.c | 2 +-
fs/nfsd/nfs4proc.c | 2 +-
fs/nfsd/nfsproc.c | 3 +-
fs/nfsd/trace.h | 1 +
fs/nfsd/vfs.c | 199 +++++++++++++++++-
fs/nfsd/vfs.h | 6 +-
fs/nfsd/xdr3.h | 2 +-
9 files changed, 343 insertions(+), 17 deletions(-)
create mode 100644 Documentation/filesystems/nfs/nfsd-io-modes.rst
--
2.51.0
next reply other threads:[~2025-11-03 16:53 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-11-03 16:53 Chuck Lever [this message]
2025-11-03 16:53 ` [PATCH v9 01/12] NFSD: Make FILE_SYNC WRITEs comply with spec Chuck Lever
2025-11-03 22:14 ` NeilBrown
2025-11-03 16:53 ` [PATCH v9 02/12] NFSD: Enable return of an updated stable_how to NFS clients Chuck Lever
2025-11-03 16:53 ` [PATCH v9 03/12] NFSD: Implement NFSD_IO_DIRECT for NFS WRITE Chuck Lever
2025-11-03 16:53 ` [PATCH v9 04/12] NFSD: Remove specific error handling Chuck Lever
2025-11-03 21:17 ` Mike Snitzer
2025-11-03 16:53 ` [PATCH v9 05/12] NFSD: Remove alignment size checking Chuck Lever
2025-11-03 21:16 ` Mike Snitzer
2025-11-03 22:30 ` NeilBrown
2025-11-04 11:52 ` Christoph Hellwig
2025-11-04 14:14 ` Chuck Lever
2025-11-04 15:54 ` Mike Snitzer
2025-11-05 12:52 ` Christoph Hellwig
2025-11-05 14:38 ` Chuck Lever
2025-11-05 14:48 ` Mike Snitzer
2025-11-05 14:55 ` Christoph Hellwig
2025-11-03 16:53 ` [PATCH v9 06/12] NFSD: Clean up struct nfsd_write_dio Chuck Lever
2025-11-03 22:36 ` NeilBrown
2025-11-03 16:53 ` [PATCH v9 07/12] NFSD: Introduce struct nfsd_write_dio_seg Chuck Lever
2025-11-03 22:45 ` NeilBrown
2025-11-03 22:48 ` Chuck Lever
2025-11-03 16:53 ` [PATCH v9 08/12] NFSD: Simplify nfsd_iov_iter_aligned_bvec() Chuck Lever
2025-11-03 21:13 ` Mike Snitzer
2025-11-03 22:48 ` NeilBrown
2025-11-03 16:53 ` [PATCH v9 09/12] NFSD: Combine direct I/O feasibility check with iterator setup Chuck Lever
2025-11-03 21:19 ` Mike Snitzer
2025-11-03 22:55 ` NeilBrown
2025-11-03 16:53 ` [PATCH v9 10/12] NFSD: Handle kiocb->ki_flags correctly Chuck Lever
2025-11-03 21:14 ` Mike Snitzer
2025-11-03 23:03 ` NeilBrown
2025-11-04 11:55 ` Christoph Hellwig
2025-11-03 16:53 ` [PATCH v9 11/12] NFSD: Refactor nfsd_vfs_write Chuck Lever
2025-11-03 21:15 ` Mike Snitzer
2025-11-03 23:05 ` NeilBrown
2025-11-03 16:53 ` [PATCH v9 12/12] NFSD: add Documentation/filesystems/nfs/nfsd-io-modes.rst Chuck Lever
2025-11-03 21:25 ` Mike Snitzer
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=20251103165351.10261-1-cel@kernel.org \
--to=cel@kernel.org \
--cc=chuck.lever@oracle.com \
--cc=dai.ngo@oracle.com \
--cc=jlayton@kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=neil@brown.name \
--cc=okorniev@redhat.com \
--cc=tom@talpey.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;
as well as URLs for NNTP newsgroup(s).