From: Christian Brauner <brauner@kernel.org>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-fsdevel@vger.kernel.org,
Thomas Gleixner <tglx@linutronix.de>,
Jens Axboe <axboe@kernel.dk>,
Christian Brauner <brauner@kernel.org>
Subject: [PATCH v2 0/3] fs: introduce file_ref_t
Date: Mon, 07 Oct 2024 16:23:56 +0200 [thread overview]
Message-ID: <20241007-brauner-file-rcuref-v2-0-387e24dc9163@kernel.org> (raw)
As atomic_inc_not_zero() is implemented with a try_cmpxchg() loop it has
O(N^2) behaviour under contention with N concurrent operations and it is
in a hot path in __fget_files_rcu().
The rcuref infrastructures remedies this problem by using an
unconditional increment relying on safe- and dead zones to make this
work and requiring rcu protection for the data structure in question.
This not just scales better it also introduces overflow protection.
However, in contrast to generic rcuref, files require a memory barrier
and thus cannot rely on *_relaxed() atomic operations and also require
to be built on atomic_long_t as having massive amounts of reference
isn't unheard of even if it is just an attack.
As suggested by Linus, add a file specific variant instead of making
this a generic library.
I've been testing this with will-it-scale using a multi-threaded fstat()
on the same file descriptor on a machine that Jens gave me access (thank
you very much!):
processor : 511
vendor_id : AuthenticAMD
cpu family : 25
model : 160
model name : AMD EPYC 9754 128-Core Processor
and I consistently get a 3-5% improvement on workloads with 256+ and
more threads comparing v6.12-rc1 as base with and without these patches
applied.
In vfs.file now.
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
Changes in v2:
- Don't introduce a separate rcuref_long_t library just implement it
only for files for now.
- Retain memory barrier by using atomic_long_add_negative() instead of
atomic_long_add_negative_relaxed() to order the loads before and after
the increment in __fget_files_rcu().
- Link to v1: https://lore.kernel.org/r/20241005-brauner-file-rcuref-v1-0-725d5e713c86@kernel.org
---
Christian Brauner (3):
fs: protect backing files with rcu
fs: add file_ref
fs: port files to file_ref
drivers/gpu/drm/i915/gt/shmem_utils.c | 2 +-
drivers/gpu/drm/vmwgfx/ttm_object.c | 2 +-
fs/eventpoll.c | 2 +-
fs/file.c | 120 ++++++++++++++++++++++++++++++++--
fs/file_table.c | 23 +++++--
include/linux/file_ref.h | 116 ++++++++++++++++++++++++++++++++
include/linux/fs.h | 9 +--
7 files changed, 253 insertions(+), 21 deletions(-)
---
base-commit: 9852d85ec9d492ebef56dc5f229416c925758edc
change-id: 20240927-brauner-file-rcuref-bfa4a4ba915b
next reply other threads:[~2024-10-07 14:24 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-07 14:23 Christian Brauner [this message]
2024-10-07 14:23 ` [PATCH v2 1/3] fs: protect backing files with rcu Christian Brauner
2024-10-07 14:23 ` [PATCH v2 2/3] fs: add file_ref Christian Brauner
2024-10-07 18:07 ` Linus Torvalds
2024-10-08 10:12 ` Christian Brauner
2024-10-08 17:29 ` Linus Torvalds
2024-10-07 14:23 ` [PATCH v2 3/3] fs: port files to file_ref Christian Brauner
2024-10-25 20:45 ` Jann Horn
2024-10-25 23:55 ` Jann Horn
2024-10-28 11:17 ` Christian Brauner
2024-10-28 18:30 ` Linus Torvalds
2024-10-29 14:18 ` Christian Brauner
2024-10-29 17:30 ` Endorsing __randomize_layout for projects! " Cedric Blancher
2024-10-07 18:27 ` [PATCH v2 0/3] fs: introduce file_ref_t Jens Axboe
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=20241007-brauner-file-rcuref-v2-0-387e24dc9163@kernel.org \
--to=brauner@kernel.org \
--cc=axboe@kernel.dk \
--cc=linux-fsdevel@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linux-foundation.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).