linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Imran Khan <imran.f.khan@oracle.com>
To: tj@kernel.org, gregkh@linuxfoundation.org, viro@zeniv.linux.org.uk
Cc: linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	joe.jin@oracle.com
Subject: [PATCH 0/3] kernfs: Introduce separate rwsem to protect inode
Date: Thu,  2 Mar 2023 15:32:00 +1100	[thread overview]
Message-ID: <20230302043203.1695051-1-imran.f.khan@oracle.com> (raw)

This change set is consolidating the changes discussed and/or mentioned
in [1] and [2]. I have not received any feedback about any of the
patches included in this change set, so I am rebasing them on current
linux-next tip and bringing them all in one place.

As mentioned in [1], since changing per-fs kernfs_rwsem into a hashed
rwsem is not working for all scenarios, PATCH-1 here tries to address
the same issue with the help of another newly introduced per-fs rwsem.
PATCH-2 and PATCH-3 are basically resend of PATCH-1 and PATCH-2
respectively in [2].

It would be really helpful if I could get some feedback about this
changeset so that we can reduce the kernfs_rwsem contention and make
sysfs access more scalable for large-scale systems.

The patches in this change set are as follows:

PATCH-1: kernfs: Introduce separate rwsem to protect inode attributes.

PATCH-2: kernfs: Use a per-fs rwsem to protect per-fs list of
kernfs_super_info.

PATCH-3: kernfs: change kernfs_rename_lock into a read-write lock.

Imran Khan (3):
  kernfs: Introduce separate rwsem to protect inode attributes.
  Use a per-fs rwsem to protect per-fs list of kernfs_super_info.
  kernfs: change kernfs_rename_lock into a read-write lock.

 fs/kernfs/dir.c             | 26 +++++++++++++++++---------
 fs/kernfs/file.c            |  2 ++
 fs/kernfs/inode.c           | 16 ++++++++--------
 fs/kernfs/kernfs-internal.h |  2 ++
 fs/kernfs/mount.c           |  8 ++++----
 5 files changed, 33 insertions(+), 21 deletions(-)


base-commit: 7f7a8831520f12a3cf894b0627641fad33971221

[1]:https://lore.kernel.org/all/74969b22-e0b6-30bd-a1f0-132f4b8485cf@oracle.com/
[2]:https://lore.kernel.org/all/20220810111017.2267160-1-imran.f.khan@oracle.com/
-- 
2.34.1


             reply	other threads:[~2023-03-02  4:32 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-03-02  4:32 Imran Khan [this message]
2023-03-02  4:32 ` [PATCH 1/3] kernfs: Introduce separate rwsem to protect inode attributes Imran Khan
2023-03-02 16:14   ` Matthew Wilcox
2023-03-02 20:32     ` Imran Khan
2023-03-02  4:32 ` [PATCH 2/3] kernfs: Use a per-fs rwsem to protect per-fs list of kernfs_super_info Imran Khan
2023-03-02 16:08   ` Matthew Wilcox
2023-03-02 21:28     ` Imran Khan
2023-03-02  4:32 ` [PATCH 3/3] kernfs: change kernfs_rename_lock into a read-write lock Imran Khan
2023-03-02 18:49   ` Matthew Wilcox

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=20230302043203.1695051-1-imran.f.khan@oracle.com \
    --to=imran.f.khan@oracle.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=joe.jin@oracle.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=tj@kernel.org \
    --cc=viro@zeniv.linux.org.uk \
    /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).