From: Al Viro <viro@zeniv.linux.org.uk>
To: Mateusz Guzik <mjguzik@gmail.com>
Cc: Oliver Sang <oliver.sang@intel.com>,
oe-lkp@lists.linux.dev, lkp@intel.com,
linux-fsdevel@vger.kernel.org,
Christian Brauner <brauner@kernel.org>,
linux-doc@vger.kernel.org, ying.huang@intel.com,
feng.tang@intel.com, fengwei.yin@intel.com,
Linus Torvalds <torvalds@linux-foundation.org>
Subject: Re: [viro-vfs:work.dcache2] [__dentry_kill()] 1b738f196e: stress-ng.sysinfo.ops_per_sec -27.2% regression
Date: Wed, 6 Dec 2023 17:09:58 +0000 [thread overview]
Message-ID: <20231206170958.GP1674809@ZenIV> (raw)
In-Reply-To: <CAGudoHF-eXYYYStBWEGzgP8RGXG2+ER4ogdtndkgLWSaboQQwA@mail.gmail.com>
On Wed, Dec 06, 2023 at 05:42:34PM +0100, Mateusz Guzik wrote:
> That is to say your patchset is probably an improvement, but this
> benchmark uses kernfs which is a total crapper, with code like this in
> kernfs_iop_permission:
>
> root = kernfs_root(kn);
>
> down_read(&root->kernfs_iattr_rwsem);
> kernfs_refresh_inode(kn, inode);
> ret = generic_permission(&nop_mnt_idmap, inode, mask);
> up_read(&root->kernfs_iattr_rwsem);
>
>
> Maybe there is an easy way to dodge this, off hand I don't see one.
At a guess - seqcount on kernfs nodes, bumped on metadata changes
and a seqretry loop, not that this was the only problem with kernfs
scalability.
That might account for sysinfo side, but not the unixbench - no kernfs
locks mentioned there. OTOH, we might be hitting the wall on
->i_rwsem with what it's doing...
next prev parent reply other threads:[~2023-12-06 17:10 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-11-30 4:54 [viro-vfs:work.dcache2] [__dentry_kill()] 1b738f196e: stress-ng.sysinfo.ops_per_sec -27.2% regression kernel test robot
2023-11-30 7:55 ` Al Viro
2023-12-01 2:13 ` Oliver Sang
2023-12-01 2:42 ` Oliver Sang
2023-12-01 4:09 ` Al Viro
2023-12-01 6:56 ` Al Viro
2023-12-01 20:04 ` Al Viro
2023-12-04 13:37 ` Oliver Sang
2023-12-04 19:53 ` Al Viro
2023-12-06 2:40 ` Oliver Sang
2023-12-06 5:49 ` Al Viro
2023-12-06 14:56 ` Oliver Sang
2023-12-06 16:15 ` Al Viro
2023-12-06 16:30 ` Mateusz Guzik
2023-12-06 16:42 ` Mateusz Guzik
2023-12-06 17:09 ` Al Viro [this message]
2023-12-06 17:24 ` Mateusz Guzik
2023-12-06 18:30 ` Mateusz Guzik
2023-12-07 2:29 ` Oliver Sang
2023-12-08 18:07 ` Mateusz Guzik
2023-12-06 21:07 ` Al Viro
2023-12-06 21:41 ` Mateusz Guzik
2023-12-06 16:45 ` Al Viro
2023-12-06 16:52 ` Mateusz Guzik
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=20231206170958.GP1674809@ZenIV \
--to=viro@zeniv.linux.org.uk \
--cc=brauner@kernel.org \
--cc=feng.tang@intel.com \
--cc=fengwei.yin@intel.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=lkp@intel.com \
--cc=mjguzik@gmail.com \
--cc=oe-lkp@lists.linux.dev \
--cc=oliver.sang@intel.com \
--cc=torvalds@linux-foundation.org \
--cc=ying.huang@intel.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).