From: Trond Myklebust <trondmy@hammerspace.com>
To: "jlayton@kernel.org" <jlayton@kernel.org>,
"neilb@suse.com" <neilb@suse.com>,
"Chuck.Lever@oracle.com" <Chuck.Lever@oracle.com>
Cc: "linux-nfs@vger.kernel.org" <linux-nfs@vger.kernel.org>
Subject: knfsd performance
Date: Tue, 18 Jun 2024 18:32:25 +0000 [thread overview]
Message-ID: <313d317dc0ca136de106979add5695ef5e2101e7.camel@hammerspace.com> (raw)
[-- Attachment #1: Type: text/plain, Size: 769 bytes --]
I recently back ported Neil's lwq code and sunrpc server changes to our
5.15.130 based kernel in the hope of improving the performance for our
data servers.
Our performance team recently ran a fio workload on a client that was
doing 100% NFSv3 reads in O_DIRECT mode over an RDMA connection
(infiniband) against that resulting server. I've attached the resulting
flame graph from a perf profile run on the server side.
Is anyone else seeing this massive contention for the spin lock in
__lwq_dequeue? As you can see, it appears to be dwarfing all the other
nfsd activity on the system in question here, being responsible for 45%
of all the perf hits.
--
Trond Myklebust
Linux NFS client maintainer, Hammerspace
trond.myklebust@hammerspace.com
[-- Attachment #2: 5.15.130-200.pd.124.el8.x86_64.dsx.svg --]
[-- Type: image/svg+xml, Size: 432471 bytes --]
next reply other threads:[~2024-06-18 18:32 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-18 18:32 Trond Myklebust [this message]
2024-06-18 18:40 ` knfsd performance Chuck Lever III
2024-06-18 19:29 ` Trond Myklebust
2024-06-18 19:39 ` Chuck Lever III
2024-06-18 19:50 ` Trond Myklebust
2024-06-18 19:54 ` Chuck Lever III
2024-06-18 20:16 ` Jeff Layton
2024-06-18 23:17 ` NeilBrown
2024-06-18 23:26 ` Chuck Lever III
2024-06-18 23:33 ` Jeff Layton
2024-06-18 23:51 ` Chuck Lever III
2024-06-19 2:56 ` Dave Chinner
2024-06-19 5:47 ` Christoph Hellwig
2024-06-19 13:44 ` Chuck Lever III
2024-06-19 21:16 ` NeilBrown
2024-06-19 0:42 ` Dave Chinner
2024-06-19 1:01 ` NeilBrown
2024-06-19 21:25 ` NeilBrown
2024-06-20 2:29 ` Dave Chinner
2024-06-20 10:18 ` Jeff Layton
2024-06-20 21:39 ` NeilBrown
2024-06-20 18:33 ` Chuck Lever III
2024-06-20 22:04 ` NeilBrown
2024-06-20 23:57 ` Trond Myklebust
2024-06-18 19:38 ` Jeff Layton
2024-06-18 23:12 ` NeilBrown
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=313d317dc0ca136de106979add5695ef5e2101e7.camel@hammerspace.com \
--to=trondmy@hammerspace.com \
--cc=Chuck.Lever@oracle.com \
--cc=jlayton@kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=neilb@suse.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.