From: "J. Bruce Fields" <bfields@fieldses.org>
To: NeilBrown <neilb@suse.com>
Cc: Jeff Layton <jlayton@kernel.org>,
Alexander Viro <viro@zeniv.linux.org.uk>,
linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
Martin Wilck <mwilck@suse.de>
Subject: Re: [PATCH 0/4] locks: avoid thundering-herd wake-ups
Date: Wed, 8 Aug 2018 15:54:45 -0400 [thread overview]
Message-ID: <20180808195445.GD23873@fieldses.org> (raw)
In-Reply-To: <153369219467.12605.13472423449508444601.stgit@noble>
On Wed, Aug 08, 2018 at 11:51:07AM +1000, NeilBrown wrote:
> If you have a many-core machine, and have many threads all wanting to
> briefly lock a give file (udev is known to do this), you can get quite
> poor performance.
>
> When one thread releases a lock, it wakes up all other threads that
> are waiting (classic thundering-herd) - one will get the lock and the
> others go to sleep.
> When you have few cores, this is not very noticeable: by the time the
> 4th or 5th thread gets enough CPU time to try to claim the lock, the
> earlier threads have claimed it, done what was needed, and released.
> With 50+ cores, the contention can easily be measured.
>
> This patchset creates a tree of pending lock request in which siblings
> don't conflict and each lock request does conflict with its parent.
> When a lock is released, only requests which don't conflict with each
> other a woken.
Are you sure you aren't depending on the (incorrect) assumption that "X
blocks Y" is a transitive relation?
OK I should be able to answer that question myself, my patience for
code-reading is at a real low this afternoon....
--b.
>
> Testing shows that lock-acquisitions-per-second is now fairly stable even
> as number of contending process goes to 1000. Without this patch,
> locks-per-second drops off steeply after a few 10s of processes.
>
> There is a small cost to this extra complexity.
> At 20 processes running a particular test on 72 cores, the lock
> acquisitions per second drops from 1.8 million to 1.4 million with
> this patch. For 100 processes, this patch still provides 1.4 million
> while without this patch there are about 700,000.
>
> NeilBrown
>
> ---
>
> NeilBrown (4):
> fs/locks: rename some lists and pointers.
> fs/locks: allow a lock request to block other requests.
> fs/locks: change all *_conflict() functions to return bool.
> fs/locks: create a tree of dependent requests.
>
>
> fs/cifs/file.c | 2 -
> fs/locks.c | 142 +++++++++++++++++++++++++--------------
> include/linux/fs.h | 5 +
> include/trace/events/filelock.h | 16 ++--
> 4 files changed, 103 insertions(+), 62 deletions(-)
>
> --
> Signature
next prev parent reply other threads:[~2018-08-08 19:54 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-08-08 1:51 [PATCH 0/4] locks: avoid thundering-herd wake-ups NeilBrown
2018-08-08 1:51 ` [PATCH 1/4] fs/locks: rename some lists and pointers NeilBrown
2018-08-08 10:47 ` Jeff Layton
2018-08-08 19:07 ` J. Bruce Fields
2018-08-08 1:51 ` [PATCH 3/4] fs/locks: change all *_conflict() functions to return bool NeilBrown
2018-08-08 1:51 ` [PATCH 2/4] fs/locks: allow a lock request to block other requests NeilBrown
2018-08-08 1:51 ` [PATCH 4/4] fs/locks: create a tree of dependent requests NeilBrown
2018-08-08 16:47 ` [PATCH 0/4] locks: avoid thundering-herd wake-ups Jeff Layton
2018-08-08 18:29 ` J. Bruce Fields
2018-08-09 0:58 ` NeilBrown
2018-08-20 11:02 ` Martin Wilck
2018-08-20 20:02 ` J. Bruce Fields
2018-08-20 20:06 ` Martin Wilck
2018-08-08 19:54 ` J. Bruce Fields [this message]
2018-08-08 20:09 ` J. Bruce Fields
2018-08-08 21:15 ` Frank Filz
2018-08-08 22:34 ` NeilBrown
2018-08-08 21:28 ` J. Bruce Fields
2018-08-08 22:39 ` NeilBrown
2018-08-08 22:50 ` Jeff Layton
2018-08-08 23:34 ` Frank Filz
2018-08-09 2:52 ` NeilBrown
2018-08-09 13:00 ` J. Bruce Fields
2018-08-09 14:49 ` Jeff Layton
2018-08-09 23:56 ` NeilBrown
2018-08-10 1:05 ` J. Bruce Fields
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=20180808195445.GD23873@fieldses.org \
--to=bfields@fieldses.org \
--cc=jlayton@kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mwilck@suse.de \
--cc=neilb@suse.com \
--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).