From: Linus Torvalds <torvalds@linux-foundation.org>
To: Jeff Layton <jlayton@kernel.org>
Cc: kernel test robot <rong.a.chen@intel.com>,
yangerkun <yangerkun@huawei.com>,
LKML <linux-kernel@vger.kernel.org>,
lkp@lists.01.org, Neil Brown <neilb@suse.de>,
Bruce Fields <bfields@fieldses.org>,
Al Viro <viro@zeniv.linux.org.uk>
Subject: Re: [locks] 6d390e4b5d: will-it-scale.per_process_ops -96.6% regression
Date: Mon, 9 Mar 2020 08:52:41 -0700 [thread overview]
Message-ID: <CAHk-=whGK712fPqmQ3FSHxqe3Aqny4bEeWEvfaytLeLV2+ijCQ@mail.gmail.com> (raw)
In-Reply-To: <e3783d060c778cb41b77380ad3e278133b52f57e.camel@kernel.org>
[-- Attachment #1: Type: text/plain, Size: 1207 bytes --]
On Mon, Mar 9, 2020 at 7:36 AM Jeff Layton <jlayton@kernel.org> wrote:
>
> On Sun, 2020-03-08 at 22:03 +0800, kernel test robot wrote:
> >
> > FYI, we noticed a -96.6% regression of will-it-scale.per_process_ops due to commit:
>
> This is not completely unexpected as we're banging on the global
> blocked_lock_lock now for every unlock. This test just thrashes file
> locks and unlocks without doing anything in between, so the workload
> looks pretty artificial [1].
>
> It would be nice to avoid the global lock in this codepath, but it
> doesn't look simple to do. I'll keep thinking about it, but for now I'm
> inclined to ignore this result unless we see a problem in more realistic
> workloads.
That is a _huge_ regression, though.
What about something like the attached? Wouldn't that work? And make
the code actually match the old comment about wow "fl_blocker" being
NULL being special.
The old code seemed to not know about things like memory ordering either.
Patch is entirely untested, but aims to have that "smp_store_release()
means I'm done and not going to touch it any more", making that
smp_load_acquire() test hopefully be valid as per the comment..
Hmm?
Linus
[-- Attachment #2: patch.diff --]
[-- Type: text/x-patch, Size: 1935 bytes --]
fs/locks.c | 29 ++++++++++++++++++++++++++++-
1 file changed, 28 insertions(+), 1 deletion(-)
diff --git a/fs/locks.c b/fs/locks.c
index 426b55d333d5..bc5ca54a0749 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -725,7 +725,6 @@ static void __locks_delete_block(struct file_lock *waiter)
{
locks_delete_global_blocked(waiter);
list_del_init(&waiter->fl_blocked_member);
- waiter->fl_blocker = NULL;
}
static void __locks_wake_up_blocks(struct file_lock *blocker)
@@ -740,6 +739,12 @@ static void __locks_wake_up_blocks(struct file_lock *blocker)
waiter->fl_lmops->lm_notify(waiter);
else
wake_up(&waiter->fl_wait);
+
+ /*
+ * Tell the world we're done with it - see comment at
+ * top of locks_delete_block().
+ */
+ smp_store_release(&waiter->fl_blocker, NULL);
}
}
@@ -753,11 +758,33 @@ int locks_delete_block(struct file_lock *waiter)
{
int status = -ENOENT;
+ /*
+ * If fl_blocker is NULL, it won't be set again as this thread
+ * "owns" the lock and is the only one that might try to claim
+ * the lock. So it is safe to test fl_blocker locklessly.
+ * Also if fl_blocker is NULL, this waiter is not listed on
+ * fl_blocked_requests for some lock, so no other request can
+ * be added to the list of fl_blocked_requests for this
+ * request. So if fl_blocker is NULL, it is safe to
+ * locklessly check if fl_blocked_requests is empty. If both
+ * of these checks succeed, there is no need to take the lock.
+ */
+ if (!smp_load_acquire(&waiter->fl_blocker)) {
+ if (list_empty(&waiter->fl_blocked_requests))
+ return status;
+ }
+
spin_lock(&blocked_lock_lock);
if (waiter->fl_blocker)
status = 0;
__locks_wake_up_blocks(waiter);
__locks_delete_block(waiter);
+
+ /*
+ * Tell the world we're done with it - see commit at top
+ * of this function
+ */
+ smp_store_release(&waiter->fl_blocker, NULL);
spin_unlock(&blocked_lock_lock);
return status;
}
next prev parent reply other threads:[~2020-03-09 15:53 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-08 14:03 [locks] 6d390e4b5d: will-it-scale.per_process_ops -96.6% regression kernel test robot
2020-03-09 14:36 ` Jeff Layton
2020-03-09 15:52 ` Linus Torvalds [this message]
2020-03-09 17:22 ` Jeff Layton
2020-03-09 19:09 ` Jeff Layton
2020-03-09 19:53 ` Jeff Layton
2020-03-09 21:42 ` NeilBrown
2020-03-09 21:58 ` Jeff Layton
2020-03-10 7:52 ` kernel test robot
2020-03-09 22:11 ` Jeff Layton
2020-03-10 3:24 ` yangerkun
2020-03-10 7:54 ` kernel test robot
2020-03-10 12:52 ` Jeff Layton
2020-03-10 14:18 ` yangerkun
2020-03-10 15:06 ` Jeff Layton
2020-03-10 17:27 ` Jeff Layton
2020-03-10 21:01 ` NeilBrown
2020-03-10 21:14 ` Jeff Layton
2020-03-10 21:21 ` NeilBrown
2020-03-10 21:47 ` Linus Torvalds
2020-03-10 22:07 ` Jeff Layton
2020-03-10 22:31 ` Linus Torvalds
2020-03-11 22:22 ` NeilBrown
2020-03-12 0:38 ` Linus Torvalds
2020-03-12 4:42 ` NeilBrown
2020-03-12 12:31 ` Jeff Layton
2020-03-12 22:19 ` NeilBrown
2020-03-14 1:11 ` Jeff Layton
2020-03-12 16:07 ` Linus Torvalds
2020-03-14 1:31 ` Jeff Layton
2020-03-14 2:31 ` NeilBrown
2020-03-14 15:58 ` Linus Torvalds
2020-03-15 13:54 ` Jeff Layton
2020-03-16 5:06 ` NeilBrown
2020-03-16 11:07 ` Jeff Layton
2020-03-16 17:26 ` Linus Torvalds
2020-03-17 1:41 ` yangerkun
2020-03-17 14:05 ` yangerkun
2020-03-17 16:07 ` Jeff Layton
2020-03-18 1:09 ` yangerkun
2020-03-19 17:51 ` Jeff Layton
2020-03-19 19:23 ` Linus Torvalds
2020-03-19 19:24 ` Jeff Layton
2020-03-19 19:35 ` Linus Torvalds
2020-03-19 20:10 ` Jeff Layton
2020-03-16 22:45 ` NeilBrown
2020-03-17 15:59 ` Jeff Layton
2020-03-17 21:27 ` NeilBrown
2020-03-18 5:12 ` kernel test robot
2020-03-16 4:26 ` NeilBrown
2020-03-11 1:57 ` yangerkun
2020-03-11 12:52 ` Jeff Layton
2020-03-11 13:26 ` yangerkun
2020-03-11 22:15 ` NeilBrown
2020-03-10 7:50 ` kernel test robot
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='CAHk-=whGK712fPqmQ3FSHxqe3Aqny4bEeWEvfaytLeLV2+ijCQ@mail.gmail.com' \
--to=torvalds@linux-foundation.org \
--cc=bfields@fieldses.org \
--cc=jlayton@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lkp@lists.01.org \
--cc=neilb@suse.de \
--cc=rong.a.chen@intel.com \
--cc=viro@zeniv.linux.org.uk \
--cc=yangerkun@huawei.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).