From: NeilBrown <neilb@suse.com>
To: "Dilger\, Andreas" <andreas.dilger@intel.com>,
David Laight <David.Laight@ACULAB.COM>
Cc: James Simmons <jsimmons@infradead.org>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
"devel\@driverdev.osuosl.org" <devel@driverdev.osuosl.org>,
"Drokin\, Oleg" <oleg.drokin@intel.com>, "Siyao\,
Lai" <lai.siyao@intel.com>,
Jinshan Xiong <jinshan.xiong@intel.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Lustre Development List <lustre-devel@lists.lustre.org>,
Li Xi <lixi@ddn.com>, Gu Zheng <gzheng@ddn.com>
Subject: Re: [PATCH 1/4] staging: lustre: obdclass: change spinlock of key to rwlock
Date: Fri, 04 May 2018 10:53:36 +1000 [thread overview]
Message-ID: <87a7tgfdgv.fsf@notabene.neil.brown.name> (raw)
In-Reply-To: <55458B75-4105-4F4F-BB50-3D506611AB24@intel.com>
[-- Attachment #1: Type: text/plain, Size: 1769 bytes --]
On Fri, May 04 2018, Dilger, Andreas wrote:
> On May 3, 2018, at 07:50, David Laight <David.Laight@ACULAB.COM> wrote:
>>
>> From: James Simmons
>>> Sent: 02 May 2018 19:22
>>> From: Li Xi <lixi@ddn.com>
>>>
>>> Most of the time, keys are never changed. So rwlock might be
>>> better for the concurrency of key read.
>>
>> OTOH unless there is contention on the spin lock during reads the
>> additional cost of a rwlock (probably double that of a spinlock)
>> will hurt performance.
>>
>> ...
>>> - spin_lock(&lu_keys_guard);
>>> + read_lock(&lu_keys_guard);
>>> atomic_inc(&lu_key_initing_cnt);
>>> - spin_unlock(&lu_keys_guard);
>>> + read_unlock(&lu_keys_guard);
>>
>> WTF, seems unlikely that you need to hold any kind of lock
>> over an atomic_inc().
>>
>> If this is just ensuring that no code holds the lock then
>> it would need to request the write_lock().
>> (and would need a comment)
>
> There was a fair amount of benchmarking done for this that shows the
> performance is significantly improved with the patch, which can be
> seen in the ticket that was referenced in the original commit comment:
>
> https://jira.hpdd.intel.com/browse/LU-6800?focusedCommentId=121776#comment-121776
That does surprise me. The only places where the lock is held for read
are very short - clearing a few fields or incrementing a value.
But numbers don't lie.
I wonder if the next patch would have had just as big an effect. Taking
and dropping the lock 40 times is not likely to be good for performance.
Thanks,
NeilBrown
>
> That said, it might be good to include this information into the
> commit comment itself.
>
> Cheers, Andreas
> --
> Andreas Dilger
> Lustre Principal Architect
> Intel Corporation
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 832 bytes --]
next prev parent reply other threads:[~2018-05-04 0:53 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-02 18:21 [PATCH 0/4] staging: lustre: obdclass: missing lu_object fixes James Simmons
2018-05-02 18:21 ` [PATCH 1/4] staging: lustre: obdclass: change spinlock of key to rwlock James Simmons
2018-05-03 13:50 ` David Laight
2018-05-03 23:26 ` NeilBrown
2018-05-04 0:11 ` Dilger, Andreas
2018-05-04 0:53 ` NeilBrown [this message]
2018-05-02 18:21 ` [PATCH 2/4] staging: lustre: obdclass: hoist locking in lu_context_exit() James Simmons
2018-05-02 18:21 ` [PATCH 3/4] staging: lustre: obdclass: guarantee all keys filled James Simmons
2018-05-02 18:21 ` [PATCH 4/4] staging: lustre: obdclass: change object lookup to no wait mode James Simmons
2018-05-04 1:15 ` NeilBrown
2018-05-15 0:37 ` James Simmons
2018-05-15 1:37 ` NeilBrown
2018-05-15 2:11 ` James Simmons
2018-05-07 1:47 ` Greg Kroah-Hartman
2018-05-08 11:45 ` Dan Carpenter
2018-05-15 15:02 ` James Simmons
2018-05-16 8:00 ` Dan Carpenter
2018-05-16 9:12 ` Dilger, Andreas
2018-05-16 15:44 ` Joe Perches
2018-05-16 16:57 ` Greg Kroah-Hartman
2018-05-17 5:07 ` James Simmons
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=87a7tgfdgv.fsf@notabene.neil.brown.name \
--to=neilb@suse.com \
--cc=David.Laight@ACULAB.COM \
--cc=andreas.dilger@intel.com \
--cc=devel@driverdev.osuosl.org \
--cc=gregkh@linuxfoundation.org \
--cc=gzheng@ddn.com \
--cc=jinshan.xiong@intel.com \
--cc=jsimmons@infradead.org \
--cc=lai.siyao@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lixi@ddn.com \
--cc=lustre-devel@lists.lustre.org \
--cc=oleg.drokin@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).