From: "Paul E. McKenney" <paulmck@linux.ibm.com>
To: Byungchul Park <byungchul.park@lge.com>
Cc: Joel Fernandes <joel@joelfernandes.org>,
linux-kernel@vger.kernel.org, Rao Shoaib <rao.shoaib@oracle.com>,
max.byungchul.park@gmail.com, kernel-team@android.com,
kernel-team@lge.com, Davidlohr Bueso <dave@stgolabs.net>,
Josh Triplett <josh@joshtriplett.org>,
Lai Jiangshan <jiangshanlai@gmail.com>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
rcu@vger.kernel.org, Steven Rostedt <rostedt@goodmis.org>
Subject: Re: [PATCH RFC v1 1/2] rcu/tree: Add basic support for kfree_rcu batching
Date: Thu, 8 Aug 2019 11:11:12 -0700 [thread overview]
Message-ID: <20190808181112.GQ28441@linux.ibm.com> (raw)
In-Reply-To: <20190808102610.GA7227@X58A-UD3R>
On Thu, Aug 08, 2019 at 07:26:10PM +0900, Byungchul Park wrote:
> On Wed, Aug 07, 2019 at 05:45:04AM -0400, Joel Fernandes wrote:
> > On Tue, Aug 06, 2019 at 04:56:31PM -0700, Paul E. McKenney wrote:
>
> [snip]
>
> > > On Tue, Aug 06, 2019 at 05:20:40PM -0400, Joel Fernandes (Google) wrote:
> > > Of course, I am hoping that a later patch uses an array of pointers built
> > > at kfree_rcu() time, similar to Rao's patch (with or without kfree_bulk)
> > > in order to reduce per-object cache-miss overhead. This would make it
> > > easier for callback invocation to keep up with multi-CPU kfree_rcu()
> > > floods.
> >
> > I think Byungchul tried an experiment with array of pointers and wasn't
> > immediately able to see a benefit. Perhaps his patch needs a bit more polish
> > or another test-case needed to show benefit due to cache-misses, and the perf
> > tool could be used to show if cache misses were reduced. For this initial
> > pass, we decided to keep it without the array optimization.
>
> I'm still seeing no improvement with kfree_bulk().
>
> I've been thinking I could see improvement with kfree_bulk() because:
>
> 1. As you guys said, the number of cache misses will be reduced.
> 2. We can save (N - 1) irq-disable instructions while N kfrees.
> 3. As Joel said, saving/restoring CPU status that kfree() does inside
> is not required.
>
> But even with the following patch applied, the result was same as just
> batching test. We might need to get kmalloc objects from random
> addresses to maximize the result when using kfree_bulk() and this is
> even closer to real practical world too.
>
> And the second and third reasons doesn't seem to work as much as I
> expected.
>
> Do you have any idea? Or what do you think about it?
I would not expect kfree_batch() to help all that much unless the
pre-grace-period kfree_rcu() code segregated the objects on a per-slab
basis.
Thanx, Paul
> Thanks,
> Byungchul
>
> -----8<-----
> diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
> index 988e1ae..6f2ab06 100644
> --- a/kernel/rcu/rcuperf.c
> +++ b/kernel/rcu/rcuperf.c
> @@ -651,10 +651,10 @@ struct kfree_obj {
> return -ENOMEM;
> }
>
> - for (i = 0; i < kfree_alloc_num; i++) {
> - if (!kfree_no_batch) {
> - kfree_rcu(alloc_ptrs[i], rh);
> - } else {
> + if (!kfree_no_batch) {
> + kfree_bulk(kfree_alloc_num, (void **)alloc_ptrs);
> + } else {
> + for (i = 0; i < kfree_alloc_num; i++) {
> rcu_callback_t cb;
>
> cb = (rcu_callback_t)(unsigned long)offsetof(struct kfree_obj, rh);
>
next prev parent reply other threads:[~2019-08-08 18:11 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-08-06 21:20 [PATCH RFC v1 1/2] rcu/tree: Add basic support for kfree_rcu batching Joel Fernandes (Google)
2019-08-06 21:20 ` [PATCH RFC v1 2/2] rcuperf: Add kfree_rcu performance Tests Joel Fernandes (Google)
2019-08-07 0:29 ` Paul E. McKenney
2019-08-07 10:22 ` Joel Fernandes
2019-08-07 17:56 ` Paul E. McKenney
2019-08-09 16:01 ` Joel Fernandes
2019-08-11 2:01 ` Joel Fernandes
2019-08-11 23:42 ` Paul E. McKenney
2019-08-06 23:56 ` [PATCH RFC v1 1/2] rcu/tree: Add basic support for kfree_rcu batching Paul E. McKenney
2019-08-07 9:45 ` Joel Fernandes
2019-08-07 17:52 ` Paul E. McKenney
2019-08-08 9:52 ` Byungchul Park
2019-08-08 12:56 ` Joel Fernandes
2019-08-08 14:23 ` Byungchul Park
2019-08-08 18:09 ` Paul E. McKenney
2019-08-11 8:36 ` Byungchul Park
2019-08-11 8:49 ` Byungchul Park
2019-08-11 23:49 ` Paul E. McKenney
2019-08-12 10:10 ` Byungchul Park
2019-08-12 13:12 ` Joel Fernandes
2019-08-13 5:29 ` Byungchul Park
2019-08-13 15:41 ` Paul E. McKenney
2019-08-14 0:11 ` Byungchul Park
2019-08-14 2:53 ` Paul E. McKenney
2019-08-14 3:43 ` Byungchul Park
2019-08-14 16:59 ` Paul E. McKenney
2019-08-11 10:37 ` Byungchul Park
2019-08-08 23:30 ` Joel Fernandes
2019-08-09 15:16 ` Paul E. McKenney
2019-08-09 15:39 ` Joel Fernandes
2019-08-09 16:33 ` Paul E. McKenney
2019-08-09 20:22 ` Joel Fernandes
2019-08-09 20:26 ` Joel Fernandes
2019-08-09 21:25 ` Joel Fernandes
2019-08-10 3:38 ` Paul E. McKenney
2019-08-09 20:29 ` Joel Fernandes
2019-08-09 20:42 ` Paul E. McKenney
2019-08-09 21:36 ` Joel Fernandes
2019-08-10 3:40 ` Paul E. McKenney
2019-08-10 3:52 ` Joel Fernandes
2019-08-10 2:42 ` Joel Fernandes
2019-08-10 3:38 ` Paul E. McKenney
2019-08-10 4:20 ` Joel Fernandes
2019-08-10 18:24 ` Paul E. McKenney
2019-08-11 2:26 ` Joel Fernandes
2019-08-11 23:35 ` Paul E. McKenney
2019-08-12 13:13 ` Joel Fernandes
2019-08-12 14:44 ` Paul E. McKenney
2019-08-08 10:26 ` Byungchul Park
2019-08-08 18:11 ` Paul E. McKenney [this message]
2019-08-08 20:13 ` Joel Fernandes
2019-08-08 20:51 ` Paul E. McKenney
2019-08-08 22:34 ` Joel Fernandes
2019-08-08 22:37 ` Paul E. McKenney
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=20190808181112.GQ28441@linux.ibm.com \
--to=paulmck@linux.ibm.com \
--cc=byungchul.park@lge.com \
--cc=dave@stgolabs.net \
--cc=jiangshanlai@gmail.com \
--cc=joel@joelfernandes.org \
--cc=josh@joshtriplett.org \
--cc=kernel-team@android.com \
--cc=kernel-team@lge.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=max.byungchul.park@gmail.com \
--cc=rao.shoaib@oracle.com \
--cc=rcu@vger.kernel.org \
--cc=rostedt@goodmis.org \
/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).