From: Marcelo Tosatti <mtosatti@redhat.com>
To: Borislav Petkov <bp@alien8.de>, michael@michaellarabel.com
Cc: Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Minchan Kim <minchan@kernel.org>,
Matthew Wilcox <willy@infradead.org>,
Mel Gorman <mgorman@techsingularity.net>,
Nicolas Saenz Julienne <nsaenzju@redhat.com>,
Juri Lelli <juri.lelli@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
"Paul E. McKenney" <paulmck@kernel.org>
Subject: Re: [patch v5] mm: lru_cache_disable: replace work queue synchronization with synchronize_rcu
Date: Thu, 28 Apr 2022 15:00:11 -0300 [thread overview]
Message-ID: <YmrWK/KoU1zrAxPI@fuller.cnet> (raw)
In-Reply-To: <YkWyLaom/r7jXgbA@zn.tnic>
On Thu, Mar 31, 2022 at 03:52:45PM +0200, Borislav Petkov wrote:
> On Thu, Mar 10, 2022 at 10:22:12AM -0300, Marcelo Tosatti wrote:
> >
> > On systems that run FIFO:1 applications that busy loop,
> > any SCHED_OTHER task that attempts to execute
> > on such a CPU (such as work threads) will not
> > be scheduled, which leads to system hangs.
> >
> > Commit d479960e44f27e0e52ba31b21740b703c538027c ("mm: disable LRU
> > pagevec during the migration temporarily") relies on
> > queueing work items on all online CPUs to ensure visibility
> > of lru_disable_count.
> >
> > To fix this, replace the usage of work items with synchronize_rcu,
> > which provides the same guarantees.
> >
> > Readers of lru_disable_count are protected by either disabling
> > preemption or rcu_read_lock:
> >
> > preempt_disable, local_irq_disable [bh_lru_lock()]
> > rcu_read_lock [rt_spin_lock CONFIG_PREEMPT_RT]
> > preempt_disable [local_lock !CONFIG_PREEMPT_RT]
> >
> > Since v5.1 kernel, synchronize_rcu() is guaranteed to wait on
> > preempt_disable() regions of code. So any CPU which sees
> > lru_disable_count = 0 will have exited the critical
> > section when synchronize_rcu() returns.
> >
> > Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
> > Reviewed-by: Nicolas Saenz Julienne <nsaenzju@redhat.com>
> > Acked-by: Minchan Kim <minchan@kernel.org>
>
> Someone pointed me at this:
>
> https://www.phoronix.com/scan.php?page=news_item&px=Linux-518-Stress-NUMA-Goes-Boom
>
> which says this one causes a performance regression with stress-ng's
> NUMA test...
Michael,
This is probably do_migrate_pages that is taking too long due to
synchronize_rcu().
Switching to synchronize_rcu_expedited() should probably fix it...
Can you give it a try, please?
diff --git a/mm/swap.c b/mm/swap.c
index bceff0cb559c..04a8bbf9817a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -879,7 +879,7 @@ void lru_cache_disable(void)
* lru_disable_count = 0 will have exited the critical
* section when synchronize_rcu() returns.
*/
- synchronize_rcu();
+ synchronize_rcu_expedited();
#ifdef CONFIG_SMP
__lru_add_drain_all(true);
#else
next prev parent reply other threads:[~2022-04-28 18:00 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-22 16:01 [patch v2] mm: lru_cache_disable: replace work queue synchronization with synchronize_rcu Marcelo Tosatti
2022-02-22 16:07 ` [patch v3] " Marcelo Tosatti
2022-02-22 16:25 ` Nicolas Saenz Julienne
2022-03-04 1:03 ` Andrew Morton
2022-03-04 1:49 ` Paul E. McKenney
2022-03-04 15:08 ` Marcelo Tosatti
2022-03-04 16:02 ` Paul E. McKenney
2022-03-04 15:11 ` Marcelo Tosatti
2022-03-04 16:29 ` [patch v4] " Marcelo Tosatti
2022-03-05 0:35 ` Andrew Morton
2022-03-07 18:52 ` Marcelo Tosatti
2022-03-10 13:22 ` [patch v5] " Marcelo Tosatti
2022-03-11 2:23 ` Andrew Morton
2022-03-11 8:35 ` Sebastian Andrzej Siewior
2022-03-12 0:40 ` Andrew Morton
2022-03-12 20:39 ` Marcelo Tosatti
2022-03-13 9:23 ` Hillf Danton
2022-03-31 13:52 ` Borislav Petkov
2022-04-28 18:00 ` Marcelo Tosatti [this message]
2022-05-28 21:18 ` Andrew Morton
2022-05-28 22:54 ` Michael Larabel
2022-05-29 0:48 ` Michael Larabel
2022-06-19 12:14 ` Thorsten Leemhuis
2022-06-22 0:15 ` Andrew Morton
2022-03-05 4:33 ` [patch v4] " Paul E. McKenney
2022-03-08 17:41 ` Minchan Kim
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=YmrWK/KoU1zrAxPI@fuller.cnet \
--to=mtosatti@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=bigeasy@linutronix.de \
--cc=bp@alien8.de \
--cc=juri.lelli@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@techsingularity.net \
--cc=michael@michaellarabel.com \
--cc=minchan@kernel.org \
--cc=nsaenzju@redhat.com \
--cc=paulmck@kernel.org \
--cc=tglx@linutronix.de \
--cc=willy@infradead.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).