vchiq: Performance regression since 5.18-rc1

[Paul E. McKenney]

On Sun, May 22, 2022 at 05:11:36PM +0200, Stefan Wahren wrote:
> Hi Paul,
> 
> Am 22.05.22 um 01:46 schrieb Paul E. McKenney:
> > On Sun, May 22, 2022 at 01:22:00AM +0200, Stefan Wahren wrote:
> > > Hi,
> > > 
> > > while testing the staging/vc04_services/interface/vchiq_arm driver with my
> > > Raspberry Pi 3 B+ (multi_v7_defconfig) i noticed a huge performance
> > > regression since [ff042f4a9b050895a42cae893cc01fa2ca81b95c] mm:
> > > lru_cache_disable: replace work queue synchronization with synchronize_rcu
> > > 
> > > Usually i run "vchiq_test -f 1" to see the driver is still working [1].
> > > 
> > > Before commit:
> > > 
> > > real    0m1,500s
> > > user    0m0,068s
> > > sys    0m0,846s
> > > 
> > > After commit:
> > > 
> > > real    7m11,449s
> > > user    0m2,049s
> > > sys    0m0,023s
> > > 
> > > Best regards
> > > 
> > > [1] - https://github.com/raspberrypi/userland
> > Please feel free to try the patch shown below.  Or the pair of patches
> > from Rik here:
> > 
> > https://lore.kernel.org/lkml/20220218183114.2867528-2-riel@surriel.com/
> > https://lore.kernel.org/lkml/20220218183114.2867528-3-riel@surriel.com/
> 
> I tried your patch and Rik's patches but in both cases vchiq_test runs 7
> minutes instead of ~ 1 second.

That is surprising.  Do you boot with rcupdate.rcu_normal=1?  That would
nullify my patch, but I would expect that Rik's patch would still provide
increased performance even in that case.

Could you please characterize where the slowdown is occurring?

							Thanx, Paul

> Best regards
> 
> > 
> > There is work ongoing to produce something better, but ongoing slowly.
> > Especially my part of that work.
> > 
> > 							Thanx, Paul
> > 
> > ------------------------------------------------------------------------
> > 
> >  From paulmck at kernel.org Mon Feb 14 11:05:49 2022
> > Date: Mon, 14 Feb 2022 11:05:49 -0800
> > From: "Paul E. McKenney" <paulmck at kernel.org>
> > To: clm at fb.com
> > Cc: riel at surriel.com, viro at zeniv.linux.org.uk, linux-kernel at vger.kernel.org,
> > 	linux-fsdevel at vger.kernel.org, kernel-team at fb.com
> > Subject: [PATCH RFC fs/namespace] Make kern_unmount() use
> >   synchronize_rcu_expedited()
> > Message-ID: <20220214190549.GA2815154 at paulmck-ThinkPad-P17-Gen-1>
> > Reply-To: paulmck at kernel.org
> > MIME-Version: 1.0
> > Content-Type: text/plain; charset=us-ascii
> > Content-Disposition: inline
> > Status: RO
> > Content-Length: 1036
> > Lines: 32
> > 
> > Experimental.  Not for inclusion.  Yet, anyway.
> > 
> > Freeing large numbers of namespaces in quick succession can result in
> > a bottleneck on the synchronize_rcu() invoked from kern_unmount().
> > This patch applies the synchronize_rcu_expedited() hammer to allow
> > further testing and fault isolation.
> > 
> > Hey, at least there was no need to change the comment!  ;-)
> > 
> > Cc: Alexander Viro <viro at zeniv.linux.org.uk>
> > Cc: <linux-fsdevel at vger.kernel.org>
> > Cc: <linux-kernel at vger.kernel.org>
> > Not-yet-signed-off-by: Paul E. McKenney <paulmck at kernel.org>
> > 
> > ---
> > 
> >   namespace.c |    2 +-
> >   1 file changed, 1 insertion(+), 1 deletion(-)
> > 
> > diff --git a/fs/namespace.c b/fs/namespace.c
> > index 40b994a29e90d..79c50ad0ade5b 100644
> > --- a/fs/namespace.c
> > +++ b/fs/namespace.c
> > @@ -4389,7 +4389,7 @@ void kern_unmount(struct vfsmount *mnt)
> >   	/* release long term mount so mount point can be released */
> >   	if (!IS_ERR_OR_NULL(mnt)) {
> >   		real_mount(mnt)->mnt_ns = NULL;
> > -		synchronize_rcu();	/* yecchhh... */
> > +		synchronize_rcu_expedited();	/* yecchhh... */
> >   		mntput(mnt);
> >   	}
> >   }
> >