Re: [PATCH - resend*2] VFS: use synchronize_rcu_expedited() in namespace_unlock()
On Thu, Nov 29 2018, Al Viro wrote: > On Fri, Nov 30, 2018 at 10:33:18AM +1100, NeilBrown wrote: >> >> The synchronize_rcu() in namespace_unlock() is called every time >> a filesystem is unmounted. If a great many filesystems are mounted, >> this can cause a noticable slow-down in, for example, system shutdown. >> >> The sequence: >> mkdir -p /tmp/Mtest/{0..5000} >> time for i in /tmp/Mtest/*; do mount -t tmpfs tmpfs $i ; done >> time umount /tmp/Mtest/* >> >> on a 4-cpu VM can report 8 seconds to mount the tmpfs filesystems, and >> 100 seconds to unmount them. >> >> Boot the same VM with 1 CPU and it takes 18 seconds to mount the >> tmpfs filesystems, but only 36 to unmount. >> >> If we change the synchronize_rcu() to synchronize_rcu_expedited() >> the umount time on a 4-cpu VM drop to 0.6 seconds >> >> I think this 200-fold speed up is worth the slightly high system >> impact of using synchronize_rcu_expedited(). >> >> Acked-by: Paul E. McKenney (from general rcu >> perspective) >> Signed-off-by: NeilBrown >> --- >> >> Al Viro says "I can live with this one" but this still hasn't landed. >> Maybe someone else could apply it? > > Applied (in work.misc, once I push it out) Excellent - thanks a lot :-) NeilBrown signature.asc Description: PGP signature
Re: [PATCH - resend*2] VFS: use synchronize_rcu_expedited() in namespace_unlock()
On Thu, Nov 29 2018, Al Viro wrote: > On Fri, Nov 30, 2018 at 10:33:18AM +1100, NeilBrown wrote: >> >> The synchronize_rcu() in namespace_unlock() is called every time >> a filesystem is unmounted. If a great many filesystems are mounted, >> this can cause a noticable slow-down in, for example, system shutdown. >> >> The sequence: >> mkdir -p /tmp/Mtest/{0..5000} >> time for i in /tmp/Mtest/*; do mount -t tmpfs tmpfs $i ; done >> time umount /tmp/Mtest/* >> >> on a 4-cpu VM can report 8 seconds to mount the tmpfs filesystems, and >> 100 seconds to unmount them. >> >> Boot the same VM with 1 CPU and it takes 18 seconds to mount the >> tmpfs filesystems, but only 36 to unmount. >> >> If we change the synchronize_rcu() to synchronize_rcu_expedited() >> the umount time on a 4-cpu VM drop to 0.6 seconds >> >> I think this 200-fold speed up is worth the slightly high system >> impact of using synchronize_rcu_expedited(). >> >> Acked-by: Paul E. McKenney (from general rcu >> perspective) >> Signed-off-by: NeilBrown >> --- >> >> Al Viro says "I can live with this one" but this still hasn't landed. >> Maybe someone else could apply it? > > Applied (in work.misc, once I push it out) Excellent - thanks a lot :-) NeilBrown signature.asc Description: PGP signature
Re: [PATCH - resend*2] VFS: use synchronize_rcu_expedited() in namespace_unlock()
On Fri, Nov 30, 2018 at 10:33:18AM +1100, NeilBrown wrote: > > The synchronize_rcu() in namespace_unlock() is called every time > a filesystem is unmounted. If a great many filesystems are mounted, > this can cause a noticable slow-down in, for example, system shutdown. > > The sequence: > mkdir -p /tmp/Mtest/{0..5000} > time for i in /tmp/Mtest/*; do mount -t tmpfs tmpfs $i ; done > time umount /tmp/Mtest/* > > on a 4-cpu VM can report 8 seconds to mount the tmpfs filesystems, and > 100 seconds to unmount them. > > Boot the same VM with 1 CPU and it takes 18 seconds to mount the > tmpfs filesystems, but only 36 to unmount. > > If we change the synchronize_rcu() to synchronize_rcu_expedited() > the umount time on a 4-cpu VM drop to 0.6 seconds > > I think this 200-fold speed up is worth the slightly high system > impact of using synchronize_rcu_expedited(). > > Acked-by: Paul E. McKenney (from general rcu > perspective) > Signed-off-by: NeilBrown > --- > > Al Viro says "I can live with this one" but this still hasn't landed. > Maybe someone else could apply it? Applied (in work.misc, once I push it out)
Re: [PATCH - resend*2] VFS: use synchronize_rcu_expedited() in namespace_unlock()
On Fri, Nov 30, 2018 at 10:33:18AM +1100, NeilBrown wrote: > > The synchronize_rcu() in namespace_unlock() is called every time > a filesystem is unmounted. If a great many filesystems are mounted, > this can cause a noticable slow-down in, for example, system shutdown. > > The sequence: > mkdir -p /tmp/Mtest/{0..5000} > time for i in /tmp/Mtest/*; do mount -t tmpfs tmpfs $i ; done > time umount /tmp/Mtest/* > > on a 4-cpu VM can report 8 seconds to mount the tmpfs filesystems, and > 100 seconds to unmount them. > > Boot the same VM with 1 CPU and it takes 18 seconds to mount the > tmpfs filesystems, but only 36 to unmount. > > If we change the synchronize_rcu() to synchronize_rcu_expedited() > the umount time on a 4-cpu VM drop to 0.6 seconds > > I think this 200-fold speed up is worth the slightly high system > impact of using synchronize_rcu_expedited(). > > Acked-by: Paul E. McKenney (from general rcu > perspective) > Signed-off-by: NeilBrown > --- > > Al Viro says "I can live with this one" but this still hasn't landed. > Maybe someone else could apply it? Applied (in work.misc, once I push it out)
Re: [PATCH - resend*2] VFS: use synchronize_rcu_expedited() in namespace_unlock()
The synchronize_rcu() in namespace_unlock() is called every time a filesystem is unmounted. If a great many filesystems are mounted, this can cause a noticable slow-down in, for example, system shutdown. The sequence: mkdir -p /tmp/Mtest/{0..5000} time for i in /tmp/Mtest/*; do mount -t tmpfs tmpfs $i ; done time umount /tmp/Mtest/* on a 4-cpu VM can report 8 seconds to mount the tmpfs filesystems, and 100 seconds to unmount them. Boot the same VM with 1 CPU and it takes 18 seconds to mount the tmpfs filesystems, but only 36 to unmount. If we change the synchronize_rcu() to synchronize_rcu_expedited() the umount time on a 4-cpu VM drop to 0.6 seconds I think this 200-fold speed up is worth the slightly high system impact of using synchronize_rcu_expedited(). Acked-by: Paul E. McKenney (from general rcu perspective) Signed-off-by: NeilBrown --- Al Viro says "I can live with this one" but this still hasn't landed. Maybe someone else could apply it? Thanks, NeilBrown Full quote from Al on 5th Oct: > Umm... IIRC, the last one got sidetracked on the other thing in the series... > that was s_anon stuff. I can live with this one; FWIW, what kind > of load would trigger the impact of the change? Paul? which Paul replied to. fs/namespace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/namespace.c b/fs/namespace.c index a7f91265ea67..43a0d2c7449d 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1360,7 +1360,7 @@ static void namespace_unlock(void) if (likely(hlist_empty())) return; - synchronize_rcu(); + synchronize_rcu_expedited(); group_pin_kill(); } -- 2.14.0.rc0.dirty signature.asc Description: PGP signature
Re: [PATCH - resend*2] VFS: use synchronize_rcu_expedited() in namespace_unlock()
The synchronize_rcu() in namespace_unlock() is called every time a filesystem is unmounted. If a great many filesystems are mounted, this can cause a noticable slow-down in, for example, system shutdown. The sequence: mkdir -p /tmp/Mtest/{0..5000} time for i in /tmp/Mtest/*; do mount -t tmpfs tmpfs $i ; done time umount /tmp/Mtest/* on a 4-cpu VM can report 8 seconds to mount the tmpfs filesystems, and 100 seconds to unmount them. Boot the same VM with 1 CPU and it takes 18 seconds to mount the tmpfs filesystems, but only 36 to unmount. If we change the synchronize_rcu() to synchronize_rcu_expedited() the umount time on a 4-cpu VM drop to 0.6 seconds I think this 200-fold speed up is worth the slightly high system impact of using synchronize_rcu_expedited(). Acked-by: Paul E. McKenney (from general rcu perspective) Signed-off-by: NeilBrown --- Al Viro says "I can live with this one" but this still hasn't landed. Maybe someone else could apply it? Thanks, NeilBrown Full quote from Al on 5th Oct: > Umm... IIRC, the last one got sidetracked on the other thing in the series... > that was s_anon stuff. I can live with this one; FWIW, what kind > of load would trigger the impact of the change? Paul? which Paul replied to. fs/namespace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/namespace.c b/fs/namespace.c index a7f91265ea67..43a0d2c7449d 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1360,7 +1360,7 @@ static void namespace_unlock(void) if (likely(hlist_empty())) return; - synchronize_rcu(); + synchronize_rcu_expedited(); group_pin_kill(); } -- 2.14.0.rc0.dirty signature.asc Description: PGP signature