Le dimanche 17 juillet 2011 à 10:46 +0200, Andi Kleen a écrit : > On Sat, Jul 16, 2011 at 07:04:28PM -0600, Matthew Wilcox wrote: > > On Sun, Jul 17, 2011 at 10:50:27AM +1000, Anton Blanchard wrote: > > > Looking closer, all of these calls are in pipefs and sockfs. > > > Since we never mount either filesystem they never get a long term > > > reference and we always end up in the very slow write brlock path > > > that takes a lock for each online CPU. > > > > > > Here is a quick hack that takes a long term reference on pipefs > > > and sockfs which fixes the problem. Any thoughts on how we should > > > fix it properly? > > > > I know Tim and Andi have been looking into this ... I forget what their > > fix was though. > > Tim posted a patch, but it wasn't applied for unknown reasons. > > https://lkml.org/lkml/2011/4/13/561 > Could Tim respin his patch then ? This problem hits even a two sockets machine. -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html