[Patch] stop_machine stalls for a considerable period on large cpu count machines.

[Patch] stop_machine stalls for a considerable period on large cpu count machines.

[Robin Holt]

I forgot to include the linux-kernel mailing list.

Robin

----- Forwarded message from Robin Holt <holt@sgi.com> -----

Date: Sat, 27 Jun 2009 05:53:11 -0500
From: Robin Holt <holt@sgi.com>
To: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>, stable@kernel.org,
	mike travis <travis@sgi.com>
Subject: [Patch] stop_machine stalls for a considerable period on large cpu
	count machines.

Mike Travis noted that a 2048 cpu machine booting would take hours
to get through its modprobes.  We would get numerous back traces from
stop_cpu indicating they had not serviced interrupts.

A quick code review indicated we have a situation of heavy cacheline                                                      contention due to the 'state' (read-mostly) and 'thread_ack'
(write-mostly) variables being located in the same cacheline.


Signed-off-by: Robin Holt <holt@sgi.com>

---
 kernel/stop_machine.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
Index: stop_machine_false_sharing/kernel/stop_machine.c
===================================================================
--- stop_machine_false_sharing.orig/kernel/stop_machine.c	2009-06-27 05:26:57.000000000 -0500
+++ stop_machine_false_sharing/kernel/stop_machine.c	2009-06-27 05:34:45.182637682 -0500
@@ -36,8 +36,8 @@ struct stop_machine_data {
 
 /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
 static unsigned int num_threads;
-static atomic_t thread_ack;
-static DEFINE_MUTEX(lock);
+static atomic_t thread_ack	____cacheline_aligned;
+static DEFINE_MUTEX(lock)	____cacheline_aligned;
 /* setup_lock protects refcount, stop_machine_wq and stop_machine_work. */
 static DEFINE_MUTEX(setup_lock);
 /* Users of stop_machine. */

----- End forwarded message -----