timekeeping: Fix leapsecond triggered load spike issue
authorJohn Stultz <johnstul@us.ibm.com>
Tue, 10 Jul 2012 22:43:20 +0000 (18:43 -0400)
committerThomas Gleixner <tglx@linutronix.de>
Wed, 11 Jul 2012 21:34:37 +0000 (23:34 +0200)
commit4873fa070ae84a4115f0b3c9dfabc224f1bc7c51
tree84479277770c3f02a3580f6d93965fb39f71e1c5
parentf55a6faa384304c89cfef162768e88374d3312cb
timekeeping: Fix leapsecond triggered load spike issue

The timekeeping code misses an update of the hrtimer subsystem after a
leap second happened. Due to that timers based on CLOCK_REALTIME are
either expiring a second early or late depending on whether a leap
second has been inserted or deleted until an operation is initiated
which causes that update. Unless the update happens by some other
means this discrepancy between the timekeeping and the hrtimer data
stays forever and timers are expired either early or late.

The reported immediate workaround - $ data -s "`date`" - is causing a
call to clock_was_set() which updates the hrtimer data structures.
See: http://www.sheeri.com/content/mysql-and-leap-second-high-cpu-and-fix

Add the missing clock_was_set() call to update_wall_time() in case of
a leap second event. The actual update is deferred to softirq context
as the necessary smp function call cannot be invoked from hard
interrupt context.

Signed-off-by: John Stultz <johnstul@us.ibm.com>
Reported-by: Jan Engelhardt <jengelh@inai.de>
Reviewed-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Prarit Bhargava <prarit@redhat.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1341960205-56738-3-git-send-email-johnstul@us.ibm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
kernel/time/timekeeping.c