]> git.karo-electronics.de Git - karo-tx-linux.git/commitdiff
timekeeping: Fix leapsecond triggered load spike issue
authorJohn Stultz <johnstul@us.ibm.com>
Tue, 17 Jul 2012 21:49:26 +0000 (17:49 -0400)
committerPaul Gortmaker <paul.gortmaker@windriver.com>
Fri, 17 Aug 2012 19:35:47 +0000 (15:35 -0400)
commit 4873fa070ae84a4115f0b3c9dfabc224f1bc7c51 upstream.

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>
Link: http://lkml.kernel.org/r/1341960205-56738-3-git-send-email-johnstul@us.ibm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Linux Kernel <linux-kernel@vger.kernel.org>
Signed-off-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
kernel/time/timekeeping.c

index adfa89dfe2c562d09cce32308bbaece2693ff032..634c9eeb451f2638df63d314e8bc1c623fa306f3 100644 (file)
@@ -769,6 +769,8 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift)
                leap = second_overflow(xtime.tv_sec);
                xtime.tv_sec += leap;
                wall_to_monotonic.tv_sec -= leap;
+               if (leap)
+                       clock_was_set_delayed();
        }
 
        /* Accumulate into raw time */