sched: Initialize rq->age_stamp on processor start
authorCorey Minyard <cminyard@mvista.com>
Thu, 8 May 2014 18:47:39 +0000 (13:47 -0500)
committerIngo Molnar <mingo@kernel.org>
Thu, 22 May 2014 09:16:35 +0000 (11:16 +0200)
commita803f0261bb2bb57aab5542af3174db43b2a3887
tree305b9aeaf5c4ccdeba62c4f99461ade245fdd960
parent72465447867b9de6b5cdea5d10f9781585136270
sched: Initialize rq->age_stamp on processor start

If the sched_clock time starts at a large value, the kernel will spin
in sched_avg_update for a long time while rq->age_stamp catches up
with rq->clock.

The comment in kernel/sched/clock.c says that there is no strict promise
that it starts at zero.  So initialize rq->age_stamp when a cpu starts up
to avoid this.

I was seeing long delays on a simulator that didn't start the clock at
zero.  This might also be an issue on reboots on processors that don't
re-initialize the timer to zero on reset, and when using kexec.

Signed-off-by: Corey Minyard <cminyard@mvista.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1399574859-11714-1-git-send-email-minyard@acm.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
kernel/sched/core.c