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>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f5605b6..da302ca 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5089,10 +5089,20 @@ static struct notifier_block migration_notifier = {
        .priority = CPU_PRI_MIGRATION,
 };
 
+static void __cpuinit set_cpu_rq_start_time(void)
+{
+       int cpu = smp_processor_id();
+       struct rq *rq = cpu_rq(cpu);
+       rq->age_stamp = sched_clock_cpu(cpu);
+}
+
 static int sched_cpu_active(struct notifier_block *nfb,
                                      unsigned long action, void *hcpu)
 {
        switch (action & ~CPU_TASKS_FROZEN) {
+       case CPU_STARTING:
+               set_cpu_rq_start_time();
+               return NOTIFY_OK;
        case CPU_DOWN_FAILED:
                set_cpu_active((long)hcpu, true);
                return NOTIFY_OK;
@@ -6970,6 +6980,7 @@ void __init sched_init(void)
        if (cpu_isolated_map == NULL)
                zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
        idle_thread_set_boot_cpu();
+       set_cpu_rq_start_time();
 #endif
        init_sched_fair_class();