Speaking of microsecond savers, the (ick) deferment experiment below
cut 60 core jitter in half. Shooting the clocksource watchdog fixes
alternating ~15us/~5us tick on my desktop box.
With workqueue twiddles and whatnot floating around, the thing is
starting to look viable.
---
kernel/sched/core.c | 5 +++--
kernel/time/clocksource.c | 5 +++++
2 files changed, 8 insertions(+), 2 deletions(-)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2604,12 +2604,13 @@ u64 scheduler_tick_max_deferment(void)
struct rq *rq = this_rq();
unsigned long next, now = ACCESS_ONCE(jiffies);
- next = rq->last_sched_tick + HZ;
+ next = (rq->last_sched_tick + HZ) | (rq->clock & 0x3f);
if (time_before_eq(next, now))
return 0;
- return jiffies_to_nsecs(next - now);
+ /* Add noise to avoid CPUs colliding at tick boundaries */
+ return jiffies_to_nsecs(next - now) | (rq->clock & 0xfffff);
}
#endif
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -267,8 +267,13 @@ static void clocksource_watchdog(unsigne
* to each other.
*/
next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask);
+skip_nohz_full:
if (next_cpu >= nr_cpu_ids)
next_cpu = cpumask_first(cpu_online_mask);
+ if (next_cpu && tick_nohz_full_cpu(next_cpu)) {
+ next_cpu = cpumask_next(next_cpu, cpu_online_mask);
+ goto skip_nohz_full;
+ }
watchdog_timer.expires += WATCHDOG_INTERVAL;
add_timer_on(&watchdog_timer, next_cpu);
out:
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/