diff options
author | Mike Galbraith <mgalbraith@suse.de> | 2012-05-08 06:20:58 -0400 |
---|---|---|
committer | Thomas Gleixner <tglx@linutronix.de> | 2012-05-24 19:44:50 -0400 |
commit | 5307c9556bc17e3cd26d4e94fc3b2565921834de (patch) | |
tree | e51937060ccd5e293dec7246a7961b0ae5509a53 | |
parent | ce004178be1bbaa292e9e6497939e2970300095a (diff) |
tick: Add tick skew boot option
Let the user decide whether power consumption or jitter is the
more important consideration for their machines.
Quoting removal commit af5ab277ded04bd9bc6b048c5a2f0e7d70ef0867:
"Historically, Linux has tried to make the regular timer tick on the
various CPUs not happen at the same time, to avoid contention on
xtime_lock.
Nowadays, with the tickless kernel, this contention no longer happens
since time keeping and updating are done differently. In addition,
this skew is actually hurting power consumption in a measurable way on
many-core systems."
Problems:
- Contrary to the above, systems do encounter contention on both
xtime_lock and RCU structure locks when the tick is synchronized.
- Moderate sized RT systems suffer intolerable jitter due to the tick
being synchronized.
- SGI reports the same for their large systems.
- Fully utilized systems reap no power saving benefit from skew removal,
but do suffer from resulting induced lock contention.
- 0209f649 rcu: limit rcu_node leaf-level fanout
This patch was born to combat lock contention which testing showed
to have been _induced by_ skew removal. Skew the tick, contention
disappeared virtually completely.
Signed-off-by: Mike Galbraith <mgalbraith@suse.de>
Link: http://lkml.kernel.org/r/1336472458.21924.78.camel@marge.simpson.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
-rw-r--r-- | Documentation/kernel-parameters.txt | 9 | ||||
-rw-r--r-- | kernel/time/tick-sched.c | 18 |
2 files changed, 27 insertions, 0 deletions
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index b69cfdc12112..ea38cd1f0aba 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt | |||
@@ -2532,6 +2532,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted. | |||
2532 | 2532 | ||
2533 | sched_debug [KNL] Enables verbose scheduler debug messages. | 2533 | sched_debug [KNL] Enables verbose scheduler debug messages. |
2534 | 2534 | ||
2535 | skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate | ||
2536 | xtime_lock contention on larger systems, and/or RCU lock | ||
2537 | contention on all systems with CONFIG_MAXSMP set. | ||
2538 | Format: { "0" | "1" } | ||
2539 | 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1" | ||
2540 | 1 -- enable. | ||
2541 | Note: increases power consumption, thus should only be | ||
2542 | enabled if running jitter sensitive (HPC/RT) workloads. | ||
2543 | |||
2535 | security= [SECURITY] Choose a security module to enable at boot. | 2544 | security= [SECURITY] Choose a security module to enable at boot. |
2536 | If this boot parameter is not specified, only the first | 2545 | If this boot parameter is not specified, only the first |
2537 | security module asking for security registration will be | 2546 | security module asking for security registration will be |
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 6a3a5b9ff561..4eddbb5ea9c5 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c | |||
@@ -814,6 +814,8 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) | |||
814 | return HRTIMER_RESTART; | 814 | return HRTIMER_RESTART; |
815 | } | 815 | } |
816 | 816 | ||
817 | static int sched_skew_tick; | ||
818 | |||
817 | /** | 819 | /** |
818 | * tick_setup_sched_timer - setup the tick emulation timer | 820 | * tick_setup_sched_timer - setup the tick emulation timer |
819 | */ | 821 | */ |
@@ -831,6 +833,14 @@ void tick_setup_sched_timer(void) | |||
831 | /* Get the next period (per cpu) */ | 833 | /* Get the next period (per cpu) */ |
832 | hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); | 834 | hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); |
833 | 835 | ||
836 | /* Offset the tick to avert xtime_lock contention. */ | ||
837 | if (sched_skew_tick) { | ||
838 | u64 offset = ktime_to_ns(tick_period) >> 1; | ||
839 | do_div(offset, num_possible_cpus()); | ||
840 | offset *= smp_processor_id(); | ||
841 | hrtimer_add_expires_ns(&ts->sched_timer, offset); | ||
842 | } | ||
843 | |||
834 | for (;;) { | 844 | for (;;) { |
835 | hrtimer_forward(&ts->sched_timer, now, tick_period); | 845 | hrtimer_forward(&ts->sched_timer, now, tick_period); |
836 | hrtimer_start_expires(&ts->sched_timer, | 846 | hrtimer_start_expires(&ts->sched_timer, |
@@ -910,3 +920,11 @@ int tick_check_oneshot_change(int allow_nohz) | |||
910 | tick_nohz_switch_to_nohz(); | 920 | tick_nohz_switch_to_nohz(); |
911 | return 0; | 921 | return 0; |
912 | } | 922 | } |
923 | |||
924 | static int __init skew_tick(char *str) | ||
925 | { | ||
926 | get_option(&str, &sched_skew_tick); | ||
927 | |||
928 | return 0; | ||
929 | } | ||
930 | early_param("skew_tick", skew_tick); | ||