From 507e123151149e578c9aae33eb876c49824da5f8 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 23 Jun 2009 17:38:15 +0200 Subject: timer stats: Optimize by adding quick check to avoid function calls When the kernel is configured with CONFIG_TIMER_STATS but timer stats are runtime disabled we still get calls to __timer_stats_timer_set_start_info which initializes some fields in the corresponding struct timer_list. So add some quick checks in the the timer stats setup functions to avoid function calls to __timer_stats_timer_set_start_info when timer stats are disabled. In an artificial workload that does nothing but playing ping pong with a single tcp packet via loopback this decreases cpu consumption by 1 - 1.5%. This is part of a modified function trace output on SLES11: perl-2497 [00] 28630647177732388 [+ 125]: sk_reset_timer <-tcp_v4_rcv perl-2497 [00] 28630647177732513 [+ 125]: mod_timer <-sk_reset_timer perl-2497 [00] 28630647177732638 [+ 125]: __timer_stats_timer_set_start_info <-mod_timer perl-2497 [00] 28630647177732763 [+ 125]: __mod_timer <-mod_timer perl-2497 [00] 28630647177732888 [+ 125]: __timer_stats_timer_set_start_info <-__mod_timer perl-2497 [00] 28630647177733013 [+ 93]: lock_timer_base <-__mod_timer Signed-off-by: Heiko Carstens Cc: Andrew Morton Cc: Martin Schwidefsky Cc: Mustafa Mesanovic Cc: Arjan van de Ven LKML-Reference: <20090623153811.GA4641@osiris.boeblingen.de.ibm.com> Signed-off-by: Ingo Molnar --- kernel/time/timer_stats.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c index c994530d166d..4cde8b9c716f 100644 --- a/kernel/time/timer_stats.c +++ b/kernel/time/timer_stats.c @@ -96,7 +96,7 @@ static DEFINE_MUTEX(show_mutex); /* * Collection status, active/inactive: */ -static int __read_mostly active; +int __read_mostly timer_stats_active; /* * Beginning/end timestamps of measurement: @@ -242,7 +242,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf, struct entry *entry, input; unsigned long flags; - if (likely(!active)) + if (likely(!timer_stats_active)) return; lock = &per_cpu(lookup_lock, raw_smp_processor_id()); @@ -254,7 +254,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf, input.timer_flag = timer_flag; spin_lock_irqsave(lock, flags); - if (!active) + if (!timer_stats_active) goto out_unlock; entry = tstat_lookup(&input, comm); @@ -290,7 +290,7 @@ static int tstats_show(struct seq_file *m, void *v) /* * If still active then calculate up to now: */ - if (active) + if (timer_stats_active) time_stop = ktime_get(); time = ktime_sub(time_stop, time_start); @@ -368,18 +368,18 @@ static ssize_t tstats_write(struct file *file, const char __user *buf, mutex_lock(&show_mutex); switch (ctl[0]) { case '0': - if (active) { - active = 0; + if (timer_stats_active) { + timer_stats_active = 0; time_stop = ktime_get(); sync_access(); } break; case '1': - if (!active) { + if (!timer_stats_active) { reset_entries(); time_start = ktime_get(); smp_mb(); - active = 1; + timer_stats_active = 1; } break; default: -- cgit v1.2.2 From 6ff7041dbfeb3bd7dfe9aa67275c21199ef760d6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 10 Jul 2009 14:57:05 +0200 Subject: hrtimer: Fix migration expiry check The timer migration expiry check should prevent the migration of a timer to another CPU when the timer expires before the next event is scheduled on the other CPU. Migrating the timer might delay it because we can not reprogram the clock event device on the other CPU. But the code implementing that check has two flaws: - for !HIGHRES the check compares the expiry value with the clock events device expiry value which is wrong for CLOCK_REALTIME based timers. - the check is racy. It holds the hrtimer base lock of the target CPU, but the clock event device expiry value can be modified nevertheless, e.g. by an timer interrupt firing. The !HIGHRES case is easy to fix as we can enqueue the timer on the cpu which was selected by the load balancer. It runs the idle balancing code once per jiffy anyway. So the maximum delay for the timer is the same as when we keep the tick on the current cpu going. In the HIGHRES case we can get the next expiry value from the hrtimer cpu_base of the target CPU and serialize the update with the cpu_base lock. This moves the lock section in hrtimer_interrupt() so we can set next_event to KTIME_MAX while we are handling the expired timers and set it to the next expiry value after we handled the timers under the base lock. While the expired timers are processed timer migration is blocked because the expiry time of the timer is always <= KTIME_MAX. Also remove the now useless clockevents_get_next_event() function. Signed-off-by: Thomas Gleixner --- kernel/time/clockevents.c | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 1ad6dd461119..a6dcd67b041d 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -254,15 +254,4 @@ void clockevents_notify(unsigned long reason, void *arg) spin_unlock(&clockevents_lock); } EXPORT_SYMBOL_GPL(clockevents_notify); - -ktime_t clockevents_get_next_event(int cpu) -{ - struct tick_device *td; - struct clock_event_device *dev; - - td = &per_cpu(tick_cpu_device, cpu); - dev = td->evtdev; - - return dev->next_event; -} #endif -- cgit v1.2.2