timer: Reduce timer migration overhead if disabled
Eric reported that the timer_migration sysctl is not really nice
performance wise as it needs to check at every timer insertion whether
the feature is enabled or not. Further the check does not live in the
timer code, so we have an extra function call which checks an extra
cache line to figure out that it is disabled.
We can do better and store that information in the per cpu (hr)timer
bases. I pondered to use a static key, but that's a nightmare to
update from the nohz code and the timer base cache line is hot anyway
when we select a timer base.
The old logic enabled the timer migration unconditionally if
CONFIG_NO_HZ was set even if nohz was disabled on the kernel command
line.
With this modification, we start off with migration disabled. The user
visible sysctl is still set to enabled. If the kernel switches to NOHZ
migration is enabled, if the user did not disable it via the sysctl
prior to the switch. If nohz=off is on the kernel command line,
migration stays disabled no matter what.
Before:
47.76% hog [.] main
14.84% [kernel] [k] _raw_spin_lock_irqsave
9.55% [kernel] [k] _raw_spin_unlock_irqrestore
6.71% [kernel] [k] mod_timer
6.24% [kernel] [k] lock_timer_base.isra.38
3.76% [kernel] [k] detach_if_pending
3.71% [kernel] [k] del_timer
2.50% [kernel] [k] internal_add_timer
1.51% [kernel] [k] get_nohz_timer_target
1.28% [kernel] [k] __internal_add_timer
0.78% [kernel] [k] timerfn
0.48% [kernel] [k] wake_up_nohz_cpu
After:
48.10% hog [.] main
15.25% [kernel] [k] _raw_spin_lock_irqsave
9.76% [kernel] [k] _raw_spin_unlock_irqrestore
6.50% [kernel] [k] mod_timer
6.44% [kernel] [k] lock_timer_base.isra.38
3.87% [kernel] [k] detach_if_pending
3.80% [kernel] [k] del_timer
2.67% [kernel] [k] internal_add_timer
1.33% [kernel] [k] __internal_add_timer
0.73% [kernel] [k] timerfn
0.54% [kernel] [k] wake_up_nohz_cpu
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Joonwoo Park <joonwoop@codeaurora.org>
Cc: Wenbo Wang <wenbo.wang@memblaze.com>
Link: http://lkml.kernel.org/r/20150526224512.127050787@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 5db0558..6955102 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -163,6 +163,7 @@
* @cpu: cpu number
* @active_bases: Bitfield to mark bases with active timers
* @clock_was_set_seq: Sequence counter of clock was set events
+ * @migration_enabled: The migration of hrtimers to other cpus is enabled
* @expires_next: absolute time of the next event which was scheduled
* via clock_set_next_event()
* @next_timer: Pointer to the first expiring timer
@@ -186,6 +187,7 @@
unsigned int cpu;
unsigned int active_bases;
unsigned int clock_was_set_seq;
+ bool migration_enabled;
#ifdef CONFIG_HIGH_RES_TIMERS
unsigned int in_hrtirq : 1,
hres_active : 1,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 26a2e61..d715146 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -335,14 +335,10 @@
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
extern void nohz_balance_enter_idle(int cpu);
extern void set_cpu_sd_state_idle(void);
-extern int get_nohz_timer_target(int pinned);
+extern int get_nohz_timer_target(void);
#else
static inline void nohz_balance_enter_idle(int cpu) { }
static inline void set_cpu_sd_state_idle(void) { }
-static inline int get_nohz_timer_target(int pinned)
-{
- return smp_processor_id();
-}
#endif
/*
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 596a0e0..c9e4731 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -57,24 +57,12 @@
extern unsigned int sysctl_sched_migration_cost;
extern unsigned int sysctl_sched_nr_migrate;
extern unsigned int sysctl_sched_time_avg;
-extern unsigned int sysctl_timer_migration;
extern unsigned int sysctl_sched_shares_window;
int sched_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length,
loff_t *ppos);
#endif
-#ifdef CONFIG_SCHED_DEBUG
-static inline unsigned int get_sysctl_timer_migration(void)
-{
- return sysctl_timer_migration;
-}
-#else
-static inline unsigned int get_sysctl_timer_migration(void)
-{
- return 1;
-}
-#endif
/*
* control realtime throttling:
diff --git a/include/linux/timer.h b/include/linux/timer.h
index ff0689b..61aa61d 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -238,6 +238,15 @@
struct hrtimer;
extern enum hrtimer_restart it_real_fn(struct hrtimer *);
+#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+#include <linux/sysctl.h>
+
+extern unsigned int sysctl_timer_migration;
+int timer_migration_handler(struct ctl_table *table, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos);
+#endif
+
unsigned long __round_jiffies(unsigned long j, int cpu);
unsigned long __round_jiffies_relative(unsigned long j, int cpu);
unsigned long round_jiffies(unsigned long j);