summaryrefslogtreecommitdiff
path: root/kernel/sched_clock.c
diff options
context:
space:
mode:
authorSteven Rostedt <rostedt@goodmis.org>2008-07-09 00:15:33 -0400
committerIngo Molnar <mingo@elte.hu>2008-07-11 15:53:28 +0200
commitc300ba252829e9325e08f0af60687add94445b25 (patch)
tree93c583012a3f26617e95aea516c02716ce254f5d /kernel/sched_clock.c
parenta83bc47c33ab182f1e48977fd5a04024d713c75e (diff)
downloadlwn-c300ba252829e9325e08f0af60687add94445b25.tar.gz
lwn-c300ba252829e9325e08f0af60687add94445b25.zip
sched_clock: and multiplier for TSC to gtod drift
The sched_clock code currently tries to keep all CPU clocks of all CPUS somewhat in sync. At every clock tick it records the gtod clock and uses that and jiffies and the TSC to calculate a CPU clock that tries to stay in sync with all the other CPUs. ftrace depends heavily on this timer and it detects when this timer "jumps". One problem is that the TSC and the gtod also drift. When the TSC is 0.1% faster or slower than the gtod it is very noticeable in ftrace. To help compensate for this, I've added a multiplier that tries to keep the CPU clock updating at the same rate as the gtod. I've tried various ways to get it to be in sync and this ended up being the most reliable. At every scheduler tick we calculate the new multiplier: multi = delta_gtod / delta_TSC This means we perform a 64 bit divide at the tick (once a HZ). A shift is used to handle the accuracy. Other methods that failed due to dynamic HZ are: (not used) multi += (gtod - tsc) / delta_gtod (not used) multi += (gtod - (last_tsc + delta_tsc)) / delta_gtod as well as other variants. This code still allows for a slight drift between TSC and gtod, but it keeps the damage down to a minimum. Signed-off-by: Steven Rostedt <srostedt@redhat.com> Cc: Steven Rostedt <srostedt@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: john stultz <johnstul@us.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'kernel/sched_clock.c')
-rw-r--r--kernel/sched_clock.c40
1 files changed, 37 insertions, 3 deletions
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index 28ff6bf5e02b..8affbfd0cdb0 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -3,6 +3,9 @@
*
* Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
*
+ * Updates and enhancements:
+ * Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <srostedt@redhat.com>
+ *
* Based on code by:
* Ingo Molnar <mingo@redhat.com>
* Guillaume Chazarain <guichaz@gmail.com>
@@ -32,6 +35,11 @@
#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+#define MULTI_SHIFT 15
+/* Max is double, Min is 1/2 */
+#define MAX_MULTI (2LL << MULTI_SHIFT)
+#define MIN_MULTI (1LL << (MULTI_SHIFT-1))
+
struct sched_clock_data {
/*
* Raw spinlock - this is a special case: this might be called
@@ -45,6 +53,7 @@ struct sched_clock_data {
u64 tick_raw;
u64 tick_gtod;
u64 clock;
+ s64 multi;
#ifdef CONFIG_NO_HZ
int check_max;
#endif
@@ -79,6 +88,7 @@ void sched_clock_init(void)
scd->tick_raw = 0;
scd->tick_gtod = ktime_now;
scd->clock = ktime_now;
+ scd->multi = 1 << MULTI_SHIFT;
#ifdef CONFIG_NO_HZ
scd->check_max = 1;
#endif
@@ -134,8 +144,13 @@ static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *tim
WARN_ON_ONCE(!irqs_disabled());
- min_clock = scd->tick_gtod +
- (delta_jiffies ? delta_jiffies - 1 : 0) * TICK_NSEC;
+ /*
+ * At schedule tick the clock can be just under the gtod. We don't
+ * want to push it too prematurely.
+ */
+ min_clock = scd->tick_gtod + (delta_jiffies * TICK_NSEC);
+ if (min_clock > TICK_NSEC)
+ min_clock -= TICK_NSEC / 2;
if (unlikely(delta < 0)) {
clock++;
@@ -149,6 +164,9 @@ static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *tim
*/
max_clock = scd->tick_gtod + (2 + delta_jiffies) * TICK_NSEC;
+ delta *= scd->multi;
+ delta >>= MULTI_SHIFT;
+
if (unlikely(clock + delta > max_clock) && check_max(scd)) {
if (clock < max_clock)
clock = max_clock;
@@ -230,6 +248,7 @@ void sched_clock_tick(void)
{
struct sched_clock_data *scd = this_scd();
unsigned long now_jiffies = jiffies;
+ s64 mult, delta_gtod, delta_raw;
u64 now, now_gtod;
if (unlikely(!sched_clock_running))
@@ -247,9 +266,23 @@ void sched_clock_tick(void)
* already observe 1 new jiffy; adding a new tick_gtod to that would
* increase the clock 2 jiffies.
*/
- scd->tick_jiffies = now_jiffies;
+ delta_gtod = now_gtod - scd->tick_gtod;
+ delta_raw = now - scd->tick_raw;
+
+ if ((long)delta_raw > 0) {
+ mult = delta_gtod << MULTI_SHIFT;
+ do_div(mult, delta_raw);
+ scd->multi = mult;
+ if (scd->multi > MAX_MULTI)
+ scd->multi = MAX_MULTI;
+ else if (scd->multi < MIN_MULTI)
+ scd->multi = MIN_MULTI;
+ } else
+ scd->multi = 1 << MULTI_SHIFT;
+
scd->tick_raw = now;
scd->tick_gtod = now_gtod;
+ scd->tick_jiffies = now_jiffies;
__raw_spin_unlock(&scd->lock);
}
@@ -279,6 +312,7 @@ void sched_clock_idle_wakeup_event(u64 delta_ns)
__raw_spin_lock(&scd->lock);
scd->prev_raw = now;
scd->clock += delta_ns;
+ scd->multi = 1 << MULTI_SHIFT;
__raw_spin_unlock(&scd->lock);
touch_softlockup_watchdog();