summaryrefslogtreecommitdiff
path: root/kernel/time
diff options
context:
space:
mode:
authorFrederic Weisbecker <fweisbec@gmail.com>2016-04-13 15:56:51 +0200
committerIngo Molnar <mingo@kernel.org>2016-04-23 14:20:42 +0200
commit1f41906a6fda1114debd3898668bd7ab6470ee41 (patch)
tree3960f1f67cd11aeadc368fee9dce6f393ad56ed3 /kernel/time
parentcee1afce3053e7aa0793fbd5f2e845fa2cef9e33 (diff)
sched/fair: Correctly handle nohz ticks CPU load accounting
Ticks can happen while the CPU is in dynticks-idle or dynticks-singletask mode. In fact "nohz" or "dynticks" only mean that we exit the periodic mode and we try to minimize the ticks as much as possible. The nohz subsystem uses a confusing terminology with the internal state "ts->tick_stopped" which is also available through its public interface with tick_nohz_tick_stopped(). This is a misnomer as the tick is instead reduced with the best effort rather than stopped. In the best case the tick can indeed be actually stopped but there is no guarantee about that. If a timer needs to fire one second later, a tick will fire while the CPU is in nohz mode and this is a very common scenario. Now this confusion happens to be a problem with CPU load updates: cpu_load_update_active() doesn't handle nohz ticks correctly because it assumes that ticks are completely stopped in nohz mode and that cpu_load_update_active() can't be called in dynticks mode. When that happens, the whole previous tickless load is ignored and the function just records the load for the current tick, ignoring potentially long idle periods behind. In order to solve this, we could account the current load for the previous nohz time but there is a risk that we account the load of a task that got freshly enqueued for the whole nohz period. So instead, lets record the dynticks load on nohz frame entry so we know what to record in case of nohz ticks, then use this record to account the tickless load on nohz ticks and nohz frame end. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Byungchul Park <byungchul.park@lge.com> Cc: Chris Metcalf <cmetcalf@ezchip.com> Cc: Christoph Lameter <cl@linux.com> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul E . McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1460555812-25375-3-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/time')
-rw-r--r--kernel/time/tick-sched.c9
1 files changed, 5 insertions, 4 deletions
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 66bdc9acc283..31872bc53bc4 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -776,6 +776,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
if (!ts->tick_stopped) {
nohz_balance_enter_idle(cpu);
calc_load_enter_idle();
+ cpu_load_update_nohz_start();
ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
@@ -802,11 +803,11 @@ out:
return tick;
}
-static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now, int active)
+static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
{
/* Update jiffies first */
tick_do_update_jiffies64(now);
- cpu_load_update_nohz(active);
+ cpu_load_update_nohz_stop();
calc_load_exit_idle();
touch_softlockup_watchdog_sched();
@@ -833,7 +834,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts)
if (can_stop_full_tick(ts))
tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
else if (ts->tick_stopped)
- tick_nohz_restart_sched_tick(ts, ktime_get(), 1);
+ tick_nohz_restart_sched_tick(ts, ktime_get());
#endif
}
@@ -1024,7 +1025,7 @@ void tick_nohz_idle_exit(void)
tick_nohz_stop_idle(ts, now);
if (ts->tick_stopped) {
- tick_nohz_restart_sched_tick(ts, now, 0);
+ tick_nohz_restart_sched_tick(ts, now);
tick_nohz_account_idle_ticks(ts);
}