sched: Keep at least 1 tick per second for active dynticks tasks

The scheduler doesn't yet fully support environments
with a single task running without a periodic tick.

In order to ensure we still maintain the duties of scheduler_tick(),
keep at least 1 tick per second.

This makes sure that we keep the progression of various scheduler
accounting and background maintainance even with a very low granularity.
Examples include cpu load, sched average, CFS entity vruntime,
avenrun and events such as load balancing, amongst other details
handled in sched_class::task_tick().

This limitation will be removed in the future once we get
these individual items to work in full dynticks CPUs.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Hakan Akkan <hakanakkan@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Kevin Hilman <khilman@linaro.org>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index ebf7095158a9ebe88ef289b11b153daebe82cb60..af008d7bad57b9bebf6c99087949628f5e6220f2 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1862,6 +1862,7 @@ static inline void wake_up_nohz_cpu(int cpu) { }
 
 #ifdef CONFIG_NO_HZ_FULL
 extern bool sched_can_stop_tick(void);
+extern u64 scheduler_tick_max_deferment(void);
 #else
 static inline bool sched_can_stop_tick(void) { return false; }
 #endif

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e94842d4400c1a53b4a5331f7f35c711e41c2c79..3bdf986a091a503f4d30e39baebae7e08a82d98a 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2736,8 +2736,35 @@ void scheduler_tick(void)
        rq->idle_balance = idle_cpu(cpu);
        trigger_load_balance(rq, cpu);
 #endif
+       rq_last_tick_reset(rq);
 }
 
+#ifdef CONFIG_NO_HZ_FULL
+/**
+ * scheduler_tick_max_deferment
+ *
+ * Keep at least one tick per second when a single
+ * active task is running because the scheduler doesn't
+ * yet completely support full dynticks environment.
+ *
+ * This makes sure that uptime, CFS vruntime, load
+ * balancing, etc... continue to move forward, even
+ * with a very low granularity.
+ */
+u64 scheduler_tick_max_deferment(void)
+{
+       struct rq *rq = this_rq();
+       unsigned long next, now = ACCESS_ONCE(jiffies);
+
+       next = rq->last_sched_tick + HZ;
+
+       if (time_before_eq(next, now))
+               return 0;
+
+       return jiffies_to_usecs(next - now) * NSEC_PER_USEC;
+}
+#endif
+
 notrace unsigned long get_parent_ip(unsigned long addr)
 {
        if (in_lock_functions(addr)) {
@@ -6993,6 +7020,9 @@ void __init sched_init(void)
 #ifdef CONFIG_NO_HZ_COMMON
                rq->nohz_flags = 0;
 #endif
+#ifdef CONFIG_NO_HZ_FULL
+               rq->last_sched_tick = 0;
+#endif
 #endif
                init_rq_hrtick(rq);
                atomic_set(&rq->nr_iowait, 0);

diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
index b8ce77328341b1636a9e5cb45312a04e9e617ee0..d8da01008d390a770acb43c22bfb1de38e389a76 100644 (file)
--- a/kernel/sched/idle_task.c
+++ b/kernel/sched/idle_task.c
@@ -17,6 +17,7 @@ select_task_rq_idle(struct task_struct *p, int sd_flag, int flags)
 static void pre_schedule_idle(struct rq *rq, struct task_struct *prev)
 {
        idle_exit_fair(rq);
+       rq_last_tick_reset(rq);
 }
 
 static void post_schedule_idle(struct rq *rq)

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 24dc2989774937be3f1161541d8fb8860aeec4d0..ce39224d615599c40a1d6e7f8f4a78d728e2acad 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -409,6 +409,9 @@ struct rq {
 #ifdef CONFIG_NO_HZ_COMMON
        u64 nohz_stamp;
        unsigned long nohz_flags;
+#endif
+#ifdef CONFIG_NO_HZ_FULL
+       unsigned long last_sched_tick;
 #endif
        int skip_clock_update;
 
@@ -1090,6 +1093,13 @@ static inline void dec_nr_running(struct rq *rq)
        rq->nr_running--;
 }
 
+static inline void rq_last_tick_reset(struct rq *rq)
+{
+#ifdef CONFIG_NO_HZ_FULL
+       rq->last_sched_tick = jiffies;
+#endif
+}
+
 extern void update_rq_clock(struct rq *rq);
 
 extern void activate_task(struct rq *rq, struct task_struct *p, int flags);

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 1c9f53b2ddb7d87d8f7c373507f1211171ef21db..07929c633570beb2fba5e245c99e5468758d386c 100644 (file)
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -600,6 +600,13 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
                        time_delta = KTIME_MAX;
                }
 
+#ifdef CONFIG_NO_HZ_FULL
+               if (!ts->inidle) {
+                       time_delta = min(time_delta,
+                                        scheduler_tick_max_deferment());
+               }
+#endif
+
                /*
                 * calculate the expiry time for the next timer wheel
                 * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals