Skip to contentSkip to conversation

coresched/proc: add forceidle report with coresched enabled

PATCH New Aubrey Li 1 participant 1 message Oct 29, 2020

Subsystems (2)
lore
Share & tools
lore

Aubrey Li

author
#0 lore raw

PATCH 1/1 coresched/proc: add forceidle report with coresched enabled

When a CPU is running a task with coresched enabled, its sibling will be forced idle if the sibling does not have a trusted task to run. It is useful to report forceidle to understand the performance of different cookies of tasks throughout the system.

forceidle is added at the last column of /proc/stat:

  $ cat /proc/stat
  cpu  102034 0 11992 8347016 1046 0 11 0 0 0 991
  cpu0 59 0 212 80364 59 0 0 0 0 0 0
  cpu1 72057 0 89 9102 0 0 0 0 0 0 90

So forceidle% can be computed by any user space tools, for example:

CPU user% system% iowait% forceidle% idle%
cpu53 24.75 0.00 0.00% 0.99% 74.26%
CPU user% system% iowait% forceidle% idle%
cpu53 25.74 0.00 0.00% 0.99% 73.27%
CPU user% system% iowait% forceidle% idle%
cpu53 24.75 0.00 0.00% 0.99% 74.26%
CPU user% system% iowait% forceidle% idle%
cpu53 25.24 0.00 0.00% 3.88% 70.87%

---
 fs/proc/stat.c              | 48 +++++++++++++++++++++++++++++++++++++
 include/linux/kernel_stat.h |  1 +
 include/linux/tick.h        |  2 ++
 kernel/time/tick-sched.c    | 48 +++++++++++++++++++++++++++++++++++++
 kernel/time/tick-sched.h    |  3 +++
 5 files changed, 102 insertions(+)
fs/proc/stat.c +48 -0
index 46b3293015fe..b27ccac7b5a4 100644
@@ -28,7 +28,11 @@ static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
 	u64 idle;
 
 	idle = kcs->cpustat[CPUTIME_IDLE];
+#ifdef CONFIG_SCHED_CORE
+	if (cpu_online(cpu) && !nr_iowait_cpu(cpu) && !cpu_rq(cpu)->core->core_forceidle)
+#else
 	if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
+#endif
 		idle += arch_idle_time(cpu);
 	return idle;
 }
@@ -43,6 +47,17 @@ static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu)
 	return iowait;
 }
 
+#ifdef CONFIG_SCHED_CORE
+static u64 get_forceidle_time(struct kernel_cpustat *kcs, int cpu)
+{
+	u64 forceidle;
+
+	forceidle = kcs->cpustat[CPUTIME_FORCEIDLE];
+	if (cpu_online(cpu) && cpu_rq(cpu)->core->core_forceidle)
+		forceidle += arch_idle_time(cpu);
+	return forceidle;
+}
+#endif
 #else
 
 static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
@@ -77,6 +92,21 @@ static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu)
 	return iowait;
 }
 
+static u64 get_forceidle_time(struct kernel_cpustat *kcs, int cpu)
+{
+	u64 forceidle, forceidle_usecs = -1ULL;
+
+	if (cpu_online(cpu))
+		forceidle_usecs = get_cpu_forceidle_time_us(cpu, NULL);
+
+	if (forceidle_usecs == -1ULL)
+		/* !NO_HZ or cpu offline so we can rely on cpustat.forceidle */
+		forceidle = kcs->cpustat[CPUTIME_FORCEIDLE];
+	else
+		forceidle = forceidle_usecs * NSEC_PER_USEC;
+
+	return forceidle;
+}
 #endif
 
 static void show_irq_gap(struct seq_file *p, unsigned int gap)
@@ -111,12 +141,18 @@ static int show_stat(struct seq_file *p, void *v)
 	u64 guest, guest_nice;
 	u64 sum = 0;
 	u64 sum_softirq = 0;
+#ifdef CONFIG_SCHED_CORE
+	u64 forceidle;
+#endif
 	unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
 	struct timespec64 boottime;
 
 	user = nice = system = idle = iowait =
 		irq = softirq = steal = 0;
 	guest = guest_nice = 0;
+#ifdef CONFIG_SCHED_CORE
+	forceidle = 0;
+#endif
 	getboottime64(&boottime);
 
 	for_each_possible_cpu(i) {
@@ -130,6 +166,9 @@ static int show_stat(struct seq_file *p, void *v)
 		system		+= cpustat[CPUTIME_SYSTEM];
 		idle		+= get_idle_time(&kcpustat, i);
 		iowait		+= get_iowait_time(&kcpustat, i);
+#ifdef CONFIG_SCHED_CORE
+		forceidle	+= get_forceidle_time(&kcpustat, i);
+#endif
 		irq		+= cpustat[CPUTIME_IRQ];
 		softirq		+= cpustat[CPUTIME_SOFTIRQ];
 		steal		+= cpustat[CPUTIME_STEAL];
@@ -157,6 +196,9 @@ static int show_stat(struct seq_file *p, void *v)
 	seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
 	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
 	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
+#ifdef CONFIG_SCHED_CORE
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(forceidle));
+#endif
 	seq_putc(p, '\n');
 
 	for_each_online_cpu(i) {
@@ -171,6 +213,9 @@ static int show_stat(struct seq_file *p, void *v)
 		system		= cpustat[CPUTIME_SYSTEM];
 		idle		= get_idle_time(&kcpustat, i);
 		iowait		= get_iowait_time(&kcpustat, i);
+#ifdef CONFIG_SCHED_CORE
+		forceidle	= get_forceidle_time(&kcpustat, i);
+#endif
 		irq		= cpustat[CPUTIME_IRQ];
 		softirq		= cpustat[CPUTIME_SOFTIRQ];
 		steal		= cpustat[CPUTIME_STEAL];
@@ -187,6 +232,9 @@ static int show_stat(struct seq_file *p, void *v)
 		seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
 		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
 		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
+#ifdef CONFIG_SCHED_CORE
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(forceidle));
+#endif
 		seq_putc(p, '\n');
 	}
 	seq_put_decimal_ull(p, "intr ", (unsigned long long)sum);
include/linux/kernel_stat.h +1 -0
index 89f0745c096d..c7ce4bfe757e 100644
@@ -25,6 +25,7 @@ enum cpu_usage_stat {
 	CPUTIME_IRQ,
 	CPUTIME_IDLE,
 	CPUTIME_IOWAIT,
+	CPUTIME_FORCEIDLE,
 	CPUTIME_STEAL,
 	CPUTIME_GUEST,
 	CPUTIME_GUEST_NICE,
include/linux/tick.h +2 -0
index 7340613c7eff..7fce78f46930 100644
@@ -139,6 +139,7 @@ extern unsigned long tick_nohz_get_idle_calls(void);
 extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
 extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
+extern u64 get_cpu_forceidle_time_us(int cpu, u64 *last_update_time);
 
 static inline void tick_nohz_idle_stop_tick_protected(void)
 {
@@ -169,6 +170,7 @@ static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
 }
 static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
 static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; }
+static inline u64 get_cpu_forceidle_time_us(int cpu, u64 *unused) { return -1; }
 
 static inline void tick_nohz_idle_stop_tick_protected(void) { }
 #endif /* !CONFIG_NO_HZ_COMMON */
kernel/time/tick-sched.c +48 -0

66 lines not on this page · raw message

kernel/time/tick-sched.h +3 -0
index 4fb06527cf64..4c00c5399055 100644
@@ -71,6 +71,9 @@ struct tick_sched {
 	ktime_t				idle_exittime;
 	ktime_t				idle_sleeptime;
 	ktime_t				iowait_sleeptime;
+#ifdef CONFIG_SCHED_CORE
+	ktime_t				forceidle_sleeptime;
+#endif
 	unsigned long			last_jiffies;
 	u64				timer_expires;
 	u64				timer_expires_base;
Signature · 1 line
2.17.1