[PATCH 3/5] timer: Change idle/iowait accounting semantics

From: Frederic Weisbecker
Date: Sat Oct 19 2013 - 11:18:41 EST


To prepare for fixing a race between iowait and idle time stats,
this patch changes the following semantics:

* iowait time is going to be accounted from the scheduler rather than
the dynticks idle code, lets remove it from the /proc/timer_list dump.

* idle sleeptime now also includes the iowait time for simplicity.
Its accounting was relying on nr_iowait_cpu() which made the whole
share of time accounting between idle and iowait very racy. So
accounting the whole sleeptime in ts->idle_sleeptime makes it more
simple and improve its correctness.

Given the semantic change of ts->idle_sleeptime, it results in another
ABI change on /proc/timer_list for this field.

/proc/stat and other callers of get_cpu_idle_time_us() and
get_cpu_iowait_time_us() are not concerned though because we maintain
the old ABI by substracting the iowait time from the idle time.

Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
Cc: Fernando Luis Vazquez Cao <fernando_b1@xxxxxxxxxxxxx>
Cc: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Arjan van de Ven <arjan@xxxxxxxxxxxxxxx>
Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
---
include/linux/ktime.h | 7 +++++++
kernel/time/tick-sched.c | 12 +++++++++---
kernel/time/timer_list.c | 3 +--
3 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 31c0cd1..7a98f6a 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -379,6 +379,13 @@ static inline ktime_t ns_to_ktime(u64 ns)
return ktime_add_ns(ktime_zero, ns);
}

+static inline ktime_t us_to_ktime(u64 us)
+{
+ static const ktime_t ktime_zero = { .tv64 = 0 };
+
+ return ktime_add_us(ktime_zero, us);
+}
+
static inline ktime_t ms_to_ktime(u64 ms)
{
static const ktime_t ktime_zero = { .tv64 = 0 };
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 7f0fb78..fbcb249 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -410,8 +410,8 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
delta = ktime_sub(now, ts->idle_entrytime);
if (nr_iowait_cpu(smp_processor_id()) > 0)
ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
- else
- ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+
+ ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
ts->idle_active = 0;

sched_clock_idle_wakeup_event(0);
@@ -445,6 +445,7 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
ktime_t now, idle;
+ u64 iowait;

if (!tick_nohz_enabled)
return -1;
@@ -453,13 +454,18 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
if (last_update_time)
*last_update_time = ktime_to_us(now);

- if (ts->idle_active && !nr_iowait_cpu(cpu)) {
+ if (ts->idle_active) {
ktime_t delta = ktime_sub(now, ts->idle_entrytime);
idle = ktime_add(ts->idle_sleeptime, delta);
} else {
idle = ts->idle_sleeptime;
}

+ iowait = get_cpu_iowait_time_us(cpu, NULL);
+
+ if (ktime_compare(idle, us_to_ktime(iowait)) > 0)
+ idle = ktime_sub_us(idle, iowait);
+
return ktime_to_us(idle);

}
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 61ed862..9a3f8e2 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -182,7 +182,6 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
P_ns(idle_waketime);
P_ns(idle_exittime);
P_ns(idle_sleeptime);
- P_ns(iowait_sleeptime);
P(last_jiffies);
P(next_jiffies);
P_ns(idle_expires);
@@ -256,7 +255,7 @@ static void timer_list_show_tickdevices_header(struct seq_file *m)

static inline void timer_list_header(struct seq_file *m, u64 now)
{
- SEQ_printf(m, "Timer List Version: v0.7\n");
+ SEQ_printf(m, "Timer List Version: v0.8\n");
SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
SEQ_printf(m, "\n");
--
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/