Add two new metrics for CPU idle states, "above" and "below", to count
the number of times the given state had been asked for (or entered
from the kernel's perspective), but the observed idle duration turned
out to be too short or too long for it (respectively).
These metrics help to estimate the quality of the CPU idle governor
in use.
Signed-off-by: Rafael J. Wysocki <[email protected]>
/sys/devices/system/cpu/cpuX/cpuidle/stateN/power
/sys/devices/system/cpu/cpuX/cpuidle/stateN/time
/sys/devices/system/cpu/cpuX/cpuidle/stateN/usage
+ /sys/devices/system/cpu/cpuX/cpuidle/stateN/above
+ /sys/devices/system/cpu/cpuX/cpuidle/stateN/below
Date: September 2007
KernelVersion: v2.6.24
usage: (RO) Number of times this state was entered (a count).
+ above: (RO) Number of times this state was entered, but the
+ observed CPU idle duration was too short for it (a count).
+
+ below: (RO) Number of times this state was entered, but the
+ observed CPU idle duration was too long for it (a count).
What: /sys/devices/system/cpu/cpuX/cpuidle/stateN/desc
Date: February 2008
a number of files (attributes) representing the properties of the idle state
object corresponding to it, as follows:
+``above``
+ Total number of times this idle state had been asked for, but the
+ observed idle duration was certainly too short to match its target
+ residency.
+
+``below``
+ Total number of times this idle state had been asked for, but cerainly
+ a deeper idle state would have been a better match for the observed idle
+ duration.
+
``desc``
Description of the idle state.
struct cpuidle_state *target_state = &drv->states[index];
bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP);
ktime_t time_start, time_end;
- s64 diff;
/*
* Tell the time framework to switch to a broadcast timer because our
local_irq_enable();
if (entered_state >= 0) {
+ s64 diff, delay = drv->states[entered_state].exit_latency;
+ int i;
+
/*
* Update cpuidle counters
* This can be moved to within driver enter routine,
dev->last_residency = (int)diff;
dev->states_usage[entered_state].time += dev->last_residency;
dev->states_usage[entered_state].usage++;
+
+ if (diff < drv->states[entered_state].target_residency) {
+ for (i = entered_state - 1; i >= 0; i--) {
+ if (drv->states[i].disabled ||
+ dev->states_usage[i].disable)
+ continue;
+
+ /* Shallower states are enabled, so update. */
+ dev->states_usage[entered_state].above++;
+ break;
+ }
+ } else if (diff > delay) {
+ for (i = entered_state + 1; i < drv->state_count; i++) {
+ if (drv->states[i].disabled ||
+ dev->states_usage[i].disable)
+ continue;
+
+ /*
+ * Update if a deeper state would have been a
+ * better match for the observed idle duration.
+ */
+ if (diff - delay >= drv->states[i].target_residency)
+ dev->states_usage[entered_state].below++;
+
+ break;
+ }
+ }
} else {
dev->last_residency = 0;
}
define_show_state_str_function(desc)
define_show_state_ull_function(disable)
define_store_state_ull_function(disable)
+define_show_state_ull_function(above)
+define_show_state_ull_function(below)
define_one_state_ro(name, show_state_name);
define_one_state_ro(desc, show_state_desc);
define_one_state_ro(usage, show_state_usage);
define_one_state_ro(time, show_state_time);
define_one_state_rw(disable, show_state_disable, store_state_disable);
+define_one_state_ro(above, show_state_above);
+define_one_state_ro(below, show_state_below);
static struct attribute *cpuidle_state_default_attrs[] = {
&attr_name.attr,
&attr_usage.attr,
&attr_time.attr,
&attr_disable.attr,
+ &attr_above.attr,
+ &attr_below.attr,
NULL
};
unsigned long long disable;
unsigned long long usage;
unsigned long long time; /* in US */
+ unsigned long long above; /* Number of times it's been too deep */
+ unsigned long long below; /* Number of times it's been too shallow */
#ifdef CONFIG_SUSPEND
unsigned long long s2idle_usage;
unsigned long long s2idle_time; /* in US */