diff options
Diffstat (limited to 'drivers/cpuidle/governors/menu.c')
| -rw-r--r-- | drivers/cpuidle/governors/menu.c | 75 |
1 files changed, 66 insertions, 9 deletions
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 73655aeb3a60..1b128702d300 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -21,9 +21,12 @@ #include <linux/math64.h> #define BUCKETS 12 +#define INTERVALS 8 #define RESOLUTION 1024 -#define DECAY 4 +#define DECAY 8 #define MAX_INTERESTING 50000 +#define STDDEV_THRESH 400 + /* * Concepts and ideas behind the menu governor @@ -64,6 +67,16 @@ * indexed based on the magnitude of the expected duration as well as the * "is IO outstanding" property. * + * Repeatable-interval-detector + * ---------------------------- + * There are some cases where "next timer" is a completely unusable predictor: + * Those cases where the interval is fixed, for example due to hardware + * interrupt mitigation, but also due to fixed transfer rate devices such as + * mice. + * For this, we use a different predictor: We track the duration of the last 8 + * intervals and if the stand deviation of these 8 intervals is below a + * threshold value, we use the average of these intervals as prediction. + * * Limiting Performance Impact * --------------------------- * C states, especially those with large exit latencies, can have a real @@ -101,10 +114,11 @@ struct menu_device { unsigned int expected_us; u64 predicted_us; - unsigned int measured_us; unsigned int exit_us; unsigned int bucket; u64 correction_factor[BUCKETS]; + u32 intervals[INTERVALS]; + int interval_ptr; }; @@ -129,7 +143,7 @@ static inline int which_bucket(unsigned int duration) * This allows us to calculate * E(duration)|iowait */ - if (nr_iowait_cpu()) + if (nr_iowait_cpu(smp_processor_id())) bucket = BUCKETS/2; if (duration < 10) @@ -161,7 +175,7 @@ static inline int performance_multiplier(void) mult += 2 * get_loadavg(); /* for IO wait tasks (per cpu!) we add 5x each */ - mult += 10 * nr_iowait_cpu(); + mult += 10 * nr_iowait_cpu(smp_processor_id()); return mult; } @@ -176,6 +190,42 @@ static u64 div_round64(u64 dividend, u32 divisor) return div_u64(dividend + (divisor / 2), divisor); } +/* + * Try detecting repeating patterns by keeping track of the last 8 + * intervals, and checking if the standard deviation of that set + * of points is below a threshold. If it is... then use the + * average of these 8 points as the estimated value. + */ +static void detect_repeating_patterns(struct menu_device *data) +{ + int i; + uint64_t avg = 0; + uint64_t stddev = 0; /* contains the square of the std deviation */ + + /* first calculate average and standard deviation of the past */ + for (i = 0; i < INTERVALS; i++) + avg += data->intervals[i]; + avg = avg / INTERVALS; + + /* if the avg is beyond the known next tick, it's worthless */ + if (avg > data->expected_us) + return; + + for (i = 0; i < INTERVALS; i++) + stddev += (data->intervals[i] - avg) * + (data->intervals[i] - avg); + + stddev = stddev / INTERVALS; + + /* + * now.. if stddev is small.. then assume we have a + * repeating pattern and predict we keep doing this. + */ + + if (avg && stddev < STDDEV_THRESH) + data->predicted_us = avg; +} + /** * menu_select - selects the next idle state to enter * @dev: the CPU @@ -183,18 +233,18 @@ static u64 div_round64(u64 dividend, u32 divisor) static int menu_select(struct cpuidle_device *dev) { struct menu_device *data = &__get_cpu_var(menu_devices); - int latency_req = pm_qos_requirement(PM_QOS_CPU_DMA_LATENCY); + int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY); int i; int multiplier; - data->last_state_idx = 0; - data->exit_us = 0; - if (data->needs_update) { menu_update(dev); data->needs_update = 0; } + data->last_state_idx = 0; + data->exit_us = 0; + /* Special case when user has set very strict latency requirement */ if (unlikely(latency_req == 0)) return 0; @@ -219,6 +269,8 @@ static int menu_select(struct cpuidle_device *dev) data->predicted_us = div_round64(data->expected_us * data->correction_factor[data->bucket], RESOLUTION * DECAY); + detect_repeating_patterns(data); + /* * We want to default to C1 (hlt), not to busy polling * unless the timer is happening really really soon. @@ -294,7 +346,7 @@ static void menu_update(struct cpuidle_device *dev) new_factor = data->correction_factor[data->bucket] * (DECAY - 1) / DECAY; - if (data->expected_us > 0 && data->measured_us < MAX_INTERESTING) + if (data->expected_us > 0 && measured_us < MAX_INTERESTING) new_factor += RESOLUTION * measured_us / data->expected_us; else /* @@ -311,6 +363,11 @@ static void menu_update(struct cpuidle_device *dev) new_factor = 1; data->correction_factor[data->bucket] = new_factor; + + /* update the repeating-pattern data */ + data->intervals[data->interval_ptr++] = last_idle_us; + if (data->interval_ptr >= INTERVALS) + data->interval_ptr = 0; } /** |