# HG changeset patch
# User Keir Fraser <keir.fraser@xxxxxxxxxx>
# Date 1260777293 0
# Node ID 2d9c58c29a94033ad7e51c2ec23fc66a92a9e391
# Parent 3d505c9f1b7344e2debe4f1a905c6d42a179b93d
cpuidle: fix the menu governor to enhance IO performance
this is a revised version of linux upstream commit
69d25870f20c4b2563304f2b79c5300dd60a067e:
"
cpuidle: fix the menu governor to boost IO performance
Fix the menu idle governor which balances power savings, energy
efficiency
and performance impact.
The reason for a reworked governor is that there have been
serious
performance issues reported with the existing code on Nehalem
server
systems.
To show this I'm sure Andrew wants to see benchmark results:
(benchmark is "fio", "no cstates" is using "idle=3Dpoll")
no cstates current linux new algorithm
1 disk 107 Mb/s 85 Mb/s 105 Mb/s
2 disks 215 Mb/s 123 Mb/s 209 Mb/s
12 disks 590 Mb/s 320 Mb/s 585 Mb/s
In various power benchmark measurements, no degredation was found
by our
measurement&diagnostics team. Obviously a small percentage more
power was
used in the "fio" benchmark, due to the much higher performance.
Signed-off-by: Arjan van de Ven <arjan@xxxxxxxxxxxxxxx>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@xxxxxxxxx>
Cc: Len Brown <lenb@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Yanmin Zhang <yanmin_zhang@xxxxxxxxxxxxxxx>
Acked-by: Ingo Molnar <mingo@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
"
in Xen version, most logic is similar and with only one exception:
linux use nr_iowait and loadavg to track the pending I/O request,
which however is not visible to Xen. so Xen use the do_irq frequency
to estimate the I/O pressure. this is not as accurate as linux, and
the better approach is to convey guest latency requirement to
hypervisor by virtual C state. this can be the future enhancement.
the detail algorithm description is in code comment. with this new
algorithm, fio benchmark performance improve ~5% with 1 disk. and no
power degration is found in idle case.
Signed-off-by: Yu Ke <ke.yu@xxxxxxxxx>
---
xen/arch/x86/acpi/cpuidle_menu.c | 233 ++++++++++++++++++++++++++++++++-------
xen/arch/x86/hpet.c | 5
xen/arch/x86/irq.c | 4
xen/include/asm-x86/irq.h | 2
xen/include/xen/cpuidle.h | 2
5 files changed, 206 insertions(+), 40 deletions(-)
diff -r 3d505c9f1b73 -r 2d9c58c29a94 xen/arch/x86/acpi/cpuidle_menu.c
--- a/xen/arch/x86/acpi/cpuidle_menu.c Mon Dec 14 07:52:22 2009 +0000
+++ b/xen/arch/x86/acpi/cpuidle_menu.c Mon Dec 14 07:54:53 2009 +0000
@@ -30,22 +30,146 @@
#include <xen/acpi.h>
#include <xen/timer.h>
#include <xen/cpuidle.h>
-
-#define BREAK_FUZZ 4 /* 4 us */
-#define PRED_HISTORY_PCT 50
-#define USEC_PER_SEC 1000000
+#include <asm/irq.h>
+
+#define BUCKETS 6
+#define RESOLUTION 1024
+#define DECAY 4
+#define MAX_INTERESTING 50000
+
+/*
+ * Concepts and ideas behind the menu governor
+ *
+ * For the menu governor, there are 3 decision factors for picking a C
+ * state:
+ * 1) Energy break even point
+ * 2) Performance impact
+ * 3) Latency tolerance (TBD: from guest virtual C state)
+ * These these three factors are treated independently.
+ *
+ * Energy break even point
+ * -----------------------
+ * C state entry and exit have an energy cost, and a certain amount of time in
+ * the C state is required to actually break even on this cost. CPUIDLE
+ * provides us this duration in the "target_residency" field. So all that we
+ * need is a good prediction of how long we'll be idle. Like the traditional
+ * menu governor, we start with the actual known "next timer event" time.
+ *
+ * Since there are other source of wakeups (interrupts for example) than
+ * the next timer event, this estimation is rather optimistic. To get a
+ * more realistic estimate, a correction factor is applied to the estimate,
+ * that is based on historic behavior. For example, if in the past the actual
+ * duration always was 50% of the next timer tick, the correction factor will
+ * be 0.5.
+ *
+ * menu uses a running average for this correction factor, however it uses a
+ * set of factors, not just a single factor. This stems from the realization
+ * that the ratio is dependent on the order of magnitude of the expected
+ * duration; if we expect 500 milliseconds of idle time the likelihood of
+ * getting an interrupt very early is much higher than if we expect 50 micro
+ * seconds of idle time.
+ * For this reason we keep an array of 6 independent factors, that gets
+ * indexed based on the magnitude of the expected duration
+ *
+ * Limiting Performance Impact
+ * ---------------------------
+ * C states, especially those with large exit latencies, can have a real
+ * noticable impact on workloads, which is not acceptable for most sysadmins,
+ * and in addition, less performance has a power price of its own.
+ *
+ * As a general rule of thumb, menu assumes that the following heuristic
+ * holds:
+ * The busier the system, the less impact of C states is acceptable
+ *
+ * This rule-of-thumb is implemented using average interrupt interval:
+ * If the exit latency times multiplier is longer than the average
+ * interrupt interval, the C state is not considered a candidate
+ * for selection due to a too high performance impact. So the smaller
+ * the average interrupt interval is, the smaller C state latency should be
+ * and thus the less likely a busy CPU will hit such a deep C state.
+ *
+ */
+
+struct perf_factor{
+ s_time_t time_stamp;
+ s_time_t duration;
+ unsigned int irq_count_stamp;
+ unsigned int irq_sum;
+};
struct menu_device
{
int last_state_idx;
unsigned int expected_us;
- unsigned int predicted_us;
- unsigned int current_predicted_us;
- unsigned int last_measured_us;
- unsigned int elapsed_us;
+ u64 predicted_us;
+ unsigned int measured_us;
+ unsigned int exit_us;
+ unsigned int bucket;
+ u64 correction_factor[BUCKETS];
+ struct perf_factor pf;
};
static DEFINE_PER_CPU(struct menu_device, menu_devices);
+
+static inline int which_bucket(unsigned int duration)
+{
+ int bucket = 0;
+
+ if (duration < 10)
+ return bucket;
+ if (duration < 100)
+ return bucket + 1;
+ if (duration < 1000)
+ return bucket + 2;
+ if (duration < 10000)
+ return bucket + 3;
+ if (duration < 100000)
+ return bucket + 4;
+ return bucket + 5;
+}
+
+/*
+ * Return the average interrupt interval to take I/O performance
+ * requirements into account. The smaller the average interrupt
+ * interval to be, the more busy I/O activity, and thus the higher
+ * the barrier to go to an expensive C state.
+ */
+
+/* 5 milisec sampling period */
+#define SAMPLING_PERIOD 5000000
+
+/* for I/O interrupt, we give 8x multiplier compared to C state latency*/
+#define IO_MULTIPLIER 8
+
+static inline s_time_t avg_intr_interval_us(void)
+{
+ struct menu_device *data = &__get_cpu_var(menu_devices);
+ s_time_t duration, now;
+ s_time_t avg_interval;
+ unsigned int irq_sum;
+
+ now = NOW();
+ duration = (data->pf.duration + (now - data->pf.time_stamp)
+ * (DECAY - 1)) / DECAY;
+
+ irq_sum = (data->pf.irq_sum + (this_cpu(irq_count) -
data->pf.irq_count_stamp)
+ * (DECAY - 1)) / DECAY;
+
+ if (irq_sum == 0)
+ /* no irq recently, so return a big enough interval: 1 sec */
+ avg_interval = 1000000;
+ else
+ avg_interval = duration / irq_sum / 1000; /* in us */
+
+ if ( duration >= SAMPLING_PERIOD){
+ data->pf.time_stamp = now;
+ data->pf.duration = duration;
+ data->pf.irq_count_stamp= this_cpu(irq_count);
+ data->pf.irq_sum = irq_sum;
+ }
+
+ return avg_interval;
+}
static unsigned int get_sleep_length_us(void)
{
@@ -62,57 +186,86 @@ static int menu_select(struct acpi_proce
{
struct menu_device *data = &__get_cpu_var(menu_devices);
int i;
-
- /* determine the expected residency time */
+ s_time_t io_interval;
+
+ /* TBD: Change to 0 if C0(polling mode) support is added later*/
+ data->last_state_idx = CPUIDLE_DRIVER_STATE_START;
+ data->exit_us = 0;
+
+ /* determine the expected residency time, round up */
data->expected_us = get_sleep_length_us();
- /* Recalculate predicted_us based on prediction_history_pct */
- data->predicted_us *= PRED_HISTORY_PCT;
- data->predicted_us += (100 - PRED_HISTORY_PCT) *
- data->current_predicted_us;
- data->predicted_us /= 100;
+ data->bucket = which_bucket(data->expected_us);
+
+ io_interval = avg_intr_interval_us();
+
+ /*
+ * if the correction factor is 0 (eg first time init or cpu hotplug
+ * etc), we actually want to start out with a unity factor.
+ */
+ if (data->correction_factor[data->bucket] == 0)
+ data->correction_factor[data->bucket] = RESOLUTION * DECAY;
+
+ /* Make sure to round up for half microseconds */
+ data->predicted_us = DIV_ROUND(
+ data->expected_us * data->correction_factor[data->bucket],
+ RESOLUTION * DECAY);
/* find the deepest idle state that satisfies our constraints */
- for ( i = 2; i < power->count; i++ )
+ for ( i = CPUIDLE_DRIVER_STATE_START + 1; i < power->count; i++ )
{
struct acpi_processor_cx *s = &power->states[i];
- if ( s->target_residency > data->expected_us + s->latency )
+ if (s->target_residency > data->predicted_us)
break;
- if ( s->target_residency > data->predicted_us )
+ if (s->latency * IO_MULTIPLIER > io_interval)
break;
/* TBD: we need to check the QoS requirment in future */
+ data->exit_us = s->latency;
+ data->last_state_idx = i;
}
- data->last_state_idx = i - 1;
- return i - 1;
+ return data->last_state_idx;
}
static void menu_reflect(struct acpi_processor_power *power)
{
struct menu_device *data = &__get_cpu_var(menu_devices);
- struct acpi_processor_cx *target = &power->states[data->last_state_idx];
- unsigned int last_residency;
+ unsigned int last_idle_us = power->last_residency;
unsigned int measured_us;
-
- last_residency = power->last_residency;
- measured_us = last_residency + data->elapsed_us;
-
- /* if wrapping, set to max uint (-1) */
- measured_us = data->elapsed_us <= measured_us ? measured_us : -1;
-
- /* Predict time remaining until next break event */
- data->current_predicted_us = max(measured_us, data->last_measured_us);
-
- /* Distinguish between expected & non-expected events */
- if ( last_residency + BREAK_FUZZ
- < data->expected_us + target->latency )
- {
- data->last_measured_us = measured_us;
- data->elapsed_us = 0;
- }
+ u64 new_factor;
+
+ measured_us = last_idle_us;
+
+ /*
+ * We correct for the exit latency; we are assuming here that the
+ * exit latency happens after the event that we're interested in.
+ */
+ if (measured_us > data->exit_us)
+ measured_us -= data->exit_us;
+
+ /* update our correction ratio */
+
+ new_factor = data->correction_factor[data->bucket]
+ * (DECAY - 1) / DECAY;
+
+ if (data->expected_us > 0 && data->measured_us < MAX_INTERESTING)
+ new_factor += RESOLUTION * measured_us / data->expected_us;
else
- data->elapsed_us = measured_us;
+ /*
+ * we were idle so long that we count it as a perfect
+ * prediction
+ */
+ new_factor += RESOLUTION;
+
+ /*
+ * We don't want 0 as factor; we always want at least
+ * a tiny bit of estimated time.
+ */
+ if (new_factor == 0)
+ new_factor = 1;
+
+ data->correction_factor[data->bucket] = new_factor;
}
static int menu_enable_device(struct acpi_processor_power *power)
diff -r 3d505c9f1b73 -r 2d9c58c29a94 xen/arch/x86/hpet.c
--- a/xen/arch/x86/hpet.c Mon Dec 14 07:52:22 2009 +0000
+++ b/xen/arch/x86/hpet.c Mon Dec 14 07:54:53 2009 +0000
@@ -211,6 +211,9 @@ static void hpet_interrupt_handler(int i
struct cpu_user_regs *regs)
{
struct hpet_event_channel *ch = (struct hpet_event_channel *)data;
+
+ this_cpu(irq_count)--;
+
if ( !ch->event_handler )
{
printk(XENLOG_WARNING "Spurious HPET timer interrupt on HPET timer
%d\n", ch->idx);
@@ -692,6 +695,8 @@ int hpet_broadcast_is_available(void)
int hpet_legacy_irq_tick(void)
{
+ this_cpu(irq_count)--;
+
if ( !legacy_hpet_event.event_handler )
return 0;
legacy_hpet_event.event_handler(&legacy_hpet_event);
diff -r 3d505c9f1b73 -r 2d9c58c29a94 xen/arch/x86/irq.c
--- a/xen/arch/x86/irq.c Mon Dec 14 07:52:22 2009 +0000
+++ b/xen/arch/x86/irq.c Mon Dec 14 07:54:53 2009 +0000
@@ -517,6 +517,8 @@ void irq_set_affinity(int irq, cpumask_t
cpus_copy(desc->pending_mask, mask);
}
+DEFINE_PER_CPU(unsigned int, irq_count);
+
asmlinkage void do_IRQ(struct cpu_user_regs *regs)
{
struct irqaction *action;
@@ -527,6 +529,8 @@ asmlinkage void do_IRQ(struct cpu_user_r
struct cpu_user_regs *old_regs = set_irq_regs(regs);
perfc_incr(irqs);
+
+ this_cpu(irq_count)++;
if (irq < 0) {
ack_APIC_irq();
diff -r 3d505c9f1b73 -r 2d9c58c29a94 xen/include/asm-x86/irq.h
--- a/xen/include/asm-x86/irq.h Mon Dec 14 07:52:22 2009 +0000
+++ b/xen/include/asm-x86/irq.h Mon Dec 14 07:54:53 2009 +0000
@@ -105,6 +105,8 @@ extern atomic_t irq_err_count;
extern atomic_t irq_err_count;
extern atomic_t irq_mis_count;
+DECLARE_PER_CPU(unsigned int, irq_count);
+
int pirq_shared(struct domain *d , int irq);
int map_domain_pirq(struct domain *d, int pirq, int irq, int type,
diff -r 3d505c9f1b73 -r 2d9c58c29a94 xen/include/xen/cpuidle.h
--- a/xen/include/xen/cpuidle.h Mon Dec 14 07:52:22 2009 +0000
+++ b/xen/include/xen/cpuidle.h Mon Dec 14 07:54:53 2009 +0000
@@ -86,4 +86,6 @@ extern struct cpuidle_governor *cpuidle_
extern struct cpuidle_governor *cpuidle_current_governor;
void cpuidle_disable_deep_cstate(void);
+#define CPUIDLE_DRIVER_STATE_START 1
+
#endif /* _XEN_CPUIDLE_H */
_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog
|
Home