Waiman reported that on large systems with a large amount of interrupts the
readout of /proc/stat takes a long time to sum up the interrupt
statistics. In principle this is not a problem. but for unknown reasons
some enterprise quality software reads /proc/stat with a high frequency.
The reason for this is that interrupt statistics are accounted per cpu. So
the /proc/stat logic has to sum up the interrupt stats for each interrupt.
This can be largely avoided for interrupts which are not marked as
'PER_CPU' interrupts by simply adding a per interrupt summation counter
which is incremented along with the per interrupt per cpu counter.
The PER_CPU interrupts need to avoid that and use only per cpu accounting
because they share the interrupt number and the interrupt descriptor and
concurrent updates would conflict or require unwanted synchronization.
Reported-by: Waiman Long <longman@xxxxxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
8<-------------
v2: Undo the unintentional layout change of struct irq_desc.
include/linux/irqdesc.h | 1 +
kernel/irq/chip.c | 12 ++++++++++--
kernel/irq/internals.h | 8 +++++++-
kernel/irq/irqdesc.c | 7 ++++++-
4 files changed, 24 insertions(+), 4 deletions(-)
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -65,6 +65,7 @@ struct irq_desc {
unsigned int core_internal_state__do_not_mess_with_it;
unsigned int depth; /* nested irq disables */
unsigned int wake_depth; /* nested wake enables */
+ unsigned int tot_count;
unsigned int irq_count; /* For detecting broken IRQs */
unsigned long last_unhandled; /* Aging timer for unhandled count */
unsigned int irqs_unhandled;
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -855,7 +855,11 @@ void handle_percpu_irq(struct irq_desc *
{
struct irq_chip *chip = irq_desc_get_chip(desc);
- kstat_incr_irqs_this_cpu(desc);
+ /*
+ * PER CPU interrupts are not serialized. Do not touch
+ * desc->tot_count.
+ */
+ __kstat_incr_irqs_this_cpu(desc);
if (chip->irq_ack)
chip->irq_ack(&desc->irq_data);
@@ -884,7 +888,11 @@ void handle_percpu_devid_irq(struct irq_
unsigned int irq = irq_desc_get_irq(desc);
irqreturn_t res;
- kstat_incr_irqs_this_cpu(desc);
+ /*
+ * PER CPU interrupts are not serialized. Do not touch
+ * desc->tot_count.
+ */
+ __kstat_incr_irqs_this_cpu(desc);
if (chip->irq_ack)
chip->irq_ack(&desc->irq_data);
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -242,12 +242,18 @@ static inline void irq_state_set_masked(
#undef __irqd_to_state
-static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc)
{
__this_cpu_inc(*desc->kstat_irqs);
__this_cpu_inc(kstat.irqs_sum);
}
+static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
+{
+ __kstat_incr_irqs_this_cpu(desc);
+ desc->tot_count++;
+}
+
static inline int irq_desc_get_node(struct irq_desc *desc)
{
return irq_common_data_get_node(&desc->irq_common_data);
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -119,6 +119,7 @@ static void desc_set_defaults(unsigned i
desc->depth = 1;
desc->irq_count = 0;
desc->irqs_unhandled = 0;
+ desc->tot_count = 0;
desc->name = NULL;
desc->owner = owner;
for_each_possible_cpu(cpu)
@@ -919,11 +920,15 @@ unsigned int kstat_irqs_cpu(unsigned int
unsigned int kstat_irqs(unsigned int irq)
{
struct irq_desc *desc = irq_to_desc(irq);
- int cpu;
unsigned int sum = 0;
+ int cpu;
if (!desc || !desc->kstat_irqs)
return 0;
+ if (!irq_settings_is_per_cpu_devid(desc) &&
+ !irq_settings_is_per_cpu(desc))
+ return desc->tot_count;
+
for_each_possible_cpu(cpu)
sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
return sum;
