The patch titled
Subject: genriq: avoid summation loops for /proc/stat
has been added to the -mm tree. Its filename is
genriq-avoid-summation-loops-for-proc-stat.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/genriq-avoid-summation-loops-for-proc-stat.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/genriq-avoid-summation-loops-for-proc-stat.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Subject: genriq: avoid summation loops for /proc/stat
Patch series "genirq, proc: Speedup /proc/stat interrupt statistics", v2.
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 series addresses this by making the interrupt statitics code in the
core generate the sum directly and by making the loop in the /proc/stat
read function smarter.
This patch (of 2):
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.
Link: http://lkml.kernel.org/r/20190208135020.925487496@xxxxxxxxxxxxx
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Reported-by: Waiman Long <longman@xxxxxxxxxx>
Reviewed-by: Waiman Long <longman@xxxxxxxxxx>
Reviewed-by: Davidlohr Bueso <dbueso@xxxxxxx>
Reviewed-by: Marc Zyngier <marc.zyngier@xxxxxxx>
Cc: Alexey Dobriyan <adobriyan@xxxxxxxxx>
Cc: Daniel Colascione <dancol@xxxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Miklos Szeredi <miklos@xxxxxxxxxx>
Cc: Randy Dunlap <rdunlap@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
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~genriq-avoid-summation-loops-for-proc-stat
+++ a/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~genriq-avoid-summation-loops-for-proc-stat
+++ a/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~genriq-avoid-summation-loops-for-proc-stat
+++ a/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~genriq-avoid-summation-loops-for-proc-stat
+++ a/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;
_
Patches currently in -mm which might be from tglx@xxxxxxxxxxxxx are
genriq-avoid-summation-loops-for-proc-stat.patch
proc-stat-make-the-interrupt-statistics-more-efficient.patch
