lkml.org 
[lkml]   [2019]   [Jan]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
SubjectRe: [PATCH v3 4/4] /proc/stat: Call kstat_irqs_usr() only for active IRQs
On Wed, 9 Jan 2019, Waiman Long wrote:
> ---
> fs/proc/stat.c | 84 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 84 insertions(+)

and the total diffstat of that patch series is:

4 files changed, 125 insertions(+), 12 deletions(-)

> static void show_stat_irqs(struct seq_file *p)
> @@ -100,9 +119,74 @@ static void show_stat_irqs(struct seq_file *p)
> int i;
>
> seq_put_decimal_ull(p, "intr ", compute_stat_irqs_sum());
> +
> + if (IS_ENABLED(CONFIG_SMP) && (nr_cpu_ids >= 10) && (nr_irqs >= 256)) {
> + /*
> + * On systems with 10 or more CPUs and 256 or more IRQs,
> + * we used a bitmap to keep track of the number of active
> + * IRQs and call kstat_irqs_usr() only for those IRQs.
> + * The bitmap will be refreshed whenever nr_active_irqs
> + * changes.
> + */
> + extern atomic_t nr_active_irqs;
> + static DEFINE_MUTEX(irqs_mutex);
> + static int last_irq = -1;
> + static int bitmap_size, active_irqs;
> + static unsigned long *bitmap;
> + int current_irqs = atomic_read(&nr_active_irqs);

This is completely overengineered. The simple patch below does not need
conditionals and atomics, is unconditional and completely avoids this
bitmap hackery.

On a VM with 144 VCPUs and nr_irqs=1576 and a loop of 5000 readouts of
/proc/stat (python):

Before After
real 0m1.331s 0m0.728s -45.3%
user 0m0.415s 0m0.359s -13.5%
sys 0m0.914s 0m0.356s -61.1%

Hmm?

Thanks,

tglx

8<------------------

fs/proc/stat.c | 28 +++++++++++++++++++++++++---
include/linux/irqdesc.h | 3 ++-
kernel/irq/internals.h | 1 +
kernel/irq/irqdesc.c | 7 ++-----
4 files changed, 30 insertions(+), 9 deletions(-)

--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -79,6 +79,30 @@ static u64 get_iowait_time(int cpu)

#endif

+static void show_irq_gap(struct seq_file *p, int gap)
+{
+ static const char zeros[] = " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0";
+
+ while (gap > 0) {
+ int inc = min_t(int, gap, ARRAY_SIZE(zeros) / 2);
+
+ seq_write(p, zeros, 2 * inc);
+ gap -= inc;
+ }
+}
+
+static void show_all_irqs(struct seq_file *p)
+{
+ int i, next = 0;
+
+ for_each_active_irq(i) {
+ show_irq_gap(p, i - next);
+ seq_put_decimal_ull(p, " ", kstat_irqs_usr(i));
+ next = i + 1;
+ }
+ show_irq_gap(p, nr_irqs - next);
+}
+
static int show_stat(struct seq_file *p, void *v)
{
int i, j;
@@ -156,9 +180,7 @@ static int show_stat(struct seq_file *p,
}
seq_put_decimal_ull(p, "intr ", (unsigned long long)sum);

- /* sum again ? it could be updated? */
- for_each_irq_nr(j)
- seq_put_decimal_ull(p, " ", kstat_irqs_usr(j));
+ show_all_irqs(p);

seq_printf(p,
"\nctxt %llu\n"
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -65,9 +65,10 @@ 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;
+ unsigned long last_unhandled; /* Aging timer for unhandled count */
atomic_t threads_handled;
int threads_handled_last;
raw_spinlock_t lock;
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -246,6 +246,7 @@ static inline void kstat_incr_irqs_this_
{
__this_cpu_inc(*desc->kstat_irqs);
__this_cpu_inc(kstat.irqs_sum);
+ desc->tot_count++;
}

static inline int irq_desc_get_node(struct irq_desc *desc)
--- 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)
@@ -919,14 +920,10 @@ 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;

if (!desc || !desc->kstat_irqs)
return 0;
- for_each_possible_cpu(cpu)
- sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
- return sum;
+ return desc->tot_count;
}

/**

\
 
 \ /
  Last update: 2019-01-11 18:24    [W:0.063 / U:0.184 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site