linux/fs/proc/stat.c
Thomas Gleixner c2da3f1b71 proc/stat: Make the interrupt statistics more efficient
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.

The interrupt core provides now a per interrupt summary counter which can
be used to avoid the summation loops completely except for interrupts
marked PER_CPU which are only a small fraction of the interrupt space if at
all.

Another simplification is to iterate only over the active interrupts and
skip the potentially large gaps in the interrupt number space and just
print zeros for the gaps without going into the interrupt core in the first
place.

Waiman provided test results from a 4-socket IvyBridge-EX system (60-core
120-thread, 3016 irqs) excuting a test program which reads /proc/stat
50,000 times:

   Before: 18.436s (sys 18.380s)
   After:   3.769s (sys  3.742s)

Reported-by: Waiman Long <longman@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Alexey Dobriyan <adobriyan@gmail.com>
Reviewed-by: Waiman Long <longman@redhat.com>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Reviewed-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Daniel Colascione <dancol@google.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Link: https://lkml.kernel.org/r/20190208135021.013828701@linutronix.de
2019-02-10 21:34:46 +01:00

229 lines
6.0 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/cpumask.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/proc_fs.h>
#include <linux/sched.h>
#include <linux/sched/stat.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/irqnr.h>
#include <linux/sched/cputime.h>
#include <linux/tick.h>
#ifndef arch_irq_stat_cpu
#define arch_irq_stat_cpu(cpu) 0
#endif
#ifndef arch_irq_stat
#define arch_irq_stat() 0
#endif
#ifdef arch_idle_time
static u64 get_idle_time(int cpu)
{
u64 idle;
idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
idle += arch_idle_time(cpu);
return idle;
}
static u64 get_iowait_time(int cpu)
{
u64 iowait;
iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
if (cpu_online(cpu) && nr_iowait_cpu(cpu))
iowait += arch_idle_time(cpu);
return iowait;
}
#else
static u64 get_idle_time(int cpu)
{
u64 idle, idle_usecs = -1ULL;
if (cpu_online(cpu))
idle_usecs = get_cpu_idle_time_us(cpu, NULL);
if (idle_usecs == -1ULL)
/* !NO_HZ or cpu offline so we can rely on cpustat.idle */
idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
else
idle = idle_usecs * NSEC_PER_USEC;
return idle;
}
static u64 get_iowait_time(int cpu)
{
u64 iowait, iowait_usecs = -1ULL;
if (cpu_online(cpu))
iowait_usecs = get_cpu_iowait_time_us(cpu, NULL);
if (iowait_usecs == -1ULL)
/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
else
iowait = iowait_usecs * NSEC_PER_USEC;
return iowait;
}
#endif
static void show_irq_gap(struct seq_file *p, unsigned 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) {
unsigned int inc;
inc = min_t(unsigned int, gap, ARRAY_SIZE(zeros) / 2);
seq_write(p, zeros, 2 * inc);
gap -= inc;
}
}
static void show_all_irqs(struct seq_file *p)
{
unsigned 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;
u64 user, nice, system, idle, iowait, irq, softirq, steal;
u64 guest, guest_nice;
u64 sum = 0;
u64 sum_softirq = 0;
unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
struct timespec64 boottime;
user = nice = system = idle = iowait =
irq = softirq = steal = 0;
guest = guest_nice = 0;
getboottime64(&boottime);
for_each_possible_cpu(i) {
user += kcpustat_cpu(i).cpustat[CPUTIME_USER];
nice += kcpustat_cpu(i).cpustat[CPUTIME_NICE];
system += kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];
idle += get_idle_time(i);
iowait += get_iowait_time(i);
irq += kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
softirq += kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];
steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
guest_nice += kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
sum += kstat_cpu_irqs_sum(i);
sum += arch_irq_stat_cpu(i);
for (j = 0; j < NR_SOFTIRQS; j++) {
unsigned int softirq_stat = kstat_softirqs_cpu(j, i);
per_softirq_sums[j] += softirq_stat;
sum_softirq += softirq_stat;
}
}
sum += arch_irq_stat();
seq_put_decimal_ull(p, "cpu ", nsec_to_clock_t(user));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
seq_putc(p, '\n');
for_each_online_cpu(i) {
/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
user = kcpustat_cpu(i).cpustat[CPUTIME_USER];
nice = kcpustat_cpu(i).cpustat[CPUTIME_NICE];
system = kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];
idle = get_idle_time(i);
iowait = get_iowait_time(i);
irq = kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
softirq = kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];
steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
seq_printf(p, "cpu%d", i);
seq_put_decimal_ull(p, " ", nsec_to_clock_t(user));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
seq_putc(p, '\n');
}
seq_put_decimal_ull(p, "intr ", (unsigned long long)sum);
show_all_irqs(p);
seq_printf(p,
"\nctxt %llu\n"
"btime %llu\n"
"processes %lu\n"
"procs_running %lu\n"
"procs_blocked %lu\n",
nr_context_switches(),
(unsigned long long)boottime.tv_sec,
total_forks,
nr_running(),
nr_iowait());
seq_put_decimal_ull(p, "softirq ", (unsigned long long)sum_softirq);
for (i = 0; i < NR_SOFTIRQS; i++)
seq_put_decimal_ull(p, " ", per_softirq_sums[i]);
seq_putc(p, '\n');
return 0;
}
static int stat_open(struct inode *inode, struct file *file)
{
unsigned int size = 1024 + 128 * num_online_cpus();
/* minimum size to display an interrupt count : 2 bytes */
size += 2 * nr_irqs;
return single_open_size(file, show_stat, NULL, size);
}
static const struct file_operations proc_stat_operations = {
.open = stat_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static int __init proc_stat_init(void)
{
proc_create("stat", 0, NULL, &proc_stat_operations);
return 0;
}
fs_initcall(proc_stat_init);