linux/fs/proc/stat.c
KAMEZAWA Hiroyuki 1ac101a5d6 procfs: add num_to_str() to speed up /proc/stat
== stat_check.py
num = 0
with open("/proc/stat") as f:
        while num < 1000 :
                data = f.read()
                f.seek(0, 0)
                num = num + 1
==

perf shows

    20.39%  stat_check.py  [kernel.kallsyms]    [k] format_decode
    13.41%  stat_check.py  [kernel.kallsyms]    [k] number
    12.61%  stat_check.py  [kernel.kallsyms]    [k] vsnprintf
    10.85%  stat_check.py  [kernel.kallsyms]    [k] memcpy
     4.85%  stat_check.py  [kernel.kallsyms]    [k] radix_tree_lookup
     4.43%  stat_check.py  [kernel.kallsyms]    [k] seq_printf

This patch removes most of calls to vsnprintf() by adding num_to_str()
and seq_print_decimal_ull(), which prints decimal numbers without rich
functions provided by printf().

On my 8cpu box.
== Before patch ==
[root@bluextal test]# time ./stat_check.py

real    0m0.150s
user    0m0.026s
sys     0m0.121s

== After patch ==
[root@bluextal test]# time ./stat_check.py

real    0m0.055s
user    0m0.022s
sys     0m0.030s

[akpm@linux-foundation.org: remove incorrect comment, use less statck in num_to_str(), move comment from .h to .c, simplify seq_put_decimal_ull()]
[andrea@betterlinux.com: avoid breaking the ABI in /proc/stat]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrea Righi <andrea@betterlinux.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Glauber Costa <glommer@parallels.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Turner <pjt@google.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-23 16:58:42 -07:00

197 lines
5.5 KiB
C

#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/seq_file.h>
#include <linux/slab.h>
#include <linux/time.h>
#include <linux/irqnr.h>
#include <asm/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
#ifndef arch_idle_time
#define arch_idle_time(cpu) 0
#endif
static u64 get_idle_time(int cpu)
{
u64 idle, idle_time = get_cpu_idle_time_us(cpu, NULL);
if (idle_time == -1ULL) {
/* !NO_HZ so we can rely on cpustat.idle */
idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
idle += arch_idle_time(cpu);
} else
idle = usecs_to_cputime64(idle_time);
return idle;
}
static u64 get_iowait_time(int cpu)
{
u64 iowait, iowait_time = get_cpu_iowait_time_us(cpu, NULL);
if (iowait_time == -1ULL)
/* !NO_HZ so we can rely on cpustat.iowait */
iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
else
iowait = usecs_to_cputime64(iowait_time);
return iowait;
}
static int show_stat(struct seq_file *p, void *v)
{
int i, j;
unsigned long jif;
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 timespec boottime;
user = nice = system = idle = iowait =
irq = softirq = steal = 0;
guest = guest_nice = 0;
getboottime(&boottime);
jif = boottime.tv_sec;
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_puts(p, "cpu ");
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(user));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
seq_put_decimal_ull(p, ' ', cputime64_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, ' ', cputime64_to_clock_t(user));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(nice));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(system));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(idle));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(iowait));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(irq));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(softirq));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(steal));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest));
seq_put_decimal_ull(p, ' ', cputime64_to_clock_t(guest_nice));
seq_putc(p, '\n');
}
seq_printf(p, "intr %llu", (unsigned long long)sum);
/* sum again ? it could be updated? */
for_each_irq_nr(j)
seq_put_decimal_ull(p, ' ', kstat_irqs(j));
seq_printf(p,
"\nctxt %llu\n"
"btime %lu\n"
"processes %lu\n"
"procs_running %lu\n"
"procs_blocked %lu\n",
nr_context_switches(),
(unsigned long)jif,
total_forks,
nr_running(),
nr_iowait());
seq_printf(p, "softirq %llu", (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 size = 1024 + 128 * num_possible_cpus();
char *buf;
struct seq_file *m;
int res;
/* minimum size to display an interrupt count : 2 bytes */
size += 2 * nr_irqs;
/* don't ask for more than the kmalloc() max size */
if (size > KMALLOC_MAX_SIZE)
size = KMALLOC_MAX_SIZE;
buf = kmalloc(size, GFP_KERNEL);
if (!buf)
return -ENOMEM;
res = single_open(file, show_stat, NULL);
if (!res) {
m = file->private_data;
m->buf = buf;
m->size = ksize(buf);
} else
kfree(buf);
return res;
}
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;
}
module_init(proc_stat_init);