mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-15 16:53:54 +08:00
f2c66cd8ee
/proc/stat shows the total number of all interrupts to each cpu. But when the number of IRQs are very large, it take very long time and 'cat /proc/stat' takes more than 10 secs. This is because sum of all irq events are counted when /proc/stat is read. This patch adds "sum of all irq" counter percpu and reduce read costs. The cost of reading /proc/stat is important because it's used by major applications as 'top', 'ps', 'w', etc.... A test on a mechin (4096cpu, 256 nodes, 4592 irqs) shows %time cat /proc/stat > /dev/null Before Patch: 12.627 sec After Patch: 2.459 sec Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Tested-by: Jack Steiner <steiner@sgi.com> Acked-by: Jack Steiner <steiner@sgi.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
177 lines
5.0 KiB
C
177 lines
5.0 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>
|
|
|
|
#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 int show_stat(struct seq_file *p, void *v)
|
|
{
|
|
int i, j;
|
|
unsigned long jif;
|
|
cputime64_t user, nice, system, idle, iowait, irq, softirq, steal;
|
|
cputime64_t guest, guest_nice;
|
|
u64 sum = 0;
|
|
u64 sum_softirq = 0;
|
|
unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
|
|
struct timespec boottime;
|
|
unsigned int per_irq_sum;
|
|
|
|
user = nice = system = idle = iowait =
|
|
irq = softirq = steal = cputime64_zero;
|
|
guest = guest_nice = cputime64_zero;
|
|
getboottime(&boottime);
|
|
jif = boottime.tv_sec;
|
|
|
|
for_each_possible_cpu(i) {
|
|
user = cputime64_add(user, kstat_cpu(i).cpustat.user);
|
|
nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice);
|
|
system = cputime64_add(system, kstat_cpu(i).cpustat.system);
|
|
idle = cputime64_add(idle, kstat_cpu(i).cpustat.idle);
|
|
idle = cputime64_add(idle, arch_idle_time(i));
|
|
iowait = cputime64_add(iowait, kstat_cpu(i).cpustat.iowait);
|
|
irq = cputime64_add(irq, kstat_cpu(i).cpustat.irq);
|
|
softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
|
|
steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
|
|
guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
|
|
guest_nice = cputime64_add(guest_nice,
|
|
kstat_cpu(i).cpustat.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_printf(p, "cpu %llu %llu %llu %llu %llu %llu %llu %llu %llu "
|
|
"%llu\n",
|
|
(unsigned long long)cputime64_to_clock_t(user),
|
|
(unsigned long long)cputime64_to_clock_t(nice),
|
|
(unsigned long long)cputime64_to_clock_t(system),
|
|
(unsigned long long)cputime64_to_clock_t(idle),
|
|
(unsigned long long)cputime64_to_clock_t(iowait),
|
|
(unsigned long long)cputime64_to_clock_t(irq),
|
|
(unsigned long long)cputime64_to_clock_t(softirq),
|
|
(unsigned long long)cputime64_to_clock_t(steal),
|
|
(unsigned long long)cputime64_to_clock_t(guest),
|
|
(unsigned long long)cputime64_to_clock_t(guest_nice));
|
|
for_each_online_cpu(i) {
|
|
|
|
/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
|
|
user = kstat_cpu(i).cpustat.user;
|
|
nice = kstat_cpu(i).cpustat.nice;
|
|
system = kstat_cpu(i).cpustat.system;
|
|
idle = kstat_cpu(i).cpustat.idle;
|
|
idle = cputime64_add(idle, arch_idle_time(i));
|
|
iowait = kstat_cpu(i).cpustat.iowait;
|
|
irq = kstat_cpu(i).cpustat.irq;
|
|
softirq = kstat_cpu(i).cpustat.softirq;
|
|
steal = kstat_cpu(i).cpustat.steal;
|
|
guest = kstat_cpu(i).cpustat.guest;
|
|
guest_nice = kstat_cpu(i).cpustat.guest_nice;
|
|
seq_printf(p,
|
|
"cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu "
|
|
"%llu\n",
|
|
i,
|
|
(unsigned long long)cputime64_to_clock_t(user),
|
|
(unsigned long long)cputime64_to_clock_t(nice),
|
|
(unsigned long long)cputime64_to_clock_t(system),
|
|
(unsigned long long)cputime64_to_clock_t(idle),
|
|
(unsigned long long)cputime64_to_clock_t(iowait),
|
|
(unsigned long long)cputime64_to_clock_t(irq),
|
|
(unsigned long long)cputime64_to_clock_t(softirq),
|
|
(unsigned long long)cputime64_to_clock_t(steal),
|
|
(unsigned long long)cputime64_to_clock_t(guest),
|
|
(unsigned long long)cputime64_to_clock_t(guest_nice));
|
|
}
|
|
seq_printf(p, "intr %llu", (unsigned long long)sum);
|
|
|
|
/* sum again ? it could be updated? */
|
|
for_each_irq_nr(j) {
|
|
per_irq_sum = 0;
|
|
for_each_possible_cpu(i)
|
|
per_irq_sum += kstat_irqs_cpu(j, i);
|
|
|
|
seq_printf(p, " %u", per_irq_sum);
|
|
}
|
|
|
|
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_printf(p, " %u", per_softirq_sums[i]);
|
|
seq_printf(p, "\n");
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int stat_open(struct inode *inode, struct file *file)
|
|
{
|
|
unsigned size = 4096 * (1 + num_possible_cpus() / 32);
|
|
char *buf;
|
|
struct seq_file *m;
|
|
int res;
|
|
|
|
/* don't ask for more than the kmalloc() max size, currently 128 KB */
|
|
if (size > 128 * 1024)
|
|
size = 128 * 1024;
|
|
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 = size;
|
|
} 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);
|