linux/fs/proc/stat.c

198 lines
5.4 KiB
C
Raw Normal View History

#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 cputime64_t get_idle_time(int cpu)
{
u64 idle_time = get_cpu_idle_time_us(cpu, NULL);
cputime64_t idle;
if (idle_time == -1ULL) {
/* !NO_HZ so we can rely on cpustat.idle */
idle = kstat_cpu(cpu).cpustat.idle;
idle = cputime64_add(idle, arch_idle_time(cpu));
} else
procfs: do not overflow get_{idle,iowait}_time for nohz Since commit a25cac5198d4 ("proc: Consider NO_HZ when printing idle and iowait times") we are reporting idle/io_wait time also while a CPU is tickless. We rely on get_{idle,iowait}_time functions to retrieve proper data. These functions, however, use usecs_to_cputime to translate micro seconds time to cputime64_t. This is just an alias to usecs_to_jiffies which reduces the data type from u64 to unsigned int and also checks whether the given parameter overflows jiffies_to_usecs(MAX_JIFFY_OFFSET) and returns MAX_JIFFY_OFFSET in that case. When we overflow depends on CONFIG_HZ but especially for CONFIG_HZ_300 it is quite low (1431649781) so we are getting MAX_JIFFY_OFFSET for >3000s! until we overflow unsigned int. Just for reference CONFIG_HZ_100 has an overflow window around 20s, CONFIG_HZ_250 ~8s and CONFIG_HZ_1000 ~2s. This results in a bug when people saw [h]top going mad reporting 100% CPU usage even though there was basically no CPU load. The reason was simply that /proc/stat stopped reporting idle/io_wait changes (and reported MAX_JIFFY_OFFSET) and so the only change happening was for user system time. Let's use nsecs_to_jiffies64 instead which doesn't reduce the precision to 32b type and it is much more appropriate for cumulative time values (unlike usecs_to_jiffies which intended for timeout calculations). Signed-off-by: Michal Hocko <mhocko@suse.cz> Tested-by: Artem S. Tashkinov <t.artem@mailcity.com> Cc: Dave Jones <davej@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-12-09 06:34:32 +08:00
idle = nsecs_to_jiffies64(1000 * idle_time);
return idle;
}
static cputime64_t get_iowait_time(int cpu)
{
u64 iowait_time = get_cpu_iowait_time_us(cpu, NULL);
cputime64_t iowait;
if (iowait_time == -1ULL)
/* !NO_HZ so we can rely on cpustat.iowait */
iowait = kstat_cpu(cpu).cpustat.iowait;
else
procfs: do not overflow get_{idle,iowait}_time for nohz Since commit a25cac5198d4 ("proc: Consider NO_HZ when printing idle and iowait times") we are reporting idle/io_wait time also while a CPU is tickless. We rely on get_{idle,iowait}_time functions to retrieve proper data. These functions, however, use usecs_to_cputime to translate micro seconds time to cputime64_t. This is just an alias to usecs_to_jiffies which reduces the data type from u64 to unsigned int and also checks whether the given parameter overflows jiffies_to_usecs(MAX_JIFFY_OFFSET) and returns MAX_JIFFY_OFFSET in that case. When we overflow depends on CONFIG_HZ but especially for CONFIG_HZ_300 it is quite low (1431649781) so we are getting MAX_JIFFY_OFFSET for >3000s! until we overflow unsigned int. Just for reference CONFIG_HZ_100 has an overflow window around 20s, CONFIG_HZ_250 ~8s and CONFIG_HZ_1000 ~2s. This results in a bug when people saw [h]top going mad reporting 100% CPU usage even though there was basically no CPU load. The reason was simply that /proc/stat stopped reporting idle/io_wait changes (and reported MAX_JIFFY_OFFSET) and so the only change happening was for user system time. Let's use nsecs_to_jiffies64 instead which doesn't reduce the precision to 32b type and it is much more appropriate for cumulative time values (unlike usecs_to_jiffies which intended for timeout calculations). Signed-off-by: Michal Hocko <mhocko@suse.cz> Tested-by: Artem S. Tashkinov <t.artem@mailcity.com> Cc: Dave Jones <davej@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-12-09 06:34:32 +08:00
iowait = nsecs_to_jiffies64(1000 * iowait_time);
return iowait;
}
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;
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, get_idle_time(i));
iowait = cputime64_add(iowait, get_iowait_time(i));
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 = get_idle_time(i);
iowait = get_iowait_time(i);
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)
seq_printf(p, " %u", 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_printf(p, " %u", per_softirq_sums[i]);
seq_putc(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 */
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 = 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);