mirror of
https://github.com/torvalds/linux.git
synced 2024-11-23 12:42:02 +00:00
7386cdbf2f
Git commit 09a1d34f85
"nohz: Make idle/iowait counter update
conditional" introduced a bug in regard to cpu hotplug. The effect is
that the number of idle ticks in the cpu summary line in /proc/stat is
still counting ticks for offline cpus.
Reproduction is easy, just start a workload that keeps all cpus busy,
switch off one or more cpus and then watch the idle field in top.
On a dual-core with one cpu 100% busy and one offline cpu you will get
something like this:
%Cpu(s): 48.7 us, 1.3 sy, 0.0 ni, 50.0 id, 0.0 wa, 0.0 hi, 0.0 si,
%0.0 st
The problem is that an offline cpu still has ts->idle_active == 1.
To fix this we should make sure that the cpu is online when calling
get_cpu_idle_time_us and get_cpu_iowait_time_us.
[Srivatsa: Rebased to current mainline]
Reported-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20121010061820.8999.57245.stgit@srivatsabhat.in.ibm.com
Cc: deepthi@linux.vnet.ibm.com
Cc: stable@vger.kernel.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
225 lines
5.9 KiB
C
225 lines
5.9 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
|
|
|
|
#ifdef arch_idle_time
|
|
|
|
static cputime64_t get_idle_time(int cpu)
|
|
{
|
|
cputime64_t idle;
|
|
|
|
idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
|
|
if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
|
|
idle += arch_idle_time(cpu);
|
|
return idle;
|
|
}
|
|
|
|
static cputime64_t get_iowait_time(int cpu)
|
|
{
|
|
cputime64_t 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_time = -1ULL;
|
|
|
|
if (cpu_online(cpu))
|
|
idle_time = get_cpu_idle_time_us(cpu, NULL);
|
|
|
|
if (idle_time == -1ULL)
|
|
/* !NO_HZ or cpu offline so we can rely on cpustat.idle */
|
|
idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
|
|
else
|
|
idle = usecs_to_cputime64(idle_time);
|
|
|
|
return idle;
|
|
}
|
|
|
|
static u64 get_iowait_time(int cpu)
|
|
{
|
|
u64 iowait, iowait_time = -1ULL;
|
|
|
|
if (cpu_online(cpu))
|
|
iowait_time = get_cpu_iowait_time_us(cpu, NULL);
|
|
|
|
if (iowait_time == -1ULL)
|
|
/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
|
|
iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
|
|
else
|
|
iowait = usecs_to_cputime64(iowait_time);
|
|
|
|
return iowait;
|
|
}
|
|
|
|
#endif
|
|
|
|
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);
|