leandrof/linux
1
0
Fork 0
forked from Minki/linux
Code Issues Pull Requests Packages Projects Releases Wiki Activity
b772f07add
linux/fs/proc/stat.c
Alexey Dobriyan d919b33daf proc: faster open/read/close with "permanent" files 
Now that "struct proc_ops" exist we can start putting there stuff which
could not fly with VFS "struct file_operations"...

Most of fs/proc/inode.c file is dedicated to make open/read/.../close
reliable in the event of disappearing /proc entries which usually happens
if module is getting removed.  Files like /proc/cpuinfo which never
disappear simply do not need such protection.

Save 2 atomic ops, 1 allocation, 1 free per open/read/close sequence for such
"permanent" files.

Enable "permanent" flag for

	/proc/cpuinfo
	/proc/kmsg
	/proc/modules
	/proc/slabinfo
	/proc/stat
	/proc/sysvipc/*
	/proc/swaps

More will come once I figure out foolproof way to prevent out module
authors from marking their stuff "permanent" for performance reasons
when it is not.

This should help with scalability: benchmark is "read /proc/cpuinfo R times
by N threads scattered over the system".

	N	R	t, s (before)	t, s (after)
	-----------------------------------------------------
	64	4096	1.582458	1.530502	-3.2%
	256	4096	6.371926	6.125168	-3.9%
	1024	4096	25.64888	24.47528	-4.6%

Benchmark source:

#include <chrono>
#include <iostream>
#include <thread>
#include <vector>

#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>

const int NR_CPUS = sysconf(_SC_NPROCESSORS_ONLN);
int N;
const char *filename;
int R;

int xxx = 0;

int glue(int n)
{
	cpu_set_t m;
	CPU_ZERO(&m);
	CPU_SET(n, &m);
	return sched_setaffinity(0, sizeof(cpu_set_t), &m);
}

void f(int n)
{
	glue(n % NR_CPUS);

	while (*(volatile int *)&xxx == 0) {
	}

	for (int i = 0; i < R; i++) {
		int fd = open(filename, O_RDONLY);
		char buf[4096];
		ssize_t rv = read(fd, buf, sizeof(buf));
		asm volatile ("" :: "g" (rv));
		close(fd);
	}
}

int main(int argc, char *argv[])
{
	if (argc < 4) {
		std::cerr << "usage: " << argv[0] << ' ' << "N /proc/filename R
";
		return 1;
	}

	N = atoi(argv[1]);
	filename = argv[2];
	R = atoi(argv[3]);

	for (int i = 0; i < NR_CPUS; i++) {
		if (glue(i) == 0)
			break;
	}

	std::vector<std::thread> T;
	T.reserve(N);
	for (int i = 0; i < N; i++) {
		T.emplace_back(f, i);
	}

	auto t0 = std::chrono::system_clock::now();
	{
		*(volatile int *)&xxx = 1;
		for (auto& t: T) {
			t.join();
		}
	}
	auto t1 = std::chrono::system_clock::now();
	std::chrono::duration<double> dt = t1 - t0;
	std::cout << dt.count() << '
';

	return 0;
}

P.S.:
Explicit randomization marker is added because adding non-function pointer
will silently disable structure layout randomization.

[akpm@linux-foundation.org: coding style fixes]
Reported-by: kbuild test robot <lkp@intel.com>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Joe Perches <joe@perches.com>
Link: http://lkml.kernel.org/r/20200222201539.GA22576@avx2
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-07 10:43:42 -07:00

240 lines
6.1 KiB
C
Raw Blame History

// 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(struct kernel_cpustat *kcs, int cpu)
{
u64 idle;
idle = kcs->cpustat[CPUTIME_IDLE];
if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
idle += arch_idle_time(cpu);
return idle;
}
static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu)
{
u64 iowait;
iowait = kcs->cpustat[CPUTIME_IOWAIT];
if (cpu_online(cpu) && nr_iowait_cpu(cpu))
iowait += arch_idle_time(cpu);
return iowait;
}
#else
static u64 get_idle_time(struct kernel_cpustat *kcs, 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 = kcs->cpustat[CPUTIME_IDLE];
else
idle = idle_usecs * NSEC_PER_USEC;
return idle;
}
static u64 get_iowait_time(struct kernel_cpustat *kcs, 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 = kcs->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) {
struct kernel_cpustat kcpustat;
u64 *cpustat = kcpustat.cpustat;
kcpustat_cpu_fetch(&kcpustat, i);
user += cpustat[CPUTIME_USER];
nice += cpustat[CPUTIME_NICE];
system += cpustat[CPUTIME_SYSTEM];
idle += get_idle_time(&kcpustat, i);
iowait += get_iowait_time(&kcpustat, i);
irq += cpustat[CPUTIME_IRQ];
softirq += cpustat[CPUTIME_SOFTIRQ];
steal += cpustat[CPUTIME_STEAL];
guest += cpustat[CPUTIME_GUEST];
guest_nice += 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) {
struct kernel_cpustat kcpustat;
u64 *cpustat = kcpustat.cpustat;
kcpustat_cpu_fetch(&kcpustat, i);
/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
user = cpustat[CPUTIME_USER];
nice = cpustat[CPUTIME_NICE];
system = cpustat[CPUTIME_SYSTEM];
idle = get_idle_time(&kcpustat, i);
iowait = get_iowait_time(&kcpustat, i);
irq = cpustat[CPUTIME_IRQ];
softirq = cpustat[CPUTIME_SOFTIRQ];
steal = cpustat[CPUTIME_STEAL];
guest = cpustat[CPUTIME_GUEST];
guest_nice = 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 proc_ops stat_proc_ops = {
.proc_flags = PROC_ENTRY_PERMANENT,
.proc_open = stat_open,
.proc_read = seq_read,
.proc_lseek = seq_lseek,
.proc_release = single_release,
};
static int __init proc_stat_init(void)
{
proc_create("stat", 0, NULL, &stat_proc_ops);
return 0;
}
fs_initcall(proc_stat_init);
Reference in New Issue View Git Blame Copy Permalink