Contributors: 10
Author Tokens Token Proportion Commits Commit Proportion
Davidlohr Bueso A 890 83.49% 8 27.59%
Athira Rajeev 58 5.44% 2 6.90%
Ian Rogers 38 3.56% 5 17.24%
Hitoshi Mitake 33 3.10% 2 6.90%
Arnaldo Carvalho de Melo 23 2.16% 6 20.69%
Tommi Rantala 14 1.31% 2 6.90%
Sohaib 5 0.47% 1 3.45%
Ingo Molnar 2 0.19% 1 3.45%
Jiri Olsa 2 0.19% 1 3.45%
Greg Kroah-Hartman 1 0.09% 1 3.45%
Total 1066 29 
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2013  Davidlohr Bueso <davidlohr@hp.com>
 *
 * futex-wake: Block a bunch of threads on a futex and wake'em up, N at a time.
 *
 * This program is particularly useful to measure the latency of nthread wakeups
 * in non-error situations:  all waiters are queued and all wake calls wakeup
 * one or more tasks, and thus the waitqueue is never empty.
 */

/* For the CLR_() macros */
#include <string.h>
#include <pthread.h>

#include <signal.h>
#include "../util/mutex.h"
#include "../util/stat.h"
#include <subcmd/parse-options.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/time64.h>
#include <errno.h>
#include <perf/cpumap.h>
#include "bench.h"
#include "futex.h"

#include <err.h>
#include <stdlib.h>
#include <sys/time.h>
#include <sys/mman.h>

/* all threads will block on the same futex */
static u_int32_t futex1 = 0;

static pthread_t *worker;
static bool done = false;
static struct mutex thread_lock;
static struct cond thread_parent, thread_worker;
static struct stats waketime_stats, wakeup_stats;
static unsigned int threads_starting;
static int futex_flag = 0;

static struct bench_futex_parameters params = {
	/*
	 * How many wakeups to do at a time.
	 * Default to 1 in order to make the kernel work more.
	 */
	.nwakes  = 1,
};

static const struct option options[] = {
	OPT_UINTEGER('t', "threads", &params.nthreads, "Specify amount of threads"),
	OPT_UINTEGER('w', "nwakes",  &params.nwakes, "Specify amount of threads to wake at once"),
	OPT_BOOLEAN( 's', "silent",  &params.silent, "Silent mode: do not display data/details"),
	OPT_BOOLEAN( 'S', "shared",  &params.fshared, "Use shared futexes instead of private ones"),
	OPT_BOOLEAN( 'm', "mlockall", &params.mlockall, "Lock all current and future memory"),

	OPT_END()
};

static const char * const bench_futex_wake_usage[] = {
	"perf bench futex wake <options>",
	NULL
};

static void *workerfn(void *arg __maybe_unused)
{
	mutex_lock(&thread_lock);
	threads_starting--;
	if (!threads_starting)
		cond_signal(&thread_parent);
	cond_wait(&thread_worker, &thread_lock);
	mutex_unlock(&thread_lock);

	while (1) {
		if (futex_wait(&futex1, 0, NULL, futex_flag) != EINTR)
			break;
	}

	pthread_exit(NULL);
	return NULL;
}

static void print_summary(void)
{
	double waketime_avg = avg_stats(&waketime_stats);
	double waketime_stddev = stddev_stats(&waketime_stats);
	unsigned int wakeup_avg = avg_stats(&wakeup_stats);

	printf("Wokeup %d of %d threads in %.4f ms (+-%.2f%%)\n",
	       wakeup_avg,
	       params.nthreads,
	       waketime_avg / USEC_PER_MSEC,
	       rel_stddev_stats(waketime_stddev, waketime_avg));
}

static void block_threads(pthread_t *w, struct perf_cpu_map *cpu)
{
	cpu_set_t *cpuset;
	unsigned int i;
	size_t size;
	int nrcpus = cpu__max_cpu().cpu;
	threads_starting = params.nthreads;

	cpuset = CPU_ALLOC(nrcpus);
	BUG_ON(!cpuset);
	size = CPU_ALLOC_SIZE(nrcpus);

	/* create and block all threads */
	for (i = 0; i < params.nthreads; i++) {
		pthread_attr_t thread_attr;

		pthread_attr_init(&thread_attr);
		CPU_ZERO_S(size, cpuset);
		CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);

		if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
			CPU_FREE(cpuset);
			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
		}

		if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) {
			CPU_FREE(cpuset);
			err(EXIT_FAILURE, "pthread_create");
		}
		pthread_attr_destroy(&thread_attr);
	}
	CPU_FREE(cpuset);
}

static void toggle_done(int sig __maybe_unused,
			siginfo_t *info __maybe_unused,
			void *uc __maybe_unused)
{
	done = true;
}

int bench_futex_wake(int argc, const char **argv)
{
	int ret = 0;
	unsigned int i, j;
	struct sigaction act;
	struct perf_cpu_map *cpu;

	argc = parse_options(argc, argv, options, bench_futex_wake_usage, 0);
	if (argc) {
		usage_with_options(bench_futex_wake_usage, options);
		exit(EXIT_FAILURE);
	}

	cpu = perf_cpu_map__new_online_cpus();
	if (!cpu)
		err(EXIT_FAILURE, "calloc");

	memset(&act, 0, sizeof(act));
	sigfillset(&act.sa_mask);
	act.sa_sigaction = toggle_done;
	sigaction(SIGINT, &act, NULL);

	if (params.mlockall) {
		if (mlockall(MCL_CURRENT | MCL_FUTURE))
			err(EXIT_FAILURE, "mlockall");
	}

	if (!params.nthreads)
		params.nthreads = perf_cpu_map__nr(cpu);

	worker = calloc(params.nthreads, sizeof(*worker));
	if (!worker)
		err(EXIT_FAILURE, "calloc");

	if (!params.fshared)
		futex_flag = FUTEX_PRIVATE_FLAG;

	printf("Run summary [PID %d]: blocking on %d threads (at [%s] futex %p), "
	       "waking up %d at a time.\n\n",
	       getpid(), params.nthreads, params.fshared ? "shared":"private",
	       &futex1, params.nwakes);

	init_stats(&wakeup_stats);
	init_stats(&waketime_stats);
	mutex_init(&thread_lock);
	cond_init(&thread_parent);
	cond_init(&thread_worker);

	for (j = 0; j < bench_repeat && !done; j++) {
		unsigned int nwoken = 0;
		struct timeval start, end, runtime;

		/* create, launch & block all threads */
		block_threads(worker, cpu);

		/* make sure all threads are already blocked */
		mutex_lock(&thread_lock);
		while (threads_starting)
			cond_wait(&thread_parent, &thread_lock);
		cond_broadcast(&thread_worker);
		mutex_unlock(&thread_lock);

		usleep(100000);

		/* Ok, all threads are patiently blocked, start waking folks up */
		gettimeofday(&start, NULL);
		while (nwoken != params.nthreads)
			nwoken += futex_wake(&futex1,
					     params.nwakes, futex_flag);
		gettimeofday(&end, NULL);
		timersub(&end, &start, &runtime);

		update_stats(&wakeup_stats, nwoken);
		update_stats(&waketime_stats, runtime.tv_usec);

		if (!params.silent) {
			printf("[Run %d]: Wokeup %d of %d threads in %.4f ms\n",
			       j + 1, nwoken, params.nthreads,
			       runtime.tv_usec / (double)USEC_PER_MSEC);
		}

		for (i = 0; i < params.nthreads; i++) {
			ret = pthread_join(worker[i], NULL);
			if (ret)
				err(EXIT_FAILURE, "pthread_join");
		}

	}

	/* cleanup & report results */
	cond_destroy(&thread_parent);
	cond_destroy(&thread_worker);
	mutex_destroy(&thread_lock);

	print_summary();

	free(worker);
	perf_cpu_map__put(cpu);
	return ret;
}