linux/tools/perf/bench/futex-requeue.c
Davidlohr Bueso 052b0f6eaf perf bench futex: Fix hung wakeup tasks after requeueing
The futex-requeue benchmark can hang because of missing wakeups once the
benchmark is done, ie:

[Run 1]: Requeued 1024 of 1024 threads in 0.3290 ms
perf: couldn't wakeup all tasks (135/1024)

This bug, while perhaps suggesting missing wakeups in kernel futex code,
is merely a consequence of the crappy FUTEX_CMP_REQUEUE man page,
incorrectly mentioning that the number of requeued tasks is in fact
returned, not the wakeups.

This patch acknowledges this and updates the corresponding futex_wake
code around it.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Mel Gorman <mgorman@suse.de>
Link: http://lkml.kernel.org/r/1429894848.10273.44.camel@stgolabs.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-27 13:57:49 -03:00

213 lines
5.6 KiB
C

/*
* Copyright (C) 2013 Davidlohr Bueso <davidlohr@hp.com>
*
* futex-requeue: Block a bunch of threads on futex1 and requeue them
* on futex2, N at a time.
*
* This program is particularly useful to measure the latency of nthread
* requeues without waking up any tasks -- thus mimicking a regular futex_wait.
*/
#include "../perf.h"
#include "../util/util.h"
#include "../util/stat.h"
#include "../util/parse-options.h"
#include "../util/header.h"
#include "bench.h"
#include "futex.h"
#include <err.h>
#include <stdlib.h>
#include <sys/time.h>
#include <pthread.h>
static u_int32_t futex1 = 0, futex2 = 0;
/*
* How many tasks to requeue at a time.
* Default to 1 in order to make the kernel work more.
*/
static unsigned int nrequeue = 1;
static pthread_t *worker;
static bool done = false, silent = false, fshared = false;
static pthread_mutex_t thread_lock;
static pthread_cond_t thread_parent, thread_worker;
static struct stats requeuetime_stats, requeued_stats;
static unsigned int ncpus, threads_starting, nthreads = 0;
static int futex_flag = 0;
static const struct option options[] = {
OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
OPT_UINTEGER('q', "nrequeue", &nrequeue, "Specify amount of threads to requeue at once"),
OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"),
OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"),
OPT_END()
};
static const char * const bench_futex_requeue_usage[] = {
"perf bench futex requeue <options>",
NULL
};
static void print_summary(void)
{
double requeuetime_avg = avg_stats(&requeuetime_stats);
double requeuetime_stddev = stddev_stats(&requeuetime_stats);
unsigned int requeued_avg = avg_stats(&requeued_stats);
printf("Requeued %d of %d threads in %.4f ms (+-%.2f%%)\n",
requeued_avg,
nthreads,
requeuetime_avg/1e3,
rel_stddev_stats(requeuetime_stddev, requeuetime_avg));
}
static void *workerfn(void *arg __maybe_unused)
{
pthread_mutex_lock(&thread_lock);
threads_starting--;
if (!threads_starting)
pthread_cond_signal(&thread_parent);
pthread_cond_wait(&thread_worker, &thread_lock);
pthread_mutex_unlock(&thread_lock);
futex_wait(&futex1, 0, NULL, futex_flag);
return NULL;
}
static void block_threads(pthread_t *w,
pthread_attr_t thread_attr)
{
cpu_set_t cpu;
unsigned int i;
threads_starting = nthreads;
/* create and block all threads */
for (i = 0; i < nthreads; i++) {
CPU_ZERO(&cpu);
CPU_SET(i % ncpus, &cpu);
if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
err(EXIT_FAILURE, "pthread_create");
}
}
static void toggle_done(int sig __maybe_unused,
siginfo_t *info __maybe_unused,
void *uc __maybe_unused)
{
done = true;
}
int bench_futex_requeue(int argc, const char **argv,
const char *prefix __maybe_unused)
{
int ret = 0;
unsigned int i, j;
struct sigaction act;
pthread_attr_t thread_attr;
argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0);
if (argc)
goto err;
ncpus = sysconf(_SC_NPROCESSORS_ONLN);
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
if (!nthreads)
nthreads = ncpus;
worker = calloc(nthreads, sizeof(*worker));
if (!worker)
err(EXIT_FAILURE, "calloc");
if (!fshared)
futex_flag = FUTEX_PRIVATE_FLAG;
if (nrequeue > nthreads)
nrequeue = nthreads;
printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), "
"%d at a time.\n\n", getpid(), nthreads,
fshared ? "shared":"private", &futex1, &futex2, nrequeue);
init_stats(&requeued_stats);
init_stats(&requeuetime_stats);
pthread_attr_init(&thread_attr);
pthread_mutex_init(&thread_lock, NULL);
pthread_cond_init(&thread_parent, NULL);
pthread_cond_init(&thread_worker, NULL);
for (j = 0; j < bench_repeat && !done; j++) {
unsigned int nrequeued = 0;
struct timeval start, end, runtime;
/* create, launch & block all threads */
block_threads(worker, thread_attr);
/* make sure all threads are already blocked */
pthread_mutex_lock(&thread_lock);
while (threads_starting)
pthread_cond_wait(&thread_parent, &thread_lock);
pthread_cond_broadcast(&thread_worker);
pthread_mutex_unlock(&thread_lock);
usleep(100000);
/* Ok, all threads are patiently blocked, start requeueing */
gettimeofday(&start, NULL);
while (nrequeued < nthreads) {
/*
* Do not wakeup any tasks blocked on futex1, allowing
* us to really measure futex_wait functionality.
*/
nrequeued += futex_cmp_requeue(&futex1, 0, &futex2, 0,
nrequeue, futex_flag);
}
gettimeofday(&end, NULL);
timersub(&end, &start, &runtime);
update_stats(&requeued_stats, nrequeued);
update_stats(&requeuetime_stats, runtime.tv_usec);
if (!silent) {
printf("[Run %d]: Requeued %d of %d threads in %.4f ms\n",
j + 1, nrequeued, nthreads, runtime.tv_usec/1e3);
}
/* everybody should be blocked on futex2, wake'em up */
nrequeued = futex_wake(&futex2, nrequeued, futex_flag);
if (nthreads != nrequeued)
warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
for (i = 0; i < nthreads; i++) {
ret = pthread_join(worker[i], NULL);
if (ret)
err(EXIT_FAILURE, "pthread_join");
}
}
/* cleanup & report results */
pthread_cond_destroy(&thread_parent);
pthread_cond_destroy(&thread_worker);
pthread_mutex_destroy(&thread_lock);
pthread_attr_destroy(&thread_attr);
print_summary();
free(worker);
return ret;
err:
usage_with_options(bench_futex_requeue_usage, options);
exit(EXIT_FAILURE);
}