* [PATCH 1/7] perf/bench-futex: Group test parameters cleanup
2021-08-09 4:32 [PATCH -tip v2 0/7] perf/bench-futex: Misc updates Davidlohr Bueso
@ 2021-08-09 4:32 ` Davidlohr Bueso
2021-08-09 4:32 ` [PATCH 2/7] perf/bench-futex: Remove bogus backslash from comment Davidlohr Bueso
` (5 subsequent siblings)
6 siblings, 0 replies; 15+ messages in thread
From: Davidlohr Bueso @ 2021-08-09 4:32 UTC (permalink / raw)
To: acme
Cc: mingo, peterz, tglx, linux-perf-users, linux-kernel, dave,
Davidlohr Bueso
Do this across all futex-bench tests such that all program parameters
neatly share a common structure, which is nicer than how we have them
now. No changes in program behavior are expected.
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
---
tools/perf/bench/futex-hash.c | 55 +++++++++++-----------
tools/perf/bench/futex-lock-pi.c | 53 ++++++++++-----------
tools/perf/bench/futex-requeue.c | 65 ++++++++++++++------------
tools/perf/bench/futex-wake-parallel.c | 58 ++++++++++++-----------
tools/perf/bench/futex-wake.c | 57 +++++++++++-----------
tools/perf/bench/futex.h | 11 +++++
6 files changed, 162 insertions(+), 137 deletions(-)
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index b65373ce5c4f..ddca7558e559 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -29,11 +29,7 @@
#include <err.h>
-static unsigned int nthreads = 0;
-static unsigned int nsecs = 10;
-/* amount of futexes per thread */
-static unsigned int nfutexes = 1024;
-static bool fshared = false, done = false, silent = false;
+static bool done = false;
static int futex_flag = 0;
struct timeval bench__start, bench__end, bench__runtime;
@@ -49,12 +45,17 @@ struct worker {
unsigned long ops;
};
+static struct bench_futex_parameters params = {
+ .nfutexes = 1024,
+ .runtime = 10,
+};
+
static const struct option options[] = {
- OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
- OPT_UINTEGER('r', "runtime", &nsecs, "Specify runtime (in seconds)"),
- OPT_UINTEGER('f', "futexes", &nfutexes, "Specify amount of futexes per threads"),
- 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_UINTEGER('t', "threads", ¶ms.nthreads, "Specify amount of threads"),
+ OPT_UINTEGER('r', "runtime", ¶ms.runtime, "Specify runtime (in seconds)"),
+ OPT_UINTEGER('f', "futexes", ¶ms.nfutexes, "Specify amount of futexes per threads"),
+ OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"),
+ OPT_BOOLEAN( 'S', "shared", ¶ms.fshared, "Use shared futexes instead of private ones"),
OPT_END()
};
@@ -78,7 +79,7 @@ static void *workerfn(void *arg)
pthread_mutex_unlock(&thread_lock);
do {
- for (i = 0; i < nfutexes; i++, ops++) {
+ for (i = 0; i < params.nfutexes; i++, ops++) {
/*
* We want the futex calls to fail in order to stress
* the hashing of uaddr and not measure other steps,
@@ -86,7 +87,7 @@ static void *workerfn(void *arg)
* the critical region protected by hb->lock.
*/
ret = futex_wait(&w->futex[i], 1234, NULL, futex_flag);
- if (!silent &&
+ if (!params.silent &&
(!ret || errno != EAGAIN || errno != EWOULDBLOCK))
warn("Non-expected futex return call");
}
@@ -112,7 +113,7 @@ static void print_summary(void)
double stddev = stddev_stats(&throughput_stats);
printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
- !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
+ !params.silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
(int)bench__runtime.tv_sec);
}
@@ -141,30 +142,30 @@ int bench_futex_hash(int argc, const char **argv)
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
- if (!nthreads) /* default to the number of CPUs */
- nthreads = cpu->nr;
+ if (!params.nthreads) /* default to the number of CPUs */
+ params.nthreads = cpu->nr;
- worker = calloc(nthreads, sizeof(*worker));
+ worker = calloc(params.nthreads, sizeof(*worker));
if (!worker)
goto errmem;
- if (!fshared)
+ if (!params.fshared)
futex_flag = FUTEX_PRIVATE_FLAG;
printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n",
- getpid(), nthreads, nfutexes, fshared ? "shared":"private", nsecs);
+ getpid(), params.nthreads, params.nfutexes, params.fshared ? "shared":"private", params.runtime);
init_stats(&throughput_stats);
pthread_mutex_init(&thread_lock, NULL);
pthread_cond_init(&thread_parent, NULL);
pthread_cond_init(&thread_worker, NULL);
- threads_starting = nthreads;
+ threads_starting = params.nthreads;
pthread_attr_init(&thread_attr);
gettimeofday(&bench__start, NULL);
- for (i = 0; i < nthreads; i++) {
+ for (i = 0; i < params.nthreads; i++) {
worker[i].tid = i;
- worker[i].futex = calloc(nfutexes, sizeof(*worker[i].futex));
+ worker[i].futex = calloc(params.nfutexes, sizeof(*worker[i].futex));
if (!worker[i].futex)
goto errmem;
@@ -189,10 +190,10 @@ int bench_futex_hash(int argc, const char **argv)
pthread_cond_broadcast(&thread_worker);
pthread_mutex_unlock(&thread_lock);
- sleep(nsecs);
+ sleep(params.runtime);
toggle_done(0, NULL, NULL);
- for (i = 0; i < nthreads; i++) {
+ for (i = 0; i < params.nthreads; i++) {
ret = pthread_join(worker[i].thread, NULL);
if (ret)
err(EXIT_FAILURE, "pthread_join");
@@ -203,18 +204,18 @@ int bench_futex_hash(int argc, const char **argv)
pthread_cond_destroy(&thread_worker);
pthread_mutex_destroy(&thread_lock);
- for (i = 0; i < nthreads; i++) {
+ for (i = 0; i < params.nthreads; i++) {
unsigned long t = bench__runtime.tv_sec > 0 ?
worker[i].ops / bench__runtime.tv_sec : 0;
update_stats(&throughput_stats, t);
- if (!silent) {
- if (nfutexes == 1)
+ if (!params.silent) {
+ if (params.nfutexes == 1)
printf("[thread %2d] futex: %p [ %ld ops/sec ]\n",
worker[i].tid, &worker[i].futex[0], t);
else
printf("[thread %2d] futexes: %p ... %p [ %ld ops/sec ]\n",
worker[i].tid, &worker[i].futex[0],
- &worker[i].futex[nfutexes-1], t);
+ &worker[i].futex[params.nfutexes-1], t);
}
zfree(&worker[i].futex);
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 89c6d160379c..ce980df23bb0 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -31,22 +31,23 @@ struct worker {
static u_int32_t global_futex = 0;
static struct worker *worker;
-static unsigned int nsecs = 10;
-static bool silent = false, multi = false;
-static bool done = false, fshared = false;
-static unsigned int nthreads = 0;
+static bool done = false;
static int futex_flag = 0;
static pthread_mutex_t thread_lock;
static unsigned int threads_starting;
static struct stats throughput_stats;
static pthread_cond_t thread_parent, thread_worker;
+static struct bench_futex_parameters params = {
+ .runtime = 10,
+};
+
static const struct option options[] = {
- OPT_UINTEGER('t', "threads", &nthreads, "Specify amount of threads"),
- OPT_UINTEGER('r', "runtime", &nsecs, "Specify runtime (in seconds)"),
- OPT_BOOLEAN( 'M', "multi", &multi, "Use multiple futexes"),
- 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_UINTEGER('t', "threads", ¶ms.nthreads, "Specify amount of threads"),
+ OPT_UINTEGER('r', "runtime", ¶ms.runtime, "Specify runtime (in seconds)"),
+ OPT_BOOLEAN( 'M', "multi", ¶ms.multi, "Use multiple futexes"),
+ OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"),
+ OPT_BOOLEAN( 'S', "shared", ¶ms.fshared, "Use shared futexes instead of private ones"),
OPT_END()
};
@@ -61,7 +62,7 @@ static void print_summary(void)
double stddev = stddev_stats(&throughput_stats);
printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n",
- !silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
+ !params.silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg),
(int)bench__runtime.tv_sec);
}
@@ -93,7 +94,7 @@ static void *workerfn(void *arg)
ret = futex_lock_pi(w->futex, NULL, futex_flag);
if (ret) { /* handle lock acquisition */
- if (!silent)
+ if (!params.silent)
warn("thread %d: Could not lock pi-lock for %p (%d)",
w->tid, w->futex, ret);
if (done)
@@ -104,7 +105,7 @@ static void *workerfn(void *arg)
usleep(1);
ret = futex_unlock_pi(w->futex, futex_flag);
- if (ret && !silent)
+ if (ret && !params.silent)
warn("thread %d: Could not unlock pi-lock for %p (%d)",
w->tid, w->futex, ret);
ops++; /* account for thread's share of work */
@@ -120,12 +121,12 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr,
cpu_set_t cpuset;
unsigned int i;
- threads_starting = nthreads;
+ threads_starting = params.nthreads;
- for (i = 0; i < nthreads; i++) {
+ for (i = 0; i < params.nthreads; i++) {
worker[i].tid = i;
- if (multi) {
+ if (params.multi) {
worker[i].futex = calloc(1, sizeof(u_int32_t));
if (!worker[i].futex)
err(EXIT_FAILURE, "calloc");
@@ -164,25 +165,25 @@ int bench_futex_lock_pi(int argc, const char **argv)
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
- if (!nthreads)
- nthreads = cpu->nr;
+ if (!params.nthreads)
+ params.nthreads = cpu->nr;
- worker = calloc(nthreads, sizeof(*worker));
+ worker = calloc(params.nthreads, sizeof(*worker));
if (!worker)
err(EXIT_FAILURE, "calloc");
- if (!fshared)
+ if (!params.fshared)
futex_flag = FUTEX_PRIVATE_FLAG;
printf("Run summary [PID %d]: %d threads doing pi lock/unlock pairing for %d secs.\n\n",
- getpid(), nthreads, nsecs);
+ getpid(), params.nthreads, params.runtime);
init_stats(&throughput_stats);
pthread_mutex_init(&thread_lock, NULL);
pthread_cond_init(&thread_parent, NULL);
pthread_cond_init(&thread_worker, NULL);
- threads_starting = nthreads;
+ threads_starting = params.nthreads;
pthread_attr_init(&thread_attr);
gettimeofday(&bench__start, NULL);
@@ -195,10 +196,10 @@ int bench_futex_lock_pi(int argc, const char **argv)
pthread_cond_broadcast(&thread_worker);
pthread_mutex_unlock(&thread_lock);
- sleep(nsecs);
+ sleep(params.runtime);
toggle_done(0, NULL, NULL);
- for (i = 0; i < nthreads; i++) {
+ for (i = 0; i < params.nthreads; i++) {
ret = pthread_join(worker[i].thread, NULL);
if (ret)
err(EXIT_FAILURE, "pthread_join");
@@ -209,16 +210,16 @@ int bench_futex_lock_pi(int argc, const char **argv)
pthread_cond_destroy(&thread_worker);
pthread_mutex_destroy(&thread_lock);
- for (i = 0; i < nthreads; i++) {
+ for (i = 0; i < params.nthreads; i++) {
unsigned long t = bench__runtime.tv_sec > 0 ?
worker[i].ops / bench__runtime.tv_sec : 0;
update_stats(&throughput_stats, t);
- if (!silent)
+ if (!params.silent)
printf("[thread %3d] futex: %p [ %ld ops/sec ]\n",
worker[i].tid, worker[i].futex, t);
- if (multi)
+ if (params.multi)
zfree(&worker[i].futex);
}
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 5fa23295ee5f..66747bfe22cf 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -30,25 +30,27 @@
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 bool done = 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 threads_starting, nthreads = 0;
+static unsigned int threads_starting;
static int futex_flag = 0;
+static struct bench_futex_parameters params = {
+ /*
+ * How many tasks to requeue at a time.
+ * Default to 1 in order to make the kernel work more.
+ */
+ .nrequeue = 1,
+};
+
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_UINTEGER('t', "threads", ¶ms.nthreads, "Specify amount of threads"),
+ OPT_UINTEGER('q', "nrequeue", ¶ms.nrequeue, "Specify amount of threads to requeue at once"),
+ OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"),
+ OPT_BOOLEAN( 'S', "shared", ¶ms.fshared, "Use shared futexes instead of private ones"),
OPT_END()
};
@@ -65,7 +67,7 @@ static void print_summary(void)
printf("Requeued %d of %d threads in %.4f ms (+-%.2f%%)\n",
requeued_avg,
- nthreads,
+ params.nthreads,
requeuetime_avg / USEC_PER_MSEC,
rel_stddev_stats(requeuetime_stddev, requeuetime_avg));
}
@@ -89,10 +91,10 @@ static void block_threads(pthread_t *w,
cpu_set_t cpuset;
unsigned int i;
- threads_starting = nthreads;
+ threads_starting = params.nthreads;
/* create and block all threads */
- for (i = 0; i < nthreads; i++) {
+ for (i = 0; i < params.nthreads; i++) {
CPU_ZERO(&cpuset);
CPU_SET(cpu->map[i % cpu->nr], &cpuset);
@@ -132,22 +134,22 @@ int bench_futex_requeue(int argc, const char **argv)
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
- if (!nthreads)
- nthreads = cpu->nr;
+ if (!params.nthreads)
+ params.nthreads = cpu->nr;
- worker = calloc(nthreads, sizeof(*worker));
+ worker = calloc(params.nthreads, sizeof(*worker));
if (!worker)
err(EXIT_FAILURE, "calloc");
- if (!fshared)
+ if (!params.fshared)
futex_flag = FUTEX_PRIVATE_FLAG;
- if (nrequeue > nthreads)
- nrequeue = nthreads;
+ if (params.nrequeue > params.nthreads)
+ params.nrequeue = params.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);
+ "%d at a time.\n\n", getpid(), params.nthreads,
+ params.fshared ? "shared":"private", &futex1, &futex2, params.nrequeue);
init_stats(&requeued_stats);
init_stats(&requeuetime_stats);
@@ -174,13 +176,14 @@ int bench_futex_requeue(int argc, const char **argv)
/* Ok, all threads are patiently blocked, start requeueing */
gettimeofday(&start, NULL);
- while (nrequeued < nthreads) {
+ while (nrequeued < params.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);
+ params.nrequeue,
+ futex_flag);
}
gettimeofday(&end, NULL);
@@ -189,17 +192,19 @@ int bench_futex_requeue(int argc, const char **argv)
update_stats(&requeued_stats, nrequeued);
update_stats(&requeuetime_stats, runtime.tv_usec);
- if (!silent) {
+ if (!params.silent) {
printf("[Run %d]: Requeued %d of %d threads in %.4f ms\n",
- j + 1, nrequeued, nthreads, runtime.tv_usec / (double)USEC_PER_MSEC);
+ j + 1, nrequeued, params.nthreads,
+ runtime.tv_usec / (double)USEC_PER_MSEC);
}
/* 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);
+ if (params.nthreads != nrequeued)
+ warnx("couldn't wakeup all tasks (%d/%d)",
+ nrequeued, params.nthreads);
- for (i = 0; i < nthreads; i++) {
+ for (i = 0; i < params.nthreads; i++) {
ret = pthread_join(worker[i], NULL);
if (ret)
err(EXIT_FAILURE, "pthread_join");
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 6e6f5247e1fe..958372ad159c 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -47,8 +47,7 @@ static unsigned int nwakes = 1;
static u_int32_t futex = 0;
static pthread_t *blocked_worker;
-static bool done = false, silent = false, fshared = false;
-static unsigned int nblocked_threads = 0, nwaking_threads = 0;
+static bool done = false;
static pthread_mutex_t thread_lock;
static pthread_cond_t thread_parent, thread_worker;
static pthread_barrier_t barrier;
@@ -56,11 +55,13 @@ static struct stats waketime_stats, wakeup_stats;
static unsigned int threads_starting;
static int futex_flag = 0;
+static struct bench_futex_parameters params;
+
static const struct option options[] = {
- OPT_UINTEGER('t', "threads", &nblocked_threads, "Specify amount of threads"),
- OPT_UINTEGER('w', "nwakers", &nwaking_threads, "Specify amount of waking threads"),
- 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_UINTEGER('t', "threads", ¶ms.nthreads, "Specify amount of threads"),
+ OPT_UINTEGER('w', "nwakers", ¶ms.nwakes, "Specify amount of waking threads"),
+ OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"),
+ OPT_BOOLEAN( 'S', "shared", ¶ms.fshared, "Use shared futexes instead of private ones"),
OPT_END()
};
@@ -96,10 +97,10 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
pthread_attr_setdetachstate(&thread_attr, PTHREAD_CREATE_JOINABLE);
- pthread_barrier_init(&barrier, NULL, nwaking_threads + 1);
+ pthread_barrier_init(&barrier, NULL, params.nwakes + 1);
/* create and block all threads */
- for (i = 0; i < nwaking_threads; i++) {
+ for (i = 0; i < params.nwakes; i++) {
/*
* Thread creation order will impact per-thread latency
* as it will affect the order to acquire the hb spinlock.
@@ -112,7 +113,7 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
pthread_barrier_wait(&barrier);
- for (i = 0; i < nwaking_threads; i++)
+ for (i = 0; i < params.nwakes; i++)
if (pthread_join(td[i].worker, NULL))
err(EXIT_FAILURE, "pthread_join");
@@ -143,10 +144,10 @@ static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
cpu_set_t cpuset;
unsigned int i;
- threads_starting = nblocked_threads;
+ threads_starting = params.nthreads;
/* create and block all threads */
- for (i = 0; i < nblocked_threads; i++) {
+ for (i = 0; i < params.nthreads; i++) {
CPU_ZERO(&cpuset);
CPU_SET(cpu->map[i % cpu->nr], &cpuset);
@@ -167,7 +168,7 @@ static void print_run(struct thread_data *waking_worker, unsigned int run_num)
init_stats(&__wakeup_stats);
init_stats(&__waketime_stats);
- for (i = 0; i < nwaking_threads; i++) {
+ for (i = 0; i < params.nwakes; i++) {
update_stats(&__waketime_stats, waking_worker[i].runtime.tv_usec);
update_stats(&__wakeup_stats, waking_worker[i].nwoken);
}
@@ -178,7 +179,7 @@ static void print_run(struct thread_data *waking_worker, unsigned int run_num)
printf("[Run %d]: Avg per-thread latency (waking %d/%d threads) "
"in %.4f ms (+-%.2f%%)\n", run_num + 1, wakeup_avg,
- nblocked_threads, waketime_avg / USEC_PER_MSEC,
+ params.nthreads, waketime_avg / USEC_PER_MSEC,
rel_stddev_stats(waketime_stddev, waketime_avg));
}
@@ -193,7 +194,7 @@ static void print_summary(void)
printf("Avg per-thread latency (waking %d/%d threads) in %.4f ms (+-%.2f%%)\n",
wakeup_avg,
- nblocked_threads,
+ params.nthreads,
waketime_avg / USEC_PER_MSEC,
rel_stddev_stats(waketime_stddev, waketime_avg));
}
@@ -203,7 +204,7 @@ static void do_run_stats(struct thread_data *waking_worker)
{
unsigned int i;
- for (i = 0; i < nwaking_threads; i++) {
+ for (i = 0; i < params.nwakes; i++) {
update_stats(&waketime_stats, waking_worker[i].runtime.tv_usec);
update_stats(&wakeup_stats, waking_worker[i].nwoken);
}
@@ -242,32 +243,33 @@ int bench_futex_wake_parallel(int argc, const char **argv)
if (!cpu)
err(EXIT_FAILURE, "calloc");
- if (!nblocked_threads)
- nblocked_threads = cpu->nr;
+ if (!params.nthreads)
+ params.nthreads = cpu->nr;
/* some sanity checks */
- if (nwaking_threads > nblocked_threads || !nwaking_threads)
- nwaking_threads = nblocked_threads;
+ if (params.nwakes > params.nthreads ||
+ !params.nwakes)
+ params.nwakes = params.nthreads;
- if (nblocked_threads % nwaking_threads)
+ if (params.nthreads % params.nwakes)
errx(EXIT_FAILURE, "Must be perfectly divisible");
/*
* Each thread will wakeup nwakes tasks in
* a single futex_wait call.
*/
- nwakes = nblocked_threads/nwaking_threads;
+ nwakes = params.nthreads/params.nwakes;
- blocked_worker = calloc(nblocked_threads, sizeof(*blocked_worker));
+ blocked_worker = calloc(params.nthreads, sizeof(*blocked_worker));
if (!blocked_worker)
err(EXIT_FAILURE, "calloc");
- if (!fshared)
+ if (!params.fshared)
futex_flag = FUTEX_PRIVATE_FLAG;
printf("Run summary [PID %d]: blocking on %d threads (at [%s] "
"futex %p), %d threads waking up %d at a time.\n\n",
- getpid(), nblocked_threads, fshared ? "shared":"private",
- &futex, nwaking_threads, nwakes);
+ getpid(), params.nthreads, params.fshared ? "shared":"private",
+ &futex, params.nwakes, nwakes);
init_stats(&wakeup_stats);
init_stats(&waketime_stats);
@@ -278,7 +280,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
pthread_cond_init(&thread_worker, NULL);
for (j = 0; j < bench_repeat && !done; j++) {
- waking_worker = calloc(nwaking_threads, sizeof(*waking_worker));
+ waking_worker = calloc(params.nwakes, sizeof(*waking_worker));
if (!waking_worker)
err(EXIT_FAILURE, "calloc");
@@ -297,14 +299,14 @@ int bench_futex_wake_parallel(int argc, const char **argv)
/* Ok, all threads are patiently blocked, start waking folks up */
wakeup_threads(waking_worker, thread_attr);
- for (i = 0; i < nblocked_threads; i++) {
+ for (i = 0; i < params.nthreads; i++) {
ret = pthread_join(blocked_worker[i], NULL);
if (ret)
err(EXIT_FAILURE, "pthread_join");
}
do_run_stats(waking_worker);
- if (!silent)
+ if (!params.silent)
print_run(waking_worker, j);
free(waking_worker);
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 6d217868f53c..9ed4d65416f3 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -31,25 +31,27 @@
/* all threads will block on the same futex */
static u_int32_t futex1 = 0;
-/*
- * How many wakeups to do at a time.
- * Default to 1 in order to make the kernel work more.
- */
-static unsigned int nwakes = 1;
-
-pthread_t *worker;
-static bool done = false, silent = false, fshared = false;
+static pthread_t *worker;
+static bool done = false;
static pthread_mutex_t thread_lock;
static pthread_cond_t thread_parent, thread_worker;
static struct stats waketime_stats, wakeup_stats;
-static unsigned int threads_starting, nthreads = 0;
+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", &nthreads, "Specify amount of threads"),
- OPT_UINTEGER('w', "nwakes", &nwakes, "Specify amount of threads to wake 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_UINTEGER('t', "threads", ¶ms.nthreads, "Specify amount of threads"),
+ OPT_UINTEGER('w', "nwakes", ¶ms.nwakes, "Specify amount of threads to wake at once"),
+ OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"),
+ OPT_BOOLEAN( 'S', "shared", ¶ms.fshared, "Use shared futexes instead of private ones"),
OPT_END()
};
@@ -84,7 +86,7 @@ static void print_summary(void)
printf("Wokeup %d of %d threads in %.4f ms (+-%.2f%%)\n",
wakeup_avg,
- nthreads,
+ params.nthreads,
waketime_avg / USEC_PER_MSEC,
rel_stddev_stats(waketime_stddev, waketime_avg));
}
@@ -95,10 +97,10 @@ static void block_threads(pthread_t *w,
cpu_set_t cpuset;
unsigned int i;
- threads_starting = nthreads;
+ threads_starting = params.nthreads;
/* create and block all threads */
- for (i = 0; i < nthreads; i++) {
+ for (i = 0; i < params.nthreads; i++) {
CPU_ZERO(&cpuset);
CPU_SET(cpu->map[i % cpu->nr], &cpuset);
@@ -140,19 +142,20 @@ int bench_futex_wake(int argc, const char **argv)
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
- if (!nthreads)
- nthreads = cpu->nr;
+ if (!params.nthreads)
+ params.nthreads = cpu->nr;
- worker = calloc(nthreads, sizeof(*worker));
+ worker = calloc(params.nthreads, sizeof(*worker));
if (!worker)
err(EXIT_FAILURE, "calloc");
- if (!fshared)
+ 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(), nthreads, fshared ? "shared":"private", &futex1, nwakes);
+ getpid(), params.nthreads, params.fshared ? "shared":"private",
+ &futex1, params.nwakes);
init_stats(&wakeup_stats);
init_stats(&waketime_stats);
@@ -179,20 +182,22 @@ int bench_futex_wake(int argc, const char **argv)
/* Ok, all threads are patiently blocked, start waking folks up */
gettimeofday(&start, NULL);
- while (nwoken != nthreads)
- nwoken += futex_wake(&futex1, nwakes, futex_flag);
+ 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 (!silent) {
+ if (!params.silent) {
printf("[Run %d]: Wokeup %d of %d threads in %.4f ms\n",
- j + 1, nwoken, nthreads, runtime.tv_usec / (double)USEC_PER_MSEC);
+ j + 1, nwoken, params.nthreads,
+ runtime.tv_usec / (double)USEC_PER_MSEC);
}
- for (i = 0; i < nthreads; i++) {
+ for (i = 0; i < params.nthreads; i++) {
ret = pthread_join(worker[i], NULL);
if (ret)
err(EXIT_FAILURE, "pthread_join");
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index 31b53cc7d5bc..5f98653e6bb3 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -13,6 +13,17 @@
#include <sys/types.h>
#include <linux/futex.h>
+struct bench_futex_parameters {
+ bool silent;
+ bool fshared;
+ bool multi; /* lock-pi */
+ unsigned int runtime; /* seconds*/
+ unsigned int nthreads;
+ unsigned int nfutexes;
+ unsigned int nwakes;
+ unsigned int nrequeue;
+};
+
/**
* futex() - SYS_futex syscall wrapper
* @uaddr: address of first futex
--
2.26.2
^ permalink raw reply related [flat|nested] 15+ messages in thread
* [PATCH 4/7] perf/bench-futex: Add --mlockall parameter
2021-08-09 4:32 [PATCH -tip v2 0/7] perf/bench-futex: Misc updates Davidlohr Bueso
` (2 preceding siblings ...)
2021-08-09 4:32 ` [PATCH 3/7] perf/bench-futex: Factor out futex_flag Davidlohr Bueso
@ 2021-08-09 4:32 ` Davidlohr Bueso
2021-08-09 14:56 ` Arnaldo Carvalho de Melo
2021-08-09 4:32 ` [PATCH 5/7] perf/bench-futex, requeue: Add --broadcast option Davidlohr Bueso
` (2 subsequent siblings)
6 siblings, 1 reply; 15+ messages in thread
From: Davidlohr Bueso @ 2021-08-09 4:32 UTC (permalink / raw)
To: acme
Cc: mingo, peterz, tglx, linux-perf-users, linux-kernel, dave,
Davidlohr Bueso
This adds, across all futex benchmarks, the -m/--mlockall option
which is a common operation for realtime workloads by not incurring
in page faults in paths that want determinism. As such, threads
started after a call to mlockall(2) will generate page faults
immediately since the new stack is immediately forced to memory,
due to the MCL_FUTURE flag.
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
---
tools/perf/bench/futex-hash.c | 7 +++++++
tools/perf/bench/futex-lock-pi.c | 7 +++++++
tools/perf/bench/futex-requeue.c | 7 +++++++
tools/perf/bench/futex-wake-parallel.c | 8 ++++++++
tools/perf/bench/futex-wake.c | 8 ++++++++
tools/perf/bench/futex.h | 1 +
6 files changed, 38 insertions(+)
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index b71a34204b79..af9fbb409472 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -20,6 +20,7 @@
#include <linux/kernel.h>
#include <linux/zalloc.h>
#include <sys/time.h>
+#include <sys/mman.h>
#include <perf/cpumap.h>
#include "../util/stat.h"
@@ -55,6 +56,7 @@ static const struct option options[] = {
OPT_UINTEGER('f', "futexes", ¶ms.nfutexes, "Specify amount of futexes per threads"),
OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"),
OPT_BOOLEAN( 'S', "shared", ¶ms.fshared, "Use shared futexes instead of private ones"),
+ OPT_BOOLEAN( 'm', "mlockall", ¶ms.mlockall, "Lock all current and future memory"),
OPT_END()
};
@@ -141,6 +143,11 @@ int bench_futex_hash(int argc, const char **argv)
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) /* default to the number of CPUs */
params.nthreads = cpu->nr;
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index bc208edf3de3..d2927d2eb3f7 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -21,6 +21,7 @@
#include <err.h>
#include <stdlib.h>
#include <sys/time.h>
+#include <sys/mman.h>
struct worker {
int tid;
@@ -47,6 +48,7 @@ static const struct option options[] = {
OPT_BOOLEAN( 'M', "multi", ¶ms.multi, "Use multiple futexes"),
OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"),
OPT_BOOLEAN( 'S', "shared", ¶ms.fshared, "Use shared futexes instead of private ones"),
+ OPT_BOOLEAN( 'm', "mlockall", ¶ms.mlockall, "Lock all current and future memory"),
OPT_END()
};
@@ -164,6 +166,11 @@ int bench_futex_lock_pi(int argc, const char **argv)
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 = cpu->nr;
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 4001312122be..88cb7e2a6729 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -27,6 +27,7 @@
#include <err.h>
#include <stdlib.h>
#include <sys/time.h>
+#include <sys/mman.h>
static u_int32_t futex1 = 0, futex2 = 0;
@@ -50,6 +51,7 @@ static const struct option options[] = {
OPT_UINTEGER('q', "nrequeue", ¶ms.nrequeue, "Specify amount of threads to requeue at once"),
OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"),
OPT_BOOLEAN( 'S', "shared", ¶ms.fshared, "Use shared futexes instead of private ones"),
+ OPT_BOOLEAN( 'm', "mlockall", ¶ms.mlockall, "Lock all current and future memory"),
OPT_END()
};
@@ -133,6 +135,11 @@ int bench_futex_requeue(int argc, const char **argv)
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 = cpu->nr;
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index ea4fdea6e2f3..ef1f8237fd81 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -34,6 +34,7 @@ int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe
#include <err.h>
#include <stdlib.h>
#include <sys/time.h>
+#include <sys/mman.h>
struct thread_data {
pthread_t worker;
@@ -61,6 +62,8 @@ static const struct option options[] = {
OPT_UINTEGER('w', "nwakers", ¶ms.nwakes, "Specify amount of waking threads"),
OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"),
OPT_BOOLEAN( 'S', "shared", ¶ms.fshared, "Use shared futexes instead of private ones"),
+ OPT_BOOLEAN( 'm', "mlockall", ¶ms.mlockall, "Lock all current and future memory"),
+
OPT_END()
};
@@ -238,6 +241,11 @@ int bench_futex_wake_parallel(int argc, const char **argv)
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
+ if (params.mlockall) {
+ if (mlockall(MCL_CURRENT | MCL_FUTURE))
+ err(EXIT_FAILURE, "mlockall");
+ }
+
cpu = perf_cpu_map__new(NULL);
if (!cpu)
err(EXIT_FAILURE, "calloc");
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 1cf651c8ee5c..40e492c7996a 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -27,6 +27,7 @@
#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;
@@ -51,6 +52,8 @@ static const struct option options[] = {
OPT_UINTEGER('w', "nwakes", ¶ms.nwakes, "Specify amount of threads to wake at once"),
OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"),
OPT_BOOLEAN( 'S', "shared", ¶ms.fshared, "Use shared futexes instead of private ones"),
+ OPT_BOOLEAN( 'm', "mlockall", ¶ms.mlockall, "Lock all current and future memory"),
+
OPT_END()
};
@@ -141,6 +144,11 @@ int bench_futex_wake(int argc, const char **argv)
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 = cpu->nr;
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index f7cd22bbd677..1c8fa469993f 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -19,6 +19,7 @@ static int futex_flag = 0;
struct bench_futex_parameters {
bool silent;
bool fshared;
+ bool mlockall;
bool multi; /* lock-pi */
unsigned int runtime; /* seconds*/
unsigned int nthreads;
--
2.26.2
^ permalink raw reply related [flat|nested] 15+ messages in thread
* [PATCH 7/7] perf/bench-futex, requeue: Add --pi parameter
2021-08-09 4:32 [PATCH -tip v2 0/7] perf/bench-futex: Misc updates Davidlohr Bueso
` (5 preceding siblings ...)
2021-08-09 4:33 ` [PATCH 6/7] perf/bench-futex, requeue: Robustify futex_wait() handling Davidlohr Bueso
@ 2021-08-09 4:33 ` Davidlohr Bueso
2021-08-09 15:01 ` Arnaldo Carvalho de Melo
6 siblings, 1 reply; 15+ messages in thread
From: Davidlohr Bueso @ 2021-08-09 4:33 UTC (permalink / raw)
To: acme
Cc: mingo, peterz, tglx, linux-perf-users, linux-kernel, dave,
Davidlohr Bueso
This extends the program to measure WAIT_REQUEUE_PI+CMP_REQUEUE_PI
pairs, which are the underlying machinery behind priority-inheritance
aware condition variables. The defaults are the same as with the regular
non-pi version, requeueing one task at a time, with the exception that
PI will always wakeup the first waiter.
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
---
tools/perf/bench/futex-requeue.c | 100 +++++++++++++++++++++++--------
tools/perf/bench/futex.h | 37 +++++++++++-
2 files changed, 111 insertions(+), 26 deletions(-)
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index e4892ba6864f..03a05814d45e 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -6,7 +6,8 @@
* 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.
+ * requeues without waking up any tasks (in the non-pi case) -- thus
+ * mimicking a regular futex_wait.
*/
/* For the CLR_() macros */
@@ -53,6 +54,8 @@ static const struct option options[] = {
OPT_BOOLEAN( 'S', "shared", ¶ms.fshared, "Use shared futexes instead of private ones"),
OPT_BOOLEAN( 'm', "mlockall", ¶ms.mlockall, "Lock all current and future memory"),
OPT_BOOLEAN( 'B', "broadcast", ¶ms.broadcast, "Requeue all threads at once"),
+ OPT_BOOLEAN( 'p', "pi", ¶ms.pi, "Use PI-aware variants of FUTEX_CMP_REQUEUE"),
+
OPT_END()
};
@@ -86,14 +89,30 @@ static void *workerfn(void *arg __maybe_unused)
pthread_mutex_unlock(&thread_lock);
while (1) {
- ret = futex_wait(&futex1, 0, NULL, futex_flag);
- if (!ret)
- break;
-
- if (ret && errno != EAGAIN) {
- if (!params.silent)
- warn("futex_wait");
- break;
+ if (!params.pi) {
+ ret = futex_wait(&futex1, 0, NULL, futex_flag);
+ if (!ret)
+ break;
+
+ if (ret && errno != EAGAIN) {
+ if (!params.silent)
+ warnx("futex_wait");
+ break;
+ }
+ } else {
+ ret = futex_wait_requeue_pi(&futex1, 0, &futex2,
+ NULL, futex_flag);
+ if (!ret) {
+ /* got the lock at futex2 */
+ futex_unlock_pi(&futex2, futex_flag);
+ break;
+ }
+
+ if (ret && errno != EAGAIN) {
+ if (!params.silent)
+ warnx("futex_wait_requeue_pi");
+ break;
+ }
}
}
@@ -170,9 +189,10 @@ int bench_futex_requeue(int argc, const char **argv)
if (params.broadcast)
params.nrequeue = params.nthreads;
- printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), "
+ printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %s%p), "
"%d at a time.\n\n", getpid(), params.nthreads,
- params.fshared ? "shared":"private", &futex1, &futex2, params.nrequeue);
+ params.fshared ? "shared":"private", &futex1,
+ params.pi ? "PI ": "", &futex2, params.nrequeue);
init_stats(&requeued_stats);
init_stats(&requeuetime_stats);
@@ -182,7 +202,7 @@ int bench_futex_requeue(int argc, const char **argv)
pthread_cond_init(&thread_worker, NULL);
for (j = 0; j < bench_repeat && !done; j++) {
- unsigned int nrequeued = 0;
+ unsigned int nrequeued = 0, wakeups = 0;
struct timeval start, end, runtime;
/* create, launch & block all threads */
@@ -200,13 +220,30 @@ int bench_futex_requeue(int argc, const char **argv)
/* Ok, all threads are patiently blocked, start requeueing */
gettimeofday(&start, NULL);
while (nrequeued < params.nthreads) {
+ int r;
+
/*
- * Do not wakeup any tasks blocked on futex1, allowing
- * us to really measure futex_wait functionality.
+ * For the regular non-pi case, do not wakeup any tasks
+ * blocked on futex1, allowing us to really measure
+ * futex_wait functionality. For the PI case the first
+ * waiter is always awoken.
*/
- nrequeued += futex_cmp_requeue(&futex1, 0, &futex2, 0,
- params.nrequeue,
- futex_flag);
+ if (!params.pi) {
+ r = futex_cmp_requeue(&futex1, 0, &futex2, 0,
+ params.nrequeue,
+ futex_flag);
+ } else {
+ r = futex_cmp_requeue_pi(&futex1, 0, &futex2,
+ params.nrequeue,
+ futex_flag);
+ wakeups++; /* assume no error */
+ }
+
+ if (r < 0)
+ err(EXIT_FAILURE, "couldn't requeue from %p to %p",
+ &futex1, &futex2);
+
+ nrequeued += r;
}
gettimeofday(&end, NULL);
@@ -216,16 +253,29 @@ int bench_futex_requeue(int argc, const char **argv)
update_stats(&requeuetime_stats, runtime.tv_usec);
if (!params.silent) {
- printf("[Run %d]: Requeued %d of %d threads in %.4f ms\n",
- j + 1, nrequeued, params.nthreads,
- runtime.tv_usec / (double)USEC_PER_MSEC);
+ if (!params.pi)
+ printf("[Run %d]: Requeued %d of %d threads in "
+ "%.4f ms\n", j + 1, nrequeued,
+ params.nthreads,
+ runtime.tv_usec / (double)USEC_PER_MSEC);
+ else {
+ nrequeued -= wakeups;
+ printf("[Run %d]: Awoke and Requeued (%d+%d) of "
+ "%d threads in %.4f ms\n",
+ j + 1, wakeups, nrequeued,
+ params.nthreads,
+ runtime.tv_usec / (double)USEC_PER_MSEC);
+ }
+
}
- /* everybody should be blocked on futex2, wake'em up */
- nrequeued = futex_wake(&futex2, nrequeued, futex_flag);
- if (params.nthreads != nrequeued)
- warnx("couldn't wakeup all tasks (%d/%d)",
- nrequeued, params.nthreads);
+ if (!params.pi) {
+ /* everybody should be blocked on futex2, wake'em up */
+ nrequeued = futex_wake(&futex2, nrequeued, futex_flag);
+ if (params.nthreads != nrequeued)
+ warnx("couldn't wakeup all tasks (%d/%d)",
+ nrequeued, params.nthreads);
+ }
for (i = 0; i < params.nthreads; i++) {
ret = pthread_join(worker[i], NULL);
diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h
index 36f158650edf..f0ad6d988349 100644
--- a/tools/perf/bench/futex.h
+++ b/tools/perf/bench/futex.h
@@ -21,6 +21,7 @@ struct bench_futex_parameters {
bool fshared;
bool mlockall;
bool multi; /* lock-pi */
+ bool pi; /* requeue-pi */
bool broadcast; /* requeue */
unsigned int runtime; /* seconds*/
unsigned int nthreads;
@@ -93,7 +94,7 @@ futex_unlock_pi(u_int32_t *uaddr, int opflags)
/**
* futex_cmp_requeue() - requeue tasks from uaddr to uaddr2
* @nr_wake: wake up to this many tasks
-* @nr_requeue: requeue up to this many tasks
+* @nr_requeue: requeue up to this many tasks
*/
static inline int
futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wake,
@@ -102,4 +103,38 @@ futex_cmp_requeue(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, int nr_wak
return futex(uaddr, FUTEX_CMP_REQUEUE, nr_wake, nr_requeue, uaddr2,
val, opflags);
}
+
+/**
+ * futex_wait_requeue_pi() - block on uaddr and prepare to requeue to uaddr2
+ * @uaddr: non-PI futex source
+ * @uaddr2: PI futex target
+ *
+ * This is the first half of the requeue_pi mechanism. It shall always be
+ * paired with futex_cmp_requeue_pi().
+ */
+static inline int
+futex_wait_requeue_pi(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2,
+ struct timespec *timeout, int opflags)
+{
+ return futex(uaddr, FUTEX_WAIT_REQUEUE_PI, val, timeout, uaddr2, 0,
+ opflags);
+}
+
+/**
+ * futex_cmp_requeue_pi() - requeue tasks from uaddr to uaddr2
+ * @uaddr: non-PI futex source
+ * @uaddr2: PI futex target
+ * @nr_requeue: requeue up to this many tasks
+ *
+ * This is the second half of the requeue_pi mechanism. It shall always be
+ * paired with futex_wait_requeue_pi(). The first waker is always awoken.
+ */
+static inline int
+futex_cmp_requeue_pi(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2,
+ int nr_requeue, int opflags)
+{
+ return futex(uaddr, FUTEX_CMP_REQUEUE_PI, 1, nr_requeue, uaddr2,
+ val, opflags);
+}
+
#endif /* _FUTEX_H */
--
2.26.2
^ permalink raw reply related [flat|nested] 15+ messages in thread