[PATCH 1/2] perf bench: futex: Support operations for shared futexes

[PATCH 1/2] perf bench: futex: Support operations for shared futexes

[Davidlohr Bueso]

Unlike futex-hash, requeuing and wakeup benchmarks do not support
shared futexes, limiting the usefulness of the programs. Correct
this, and allow using the local -S parameter. The default remains
using private futexes.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
---
 tools/perf/bench/futex-hash.c    |  7 +++++--
 tools/perf/bench/futex-requeue.c | 24 +++++++++++++++---------
 tools/perf/bench/futex-wake.c    | 15 ++++++++++-----
 3 files changed, 30 insertions(+), 16 deletions(-)

diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index a84206e..fc9bebd 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -26,6 +26,7 @@ static unsigned int nsecs    = 10;
 /* amount of futexes per thread */
 static unsigned int nfutexes = 1024;
 static bool fshared = false, done = false, silent = false;
+static int futex_flag = 0;
 
 struct timeval start, end, runtime;
 static pthread_mutex_t thread_lock;
@@ -75,8 +76,7 @@ static void *workerfn(void *arg)
 			 * such as internal waitqueue handling, thus enlarging
 			 * the critical region protected by hb->lock.
 			 */
-			ret = futex_wait(&w->futex[i], 1234, NULL,
-					 fshared ? 0 : FUTEX_PRIVATE_FLAG);
+			ret = futex_wait(&w->futex[i], 1234, NULL, futex_flag);
 			if (!silent &&
 			    (!ret || errno != EAGAIN || errno != EWOULDBLOCK))
 				warn("Non-expected futex return call");
@@ -135,6 +135,9 @@ int bench_futex_hash(int argc, const char **argv,
 	if (!worker)
 		goto errmem;
 
+	if (!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);
 
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 732403b..9837a88 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -30,16 +30,18 @@ static u_int32_t futex1 = 0, futex2 = 0;
 static unsigned int nrequeue = 1;
 
 static pthread_t *worker;
-static bool done = 0, silent = 0;
+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()
 };
 
@@ -70,7 +72,7 @@ static void *workerfn(void *arg __maybe_unused)
 	pthread_cond_wait(&thread_worker, &thread_lock);
 	pthread_mutex_unlock(&thread_lock);
 
-	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	futex_wait(&futex1, 0, NULL, futex_flag);
 	return NULL;
 }
 
@@ -127,9 +129,12 @@ int bench_futex_requeue(int argc, const char **argv,
 	if (!worker)
 		err(EXIT_FAILURE, "calloc");
 
-	printf("Run summary [PID %d]: Requeuing %d threads (from %p to %p), "
-	       "%d at a time.\n\n",
-	       getpid(), nthreads, &futex1, &futex2, nrequeue);
+	if (!fshared)
+		futex_flag = FUTEX_PRIVATE_FLAG;
+
+	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);
@@ -156,13 +161,14 @@ int bench_futex_requeue(int argc, const char **argv,
 
 		/* Ok, all threads are patiently blocked, start requeueing */
 		gettimeofday(&start, NULL);
-		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue)
+		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) {
 			/*
 			 * Do not wakeup any tasks blocked on futex1, allowing
 			 * us to really measure futex_wait functionality.
 			 */
-			futex_cmp_requeue(&futex1, 0, &futex2, 0, nrequeue,
-					  FUTEX_PRIVATE_FLAG);
+			futex_cmp_requeue(&futex1, 0, &futex2, 0,
+					  nrequeue, futex_flag);
+		}
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 
@@ -175,7 +181,7 @@ int bench_futex_requeue(int argc, const char **argv,
 		}
 
 		/* everybody should be blocked on futex2, wake'em up */
-		nrequeued = futex_wake(&futex2, nthreads, FUTEX_PRIVATE_FLAG);
+		nrequeued = futex_wake(&futex2, nthreads, futex_flag);
 		if (nthreads != nrequeued)
 			warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
 
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 50022cb..929f762 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -31,16 +31,18 @@ static u_int32_t futex1 = 0;
 static unsigned int nwakes = 1;
 
 pthread_t *worker;
-static bool done = false, silent = false;
+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 waketime_stats, wakeup_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('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_END()
 };
 
@@ -58,7 +60,7 @@ static void *workerfn(void *arg __maybe_unused)
 	pthread_cond_wait(&thread_worker, &thread_lock);
 	pthread_mutex_unlock(&thread_lock);
 
-	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	futex_wait(&futex1, 0, NULL, futex_flag);
 	return NULL;
 }
 
@@ -130,9 +132,12 @@ int bench_futex_wake(int argc, const char **argv,
 	if (!worker)
 		err(EXIT_FAILURE, "calloc");
 
-	printf("Run summary [PID %d]: blocking on %d threads (at futex %p), "
+	if (!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, &futex1, nwakes);
+	       getpid(), nthreads, fshared ? "shared":"private",  &futex1, nwakes);
 
 	init_stats(&wakeup_stats);
 	init_stats(&waketime_stats);
@@ -160,7 +165,7 @@ 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_PRIVATE_FLAG);
+			nwoken += futex_wake(&futex1, nwakes, futex_flag);
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 
-- 
1.8.4.5

[PATCH 2/2] perf bench: futex: Sanitize -q option in requeue

[Davidlohr Bueso]

When given the number of threads to requeue at once by
user input, there's always the risk of this value being
larger than the total number of threads. This doesn't
make any sense, and the kernel can easily deal with
such sort of situations, hence no big deal. We should
however prevent bogus output such as:

./perf bench --repeat 2 futex requeue -q 10
Run summary [PID 22210]: Requeuing 4 threads (from [private] 0x99ef3c to 0x99ef38), 10 at a time.

[Run 1]: Requeued 10 of 4 threads in 0.0040 ms
[Run 2]: Requeued 10 of 4 threads in 0.0030 ms
Requeued 10 of 4 threads in 0.0035 ms (+-14.29%)

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
---
 tools/perf/bench/futex-requeue.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 9837a88..bedff6b 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -172,6 +172,9 @@ int bench_futex_requeue(int argc, const char **argv,
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 
+		if (nrequeued > nthreads)
+			nrequeued = nthreads;
+
 		update_stats(&requeued_stats, nrequeued);
 		update_stats(&requeuetime_stats, runtime.tv_usec);
 
@@ -190,7 +193,6 @@ int bench_futex_requeue(int argc, const char **argv,
 			if (ret)
 				err(EXIT_FAILURE, "pthread_join");
 		}
-
 	}
 
 	/* cleanup & report results */
-- 
1.8.4.5

[tip:perf/core] perf bench futex: Support operations for shared futexes

[tip-bot for Davidlohr Bueso]

Commit-ID:  86c87e13f8a5dffc6cc7b0f37340f815dc172945
Gitweb:     http://git.kernel.org/tip/86c87e13f8a5dffc6cc7b0f37340f815dc172945
Author:     Davidlohr Bueso <dave@stgolabs.net>
AuthorDate: Mon, 29 Sep 2014 09:41:07 -0700
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 29 Sep 2014 15:43:21 -0300

perf bench futex: Support operations for shared futexes

Unlike futex-hash, requeuing and wakeup benchmarks do not support shared
futexes, limiting the usefulness of the programs. Correct this, and
allow using the local -S parameter. The default remains using private
futexes.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Davidlohr Bueso <dbueso@suse.de>
Link: http://lkml.kernel.org/r/1412008868-22328-1-git-send-email-dave@stgolabs.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/futex-hash.c    |  7 +++++--
 tools/perf/bench/futex-requeue.c | 24 +++++++++++++++---------
 tools/perf/bench/futex-wake.c    | 15 ++++++++++-----
 3 files changed, 30 insertions(+), 16 deletions(-)

diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index a84206e..fc9bebd 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -26,6 +26,7 @@ static unsigned int nsecs    = 10;
 /* amount of futexes per thread */
 static unsigned int nfutexes = 1024;
 static bool fshared = false, done = false, silent = false;
+static int futex_flag = 0;
 
 struct timeval start, end, runtime;
 static pthread_mutex_t thread_lock;
@@ -75,8 +76,7 @@ static void *workerfn(void *arg)
 			 * such as internal waitqueue handling, thus enlarging
 			 * the critical region protected by hb->lock.
 			 */
-			ret = futex_wait(&w->futex[i], 1234, NULL,
-					 fshared ? 0 : FUTEX_PRIVATE_FLAG);
+			ret = futex_wait(&w->futex[i], 1234, NULL, futex_flag);
 			if (!silent &&
 			    (!ret || errno != EAGAIN || errno != EWOULDBLOCK))
 				warn("Non-expected futex return call");
@@ -135,6 +135,9 @@ int bench_futex_hash(int argc, const char **argv,
 	if (!worker)
 		goto errmem;
 
+	if (!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);
 
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 732403b..9837a88 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -30,16 +30,18 @@ static u_int32_t futex1 = 0, futex2 = 0;
 static unsigned int nrequeue = 1;
 
 static pthread_t *worker;
-static bool done = 0, silent = 0;
+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()
 };
 
@@ -70,7 +72,7 @@ static void *workerfn(void *arg __maybe_unused)
 	pthread_cond_wait(&thread_worker, &thread_lock);
 	pthread_mutex_unlock(&thread_lock);
 
-	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	futex_wait(&futex1, 0, NULL, futex_flag);
 	return NULL;
 }
 
@@ -127,9 +129,12 @@ int bench_futex_requeue(int argc, const char **argv,
 	if (!worker)
 		err(EXIT_FAILURE, "calloc");
 
-	printf("Run summary [PID %d]: Requeuing %d threads (from %p to %p), "
-	       "%d at a time.\n\n",
-	       getpid(), nthreads, &futex1, &futex2, nrequeue);
+	if (!fshared)
+		futex_flag = FUTEX_PRIVATE_FLAG;
+
+	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);
@@ -156,13 +161,14 @@ int bench_futex_requeue(int argc, const char **argv,
 
 		/* Ok, all threads are patiently blocked, start requeueing */
 		gettimeofday(&start, NULL);
-		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue)
+		for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) {
 			/*
 			 * Do not wakeup any tasks blocked on futex1, allowing
 			 * us to really measure futex_wait functionality.
 			 */
-			futex_cmp_requeue(&futex1, 0, &futex2, 0, nrequeue,
-					  FUTEX_PRIVATE_FLAG);
+			futex_cmp_requeue(&futex1, 0, &futex2, 0,
+					  nrequeue, futex_flag);
+		}
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 
@@ -175,7 +181,7 @@ int bench_futex_requeue(int argc, const char **argv,
 		}
 
 		/* everybody should be blocked on futex2, wake'em up */
-		nrequeued = futex_wake(&futex2, nthreads, FUTEX_PRIVATE_FLAG);
+		nrequeued = futex_wake(&futex2, nthreads, futex_flag);
 		if (nthreads != nrequeued)
 			warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads);
 
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 50022cb..929f762 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -31,16 +31,18 @@ static u_int32_t futex1 = 0;
 static unsigned int nwakes = 1;
 
 pthread_t *worker;
-static bool done = false, silent = false;
+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 waketime_stats, wakeup_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('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_END()
 };
 
@@ -58,7 +60,7 @@ static void *workerfn(void *arg __maybe_unused)
 	pthread_cond_wait(&thread_worker, &thread_lock);
 	pthread_mutex_unlock(&thread_lock);
 
-	futex_wait(&futex1, 0, NULL, FUTEX_PRIVATE_FLAG);
+	futex_wait(&futex1, 0, NULL, futex_flag);
 	return NULL;
 }
 
@@ -130,9 +132,12 @@ int bench_futex_wake(int argc, const char **argv,
 	if (!worker)
 		err(EXIT_FAILURE, "calloc");
 
-	printf("Run summary [PID %d]: blocking on %d threads (at futex %p), "
+	if (!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, &futex1, nwakes);
+	       getpid(), nthreads, fshared ? "shared":"private",  &futex1, nwakes);
 
 	init_stats(&wakeup_stats);
 	init_stats(&waketime_stats);
@@ -160,7 +165,7 @@ 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_PRIVATE_FLAG);
+			nwoken += futex_wake(&futex1, nwakes, futex_flag);
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 

[tip:perf/core] perf bench futex: Sanitize -q option in requeue

[tip-bot for Davidlohr Bueso]

Commit-ID:  e19685ed24b518440c0717719ff02e74c0e6d2cb
Gitweb:     http://git.kernel.org/tip/e19685ed24b518440c0717719ff02e74c0e6d2cb
Author:     Davidlohr Bueso <dave@stgolabs.net>
AuthorDate: Mon, 29 Sep 2014 09:41:08 -0700
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 29 Sep 2014 15:43:26 -0300

perf bench futex: Sanitize -q option in requeue

When given the number of threads to requeue at once by user input,
there's always the risk of this value being larger than the total number
of threads.  This doesn't make any sense, and the kernel can easily deal
with such sort of situations, hence no big deal. We should however
prevent bogus output such as:

./perf bench --repeat 2 futex requeue -q 10
Run summary [PID 22210]: Requeuing 4 threads (from [private] 0x99ef3c to 0x99ef38), 10 at a time.

[Run 1]: Requeued 10 of 4 threads in 0.0040 ms
[Run 2]: Requeued 10 of 4 threads in 0.0030 ms
Requeued 10 of 4 threads in 0.0035 ms (+-14.29%)

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Davidlohr Bueso <dbueso@suse.de>
Link: http://lkml.kernel.org/r/1412008868-22328-2-git-send-email-dave@stgolabs.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/bench/futex-requeue.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 9837a88..bedff6b 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -172,6 +172,9 @@ int bench_futex_requeue(int argc, const char **argv,
 		gettimeofday(&end, NULL);
 		timersub(&end, &start, &runtime);
 
+		if (nrequeued > nthreads)
+			nrequeued = nthreads;
+
 		update_stats(&requeued_stats, nrequeued);
 		update_stats(&requeuetime_stats, runtime.tv_usec);
 
@@ -190,7 +193,6 @@ int bench_futex_requeue(int argc, const char **argv,
 			if (ret)
 				err(EXIT_FAILURE, "pthread_join");
 		}
-
 	}
 
 	/* cleanup & report results */