[PATCH 2/3] perf bench futex: Add --affine-wakers option to wake-parallel

[Davidlohr Bueso <dave@stgolabs.net>]

From: James Yang <james.yang@arm.com>

The waker threads' processor affinity is not specified, so
the result has run-to-run variability as the scheduler
decides on which CPUs they are to run.  So we add a
-W/--affine-wakers flag to stripe the affinity of the
waker threads across the online CPUs instead of having
the scheduler place them.

Cc: Kim Phillips <Kim.Phillips@arm.com>
Signed-off-by: James Yang <james.yang@arm.com>
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
---
 tools/perf/bench/futex-wake-parallel.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 979e303e4797..c04e207ea37c 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -39,6 +39,7 @@ static u_int32_t futex = 0;
 
 static pthread_t *blocked_worker;
 static bool done = false, silent = false, fshared = false;
+static bool affine_wakers = false;
 static unsigned int nblocked_threads = 0, nwaking_threads = 0;
 static pthread_mutex_t thread_lock;
 static pthread_cond_t thread_parent, thread_worker;
@@ -51,6 +52,7 @@ static const struct option options[] = {
 	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_BOOLEAN( 'W', "affine-wakers", &affine_wakers, "Stripe affinity of waker threads across CPUs"),
 	OPT_END()
 };
 
@@ -78,7 +80,8 @@ static void *waking_workerfn(void *arg)
 	return NULL;
 }
 
-static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
+static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr,
+			   struct cpu_map *cpu)
 {
 	unsigned int i;
 
@@ -91,6 +94,17 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
 		 * as it will affect the order to acquire the hb spinlock.
 		 * For now let the scheduler decide.
 		 */
+		if (affine_wakers) {
+			cpu_set_t cpuset;
+			CPU_ZERO(&cpuset);
+			CPU_SET(cpu->map[(i + 1) % cpu->nr], &cpuset);
+
+			if (pthread_attr_setaffinity_np(&thread_attr,
+							sizeof(cpu_set_t),
+							&cpuset))
+				err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+		}
+
 		if (pthread_create(&td[i].worker, &thread_attr,
 				   waking_workerfn, (void *)&td[i]))
 			err(EXIT_FAILURE, "pthread_create");
@@ -276,7 +290,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 		usleep(100000);
 
 		/* Ok, all threads are patiently blocked, start waking folks up */
-		wakeup_threads(waking_worker, thread_attr);
+		wakeup_threads(waking_worker, thread_attr, cpu);
 
 		for (i = 0; i < nblocked_threads; i++) {
 			ret = pthread_join(blocked_worker[i], NULL);
-- 
2.13.6