[PATCH 1/3] perf bench futex: benchmark only online CPUs

[Kim Phillips]

From: James Yang <james.yang@xxxxxxx>

The "perf bench futex" benchmarks have a problem when not all CPUs in
the system are online:  perf assumes the CPUs that are online are
contiguously numbered and assigns processor affinity to the threads by
modulo striping.  When the online CPUs are not contiguously numbered,
perf errors out with:

$ echo 0 | sudo tee /sys/devices/system/cpu/cpu3/online
0
$ ./oldperf bench futex all
perf: pthread_create: Operation not permitted
Run summary [PID 14934]: 7 threads, each operating on 1024 [private] futexes for 10 secs.

$

This patch makes perf not assume all CPUs configured are online, and
adds a mapping table to stripe affinity across the CPUs that are
online.

Signed-off-by: James Yang <james.yang@xxxxxxx>
Signed-off-by: Kim Phillips <kim.phillips@xxxxxxx>
---
 tools/perf/bench/Build                 |  1 +
 tools/perf/bench/cpu-online-map.c      | 21 +++++++++++++++++++++
 tools/perf/bench/cpu-online-map.h      |  6 ++++++
 tools/perf/bench/futex-hash.c          | 14 ++++++++++++--
 tools/perf/bench/futex-lock-pi.c       | 15 ++++++++++++---
 tools/perf/bench/futex-requeue.c       | 14 +++++++++++---
 tools/perf/bench/futex-wake-parallel.c | 17 ++++++++++++++---
 tools/perf/bench/futex-wake.c          | 15 ++++++++++++---
 8 files changed, 89 insertions(+), 14 deletions(-)
 create mode 100644 tools/perf/bench/cpu-online-map.c
 create mode 100644 tools/perf/bench/cpu-online-map.h

diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build
index 60bf11943047..bc79d3577ace 100644
--- a/tools/perf/bench/Build
+++ b/tools/perf/bench/Build
@@ -6,6 +6,7 @@ perf-y += futex-wake.o
 perf-y += futex-wake-parallel.o
 perf-y += futex-requeue.o
 perf-y += futex-lock-pi.o
+perf-y += cpu-online-map.o
 
 perf-$(CONFIG_X86_64) += mem-memcpy-x86-64-asm.o
 perf-$(CONFIG_X86_64) += mem-memset-x86-64-asm.o
diff --git a/tools/perf/bench/cpu-online-map.c b/tools/perf/bench/cpu-online-map.c
new file mode 100644
index 000000000000..4157d2220bf4
--- /dev/null
+++ b/tools/perf/bench/cpu-online-map.c
@@ -0,0 +1,21 @@
+#include <sched.h>
+#include <unistd.h>
+#include <err.h>
+#include <stdlib.h>
+#include "cpu-online-map.h"
+
+void compute_cpu_online_map(int *cpu_online_map)
+{
+	long ncpus_conf = sysconf(_SC_NPROCESSORS_CONF);
+	cpu_set_t set;
+	size_t j = 0;
+
+	CPU_ZERO(&set);
+
+	if (sched_getaffinity(0, sizeof(set), &set))
+		err(EXIT_FAILURE, "sched_getaffinity");
+
+	for (int i = 0; i < ncpus_conf; i++)
+		if (CPU_ISSET(i, &set))
+			cpu_online_map[j++] = i;
+}
diff --git a/tools/perf/bench/cpu-online-map.h b/tools/perf/bench/cpu-online-map.h
new file mode 100644
index 000000000000..0620a674c6d8
--- /dev/null
+++ b/tools/perf/bench/cpu-online-map.h
@@ -0,0 +1,6 @@
+#ifndef CPU_ONLINE_MAP_H
+#define CPU_ONLINE_MAP_H
+
+void compute_cpu_online_map(int *cpu_online_map);
+
+#endif
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 58ae6ed8f38b..81314eea1cf5 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -24,6 +24,7 @@
 #include <subcmd/parse-options.h>
 #include "bench.h"
 #include "futex.h"
+#include "cpu-online-map.h"
 
 #include <err.h>
 #include <sys/time.h>
@@ -120,9 +121,11 @@ int bench_futex_hash(int argc, const char **argv)
 	int ret = 0;
 	cpu_set_t cpu;
 	struct sigaction act;
-	unsigned int i, ncpus;
+	unsigned int i;
+	long ncpus;
 	pthread_attr_t thread_attr;
 	struct worker *worker = NULL;
+	int *cpu_map;
 
 	argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0);
 	if (argc) {
@@ -132,6 +135,12 @@ int bench_futex_hash(int argc, const char **argv)
 
 	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
 
+	cpu_map = calloc(ncpus, sizeof(int));
+	if (!cpu_map)
+		goto errmem;
+
+	compute_cpu_online_map(cpu_map);
+
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
@@ -164,7 +173,7 @@ int bench_futex_hash(int argc, const char **argv)
 			goto errmem;
 
 		CPU_ZERO(&cpu);
-		CPU_SET(i % ncpus, &cpu);
+		CPU_SET(cpu_map[i % ncpus], &cpu);
 
 		ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu);
 		if (ret)
@@ -217,6 +226,7 @@ int bench_futex_hash(int argc, const char **argv)
 	print_summary();
 
 	free(worker);
+	free(cpu_map);
 	return ret;
 errmem:
 	err(EXIT_FAILURE, "calloc");
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 08653ae8a8c4..42ab351b2c50 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -15,6 +15,7 @@
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
+#include "cpu-online-map.h"
 
 #include <err.h>
 #include <stdlib.h>
@@ -113,7 +114,8 @@ static void *workerfn(void *arg)
 	return NULL;
 }
 
-static void create_threads(struct worker *w, pthread_attr_t thread_attr)
+static void create_threads(struct worker *w, pthread_attr_t thread_attr,
+			   int *cpu_map)
 {
 	cpu_set_t cpu;
 	unsigned int i;
@@ -131,7 +133,7 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr)
 			worker[i].futex = &global_futex;
 
 		CPU_ZERO(&cpu);
-		CPU_SET(i % ncpus, &cpu);
+		CPU_SET(cpu_map[i % ncpus], &cpu);
 
 		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
@@ -147,12 +149,18 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	unsigned int i;
 	struct sigaction act;
 	pthread_attr_t thread_attr;
+	int *cpu_map;
 
 	argc = parse_options(argc, argv, options, bench_futex_lock_pi_usage, 0);
 	if (argc)
 		goto err;
 
 	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+	cpu_map = calloc(ncpus, sizeof(int));
+	if (!cpu_map)
+		err(EXIT_FAILURE, "calloc");
+
+	compute_cpu_online_map(cpu_map);
 
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
@@ -180,7 +188,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	pthread_attr_init(&thread_attr);
 	gettimeofday(&start, NULL);
 
-	create_threads(worker, thread_attr);
+	create_threads(worker, thread_attr, cpu_map);
 	pthread_attr_destroy(&thread_attr);
 
 	pthread_mutex_lock(&thread_lock);
@@ -218,6 +226,7 @@ int bench_futex_lock_pi(int argc, const char **argv)
 	print_summary();
 
 	free(worker);
+	free(cpu_map);
 	return ret;
 err:
 	usage_with_options(bench_futex_lock_pi_usage, options);
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 1058c194608a..366961b901c6 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -22,6 +22,7 @@
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
+#include "cpu-online-map.h"
 
 #include <err.h>
 #include <stdlib.h>
@@ -83,7 +84,7 @@ static void *workerfn(void *arg __maybe_unused)
 }
 
 static void block_threads(pthread_t *w,
-			  pthread_attr_t thread_attr)
+			  pthread_attr_t thread_attr, int *cpu_map)
 {
 	cpu_set_t cpu;
 	unsigned int i;
@@ -93,7 +94,7 @@ static void block_threads(pthread_t *w,
 	/* create and block all threads */
 	for (i = 0; i < nthreads; i++) {
 		CPU_ZERO(&cpu);
-		CPU_SET(i % ncpus, &cpu);
+		CPU_SET(cpu_map[i % ncpus], &cpu);
 
 		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
@@ -116,12 +117,18 @@ int bench_futex_requeue(int argc, const char **argv)
 	unsigned int i, j;
 	struct sigaction act;
 	pthread_attr_t thread_attr;
+	int *cpu_map;
 
 	argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0);
 	if (argc)
 		goto err;
 
 	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+	cpu_map = calloc(ncpus, sizeof(int));
+	if (!cpu_map)
+		err(EXIT_FAILURE, "calloc");
+
+	compute_cpu_online_map(cpu_map);
 
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
@@ -156,7 +163,7 @@ int bench_futex_requeue(int argc, const char **argv)
 		struct timeval start, end, runtime;
 
 		/* create, launch & block all threads */
-		block_threads(worker, thread_attr);
+		block_threads(worker, thread_attr, cpu_map);
 
 		/* make sure all threads are already blocked */
 		pthread_mutex_lock(&thread_lock);
@@ -210,6 +217,7 @@ int bench_futex_requeue(int argc, const char **argv)
 	print_summary();
 
 	free(worker);
+	free(cpu_map);
 	return ret;
 err:
 	usage_with_options(bench_futex_requeue_usage, options);
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index b4732dad9f89..5617bcd17e55 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -21,6 +21,7 @@
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
+#include "cpu-online-map.h"
 
 #include <err.h>
 #include <stdlib.h>
@@ -119,7 +120,8 @@ static void *blocked_workerfn(void *arg __maybe_unused)
 	return NULL;
 }
 
-static void block_threads(pthread_t *w, pthread_attr_t thread_attr)
+static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
+			  int *cpu_map)
 {
 	cpu_set_t cpu;
 	unsigned int i;
@@ -129,7 +131,7 @@ static void block_threads(pthread_t *w, pthread_attr_t thread_attr)
 	/* create and block all threads */
 	for (i = 0; i < nblocked_threads; i++) {
 		CPU_ZERO(&cpu);
-		CPU_SET(i % ncpus, &cpu);
+		CPU_SET(cpu_map[i % ncpus], &cpu);
 
 		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
@@ -205,6 +207,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	struct sigaction act;
 	pthread_attr_t thread_attr;
 	struct thread_data *waking_worker;
+	int *cpu_map;
 
 	argc = parse_options(argc, argv, options,
 			     bench_futex_wake_parallel_usage, 0);
@@ -218,6 +221,13 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	sigaction(SIGINT, &act, NULL);
 
 	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+
+	cpu_map = calloc(ncpus, sizeof(int));
+	if (!cpu_map)
+		err(EXIT_FAILURE, "calloc");
+
+	compute_cpu_online_map(cpu_map);
+
 	if (!nblocked_threads)
 		nblocked_threads = ncpus;
 
@@ -259,7 +269,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 			err(EXIT_FAILURE, "calloc");
 
 		/* create, launch & block all threads */
-		block_threads(blocked_worker, thread_attr);
+		block_threads(blocked_worker, thread_attr, cpu_map);
 
 		/* make sure all threads are already blocked */
 		pthread_mutex_lock(&thread_lock);
@@ -295,5 +305,6 @@ int bench_futex_wake_parallel(int argc, const char **argv)
 	print_summary();
 
 	free(blocked_worker);
+	free(cpu_map);
 	return ret;
 }
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 8c5c0b6b5c97..c0c71a769d2f 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -22,6 +22,7 @@
 #include <errno.h>
 #include "bench.h"
 #include "futex.h"
+#include "cpu-online-map.h"
 
 #include <err.h>
 #include <stdlib.h>
@@ -89,7 +90,7 @@ static void print_summary(void)
 }
 
 static void block_threads(pthread_t *w,
-			  pthread_attr_t thread_attr)
+			  pthread_attr_t thread_attr, int *cpu_map)
 {
 	cpu_set_t cpu;
 	unsigned int i;
@@ -99,7 +100,7 @@ static void block_threads(pthread_t *w,
 	/* create and block all threads */
 	for (i = 0; i < nthreads; i++) {
 		CPU_ZERO(&cpu);
-		CPU_SET(i % ncpus, &cpu);
+		CPU_SET(cpu_map[i % ncpus], &cpu);
 
 		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
@@ -122,6 +123,7 @@ int bench_futex_wake(int argc, const char **argv)
 	unsigned int i, j;
 	struct sigaction act;
 	pthread_attr_t thread_attr;
+	int *cpu_map;
 
 	argc = parse_options(argc, argv, options, bench_futex_wake_usage, 0);
 	if (argc) {
@@ -131,6 +133,12 @@ int bench_futex_wake(int argc, const char **argv)
 
 	ncpus = sysconf(_SC_NPROCESSORS_ONLN);
 
+	cpu_map = calloc(ncpus, sizeof(int));
+	if (! cpu_map)
+		err(EXIT_FAILURE, "calloc");
+
+	compute_cpu_online_map(cpu_map);
+
 	sigfillset(&act.sa_mask);
 	act.sa_sigaction = toggle_done;
 	sigaction(SIGINT, &act, NULL);
@@ -161,7 +169,7 @@ int bench_futex_wake(int argc, const char **argv)
 		struct timeval start, end, runtime;
 
 		/* create, launch & block all threads */
-		block_threads(worker, thread_attr);
+		block_threads(worker, thread_attr, cpu_map);
 
 		/* make sure all threads are already blocked */
 		pthread_mutex_lock(&thread_lock);
@@ -204,5 +212,6 @@ int bench_futex_wake(int argc, const char **argv)
 	print_summary();
 
 	free(worker);
+	free(cpu_map);
 	return ret;
 }
-- 
2.15.0