aboutsummaryrefslogtreecommitdiff
path: root/tools/perf/bench
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/bench')
-rw-r--r--tools/perf/bench/futex-hash.c20
-rw-r--r--tools/perf/bench/futex-lock-pi.c23
-rw-r--r--tools/perf/bench/futex-requeue.c22
-rw-r--r--tools/perf/bench/futex-wake-parallel.c46
-rw-r--r--tools/perf/bench/futex-wake.c18
-rw-r--r--tools/perf/bench/numa.c56
6 files changed, 136 insertions, 49 deletions
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index 58ae6ed8f38b..9aa3a674829b 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -24,9 +24,9 @@
#include <subcmd/parse-options.h>
#include "bench.h"
#include "futex.h"
+#include "cpumap.h"
#include <err.h>
-#include <sys/time.h>
static unsigned int nthreads = 0;
static unsigned int nsecs = 10;
@@ -118,11 +118,12 @@ static void print_summary(void)
int bench_futex_hash(int argc, const char **argv)
{
int ret = 0;
- cpu_set_t cpu;
+ cpu_set_t cpuset;
struct sigaction act;
- unsigned int i, ncpus;
+ unsigned int i;
pthread_attr_t thread_attr;
struct worker *worker = NULL;
+ struct cpu_map *cpu;
argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0);
if (argc) {
@@ -130,14 +131,16 @@ int bench_futex_hash(int argc, const char **argv)
exit(EXIT_FAILURE);
}
- ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+ cpu = cpu_map__new(NULL);
+ if (!cpu)
+ goto errmem;
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
if (!nthreads) /* default to the number of CPUs */
- nthreads = ncpus;
+ nthreads = cpu->nr;
worker = calloc(nthreads, sizeof(*worker));
if (!worker)
@@ -163,10 +166,10 @@ int bench_futex_hash(int argc, const char **argv)
if (!worker[i].futex)
goto errmem;
- CPU_ZERO(&cpu);
- CPU_SET(i % ncpus, &cpu);
+ CPU_ZERO(&cpuset);
+ CPU_SET(cpu->map[i % cpu->nr], &cpuset);
- ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu);
+ ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
if (ret)
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
@@ -217,6 +220,7 @@ int bench_futex_hash(int argc, const char **argv)
print_summary();
free(worker);
+ free(cpu);
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..8e9c4753e304 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 "cpumap.h"
#include <err.h>
#include <stdlib.h>
@@ -32,7 +33,7 @@ static struct worker *worker;
static unsigned int nsecs = 10;
static bool silent = false, multi = false;
static bool done = false, fshared = false;
-static unsigned int ncpus, nthreads = 0;
+static unsigned int nthreads = 0;
static int futex_flag = 0;
struct timeval start, end, runtime;
static pthread_mutex_t thread_lock;
@@ -113,9 +114,10 @@ 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,
+ struct cpu_map *cpu)
{
- cpu_set_t cpu;
+ cpu_set_t cpuset;
unsigned int i;
threads_starting = nthreads;
@@ -130,10 +132,10 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr)
} else
worker[i].futex = &global_futex;
- CPU_ZERO(&cpu);
- CPU_SET(i % ncpus, &cpu);
+ CPU_ZERO(&cpuset);
+ CPU_SET(cpu->map[i % cpu->nr], &cpuset);
- if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+ if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i]))
@@ -147,19 +149,22 @@ int bench_futex_lock_pi(int argc, const char **argv)
unsigned int i;
struct sigaction act;
pthread_attr_t thread_attr;
+ struct cpu_map *cpu;
argc = parse_options(argc, argv, options, bench_futex_lock_pi_usage, 0);
if (argc)
goto err;
- ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+ cpu = cpu_map__new(NULL);
+ if (!cpu)
+ err(EXIT_FAILURE, "calloc");
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
if (!nthreads)
- nthreads = ncpus;
+ nthreads = cpu->nr;
worker = calloc(nthreads, sizeof(*worker));
if (!worker)
@@ -180,7 +185,7 @@ 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);
pthread_attr_destroy(&thread_attr);
pthread_mutex_lock(&thread_lock);
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 1058c194608a..fc692efa0c05 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 "cpumap.h"
#include <err.h>
#include <stdlib.h>
@@ -40,7 +41,7 @@ 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 unsigned int threads_starting, nthreads = 0;
static int futex_flag = 0;
static const struct option options[] = {
@@ -83,19 +84,19 @@ static void *workerfn(void *arg __maybe_unused)
}
static void block_threads(pthread_t *w,
- pthread_attr_t thread_attr)
+ pthread_attr_t thread_attr, struct cpu_map *cpu)
{
- cpu_set_t cpu;
+ cpu_set_t cpuset;
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);
+ CPU_ZERO(&cpuset);
+ CPU_SET(cpu->map[i % cpu->nr], &cpuset);
- if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+ if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
@@ -116,19 +117,22 @@ int bench_futex_requeue(int argc, const char **argv)
unsigned int i, j;
struct sigaction act;
pthread_attr_t thread_attr;
+ struct cpu_map *cpu;
argc = parse_options(argc, argv, options, bench_futex_requeue_usage, 0);
if (argc)
goto err;
- ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+ cpu = cpu_map__new(NULL);
+ if (!cpu)
+ err(EXIT_FAILURE, "cpu_map__new");
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
if (!nthreads)
- nthreads = ncpus;
+ nthreads = cpu->nr;
worker = calloc(nthreads, sizeof(*worker));
if (!worker)
@@ -156,7 +160,7 @@ 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);
/* make sure all threads are already blocked */
pthread_mutex_lock(&thread_lock);
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index b4732dad9f89..69d8fdc87315 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -7,7 +7,17 @@
* for each individual thread to service its share of work. Ultimately
* it can be used to measure futex_wake() changes.
*/
+#include "bench.h"
+#include <linux/compiler.h>
+#include "../util/debug.h"
+#ifndef HAVE_PTHREAD_BARRIER
+int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe_unused)
+{
+ pr_err("%s: pthread_barrier_t unavailable, disabling this test...\n", __func__);
+ return 0;
+}
+#else /* HAVE_PTHREAD_BARRIER */
/* For the CLR_() macros */
#include <string.h>
#include <pthread.h>
@@ -15,12 +25,11 @@
#include <signal.h>
#include "../util/stat.h"
#include <subcmd/parse-options.h>
-#include <linux/compiler.h>
#include <linux/kernel.h>
#include <linux/time64.h>
#include <errno.h>
-#include "bench.h"
#include "futex.h"
+#include "cpumap.h"
#include <err.h>
#include <stdlib.h>
@@ -42,8 +51,9 @@ static bool done = false, silent = false, fshared = false;
static unsigned int nblocked_threads = 0, nwaking_threads = 0;
static pthread_mutex_t thread_lock;
static pthread_cond_t thread_parent, thread_worker;
+static pthread_barrier_t barrier;
static struct stats waketime_stats, wakeup_stats;
-static unsigned int ncpus, threads_starting;
+static unsigned int threads_starting;
static int futex_flag = 0;
static const struct option options[] = {
@@ -64,6 +74,8 @@ static void *waking_workerfn(void *arg)
struct thread_data *waker = (struct thread_data *) arg;
struct timeval start, end;
+ pthread_barrier_wait(&barrier);
+
gettimeofday(&start, NULL);
waker->nwoken = futex_wake(&futex, nwakes, futex_flag);
@@ -84,6 +96,8 @@ 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);
+
/* create and block all threads */
for (i = 0; i < nwaking_threads; i++) {
/*
@@ -96,9 +110,13 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr)
err(EXIT_FAILURE, "pthread_create");
}
+ pthread_barrier_wait(&barrier);
+
for (i = 0; i < nwaking_threads; i++)
if (pthread_join(td[i].worker, NULL))
err(EXIT_FAILURE, "pthread_join");
+
+ pthread_barrier_destroy(&barrier);
}
static void *blocked_workerfn(void *arg __maybe_unused)
@@ -119,19 +137,20 @@ 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,
+ struct cpu_map *cpu)
{
- cpu_set_t cpu;
+ cpu_set_t cpuset;
unsigned int i;
threads_starting = nblocked_threads;
/* create and block all threads */
for (i = 0; i < nblocked_threads; i++) {
- CPU_ZERO(&cpu);
- CPU_SET(i % ncpus, &cpu);
+ CPU_ZERO(&cpuset);
+ CPU_SET(cpu->map[i % cpu->nr], &cpuset);
- if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+ if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL))
@@ -205,6 +224,7 @@ int bench_futex_wake_parallel(int argc, const char **argv)
struct sigaction act;
pthread_attr_t thread_attr;
struct thread_data *waking_worker;
+ struct cpu_map *cpu;
argc = parse_options(argc, argv, options,
bench_futex_wake_parallel_usage, 0);
@@ -217,9 +237,12 @@ int bench_futex_wake_parallel(int argc, const char **argv)
act.sa_sigaction = toggle_done;
sigaction(SIGINT, &act, NULL);
- ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+ cpu = cpu_map__new(NULL);
+ if (!cpu)
+ err(EXIT_FAILURE, "calloc");
+
if (!nblocked_threads)
- nblocked_threads = ncpus;
+ nblocked_threads = cpu->nr;
/* some sanity checks */
if (nwaking_threads > nblocked_threads || !nwaking_threads)
@@ -259,7 +282,7 @@ 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);
/* make sure all threads are already blocked */
pthread_mutex_lock(&thread_lock);
@@ -297,3 +320,4 @@ int bench_futex_wake_parallel(int argc, const char **argv)
free(blocked_worker);
return ret;
}
+#endif /* HAVE_PTHREAD_BARRIER */
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 8c5c0b6b5c97..e8181ad7d088 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 "cpumap.h"
#include <err.h>
#include <stdlib.h>
@@ -89,19 +90,19 @@ static void print_summary(void)
}
static void block_threads(pthread_t *w,
- pthread_attr_t thread_attr)
+ pthread_attr_t thread_attr, struct cpu_map *cpu)
{
- cpu_set_t cpu;
+ cpu_set_t cpuset;
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);
+ CPU_ZERO(&cpuset);
+ CPU_SET(cpu->map[i % cpu->nr], &cpuset);
- if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpu))
+ if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
@@ -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;
+ struct cpu_map *cpu;
argc = parse_options(argc, argv, options, bench_futex_wake_usage, 0);
if (argc) {
@@ -129,7 +131,9 @@ int bench_futex_wake(int argc, const char **argv)
exit(EXIT_FAILURE);
}
- ncpus = sysconf(_SC_NPROCESSORS_ONLN);
+ cpu = cpu_map__new(NULL);
+ if (!cpu)
+ err(EXIT_FAILURE, "calloc");
sigfillset(&act.sa_mask);
act.sa_sigaction = toggle_done;
@@ -161,7 +165,7 @@ 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);
/* make sure all threads are already blocked */
pthread_mutex_lock(&thread_lock);
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index d95fdcc26f4b..944070e98a2c 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -216,6 +216,47 @@ static const char * const numa_usage[] = {
NULL
};
+/*
+ * To get number of numa nodes present.
+ */
+static int nr_numa_nodes(void)
+{
+ int i, nr_nodes = 0;
+
+ for (i = 0; i < g->p.nr_nodes; i++) {
+ if (numa_bitmask_isbitset(numa_nodes_ptr, i))
+ nr_nodes++;
+ }
+
+ return nr_nodes;
+}
+
+/*
+ * To check if given numa node is present.
+ */
+static int is_node_present(int node)
+{
+ return numa_bitmask_isbitset(numa_nodes_ptr, node);
+}
+
+/*
+ * To check given numa node has cpus.
+ */
+static bool node_has_cpus(int node)
+{
+ struct bitmask *cpu = numa_allocate_cpumask();
+ unsigned int i;
+
+ if (cpu && !numa_node_to_cpus(node, cpu)) {
+ for (i = 0; i < cpu->size; i++) {
+ if (numa_bitmask_isbitset(cpu, i))
+ return true;
+ }
+ }
+
+ return false; /* lets fall back to nocpus safely */
+}
+
static cpu_set_t bind_to_cpu(int target_cpu)
{
cpu_set_t orig_mask, mask;
@@ -244,12 +285,12 @@ static cpu_set_t bind_to_cpu(int target_cpu)
static cpu_set_t bind_to_node(int target_node)
{
- int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes;
+ int cpus_per_node = g->p.nr_cpus / nr_numa_nodes();
cpu_set_t orig_mask, mask;
int cpu;
int ret;
- BUG_ON(cpus_per_node*g->p.nr_nodes != g->p.nr_cpus);
+ BUG_ON(cpus_per_node * nr_numa_nodes() != g->p.nr_cpus);
BUG_ON(!cpus_per_node);
ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
@@ -649,7 +690,7 @@ static int parse_setup_node_list(void)
int i;
for (i = 0; i < mul; i++) {
- if (t >= g->p.nr_tasks) {
+ if (t >= g->p.nr_tasks || !node_has_cpus(bind_node)) {
printf("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n", bind_node);
goto out;
}
@@ -964,6 +1005,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
sum = 0;
for (node = 0; node < g->p.nr_nodes; node++) {
+ if (!is_node_present(node))
+ continue;
nr = nodes[node];
nr_min = min(nr, nr_min);
nr_max = max(nr, nr_max);
@@ -984,8 +1027,11 @@ static void calc_convergence(double runtime_ns_max, double *convergence)
process_groups = 0;
for (node = 0; node < g->p.nr_nodes; node++) {
- int processes = count_node_processes(node);
+ int processes;
+ if (!is_node_present(node))
+ continue;
+ processes = count_node_processes(node);
nr = nodes[node];
tprintf(" %2d/%-2d", nr, processes);
@@ -1291,7 +1337,7 @@ static void print_summary(void)
printf("\n ###\n");
printf(" # %d %s will execute (on %d nodes, %d CPUs):\n",
- g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", g->p.nr_nodes, g->p.nr_cpus);
+ g->p.nr_tasks, g->p.nr_tasks == 1 ? "task" : "tasks", nr_numa_nodes(), g->p.nr_cpus);
printf(" # %5dx %5ldMB global shared mem operations\n",
g->p.nr_loops, g->p.bytes_global/1024/1024);
printf(" # %5dx %5ldMB process shared mem operations\n",
Powered by cgit, Gruvboxed by Blaster4385.