xiaomi-sm8450/android_kernel_xiaomi_sm8450
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

perf bench futex: Use cpumaps

Browse Source 
It was reported that the whole futex bench breaks when dealing with
non-contiguously numbered cpus.

$ echo 0 | sudo tee /sys/devices/system/cpu/cpu3/online
$ ./perf bench futex all
 perf: pthread_create: Operation not permitted
 Run summary [PID 14934]: 7 threads, each ....

James had implemented an approach with cpumaps that use an in house
flavor. Instead of re-inventing the wheel, I've redone the patch such
that we use the perf's util/cpumap.c interface instead.

Applies to all futex benchmarks.

Suggested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Originally-from: James Yang <james.yang@arm.com>
Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Cc: Davidlohr Bueso <dbueso@suse.de>
Cc: Kim Phillips <kim.phillips@arm.com>
Link: http://lkml.kernel.org/r/20171127042101.3659-2-dave@stgolabs.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Davidlohr Bueso
2017-11-26 20:20:59 -08:00
committed by Arnaldo Carvalho de Melo
parent 17a68b8359
commit 3b2323c2c1
5 changed files with 65 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
tools/perf/bench/futex-wake-parallel.c
View File

@@ -21,6 +21,7 @@
#include <errno.h>
#include "bench.h"
#include "futex.h"
#include "cpumap.h"
#include <err.h>
#include <stdlib.h>
@@ -43,7 +44,7 @@ static unsigned int nblocked_threads = 0, nwaking_threads = 0;
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;
static unsigned int threads_starting;
static int futex_flag = 0;
static const struct option options[] = {
@@ -119,19 +120,20 @@ 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 +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;
struct cpu_map *cpu;
argc = parse_options(argc, argv, options,
bench_futex_wake_parallel_usage, 0);
@@ -217,9 +220,12 @@ 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 +265,7 @@ 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);