diff options
| author | Davidlohr Bueso <dave@stgolabs.net> | 2017-11-26 20:20:59 -0800 |
|---|---|---|
| committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2017-11-30 14:02:05 -0300 |
| commit | 3b2323c2c1c4acf8961cfcdddcee9889daaa21e3 (patch) | |
| tree | a366e8b5137d89f10885ff7d0e6ade8ed0cbf047 /tools/perf/bench/futex-wake-parallel.c | |
| parent | 17a68b835921c4664929376447cae5e3374ce2a7 (diff) | |
perf bench futex: Use cpumaps
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>
Diffstat (limited to 'tools/perf/bench/futex-wake-parallel.c')
| -rw-r--r-- | tools/perf/bench/futex-wake-parallel.c | 24 |
1 files changed, 15 insertions, 9 deletions
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index b4732dad9f89..4488c27e8a43 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 "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); |