diff options
Diffstat (limited to 'tools/perf/bench')
-rw-r--r-- | tools/perf/bench/Build | 1 | ||||
-rw-r--r-- | tools/perf/bench/evlist-open-close.c | 76 | ||||
-rw-r--r-- | tools/perf/bench/futex-hash.c | 5 | ||||
-rw-r--r-- | tools/perf/bench/futex-lock-pi.c | 4 | ||||
-rw-r--r-- | tools/perf/bench/futex-requeue.c | 5 | ||||
-rw-r--r-- | tools/perf/bench/futex-wake-parallel.c | 8 | ||||
-rw-r--r-- | tools/perf/bench/futex-wake.c | 3 | ||||
-rw-r--r-- | tools/perf/bench/futex.c | 63 | ||||
-rw-r--r-- | tools/perf/bench/futex.h | 4 | ||||
-rw-r--r-- | tools/perf/bench/inject-buildid.c | 2 | ||||
-rw-r--r-- | tools/perf/bench/synthesize.c | 27 |
11 files changed, 155 insertions, 43 deletions
diff --git a/tools/perf/bench/Build b/tools/perf/bench/Build index 279ab2ab4abe..b558ab98719f 100644 --- a/tools/perf/bench/Build +++ b/tools/perf/bench/Build @@ -3,6 +3,7 @@ perf-bench-y += sched-pipe.o perf-bench-y += sched-seccomp-notify.o perf-bench-y += syscall.o perf-bench-y += mem-functions.o +perf-bench-y += futex.o perf-bench-y += futex-hash.o perf-bench-y += futex-wake.o perf-bench-y += futex-wake-parallel.o diff --git a/tools/perf/bench/evlist-open-close.c b/tools/perf/bench/evlist-open-close.c index 5a27691469ed..bfaf50e4e519 100644 --- a/tools/perf/bench/evlist-open-close.c +++ b/tools/perf/bench/evlist-open-close.c @@ -46,25 +46,6 @@ static struct record_opts opts = { .ctl_fd_ack = -1, }; -static const struct option options[] = { - OPT_STRING('e', "event", &event_string, "event", "event selector. use 'perf list' to list available events"), - OPT_INTEGER('n', "nr-events", &nr_events, - "number of dummy events to create (default 1). If used with -e, it clones those events n times (1 = no change)"), - OPT_INTEGER('i', "iterations", &iterations, "Number of iterations used to compute average (default=100)"), - OPT_BOOLEAN('a', "all-cpus", &opts.target.system_wide, "system-wide collection from all CPUs"), - OPT_STRING('C', "cpu", &opts.target.cpu_list, "cpu", "list of cpus where to open events"), - OPT_STRING('p', "pid", &opts.target.pid, "pid", "record events on existing process id"), - OPT_STRING('t', "tid", &opts.target.tid, "tid", "record events on existing thread id"), - OPT_STRING('u', "uid", &opts.target.uid_str, "user", "user to profile"), - OPT_BOOLEAN(0, "per-thread", &opts.target.per_thread, "use per-thread mmaps"), - OPT_END() -}; - -static const char *const bench_usage[] = { - "perf bench internals evlist-open-close <options>", - NULL -}; - static int evlist__count_evsel_fds(struct evlist *evlist) { struct evsel *evsel; @@ -76,7 +57,7 @@ static int evlist__count_evsel_fds(struct evlist *evlist) return cnt; } -static struct evlist *bench__create_evlist(char *evstr) +static struct evlist *bench__create_evlist(char *evstr, const char *uid_str) { struct parse_events_error err; struct evlist *evlist = evlist__new(); @@ -97,6 +78,18 @@ static struct evlist *bench__create_evlist(char *evstr) goto out_delete_evlist; } parse_events_error__exit(&err); + if (uid_str) { + uid_t uid = parse_uid(uid_str); + + if (uid == UINT_MAX) { + pr_err("Invalid User: %s", uid_str); + ret = -EINVAL; + goto out_delete_evlist; + } + ret = parse_uid_filter(evlist, uid); + if (ret) + goto out_delete_evlist; + } ret = evlist__create_maps(evlist, &opts.target); if (ret < 0) { pr_err("Not enough memory to create thread/cpu maps\n"); @@ -136,10 +129,10 @@ static int bench__do_evlist_open_close(struct evlist *evlist) return 0; } -static int bench_evlist_open_close__run(char *evstr) +static int bench_evlist_open_close__run(char *evstr, const char *uid_str) { // used to print statistics only - struct evlist *evlist = bench__create_evlist(evstr); + struct evlist *evlist = bench__create_evlist(evstr, uid_str); double time_average, time_stddev; struct timeval start, end, diff; struct stats time_stats; @@ -161,7 +154,7 @@ static int bench_evlist_open_close__run(char *evstr) for (i = 0; i < iterations; i++) { pr_debug("Started iteration %d\n", i); - evlist = bench__create_evlist(evstr); + evlist = bench__create_evlist(evstr, uid_str); if (!evlist) return -ENOMEM; @@ -225,6 +218,30 @@ out_error: int bench_evlist_open_close(int argc, const char **argv) { + const char *uid_str = NULL; + const struct option options[] = { + OPT_STRING('e', "event", &event_string, "event", + "event selector. use 'perf list' to list available events"), + OPT_INTEGER('n', "nr-events", &nr_events, + "number of dummy events to create (default 1). If used with -e, it clones those events n times (1 = no change)"), + OPT_INTEGER('i', "iterations", &iterations, + "Number of iterations used to compute average (default=100)"), + OPT_BOOLEAN('a', "all-cpus", &opts.target.system_wide, + "system-wide collection from all CPUs"), + OPT_STRING('C', "cpu", &opts.target.cpu_list, "cpu", + "list of cpus where to open events"), + OPT_STRING('p', "pid", &opts.target.pid, "pid", + "record events on existing process id"), + OPT_STRING('t', "tid", &opts.target.tid, "tid", + "record events on existing thread id"), + OPT_STRING('u', "uid", &uid_str, "user", "user to profile"), + OPT_BOOLEAN(0, "per-thread", &opts.target.per_thread, "use per-thread mmaps"), + OPT_END() + }; + const char *const bench_usage[] = { + "perf bench internals evlist-open-close <options>", + NULL + }; char *evstr, errbuf[BUFSIZ]; int err; @@ -241,15 +258,8 @@ int bench_evlist_open_close(int argc, const char **argv) goto out; } - err = target__parse_uid(&opts.target); - if (err) { - target__strerror(&opts.target, err, errbuf, sizeof(errbuf)); - pr_err("%s", errbuf); - goto out; - } - - /* Enable ignoring missing threads when -u/-p option is defined. */ - opts.ignore_missing_thread = opts.target.uid != UINT_MAX || opts.target.pid; + /* Enable ignoring missing threads when -p option is defined. */ + opts.ignore_missing_thread = opts.target.pid; evstr = bench__repeat_event_string(event_string, nr_events); if (!evstr) { @@ -257,7 +267,7 @@ int bench_evlist_open_close(int argc, const char **argv) goto out; } - err = bench_evlist_open_close__run(evstr); + err = bench_evlist_open_close__run(evstr, uid_str); free(evstr); out: diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index b472eded521b..7e29f04da744 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -21,6 +21,7 @@ #include <linux/zalloc.h> #include <sys/time.h> #include <sys/mman.h> +#include <sys/prctl.h> #include <perf/cpumap.h> #include "../util/mutex.h" @@ -50,9 +51,11 @@ struct worker { static struct bench_futex_parameters params = { .nfutexes = 1024, .runtime = 10, + .nbuckets = -1, }; static const struct option options[] = { + OPT_INTEGER( 'b', "buckets", ¶ms.nbuckets, "Specify amount of hash buckets"), OPT_UINTEGER('t', "threads", ¶ms.nthreads, "Specify amount of threads"), OPT_UINTEGER('r', "runtime", ¶ms.runtime, "Specify runtime (in seconds)"), OPT_UINTEGER('f', "futexes", ¶ms.nfutexes, "Specify amount of futexes per threads"), @@ -118,6 +121,7 @@ static void print_summary(void) printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", !params.silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg), (int)bench__runtime.tv_sec); + futex_print_nbuckets(¶ms); } int bench_futex_hash(int argc, const char **argv) @@ -161,6 +165,7 @@ int bench_futex_hash(int argc, const char **argv) if (!params.fshared) futex_flag = FUTEX_PRIVATE_FLAG; + futex_set_nbuckets_param(¶ms); printf("Run summary [PID %d]: %d threads, each operating on %d [%s] futexes for %d secs.\n\n", getpid(), params.nthreads, params.nfutexes, params.fshared ? "shared":"private", params.runtime); diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 0416120c091b..40640b674427 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -41,10 +41,12 @@ static struct stats throughput_stats; static struct cond thread_parent, thread_worker; static struct bench_futex_parameters params = { + .nbuckets = -1, .runtime = 10, }; static const struct option options[] = { + OPT_INTEGER( 'b', "buckets", ¶ms.nbuckets, "Specify amount of hash buckets"), OPT_UINTEGER('t', "threads", ¶ms.nthreads, "Specify amount of threads"), OPT_UINTEGER('r', "runtime", ¶ms.runtime, "Specify runtime (in seconds)"), OPT_BOOLEAN( 'M', "multi", ¶ms.multi, "Use multiple futexes"), @@ -67,6 +69,7 @@ static void print_summary(void) printf("%sAveraged %ld operations/sec (+- %.2f%%), total secs = %d\n", !params.silent ? "\n" : "", avg, rel_stddev_stats(stddev, avg), (int)bench__runtime.tv_sec); + futex_print_nbuckets(¶ms); } static void toggle_done(int sig __maybe_unused, @@ -203,6 +206,7 @@ int bench_futex_lock_pi(int argc, const char **argv) mutex_init(&thread_lock); cond_init(&thread_parent); cond_init(&thread_worker); + futex_set_nbuckets_param(¶ms); threads_starting = params.nthreads; gettimeofday(&bench__start, NULL); diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index aad5bfc4fe18..0748b0fd689e 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -42,6 +42,7 @@ static unsigned int threads_starting; static int futex_flag = 0; static struct bench_futex_parameters params = { + .nbuckets = -1, /* * How many tasks to requeue at a time. * Default to 1 in order to make the kernel work more. @@ -50,6 +51,7 @@ static struct bench_futex_parameters params = { }; static const struct option options[] = { + OPT_INTEGER( 'b', "buckets", ¶ms.nbuckets, "Specify amount of hash buckets"), OPT_UINTEGER('t', "threads", ¶ms.nthreads, "Specify amount of threads"), OPT_UINTEGER('q', "nrequeue", ¶ms.nrequeue, "Specify amount of threads to requeue at once"), OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"), @@ -77,6 +79,7 @@ static void print_summary(void) params.nthreads, requeuetime_avg / USEC_PER_MSEC, rel_stddev_stats(requeuetime_stddev, requeuetime_avg)); + futex_print_nbuckets(¶ms); } static void *workerfn(void *arg __maybe_unused) @@ -204,6 +207,8 @@ int bench_futex_requeue(int argc, const char **argv) if (params.broadcast) params.nrequeue = params.nthreads; + futex_set_nbuckets_param(¶ms); + printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %s%p), " "%d at a time.\n\n", getpid(), params.nthreads, params.fshared ? "shared":"private", &futex1, diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 4352e318631e..6aede7c46b33 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -57,9 +57,12 @@ static struct stats waketime_stats, wakeup_stats; static unsigned int threads_starting; static int futex_flag = 0; -static struct bench_futex_parameters params; +static struct bench_futex_parameters params = { + .nbuckets = -1, +}; static const struct option options[] = { + OPT_INTEGER( 'b', "buckets", ¶ms.nbuckets, "Specify amount of hash buckets"), OPT_UINTEGER('t', "threads", ¶ms.nthreads, "Specify amount of threads"), OPT_UINTEGER('w', "nwakers", ¶ms.nwakes, "Specify amount of waking threads"), OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"), @@ -218,6 +221,7 @@ static void print_summary(void) params.nthreads, waketime_avg / USEC_PER_MSEC, rel_stddev_stats(waketime_stddev, waketime_avg)); + futex_print_nbuckets(¶ms); } @@ -291,6 +295,8 @@ int bench_futex_wake_parallel(int argc, const char **argv) if (!params.fshared) futex_flag = FUTEX_PRIVATE_FLAG; + futex_set_nbuckets_param(¶ms); + printf("Run summary [PID %d]: blocking on %d threads (at [%s] " "futex %p), %d threads waking up %d at a time.\n\n", getpid(), params.nthreads, params.fshared ? "shared":"private", diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index 49b3c89b0b35..a31fc1563862 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -42,6 +42,7 @@ static unsigned int threads_starting; static int futex_flag = 0; static struct bench_futex_parameters params = { + .nbuckets = -1, /* * How many wakeups to do at a time. * Default to 1 in order to make the kernel work more. @@ -50,6 +51,7 @@ static struct bench_futex_parameters params = { }; static const struct option options[] = { + OPT_INTEGER( 'b', "buckets", ¶ms.nbuckets, "Specify amount of hash buckets"), OPT_UINTEGER('t', "threads", ¶ms.nthreads, "Specify amount of threads"), OPT_UINTEGER('w', "nwakes", ¶ms.nwakes, "Specify amount of threads to wake at once"), OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"), @@ -93,6 +95,7 @@ static void print_summary(void) params.nthreads, waketime_avg / USEC_PER_MSEC, rel_stddev_stats(waketime_stddev, waketime_avg)); + futex_print_nbuckets(¶ms); } static void block_threads(pthread_t *w, struct perf_cpu_map *cpu) diff --git a/tools/perf/bench/futex.c b/tools/perf/bench/futex.c new file mode 100644 index 000000000000..1481196a22f0 --- /dev/null +++ b/tools/perf/bench/futex.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <err.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/prctl.h> + +#include "futex.h" + +#ifndef PR_FUTEX_HASH +#define PR_FUTEX_HASH 78 +# define PR_FUTEX_HASH_SET_SLOTS 1 +# define PR_FUTEX_HASH_GET_SLOTS 2 +#endif // PR_FUTEX_HASH + +void futex_set_nbuckets_param(struct bench_futex_parameters *params) +{ + int ret; + + if (params->nbuckets < 0) + return; + + ret = prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_SET_SLOTS, params->nbuckets, 0); + if (ret) { + printf("Requesting %d hash buckets failed: %d/%m\n", + params->nbuckets, ret); + err(EXIT_FAILURE, "prctl(PR_FUTEX_HASH)"); + } +} + +void futex_print_nbuckets(struct bench_futex_parameters *params) +{ + char *futex_hash_mode; + int ret; + + ret = prctl(PR_FUTEX_HASH, PR_FUTEX_HASH_GET_SLOTS); + if (params->nbuckets >= 0) { + if (ret != params->nbuckets) { + if (ret < 0) { + printf("Can't query number of buckets: %m\n"); + err(EXIT_FAILURE, "prctl(PR_FUTEX_HASH)"); + } + printf("Requested number of hash buckets does not currently used.\n"); + printf("Requested: %d in usage: %d\n", params->nbuckets, ret); + err(EXIT_FAILURE, "prctl(PR_FUTEX_HASH)"); + } + if (params->nbuckets == 0) + ret = asprintf(&futex_hash_mode, "Futex hashing: global hash"); + else + ret = asprintf(&futex_hash_mode, "Futex hashing: %d hash buckets", + params->nbuckets); + } else { + if (ret <= 0) { + ret = asprintf(&futex_hash_mode, "Futex hashing: global hash"); + } else { + ret = asprintf(&futex_hash_mode, "Futex hashing: auto resized to %d buckets", + ret); + } + } + if (ret < 0) + err(EXIT_FAILURE, "ENOMEM, futex_hash_mode"); + printf("%s\n", futex_hash_mode); + free(futex_hash_mode); +} diff --git a/tools/perf/bench/futex.h b/tools/perf/bench/futex.h index ebdc2b032afc..dd295d27044a 100644 --- a/tools/perf/bench/futex.h +++ b/tools/perf/bench/futex.h @@ -25,6 +25,7 @@ struct bench_futex_parameters { unsigned int nfutexes; unsigned int nwakes; unsigned int nrequeue; + int nbuckets; }; /** @@ -143,4 +144,7 @@ futex_cmp_requeue_pi(u_int32_t *uaddr, u_int32_t val, u_int32_t *uaddr2, val, opflags); } +void futex_set_nbuckets_param(struct bench_futex_parameters *params); +void futex_print_nbuckets(struct bench_futex_parameters *params); + #endif /* _FUTEX_H */ diff --git a/tools/perf/bench/inject-buildid.c b/tools/perf/bench/inject-buildid.c index f55c07e4be94..aad572a78d7f 100644 --- a/tools/perf/bench/inject-buildid.c +++ b/tools/perf/bench/inject-buildid.c @@ -80,7 +80,7 @@ static int add_dso(const char *fpath, const struct stat *sb __maybe_unused, int typeflag, struct FTW *ftwbuf __maybe_unused) { struct bench_dso *dso = &dsos[nr_dsos]; - struct build_id bid; + struct build_id bid = { .size = 0, }; if (typeflag == FTW_D || typeflag == FTW_SL) return 0; diff --git a/tools/perf/bench/synthesize.c b/tools/perf/bench/synthesize.c index 9b333276cbdb..b3d493697675 100644 --- a/tools/perf/bench/synthesize.c +++ b/tools/perf/bench/synthesize.c @@ -114,12 +114,16 @@ static int run_single_threaded(void) .pid = "self", }; struct perf_thread_map *threads; + struct perf_env host_env; int err; perf_set_singlethreaded(); - session = perf_session__new(NULL, NULL); + perf_env__init(&host_env); + session = __perf_session__new(/*data=*/NULL, /*tool=*/NULL, + /*trace_event_repipe=*/false, &host_env); if (IS_ERR(session)) { pr_err("Session creation failed.\n"); + perf_env__exit(&host_env); return PTR_ERR(session); } threads = thread_map__new_by_pid(getpid()); @@ -144,6 +148,7 @@ err_out: perf_thread_map__put(threads); perf_session__delete(session); + perf_env__exit(&host_env); return err; } @@ -154,17 +159,21 @@ static int do_run_multi_threaded(struct target *target, u64 runtime_us; unsigned int i; double time_average, time_stddev, event_average, event_stddev; - int err; + int err = 0; struct stats time_stats, event_stats; struct perf_session *session; + struct perf_env host_env; + perf_env__init(&host_env); init_stats(&time_stats); init_stats(&event_stats); for (i = 0; i < multi_iterations; i++) { - session = perf_session__new(NULL, NULL); - if (IS_ERR(session)) - return PTR_ERR(session); - + session = __perf_session__new(/*data=*/NULL, /*tool=*/NULL, + /*trace_event_repipe=*/false, &host_env); + if (IS_ERR(session)) { + err = PTR_ERR(session); + goto err_out; + } atomic_set(&event_count, 0); gettimeofday(&start, NULL); err = __machine__synthesize_threads(&session->machines.host, @@ -175,7 +184,7 @@ static int do_run_multi_threaded(struct target *target, nr_threads_synthesize); if (err) { perf_session__delete(session); - return err; + goto err_out; } gettimeofday(&end, NULL); @@ -198,7 +207,9 @@ static int do_run_multi_threaded(struct target *target, printf(" Average time per event %.3f usec\n", time_average / event_average); - return 0; +err_out: + perf_env__exit(&host_env); + return err; } static int run_multi_threaded(void) |