OpenCloudOS-Kernel/tools/perf/bench/evlist-open-close.c

266 lines
6.6 KiB
C
Raw Normal View History

perf bench: Add benchmark for evlist open/close operations This new benchmark finds the total time that is taken to open, mmap, enable, disable, munmap, close an evlist (time taken for new, create_maps, config, delete is not counted in). The evlist can be configured as in perf-record using the -a,-C,-e,-u,--per-thread,-t,-p options. The events can be duplicated in the evlist to quickly test performance with many events using the -n options. Furthermore, also the number of iterations used to calculate the statistics is customizable. Examples: - Open one dummy event system-wide: $ sudo ./perf bench internals evlist-open-close Number of cpus: 4 Number of threads: 1 Number of events: 1 (4 fds) Number of iterations: 100 Average open-close took: 613.870 usec (+- 32.852 usec) - Open the group '{cs,cycles}' on CPU 0 $ sudo ./perf bench internals evlist-open-close -e '{cs,cycles}' -C 0 Number of cpus: 1 Number of threads: 1 Number of events: 2 (2 fds) Number of iterations: 100 Average open-close took: 8503.220 usec (+- 252.652 usec) - Open 10 'cycles' events for user 0, calculate average over 100 runs $ sudo ./perf bench internals evlist-open-close -e cycles -n 10 -u 0 -i 100 Number of cpus: 4 Number of threads: 328 Number of events: 10 (13120 fds) Number of iterations: 100 Average open-close took: 180043.140 usec (+- 2295.889 usec) Committer notes: Replaced a deprecated bzero() call with designated initialized zeroing. Added some missing evlist allocation checks, one noted by Riccardo on the mailing list. Minor cosmetic changes (sent in private). Signed-off-by: Riccardo Mancini <rickyman7@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210809201101.277594-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-08-10 04:11:02 +08:00
// SPDX-License-Identifier: GPL-2.0
#include <inttypes.h>
perf bench: Add benchmark for evlist open/close operations This new benchmark finds the total time that is taken to open, mmap, enable, disable, munmap, close an evlist (time taken for new, create_maps, config, delete is not counted in). The evlist can be configured as in perf-record using the -a,-C,-e,-u,--per-thread,-t,-p options. The events can be duplicated in the evlist to quickly test performance with many events using the -n options. Furthermore, also the number of iterations used to calculate the statistics is customizable. Examples: - Open one dummy event system-wide: $ sudo ./perf bench internals evlist-open-close Number of cpus: 4 Number of threads: 1 Number of events: 1 (4 fds) Number of iterations: 100 Average open-close took: 613.870 usec (+- 32.852 usec) - Open the group '{cs,cycles}' on CPU 0 $ sudo ./perf bench internals evlist-open-close -e '{cs,cycles}' -C 0 Number of cpus: 1 Number of threads: 1 Number of events: 2 (2 fds) Number of iterations: 100 Average open-close took: 8503.220 usec (+- 252.652 usec) - Open 10 'cycles' events for user 0, calculate average over 100 runs $ sudo ./perf bench internals evlist-open-close -e cycles -n 10 -u 0 -i 100 Number of cpus: 4 Number of threads: 328 Number of events: 10 (13120 fds) Number of iterations: 100 Average open-close took: 180043.140 usec (+- 2295.889 usec) Committer notes: Replaced a deprecated bzero() call with designated initialized zeroing. Added some missing evlist allocation checks, one noted by Riccardo on the mailing list. Minor cosmetic changes (sent in private). Signed-off-by: Riccardo Mancini <rickyman7@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210809201101.277594-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-08-10 04:11:02 +08:00
#include <stdio.h>
#include <stdlib.h>
#include <limits.h>
#include "bench.h"
#include "../util/debug.h"
#include "../util/stat.h"
#include "../util/evlist.h"
#include "../util/evsel.h"
#include "../util/strbuf.h"
#include "../util/record.h"
#include "../util/parse-events.h"
#include "internal/threadmap.h"
#include "internal/cpumap.h"
#include <linux/perf_event.h>
#include <linux/kernel.h>
#include <linux/time64.h>
#include <linux/string.h>
#include <subcmd/parse-options.h>
#define MMAP_FLUSH_DEFAULT 1
static int iterations = 100;
static int nr_events = 1;
static const char *event_string = "dummy";
static inline u64 timeval2usec(struct timeval *tv)
{
return tv->tv_sec * USEC_PER_SEC + tv->tv_usec;
}
perf bench: Add benchmark for evlist open/close operations This new benchmark finds the total time that is taken to open, mmap, enable, disable, munmap, close an evlist (time taken for new, create_maps, config, delete is not counted in). The evlist can be configured as in perf-record using the -a,-C,-e,-u,--per-thread,-t,-p options. The events can be duplicated in the evlist to quickly test performance with many events using the -n options. Furthermore, also the number of iterations used to calculate the statistics is customizable. Examples: - Open one dummy event system-wide: $ sudo ./perf bench internals evlist-open-close Number of cpus: 4 Number of threads: 1 Number of events: 1 (4 fds) Number of iterations: 100 Average open-close took: 613.870 usec (+- 32.852 usec) - Open the group '{cs,cycles}' on CPU 0 $ sudo ./perf bench internals evlist-open-close -e '{cs,cycles}' -C 0 Number of cpus: 1 Number of threads: 1 Number of events: 2 (2 fds) Number of iterations: 100 Average open-close took: 8503.220 usec (+- 252.652 usec) - Open 10 'cycles' events for user 0, calculate average over 100 runs $ sudo ./perf bench internals evlist-open-close -e cycles -n 10 -u 0 -i 100 Number of cpus: 4 Number of threads: 328 Number of events: 10 (13120 fds) Number of iterations: 100 Average open-close took: 180043.140 usec (+- 2295.889 usec) Committer notes: Replaced a deprecated bzero() call with designated initialized zeroing. Added some missing evlist allocation checks, one noted by Riccardo on the mailing list. Minor cosmetic changes (sent in private). Signed-off-by: Riccardo Mancini <rickyman7@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210809201101.277594-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-08-10 04:11:02 +08:00
static struct record_opts opts = {
.sample_time = true,
.mmap_pages = UINT_MAX,
.user_freq = UINT_MAX,
.user_interval = ULLONG_MAX,
.freq = 4000,
.target = {
.uses_mmap = true,
.default_per_cpu = true,
},
.mmap_flush = MMAP_FLUSH_DEFAULT,
.nr_threads_synthesize = 1,
.ctl_fd = -1,
.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;
int cnt = 0;
evlist__for_each_entry(evlist, evsel)
perf cpumap: Migrate to libperf cpumap api Switch from directly accessing the perf_cpu_map to using the appropriate libperf API when possible. Using the API simplifies the job of refactoring use of perf_cpu_map. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: André Almeida <andrealmeid@collabora.com> Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Dmitriy Vyukov <dvyukov@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: German Gomez <german.gomez@arm.com> Cc: James Clark <james.clark@arm.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Garry <john.garry@huawei.com> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Madhavan Srinivasan <maddy@linux.ibm.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Miaoqian Lin <linmq006@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Shunsuke Nakamura <nakamura.shun@fujitsu.com> Cc: Song Liu <song@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Stephen Brennan <stephen.s.brennan@oracle.com> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Richter <tmricht@linux.ibm.com> Cc: Yury Norov <yury.norov@gmail.com> Link: http://lore.kernel.org/lkml/20220122045811.3402706-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-01-22 12:58:10 +08:00
cnt += evsel->core.threads->nr * perf_cpu_map__nr(evsel->core.cpus);
perf bench: Add benchmark for evlist open/close operations This new benchmark finds the total time that is taken to open, mmap, enable, disable, munmap, close an evlist (time taken for new, create_maps, config, delete is not counted in). The evlist can be configured as in perf-record using the -a,-C,-e,-u,--per-thread,-t,-p options. The events can be duplicated in the evlist to quickly test performance with many events using the -n options. Furthermore, also the number of iterations used to calculate the statistics is customizable. Examples: - Open one dummy event system-wide: $ sudo ./perf bench internals evlist-open-close Number of cpus: 4 Number of threads: 1 Number of events: 1 (4 fds) Number of iterations: 100 Average open-close took: 613.870 usec (+- 32.852 usec) - Open the group '{cs,cycles}' on CPU 0 $ sudo ./perf bench internals evlist-open-close -e '{cs,cycles}' -C 0 Number of cpus: 1 Number of threads: 1 Number of events: 2 (2 fds) Number of iterations: 100 Average open-close took: 8503.220 usec (+- 252.652 usec) - Open 10 'cycles' events for user 0, calculate average over 100 runs $ sudo ./perf bench internals evlist-open-close -e cycles -n 10 -u 0 -i 100 Number of cpus: 4 Number of threads: 328 Number of events: 10 (13120 fds) Number of iterations: 100 Average open-close took: 180043.140 usec (+- 2295.889 usec) Committer notes: Replaced a deprecated bzero() call with designated initialized zeroing. Added some missing evlist allocation checks, one noted by Riccardo on the mailing list. Minor cosmetic changes (sent in private). Signed-off-by: Riccardo Mancini <rickyman7@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210809201101.277594-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-08-10 04:11:02 +08:00
return cnt;
}
static struct evlist *bench__create_evlist(char *evstr)
{
struct parse_events_error err;
perf bench: Add benchmark for evlist open/close operations This new benchmark finds the total time that is taken to open, mmap, enable, disable, munmap, close an evlist (time taken for new, create_maps, config, delete is not counted in). The evlist can be configured as in perf-record using the -a,-C,-e,-u,--per-thread,-t,-p options. The events can be duplicated in the evlist to quickly test performance with many events using the -n options. Furthermore, also the number of iterations used to calculate the statistics is customizable. Examples: - Open one dummy event system-wide: $ sudo ./perf bench internals evlist-open-close Number of cpus: 4 Number of threads: 1 Number of events: 1 (4 fds) Number of iterations: 100 Average open-close took: 613.870 usec (+- 32.852 usec) - Open the group '{cs,cycles}' on CPU 0 $ sudo ./perf bench internals evlist-open-close -e '{cs,cycles}' -C 0 Number of cpus: 1 Number of threads: 1 Number of events: 2 (2 fds) Number of iterations: 100 Average open-close took: 8503.220 usec (+- 252.652 usec) - Open 10 'cycles' events for user 0, calculate average over 100 runs $ sudo ./perf bench internals evlist-open-close -e cycles -n 10 -u 0 -i 100 Number of cpus: 4 Number of threads: 328 Number of events: 10 (13120 fds) Number of iterations: 100 Average open-close took: 180043.140 usec (+- 2295.889 usec) Committer notes: Replaced a deprecated bzero() call with designated initialized zeroing. Added some missing evlist allocation checks, one noted by Riccardo on the mailing list. Minor cosmetic changes (sent in private). Signed-off-by: Riccardo Mancini <rickyman7@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210809201101.277594-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-08-10 04:11:02 +08:00
struct evlist *evlist = evlist__new();
int ret;
if (!evlist) {
pr_err("Not enough memory to create evlist\n");
return NULL;
}
parse_events_error__init(&err);
perf bench: Add benchmark for evlist open/close operations This new benchmark finds the total time that is taken to open, mmap, enable, disable, munmap, close an evlist (time taken for new, create_maps, config, delete is not counted in). The evlist can be configured as in perf-record using the -a,-C,-e,-u,--per-thread,-t,-p options. The events can be duplicated in the evlist to quickly test performance with many events using the -n options. Furthermore, also the number of iterations used to calculate the statistics is customizable. Examples: - Open one dummy event system-wide: $ sudo ./perf bench internals evlist-open-close Number of cpus: 4 Number of threads: 1 Number of events: 1 (4 fds) Number of iterations: 100 Average open-close took: 613.870 usec (+- 32.852 usec) - Open the group '{cs,cycles}' on CPU 0 $ sudo ./perf bench internals evlist-open-close -e '{cs,cycles}' -C 0 Number of cpus: 1 Number of threads: 1 Number of events: 2 (2 fds) Number of iterations: 100 Average open-close took: 8503.220 usec (+- 252.652 usec) - Open 10 'cycles' events for user 0, calculate average over 100 runs $ sudo ./perf bench internals evlist-open-close -e cycles -n 10 -u 0 -i 100 Number of cpus: 4 Number of threads: 328 Number of events: 10 (13120 fds) Number of iterations: 100 Average open-close took: 180043.140 usec (+- 2295.889 usec) Committer notes: Replaced a deprecated bzero() call with designated initialized zeroing. Added some missing evlist allocation checks, one noted by Riccardo on the mailing list. Minor cosmetic changes (sent in private). Signed-off-by: Riccardo Mancini <rickyman7@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210809201101.277594-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-08-10 04:11:02 +08:00
ret = parse_events(evlist, evstr, &err);
if (ret) {
parse_events_error__print(&err, evstr);
parse_events_error__exit(&err);
perf bench: Add benchmark for evlist open/close operations This new benchmark finds the total time that is taken to open, mmap, enable, disable, munmap, close an evlist (time taken for new, create_maps, config, delete is not counted in). The evlist can be configured as in perf-record using the -a,-C,-e,-u,--per-thread,-t,-p options. The events can be duplicated in the evlist to quickly test performance with many events using the -n options. Furthermore, also the number of iterations used to calculate the statistics is customizable. Examples: - Open one dummy event system-wide: $ sudo ./perf bench internals evlist-open-close Number of cpus: 4 Number of threads: 1 Number of events: 1 (4 fds) Number of iterations: 100 Average open-close took: 613.870 usec (+- 32.852 usec) - Open the group '{cs,cycles}' on CPU 0 $ sudo ./perf bench internals evlist-open-close -e '{cs,cycles}' -C 0 Number of cpus: 1 Number of threads: 1 Number of events: 2 (2 fds) Number of iterations: 100 Average open-close took: 8503.220 usec (+- 252.652 usec) - Open 10 'cycles' events for user 0, calculate average over 100 runs $ sudo ./perf bench internals evlist-open-close -e cycles -n 10 -u 0 -i 100 Number of cpus: 4 Number of threads: 328 Number of events: 10 (13120 fds) Number of iterations: 100 Average open-close took: 180043.140 usec (+- 2295.889 usec) Committer notes: Replaced a deprecated bzero() call with designated initialized zeroing. Added some missing evlist allocation checks, one noted by Riccardo on the mailing list. Minor cosmetic changes (sent in private). Signed-off-by: Riccardo Mancini <rickyman7@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210809201101.277594-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-08-10 04:11:02 +08:00
pr_err("Run 'perf list' for a list of valid events\n");
ret = 1;
goto out_delete_evlist;
}
parse_events_error__exit(&err);
perf bench: Add benchmark for evlist open/close operations This new benchmark finds the total time that is taken to open, mmap, enable, disable, munmap, close an evlist (time taken for new, create_maps, config, delete is not counted in). The evlist can be configured as in perf-record using the -a,-C,-e,-u,--per-thread,-t,-p options. The events can be duplicated in the evlist to quickly test performance with many events using the -n options. Furthermore, also the number of iterations used to calculate the statistics is customizable. Examples: - Open one dummy event system-wide: $ sudo ./perf bench internals evlist-open-close Number of cpus: 4 Number of threads: 1 Number of events: 1 (4 fds) Number of iterations: 100 Average open-close took: 613.870 usec (+- 32.852 usec) - Open the group '{cs,cycles}' on CPU 0 $ sudo ./perf bench internals evlist-open-close -e '{cs,cycles}' -C 0 Number of cpus: 1 Number of threads: 1 Number of events: 2 (2 fds) Number of iterations: 100 Average open-close took: 8503.220 usec (+- 252.652 usec) - Open 10 'cycles' events for user 0, calculate average over 100 runs $ sudo ./perf bench internals evlist-open-close -e cycles -n 10 -u 0 -i 100 Number of cpus: 4 Number of threads: 328 Number of events: 10 (13120 fds) Number of iterations: 100 Average open-close took: 180043.140 usec (+- 2295.889 usec) Committer notes: Replaced a deprecated bzero() call with designated initialized zeroing. Added some missing evlist allocation checks, one noted by Riccardo on the mailing list. Minor cosmetic changes (sent in private). Signed-off-by: Riccardo Mancini <rickyman7@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210809201101.277594-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-08-10 04:11:02 +08:00
ret = evlist__create_maps(evlist, &opts.target);
if (ret < 0) {
pr_err("Not enough memory to create thread/cpu maps\n");
goto out_delete_evlist;
}
evlist__config(evlist, &opts, NULL);
return evlist;
out_delete_evlist:
evlist__delete(evlist);
return NULL;
}
static int bench__do_evlist_open_close(struct evlist *evlist)
{
char sbuf[STRERR_BUFSIZE];
int err = evlist__open(evlist);
if (err < 0) {
pr_err("evlist__open: %s\n", str_error_r(errno, sbuf, sizeof(sbuf)));
return err;
}
err = evlist__mmap(evlist, opts.mmap_pages);
if (err < 0) {
pr_err("evlist__mmap: %s\n", str_error_r(errno, sbuf, sizeof(sbuf)));
return err;
}
evlist__enable(evlist);
evlist__disable(evlist);
evlist__munmap(evlist);
evlist__close(evlist);
return 0;
}
static int bench_evlist_open_close__run(char *evstr)
{
// used to print statistics only
struct evlist *evlist = bench__create_evlist(evstr);
double time_average, time_stddev;
struct timeval start, end, diff;
struct stats time_stats;
u64 runtime_us;
int i, err;
if (!evlist)
return -ENOMEM;
init_stats(&time_stats);
perf evlist: Rename cpus to user_requested_cpus evlist contains cpus and all_cpus. all_cpus is the union of the cpu maps of all evsels. For non-task targets, cpus is set to be cpus requested from the command line, defaulting to all online cpus if no cpus are specified. For an uncore event, all_cpus may be just CPU 0 or every online CPU. This causes all_cpus to have fewer values than the cpus variable which is confusing given the 'all' in the name. To try to make the behavior clearer, rename cpus to user_requested_cpus and add comments on the two struct variables. Signed-off-by: Ian Rogers <irogers@google.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Antonov <alexander.antonov@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Alexey Bayduraev <alexey.v.bayduraev@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Andrii Nakryiko <andrii@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: German Gomez <german.gomez@arm.com> Cc: James Clark <james.clark@arm.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: John Fastabend <john.fastabend@gmail.com> Cc: John Garry <john.garry@huawei.com> Cc: KP Singh <kpsingh@kernel.org> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Riccardo Mancini <rickyman7@gmail.com> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Yonghong Song <yhs@fb.com> Cc: bpf@vger.kernel.org Cc: coresight@lists.linaro.org Cc: linux-arm-kernel@lists.infradead.org Cc: netdev@vger.kernel.org Link: http://lore.kernel.org/lkml/20220328232648.2127340-3-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2022-03-29 07:26:44 +08:00
printf(" Number of cpus:\t%d\n", perf_cpu_map__nr(evlist->core.user_requested_cpus));
perf bench: Add benchmark for evlist open/close operations This new benchmark finds the total time that is taken to open, mmap, enable, disable, munmap, close an evlist (time taken for new, create_maps, config, delete is not counted in). The evlist can be configured as in perf-record using the -a,-C,-e,-u,--per-thread,-t,-p options. The events can be duplicated in the evlist to quickly test performance with many events using the -n options. Furthermore, also the number of iterations used to calculate the statistics is customizable. Examples: - Open one dummy event system-wide: $ sudo ./perf bench internals evlist-open-close Number of cpus: 4 Number of threads: 1 Number of events: 1 (4 fds) Number of iterations: 100 Average open-close took: 613.870 usec (+- 32.852 usec) - Open the group '{cs,cycles}' on CPU 0 $ sudo ./perf bench internals evlist-open-close -e '{cs,cycles}' -C 0 Number of cpus: 1 Number of threads: 1 Number of events: 2 (2 fds) Number of iterations: 100 Average open-close took: 8503.220 usec (+- 252.652 usec) - Open 10 'cycles' events for user 0, calculate average over 100 runs $ sudo ./perf bench internals evlist-open-close -e cycles -n 10 -u 0 -i 100 Number of cpus: 4 Number of threads: 328 Number of events: 10 (13120 fds) Number of iterations: 100 Average open-close took: 180043.140 usec (+- 2295.889 usec) Committer notes: Replaced a deprecated bzero() call with designated initialized zeroing. Added some missing evlist allocation checks, one noted by Riccardo on the mailing list. Minor cosmetic changes (sent in private). Signed-off-by: Riccardo Mancini <rickyman7@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210809201101.277594-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-08-10 04:11:02 +08:00
printf(" Number of threads:\t%d\n", evlist->core.threads->nr);
printf(" Number of events:\t%d (%d fds)\n",
evlist->core.nr_entries, evlist__count_evsel_fds(evlist));
printf(" Number of iterations:\t%d\n", iterations);
evlist__delete(evlist);
for (i = 0; i < iterations; i++) {
pr_debug("Started iteration %d\n", i);
evlist = bench__create_evlist(evstr);
if (!evlist)
return -ENOMEM;
gettimeofday(&start, NULL);
err = bench__do_evlist_open_close(evlist);
if (err) {
evlist__delete(evlist);
return err;
}
gettimeofday(&end, NULL);
timersub(&end, &start, &diff);
runtime_us = timeval2usec(&diff);
perf bench: Add benchmark for evlist open/close operations This new benchmark finds the total time that is taken to open, mmap, enable, disable, munmap, close an evlist (time taken for new, create_maps, config, delete is not counted in). The evlist can be configured as in perf-record using the -a,-C,-e,-u,--per-thread,-t,-p options. The events can be duplicated in the evlist to quickly test performance with many events using the -n options. Furthermore, also the number of iterations used to calculate the statistics is customizable. Examples: - Open one dummy event system-wide: $ sudo ./perf bench internals evlist-open-close Number of cpus: 4 Number of threads: 1 Number of events: 1 (4 fds) Number of iterations: 100 Average open-close took: 613.870 usec (+- 32.852 usec) - Open the group '{cs,cycles}' on CPU 0 $ sudo ./perf bench internals evlist-open-close -e '{cs,cycles}' -C 0 Number of cpus: 1 Number of threads: 1 Number of events: 2 (2 fds) Number of iterations: 100 Average open-close took: 8503.220 usec (+- 252.652 usec) - Open 10 'cycles' events for user 0, calculate average over 100 runs $ sudo ./perf bench internals evlist-open-close -e cycles -n 10 -u 0 -i 100 Number of cpus: 4 Number of threads: 328 Number of events: 10 (13120 fds) Number of iterations: 100 Average open-close took: 180043.140 usec (+- 2295.889 usec) Committer notes: Replaced a deprecated bzero() call with designated initialized zeroing. Added some missing evlist allocation checks, one noted by Riccardo on the mailing list. Minor cosmetic changes (sent in private). Signed-off-by: Riccardo Mancini <rickyman7@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210809201101.277594-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-08-10 04:11:02 +08:00
update_stats(&time_stats, runtime_us);
evlist__delete(evlist);
pr_debug("Iteration %d took:\t%" PRIu64 "us\n", i, runtime_us);
perf bench: Add benchmark for evlist open/close operations This new benchmark finds the total time that is taken to open, mmap, enable, disable, munmap, close an evlist (time taken for new, create_maps, config, delete is not counted in). The evlist can be configured as in perf-record using the -a,-C,-e,-u,--per-thread,-t,-p options. The events can be duplicated in the evlist to quickly test performance with many events using the -n options. Furthermore, also the number of iterations used to calculate the statistics is customizable. Examples: - Open one dummy event system-wide: $ sudo ./perf bench internals evlist-open-close Number of cpus: 4 Number of threads: 1 Number of events: 1 (4 fds) Number of iterations: 100 Average open-close took: 613.870 usec (+- 32.852 usec) - Open the group '{cs,cycles}' on CPU 0 $ sudo ./perf bench internals evlist-open-close -e '{cs,cycles}' -C 0 Number of cpus: 1 Number of threads: 1 Number of events: 2 (2 fds) Number of iterations: 100 Average open-close took: 8503.220 usec (+- 252.652 usec) - Open 10 'cycles' events for user 0, calculate average over 100 runs $ sudo ./perf bench internals evlist-open-close -e cycles -n 10 -u 0 -i 100 Number of cpus: 4 Number of threads: 328 Number of events: 10 (13120 fds) Number of iterations: 100 Average open-close took: 180043.140 usec (+- 2295.889 usec) Committer notes: Replaced a deprecated bzero() call with designated initialized zeroing. Added some missing evlist allocation checks, one noted by Riccardo on the mailing list. Minor cosmetic changes (sent in private). Signed-off-by: Riccardo Mancini <rickyman7@gmail.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20210809201101.277594-1-rickyman7@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2021-08-10 04:11:02 +08:00
}
time_average = avg_stats(&time_stats);
time_stddev = stddev_stats(&time_stats);
printf(" Average open-close took: %.3f usec (+- %.3f usec)\n", time_average, time_stddev);
return 0;
}
static char *bench__repeat_event_string(const char *evstr, int n)
{
char sbuf[STRERR_BUFSIZE];
struct strbuf buf;
int i, str_size = strlen(evstr),
final_size = str_size * n + n,
err = strbuf_init(&buf, final_size);
if (err) {
pr_err("strbuf_init: %s\n", str_error_r(err, sbuf, sizeof(sbuf)));
goto out_error;
}
for (i = 0; i < n; i++) {
err = strbuf_add(&buf, evstr, str_size);
if (err) {
pr_err("strbuf_add: %s\n", str_error_r(err, sbuf, sizeof(sbuf)));
goto out_error;
}
err = strbuf_addch(&buf, i == n-1 ? '\0' : ',');
if (err) {
pr_err("strbuf_addch: %s\n", str_error_r(err, sbuf, sizeof(sbuf)));
goto out_error;
}
}
return strbuf_detach(&buf, NULL);
out_error:
strbuf_release(&buf);
return NULL;
}
int bench_evlist_open_close(int argc, const char **argv)
{
char *evstr, errbuf[BUFSIZ];
int err;
argc = parse_options(argc, argv, options, bench_usage, 0);
if (argc) {
usage_with_options(bench_usage, options);
exit(EXIT_FAILURE);
}
err = target__validate(&opts.target);
if (err) {
target__strerror(&opts.target, err, errbuf, sizeof(errbuf));
pr_err("%s\n", errbuf);
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;
evstr = bench__repeat_event_string(event_string, nr_events);
if (!evstr) {
err = -ENOMEM;
goto out;
}
err = bench_evlist_open_close__run(evstr);
free(evstr);
out:
return err;
}