mirror of
https://github.com/torvalds/linux.git
synced 2024-11-27 22:51:35 +00:00
perf tools: By default use the most precise "cycles" hw counter available
If the user doesn't specify any event, try the most precise "cycles" available, i.e. start by "cycles:ppp" and go on removing "p" till it works. E.g. $ perf record usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.017 MB perf.data (11 samples) ] $ perf evlist cycles:pp $ perf evlist -v cycles:pp: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 2, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 $ grep 'model name' /proc/cpuinfo | head -1 model name : Intel(R) Core(TM) i7-3667U CPU @ 2.00GHz $ When 'cycles' appears explicitely is specified this will not be tried, i.e. the user has full control of the level of precision to be used: $ perf record -e cycles usleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.016 MB perf.data (9 samples) ] $ perf evlist cycles $ perf evlist -v cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1 $ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: Chandler Carruth <chandlerc@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Cc: Wang Nan <wangnan0@huawei.com> Link: https://www.youtube.com/watch?v=nXaxk27zwlk Link: http://lkml.kernel.org/n/tip-b1ywebmt22pi78vjxau01wth@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
parent
dfc431cbdc
commit
7f8d1ade1b
@ -205,6 +205,20 @@ void perf_evlist__set_leader(struct perf_evlist *evlist)
|
||||
}
|
||||
}
|
||||
|
||||
static void perf_event_attr__set_max_precise_ip(struct perf_event_attr *attr)
|
||||
{
|
||||
attr->precise_ip = 3;
|
||||
|
||||
while (attr->precise_ip != 0) {
|
||||
int fd = sys_perf_event_open(attr, 0, -1, -1, 0);
|
||||
if (fd != -1) {
|
||||
close(fd);
|
||||
break;
|
||||
}
|
||||
--attr->precise_ip;
|
||||
}
|
||||
}
|
||||
|
||||
int perf_evlist__add_default(struct perf_evlist *evlist)
|
||||
{
|
||||
struct perf_event_attr attr = {
|
||||
@ -215,13 +229,15 @@ int perf_evlist__add_default(struct perf_evlist *evlist)
|
||||
|
||||
event_attr_init(&attr);
|
||||
|
||||
perf_event_attr__set_max_precise_ip(&attr);
|
||||
|
||||
evsel = perf_evsel__new(&attr);
|
||||
if (evsel == NULL)
|
||||
goto error;
|
||||
|
||||
/* use strdup() because free(evsel) assumes name is allocated */
|
||||
evsel->name = strdup("cycles");
|
||||
if (!evsel->name)
|
||||
/* use asprintf() because free(evsel) assumes name is allocated */
|
||||
if (asprintf(&evsel->name, "cycles%.*s",
|
||||
attr.precise_ip ? attr.precise_ip + 1 : 0, ":ppp") < 0)
|
||||
goto error_free;
|
||||
|
||||
perf_evlist__add(evlist, evsel);
|
||||
|
Loading…
Reference in New Issue
Block a user