perf evlist: Maintain evlist->all_cpus
Maintain a cpumap in the evlist that is the union of all the cpus of the events. This needs a cpumap merge operation, which is added together with tests. v2: Add tests for cpu map merge Fix handling of duplicates Rename _update to _merge Factor out sorting. Fix handling of NULL maps in merge v3: Add comments and empty lines to _merge Committer testing: # perf test "Merge cpu map" 52: Merge cpu map : Ok # Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: http://lore.kernel.org/lkml/20191121001522.180827-5-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
parent
7074674e73
commit
a2408a7036
|
@ -286,3 +286,60 @@ int perf_cpu_map__max(struct perf_cpu_map *map)
|
|||
|
||||
return max;
|
||||
}
|
||||
|
||||
/*
|
||||
* Merge two cpumaps
|
||||
*
|
||||
* orig either gets freed and replaced with a new map, or reused
|
||||
* with no reference count change (similar to "realloc")
|
||||
* other has its reference count increased.
|
||||
*/
|
||||
|
||||
struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
|
||||
struct perf_cpu_map *other)
|
||||
{
|
||||
int *tmp_cpus;
|
||||
int tmp_len;
|
||||
int i, j, k;
|
||||
struct perf_cpu_map *merged;
|
||||
|
||||
if (!orig && !other)
|
||||
return NULL;
|
||||
if (!orig) {
|
||||
perf_cpu_map__get(other);
|
||||
return other;
|
||||
}
|
||||
if (!other)
|
||||
return orig;
|
||||
if (orig->nr == other->nr &&
|
||||
!memcmp(orig->map, other->map, orig->nr * sizeof(int)))
|
||||
return orig;
|
||||
|
||||
tmp_len = orig->nr + other->nr;
|
||||
tmp_cpus = malloc(tmp_len * sizeof(int));
|
||||
if (!tmp_cpus)
|
||||
return NULL;
|
||||
|
||||
/* Standard merge algorithm from wikipedia */
|
||||
i = j = k = 0;
|
||||
while (i < orig->nr && j < other->nr) {
|
||||
if (orig->map[i] <= other->map[j]) {
|
||||
if (orig->map[i] == other->map[j])
|
||||
j++;
|
||||
tmp_cpus[k++] = orig->map[i++];
|
||||
} else
|
||||
tmp_cpus[k++] = other->map[j++];
|
||||
}
|
||||
|
||||
while (i < orig->nr)
|
||||
tmp_cpus[k++] = orig->map[i++];
|
||||
|
||||
while (j < other->nr)
|
||||
tmp_cpus[k++] = other->map[j++];
|
||||
assert(k <= tmp_len);
|
||||
|
||||
merged = cpu_map__trim_new(k, tmp_cpus);
|
||||
free(tmp_cpus);
|
||||
perf_cpu_map__put(orig);
|
||||
return merged;
|
||||
}
|
||||
|
|
|
@ -54,6 +54,7 @@ static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
|
|||
|
||||
perf_thread_map__put(evsel->threads);
|
||||
evsel->threads = perf_thread_map__get(evlist->threads);
|
||||
evlist->all_cpus = perf_cpu_map__merge(evlist->all_cpus, evsel->cpus);
|
||||
}
|
||||
|
||||
static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
|
||||
|
|
|
@ -18,6 +18,7 @@ struct perf_evlist {
|
|||
int nr_entries;
|
||||
bool has_user_cpus;
|
||||
struct perf_cpu_map *cpus;
|
||||
struct perf_cpu_map *all_cpus;
|
||||
struct perf_thread_map *threads;
|
||||
int nr_mmaps;
|
||||
size_t mmap_len;
|
||||
|
|
|
@ -12,6 +12,8 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
|
|||
LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
|
||||
LIBPERF_API struct perf_cpu_map *perf_cpu_map__read(FILE *file);
|
||||
LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
|
||||
LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
|
||||
struct perf_cpu_map *other);
|
||||
LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
|
||||
LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
|
||||
LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
|
||||
|
|
|
@ -259,6 +259,11 @@ static struct test generic_tests[] = {
|
|||
.desc = "Print cpu map",
|
||||
.func = test__cpu_map_print,
|
||||
},
|
||||
{
|
||||
.desc = "Merge cpu map",
|
||||
.func = test__cpu_map_merge,
|
||||
},
|
||||
|
||||
{
|
||||
.desc = "Probe SDT events",
|
||||
.func = test__sdt_event,
|
||||
|
|
|
@ -120,3 +120,19 @@ int test__cpu_map_print(struct test *test __maybe_unused, int subtest __maybe_un
|
|||
TEST_ASSERT_VAL("failed to convert map", cpu_map_print("1-10,12-20,22-30,32-40"));
|
||||
return 0;
|
||||
}
|
||||
|
||||
int test__cpu_map_merge(struct test *test __maybe_unused, int subtest __maybe_unused)
|
||||
{
|
||||
struct perf_cpu_map *a = perf_cpu_map__new("4,2,1");
|
||||
struct perf_cpu_map *b = perf_cpu_map__new("4,5,7");
|
||||
struct perf_cpu_map *c = perf_cpu_map__merge(a, b);
|
||||
char buf[100];
|
||||
|
||||
TEST_ASSERT_VAL("failed to merge map: bad nr", c->nr == 5);
|
||||
cpu_map__snprint(c, buf, sizeof(buf));
|
||||
TEST_ASSERT_VAL("failed to merge map: bad result", !strcmp(buf, "1-2,4-5,7"));
|
||||
perf_cpu_map__put(a);
|
||||
perf_cpu_map__put(b);
|
||||
perf_cpu_map__put(c);
|
||||
return 0;
|
||||
}
|
||||
|
|
|
@ -98,6 +98,7 @@ int test__event_update(struct test *test, int subtest);
|
|||
int test__event_times(struct test *test, int subtest);
|
||||
int test__backward_ring_buffer(struct test *test, int subtest);
|
||||
int test__cpu_map_print(struct test *test, int subtest);
|
||||
int test__cpu_map_merge(struct test *test, int subtest);
|
||||
int test__sdt_event(struct test *test, int subtest);
|
||||
int test__is_printable_array(struct test *test, int subtest);
|
||||
int test__bitmap_print(struct test *test, int subtest);
|
||||
|
|
Loading…
Reference in a new issue