9a0b36266f
Topdown metrics are missed in the default perf stat on the hybrid machine,
add Topdown metrics in default perf stat for hybrid systems.
Currently, we support the perf metrics Topdown for the p-core PMU in the
perf stat default, the perf metrics Topdown support for e-core PMU will be
implemented later separately. Refactor the code adds two x86 specific
functions. Widen the size of the event name column by 7 chars, so that all
metrics after the "#" become aligned again.
The perf metrics topdown feature is supported on the cpu_core of ADL. The
dedicated perf metrics counter and the fixed counter 3 are used for the
topdown events. Adding the topdown metrics doesn't trigger multiplexing.
Before:
# ./perf stat -a true
Performance counter stats for 'system wide':
53.70 msec cpu-clock # 25.736 CPUs utilized
80 context-switches # 1.490 K/sec
24 cpu-migrations # 446.951 /sec
52 page-faults # 968.394 /sec
2,788,555 cpu_core/cycles/ # 51.931 M/sec
851,129 cpu_atom/cycles/ # 15.851 M/sec
2,974,030 cpu_core/instructions/ # 55.385 M/sec
416,919 cpu_atom/instructions/ # 7.764 M/sec
586,136 cpu_core/branches/ # 10.916 M/sec
79,872 cpu_atom/branches/ # 1.487 M/sec
14,220 cpu_core/branch-misses/ # 264.819 K/sec
7,691 cpu_atom/branch-misses/ # 143.229 K/sec
0.002086438 seconds time elapsed
After:
# ./perf stat -a true
Performance counter stats for 'system wide':
61.39 msec cpu-clock # 24.874 CPUs utilized
76 context-switches # 1.238 K/sec
24 cpu-migrations # 390.968 /sec
52 page-faults # 847.097 /sec
2,753,695 cpu_core/cycles/ # 44.859 M/sec
903,899 cpu_atom/cycles/ # 14.725 M/sec
2,927,529 cpu_core/instructions/ # 47.690 M/sec
428,498 cpu_atom/instructions/ # 6.980 M/sec
581,299 cpu_core/branches/ # 9.470 M/sec
83,409 cpu_atom/branches/ # 1.359 M/sec
13,641 cpu_core/branch-misses/ # 222.216 K/sec
8,008 cpu_atom/branch-misses/ # 130.453 K/sec
14,761,308 cpu_core/slots/ # 240.466 M/sec
3,288,625 cpu_core/topdown-retiring/ # 22.3% retiring
1,323,323 cpu_core/topdown-bad-spec/ # 9.0% bad speculation
5,477,470 cpu_core/topdown-fe-bound/ # 37.1% frontend bound
4,679,199 cpu_core/topdown-be-bound/ # 31.7% backend bound
646,194 cpu_core/topdown-heavy-ops/ # 4.4% heavy operations # 17.9% light operations
1,244,999 cpu_core/topdown-br-mispredict/ # 8.4% branch mispredict # 0.5% machine clears
3,891,800 cpu_core/topdown-fetch-lat/ # 26.4% fetch latency # 10.7% fetch bandwidth
1,879,034 cpu_core/topdown-mem-bound/ # 12.7% memory bound # 19.0% Core bound
0.002467839 seconds time elapsed
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Acked-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220721065706.2886112-6-zhengjun.xing@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
93 lines
2.3 KiB
C
93 lines
2.3 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <stdio.h>
|
|
#include "util/pmu.h"
|
|
#include "util/evlist.h"
|
|
#include "util/parse-events.h"
|
|
#include "util/event.h"
|
|
#include "util/pmu-hybrid.h"
|
|
#include "topdown.h"
|
|
|
|
static int ___evlist__add_default_attrs(struct evlist *evlist,
|
|
struct perf_event_attr *attrs,
|
|
size_t nr_attrs)
|
|
{
|
|
struct perf_cpu_map *cpus;
|
|
struct evsel *evsel, *n;
|
|
struct perf_pmu *pmu;
|
|
LIST_HEAD(head);
|
|
size_t i = 0;
|
|
|
|
for (i = 0; i < nr_attrs; i++)
|
|
event_attr_init(attrs + i);
|
|
|
|
if (!perf_pmu__has_hybrid())
|
|
return evlist__add_attrs(evlist, attrs, nr_attrs);
|
|
|
|
for (i = 0; i < nr_attrs; i++) {
|
|
if (attrs[i].type == PERF_TYPE_SOFTWARE) {
|
|
evsel = evsel__new(attrs + i);
|
|
if (evsel == NULL)
|
|
goto out_delete_partial_list;
|
|
list_add_tail(&evsel->core.node, &head);
|
|
continue;
|
|
}
|
|
|
|
perf_pmu__for_each_hybrid_pmu(pmu) {
|
|
evsel = evsel__new(attrs + i);
|
|
if (evsel == NULL)
|
|
goto out_delete_partial_list;
|
|
evsel->core.attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
|
|
cpus = perf_cpu_map__get(pmu->cpus);
|
|
evsel->core.cpus = cpus;
|
|
evsel->core.own_cpus = perf_cpu_map__get(cpus);
|
|
evsel->pmu_name = strdup(pmu->name);
|
|
list_add_tail(&evsel->core.node, &head);
|
|
}
|
|
}
|
|
|
|
evlist__splice_list_tail(evlist, &head);
|
|
|
|
return 0;
|
|
|
|
out_delete_partial_list:
|
|
__evlist__for_each_entry_safe(&head, n, evsel)
|
|
evsel__delete(evsel);
|
|
return -1;
|
|
}
|
|
|
|
int arch_evlist__add_default_attrs(struct evlist *evlist,
|
|
struct perf_event_attr *attrs,
|
|
size_t nr_attrs)
|
|
{
|
|
if (nr_attrs)
|
|
return ___evlist__add_default_attrs(evlist, attrs, nr_attrs);
|
|
|
|
return topdown_parse_events(evlist);
|
|
}
|
|
|
|
struct evsel *arch_evlist__leader(struct list_head *list)
|
|
{
|
|
struct evsel *evsel, *first, *slots = NULL;
|
|
bool has_topdown = false;
|
|
|
|
first = list_first_entry(list, struct evsel, core.node);
|
|
|
|
if (!topdown_sys_has_perf_metrics())
|
|
return first;
|
|
|
|
/* If there is a slots event and a topdown event then the slots event comes first. */
|
|
__evlist__for_each_entry(list, evsel) {
|
|
if (evsel->pmu_name && !strncmp(evsel->pmu_name, "cpu", 3) && evsel->name) {
|
|
if (strcasestr(evsel->name, "slots")) {
|
|
slots = evsel;
|
|
if (slots == first)
|
|
return first;
|
|
}
|
|
if (strcasestr(evsel->name, "topdown"))
|
|
has_topdown = true;
|
|
if (slots && has_topdown)
|
|
return slots;
|
|
}
|
|
}
|
|
return first;
|
|
}
|