mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-03-22 07:27:12 +08:00
Currently, `perf stat` skips or hides metrics when the underlying
hardware events cannot be counted (e.g., due to insufficient permissions
or unsupported events).
In `--metric-only` mode, this often results in missing columns or blank
spaces, making the output difficult to parse.
Modify the logic to ensure metrics are consistently displayed by
propagating NAN (Not a Number) through the expression evaluator.
Specifically:
1. Update `prepare_metric()` in stat-shadow.c to treat uncounted events
(where `run == 0`) as NAN. This leverages the existing math in expr.y
to propagate NAN through metric expressions.
2. Remove the early return in the display logic's `printout()` function
that was previously skipping metrics in `--metric-only` mode for
failed events.
l
3. Simplify `perf_stat__skip_metric_event()` to no longer depend on
event runtime.
Tested:
1. `perf all metrics test` did not crash while paranoid is 2.
2. Multiple combinations with `CPUs_utilized` while paranoid is 2.
$ ./perf stat -M CPUs_utilized -a -- sleep 1
Performance counter stats for 'system wide':
<not supported> msec cpu-clock:u # nan CPUs CPUs_utilized
1,006,356,120 duration_time
1.004375550 seconds time elapsed
$ ./perf stat -M CPUs_utilized -a -j -- sleep 1
{"counter-value" : "<not supported>", "unit" : "msec", "event" : "cpu-clock:u", "event-runtime" : 0, "pcnt-running" : 100.00, "metric-value" : "nan", "metric-unit" : "CPUs CPUs_utilized"}
{"counter-value" : "1006642462.000000", "unit" : "", "event" : "duration_time", "event-runtime" : 1, "pcnt-running" : 100.00}
$ ./perf stat -M CPUs_utilized -a --metric-only -- sleep 1
Performance counter stats for 'system wide':
CPUs CPUs_utilized
nan
1.004424652 seconds time elapsed
$ ./perf stat -M CPUs_utilized -a --metric-only -j -- sleep 1
{"CPUs CPUs_utilized" : "none"}
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Chun-Tse Shao <ctshao@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Yang Li <yang.lee@linux.alibaba.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
210 lines
5.6 KiB
C
210 lines
5.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __PERF_STATS_H
|
|
#define __PERF_STATS_H
|
|
|
|
#include <linux/types.h>
|
|
#include <stdio.h>
|
|
#include <sys/types.h>
|
|
#include <sys/resource.h>
|
|
#include "cpumap.h"
|
|
#include "counts.h"
|
|
|
|
struct perf_cpu_map;
|
|
struct perf_stat_config;
|
|
struct timespec;
|
|
|
|
struct stats {
|
|
double n, mean, M2;
|
|
u64 max, min;
|
|
};
|
|
|
|
/* hold aggregated event info */
|
|
struct perf_stat_aggr {
|
|
/* aggregated values */
|
|
struct perf_counts_values counts;
|
|
/* number of entries (CPUs) aggregated */
|
|
int nr;
|
|
/* whether any entry has failed to read/process event */
|
|
bool failed;
|
|
/* to mark this data is processed already */
|
|
bool used;
|
|
};
|
|
|
|
/* per-evsel event stats */
|
|
struct perf_stat_evsel {
|
|
/* used for repeated runs */
|
|
struct stats res_stats;
|
|
/* number of allocated 'aggr' */
|
|
int nr_aggr;
|
|
/* aggregated event values */
|
|
struct perf_stat_aggr *aggr;
|
|
/* used for group read */
|
|
u64 *group_data;
|
|
};
|
|
|
|
enum aggr_mode {
|
|
AGGR_NONE,
|
|
AGGR_GLOBAL,
|
|
AGGR_SOCKET,
|
|
AGGR_DIE,
|
|
AGGR_CLUSTER,
|
|
AGGR_CACHE,
|
|
AGGR_CORE,
|
|
AGGR_THREAD,
|
|
AGGR_UNSET,
|
|
AGGR_NODE,
|
|
AGGR_MAX
|
|
};
|
|
|
|
typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, struct perf_cpu cpu);
|
|
|
|
struct perf_stat_config {
|
|
enum aggr_mode aggr_mode;
|
|
u32 aggr_level;
|
|
bool scale;
|
|
bool no_inherit;
|
|
bool identifier;
|
|
bool csv_output;
|
|
bool json_output;
|
|
bool interval_clear;
|
|
bool metric_only;
|
|
bool null_run;
|
|
bool ru_display;
|
|
bool big_num;
|
|
bool hybrid_merge;
|
|
bool walltime_run_table;
|
|
bool all_kernel;
|
|
bool all_user;
|
|
bool percore_show_thread;
|
|
bool summary;
|
|
bool no_csv_summary;
|
|
bool metric_no_group;
|
|
bool metric_no_merge;
|
|
bool metric_no_threshold;
|
|
bool hardware_aware_grouping;
|
|
bool stop_read_counter;
|
|
bool iostat_run;
|
|
char *user_requested_cpu_list;
|
|
bool system_wide;
|
|
FILE *output;
|
|
unsigned int interval;
|
|
unsigned int timeout;
|
|
unsigned int unit_width;
|
|
unsigned int metric_only_len;
|
|
int times;
|
|
int run_count;
|
|
int print_free_counters_hint;
|
|
const char *csv_sep;
|
|
struct stats *walltime_nsecs_stats;
|
|
struct rusage ru_data;
|
|
struct cpu_aggr_map *aggr_map;
|
|
aggr_get_id_t aggr_get_id;
|
|
struct cpu_aggr_map *cpus_aggr_map;
|
|
u64 *walltime_run;
|
|
int ctl_fd;
|
|
int ctl_fd_ack;
|
|
bool ctl_fd_close;
|
|
const char *cgroup_list;
|
|
unsigned int topdown_level;
|
|
};
|
|
|
|
extern struct perf_stat_config stat_config;
|
|
|
|
void perf_stat__set_big_num(int set);
|
|
|
|
void update_stats(struct stats *stats, u64 val);
|
|
double avg_stats(struct stats *stats);
|
|
double stddev_stats(struct stats *stats);
|
|
double rel_stddev_stats(double stddev, double avg);
|
|
|
|
static inline void init_stats(struct stats *stats)
|
|
{
|
|
stats->n = 0.0;
|
|
stats->mean = 0.0;
|
|
stats->M2 = 0.0;
|
|
stats->min = (u64) -1;
|
|
stats->max = 0;
|
|
}
|
|
|
|
struct evsel;
|
|
struct evlist;
|
|
|
|
enum metric_threshold_classify {
|
|
METRIC_THRESHOLD_UNKNOWN,
|
|
METRIC_THRESHOLD_BAD,
|
|
METRIC_THRESHOLD_NEARLY_BAD,
|
|
METRIC_THRESHOLD_LESS_GOOD,
|
|
METRIC_THRESHOLD_GOOD,
|
|
};
|
|
const char *metric_threshold_classify__color(enum metric_threshold_classify thresh);
|
|
|
|
typedef void (*print_metric_t)(struct perf_stat_config *config,
|
|
void *ctx,
|
|
enum metric_threshold_classify thresh,
|
|
const char *fmt,
|
|
const char *unit,
|
|
double val);
|
|
typedef void (*new_line_t)(struct perf_stat_config *config, void *ctx);
|
|
|
|
/* Used to print the display name of the Default metricgroup for now. */
|
|
typedef void (*print_metricgroup_header_t)(struct perf_stat_config *config,
|
|
void *ctx, const char *metricgroup_name);
|
|
|
|
void perf_stat__reset_shadow_stats(void);
|
|
struct perf_stat_output_ctx {
|
|
void *ctx;
|
|
print_metric_t print_metric;
|
|
new_line_t new_line;
|
|
print_metricgroup_header_t print_metricgroup_header;
|
|
bool force_header;
|
|
};
|
|
|
|
void perf_stat__print_shadow_stats(struct perf_stat_config *config,
|
|
struct evsel *evsel,
|
|
int aggr_idx,
|
|
struct perf_stat_output_ctx *out);
|
|
bool perf_stat__skip_metric_event(struct evsel *evsel);
|
|
void *perf_stat__print_shadow_stats_metricgroup(struct perf_stat_config *config,
|
|
struct evsel *evsel,
|
|
int aggr_idx,
|
|
int *num,
|
|
void *from,
|
|
struct perf_stat_output_ctx *out);
|
|
|
|
int evlist__alloc_stats(struct perf_stat_config *config,
|
|
struct evlist *evlist, bool alloc_raw);
|
|
void evlist__free_stats(struct evlist *evlist);
|
|
void evlist__reset_stats(struct evlist *evlist);
|
|
void evlist__reset_prev_raw_counts(struct evlist *evlist);
|
|
void evlist__copy_prev_raw_counts(struct evlist *evlist);
|
|
void evlist__save_aggr_prev_raw_counts(struct evlist *evlist);
|
|
|
|
int evlist__alloc_aggr_stats(struct evlist *evlist, int nr_aggr);
|
|
void evlist__reset_aggr_stats(struct evlist *evlist);
|
|
void evlist__copy_res_stats(struct perf_stat_config *config, struct evlist *evlist);
|
|
|
|
int perf_stat_process_counter(struct perf_stat_config *config,
|
|
struct evsel *counter);
|
|
void perf_stat_merge_counters(struct perf_stat_config *config, struct evlist *evlist);
|
|
void perf_stat_process_percore(struct perf_stat_config *config, struct evlist *evlist);
|
|
|
|
struct perf_tool;
|
|
union perf_event;
|
|
struct perf_session;
|
|
struct target;
|
|
|
|
int perf_event__process_stat_event(const struct perf_tool *tool,
|
|
struct perf_session *session,
|
|
union perf_event *event);
|
|
|
|
size_t perf_event__fprintf_stat(union perf_event *event, FILE *fp);
|
|
size_t perf_event__fprintf_stat_round(union perf_event *event, FILE *fp);
|
|
size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
|
|
|
|
void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config,
|
|
struct target *_target, struct timespec *ts, int argc, const char **argv);
|
|
|
|
struct metric_expr;
|
|
double test_generic_metric(struct metric_expr *mexp, int aggr_idx);
|
|
#endif
|