linux_dsm_epyc7002/tools/perf/util/stat.h

116 lines
3.0 KiB
C
Raw Normal View History

#ifndef __PERF_STATS_H
#define __PERF_STATS_H
#include <linux/types.h>
#include <stdio.h>
#include "xyarray.h"
struct stats
{
double n, mean, M2;
u64 max, min;
};
enum perf_stat_evsel_id {
PERF_STAT_EVSEL_ID__NONE = 0,
PERF_STAT_EVSEL_ID__CYCLES_IN_TX,
PERF_STAT_EVSEL_ID__TRANSACTION_START,
PERF_STAT_EVSEL_ID__ELISION_START,
PERF_STAT_EVSEL_ID__CYCLES_IN_TX_CP,
PERF_STAT_EVSEL_ID__TOPDOWN_TOTAL_SLOTS,
PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_ISSUED,
PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED,
PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES,
PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES,
PERF_STAT_EVSEL_ID__SMI_NUM,
PERF_STAT_EVSEL_ID__APERF,
PERF_STAT_EVSEL_ID__MAX,
};
struct perf_stat_evsel {
struct stats res_stats[3];
enum perf_stat_evsel_id id;
u64 *group_data;
};
enum aggr_mode {
AGGR_NONE,
AGGR_GLOBAL,
AGGR_SOCKET,
AGGR_CORE,
perf stat: Introduce --per-thread option Currently all the -p option PID arguments tasks values get aggregated and printed as single values. Adding --per-tasks option to print values per task. $ perf stat -e cycles,instructions --per-thread -p 30190,30242 ^C Performance counter stats for process id '30190,30242': cat-30190 0 cycles yes-30242 3,842,525,421 cycles cat-30190 0 instructions yes-30242 10,370,817,010 instructions 1.143155657 seconds time elapsed Also works under interval mode: $ perf stat -e cycles,instructions --per-thread -p 30190,30242 -I 1000 # time comm-pid counts unit events 1.000073435 cat-30190 89,058 cycles 1.000073435 yes-30242 3,360,786,902 cycles (100.00%) 1.000073435 cat-30190 14,066 instructions 1.000073435 yes-30242 9,069,937,462 instructions 2.000204830 cat-30190 0 cycles 2.000204830 yes-30242 3,351,667,626 cycles 2.000204830 cat-30190 0 instructions 2.000204830 yes-30242 9,045,796,885 instructions ^C 2.771286639 cat-30190 0 cycles 2.771286639 yes-30242 2,593,884,166 cycles 2.771286639 cat-30190 0 instructions 2.771286639 yes-30242 7,001,171,191 instructions It works only with -t and -p options, otherwise following error is printed: $ perf stat -e cycles --per-thread -I 1000 ls The --per-thread option is only available when monitoring via -p -t options. -p, --pid <pid> stat events on existing process id -t, --tid <tid> stat events on existing thread id Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1435310967-14570-23-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-26 16:29:27 +07:00
AGGR_THREAD,
AGGR_UNSET,
};
struct perf_stat_config {
enum aggr_mode aggr_mode;
bool scale;
FILE *output;
unsigned int interval;
};
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 perf_evsel;
struct perf_evlist;
bool __perf_evsel_stat__is(struct perf_evsel *evsel,
enum perf_stat_evsel_id id);
#define perf_stat_evsel__is(evsel, id) \
__perf_evsel_stat__is(evsel, PERF_STAT_EVSEL_ID__ ## id)
void perf_stat_evsel_id_init(struct perf_evsel *evsel);
extern struct stats walltime_nsecs_stats;
typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
const char *fmt, double val);
typedef void (*new_line_t )(void *ctx);
void perf_stat__init_shadow_stats(void);
void perf_stat__reset_shadow_stats(void);
void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
int cpu);
struct perf_stat_output_ctx {
void *ctx;
print_metric_t print_metric;
new_line_t new_line;
perf stat: Output JSON MetricExpr metric Add generic infrastructure to perf stat to output ratios for "MetricExpr" entries in the event lists. Many events are more useful as ratios than in raw form, typically some count in relation to total ticks. Transfer the MetricExpr information from the alias to the evsel. We mark the events that need to be collected for MetricExpr, and also link the events using them with a pointer. The code is careful to always prefer the right event in the same group to minimize multiplexing errors. At the moment only a single relation is supported. Then add a rblist to the stat shadow code that remembers stats based on the cpu and context. Then finally update and retrieve and print these values similarly to the existing hardcoded perf metrics. We use the simple expression parser added earlier to evaluate the expression. Normally we just output the result without further commentary, but for --metric-only this would lead to empty columns. So for this case use the original event as description. There is no attempt to automatically add the MetricExpr event, if it is missing, however we suggest it to the user, because the user tool doesn't have enough information to reliably construct a group that is guaranteed to schedule. So we leave that to the user. % perf stat -a -I 1000 -e '{unc_p_clockticks,unc_p_freq_max_os_cycles}' 1.000147889 800,085,181 unc_p_clockticks 1.000147889 93,126,241 unc_p_freq_max_os_cycles # 11.6 2.000448381 800,218,217 unc_p_clockticks 2.000448381 142,516,095 unc_p_freq_max_os_cycles # 17.8 3.000639852 800,243,057 unc_p_clockticks 3.000639852 162,292,689 unc_p_freq_max_os_cycles # 20.3 % perf stat -a -I 1000 -e '{unc_p_clockticks,unc_p_freq_max_os_cycles}' --metric-only # time freq_max_os_cycles % 1.000127077 0.9 2.000301436 0.7 3.000456379 0.0 v2: Change from DivideBy to MetricExpr v3: Use expr__ prefix. Support more than one other event. v4: Update description v5: Only print warning message once for multiple PMUs. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170320201711.14142-11-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-21 03:17:08 +07:00
bool force_header;
};
void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
double avg, int cpu,
struct perf_stat_output_ctx *out);
perf stat: Output JSON MetricExpr metric Add generic infrastructure to perf stat to output ratios for "MetricExpr" entries in the event lists. Many events are more useful as ratios than in raw form, typically some count in relation to total ticks. Transfer the MetricExpr information from the alias to the evsel. We mark the events that need to be collected for MetricExpr, and also link the events using them with a pointer. The code is careful to always prefer the right event in the same group to minimize multiplexing errors. At the moment only a single relation is supported. Then add a rblist to the stat shadow code that remembers stats based on the cpu and context. Then finally update and retrieve and print these values similarly to the existing hardcoded perf metrics. We use the simple expression parser added earlier to evaluate the expression. Normally we just output the result without further commentary, but for --metric-only this would lead to empty columns. So for this case use the original event as description. There is no attempt to automatically add the MetricExpr event, if it is missing, however we suggest it to the user, because the user tool doesn't have enough information to reliably construct a group that is guaranteed to schedule. So we leave that to the user. % perf stat -a -I 1000 -e '{unc_p_clockticks,unc_p_freq_max_os_cycles}' 1.000147889 800,085,181 unc_p_clockticks 1.000147889 93,126,241 unc_p_freq_max_os_cycles # 11.6 2.000448381 800,218,217 unc_p_clockticks 2.000448381 142,516,095 unc_p_freq_max_os_cycles # 17.8 3.000639852 800,243,057 unc_p_clockticks 3.000639852 162,292,689 unc_p_freq_max_os_cycles # 20.3 % perf stat -a -I 1000 -e '{unc_p_clockticks,unc_p_freq_max_os_cycles}' --metric-only # time freq_max_os_cycles % 1.000127077 0.9 2.000301436 0.7 3.000456379 0.0 v2: Change from DivideBy to MetricExpr v3: Use expr__ prefix. Support more than one other event. v4: Update description v5: Only print warning message once for multiple PMUs. Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20170320201711.14142-11-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-21 03:17:08 +07:00
void perf_stat__collect_metric_expr(struct perf_evlist *);
int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
void perf_evlist__free_stats(struct perf_evlist *evlist);
void perf_evlist__reset_stats(struct perf_evlist *evlist);
int perf_stat_process_counter(struct perf_stat_config *config,
struct perf_evsel *counter);
struct perf_tool;
union perf_event;
struct perf_session;
int perf_event__process_stat_event(struct perf_tool *tool,
union perf_event *event,
struct perf_session *session);
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);
#endif