mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-15 16:24:13 +08:00
6a4bb04caa
This patch adds a functionality that allows to create event groups
based on the way they are specified on the command line. Adding
functionality to the '{}' group syntax introduced in earlier patch.
The current '--group/-g' option behaviour remains intact. If you
specify it for record/stat/top command, all the specified events
become members of a single group with the first event as a group
leader.
With the new '{}' group syntax you can create group like:
# perf record -e '{cycles,faults}' ls
resulting in single event group containing 'cycles' and 'faults'
events, with cycles event as group leader.
All groups are created with regards to threads and cpus. Thus
recording an event group within a 2 threads on server with
4 CPUs will create 8 separate groups.
Examples (first event in brackets is group leader):
# 1 group (cpu-clock,task-clock)
perf record --group -e cpu-clock,task-clock ls
perf record -e '{cpu-clock,task-clock}' ls
# 2 groups (cpu-clock,task-clock) (minor-faults,major-faults)
perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls
# 1 group (cpu-clock,task-clock,minor-faults,major-faults)
perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls
perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls
# 2 groups (cpu-clock,task-clock) (minor-faults,major-faults)
perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \
-e instructions ls
# 1 group
# (cpu-clock,task-clock,minor-faults,major-faults,instructions)
perf record --group -e cpu-clock,task-clock \
-e minor-faults,major-faults -e instructions ls perf record -e
'{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls
It's possible to use standard event modifier for a group, which spans
over all events in the group and updates each event modifier settings,
for example:
# perf record -r '{faults:k,cache-references}:p'
resulting in ':kp' modifier being used for 'faults' and ':p' modifier
being used for 'cache-references' event.
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ulrich Drepper <drepper@gmail.com>
Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
188 lines
5.1 KiB
C
188 lines
5.1 KiB
C
#ifndef __PERF_EVSEL_H
|
|
#define __PERF_EVSEL_H 1
|
|
|
|
#include <linux/list.h>
|
|
#include <stdbool.h>
|
|
#include "../../../include/linux/perf_event.h"
|
|
#include "types.h"
|
|
#include "xyarray.h"
|
|
#include "cgroup.h"
|
|
#include "hist.h"
|
|
|
|
struct perf_counts_values {
|
|
union {
|
|
struct {
|
|
u64 val;
|
|
u64 ena;
|
|
u64 run;
|
|
};
|
|
u64 values[3];
|
|
};
|
|
};
|
|
|
|
struct perf_counts {
|
|
s8 scaled;
|
|
struct perf_counts_values aggr;
|
|
struct perf_counts_values cpu[];
|
|
};
|
|
|
|
struct perf_evsel;
|
|
|
|
/*
|
|
* Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there are
|
|
* more than one entry in the evlist.
|
|
*/
|
|
struct perf_sample_id {
|
|
struct hlist_node node;
|
|
u64 id;
|
|
struct perf_evsel *evsel;
|
|
};
|
|
|
|
/** struct perf_evsel - event selector
|
|
*
|
|
* @name - Can be set to retain the original event name passed by the user,
|
|
* so that when showing results in tools such as 'perf stat', we
|
|
* show the name used, not some alias.
|
|
*/
|
|
struct perf_evsel {
|
|
struct list_head node;
|
|
struct perf_event_attr attr;
|
|
char *filter;
|
|
struct xyarray *fd;
|
|
struct xyarray *sample_id;
|
|
u64 *id;
|
|
struct perf_counts *counts;
|
|
int idx;
|
|
int ids;
|
|
struct hists hists;
|
|
char *name;
|
|
struct event_format *tp_format;
|
|
union {
|
|
void *priv;
|
|
off_t id_offset;
|
|
};
|
|
struct cgroup_sel *cgrp;
|
|
struct {
|
|
void *func;
|
|
void *data;
|
|
} handler;
|
|
unsigned int sample_size;
|
|
bool supported;
|
|
/* parse modifier helper */
|
|
int exclude_GH;
|
|
struct perf_evsel *leader;
|
|
char *group_name;
|
|
};
|
|
|
|
struct cpu_map;
|
|
struct thread_map;
|
|
struct perf_evlist;
|
|
struct perf_record_opts;
|
|
|
|
struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx);
|
|
void perf_evsel__init(struct perf_evsel *evsel,
|
|
struct perf_event_attr *attr, int idx);
|
|
void perf_evsel__exit(struct perf_evsel *evsel);
|
|
void perf_evsel__delete(struct perf_evsel *evsel);
|
|
|
|
void perf_evsel__config(struct perf_evsel *evsel,
|
|
struct perf_record_opts *opts,
|
|
struct perf_evsel *first);
|
|
|
|
bool perf_evsel__is_cache_op_valid(u8 type, u8 op);
|
|
|
|
#define PERF_EVSEL__MAX_ALIASES 8
|
|
|
|
extern const char *perf_evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX]
|
|
[PERF_EVSEL__MAX_ALIASES];
|
|
extern const char *perf_evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX]
|
|
[PERF_EVSEL__MAX_ALIASES];
|
|
const char *perf_evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX]
|
|
[PERF_EVSEL__MAX_ALIASES];
|
|
int __perf_evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result,
|
|
char *bf, size_t size);
|
|
const char *perf_evsel__name(struct perf_evsel *evsel);
|
|
|
|
int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
|
|
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
|
|
int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
|
|
void perf_evsel__free_fd(struct perf_evsel *evsel);
|
|
void perf_evsel__free_id(struct perf_evsel *evsel);
|
|
void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
|
|
|
|
int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
|
|
struct cpu_map *cpus);
|
|
int perf_evsel__open_per_thread(struct perf_evsel *evsel,
|
|
struct thread_map *threads);
|
|
int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
|
|
struct thread_map *threads);
|
|
void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads);
|
|
|
|
#define perf_evsel__match(evsel, t, c) \
|
|
(evsel->attr.type == PERF_TYPE_##t && \
|
|
evsel->attr.config == PERF_COUNT_##c)
|
|
|
|
int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
|
|
int cpu, int thread, bool scale);
|
|
|
|
/**
|
|
* perf_evsel__read_on_cpu - Read out the results on a CPU and thread
|
|
*
|
|
* @evsel - event selector to read value
|
|
* @cpu - CPU of interest
|
|
* @thread - thread of interest
|
|
*/
|
|
static inline int perf_evsel__read_on_cpu(struct perf_evsel *evsel,
|
|
int cpu, int thread)
|
|
{
|
|
return __perf_evsel__read_on_cpu(evsel, cpu, thread, false);
|
|
}
|
|
|
|
/**
|
|
* perf_evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled
|
|
*
|
|
* @evsel - event selector to read value
|
|
* @cpu - CPU of interest
|
|
* @thread - thread of interest
|
|
*/
|
|
static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel,
|
|
int cpu, int thread)
|
|
{
|
|
return __perf_evsel__read_on_cpu(evsel, cpu, thread, true);
|
|
}
|
|
|
|
int __perf_evsel__read(struct perf_evsel *evsel, int ncpus, int nthreads,
|
|
bool scale);
|
|
|
|
/**
|
|
* perf_evsel__read - Read the aggregate results on all CPUs
|
|
*
|
|
* @evsel - event selector to read value
|
|
* @ncpus - Number of cpus affected, from zero
|
|
* @nthreads - Number of threads affected, from zero
|
|
*/
|
|
static inline int perf_evsel__read(struct perf_evsel *evsel,
|
|
int ncpus, int nthreads)
|
|
{
|
|
return __perf_evsel__read(evsel, ncpus, nthreads, false);
|
|
}
|
|
|
|
/**
|
|
* perf_evsel__read_scaled - Read the aggregate results on all CPUs, scaled
|
|
*
|
|
* @evsel - event selector to read value
|
|
* @ncpus - Number of cpus affected, from zero
|
|
* @nthreads - Number of threads affected, from zero
|
|
*/
|
|
static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
|
|
int ncpus, int nthreads)
|
|
{
|
|
return __perf_evsel__read(evsel, ncpus, nthreads, true);
|
|
}
|
|
|
|
void hists__init(struct hists *hists);
|
|
|
|
int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
|
|
struct perf_sample *sample, bool swapped);
|
|
#endif /* __PERF_EVSEL_H */
|