2011-01-04 02:39:04 +08:00
|
|
|
#ifndef __PERF_EVSEL_H
|
|
|
|
#define __PERF_EVSEL_H 1
|
|
|
|
|
|
|
|
#include <linux/list.h>
|
2011-01-04 03:45:52 +08:00
|
|
|
#include <stdbool.h>
|
2011-01-04 22:30:01 +08:00
|
|
|
#include "../../../include/linux/perf_event.h"
|
2011-01-04 02:39:04 +08:00
|
|
|
#include "types.h"
|
|
|
|
#include "xyarray.h"
|
perf tool: Add cgroup support
This patch adds the ability to filter monitoring based on container groups
(cgroups) for both perf stat and perf record. It is possible to monitor
multiple cgroup in parallel. There is one cgroup per event. The cgroups to
monitor are passed via a new -G option followed by a comma separated list of
cgroup names.
The cgroup filesystem has to be mounted. Given a cgroup name, the perf tool
finds the corresponding directory in the cgroup filesystem and opens it. It
then passes that file descriptor to the kernel.
Example:
$ perf stat -B -a -e cycles:u,cycles:u,cycles:u -G test1,,test2 -- sleep 1
Performance counter stats for 'sleep 1':
2,368,667,414 cycles test1
2,369,661,459 cycles
<not counted> cycles test2
1.001856890 seconds time elapsed
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590290.825bdf0a.7d0a.4890@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-02-14 17:20:01 +08:00
|
|
|
#include "cgroup.h"
|
2011-03-06 08:40:06 +08:00
|
|
|
#include "hist.h"
|
2011-01-04 03:45:52 +08:00
|
|
|
|
|
|
|
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[];
|
|
|
|
};
|
2011-01-04 02:39:04 +08:00
|
|
|
|
2011-01-13 08:39:13 +08:00
|
|
|
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;
|
|
|
|
};
|
|
|
|
|
2011-02-16 21:10:01 +08:00
|
|
|
/** 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.
|
|
|
|
*/
|
2011-01-04 02:39:04 +08:00
|
|
|
struct perf_evsel {
|
|
|
|
struct list_head node;
|
|
|
|
struct perf_event_attr attr;
|
|
|
|
char *filter;
|
|
|
|
struct xyarray *fd;
|
2011-03-10 22:15:54 +08:00
|
|
|
struct xyarray *sample_id;
|
|
|
|
u64 *id;
|
2011-01-04 03:45:52 +08:00
|
|
|
struct perf_counts *counts;
|
2011-01-04 02:39:04 +08:00
|
|
|
int idx;
|
2011-03-10 22:15:54 +08:00
|
|
|
int ids;
|
2011-03-06 08:40:06 +08:00
|
|
|
struct hists hists;
|
2011-02-16 21:10:01 +08:00
|
|
|
char *name;
|
2011-03-10 22:15:54 +08:00
|
|
|
union {
|
|
|
|
void *priv;
|
|
|
|
off_t id_offset;
|
|
|
|
};
|
perf tool: Add cgroup support
This patch adds the ability to filter monitoring based on container groups
(cgroups) for both perf stat and perf record. It is possible to monitor
multiple cgroup in parallel. There is one cgroup per event. The cgroups to
monitor are passed via a new -G option followed by a comma separated list of
cgroup names.
The cgroup filesystem has to be mounted. Given a cgroup name, the perf tool
finds the corresponding directory in the cgroup filesystem and opens it. It
then passes that file descriptor to the kernel.
Example:
$ perf stat -B -a -e cycles:u,cycles:u,cycles:u -G test1,,test2 -- sleep 1
Performance counter stats for 'sleep 1':
2,368,667,414 cycles test1
2,369,661,459 cycles
<not counted> cycles test2
1.001856890 seconds time elapsed
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4d590290.825bdf0a.7d0a.4890@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-02-14 17:20:01 +08:00
|
|
|
struct cgroup_sel *cgrp;
|
perf tools: Save some loops using perf_evlist__id2evsel
Since we already ask for PERF_SAMPLE_ID and use it to quickly find the
associated evsel, add handler func + data to struct perf_evsel to avoid
using chains of if(strcmp(event_name)) and also to avoid all the linear
list searches via trace_event_find.
To demonstrate the technique convert 'perf sched' to it:
# perf sched record sleep 5m
And then:
Performance counter stats for '/tmp/oldperf sched lat':
646.929438 task-clock # 0.999 CPUs utilized
9 context-switches # 0.000 M/sec
0 CPU-migrations # 0.000 M/sec
20,901 page-faults # 0.032 M/sec
1,290,144,450 cycles # 1.994 GHz
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
1,606,158,439 instructions # 1.24 insns per cycle
339,088,395 branches # 524.151 M/sec
4,550,735 branch-misses # 1.34% of all branches
0.647524759 seconds time elapsed
Versus:
Performance counter stats for 'perf sched lat':
473.564691 task-clock # 0.999 CPUs utilized
9 context-switches # 0.000 M/sec
0 CPU-migrations # 0.000 M/sec
20,903 page-faults # 0.044 M/sec
944,367,984 cycles # 1.994 GHz
<not supported> stalled-cycles-frontend
<not supported> stalled-cycles-backend
1,442,385,571 instructions # 1.53 insns per cycle
308,383,106 branches # 651.195 M/sec
4,481,784 branch-misses # 1.45% of all branches
0.474215751 seconds time elapsed
[root@emilia ~]#
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-1kbzpl74lwi6lavpqke2u2p3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-11-29 03:57:40 +08:00
|
|
|
struct {
|
|
|
|
void *func;
|
|
|
|
void *data;
|
|
|
|
} handler;
|
2012-08-02 05:53:11 +08:00
|
|
|
unsigned int sample_size;
|
2011-05-30 22:55:59 +08:00
|
|
|
bool supported;
|
2011-01-04 02:39:04 +08:00
|
|
|
};
|
|
|
|
|
2011-01-04 09:09:46 +08:00
|
|
|
struct cpu_map;
|
|
|
|
struct thread_map;
|
2011-01-13 03:03:24 +08:00
|
|
|
struct perf_evlist;
|
2011-11-09 00:41:57 +08:00
|
|
|
struct perf_record_opts;
|
2011-01-04 09:09:46 +08:00
|
|
|
|
2011-01-07 11:11:09 +08:00
|
|
|
struct perf_evsel *perf_evsel__new(struct perf_event_attr *attr, int idx);
|
2011-01-19 07:41:45 +08:00
|
|
|
void perf_evsel__init(struct perf_evsel *evsel,
|
|
|
|
struct perf_event_attr *attr, int idx);
|
|
|
|
void perf_evsel__exit(struct perf_evsel *evsel);
|
2011-01-04 02:39:04 +08:00
|
|
|
void perf_evsel__delete(struct perf_evsel *evsel);
|
|
|
|
|
2011-11-09 00:41:57 +08:00
|
|
|
void perf_evsel__config(struct perf_evsel *evsel,
|
2012-03-16 16:42:20 +08:00
|
|
|
struct perf_record_opts *opts,
|
|
|
|
struct perf_evsel *first);
|
2011-11-09 00:41:57 +08:00
|
|
|
|
2012-06-12 01:08:07 +08:00
|
|
|
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);
|
2012-06-12 23:34:58 +08:00
|
|
|
const char *perf_evsel__name(struct perf_evsel *evsel);
|
2012-05-26 03:38:11 +08:00
|
|
|
|
2011-01-04 02:39:04 +08:00
|
|
|
int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
|
2011-01-13 08:39:13 +08:00
|
|
|
int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads);
|
2011-01-04 03:45:52 +08:00
|
|
|
int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
|
2011-01-04 02:39:04 +08:00
|
|
|
void perf_evsel__free_fd(struct perf_evsel *evsel);
|
2011-01-13 08:39:13 +08:00
|
|
|
void perf_evsel__free_id(struct perf_evsel *evsel);
|
2011-01-04 03:45:52 +08:00
|
|
|
void perf_evsel__close_fd(struct perf_evsel *evsel, int ncpus, int nthreads);
|
2011-01-04 02:39:04 +08:00
|
|
|
|
2011-01-12 09:42:19 +08:00
|
|
|
int perf_evsel__open_per_cpu(struct perf_evsel *evsel,
|
2011-10-25 20:42:19 +08:00
|
|
|
struct cpu_map *cpus, bool group,
|
|
|
|
struct xyarray *group_fds);
|
2011-01-12 09:42:19 +08:00
|
|
|
int perf_evsel__open_per_thread(struct perf_evsel *evsel,
|
2011-10-25 20:42:19 +08:00
|
|
|
struct thread_map *threads, bool group,
|
|
|
|
struct xyarray *group_fds);
|
2011-01-12 09:42:19 +08:00
|
|
|
int perf_evsel__open(struct perf_evsel *evsel, struct cpu_map *cpus,
|
2011-10-25 20:42:19 +08:00
|
|
|
struct thread_map *threads, bool group,
|
|
|
|
struct xyarray *group_fds);
|
|
|
|
void perf_evsel__close(struct perf_evsel *evsel, int ncpus, int nthreads);
|
2011-01-04 03:48:12 +08:00
|
|
|
|
2011-01-04 02:49:44 +08:00
|
|
|
#define perf_evsel__match(evsel, t, c) \
|
|
|
|
(evsel->attr.type == PERF_TYPE_##t && \
|
|
|
|
evsel->attr.config == PERF_COUNT_##c)
|
|
|
|
|
2011-01-04 03:45:52 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2012-03-22 21:37:26 +08:00
|
|
|
void hists__init(struct hists *hists);
|
|
|
|
|
2012-08-02 23:23:46 +08:00
|
|
|
int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
|
|
|
|
struct perf_sample *sample, bool swapped);
|
2011-01-04 02:39:04 +08:00
|
|
|
#endif /* __PERF_EVSEL_H */
|