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>
This commit is contained in:
Arnaldo Carvalho de Melo
parent
e7984b7bee
commit
ee29be625b
5 changed files with 137 additions and 76 deletions
|
|
@ -2,6 +2,7 @@
|
|||
#include "perf.h"
|
||||
|
||||
#include "util/util.h"
|
||||
#include "util/evlist.h"
|
||||
#include "util/cache.h"
|
||||
#include "util/evsel.h"
|
||||
#include "util/symbol.h"
|
||||
|
|
@ -1358,12 +1359,13 @@ static void sort_lat(void)
|
|||
static struct trace_sched_handler *trace_handler;
|
||||
|
||||
static void
|
||||
process_sched_wakeup_event(void *data, struct machine *machine,
|
||||
process_sched_wakeup_event(struct perf_tool *tool __used,
|
||||
struct event *event,
|
||||
int cpu __used,
|
||||
u64 timestamp __used,
|
||||
struct thread *thread __used)
|
||||
struct perf_sample *sample,
|
||||
struct machine *machine,
|
||||
struct thread *thread)
|
||||
{
|
||||
void *data = sample->raw_data;
|
||||
struct trace_wakeup_event wakeup_event;
|
||||
|
||||
FILL_COMMON_FIELDS(wakeup_event, event, data);
|
||||
|
|
@ -1376,7 +1378,7 @@ process_sched_wakeup_event(void *data, struct machine *machine,
|
|||
|
||||
if (trace_handler->wakeup_event)
|
||||
trace_handler->wakeup_event(&wakeup_event, machine, event,
|
||||
cpu, timestamp, thread);
|
||||
sample->cpu, sample->time, thread);
|
||||
}
|
||||
|
||||
/*
|
||||
|
|
@ -1471,14 +1473,15 @@ map_switch_event(struct trace_switch_event *switch_event,
|
|||
}
|
||||
}
|
||||
|
||||
|
||||
static void
|
||||
process_sched_switch_event(void *data, struct machine *machine,
|
||||
process_sched_switch_event(struct perf_tool *tool __used,
|
||||
struct event *event,
|
||||
int this_cpu,
|
||||
u64 timestamp __used,
|
||||
struct thread *thread __used)
|
||||
struct perf_sample *sample,
|
||||
struct machine *machine,
|
||||
struct thread *thread)
|
||||
{
|
||||
int this_cpu = sample->cpu;
|
||||
void *data = sample->raw_data;
|
||||
struct trace_switch_event switch_event;
|
||||
|
||||
FILL_COMMON_FIELDS(switch_event, event, data);
|
||||
|
|
@ -1501,18 +1504,19 @@ process_sched_switch_event(void *data, struct machine *machine,
|
|||
}
|
||||
if (trace_handler->switch_event)
|
||||
trace_handler->switch_event(&switch_event, machine, event,
|
||||
this_cpu, timestamp, thread);
|
||||
this_cpu, sample->time, thread);
|
||||
|
||||
curr_pid[this_cpu] = switch_event.next_pid;
|
||||
}
|
||||
|
||||
static void
|
||||
process_sched_runtime_event(void *data, struct machine *machine,
|
||||
struct event *event,
|
||||
int cpu __used,
|
||||
u64 timestamp __used,
|
||||
struct thread *thread __used)
|
||||
process_sched_runtime_event(struct perf_tool *tool __used,
|
||||
struct event *event,
|
||||
struct perf_sample *sample,
|
||||
struct machine *machine,
|
||||
struct thread *thread)
|
||||
{
|
||||
void *data = sample->raw_data;
|
||||
struct trace_runtime_event runtime_event;
|
||||
|
||||
FILL_ARRAY(runtime_event, comm, event, data);
|
||||
|
|
@ -1521,16 +1525,18 @@ process_sched_runtime_event(void *data, struct machine *machine,
|
|||
FILL_FIELD(runtime_event, vruntime, event, data);
|
||||
|
||||
if (trace_handler->runtime_event)
|
||||
trace_handler->runtime_event(&runtime_event, machine, event, cpu, timestamp, thread);
|
||||
trace_handler->runtime_event(&runtime_event, machine, event,
|
||||
sample->cpu, sample->time, thread);
|
||||
}
|
||||
|
||||
static void
|
||||
process_sched_fork_event(void *data,
|
||||
process_sched_fork_event(struct perf_tool *tool __used,
|
||||
struct event *event,
|
||||
int cpu __used,
|
||||
u64 timestamp __used,
|
||||
struct thread *thread __used)
|
||||
struct perf_sample *sample,
|
||||
struct machine *machine __used,
|
||||
struct thread *thread)
|
||||
{
|
||||
void *data = sample->raw_data;
|
||||
struct trace_fork_event fork_event;
|
||||
|
||||
FILL_COMMON_FIELDS(fork_event, event, data);
|
||||
|
|
@ -1542,13 +1548,14 @@ process_sched_fork_event(void *data,
|
|||
|
||||
if (trace_handler->fork_event)
|
||||
trace_handler->fork_event(&fork_event, event,
|
||||
cpu, timestamp, thread);
|
||||
sample->cpu, sample->time, thread);
|
||||
}
|
||||
|
||||
static void
|
||||
process_sched_exit_event(struct event *event,
|
||||
int cpu __used,
|
||||
u64 timestamp __used,
|
||||
process_sched_exit_event(struct perf_tool *tool __used,
|
||||
struct event *event,
|
||||
struct perf_sample *sample __used,
|
||||
struct machine *machine __used,
|
||||
struct thread *thread __used)
|
||||
{
|
||||
if (verbose)
|
||||
|
|
@ -1556,12 +1563,13 @@ process_sched_exit_event(struct event *event,
|
|||
}
|
||||
|
||||
static void
|
||||
process_sched_migrate_task_event(void *data, struct machine *machine,
|
||||
struct event *event,
|
||||
int cpu __used,
|
||||
u64 timestamp __used,
|
||||
struct thread *thread __used)
|
||||
process_sched_migrate_task_event(struct perf_tool *tool __used,
|
||||
struct event *event,
|
||||
struct perf_sample *sample,
|
||||
struct machine *machine,
|
||||
struct thread *thread)
|
||||
{
|
||||
void *data = sample->raw_data;
|
||||
struct trace_migrate_task_event migrate_task_event;
|
||||
|
||||
FILL_COMMON_FIELDS(migrate_task_event, event, data);
|
||||
|
|
@ -1573,67 +1581,46 @@ process_sched_migrate_task_event(void *data, struct machine *machine,
|
|||
|
||||
if (trace_handler->migrate_task_event)
|
||||
trace_handler->migrate_task_event(&migrate_task_event, machine,
|
||||
event, cpu, timestamp, thread);
|
||||
event, sample->cpu,
|
||||
sample->time, thread);
|
||||
}
|
||||
|
||||
static void process_raw_event(union perf_event *raw_event __used,
|
||||
struct machine *machine, void *data, int cpu,
|
||||
u64 timestamp, struct thread *thread)
|
||||
typedef void (*tracepoint_handler)(struct perf_tool *tool, struct event *event,
|
||||
struct perf_sample *sample,
|
||||
struct machine *machine,
|
||||
struct thread *thread);
|
||||
|
||||
static int perf_sched__process_tracepoint_sample(struct perf_tool *tool,
|
||||
union perf_event *event __used,
|
||||
struct perf_sample *sample,
|
||||
struct perf_evsel *evsel,
|
||||
struct machine *machine)
|
||||
{
|
||||
struct event *event;
|
||||
int type;
|
||||
struct thread *thread = machine__findnew_thread(machine, sample->pid);
|
||||
|
||||
|
||||
type = trace_parse_common_type(data);
|
||||
event = trace_find_event(type);
|
||||
|
||||
if (!strcmp(event->name, "sched_switch"))
|
||||
process_sched_switch_event(data, machine, event, cpu, timestamp, thread);
|
||||
if (!strcmp(event->name, "sched_stat_runtime"))
|
||||
process_sched_runtime_event(data, machine, event, cpu, timestamp, thread);
|
||||
if (!strcmp(event->name, "sched_wakeup"))
|
||||
process_sched_wakeup_event(data, machine, event, cpu, timestamp, thread);
|
||||
if (!strcmp(event->name, "sched_wakeup_new"))
|
||||
process_sched_wakeup_event(data, machine, event, cpu, timestamp, thread);
|
||||
if (!strcmp(event->name, "sched_process_fork"))
|
||||
process_sched_fork_event(data, event, cpu, timestamp, thread);
|
||||
if (!strcmp(event->name, "sched_process_exit"))
|
||||
process_sched_exit_event(event, cpu, timestamp, thread);
|
||||
if (!strcmp(event->name, "sched_migrate_task"))
|
||||
process_sched_migrate_task_event(data, machine, event, cpu, timestamp, thread);
|
||||
}
|
||||
|
||||
static int process_sample_event(struct perf_tool *tool __used,
|
||||
union perf_event *event,
|
||||
struct perf_sample *sample,
|
||||
struct perf_evsel *evsel,
|
||||
struct machine *machine)
|
||||
{
|
||||
struct thread *thread;
|
||||
|
||||
if (!(evsel->attr.sample_type & PERF_SAMPLE_RAW))
|
||||
return 0;
|
||||
|
||||
thread = machine__findnew_thread(machine, sample->pid);
|
||||
if (thread == NULL) {
|
||||
pr_debug("problem processing %d event, skipping it.\n",
|
||||
event->header.type);
|
||||
pr_debug("problem processing %s event, skipping it.\n",
|
||||
evsel->name);
|
||||
return -1;
|
||||
}
|
||||
|
||||
dump_printf(" ... thread: %s:%d\n", thread->comm, thread->pid);
|
||||
evsel->hists.stats.total_period += sample->period;
|
||||
hists__inc_nr_events(&evsel->hists, PERF_RECORD_SAMPLE);
|
||||
|
||||
if (profile_cpu != -1 && profile_cpu != (int)sample->cpu)
|
||||
return 0;
|
||||
if (evsel->handler.func != NULL) {
|
||||
tracepoint_handler f = evsel->handler.func;
|
||||
|
||||
process_raw_event(event, machine, sample->raw_data, sample->cpu,
|
||||
sample->time, thread);
|
||||
if (evsel->handler.data == NULL)
|
||||
evsel->handler.data = trace_find_event(evsel->attr.config);
|
||||
|
||||
f(tool, evsel->handler.data, sample, machine, thread);
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static struct perf_tool perf_sched = {
|
||||
.sample = process_sample_event,
|
||||
.sample = perf_sched__process_tracepoint_sample,
|
||||
.comm = perf_event__process_comm,
|
||||
.lost = perf_event__process_lost,
|
||||
.fork = perf_event__process_task,
|
||||
|
|
@ -1643,11 +1630,23 @@ static struct perf_tool perf_sched = {
|
|||
static void read_events(bool destroy, struct perf_session **psession)
|
||||
{
|
||||
int err = -EINVAL;
|
||||
const struct perf_evsel_str_handler handlers[] = {
|
||||
{ "sched:sched_switch", process_sched_switch_event, },
|
||||
{ "sched:sched_stat_runtime", process_sched_runtime_event, },
|
||||
{ "sched:sched_wakeup", process_sched_wakeup_event, },
|
||||
{ "sched:sched_wakeup_new", process_sched_wakeup_event, },
|
||||
{ "sched:sched_process_fork", process_sched_fork_event, },
|
||||
{ "sched:sched_process_exit", process_sched_exit_event, },
|
||||
{ "sched:sched_migrate_task", process_sched_migrate_task_event, },
|
||||
};
|
||||
struct perf_session *session = perf_session__new(input_name, O_RDONLY,
|
||||
0, false, &perf_sched);
|
||||
if (session == NULL)
|
||||
die("No Memory");
|
||||
|
||||
err = perf_evlist__set_tracepoints_handlers_array(session->evlist, handlers);
|
||||
assert(err == 0);
|
||||
|
||||
if (perf_session__has_traces(session, "record -R")) {
|
||||
err = perf_session__process_events(session, &perf_sched);
|
||||
if (err)
|
||||
|
|
|
|||
|
|
@ -207,6 +207,48 @@ int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
|
|||
return err;
|
||||
}
|
||||
|
||||
static struct perf_evsel *
|
||||
perf_evlist__find_tracepoint_by_id(struct perf_evlist *evlist, int id)
|
||||
{
|
||||
struct perf_evsel *evsel;
|
||||
|
||||
list_for_each_entry(evsel, &evlist->entries, node) {
|
||||
if (evsel->attr.type == PERF_TYPE_TRACEPOINT &&
|
||||
(int)evsel->attr.config == id)
|
||||
return evsel;
|
||||
}
|
||||
|
||||
return NULL;
|
||||
}
|
||||
|
||||
int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
|
||||
const struct perf_evsel_str_handler *assocs,
|
||||
size_t nr_assocs)
|
||||
{
|
||||
struct perf_evsel *evsel;
|
||||
int err;
|
||||
size_t i;
|
||||
|
||||
for (i = 0; i < nr_assocs; i++) {
|
||||
err = trace_event__id(assocs[i].name);
|
||||
if (err < 0)
|
||||
goto out;
|
||||
|
||||
evsel = perf_evlist__find_tracepoint_by_id(evlist, err);
|
||||
if (evsel == NULL)
|
||||
continue;
|
||||
|
||||
err = -EEXIST;
|
||||
if (evsel->handler.func != NULL)
|
||||
goto out;
|
||||
evsel->handler.func = assocs[i].handler;
|
||||
}
|
||||
|
||||
err = 0;
|
||||
out:
|
||||
return err;
|
||||
}
|
||||
|
||||
void perf_evlist__disable(struct perf_evlist *evlist)
|
||||
{
|
||||
int cpu, thread;
|
||||
|
|
|
|||
|
|
@ -36,6 +36,11 @@ struct perf_evlist {
|
|||
struct perf_evsel *selected;
|
||||
};
|
||||
|
||||
struct perf_evsel_str_handler {
|
||||
const char *name;
|
||||
void *handler;
|
||||
};
|
||||
|
||||
struct perf_evsel;
|
||||
|
||||
struct perf_evlist *perf_evlist__new(struct cpu_map *cpus,
|
||||
|
|
@ -51,6 +56,9 @@ int perf_evlist__add_attrs(struct perf_evlist *evlist,
|
|||
struct perf_event_attr *attrs, size_t nr_attrs);
|
||||
int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
|
||||
const char *tracepoints[], size_t nr_tracepoints);
|
||||
int perf_evlist__set_tracepoints_handlers(struct perf_evlist *evlist,
|
||||
const struct perf_evsel_str_handler *assocs,
|
||||
size_t nr_assocs);
|
||||
|
||||
#define perf_evlist__add_attrs_array(evlist, array) \
|
||||
perf_evlist__add_attrs(evlist, array, ARRAY_SIZE(array))
|
||||
|
|
@ -58,6 +66,9 @@ int perf_evlist__add_tracepoints(struct perf_evlist *evlist,
|
|||
#define perf_evlist__add_tracepoints_array(evlist, array) \
|
||||
perf_evlist__add_tracepoints(evlist, array, ARRAY_SIZE(array))
|
||||
|
||||
#define perf_evlist__set_tracepoints_handlers_array(evlist, array) \
|
||||
perf_evlist__set_tracepoints_handlers(evlist, array, ARRAY_SIZE(array))
|
||||
|
||||
void perf_evlist__id_add(struct perf_evlist *evlist, struct perf_evsel *evsel,
|
||||
int cpu, int thread, u64 id);
|
||||
|
||||
|
|
|
|||
|
|
@ -61,6 +61,10 @@ struct perf_evsel {
|
|||
off_t id_offset;
|
||||
};
|
||||
struct cgroup_sel *cgrp;
|
||||
struct {
|
||||
void *func;
|
||||
void *data;
|
||||
} handler;
|
||||
bool supported;
|
||||
};
|
||||
|
||||
|
|
|
|||
|
|
@ -1,8 +1,13 @@
|
|||
#ifndef __PERF_TOOL_H
|
||||
#define __PERF_TOOL_H
|
||||
|
||||
#include <stdbool.h>
|
||||
|
||||
struct perf_session;
|
||||
union perf_event;
|
||||
struct perf_evlist;
|
||||
struct perf_evsel;
|
||||
struct perf_sample;
|
||||
struct perf_tool;
|
||||
struct machine;
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue