linux_dsm_epyc7002/tools/perf/builtin-inject.c
Andrew Vagin 26a031e136 perf inject: Merge sched_stat_* and sched_switch events
You may want to know where and how long a task is sleeping. A callchain
may be found in sched_switch and a time slice in stat_iowait, so I add
handler in perf inject for merging this events.

My code saves sched_switch event for each process and when it meets
stat_iowait, it reports the sched_switch event, because this event
contains a correct callchain. By another words it replaces all
stat_iowait events on proper sched_switch events.

I use the next sequence of commands for testing:

  perf record -e sched:sched_stat_sleep -e sched:sched_switch \
	      -e sched:sched_process_exit -g -o ~/perf.data.raw \
	      ~/test-program
  perf inject -v -s -i ~/perf.data.raw -o ~/perf.data
  perf report --stdio -i ~/perf.data
   100.00%	foo  [kernel.kallsyms]  [k] __schedule
               	|
                --- __schedule
                    schedule
                   |
                   |--79.75%-- schedule_hrtimeout_range_clock
                   |          schedule_hrtimeout_range
                   |          poll_schedule_timeout
                   |          do_select
                   |          core_sys_select
                   |          sys_select
                   |          system_call_fastpath
                   |          __select
                   |          __libc_start_main
                   |
                    --20.25%-- do_nanosleep
                              hrtimer_nanosleep
                              sys_nanosleep
                              system_call_fastpath
                              __GI___libc_nanosleep
                              __libc_start_main

 And here is test-program.c:

 #include<unistd.h>
 #include<time.h>
 #include<sys/select.h>

 int main()
 {
	struct timespec ts1;
	struct timeval tv1;
	int i;
	long s;

	for (i = 0; i <  10; i++) {
		ts1.tv_sec = 0;
		ts1.tv_nsec = 10000000;
		nanosleep(&ts1, NULL);

		tv1.tv_sec = 0;
		tv1.tv_usec = 40000;
		select(0, NULL, NULL, NULL,&tv1);
	}
	return 1;
 }

Signed-off-by: Andrew Vagin <avagin@openvz.org>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1344344165-369636-4-git-send-email-avagin@openvz.org
[ committer note: Made it use evsel->handler ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-26 11:22:25 -02:00

457 lines
11 KiB
C

/*
* builtin-inject.c
*
* Builtin inject command: Examine the live mode (stdin) event stream
* and repipe it to stdout while optionally injecting additional
* events into it.
*/
#include "builtin.h"
#include "perf.h"
#include "util/color.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/session.h"
#include "util/tool.h"
#include "util/debug.h"
#include "util/parse-options.h"
#include <linux/list.h>
struct perf_inject {
struct perf_tool tool;
bool build_ids;
bool sched_stat;
const char *input_name;
int pipe_output,
output;
u64 bytes_written;
struct list_head samples;
};
struct event_entry {
struct list_head node;
u32 tid;
union perf_event event[0];
};
static int perf_event__repipe_synth(struct perf_tool *tool,
union perf_event *event,
struct machine *machine __maybe_unused)
{
struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
uint32_t size;
void *buf = event;
size = event->header.size;
while (size) {
int ret = write(inject->output, buf, size);
if (ret < 0)
return -errno;
size -= ret;
buf += ret;
inject->bytes_written += ret;
}
return 0;
}
static int perf_event__repipe_op2_synth(struct perf_tool *tool,
union perf_event *event,
struct perf_session *session
__maybe_unused)
{
return perf_event__repipe_synth(tool, event, NULL);
}
static int perf_event__repipe_event_type_synth(struct perf_tool *tool,
union perf_event *event)
{
return perf_event__repipe_synth(tool, event, NULL);
}
static int perf_event__repipe_tracing_data_synth(union perf_event *event,
struct perf_session *session
__maybe_unused)
{
return perf_event__repipe_synth(NULL, event, NULL);
}
static int perf_event__repipe_attr(union perf_event *event,
struct perf_evlist **pevlist __maybe_unused)
{
int ret;
ret = perf_event__process_attr(event, pevlist);
if (ret)
return ret;
return perf_event__repipe_synth(NULL, event, NULL);
}
static int perf_event__repipe(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample __maybe_unused,
struct machine *machine)
{
return perf_event__repipe_synth(tool, event, machine);
}
typedef int (*inject_handler)(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine);
static int perf_event__repipe_sample(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine)
{
if (evsel->handler.func) {
inject_handler f = evsel->handler.func;
return f(tool, event, sample, evsel, machine);
}
return perf_event__repipe_synth(tool, event, machine);
}
static int perf_event__repipe_mmap(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine)
{
int err;
err = perf_event__process_mmap(tool, event, sample, machine);
perf_event__repipe(tool, event, sample, machine);
return err;
}
static int perf_event__repipe_fork(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct machine *machine)
{
int err;
err = perf_event__process_fork(tool, event, sample, machine);
perf_event__repipe(tool, event, sample, machine);
return err;
}
static int perf_event__repipe_tracing_data(union perf_event *event,
struct perf_session *session)
{
int err;
perf_event__repipe_synth(NULL, event, NULL);
err = perf_event__process_tracing_data(event, session);
return err;
}
static int dso__read_build_id(struct dso *self)
{
if (self->has_build_id)
return 0;
if (filename__read_build_id(self->long_name, self->build_id,
sizeof(self->build_id)) > 0) {
self->has_build_id = true;
return 0;
}
return -1;
}
static int dso__inject_build_id(struct dso *self, struct perf_tool *tool,
struct machine *machine)
{
u16 misc = PERF_RECORD_MISC_USER;
int err;
if (dso__read_build_id(self) < 0) {
pr_debug("no build_id found for %s\n", self->long_name);
return -1;
}
if (self->kernel)
misc = PERF_RECORD_MISC_KERNEL;
err = perf_event__synthesize_build_id(tool, self, misc, perf_event__repipe,
machine);
if (err) {
pr_err("Can't synthesize build_id event for %s\n", self->long_name);
return -1;
}
return 0;
}
static int perf_event__inject_buildid(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel __maybe_unused,
struct machine *machine)
{
struct addr_location al;
struct thread *thread;
u8 cpumode;
cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
thread = machine__findnew_thread(machine, event->ip.pid);
if (thread == NULL) {
pr_err("problem processing %d event, skipping it.\n",
event->header.type);
goto repipe;
}
thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
event->ip.ip, &al);
if (al.map != NULL) {
if (!al.map->dso->hit) {
al.map->dso->hit = 1;
if (map__load(al.map, NULL) >= 0) {
dso__inject_build_id(al.map->dso, tool, machine);
/*
* If this fails, too bad, let the other side
* account this as unresolved.
*/
} else {
#ifdef LIBELF_SUPPORT
pr_warning("no symbols found in %s, maybe "
"install a debug package?\n",
al.map->dso->long_name);
#endif
}
}
}
repipe:
perf_event__repipe(tool, event, sample, machine);
return 0;
}
static int perf_inject__sched_process_exit(struct perf_tool *tool,
union perf_event *event __maybe_unused,
struct perf_sample *sample,
struct perf_evsel *evsel __maybe_unused,
struct machine *machine __maybe_unused)
{
struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
struct event_entry *ent;
list_for_each_entry(ent, &inject->samples, node) {
if (sample->tid == ent->tid) {
list_del_init(&ent->node);
free(ent);
break;
}
}
return 0;
}
static int perf_inject__sched_switch(struct perf_tool *tool,
union perf_event *event,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine)
{
struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
struct event_entry *ent;
perf_inject__sched_process_exit(tool, event, sample, evsel, machine);
ent = malloc(event->header.size + sizeof(struct event_entry));
if (ent == NULL) {
color_fprintf(stderr, PERF_COLOR_RED,
"Not enough memory to process sched switch event!");
return -1;
}
ent->tid = sample->tid;
memcpy(&ent->event, event, event->header.size);
list_add(&ent->node, &inject->samples);
return 0;
}
static int perf_inject__sched_stat(struct perf_tool *tool,
union perf_event *event __maybe_unused,
struct perf_sample *sample,
struct perf_evsel *evsel,
struct machine *machine)
{
struct event_entry *ent;
union perf_event *event_sw;
struct perf_sample sample_sw;
struct perf_inject *inject = container_of(tool, struct perf_inject, tool);
u32 pid = perf_evsel__intval(evsel, sample, "pid");
list_for_each_entry(ent, &inject->samples, node) {
if (pid == ent->tid)
goto found;
}
return 0;
found:
event_sw = &ent->event[0];
perf_evsel__parse_sample(evsel, event_sw, &sample_sw);
sample_sw.period = sample->period;
sample_sw.time = sample->time;
perf_event__synthesize_sample(event_sw, evsel->attr.sample_type,
&sample_sw, false);
return perf_event__repipe(tool, event_sw, &sample_sw, machine);
}
extern volatile int session_done;
static void sig_handler(int sig __maybe_unused)
{
session_done = 1;
}
static int perf_evsel__check_stype(struct perf_evsel *evsel,
u64 sample_type, const char *sample_msg)
{
struct perf_event_attr *attr = &evsel->attr;
const char *name = perf_evsel__name(evsel);
if (!(attr->sample_type & sample_type)) {
pr_err("Samples for %s event do not have %s attribute set.",
name, sample_msg);
return -EINVAL;
}
return 0;
}
static int __cmd_inject(struct perf_inject *inject)
{
struct perf_session *session;
int ret = -EINVAL;
signal(SIGINT, sig_handler);
if (inject->build_ids) {
inject->tool.sample = perf_event__inject_buildid;
inject->tool.mmap = perf_event__repipe_mmap;
inject->tool.fork = perf_event__repipe_fork;
inject->tool.tracing_data = perf_event__repipe_tracing_data;
}
session = perf_session__new(inject->input_name, O_RDONLY, false, true, &inject->tool);
if (session == NULL)
return -ENOMEM;
if (inject->sched_stat) {
struct perf_evsel *evsel;
inject->tool.ordered_samples = true;
list_for_each_entry(evsel, &session->evlist->entries, node) {
const char *name = perf_evsel__name(evsel);
if (!strcmp(name, "sched:sched_switch")) {
if (perf_evsel__check_stype(evsel, PERF_SAMPLE_TID, "TID"))
return -EINVAL;
evsel->handler.func = perf_inject__sched_switch;
} else if (!strcmp(name, "sched:sched_process_exit"))
evsel->handler.func = perf_inject__sched_process_exit;
else if (!strncmp(name, "sched:sched_stat_", 17))
evsel->handler.func = perf_inject__sched_stat;
}
}
if (!inject->pipe_output)
lseek(inject->output, session->header.data_offset, SEEK_SET);
ret = perf_session__process_events(session, &inject->tool);
if (!inject->pipe_output) {
session->header.data_size = inject->bytes_written;
perf_session__write_header(session, session->evlist, inject->output, true);
}
perf_session__delete(session);
return ret;
}
int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
{
struct perf_inject inject = {
.tool = {
.sample = perf_event__repipe_sample,
.mmap = perf_event__repipe,
.comm = perf_event__repipe,
.fork = perf_event__repipe,
.exit = perf_event__repipe,
.lost = perf_event__repipe,
.read = perf_event__repipe_sample,
.throttle = perf_event__repipe,
.unthrottle = perf_event__repipe,
.attr = perf_event__repipe_attr,
.event_type = perf_event__repipe_event_type_synth,
.tracing_data = perf_event__repipe_tracing_data_synth,
.build_id = perf_event__repipe_op2_synth,
},
.input_name = "-",
.samples = LIST_HEAD_INIT(inject.samples),
};
const char *output_name = "-";
const struct option options[] = {
OPT_BOOLEAN('b', "build-ids", &inject.build_ids,
"Inject build-ids into the output stream"),
OPT_STRING('i', "input", &inject.input_name, "file",
"input file name"),
OPT_STRING('o', "output", &output_name, "file",
"output file name"),
OPT_BOOLEAN('s', "sched-stat", &inject.sched_stat,
"Merge sched-stat and sched-switch for getting events "
"where and how long tasks slept"),
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show build ids, etc)"),
OPT_END()
};
const char * const inject_usage[] = {
"perf inject [<options>]",
NULL
};
argc = parse_options(argc, argv, options, inject_usage, 0);
/*
* Any (unrecognized) arguments left?
*/
if (argc)
usage_with_options(inject_usage, options);
if (!strcmp(output_name, "-")) {
inject.pipe_output = 1;
inject.output = STDOUT_FILENO;
} else {
inject.output = open(output_name, O_CREAT | O_WRONLY | O_TRUNC,
S_IRUSR | S_IWUSR);
if (inject.output < 0) {
perror("failed to create output file");
return -1;
}
}
if (symbol__init() < 0)
return -1;
return __cmd_inject(&inject);
}