perf record: Properly synchronize child creation

Remove that ugly usleep and provide proper serialization between
parent and child just like perf-stat does.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: fweisbec@gmail.com
Cc: Paul Mackerras <paulus@samba.org>
LKML-Reference: <20091216165904.908184135@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Peter Zijlstra 2009-12-16 17:55:55 +01:00 committed by Ingo Molnar
parent f4c4176f21
commit 856e96608a
1 changed files with 72 additions and 39 deletions

View File

@ -402,7 +402,7 @@ static void atexit_header(void)
perf_header__write(&session->header, output, true); perf_header__write(&session->header, output, true);
} }
static int __cmd_record(int argc, const char **argv) static int __cmd_record(int argc __used, const char **argv)
{ {
int i, counter; int i, counter;
struct stat st; struct stat st;
@ -410,6 +410,8 @@ static int __cmd_record(int argc, const char **argv)
int flags; int flags;
int err; int err;
unsigned long waking = 0; unsigned long waking = 0;
int child_ready_pipe[2], go_pipe[2];
char buf;
page_size = sysconf(_SC_PAGE_SIZE); page_size = sysconf(_SC_PAGE_SIZE);
nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
@ -420,6 +422,11 @@ static int __cmd_record(int argc, const char **argv)
signal(SIGCHLD, sig_handler); signal(SIGCHLD, sig_handler);
signal(SIGINT, sig_handler); signal(SIGINT, sig_handler);
if (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0) {
perror("failed to create pipes");
exit(-1);
}
if (!stat(output_name, &st) && st.st_size) { if (!stat(output_name, &st) && st.st_size) {
if (!force) { if (!force) {
if (!append_file) { if (!append_file) {
@ -476,20 +483,66 @@ static int __cmd_record(int argc, const char **argv)
atexit(atexit_header); atexit(atexit_header);
if (!system_wide) { if (target_pid == -1) {
pid = target_pid; pid = fork();
if (pid == -1) if (pid < 0) {
pid = getpid(); perror("failed to fork");
exit(-1);
}
open_counters(profile_cpu, pid); if (!pid) {
} else { close(child_ready_pipe[0]);
if (profile_cpu != -1) { close(go_pipe[1]);
fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
/*
* Do a dummy execvp to get the PLT entry resolved,
* so we avoid the resolver overhead on the real
* execvp call.
*/
execvp("", (char **)argv);
/*
* Tell the parent we're ready to go
*/
close(child_ready_pipe[1]);
/*
* Wait until the parent tells us to go.
*/
if (read(go_pipe[0], &buf, 1) == -1)
perror("unable to read pipe");
execvp(argv[0], (char **)argv);
perror(argv[0]);
exit(-1);
}
child_pid = pid;
if (!system_wide)
target_pid = pid;
close(child_ready_pipe[1]);
close(go_pipe[0]);
/*
* wait for child to settle
*/
if (read(child_ready_pipe[0], &buf, 1) == -1) {
perror("unable to read pipe");
exit(-1);
}
close(child_ready_pipe[0]);
}
if (!system_wide || profile_cpu != -1) {
open_counters(profile_cpu, target_pid); open_counters(profile_cpu, target_pid);
} else { } else {
for (i = 0; i < nr_cpus; i++) for (i = 0; i < nr_cpus; i++)
open_counters(i, target_pid); open_counters(i, target_pid);
} }
}
if (file_new) { if (file_new) {
err = perf_header__write(&session->header, output, false); err = perf_header__write(&session->header, output, false);
@ -503,31 +556,6 @@ static int __cmd_record(int argc, const char **argv)
else else
event__synthesize_threads(process_synthesized_event, session); event__synthesize_threads(process_synthesized_event, session);
if (target_pid == -1 && argc) {
pid = fork();
if (pid < 0)
die("failed to fork");
if (!pid) {
if (execvp(argv[0], (char **)argv)) {
perror(argv[0]);
exit(-1);
}
} else {
/*
* Wait a bit for the execv'ed child to appear
* and be updated in /proc
* FIXME: Do you know a less heuristical solution?
*/
usleep(1000);
event__synthesize_thread(pid,
process_synthesized_event,
session);
}
child_pid = pid;
}
if (realtime_prio) { if (realtime_prio) {
struct sched_param param; struct sched_param param;
@ -538,6 +566,11 @@ static int __cmd_record(int argc, const char **argv)
} }
} }
/*
* Let the child rip
*/
close(go_pipe[1]);
for (;;) { for (;;) {
int hits = samples; int hits = samples;
@ -634,7 +667,7 @@ int cmd_record(int argc, const char **argv, const char *prefix __used)
argc = parse_options(argc, argv, options, record_usage, argc = parse_options(argc, argv, options, record_usage,
PARSE_OPT_STOP_AT_NON_OPTION); PARSE_OPT_STOP_AT_NON_OPTION);
if (!argc && target_pid == -1 && !system_wide) if (!argc && target_pid == -1 && (!system_wide || profile_cpu == -1))
usage_with_options(record_usage, options); usage_with_options(record_usage, options);
symbol__init(); symbol__init();