perf record: Enable counters only when kernel is execing subcommand
'perf record' starts counters before subcommand is execed, so
the statistics is not precise because it includes data of some
preparation steps. I fix it with the patch.
In addition, change the condition to fork/exec subcommand. If
there is a subcommand parameter, perf always fork/exec it. The
usage example is:
# perf record -f -a sleep 10
So this command could collect statistics for 10 seconds
precisely. User still could stop it by CTRL+C. Without the new
capability, user could only input CTRL+C to stop it without
precise time clock.
Signed-off-by: Zhang Yanmin <yanmin_zhang@linux.intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Sheng Yang <sheng@linux.intel.com>
Cc: oerg Roedel <joro@8bytes.org>
Cc: Jes Sorensen <Jes.Sorensen@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: <zhiteng.huang@intel.com>
Cc: Zachary Amsden <zamsden@redhat.com>
LKML-Reference: <1268922965-14774-2-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 962cdbf..e2b35ad 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -225,7 +225,7 @@
return h_attr;
}
-static void create_counter(int counter, int cpu, pid_t pid, bool forks)
+static void create_counter(int counter, int cpu, pid_t pid)
{
char *filter = filters[counter];
struct perf_event_attr *attr = attrs + counter;
@@ -275,10 +275,10 @@
attr->mmap = track;
attr->comm = track;
attr->inherit = inherit;
- attr->disabled = 1;
-
- if (forks)
+ if (target_pid == -1 && !system_wide) {
+ attr->disabled = 1;
attr->enable_on_exec = 1;
+ }
try_again:
fd[nr_cpu][counter] = sys_perf_event_open(attr, pid, cpu, group_fd, 0);
@@ -380,17 +380,15 @@
exit(-1);
}
}
-
- ioctl(fd[nr_cpu][counter], PERF_EVENT_IOC_ENABLE);
}
-static void open_counters(int cpu, pid_t pid, bool forks)
+static void open_counters(int cpu, pid_t pid)
{
int counter;
group_fd = -1;
for (counter = 0; counter < nr_counters; counter++)
- create_counter(counter, cpu, pid, forks);
+ create_counter(counter, cpu, pid);
nr_cpu++;
}
@@ -425,7 +423,7 @@
int err;
unsigned long waking = 0;
int child_ready_pipe[2], go_pipe[2];
- const bool forks = target_pid == -1 && argc > 0;
+ const bool forks = argc > 0;
char buf;
page_size = sysconf(_SC_PAGE_SIZE);
@@ -496,13 +494,13 @@
atexit(atexit_header);
if (forks) {
- pid = fork();
+ child_pid = fork();
if (pid < 0) {
perror("failed to fork");
exit(-1);
}
- if (!pid) {
+ if (!child_pid) {
close(child_ready_pipe[0]);
close(go_pipe[1]);
fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
@@ -531,11 +529,6 @@
exit(-1);
}
- child_pid = pid;
-
- if (!system_wide)
- target_pid = pid;
-
close(child_ready_pipe[1]);
close(go_pipe[0]);
/*
@@ -548,13 +541,17 @@
close(child_ready_pipe[0]);
}
+ if (forks && target_pid == -1 && !system_wide)
+ pid = child_pid;
+ else
+ pid = target_pid;
if ((!system_wide && !inherit) || profile_cpu != -1) {
- open_counters(profile_cpu, target_pid, forks);
+ open_counters(profile_cpu, pid);
} else {
nr_cpus = read_cpu_map();
for (i = 0; i < nr_cpus; i++)
- open_counters(cpumap[i], target_pid, forks);
+ open_counters(cpumap[i], pid);
}
if (file_new) {