perf stat: Enable counters when collecting process-wide or system-wide data

Command 'perf stat' doesn't enable counters when collecting an
existing (by -p) process or system-wide statistics. Fix the
issue.

Change the condition of fork/exec subcommand. If there is a
subcommand parameter, perf always forks/execs it. The usage
example is:

 # perf stat -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 use CTRL+C to stop it without
precise time clock.

Another issue is 'perf stat -a' consumes 100% time of a full
single logical cpu. It has a bad impact on running workload.

Fix it by adding a sleep(1) in the while(!done) loop in function
run_perf_stat.

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: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Jes Sorensen <Jes.Sorensen@redhat.com>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: Zachary Amsden <zamsden@redhat.com>
Cc: <zhiteng.huang@intel.com>
LKML-Reference: <1268922965-14774-1-git-send-email-acme@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 95db31cff6fdbb63e714dc0725998d7ef76103ea..5f41244cbbf2d5ce0f506f7b474a98c6db666628 100644 (file)
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -159,8 +159,10 @@ static void create_perf_stat_counter(int counter, int pid)
                }
        } else {
                attr->inherit        = inherit;
-               attr->disabled       = 1;
-               attr->enable_on_exec = 1;
+               if (target_pid == -1) {
+                       attr->disabled = 1;
+                       attr->enable_on_exec = 1;
+               }
 
                fd[0][counter] = sys_perf_event_open(attr, pid, -1, -1, 0);
                if (fd[0][counter] < 0 && verbose)
@@ -251,9 +253,9 @@ static int run_perf_stat(int argc __used, const char **argv)
        unsigned long long t0, t1;
        int status = 0;
        int counter;
-       int pid = target_pid;
+       int pid;
        int child_ready_pipe[2], go_pipe[2];
-       const bool forks = (target_pid == -1 && argc > 0);
+       const bool forks = (argc > 0);
        char buf;
 
        if (!system_wide)
@@ -265,10 +267,10 @@ static int run_perf_stat(int argc __used, const char **argv)
        }
 
        if (forks) {
-               if ((pid = fork()) < 0)
+               if ((child_pid = fork()) < 0)
                        perror("failed to fork");
 
-               if (!pid) {
+               if (!child_pid) {
                        close(child_ready_pipe[0]);
                        close(go_pipe[1]);
                        fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
@@ -297,8 +299,6 @@ static int run_perf_stat(int argc __used, const char **argv)
                        exit(-1);
                }
 
-               child_pid = pid;
-
                /*
                 * Wait for the child to be ready to exec.
                 */
@@ -309,6 +309,10 @@ static int run_perf_stat(int argc __used, const char **argv)
                close(child_ready_pipe[0]);
        }
 
+       if (target_pid == -1)
+               pid = child_pid;
+       else
+               pid = target_pid;
        for (counter = 0; counter < nr_counters; counter++)
                create_perf_stat_counter(counter, pid);
 
@@ -321,7 +325,7 @@ static int run_perf_stat(int argc __used, const char **argv)
                close(go_pipe[1]);
                wait(&status);
        } else {
-               while(!done);
+               while(!done) sleep(1);
        }
 
        t1 = rdclock();
@@ -459,7 +463,7 @@ static volatile int signr = -1;
 
 static void skip_signal(int signo)
 {
-       if(target_pid != -1)
+       if(child_pid == -1)
                done = 1;
 
        signr = signo;