summaryrefslogtreecommitdiff
path: root/tools/perf/builtin-stat.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/builtin-stat.c')
-rw-r--r--tools/perf/builtin-stat.c171
1 files changed, 102 insertions, 69 deletions
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 6d3eeac1ea25..2e03524a1de0 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -32,6 +32,7 @@
* Wu Fengguang <fengguang.wu@intel.com>
* Mike Galbraith <efault@gmx.de>
* Paul Mackerras <paulus@samba.org>
+ * Jaswinder Singh Rajput <jaswinder@kernel.org>
*
* Released under the GPL v2. (and only v2, not any later version)
*/
@@ -45,7 +46,7 @@
#include <sys/prctl.h>
#include <math.h>
-static struct perf_counter_attr default_attrs[MAX_COUNTERS] = {
+static struct perf_counter_attr default_attrs[] = {
{ .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK },
{ .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES},
@@ -59,42 +60,28 @@ static struct perf_counter_attr default_attrs[MAX_COUNTERS] = {
};
+#define MAX_RUN 100
+
static int system_wide = 0;
-static int inherit = 1;
static int verbose = 0;
-
-static int fd[MAX_NR_CPUS][MAX_COUNTERS];
-
-static int target_pid = -1;
static int nr_cpus = 0;
-static unsigned int page_size;
+static int run_idx = 0;
+static int run_count = 1;
+static int inherit = 1;
static int scale = 1;
+static int target_pid = -1;
+static int null_run = 0;
-static const unsigned int default_count[] = {
- 1000000,
- 1000000,
- 10000,
- 10000,
- 1000000,
- 10000,
-};
-
-#define MAX_RUN 100
-
-static int run_count = 1;
-static int run_idx = 0;
-
-static u64 event_res[MAX_RUN][MAX_COUNTERS][3];
-static u64 event_scaled[MAX_RUN][MAX_COUNTERS];
-
-//static u64 event_hist[MAX_RUN][MAX_COUNTERS][3];
-
+static int fd[MAX_NR_CPUS][MAX_COUNTERS];
static u64 runtime_nsecs[MAX_RUN];
static u64 walltime_nsecs[MAX_RUN];
static u64 runtime_cycles[MAX_RUN];
+static u64 event_res[MAX_RUN][MAX_COUNTERS][3];
+static u64 event_scaled[MAX_RUN][MAX_COUNTERS];
+
static u64 event_res_avg[MAX_COUNTERS][3];
static u64 event_res_noise[MAX_COUNTERS][3];
@@ -109,7 +96,10 @@ static u64 walltime_nsecs_noise;
static u64 runtime_cycles_avg;
static u64 runtime_cycles_noise;
-static void create_perf_stat_counter(int counter)
+#define ERR_PERF_OPEN \
+"Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n"
+
+static void create_perf_stat_counter(int counter, int pid)
{
struct perf_counter_attr *attr = attrs + counter;
@@ -119,20 +109,21 @@ static void create_perf_stat_counter(int counter)
if (system_wide) {
int cpu;
- for (cpu = 0; cpu < nr_cpus; cpu ++) {
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
fd[cpu][counter] = sys_perf_counter_open(attr, -1, cpu, -1, 0);
- if (fd[cpu][counter] < 0 && verbose) {
- printf("Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n", counter, fd[cpu][counter], strerror(errno));
- }
+ if (fd[cpu][counter] < 0 && verbose)
+ fprintf(stderr, ERR_PERF_OPEN, counter,
+ fd[cpu][counter], strerror(errno));
}
} else {
- attr->inherit = inherit;
- attr->disabled = 1;
-
- fd[0][counter] = sys_perf_counter_open(attr, 0, -1, -1, 0);
- if (fd[0][counter] < 0 && verbose) {
- printf("Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n", counter, fd[0][counter], strerror(errno));
- }
+ attr->inherit = inherit;
+ attr->disabled = 1;
+ attr->enable_on_exec = 1;
+
+ fd[0][counter] = sys_perf_counter_open(attr, pid, -1, -1, 0);
+ if (fd[0][counter] < 0 && verbose)
+ fprintf(stderr, ERR_PERF_OPEN, counter,
+ fd[0][counter], strerror(errno));
}
}
@@ -168,7 +159,7 @@ static void read_counter(int counter)
count[0] = count[1] = count[2] = 0;
nv = scale ? 3 : 1;
- for (cpu = 0; cpu < nr_cpus; cpu ++) {
+ for (cpu = 0; cpu < nr_cpus; cpu++) {
if (fd[cpu][counter] < 0)
continue;
@@ -215,32 +206,67 @@ static int run_perf_stat(int argc, const char **argv)
int status = 0;
int counter;
int pid;
+ int child_ready_pipe[2], go_pipe[2];
+ char buf;
if (!system_wide)
nr_cpus = 1;
- for (counter = 0; counter < nr_counters; counter++)
- create_perf_stat_counter(counter);
-
- /*
- * Enable counters and exec the command:
- */
- t0 = rdclock();
- prctl(PR_TASK_PERF_COUNTERS_ENABLE);
+ if (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0) {
+ perror("failed to create pipes");
+ exit(1);
+ }
if ((pid = fork()) < 0)
perror("failed to fork");
if (!pid) {
- if (execvp(argv[0], (char **)argv)) {
- perror(argv[0]);
- exit(-1);
- }
+ close(child_ready_pipe[0]);
+ 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.
+ */
+ read(go_pipe[0], &buf, 1);
+
+ execvp(argv[0], (char **)argv);
+
+ perror(argv[0]);
+ exit(-1);
}
+ /*
+ * Wait for the child to be ready to exec.
+ */
+ close(child_ready_pipe[1]);
+ close(go_pipe[0]);
+ read(child_ready_pipe[0], &buf, 1);
+ close(child_ready_pipe[0]);
+
+ for (counter = 0; counter < nr_counters; counter++)
+ create_perf_stat_counter(counter, pid);
+
+ /*
+ * Enable counters and exec the command:
+ */
+ t0 = rdclock();
+
+ close(go_pipe[1]);
wait(&status);
- prctl(PR_TASK_PERF_COUNTERS_DISABLE);
t1 = rdclock();
walltime_nsecs[run_idx] = t1 - t0;
@@ -262,7 +288,7 @@ static void nsec_printout(int counter, u64 *count, u64 *noise)
{
double msecs = (double)count[0] / 1000000;
- fprintf(stderr, " %14.6f %-20s", msecs, event_name(counter));
+ fprintf(stderr, " %14.6f %-24s", msecs, event_name(counter));
if (attrs[counter].type == PERF_TYPE_SOFTWARE &&
attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK) {
@@ -276,7 +302,7 @@ static void nsec_printout(int counter, u64 *count, u64 *noise)
static void abs_printout(int counter, u64 *count, u64 *noise)
{
- fprintf(stderr, " %14Ld %-20s", count[0], event_name(counter));
+ fprintf(stderr, " %14Ld %-24s", count[0], event_name(counter));
if (runtime_cycles_avg &&
attrs[counter].type == PERF_TYPE_HARDWARE &&
@@ -306,7 +332,7 @@ static void print_counter(int counter)
scaled = event_scaled_avg[counter];
if (scaled == -1) {
- fprintf(stderr, " %14s %-20s\n",
+ fprintf(stderr, " %14s %-24s\n",
"<not counted>", event_name(counter));
return;
}
@@ -364,8 +390,11 @@ static void calc_avg(void)
event_res_avg[j]+1, event_res[i][j]+1);
update_avg("counter/2", j,
event_res_avg[j]+2, event_res[i][j]+2);
- update_avg("scaled", j,
- event_scaled_avg + j, event_scaled[i]+j);
+ if (event_scaled[i][j] != -1)
+ update_avg("scaled", j,
+ event_scaled_avg + j, event_scaled[i]+j);
+ else
+ event_scaled_avg[j] = -1;
}
}
runtime_nsecs_avg /= run_count;
@@ -429,11 +458,14 @@ static void print_stat(int argc, const char **argv)
for (counter = 0; counter < nr_counters; counter++)
print_counter(counter);
-
fprintf(stderr, "\n");
- fprintf(stderr, " %14.9f seconds time elapsed.\n",
+ fprintf(stderr, " %14.9f seconds time elapsed",
(double)walltime_nsecs_avg/1e9);
- fprintf(stderr, "\n");
+ if (run_count > 1) {
+ fprintf(stderr, " ( +- %7.3f%% )",
+ 100.0*(double)walltime_nsecs_noise/(double)walltime_nsecs_avg);
+ }
+ fprintf(stderr, "\n\n");
}
static volatile int signr = -1;
@@ -466,13 +498,15 @@ static const struct option options[] = {
OPT_INTEGER('p', "pid", &target_pid,
"stat events on existing pid"),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
- "system-wide collection from all CPUs"),
+ "system-wide collection from all CPUs"),
OPT_BOOLEAN('S', "scale", &scale,
- "scale/normalize counters"),
+ "scale/normalize counters"),
OPT_BOOLEAN('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
OPT_INTEGER('r', "repeat", &run_count,
"repeat command and print average + stddev (max: 100)"),
+ OPT_BOOLEAN('n', "null", &null_run,
+ "null run - dont start any counters"),
OPT_END()
};
@@ -480,18 +514,17 @@ int cmd_stat(int argc, const char **argv, const char *prefix)
{
int status;
- page_size = sysconf(_SC_PAGE_SIZE);
-
- memcpy(attrs, default_attrs, sizeof(attrs));
-
argc = parse_options(argc, argv, options, stat_usage, 0);
if (!argc)
usage_with_options(stat_usage, options);
if (run_count <= 0 || run_count > MAX_RUN)
usage_with_options(stat_usage, options);
- if (!nr_counters)
- nr_counters = 8;
+ /* Set attrs and nr_counters if no event is selected and !null_run */
+ if (!null_run && !nr_counters) {
+ memcpy(attrs, default_attrs, sizeof(default_attrs));
+ nr_counters = ARRAY_SIZE(default_attrs);
+ }
nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
assert(nr_cpus <= MAX_NR_CPUS);
@@ -511,7 +544,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix)
status = 0;
for (run_idx = 0; run_idx < run_count; run_idx++) {
if (run_count != 1 && verbose)
- fprintf(stderr, "[ perf stat: executing run #%d ... ]\n", run_idx+1);
+ fprintf(stderr, "[ perf stat: executing run #%d ... ]\n", run_idx + 1);
status = run_perf_stat(argc, argv);
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-05 22:04:51 +0000