#include "util/parse-events.h"
#include "util/event.h"
#include "util/debug.h"
+#include "util/header.h"
+#include "util/cpumap.h"
+#include "util/thread.h"
#include <sys/prctl.h>
#include <math.h>
-static struct perf_counter_attr default_attrs[] = {
+static struct perf_event_attr default_attrs[] = {
- { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK },
- { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES},
- { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS },
- { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS },
+ { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK },
+ { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES },
+ { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS },
+ { .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS },
- { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES },
- { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS },
- { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES},
- { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES },
+ { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES },
+ { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS },
+ { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
+ { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES },
+ { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_REFERENCES },
+ { .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CACHE_MISSES },
};
-static int system_wide = 0;
+static bool system_wide = false;
static unsigned int nr_cpus = 0;
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 bool no_inherit = false;
+static bool scale = true;
+static pid_t target_pid = -1;
+static pid_t target_tid = -1;
+static pid_t *all_tids = NULL;
+static int thread_num = 0;
+static pid_t child_pid = -1;
+static bool null_run = false;
-static int fd[MAX_NR_CPUS][MAX_COUNTERS];
+static int *fd[MAX_NR_CPUS][MAX_COUNTERS];
static int event_scaled[MAX_COUNTERS];
+static volatile int done = 0;
+
struct stats
{
double n, mean, M2;
struct stats runtime_nsecs_stats;
struct stats walltime_nsecs_stats;
struct stats runtime_cycles_stats;
+struct stats runtime_branches_stats;
#define MATCH_EVENT(t, c, counter) \
(attrs[counter].type == PERF_TYPE_##t && \
attrs[counter].config == PERF_COUNT_##c)
#define ERR_PERF_OPEN \
-"Error: counter %d, sys_perf_counter_open() syscall returned with %d (%s)\n"
+"Error: counter %d, sys_perf_event_open() syscall returned with %d (%s)\n"
-static void create_perf_stat_counter(int counter, int pid)
+static int create_perf_stat_counter(int counter)
{
- struct perf_counter_attr *attr = attrs + counter;
+ struct perf_event_attr *attr = attrs + counter;
+ int thread;
+ int ncreated = 0;
if (scale)
attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
unsigned int 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)
- fprintf(stderr, ERR_PERF_OPEN, counter,
- fd[cpu][counter], strerror(errno));
+ fd[cpu][counter][0] = sys_perf_event_open(attr,
+ -1, cpumap[cpu], -1, 0);
+ if (fd[cpu][counter][0] < 0)
+ pr_debug(ERR_PERF_OPEN, counter,
+ fd[cpu][counter][0], strerror(errno));
+ else
+ ++ncreated;
}
} else {
- 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));
+ attr->inherit = !no_inherit;
+ if (target_pid == -1 && target_tid == -1) {
+ attr->disabled = 1;
+ attr->enable_on_exec = 1;
+ }
+ for (thread = 0; thread < thread_num; thread++) {
+ fd[0][counter][thread] = sys_perf_event_open(attr,
+ all_tids[thread], -1, -1, 0);
+ if (fd[0][counter][thread] < 0)
+ pr_debug(ERR_PERF_OPEN, counter,
+ fd[0][counter][thread],
+ strerror(errno));
+ else
+ ++ncreated;
+ }
}
+
+ return ncreated;
}
/*
unsigned int cpu;
size_t res, nv;
int scaled;
- int i;
+ int i, thread;
count[0] = count[1] = count[2] = 0;
nv = scale ? 3 : 1;
for (cpu = 0; cpu < nr_cpus; cpu++) {
- if (fd[cpu][counter] < 0)
- continue;
-
- res = read(fd[cpu][counter], single_count, nv * sizeof(u64));
- assert(res == nv * sizeof(u64));
-
- close(fd[cpu][counter]);
- fd[cpu][counter] = -1;
-
- count[0] += single_count[0];
- if (scale) {
- count[1] += single_count[1];
- count[2] += single_count[2];
+ for (thread = 0; thread < thread_num; thread++) {
+ if (fd[cpu][counter][thread] < 0)
+ continue;
+
+ res = read(fd[cpu][counter][thread],
+ single_count, nv * sizeof(u64));
+ assert(res == nv * sizeof(u64));
+
+ close(fd[cpu][counter][thread]);
+ fd[cpu][counter][thread] = -1;
+
+ count[0] += single_count[0];
+ if (scale) {
+ count[1] += single_count[1];
+ count[2] += single_count[2];
+ }
}
}
update_stats(&runtime_nsecs_stats, count[0]);
if (MATCH_EVENT(HARDWARE, HW_CPU_CYCLES, counter))
update_stats(&runtime_cycles_stats, count[0]);
+ if (MATCH_EVENT(HARDWARE, HW_BRANCH_INSTRUCTIONS, counter))
+ update_stats(&runtime_branches_stats, count[0]);
}
static int run_perf_stat(int argc __used, const char **argv)
{
unsigned long long t0, t1;
int status = 0;
- int counter;
- int pid;
+ int counter, ncreated = 0;
int child_ready_pipe[2], go_pipe[2];
+ const bool forks = (argc > 0);
char buf;
if (!system_wide)
nr_cpus = 1;
- if (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0) {
+ if (forks && (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) {
- close(child_ready_pipe[0]);
- close(go_pipe[1]);
- fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
+ if (forks) {
+ if ((child_pid = fork()) < 0)
+ perror("failed to fork");
+
+ if (!child_pid) {
+ 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.
+ */
+ if (read(go_pipe[0], &buf, 1) == -1)
+ perror("unable to read pipe");
+
+ execvp(argv[0], (char **)argv);
+
+ perror(argv[0]);
+ exit(-1);
+ }
- /*
- * Do a dummy execvp to get the PLT entry resolved,
- * so we avoid the resolver overhead on the real
- * execvp call.
- */
- execvp("", (char **)argv);
+ if (target_tid == -1 && target_pid == -1 && !system_wide)
+ all_tids[0] = child_pid;
/*
- * Tell the parent we're ready to go
+ * Wait for the child to be ready to exec.
*/
close(child_ready_pipe[1]);
-
- /*
- * Wait until the parent tells us to go.
- */
- if (read(go_pipe[0], &buf, 1) == -1)
+ close(go_pipe[0]);
+ if (read(child_ready_pipe[0], &buf, 1) == -1)
perror("unable to read pipe");
-
- execvp(argv[0], (char **)argv);
-
- perror(argv[0]);
- exit(-1);
+ close(child_ready_pipe[0]);
}
- /*
- * Wait for the child to be ready to exec.
- */
- close(child_ready_pipe[1]);
- close(go_pipe[0]);
- if (read(child_ready_pipe[0], &buf, 1) == -1)
- perror("unable to read pipe");
- close(child_ready_pipe[0]);
-
for (counter = 0; counter < nr_counters; counter++)
- create_perf_stat_counter(counter, pid);
+ ncreated += create_perf_stat_counter(counter);
+
+ if (ncreated == 0) {
+ pr_err("No permission to collect %sstats.\n"
+ "Consider tweaking /proc/sys/kernel/perf_event_paranoid.\n",
+ system_wide ? "system-wide " : "");
+ if (child_pid != -1)
+ kill(child_pid, SIGTERM);
+ return -1;
+ }
/*
* Enable counters and exec the command:
*/
t0 = rdclock();
- close(go_pipe[1]);
- wait(&status);
+ if (forks) {
+ close(go_pipe[1]);
+ wait(&status);
+ } else {
+ while(!done) sleep(1);
+ }
t1 = rdclock();
static void abs_printout(int counter, double avg)
{
+ double total, ratio = 0.0;
+
fprintf(stderr, " %14.0f %-24s", avg, event_name(counter));
if (MATCH_EVENT(HARDWARE, HW_INSTRUCTIONS, counter)) {
- fprintf(stderr, " # %10.3f IPC ",
- avg / avg_stats(&runtime_cycles_stats));
- } else {
- fprintf(stderr, " # %10.3f M/sec",
- 1000.0 * avg / avg_stats(&runtime_nsecs_stats));
+ total = avg_stats(&runtime_cycles_stats);
+
+ if (total)
+ ratio = avg / total;
+
+ fprintf(stderr, " # %10.3f IPC ", ratio);
+ } else if (MATCH_EVENT(HARDWARE, HW_BRANCH_MISSES, counter) &&
+ runtime_branches_stats.n != 0) {
+ total = avg_stats(&runtime_branches_stats);
+
+ if (total)
+ ratio = avg * 100 / total;
+
+ fprintf(stderr, " # %10.3f %% ", ratio);
+
+ } else if (runtime_nsecs_stats.n != 0) {
+ total = avg_stats(&runtime_nsecs_stats);
+
+ if (total)
+ ratio = 1000.0 * avg / total;
+
+ fprintf(stderr, " # %10.3f M/sec", ratio);
}
}
fflush(stdout);
fprintf(stderr, "\n");
- fprintf(stderr, " Performance counter stats for \'%s", argv[0]);
-
- for (i = 1; i < argc; i++)
- fprintf(stderr, " %s", argv[i]);
+ fprintf(stderr, " Performance counter stats for ");
+ if(target_pid == -1 && target_tid == -1) {
+ fprintf(stderr, "\'%s", argv[0]);
+ for (i = 1; i < argc; i++)
+ fprintf(stderr, " %s", argv[i]);
+ } else if (target_pid != -1)
+ fprintf(stderr, "process id \'%d", target_pid);
+ else
+ fprintf(stderr, "thread id \'%d", target_tid);
fprintf(stderr, "\'");
if (run_count > 1)
static void skip_signal(int signo)
{
+ if(child_pid == -1)
+ done = 1;
+
signr = signo;
}
static void sig_atexit(void)
{
+ if (child_pid != -1)
+ kill(child_pid, SIGTERM);
+
if (signr == -1)
return;
}
static const char * const stat_usage[] = {
- "perf stat [<options>] <command>",
+ "perf stat [<options>] [<command>]",
NULL
};
OPT_CALLBACK('e', "event", NULL, "event",
"event selector. use 'perf list' to list available events",
parse_events),
- OPT_BOOLEAN('i', "inherit", &inherit,
- "child tasks inherit counters"),
+ OPT_BOOLEAN('i', "no-inherit", &no_inherit,
+ "child tasks do not inherit counters"),
OPT_INTEGER('p', "pid", &target_pid,
- "stat events on existing pid"),
+ "stat events on existing process id"),
+ OPT_INTEGER('t', "tid", &target_tid,
+ "stat events on existing thread id"),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
OPT_BOOLEAN('c', "scale", &scale,
"scale/normalize counters"),
- OPT_BOOLEAN('v', "verbose", &verbose,
+ OPT_INCR('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)"),
int cmd_stat(int argc, const char **argv, const char *prefix __used)
{
int status;
+ int i,j;
argc = parse_options(argc, argv, options, stat_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
- if (!argc)
+ if (!argc && target_pid == -1 && target_tid == -1)
usage_with_options(stat_usage, options);
if (run_count <= 0)
usage_with_options(stat_usage, options);
nr_counters = ARRAY_SIZE(default_attrs);
}
- nr_cpus = sysconf(_SC_NPROCESSORS_ONLN);
- assert(nr_cpus <= MAX_NR_CPUS);
- assert((int)nr_cpus >= 0);
+ if (system_wide)
+ nr_cpus = read_cpu_map();
+ else
+ nr_cpus = 1;
+
+ if (target_pid != -1) {
+ target_tid = target_pid;
+ thread_num = find_all_tid(target_pid, &all_tids);
+ if (thread_num <= 0) {
+ fprintf(stderr, "Can't find all threads of pid %d\n",
+ target_pid);
+ usage_with_options(stat_usage, options);
+ }
+ } else {
+ all_tids=malloc(sizeof(pid_t));
+ if (!all_tids)
+ return -ENOMEM;
+
+ all_tids[0] = target_tid;
+ thread_num = 1;
+ }
+
+ for (i = 0; i < MAX_NR_CPUS; i++) {
+ for (j = 0; j < MAX_COUNTERS; j++) {
+ fd[i][j] = malloc(sizeof(int)*thread_num);
+ if (!fd[i][j])
+ return -ENOMEM;
+ }
+ }
/*
* We dont want to block the signals - that would cause
status = run_perf_stat(argc, argv);
}
- print_stat(argc, argv);
+ if (status != -1)
+ print_stat(argc, argv);
return status;
}