perf stat: Support metrics in --per-core/socket mode
Enable metrics printing in --per-core / --per-socket mode. We need to save the shadow metrics in a unique place. Always use the first CPU in the aggregation. Then use the same CPU to retrieve the shadow value later. Example output: % perf stat --per-core -a ./BC1s Performance counter stats for 'system wide': S0-C0 2 2966.020381 task-clock (msec) # 2.004 CPUs utilized (100.00%) S0-C0 2 49 context-switches # 0.017 K/sec (100.00%) S0-C0 2 4 cpu-migrations # 0.001 K/sec (100.00%) S0-C0 2 467 page-faults # 0.157 K/sec S0-C0 2 4,599,061,773 cycles # 1.551 GHz (100.00%) S0-C0 2 9,755,886,883 instructions # 2.12 insn per cycle (100.00%) S0-C0 2 1,906,272,125 branches # 642.704 M/sec (100.00%) S0-C0 2 81,180,867 branch-misses # 4.26% of all branches S0-C1 2 2965.995373 task-clock (msec) # 2.003 CPUs utilized (100.00%) S0-C1 2 62 context-switches # 0.021 K/sec (100.00%) S0-C1 2 8 cpu-migrations # 0.003 K/sec (100.00%) S0-C1 2 281 page-faults # 0.095 K/sec S0-C1 2 6,347,290 cycles # 0.002 GHz (100.00%) S0-C1 2 4,654,156 instructions # 0.73 insn per cycle (100.00%) S0-C1 2 947,121 branches # 0.319 M/sec (100.00%) S0-C1 2 37,322 branch-misses # 3.94% of all branches 1.480409747 seconds time elapsed v2: Rebase to older patches v3: Document shadow cpus. Fix aggr_get_id argument. Fix -A shadows (Jiri) Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/1456785386-19481-4-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
parent
92a61f6412
commit
44d49a6002
|
@ -740,6 +740,8 @@ struct outstate {
|
|||
bool newline;
|
||||
const char *prefix;
|
||||
int nfields;
|
||||
int id, nr;
|
||||
struct perf_evsel *evsel;
|
||||
};
|
||||
|
||||
#define METRIC_LEN 35
|
||||
|
@ -755,12 +757,9 @@ static void do_new_line_std(struct outstate *os)
|
|||
{
|
||||
fputc('\n', os->fh);
|
||||
fputs(os->prefix, os->fh);
|
||||
aggr_printout(os->evsel, os->id, os->nr);
|
||||
if (stat_config.aggr_mode == AGGR_NONE)
|
||||
fprintf(os->fh, " ");
|
||||
if (stat_config.aggr_mode == AGGR_CORE)
|
||||
fprintf(os->fh, " ");
|
||||
if (stat_config.aggr_mode == AGGR_SOCKET)
|
||||
fprintf(os->fh, " ");
|
||||
fprintf(os->fh, " ");
|
||||
}
|
||||
|
||||
|
@ -798,6 +797,7 @@ static void new_line_csv(void *ctx)
|
|||
fputc('\n', os->fh);
|
||||
if (os->prefix)
|
||||
fprintf(os->fh, "%s%s", os->prefix, csv_sep);
|
||||
aggr_printout(os->evsel, os->id, os->nr);
|
||||
for (i = 0; i < os->nfields; i++)
|
||||
fputs(csv_sep, os->fh);
|
||||
}
|
||||
|
@ -855,6 +855,28 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
|
|||
fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
|
||||
}
|
||||
|
||||
static int first_shadow_cpu(struct perf_evsel *evsel, int id)
|
||||
{
|
||||
int i;
|
||||
|
||||
if (!aggr_get_id)
|
||||
return 0;
|
||||
|
||||
if (stat_config.aggr_mode == AGGR_NONE)
|
||||
return id;
|
||||
|
||||
if (stat_config.aggr_mode == AGGR_GLOBAL)
|
||||
return 0;
|
||||
|
||||
for (i = 0; i < perf_evsel__nr_cpus(evsel); i++) {
|
||||
int cpu2 = perf_evsel__cpus(evsel)->map[i];
|
||||
|
||||
if (aggr_get_id(evsel_list->cpus, cpu2) == id)
|
||||
return cpu2;
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
|
||||
{
|
||||
FILE *output = stat_config.output;
|
||||
|
@ -891,7 +913,10 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
|
|||
struct perf_stat_output_ctx out;
|
||||
struct outstate os = {
|
||||
.fh = stat_config.output,
|
||||
.prefix = prefix ? prefix : ""
|
||||
.prefix = prefix ? prefix : "",
|
||||
.id = id,
|
||||
.nr = nr,
|
||||
.evsel = counter,
|
||||
};
|
||||
print_metric_t pm = print_metric_std;
|
||||
void (*nl)(void *);
|
||||
|
@ -958,16 +983,37 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
|
|||
}
|
||||
|
||||
perf_stat__print_shadow_stats(counter, uval,
|
||||
stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
|
||||
cpu_map__id_to_cpu(id),
|
||||
first_shadow_cpu(counter, id),
|
||||
&out);
|
||||
|
||||
if (!csv_output) {
|
||||
print_noise(counter, noise);
|
||||
print_running(run, ena);
|
||||
}
|
||||
}
|
||||
|
||||
static void aggr_update_shadow(void)
|
||||
{
|
||||
int cpu, s2, id, s;
|
||||
u64 val;
|
||||
struct perf_evsel *counter;
|
||||
|
||||
for (s = 0; s < aggr_map->nr; s++) {
|
||||
id = aggr_map->map[s];
|
||||
evlist__for_each(evsel_list, counter) {
|
||||
val = 0;
|
||||
for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
|
||||
s2 = aggr_get_id(evsel_list->cpus, cpu);
|
||||
if (s2 != id)
|
||||
continue;
|
||||
val += perf_counts(counter->counts, cpu, 0)->val;
|
||||
}
|
||||
val = val * counter->scale;
|
||||
perf_stat__update_shadow_stats(counter, &val,
|
||||
first_shadow_cpu(counter, id));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
static void print_aggr(char *prefix)
|
||||
{
|
||||
FILE *output = stat_config.output;
|
||||
|
@ -979,6 +1025,8 @@ static void print_aggr(char *prefix)
|
|||
if (!(aggr_map || aggr_get_id))
|
||||
return;
|
||||
|
||||
aggr_update_shadow();
|
||||
|
||||
for (s = 0; s < aggr_map->nr; s++) {
|
||||
id = aggr_map->map[s];
|
||||
evlist__for_each(evsel_list, counter) {
|
||||
|
|
|
@ -14,6 +14,13 @@ enum {
|
|||
|
||||
#define NUM_CTX CTX_BIT_MAX
|
||||
|
||||
/*
|
||||
* AGGR_GLOBAL: Use CPU 0
|
||||
* AGGR_SOCKET: Use first CPU of socket
|
||||
* AGGR_CORE: Use first CPU of core
|
||||
* AGGR_NONE: Use matching CPU
|
||||
* AGGR_THREAD: Not supported?
|
||||
*/
|
||||
static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
|
||||
static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
|
||||
static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
|
||||
|
|
Loading…
Reference in New Issue