Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1336846 > unrolled thread
| Started by | Andi Kleen <andi@firstfloor.org> |
|---|---|
| First post | 2016-02-17 23:50 +0100 |
| Last post | 2016-02-22 18:00 +0100 |
| Articles | 5 — 2 participants |
Back to article view | Back to linux.kernel
This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by
below is the oldest one visible, not the original post.
[PATCH 3/6] perf, tools, stat: Support metrics in --per-core/socket mode Andi Kleen <andi@firstfloor.org> - 2016-02-17 23:50 +0100
Re: [PATCH 3/6] perf, tools, stat: Support metrics in --per-core/socket mode Jiri Olsa <jolsa@redhat.com> - 2016-02-21 18:20 +0100
Re: [PATCH 3/6] perf, tools, stat: Support metrics in --per-core/socket mode Jiri Olsa <jolsa@redhat.com> - 2016-02-21 18:30 +0100
Re: [PATCH 3/6] perf, tools, stat: Support metrics in --per-core/socket mode Jiri Olsa <jolsa@redhat.com> - 2016-02-21 18:30 +0100
Re: [PATCH 3/6] perf, tools, stat: Support metrics in --per-core/socket mode Andi Kleen <andi@firstfloor.org> - 2016-02-22 18:00 +0100
| From | Andi Kleen <andi@firstfloor.org> |
|---|---|
| Date | 2016-02-17 23:50 +0100 |
| Subject | [PATCH 3/6] perf, tools, stat: Support metrics in --per-core/socket mode |
| Message-ID | <r3j51-4A2-45@gated-at.bofh.it> |
From: Andi Kleen <ak@linux.intel.com>
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
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
tools/perf/builtin-stat.c | 58 +++++++++++++++++++++++++++++++++++++++++------
1 file changed, 51 insertions(+), 7 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 6c2c1d2..715e5b5 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -741,6 +741,8 @@ struct outstate {
const char *prefix;
int nfields;
u64 run, ena;
+ int id, nr;
+ struct perf_evsel *evsel;
};
#define METRIC_LEN 35
@@ -756,12 +758,9 @@ 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, " ");
}
@@ -799,6 +798,7 @@ 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);
}
@@ -856,6 +856,22 @@ 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 == NULL)
+ 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;
@@ -892,7 +908,10 @@ 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 *);
@@ -962,15 +981,38 @@ 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, cpu2, 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++) {
+ cpu2 = perf_evsel__cpus(counter)->map[cpu];
+ s2 = aggr_get_id(evsel_list->cpus, cpu2);
+ 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;
@@ -982,6 +1024,8 @@ 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) {
--
2.5.0
[toc] | [next] | [standalone]
| From | Jiri Olsa <jolsa@redhat.com> |
|---|---|
| Date | 2016-02-21 18:20 +0100 |
| Subject | Re: [PATCH 3/6] perf, tools, stat: Support metrics in --per-core/socket mode |
| Message-ID | <r4FPQ-O0-5@gated-at.bofh.it> |
| In reply to | #1336846 |
On Wed, Feb 17, 2016 at 02:44:02PM -0800, Andi Kleen wrote:
SNIP
>
> 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, cpu2, 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++) {
> + cpu2 = perf_evsel__cpus(counter)->map[cpu];
> + s2 = aggr_get_id(evsel_list->cpus, cpu2);
I think you need to pass cpu's 'idx' into aggr_get_id,
because it will do evsel_list->cpus[cpu2] for you
jirka
[toc] | [prev] | [next] | [standalone]
| From | Jiri Olsa <jolsa@redhat.com> |
|---|---|
| Date | 2016-02-21 18:30 +0100 |
| Subject | Re: [PATCH 3/6] perf, tools, stat: Support metrics in --per-core/socket mode |
| Message-ID | <r4FZx-Tg-41@gated-at.bofh.it> |
| In reply to | #1336846 |
On Wed, Feb 17, 2016 at 02:44:02PM -0800, Andi Kleen wrote:
SNIP
> +static void aggr_update_shadow(void)
> +{
> + int cpu, cpu2, 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++) {
> + cpu2 = perf_evsel__cpus(counter)->map[cpu];
> + s2 = aggr_get_id(evsel_list->cpus, cpu2);
> + 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;
> @@ -982,6 +1024,8 @@ static void print_aggr(char *prefix)
> if (!(aggr_map || aggr_get_id))
> return;
>
> + aggr_update_shadow();
this should be called from perf_stat_process_counter,
not from display function
also please document somewhere (best around shadow stats variables)
what cpus (array members) are used for given AGGR_*
thanks,
jirka
[toc] | [prev] | [next] | [standalone]
| From | Jiri Olsa <jolsa@redhat.com> |
|---|---|
| Date | 2016-02-21 18:30 +0100 |
| Subject | Re: [PATCH 3/6] perf, tools, stat: Support metrics in --per-core/socket mode |
| Message-ID | <r4FZy-Tg-47@gated-at.bofh.it> |
| In reply to | #1336846 |
On Wed, Feb 17, 2016 at 02:44:02PM -0800, Andi Kleen wrote:
SNIP
> @@ -892,7 +908,10 @@ 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 *);
> @@ -962,15 +981,38 @@ 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),
hum, IIUC you need to handle AGGR_NONE in here as well?
thanks,
jirka
[toc] | [prev] | [next] | [standalone]
| From | Andi Kleen <andi@firstfloor.org> |
|---|---|
| Date | 2016-02-22 18:00 +0100 |
| Subject | Re: [PATCH 3/6] perf, tools, stat: Support metrics in --per-core/socket mode |
| Message-ID | <r5202-eH-15@gated-at.bofh.it> |
| In reply to | #1338865 |
On Sun, Feb 21, 2016 at 06:15:35PM +0100, Jiri Olsa wrote:
> On Wed, Feb 17, 2016 at 02:44:02PM -0800, Andi Kleen wrote:
>
> SNIP
>
> > @@ -892,7 +908,10 @@ 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 *);
> > @@ -962,15 +981,38 @@ 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),
>
> hum, IIUC you need to handle AGGR_NONE in here as well?
AFAIK it works. aggr_get_id in first_shadow_cpu and cpu_map__id_to_cpu
handle this case, right?
-Andi
[toc] | [prev] | [standalone]
Back to top | Article view | linux.kernel
csiph-web