Re: [PATCH v5 06/12] perf util: Update and print per-thread shadow stats

From: Jin, Yao
Date: Fri Dec 01 2017 - 23:46:18 EST




On 12/1/2017 10:21 PM, Arnaldo Carvalho de Melo wrote:
Em Fri, Dec 01, 2017 at 06:57:30PM +0800, Jin Yao escreveu:
The functions perf_stat__update_shadow_stats() and
perf_stat__print_shadow_statss() are called to update
and print the shadow stats on a set of static variables.

But the static variables are the limitations to support
per-thread shadow stats.

This patch lets the perf_stat__update_shadow_stats() support
to update the shadow stats on a input parameter 'stat' and
uses update_runtime_stat() to update the stats. It will not
directly update the static variables as before.

And this patch also lets the perf_stat__print_shadow_stats()

When 'also' appears on a patch usually it means it should be split in
two, one for the things up to the 'also' and another for the remaining
parts.

A patch that has these stats:

5 files changed, 219 insertions(+), 120 deletions(-)

raises eyebrows :-\

I'm trying now to break it into at least two, one for printing and the
other for the rest.

- Arnaldo


Yes, too much in this patch.

Actually I also want to split it into more patches. While I just feel a little bit difficulty because some dependencies are there.

If you need me to do anything on this patch (e.g. refine/split/reorg/...), I'd like to, please let me know.

Thanks
Jin Yao

support to print the shadow stats from a input parameter 'stat'.

It will not directly get value from static variable. Instead, it now
uses runtime_stat_avg() and runtime_stat_n() to get and compute the
values.

Signed-off-by: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>
---
tools/perf/builtin-script.c | 6 +-
tools/perf/builtin-stat.c | 27 ++--
tools/perf/util/stat-shadow.c | 293 +++++++++++++++++++++++++++---------------
tools/perf/util/stat.c | 8 +-
tools/perf/util/stat.h | 5 +-
5 files changed, 219 insertions(+), 120 deletions(-)

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 39d8b55..fac6f05 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1548,7 +1548,8 @@ static void perf_sample__fprint_metric(struct perf_script *script,
val = sample->period * evsel->scale;
perf_stat__update_shadow_stats(evsel,
val,
- sample->cpu);
+ sample->cpu,
+ &rt_stat);
evsel_script(evsel)->val = val;
if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) {
for_each_group_member (ev2, evsel->leader) {
@@ -1556,7 +1557,8 @@ static void perf_sample__fprint_metric(struct perf_script *script,
evsel_script(ev2)->val,
sample->cpu,
&ctx,
- NULL);
+ NULL,
+ &rt_stat);
}
evsel_script(evsel->leader)->gnum = 0;
}
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a027b47..1edc082 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1097,7 +1097,8 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
}
static void printout(int id, int nr, struct perf_evsel *counter, double uval,
- char *prefix, u64 run, u64 ena, double noise)
+ char *prefix, u64 run, u64 ena, double noise,
+ struct runtime_stat *stat)
{
struct perf_stat_output_ctx out;
struct outstate os = {
@@ -1190,7 +1191,8 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
perf_stat__print_shadow_stats(counter, uval,
first_shadow_cpu(counter, id),
- &out, &metric_events);
+ &out, &metric_events,
+ stat);
if (!csv_output && !metric_only) {
print_noise(counter, noise);
print_running(run, ena);
@@ -1214,7 +1216,8 @@ static void aggr_update_shadow(void)
val += perf_counts(counter->counts, cpu, 0)->val;
}
perf_stat__update_shadow_stats(counter, val,
- first_shadow_cpu(counter, id));
+ first_shadow_cpu(counter, id),
+ &rt_stat);
}
}
}
@@ -1334,7 +1337,8 @@ static void print_aggr(char *prefix)
fprintf(output, "%s", prefix);
uval = val * counter->scale;
- printout(id, nr, counter, uval, prefix, run, ena, 1.0);
+ printout(id, nr, counter, uval, prefix, run, ena, 1.0,
+ &rt_stat);
if (!metric_only)
fputc('\n', output);
}
@@ -1364,7 +1368,8 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
fprintf(output, "%s", prefix);
uval = val * counter->scale;
- printout(thread, 0, counter, uval, prefix, run, ena, 1.0);
+ printout(thread, 0, counter, uval, prefix, run, ena, 1.0,
+ &rt_stat);
fputc('\n', output);
}
}
@@ -1401,7 +1406,8 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
fprintf(output, "%s", prefix);
uval = cd.avg * counter->scale;
- printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled, cd.avg);
+ printout(-1, 0, counter, uval, prefix, cd.avg_running, cd.avg_enabled,
+ cd.avg, &rt_stat);
if (!metric_only)
fprintf(output, "\n");
}
@@ -1440,7 +1446,8 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
fprintf(output, "%s", prefix);
uval = val * counter->scale;
- printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+ printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
+ &rt_stat);
fputc('\n', output);
}
@@ -1472,7 +1479,8 @@ static void print_no_aggr_metric(char *prefix)
run = perf_counts(counter->counts, cpu, 0)->run;
uval = val * counter->scale;
- printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+ printout(cpu, 0, counter, uval, prefix, run, ena, 1.0,
+ &rt_stat);
}
fputc('\n', stat_config.output);
}
@@ -1528,7 +1536,8 @@ static void print_metric_headers(const char *prefix, bool no_indent)
perf_stat__print_shadow_stats(counter, 0,
0,
&out,
- &metric_events);
+ &metric_events,
+ &rt_stat);
}
fputc('\n', stat_config.output);
}
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index e60c321..0d34d5e 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -116,19 +116,29 @@ static void saved_value_delete(struct rblist *rblist __maybe_unused,
static struct saved_value *saved_value_lookup(struct perf_evsel *evsel,
int cpu,
- bool create)
+ bool create,
+ enum stat_type type,
+ int ctx,
+ struct runtime_stat *stat)
{
+ struct rblist *rblist;
struct rb_node *nd;
struct saved_value dm = {
.cpu = cpu,
.evsel = evsel,
+ .type = type,
+ .ctx = ctx,
+ .stat = stat,
};
- nd = rblist__find(&runtime_saved_values, &dm);
+
+ rblist = &stat->value_list;
+
+ nd = rblist__find(rblist, &dm);
if (nd)
return container_of(nd, struct saved_value, rb_node);
if (create) {
- rblist__add_node(&runtime_saved_values, &dm);
- nd = rblist__find(&runtime_saved_values, &dm);
+ rblist__add_node(rblist, &dm);
+ nd = rblist__find(rblist, &dm);
if (nd)
return container_of(nd, struct saved_value, rb_node);
}
@@ -217,13 +227,24 @@ void perf_stat__reset_shadow_stats(void)
}
}
+static void update_runtime_stat(struct runtime_stat *stat,
+ enum stat_type type,
+ int ctx, int cpu, u64 count)
+{
+ struct saved_value *v = saved_value_lookup(NULL, cpu, true,
+ type, ctx, stat);
+
+ if (v)
+ update_stats(&v->stats, count);
+}
+
/*
* Update various tracking values we maintain to print
* more semantic information such as miss/hit ratios,
* instruction rates, etc:
*/
void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
- int cpu)
+ int cpu, struct runtime_stat *stat)
{
int ctx = evsel_context(counter);
@@ -231,50 +252,58 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK) ||
perf_evsel__match(counter, SOFTWARE, SW_CPU_CLOCK))
- update_stats(&runtime_nsecs_stats[cpu], count);
+ update_runtime_stat(stat, STAT_NSECS, 0, cpu, count);
else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
- update_stats(&runtime_cycles_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_CYCLES, ctx, cpu, count);
else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
- update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_CYCLES_IN_TX, ctx, cpu, count);
else if (perf_stat_evsel__is(counter, TRANSACTION_START))
- update_stats(&runtime_transaction_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_TRANSACTION, ctx, cpu, count);
else if (perf_stat_evsel__is(counter, ELISION_START))
- update_stats(&runtime_elision_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_ELISION, ctx, cpu, count);
else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
- update_stats(&runtime_topdown_total_slots[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_TOPDOWN_TOTAL_SLOTS,
+ ctx, cpu, count);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
- update_stats(&runtime_topdown_slots_issued[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_TOPDOWN_SLOTS_ISSUED,
+ ctx, cpu, count);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
- update_stats(&runtime_topdown_slots_retired[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_TOPDOWN_SLOTS_RETIRED,
+ ctx, cpu, count);
else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
- update_stats(&runtime_topdown_fetch_bubbles[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_TOPDOWN_FETCH_BUBBLES,
+ ctx, cpu, count);
else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
- update_stats(&runtime_topdown_recovery_bubbles[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_TOPDOWN_RECOVERY_BUBBLES,
+ ctx, cpu, count);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
- update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_STALLED_CYCLES_FRONT,
+ ctx, cpu, count);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
- update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_STALLED_CYCLES_BACK,
+ ctx, cpu, count);
else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
- update_stats(&runtime_branches_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_BRANCHES, ctx, cpu, count);
else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
- update_stats(&runtime_cacherefs_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_CACHEREFS, ctx, cpu, count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
- update_stats(&runtime_l1_dcache_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_L1_DCACHE, ctx, cpu, count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
- update_stats(&runtime_ll_cache_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_L1_ICACHE, ctx, cpu, count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
- update_stats(&runtime_ll_cache_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_LL_CACHE, ctx, cpu, count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
- update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_DTLB_CACHE, ctx, cpu, count);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
- update_stats(&runtime_itlb_cache_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_ITLB_CACHE, ctx, cpu, count);
else if (perf_stat_evsel__is(counter, SMI_NUM))
- update_stats(&runtime_smi_num_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_SMI_NUM, ctx, cpu, count);
else if (perf_stat_evsel__is(counter, APERF))
- update_stats(&runtime_aperf_stats[ctx][cpu], count);
+ update_runtime_stat(stat, STAT_APERF, ctx, cpu, count);
if (counter->collect_stat) {
- struct saved_value *v = saved_value_lookup(counter, cpu, true);
+ struct saved_value *v = saved_value_lookup(counter, cpu, true,
+ STAT_NONE, 0, stat);
update_stats(&v->stats, count);
}
}
@@ -395,15 +424,40 @@ void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list)
}
}
+static double runtime_stat_avg(struct runtime_stat *stat,
+ enum stat_type type, int ctx, int cpu)
+{
+ struct saved_value *v;
+
+ v = saved_value_lookup(NULL, cpu, false, type, ctx, stat);
+ if (!v)
+ return 0.0;
+
+ return avg_stats(&v->stats);
+}
+
+static double runtime_stat_n(struct runtime_stat *stat,
+ enum stat_type type, int ctx, int cpu)
+{
+ struct saved_value *v;
+
+ v = saved_value_lookup(NULL, cpu, false, type, ctx, stat);
+ if (!v)
+ return 0.0;
+
+ return v->stats.n;
+}
+
static void print_stalled_cycles_frontend(int cpu,
struct perf_evsel *evsel, double avg,
- struct perf_stat_output_ctx *out)
+ struct perf_stat_output_ctx *out,
+ struct runtime_stat *stat)
{
double total, ratio = 0.0;
const char *color;
int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_CYCLES, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -419,13 +473,14 @@ static void print_stalled_cycles_frontend(int cpu,
static void print_stalled_cycles_backend(int cpu,
struct perf_evsel *evsel, double avg,
- struct perf_stat_output_ctx *out)
+ struct perf_stat_output_ctx *out,
+ struct runtime_stat *stat)
{
double total, ratio = 0.0;
const char *color;
int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_CYCLES, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -438,13 +493,14 @@ static void print_stalled_cycles_backend(int cpu,
static void print_branch_misses(int cpu,
struct perf_evsel *evsel,
double avg,
- struct perf_stat_output_ctx *out)
+ struct perf_stat_output_ctx *out,
+ struct runtime_stat *stat)
{
double total, ratio = 0.0;
const char *color;
int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_branches_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_BRANCHES, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -457,13 +513,15 @@ static void print_branch_misses(int cpu,
static void print_l1_dcache_misses(int cpu,
struct perf_evsel *evsel,
double avg,
- struct perf_stat_output_ctx *out)
+ struct perf_stat_output_ctx *out,
+ struct runtime_stat *stat)
+
{
double total, ratio = 0.0;
const char *color;
int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_l1_dcache_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_L1_DCACHE, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -476,13 +534,15 @@ static void print_l1_dcache_misses(int cpu,
static void print_l1_icache_misses(int cpu,
struct perf_evsel *evsel,
double avg,
- struct perf_stat_output_ctx *out)
+ struct perf_stat_output_ctx *out,
+ struct runtime_stat *stat)
+
{
double total, ratio = 0.0;
const char *color;
int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_l1_icache_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_L1_ICACHE, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -494,13 +554,14 @@ static void print_l1_icache_misses(int cpu,
static void print_dtlb_cache_misses(int cpu,
struct perf_evsel *evsel,
double avg,
- struct perf_stat_output_ctx *out)
+ struct perf_stat_output_ctx *out,
+ struct runtime_stat *stat)
{
double total, ratio = 0.0;
const char *color;
int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_dtlb_cache_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_DTLB_CACHE, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -512,13 +573,14 @@ static void print_dtlb_cache_misses(int cpu,
static void print_itlb_cache_misses(int cpu,
struct perf_evsel *evsel,
double avg,
- struct perf_stat_output_ctx *out)
+ struct perf_stat_output_ctx *out,
+ struct runtime_stat *stat)
{
double total, ratio = 0.0;
const char *color;
int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_itlb_cache_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_ITLB_CACHE, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -530,13 +592,14 @@ static void print_itlb_cache_misses(int cpu,
static void print_ll_cache_misses(int cpu,
struct perf_evsel *evsel,
double avg,
- struct perf_stat_output_ctx *out)
+ struct perf_stat_output_ctx *out,
+ struct runtime_stat *stat)
{
double total, ratio = 0.0;
const char *color;
int ctx = evsel_context(evsel);
- total = avg_stats(&runtime_ll_cache_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_LL_CACHE, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -594,68 +657,72 @@ static double sanitize_val(double x)
return x;
}
-static double td_total_slots(int ctx, int cpu)
+static double td_total_slots(int ctx, int cpu, struct runtime_stat *stat)
{
- return avg_stats(&runtime_topdown_total_slots[ctx][cpu]);
+ return runtime_stat_avg(stat, STAT_TOPDOWN_TOTAL_SLOTS, ctx, cpu);
}
-static double td_bad_spec(int ctx, int cpu)
+static double td_bad_spec(int ctx, int cpu, struct runtime_stat *stat)
{
double bad_spec = 0;
double total_slots;
double total;
- total = avg_stats(&runtime_topdown_slots_issued[ctx][cpu]) -
- avg_stats(&runtime_topdown_slots_retired[ctx][cpu]) +
- avg_stats(&runtime_topdown_recovery_bubbles[ctx][cpu]);
- total_slots = td_total_slots(ctx, cpu);
+ total = runtime_stat_avg(stat, STAT_TOPDOWN_SLOTS_ISSUED, ctx, cpu) -
+ runtime_stat_avg(stat, STAT_TOPDOWN_SLOTS_RETIRED, ctx, cpu) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_RECOVERY_BUBBLES, ctx, cpu);
+
+ total_slots = td_total_slots(ctx, cpu, stat);
if (total_slots)
bad_spec = total / total_slots;
return sanitize_val(bad_spec);
}
-static double td_retiring(int ctx, int cpu)
+static double td_retiring(int ctx, int cpu, struct runtime_stat *stat)
{
double retiring = 0;
- double total_slots = td_total_slots(ctx, cpu);
- double ret_slots = avg_stats(&runtime_topdown_slots_retired[ctx][cpu]);
+ double total_slots = td_total_slots(ctx, cpu, stat);
+ double ret_slots = runtime_stat_avg(stat, STAT_TOPDOWN_SLOTS_RETIRED,
+ ctx, cpu);
if (total_slots)
retiring = ret_slots / total_slots;
return retiring;
}
-static double td_fe_bound(int ctx, int cpu)
+static double td_fe_bound(int ctx, int cpu, struct runtime_stat *stat)
{
double fe_bound = 0;
- double total_slots = td_total_slots(ctx, cpu);
- double fetch_bub = avg_stats(&runtime_topdown_fetch_bubbles[ctx][cpu]);
+ double total_slots = td_total_slots(ctx, cpu, stat);
+ double fetch_bub = runtime_stat_avg(stat, STAT_TOPDOWN_FETCH_BUBBLES,
+ ctx, cpu);
if (total_slots)
fe_bound = fetch_bub / total_slots;
return fe_bound;
}
-static double td_be_bound(int ctx, int cpu)
+static double td_be_bound(int ctx, int cpu, struct runtime_stat *stat)
{
- double sum = (td_fe_bound(ctx, cpu) +
- td_bad_spec(ctx, cpu) +
- td_retiring(ctx, cpu));
+ double sum = (td_fe_bound(ctx, cpu, stat) +
+ td_bad_spec(ctx, cpu, stat) +
+ td_retiring(ctx, cpu, stat));
if (sum == 0)
return 0;
return sanitize_val(1.0 - sum);
}
static void print_smi_cost(int cpu, struct perf_evsel *evsel,
- struct perf_stat_output_ctx *out)
+ struct perf_stat_output_ctx *out,
+ struct runtime_stat *stat)
{
double smi_num, aperf, cycles, cost = 0.0;
int ctx = evsel_context(evsel);
const char *color = NULL;
- smi_num = avg_stats(&runtime_smi_num_stats[ctx][cpu]);
- aperf = avg_stats(&runtime_aperf_stats[ctx][cpu]);
- cycles = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+ smi_num = runtime_stat_avg(stat, STAT_SMI_NUM, ctx, cpu);
+ aperf = runtime_stat_avg(stat, STAT_APERF, ctx, cpu);
+ cycles = runtime_stat_avg(stat, STAT_CYCLES, ctx, cpu);
if ((cycles == 0) || (aperf == 0))
return;
@@ -675,7 +742,8 @@ static void generic_metric(const char *metric_expr,
const char *metric_name,
double avg,
int cpu,
- struct perf_stat_output_ctx *out)
+ struct perf_stat_output_ctx *out,
+ struct runtime_stat *stat)
{
print_metric_t print_metric = out->print_metric;
struct parse_ctx pctx;
@@ -694,7 +762,8 @@ static void generic_metric(const char *metric_expr,
stats = &walltime_nsecs_stats;
scale = 1e-9;
} else {
- v = saved_value_lookup(metric_events[i], cpu, false);
+ v = saved_value_lookup(metric_events[i], cpu, false,
+ STAT_NONE, 0, stat);
if (!v)
break;
stats = &v->stats;
@@ -722,7 +791,8 @@ static void generic_metric(const char *metric_expr,
void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
double avg, int cpu,
struct perf_stat_output_ctx *out,
- struct rblist *metric_events)
+ struct rblist *metric_events,
+ struct runtime_stat *stat)
{
void *ctxp = out->ctx;
print_metric_t print_metric = out->print_metric;
@@ -733,7 +803,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
int num = 1;
if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
- total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_CYCLES, ctx, cpu);
+
if (total) {
ratio = avg / total;
print_metric(ctxp, NULL, "%7.2f ",
@@ -741,8 +812,13 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
} else {
print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
}
- total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
- total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
+
+ total = runtime_stat_avg(stat, STAT_STALLED_CYCLES_FRONT,
+ ctx, cpu);
+
+ total = max(total, runtime_stat_avg(stat,
+ STAT_STALLED_CYCLES_BACK,
+ ctx, cpu));
if (total && avg) {
out->new_line(ctxp);
@@ -755,8 +831,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
"stalled cycles per insn", 0);
}
} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
- if (runtime_branches_stats[ctx][cpu].n != 0)
- print_branch_misses(cpu, evsel, avg, out);
+ if (runtime_stat_n(stat, STAT_BRANCHES, ctx, cpu) != 0)
+ print_branch_misses(cpu, evsel, avg, out, stat);
else
print_metric(ctxp, NULL, NULL, "of all branches", 0);
} else if (
@@ -764,8 +840,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
- print_l1_dcache_misses(cpu, evsel, avg, out);
+
+ if (runtime_stat_n(stat, STAT_L1_DCACHE, ctx, cpu) != 0)
+ print_l1_dcache_misses(cpu, evsel, avg, out, stat);
else
print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
} else if (
@@ -773,8 +850,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_l1_icache_stats[ctx][cpu].n != 0)
- print_l1_icache_misses(cpu, evsel, avg, out);
+
+ if (runtime_stat_n(stat, STAT_L1_ICACHE, ctx, cpu) != 0)
+ print_l1_icache_misses(cpu, evsel, avg, out, stat);
else
print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
} else if (
@@ -782,8 +860,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
- print_dtlb_cache_misses(cpu, evsel, avg, out);
+
+ if (runtime_stat_n(stat, STAT_DTLB_CACHE, ctx, cpu) != 0)
+ print_dtlb_cache_misses(cpu, evsel, avg, out, stat);
else
print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
} else if (
@@ -791,8 +870,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
- print_itlb_cache_misses(cpu, evsel, avg, out);
+
+ if (runtime_stat_n(stat, STAT_ITLB_CACHE, ctx, cpu) != 0)
+ print_itlb_cache_misses(cpu, evsel, avg, out, stat);
else
print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
} else if (
@@ -800,27 +880,28 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_ll_cache_stats[ctx][cpu].n != 0)
- print_ll_cache_misses(cpu, evsel, avg, out);
+
+ if (runtime_stat_n(stat, STAT_LL_CACHE, ctx, cpu) != 0)
+ print_ll_cache_misses(cpu, evsel, avg, out, stat);
else
print_metric(ctxp, NULL, NULL, "of all LL-cache hits", 0);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
- total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_CACHEREFS, ctx, cpu);
if (total)
ratio = avg * 100 / total;
- if (runtime_cacherefs_stats[ctx][cpu].n != 0)
+ if (runtime_stat_n(stat, STAT_CACHEREFS, ctx, cpu) != 0)
print_metric(ctxp, NULL, "%8.3f %%",
"of all cache refs", ratio);
else
print_metric(ctxp, NULL, NULL, "of all cache refs", 0);
} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
- print_stalled_cycles_frontend(cpu, evsel, avg, out);
+ print_stalled_cycles_frontend(cpu, evsel, avg, out, stat);
} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
- print_stalled_cycles_backend(cpu, evsel, avg, out);
+ print_stalled_cycles_backend(cpu, evsel, avg, out, stat);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
- total = avg_stats(&runtime_nsecs_stats[cpu]);
+ total = runtime_stat_avg(stat, STAT_NSECS, 0, cpu);
if (total) {
ratio = avg / total;
@@ -829,7 +910,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
print_metric(ctxp, NULL, NULL, "Ghz", 0);
}
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
- total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_CYCLES, ctx, cpu);
+
if (total)
print_metric(ctxp, NULL,
"%7.2f%%", "transactional cycles",
@@ -838,8 +920,9 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
print_metric(ctxp, NULL, NULL, "transactional cycles",
0);
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
- total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
- total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_CYCLES, ctx, cpu);
+ total2 = runtime_stat_avg(stat, STAT_CYCLES_IN_TX, ctx, cpu);
+
if (total2 < avg)
total2 = avg;
if (total)
@@ -848,19 +931,21 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
else
print_metric(ctxp, NULL, NULL, "aborted cycles", 0);
} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
- total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_CYCLES_IN_TX,
+ ctx, cpu);
if (avg)
ratio = total / avg;
- if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+ if (runtime_stat_n(stat, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
print_metric(ctxp, NULL, "%8.0f",
"cycles / transaction", ratio);
else
print_metric(ctxp, NULL, NULL, "cycles / transaction",
- 0);
+ 0);
} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
- total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+ total = runtime_stat_avg(stat, STAT_CYCLES_IN_TX,
+ ctx, cpu);
if (avg)
ratio = total / avg;
@@ -874,28 +959,28 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
else
print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
- double fe_bound = td_fe_bound(ctx, cpu);
+ double fe_bound = td_fe_bound(ctx, cpu, stat);
if (fe_bound > 0.2)
color = PERF_COLOR_RED;
print_metric(ctxp, color, "%8.1f%%", "frontend bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
- double retiring = td_retiring(ctx, cpu);
+ double retiring = td_retiring(ctx, cpu, stat);
if (retiring > 0.7)
color = PERF_COLOR_GREEN;
print_metric(ctxp, color, "%8.1f%%", "retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
- double bad_spec = td_bad_spec(ctx, cpu);
+ double bad_spec = td_bad_spec(ctx, cpu, stat);
if (bad_spec > 0.1)
color = PERF_COLOR_RED;
print_metric(ctxp, color, "%8.1f%%", "bad speculation",
bad_spec * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
- double be_bound = td_be_bound(ctx, cpu);
+ double be_bound = td_be_bound(ctx, cpu, stat);
const char *name = "backend bound";
static int have_recovery_bubbles = -1;
@@ -908,19 +993,19 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
if (be_bound > 0.2)
color = PERF_COLOR_RED;
- if (td_total_slots(ctx, cpu) > 0)
+ if (td_total_slots(ctx, cpu, stat) > 0)
print_metric(ctxp, color, "%8.1f%%", name,
be_bound * 100.);
else
print_metric(ctxp, NULL, NULL, name, 0);
} else if (evsel->metric_expr) {
generic_metric(evsel->metric_expr, evsel->metric_events, evsel->name,
- evsel->metric_name, avg, cpu, out);
- } else if (runtime_nsecs_stats[cpu].n != 0) {
+ evsel->metric_name, avg, cpu, out, stat);
+ } else if (runtime_stat_n(stat, STAT_NSECS, 0, cpu) != 0) {
char unit = 'M';
char unit_buf[10];
- total = avg_stats(&runtime_nsecs_stats[cpu]);
+ total = runtime_stat_avg(stat, STAT_NSECS, 0, cpu);
if (total)
ratio = 1000.0 * avg / total;
@@ -931,7 +1016,7 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
- print_smi_cost(cpu, evsel, out);
+ print_smi_cost(cpu, evsel, out, stat);
} else {
num = 0;
}
@@ -944,7 +1029,7 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
out->new_line(ctxp);
generic_metric(mexp->metric_expr, mexp->metric_events,
evsel->name, mexp->metric_name,
- avg, cpu, out);
+ avg, cpu, out, stat);
}
}
if (num == 0)
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 151e9ef..78abfd4 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -278,9 +278,11 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
perf_evsel__compute_deltas(evsel, cpu, thread, count);
perf_counts_values__scale(count, config->scale, NULL);
if (config->aggr_mode == AGGR_NONE)
- perf_stat__update_shadow_stats(evsel, count->val, cpu);
+ perf_stat__update_shadow_stats(evsel, count->val, cpu,
+ &rt_stat);
if (config->aggr_mode == AGGR_THREAD)
- perf_stat__update_shadow_stats(evsel, count->val, 0);
+ perf_stat__update_shadow_stats(evsel, count->val, 0,
+ &rt_stat);
break;
case AGGR_GLOBAL:
aggr->val += count->val;
@@ -362,7 +364,7 @@ int perf_stat_process_counter(struct perf_stat_config *config,
/*
* Save the full runtime - to allow normalization during printout:
*/
- perf_stat__update_shadow_stats(counter, *count, 0);
+ perf_stat__update_shadow_stats(counter, *count, 0, &rt_stat);
return 0;
}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 1e2b761..b8448b1 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -130,7 +130,7 @@ void runtime_stat__exit(struct runtime_stat *stat);
void perf_stat__init_shadow_stats(void);
void perf_stat__reset_shadow_stats(void);
void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
- int cpu);
+ int cpu, struct runtime_stat *stat);
struct perf_stat_output_ctx {
void *ctx;
print_metric_t print_metric;
@@ -141,7 +141,8 @@ struct perf_stat_output_ctx {
void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
double avg, int cpu,
struct perf_stat_output_ctx *out,
- struct rblist *metric_events);
+ struct rblist *metric_events,
+ struct runtime_stat *stat);
void perf_stat__collect_metric_expr(struct perf_evlist *);
int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
--
2.7.4