From: tip-bot for Jin Yao <tipbot@zytor.com>
To: linux-tip-commits@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, acme@redhat.com,
yao.jin@linux.intel.com, kan.liang@intel.com,
peterz@infradead.org, jolsa@kernel.org, mingo@kernel.org,
hpa@zytor.com, alexander.shishkin@linux.intel.com,
ak@linux.intel.com, tglx@linutronix.de
Subject: [tip:perf/core] perf stat: Print per-thread shadow stats
Date: Thu, 28 Dec 2017 07:23:46 -0800 [thread overview]
Message-ID: <tip-e0128b30dbfb2884530251b4accdffdbf55a6b72@git.kernel.org> (raw)
In-Reply-To: <1512482591-4646-6-git-send-email-yao.jin@linux.intel.com>
Commit-ID: e0128b30dbfb2884530251b4accdffdbf55a6b72
Gitweb: https://git.kernel.org/tip/e0128b30dbfb2884530251b4accdffdbf55a6b72
Author: Jin Yao <yao.jin@linux.intel.com>
AuthorDate: Tue, 5 Dec 2017 22:03:05 +0800
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Wed, 27 Dec 2017 12:15:44 -0300
perf stat: Print per-thread shadow stats
The function perf_stat__print_shadow_stats() is called to 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__print_shadow_stats() support
to print the shadow stats from a input parameter 'st'.
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@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1512482591-4646-6-git-send-email-yao.jin@linux.intel.com
[ Rename 'stat' variables to 'st' to build on centos:{5,6} and others where it shadows a global declaration ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-script.c | 3 +-
tools/perf/builtin-stat.c | 23 +++--
tools/perf/util/stat-shadow.c | 209 ++++++++++++++++++++++++++----------------
tools/perf/util/stat.h | 3 +-
4 files changed, 151 insertions(+), 87 deletions(-)
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 81b3950..fac6f05 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1557,7 +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 3f4a2c2..097a694 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 *st)
{
struct perf_stat_output_ctx out;
struct outstate os = {
@@ -1190,7 +1191,7 @@ 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, st);
if (!csv_output && !metric_only) {
print_noise(counter, noise);
print_running(run, ena);
@@ -1335,7 +1336,8 @@ 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);
}
@@ -1365,7 +1367,8 @@ 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);
}
}
@@ -1402,7 +1405,8 @@ 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");
}
@@ -1441,7 +1445,8 @@ 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);
}
@@ -1473,7 +1478,8 @@ 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);
}
@@ -1529,7 +1535,8 @@ 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 4b28c40..a95c4fe 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -424,15 +424,40 @@ void perf_stat__collect_metric_expr(struct perf_evlist *evsel_list)
}
}
+static double runtime_stat_avg(struct runtime_stat *st,
+ enum stat_type type, int ctx, int cpu)
+{
+ struct saved_value *v;
+
+ v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+ if (!v)
+ return 0.0;
+
+ return avg_stats(&v->stats);
+}
+
+static double runtime_stat_n(struct runtime_stat *st,
+ enum stat_type type, int ctx, int cpu)
+{
+ struct saved_value *v;
+
+ v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+ 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 *st)
{
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(st, STAT_CYCLES, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -448,13 +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 *st)
{
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(st, STAT_CYCLES, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -467,13 +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 *st)
{
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(st, STAT_BRANCHES, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -486,13 +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 *st)
+
{
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(st, STAT_L1_DCACHE, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -505,13 +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 *st)
+
{
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(st, STAT_L1_ICACHE, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -523,13 +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 *st)
{
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(st, STAT_DTLB_CACHE, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -541,13 +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 *st)
{
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(st, STAT_ITLB_CACHE, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -559,13 +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 *st)
{
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(st, STAT_LL_CACHE, ctx, cpu);
if (total)
ratio = avg / total * 100.0;
@@ -623,68 +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 *st)
{
- return avg_stats(&runtime_topdown_total_slots[ctx][cpu]);
+ return runtime_stat_avg(st, 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 *st)
{
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(st, STAT_TOPDOWN_SLOTS_ISSUED, ctx, cpu) -
+ runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, ctx, cpu) +
+ runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, ctx, cpu);
+
+ total_slots = td_total_slots(ctx, cpu, st);
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 *st)
{
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, st);
+ double ret_slots = runtime_stat_avg(st, 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 *st)
{
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, st);
+ double fetch_bub = runtime_stat_avg(st, 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 *st)
{
- double sum = (td_fe_bound(ctx, cpu) +
- td_bad_spec(ctx, cpu) +
- td_retiring(ctx, cpu));
+ double sum = (td_fe_bound(ctx, cpu, st) +
+ td_bad_spec(ctx, cpu, st) +
+ td_retiring(ctx, cpu, st));
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 *st)
{
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(st, STAT_SMI_NUM, ctx, cpu);
+ aperf = runtime_stat_avg(st, STAT_APERF, ctx, cpu);
+ cycles = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
if ((cycles == 0) || (aperf == 0))
return;
@@ -704,7 +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 *st)
{
print_metric_t print_metric = out->print_metric;
struct parse_ctx pctx;
@@ -724,7 +763,7 @@ static void generic_metric(const char *metric_expr,
scale = 1e-9;
} else {
v = saved_value_lookup(metric_events[i], cpu, false,
- STAT_NONE, 0, &rt_stat);
+ STAT_NONE, 0, st);
if (!v)
break;
stats = &v->stats;
@@ -752,7 +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 *st)
{
void *ctxp = out->ctx;
print_metric_t print_metric = out->print_metric;
@@ -763,7 +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(st, STAT_CYCLES, ctx, cpu);
+
if (total) {
ratio = avg / total;
print_metric(ctxp, NULL, "%7.2f ",
@@ -771,8 +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(st, STAT_STALLED_CYCLES_FRONT,
+ ctx, cpu);
+
+ total = max(total, runtime_stat_avg(st,
+ STAT_STALLED_CYCLES_BACK,
+ ctx, cpu));
if (total && avg) {
out->new_line(ctxp);
@@ -785,8 +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(st, STAT_BRANCHES, ctx, cpu) != 0)
+ print_branch_misses(cpu, evsel, avg, out, st);
else
print_metric(ctxp, NULL, NULL, "of all branches", 0);
} else if (
@@ -794,8 +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(st, STAT_L1_DCACHE, ctx, cpu) != 0)
+ print_l1_dcache_misses(cpu, evsel, avg, out, st);
else
print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
} else if (
@@ -803,8 +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(st, STAT_L1_ICACHE, ctx, cpu) != 0)
+ print_l1_icache_misses(cpu, evsel, avg, out, st);
else
print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
} else if (
@@ -812,8 +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(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
+ print_dtlb_cache_misses(cpu, evsel, avg, out, st);
else
print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
} else if (
@@ -821,8 +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(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
+ print_itlb_cache_misses(cpu, evsel, avg, out, st);
else
print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
} else if (
@@ -830,27 +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(st, STAT_LL_CACHE, ctx, cpu) != 0)
+ print_ll_cache_misses(cpu, evsel, avg, out, st);
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(st, STAT_CACHEREFS, ctx, cpu);
if (total)
ratio = avg * 100 / total;
- if (runtime_cacherefs_stats[ctx][cpu].n != 0)
+ if (runtime_stat_n(st, 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, st);
} 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, st);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
- total = avg_stats(&runtime_nsecs_stats[cpu]);
+ total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
if (total) {
ratio = avg / total;
@@ -859,7 +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(st, STAT_CYCLES, ctx, cpu);
+
if (total)
print_metric(ctxp, NULL,
"%7.2f%%", "transactional cycles",
@@ -868,8 +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(st, STAT_CYCLES, ctx, cpu);
+ total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, ctx, cpu);
+
if (total2 < avg)
total2 = avg;
if (total)
@@ -878,19 +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(st, 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(st, 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(st, STAT_CYCLES_IN_TX,
+ ctx, cpu);
if (avg)
ratio = total / avg;
@@ -904,28 +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, st);
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, st);
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, st);
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, st);
const char *name = "backend bound";
static int have_recovery_bubbles = -1;
@@ -938,19 +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, st) > 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, st);
+ } else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
char unit = 'M';
char unit_buf[10];
- total = avg_stats(&runtime_nsecs_stats[cpu]);
+ total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
if (total)
ratio = 1000.0 * avg / total;
@@ -961,7 +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, st);
} else {
num = 0;
}
@@ -974,7 +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, st);
}
}
if (num == 0)
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index bb9902a..76b322a 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -140,7 +140,8 @@ 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 *st);
void perf_stat__collect_metric_expr(struct perf_evlist *);
int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
next prev parent reply other threads:[~2017-12-28 15:26 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-12-05 14:03 [PATCH v6 00/11] perf stat: Enable '--per-thread' on all thread Jin Yao
2017-12-05 10:21 ` Jiri Olsa
2017-12-05 12:21 ` Jin, Yao
2017-12-05 14:03 ` [PATCH v6 01/11] perf util: Define a structure for per-thread shadow stats Jin Yao
2017-12-28 15:21 ` [tip:perf/core] perf stat: " tip-bot for Jin Yao
2017-12-05 14:03 ` [PATCH v6 02/11] perf stat: Extend rbtree to support " Jin Yao
2017-12-28 15:22 ` [tip:perf/core] " tip-bot for Jin Yao
2017-12-05 14:03 ` [PATCH v6 03/11] perf util: Create the runtime_stat init/exit function Jin Yao
2017-12-28 15:22 ` [tip:perf/core] perf stat: " tip-bot for Jin Yao
2017-12-05 14:03 ` [PATCH v6 04/11] perf util: Update per-thread shadow stats Jin Yao
2017-12-28 15:23 ` [tip:perf/core] perf stat: " tip-bot for Jin Yao
2017-12-05 14:03 ` [PATCH v6 05/11] perf util: Print " Jin Yao
2017-12-28 15:23 ` tip-bot for Jin Yao [this message]
2017-12-05 14:03 ` [PATCH v6 06/11] perf util: Remove a set of shadow stats static variables Jin Yao
2017-12-28 15:24 ` [tip:perf/core] perf stat: " tip-bot for Jin Yao
2017-12-05 14:03 ` [PATCH v6 07/11] perf stat: Allocate shadow stats buffer for threads Jin Yao
2017-12-28 15:24 ` [tip:perf/core] " tip-bot for Jin Yao
2017-12-05 14:03 ` [PATCH v6 08/11] perf stat: Update or print per-thread stats Jin Yao
2017-12-28 15:25 ` [tip:perf/core] " tip-bot for Jin Yao
2017-12-05 14:03 ` [PATCH v6 09/11] perf util: Enumerate all threads from /proc Jin Yao
2017-12-28 15:25 ` [tip:perf/core] perf thread_map: " tip-bot for Jin Yao
2017-12-05 14:03 ` [PATCH v6 10/11] perf stat: Remove --per-thread pid/tid limitation Jin Yao
2017-12-28 15:25 ` [tip:perf/core] " tip-bot for Jin Yao
2017-12-05 14:03 ` [PATCH v6 11/11] perf stat: Resort '--per-thread' result Jin Yao
2017-12-28 15:26 ` [tip:perf/core] " tip-bot for Jin Yao
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=tip-e0128b30dbfb2884530251b4accdffdbf55a6b72@git.kernel.org \
--to=tipbot@zytor.com \
--cc=acme@redhat.com \
--cc=ak@linux.intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=hpa@zytor.com \
--cc=jolsa@kernel.org \
--cc=kan.liang@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-tip-commits@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=yao.jin@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.