[PATCH 4/8] perf, tools, stat: Abstract stat metrics printing

From: Andi Kleen
Date: Mon Aug 03 2015 - 20:53:07 EST


From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

Abstract the printing of shadow metrics. Instead of every
metric calling fprintf directly and taking care of indentation,
use two call backs: one to print metrics and another to
start a new line.

This will allow adding metrics to CSV mode and also
using them for other purposes.

The computation of padding is now done in the central
callback, instead of every metric doing it manually.
This makes it easier to add new metrics.

v2: Refactor functions, printout now does more. Move
shadow printing.
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
tools/perf/builtin-stat.c | 96 +++++++++++++++++--------
tools/perf/util/stat-shadow.c | 158 ++++++++++++++++++++++--------------------
tools/perf/util/stat.h | 10 ++-
3 files changed, 158 insertions(+), 106 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index baca81d..31395c8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -617,6 +617,47 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
}
}

+struct outstate {
+ FILE *fh;
+};
+
+#define BASE_INDENT 41
+#define AGGR_INDENT 8
+#define METRIC_LEN 35
+#define NA_INDENT 16
+
+static void new_line_no_aggr_std(void *ctx)
+{
+ struct outstate *os = ctx;
+ fprintf(os->fh, "\n%*s", BASE_INDENT + NA_INDENT, "");
+}
+
+static void new_line_std(void *ctx)
+{
+ struct outstate *os = ctx;
+ fprintf(os->fh, "\n%-*s", BASE_INDENT + AGGR_INDENT, "");
+}
+
+static void print_metric_std(void *ctx, const char *color, const char *fmt,
+ const char *unit, double val)
+{
+ struct outstate *os = ctx;
+ FILE *out = os->fh;
+ int n;
+
+ if (unit == NULL) {
+ fprintf(out, "%-*s", METRIC_LEN, "");
+ return;
+ }
+
+ n = fprintf(out, " # ");
+ if (color)
+ n += color_fprintf(out, color, fmt, val);
+ else
+ n += fprintf(out, fmt, val);
+ fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
+}
+
static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
{
double msecs = avg / 1e6;
@@ -648,7 +689,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
{
double sc = evsel->scale;
const char *fmt;
- int cpu = cpu_map__id_to_cpu(id);

if (csv_output) {
fmt = sc != 1.0 ? "%.2f%s" : "%.0f%s";
@@ -661,9 +701,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)

aggr_printout(evsel, id, nr);

- if (aggr_mode == AGGR_GLOBAL)
- cpu = 0;
-
fprintf(output, fmt, avg, csv_sep);

if (evsel->unit)
@@ -676,10 +713,30 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
if (evsel->cgrp)
fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);

- if (csv_output || interval)
- return;
+}

- perf_stat__print_shadow_stats(output, evsel, avg, cpu, aggr_mode);
+static void printout(int id, int nr, struct perf_evsel *counter, double uval)
+{
+ struct outstate os = { .fh = output };
+ print_metric_t pm = print_metric_std;
+ void (*nl)(void *);
+
+ if (aggr_mode == AGGR_NONE)
+ nl = new_line_no_aggr_std;
+ else
+ nl = new_line_std;
+
+ if (nsec_counter(counter))
+ nsec_printout(id, nr, counter, uval);
+ else
+ abs_printout(id, nr, counter, uval);
+
+ perf_stat__print_shadow_stats(counter, uval,
+ aggr_mode == AGGR_GLOBAL ? 0 :
+ cpu_map__id_to_cpu(id),
+ pm,
+ nl,
+ &os);
}

static void print_aggr(char *prefix)
@@ -735,12 +792,7 @@ static void print_aggr(char *prefix)
continue;
}
uval = val * counter->scale;
-
- if (nsec_counter(counter))
- nsec_printout(id, nr, counter, uval);
- else
- abs_printout(id, nr, counter, uval);
-
+ printout(id, nr, counter, uval);
if (!csv_output)
print_noise(counter, 1.0);

@@ -770,11 +822,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
fprintf(output, "%s", prefix);

uval = val * counter->scale;
-
- if (nsec_counter(counter))
- nsec_printout(thread, 0, counter, uval);
- else
- abs_printout(thread, 0, counter, uval);
+ printout(thread, 0, counter, uval);

if (!csv_output)
print_noise(counter, 1.0);
@@ -823,11 +871,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
}

uval = avg * counter->scale;
-
- if (nsec_counter(counter))
- nsec_printout(-1, 0, counter, uval);
- else
- abs_printout(-1, 0, counter, uval);
+ printout(-1, 0, counter, uval);

print_noise(counter, avg);

@@ -879,11 +923,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
}

uval = val * counter->scale;
-
- if (nsec_counter(counter))
- nsec_printout(cpu, 0, counter, uval);
- else
- abs_printout(cpu, 0, counter, uval);
+ printout(cpu, 0, counter, uval);

if (!csv_output)
print_noise(counter, 1.0);
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 88d23d9..4f56717 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -137,9 +137,11 @@ static const char *get_ratio_color(enum grc_type type, double ratio)
return color;
}

-static void print_stalled_cycles_frontend(FILE *out, int cpu,
+static void print_stalled_cycles_frontend(int cpu,
struct perf_evsel *evsel
- __maybe_unused, double avg)
+ __maybe_unused, double avg,
+ print_metric_t print_metric,
+ void *ctxp)
{
double total, ratio = 0.0;
const char *color;
@@ -152,14 +154,14 @@ static void print_stalled_cycles_frontend(FILE *out, int cpu,

color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);

- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " frontend cycles idle ");
+ print_metric(ctxp, color, "%7.2f%%", "frontend cycles idle", ratio);
}

-static void print_stalled_cycles_backend(FILE *out, int cpu,
+static void print_stalled_cycles_backend(int cpu,
struct perf_evsel *evsel
- __maybe_unused, double avg)
+ __maybe_unused, double avg,
+ print_metric_t print_metric,
+ void *ctxp)
{
double total, ratio = 0.0;
const char *color;
@@ -172,14 +174,14 @@ static void print_stalled_cycles_backend(FILE *out, int cpu,

color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);

- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " backend cycles idle ");
+ print_metric(ctxp, color, "%6.2f%%", "backend cycles idle", ratio);
}

-static void print_branch_misses(FILE *out, int cpu,
+static void print_branch_misses(int cpu,
struct perf_evsel *evsel __maybe_unused,
- double avg)
+ double avg,
+ print_metric_t print_metric,
+ void *ctxp)
{
double total, ratio = 0.0;
const char *color;
@@ -192,14 +194,14 @@ static void print_branch_misses(FILE *out, int cpu,

color = get_ratio_color(GRC_CACHE_MISSES, ratio);

- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " of all branches ");
+ print_metric(ctxp, color, "%7.2f%%", "of all branches", ratio);
}

-static void print_l1_dcache_misses(FILE *out, int cpu,
+static void print_l1_dcache_misses(int cpu,
struct perf_evsel *evsel __maybe_unused,
- double avg)
+ double avg,
+ print_metric_t print_metric,
+ void *ctxp)
{
double total, ratio = 0.0;
const char *color;
@@ -212,14 +214,14 @@ static void print_l1_dcache_misses(FILE *out, int cpu,

color = get_ratio_color(GRC_CACHE_MISSES, ratio);

- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " of all L1-dcache hits ");
+ print_metric(ctxp, color, "%7.2f%%", "of all L1-dcache hits", ratio);
}

-static void print_l1_icache_misses(FILE *out, int cpu,
+static void print_l1_icache_misses(int cpu,
struct perf_evsel *evsel __maybe_unused,
- double avg)
+ double avg,
+ print_metric_t print_metric,
+ void *ctxp)
{
double total, ratio = 0.0;
const char *color;
@@ -231,15 +233,14 @@ static void print_l1_icache_misses(FILE *out, int cpu,
ratio = avg / total * 100.0;

color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " of all L1-icache hits ");
+ print_metric(ctxp, color, "%7.2f%%", "of all L1-icache hits", ratio);
}

-static void print_dtlb_cache_misses(FILE *out, int cpu,
+static void print_dtlb_cache_misses(int cpu,
struct perf_evsel *evsel __maybe_unused,
- double avg)
+ double avg,
+ print_metric_t print_metric,
+ void *ctxp)
{
double total, ratio = 0.0;
const char *color;
@@ -251,15 +252,14 @@ static void print_dtlb_cache_misses(FILE *out, int cpu,
ratio = avg / total * 100.0;

color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " of all dTLB cache hits ");
+ print_metric(ctxp, color, "%7.2f%%", "of all dTLB cache hits", ratio);
}

-static void print_itlb_cache_misses(FILE *out, int cpu,
+static void print_itlb_cache_misses(int cpu,
struct perf_evsel *evsel __maybe_unused,
- double avg)
+ double avg,
+ print_metric_t print_metric,
+ void *ctxp)
{
double total, ratio = 0.0;
const char *color;
@@ -271,15 +271,14 @@ static void print_itlb_cache_misses(FILE *out, int cpu,
ratio = avg / total * 100.0;

color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " of all iTLB cache hits ");
+ print_metric(ctxp, color, "%7.2f%%", "of all iTLB cache hits", ratio);
}

-static void print_ll_cache_misses(FILE *out, int cpu,
+static void print_ll_cache_misses(int cpu,
struct perf_evsel *evsel __maybe_unused,
- double avg)
+ double avg,
+ print_metric_t print_metric,
+ void *ctxp)
{
double total, ratio = 0.0;
const char *color;
@@ -291,14 +290,14 @@ static void print_ll_cache_misses(FILE *out, int cpu,
ratio = avg / total * 100.0;

color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " of all LL-cache hits ");
+ print_metric(ctxp, color, "%7.2f%%", "of all LL-cache hits", ratio);
}

-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
- double avg, int cpu, enum aggr_mode aggr)
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+ double avg, int cpu,
+ print_metric_t print_metric,
+ void (*new_line)(void *ctx),
+ void *ctxp)
{
double total, ratio = 0.0, total2;
int ctx = evsel_context(evsel);
@@ -307,59 +306,60 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
if (total) {
ratio = avg / total;
- fprintf(out, " # %5.2f insns per cycle ", ratio);
+ print_metric(ctxp, NULL, "%7.2f ",
+ "insn per cycle", ratio);
} else {
- fprintf(out, " ");
+ print_metric(ctxp, NULL, NULL, NULL, 0);
}
total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));

if (total && avg) {
ratio = total / avg;
- fprintf(out, "\n");
- if (aggr == AGGR_NONE)
- fprintf(out, " ");
- fprintf(out, " # %5.2f stalled cycles per insn", ratio);
+ new_line(ctxp);
+ print_metric(ctxp, NULL, "%7.2f ",
+ "stalled cycles per insn",
+ ratio);
}

} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
runtime_branches_stats[ctx][cpu].n != 0) {
- print_branch_misses(out, cpu, evsel, avg);
+ print_branch_misses(cpu, evsel, avg, print_metric, ctxp);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_l1_dcache_stats[ctx][cpu].n != 0) {
- print_l1_dcache_misses(out, cpu, evsel, avg);
+ print_l1_dcache_misses(cpu, evsel, avg, print_metric, ctxp);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_l1_icache_stats[ctx][cpu].n != 0) {
- print_l1_icache_misses(out, cpu, evsel, avg);
+ print_l1_icache_misses(cpu, evsel, avg, print_metric, ctxp);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
- print_dtlb_cache_misses(out, cpu, evsel, avg);
+ print_dtlb_cache_misses(cpu, evsel, avg, print_metric, ctxp);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_itlb_cache_stats[ctx][cpu].n != 0) {
- print_itlb_cache_misses(out, cpu, evsel, avg);
+ print_itlb_cache_misses(cpu, evsel, avg, print_metric, ctxp);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_ll_cache_stats[ctx][cpu].n != 0) {
- print_ll_cache_misses(out, cpu, evsel, avg);
+ print_ll_cache_misses(cpu, evsel, avg, print_metric, ctxp);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
runtime_cacherefs_stats[ctx][cpu].n != 0) {
total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
@@ -367,36 +367,41 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
if (total)
ratio = avg * 100 / total;

- fprintf(out, " # %8.3f %% of all cache refs ", ratio);
-
+ print_metric(ctxp, NULL, "%8.3f %%",
+ "of all cache refs", ratio);
} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
- print_stalled_cycles_frontend(out, cpu, evsel, avg);
+ print_stalled_cycles_frontend(cpu, evsel, avg, print_metric,
+ ctxp);
} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
- print_stalled_cycles_backend(out, cpu, evsel, avg);
+ print_stalled_cycles_backend(cpu, evsel, avg, print_metric,
+ ctxp);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
total = avg_stats(&runtime_nsecs_stats[cpu]);

if (total) {
ratio = avg / total;
- fprintf(out, " # %8.3f GHz ", ratio);
+ print_metric(ctxp, NULL, "%8.3f", "GHz", ratio);
} else {
- fprintf(out, " ");
+ print_metric(ctxp, NULL, NULL, NULL, 0);
}
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
if (total)
- fprintf(out,
- " # %5.2f%% transactional cycles ",
- 100.0 * (avg / total));
+ print_metric(ctxp, NULL,
+ "%7.2f%%", "transactional cycles",
+ 100.0 * (avg / total));
+ else
+ print_metric(ctxp, NULL, NULL, NULL, 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]);
if (total2 < avg)
total2 = avg;
if (total)
- fprintf(out,
- " # %5.2f%% aborted cycles ",
+ print_metric(ctxp, NULL, "%7.2f%%", "aborted cycles",
100.0 * ((total2-avg) / total));
+ else
+ print_metric(ctxp, NULL, NULL, NULL, 0);
} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
avg > 0 &&
runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
@@ -405,7 +410,8 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
if (total)
ratio = total / avg;

- fprintf(out, " # %8.0f cycles / transaction ", ratio);
+ print_metric(ctxp, NULL, "%8.0f",
+ "cycles / transaction", ratio);
} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
avg > 0 &&
runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
@@ -414,13 +420,13 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
if (total)
ratio = total / avg;

- fprintf(out, " # %8.0f cycles / elision ", ratio);
+ print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) &&
(ratio = avg_stats(&walltime_nsecs_stats)) != 0) {
- fprintf(output, " # %8.3f CPUs utilized ",
- avg / ratio);
+ print_metric(ctxp, NULL, "%8.3f", "CPUs utilized", avg / ratio);
} else if (runtime_nsecs_stats[cpu].n != 0) {
char unit = 'M';
+ char unit_buf[10];

total = avg_stats(&runtime_nsecs_stats[cpu]);

@@ -430,9 +436,9 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
ratio *= 1000;
unit = 'K';
}
-
- fprintf(out, " # %8.3f %c/sec ", ratio, unit);
+ snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
+ print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
} else {
- fprintf(out, " ");
+ print_metric(ctxp, NULL, NULL, NULL, 0);
}
}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 1cfbe0a..152322d 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -83,11 +83,17 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel);

extern struct stats walltime_nsecs_stats;

+typedef void (*print_metric_t)(void *ctx, const char *color, const char *unit,
+ const char *fmt, double val);
+
void perf_stat__reset_shadow_stats(void);
void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
int cpu);
-void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
- double avg, int cpu, enum aggr_mode aggr);
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+ double avg, int cpu,
+ print_metric_t print_metric,
+ void (*new_line)(void *ctx),
+ void *ctx);

struct perf_counts *perf_counts__new(int ncpus, int nthreads);
void perf_counts__delete(struct perf_counts *counts);
--
2.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/