* [PATCH 1/8] perf, tools, stat: Abstract stat metrics printing
2016-01-30 17:06 perf, tools: Refactor and support interval and CSV metrics Andi Kleen
@ 2016-01-30 17:06 ` Andi Kleen
2016-02-16 19:33 ` Arnaldo Carvalho de Melo
2016-02-17 12:09 ` [tip:perf/core] perf " tip-bot for Andi Kleen
2016-01-30 17:06 ` [PATCH 2/8] perf, tools, stat: Add support for metrics in interval mode Andi Kleen
` (6 subsequent siblings)
7 siblings, 2 replies; 20+ messages in thread
From: Andi Kleen @ 2016-01-30 17:06 UTC (permalink / raw)
To: acme; +Cc: jolsa, eranian, mingo, linux-kernel, Andi Kleen
From: Andi Kleen <ak@linux.intel.com>
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. Improve fallback callbacks. Don't
use void * callback data.
v3: Remove unnecessary hunk. Add typedef for new_line
v4: Remove unnecessary hunk. Don't print metrics for CSV/interval
mode yet. Move printout change to separate patch.
v5: Fix bisect bugs. Avoid bogus frontend cycles printing.
Fix indentation in different aggregation modes.
v6: Delay newline handling
Acked-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
tools/perf/builtin-stat.c | 71 ++++++++++++--
tools/perf/util/stat-shadow.c | 211 +++++++++++++++++++++++-------------------
tools/perf/util/stat.h | 15 ++-
3 files changed, 194 insertions(+), 103 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7f56824..b675b5e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -735,6 +735,58 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
}
}
+struct outstate {
+ FILE *fh;
+ bool newline;
+};
+
+#define METRIC_LEN 35
+
+static void new_line_std(void *ctx)
+{
+ struct outstate *os = ctx;
+
+ os->newline = true;
+}
+
+static void do_new_line_std(struct outstate *os)
+{
+ fputc('\n', os->fh);
+ 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, " ");
+}
+
+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;
+ bool newline = os->newline;
+
+ os->newline = false;
+
+ if (unit == NULL || fmt == NULL) {
+ fprintf(out, "%-*s", METRIC_LEN, "");
+ return;
+ }
+
+ if (newline)
+ do_new_line_std(os);
+
+ 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)
{
FILE *output = stat_config.output;
@@ -795,20 +847,27 @@ 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)
{
- int cpu = cpu_map__id_to_cpu(id);
+ struct outstate os = { .fh = stat_config.output };
+ struct perf_stat_output_ctx out;
+ print_metric_t pm = print_metric_std;
+ void (*nl)(void *);
- if (stat_config.aggr_mode == AGGR_GLOBAL)
- cpu = 0;
+ nl = new_line_std;
if (nsec_counter(counter))
nsec_printout(id, nr, counter, uval);
else
abs_printout(id, nr, counter, uval);
+ out.print_metric = pm;
+ out.new_line = nl;
+ out.ctx = &os;
+
if (!csv_output && !stat_config.interval)
- perf_stat__print_shadow_stats(stat_config.output, counter,
- uval, cpu,
- stat_config.aggr_mode);
+ perf_stat__print_shadow_stats(counter, uval,
+ stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
+ cpu_map__id_to_cpu(id),
+ &out);
}
static void print_aggr(char *prefix)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 6ac0314..4d8f185 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -137,9 +137,10 @@ 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -152,14 +153,17 @@ 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 ");
+ if (ratio)
+ out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+ ratio);
+ else
+ out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
}
-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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -172,14 +176,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -192,14 +195,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -212,14 +214,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -231,15 +232,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -251,15 +250,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -271,15 +268,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -291,15 +286,15 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
+ void *ctxp = out->ctx;
+ print_metric_t print_metric = out->print_metric;
double total, ratio = 0.0, total2;
int ctx = evsel_context(evsel);
@@ -307,119 +302,145 @@ 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, "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]));
+ out->new_line(ctxp);
if (total && avg) {
ratio = total / avg;
- fprintf(out, "\n");
- if (aggr == AGGR_NONE)
- fprintf(out, " ");
- fprintf(out, " # %5.2f stalled cycles per insn", ratio);
+ print_metric(ctxp, NULL, "%7.2f ",
+ "stalled cycles per insn",
+ ratio);
+ } else {
+ print_metric(ctxp, NULL, NULL,
+ "stalled cycles per insn", 0);
}
-
- } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
- runtime_branches_stats[ctx][cpu].n != 0) {
- print_branch_misses(out, cpu, evsel, avg);
+ } 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);
+ else
+ print_metric(ctxp, NULL, NULL, "of all branches", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
+ print_l1_dcache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_l1_icache_stats[ctx][cpu].n != 0)
+ print_l1_icache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
+ print_dtlb_cache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
+ print_itlb_cache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
} 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);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
- runtime_cacherefs_stats[ctx][cpu].n != 0) {
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_ll_cache_stats[ctx][cpu].n != 0)
+ print_ll_cache_misses(cpu, evsel, avg, out);
+ 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]);
if (total)
ratio = avg * 100 / total;
- fprintf(out, " # %8.3f %% of all cache refs ", ratio);
-
+ if (runtime_cacherefs_stats[ctx][cpu].n != 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(out, cpu, evsel, avg);
+ print_stalled_cycles_frontend(cpu, evsel, avg, out);
} 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, out);
} 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, "Ghz", 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, "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]);
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 if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
- runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ 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]);
if (avg)
ratio = total / avg;
- fprintf(out, " # %8.0f cycles / transaction ", ratio);
- } else if (perf_stat_evsel__is(evsel, ELISION_START) &&
- runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+ print_metric(ctxp, NULL, "%8.0f",
+ "cycles / transaction", ratio);
+ else
+ print_metric(ctxp, NULL, NULL, "cycles / transaction",
+ 0);
+ } else if (perf_stat_evsel__is(evsel, ELISION_START)) {
total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
if (avg)
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)) {
if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
- fprintf(out, " # %8.3f CPUs utilized ", avg / ratio);
+ print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+ avg / ratio);
else
- fprintf(out, " ");
+ print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
} else if (runtime_nsecs_stats[cpu].n != 0) {
char unit = 'M';
+ char unit_buf[10];
total = avg_stats(&runtime_nsecs_stats[cpu]);
@@ -429,9 +450,9 @@ 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 086f4e1..f14c0f4 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -68,11 +68,22 @@ 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);
+typedef void (*new_line_t )(void *ctx);
+
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);
+struct perf_stat_output_ctx {
+ void *ctx;
+ print_metric_t print_metric;
+ new_line_t new_line;
+};
+
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+ double avg, int cpu,
+ struct perf_stat_output_ctx *out);
void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
--
2.4.3
^ permalink raw reply related [flat|nested] 20+ messages in thread
* Re: [PATCH 1/8] perf, tools, stat: Abstract stat metrics printing
2016-01-30 17:06 ` [PATCH 1/8] perf, tools, stat: Abstract stat metrics printing Andi Kleen
@ 2016-02-16 19:33 ` Arnaldo Carvalho de Melo
2016-02-17 12:09 ` [tip:perf/core] perf " tip-bot for Andi Kleen
1 sibling, 0 replies; 20+ messages in thread
From: Arnaldo Carvalho de Melo @ 2016-02-16 19:33 UTC (permalink / raw)
To: Andi Kleen; +Cc: jolsa, eranian, mingo, linux-kernel, Andi Kleen
Em Sat, Jan 30, 2016 at 09:06:49AM -0800, Andi Kleen escreveu:
> v2: Refactor functions, printout now does more. Move
> shadow printing. Improve fallback callbacks. Don't
> use void * callback data.
> v3: Remove unnecessary hunk. Add typedef for new_line
> v4: Remove unnecessary hunk. Don't print metrics for CSV/interval
> mode yet. Move printout change to separate patch.
> v5: Fix bisect bugs. Avoid bogus frontend cycles printing.
> Fix indentation in different aggregation modes.
> v6: Delay newline handling
>
> Acked-by: Jiri Olsa <jolsa@redhat.com>
Applied.
- Arnaldo
^ permalink raw reply [flat|nested] 20+ messages in thread
* [tip:perf/core] perf stat: Abstract stat metrics printing
2016-01-30 17:06 ` [PATCH 1/8] perf, tools, stat: Abstract stat metrics printing Andi Kleen
2016-02-16 19:33 ` Arnaldo Carvalho de Melo
@ 2016-02-17 12:09 ` tip-bot for Andi Kleen
1 sibling, 0 replies; 20+ messages in thread
From: tip-bot for Andi Kleen @ 2016-02-17 12:09 UTC (permalink / raw)
To: linux-tip-commits
Cc: ak, hpa, mingo, eranian, tglx, acme, jolsa, linux-kernel
Commit-ID: 140aeadc1fb51d38130fd06a272a381f22e3070c
Gitweb: http://git.kernel.org/tip/140aeadc1fb51d38130fd06a272a381f22e3070c
Author: Andi Kleen <ak@linux.intel.com>
AuthorDate: Sat, 30 Jan 2016 09:06:49 -0800
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 16 Feb 2016 17:13:00 -0300
perf stat: Abstract stat metrics printing
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. Improve fallback callbacks. Don't
use void * callback data.
v3: Remove unnecessary hunk. Add typedef for new_line
v4: Remove unnecessary hunk. Don't print metrics for CSV/interval
mode yet. Move printout change to separate patch.
v5: Fix bisect bugs. Avoid bogus frontend cycles printing.
Fix indentation in different aggregation modes.
v6: Delay newline handling
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1454173616-17710-2-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-stat.c | 71 ++++++++++++--
tools/perf/util/stat-shadow.c | 211 +++++++++++++++++++++++-------------------
tools/perf/util/stat.h | 15 ++-
3 files changed, 194 insertions(+), 103 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 038e877..fabcadb 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -735,6 +735,58 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
}
}
+struct outstate {
+ FILE *fh;
+ bool newline;
+};
+
+#define METRIC_LEN 35
+
+static void new_line_std(void *ctx)
+{
+ struct outstate *os = ctx;
+
+ os->newline = true;
+}
+
+static void do_new_line_std(struct outstate *os)
+{
+ fputc('\n', os->fh);
+ 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, " ");
+}
+
+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;
+ bool newline = os->newline;
+
+ os->newline = false;
+
+ if (unit == NULL || fmt == NULL) {
+ fprintf(out, "%-*s", METRIC_LEN, "");
+ return;
+ }
+
+ if (newline)
+ do_new_line_std(os);
+
+ 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)
{
FILE *output = stat_config.output;
@@ -795,20 +847,27 @@ 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)
{
- int cpu = cpu_map__id_to_cpu(id);
+ struct outstate os = { .fh = stat_config.output };
+ struct perf_stat_output_ctx out;
+ print_metric_t pm = print_metric_std;
+ void (*nl)(void *);
- if (stat_config.aggr_mode == AGGR_GLOBAL)
- cpu = 0;
+ nl = new_line_std;
if (nsec_counter(counter))
nsec_printout(id, nr, counter, uval);
else
abs_printout(id, nr, counter, uval);
+ out.print_metric = pm;
+ out.new_line = nl;
+ out.ctx = &os;
+
if (!csv_output && !stat_config.interval)
- perf_stat__print_shadow_stats(stat_config.output, counter,
- uval, cpu,
- stat_config.aggr_mode);
+ perf_stat__print_shadow_stats(counter, uval,
+ stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
+ cpu_map__id_to_cpu(id),
+ &out);
}
static void print_aggr(char *prefix)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 6ac0314..4d8f185 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -137,9 +137,10 @@ 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -152,14 +153,17 @@ 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 ");
+ if (ratio)
+ out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+ ratio);
+ else
+ out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
}
-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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -172,14 +176,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -192,14 +195,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -212,14 +214,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -231,15 +232,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -251,15 +250,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -271,15 +268,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -291,15 +286,15 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
+ void *ctxp = out->ctx;
+ print_metric_t print_metric = out->print_metric;
double total, ratio = 0.0, total2;
int ctx = evsel_context(evsel);
@@ -307,119 +302,145 @@ 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, "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]));
+ out->new_line(ctxp);
if (total && avg) {
ratio = total / avg;
- fprintf(out, "\n");
- if (aggr == AGGR_NONE)
- fprintf(out, " ");
- fprintf(out, " # %5.2f stalled cycles per insn", ratio);
+ print_metric(ctxp, NULL, "%7.2f ",
+ "stalled cycles per insn",
+ ratio);
+ } else {
+ print_metric(ctxp, NULL, NULL,
+ "stalled cycles per insn", 0);
}
-
- } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
- runtime_branches_stats[ctx][cpu].n != 0) {
- print_branch_misses(out, cpu, evsel, avg);
+ } 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);
+ else
+ print_metric(ctxp, NULL, NULL, "of all branches", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
+ print_l1_dcache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_l1_icache_stats[ctx][cpu].n != 0)
+ print_l1_icache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
+ print_dtlb_cache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
+ print_itlb_cache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
} 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);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
- runtime_cacherefs_stats[ctx][cpu].n != 0) {
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_ll_cache_stats[ctx][cpu].n != 0)
+ print_ll_cache_misses(cpu, evsel, avg, out);
+ 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]);
if (total)
ratio = avg * 100 / total;
- fprintf(out, " # %8.3f %% of all cache refs ", ratio);
-
+ if (runtime_cacherefs_stats[ctx][cpu].n != 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(out, cpu, evsel, avg);
+ print_stalled_cycles_frontend(cpu, evsel, avg, out);
} 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, out);
} 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, "Ghz", 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, "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]);
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 if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
- runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ 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]);
if (avg)
ratio = total / avg;
- fprintf(out, " # %8.0f cycles / transaction ", ratio);
- } else if (perf_stat_evsel__is(evsel, ELISION_START) &&
- runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+ print_metric(ctxp, NULL, "%8.0f",
+ "cycles / transaction", ratio);
+ else
+ print_metric(ctxp, NULL, NULL, "cycles / transaction",
+ 0);
+ } else if (perf_stat_evsel__is(evsel, ELISION_START)) {
total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
if (avg)
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)) {
if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
- fprintf(out, " # %8.3f CPUs utilized ", avg / ratio);
+ print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+ avg / ratio);
else
- fprintf(out, " ");
+ print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
} else if (runtime_nsecs_stats[cpu].n != 0) {
char unit = 'M';
+ char unit_buf[10];
total = avg_stats(&runtime_nsecs_stats[cpu]);
@@ -429,9 +450,9 @@ 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 2af63c9..f02af68 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -68,11 +68,22 @@ 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);
+typedef void (*new_line_t )(void *ctx);
+
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);
+struct perf_stat_output_ctx {
+ void *ctx;
+ print_metric_t print_metric;
+ new_line_t new_line;
+};
+
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+ double avg, int cpu,
+ struct perf_stat_output_ctx *out);
int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
void perf_evlist__free_stats(struct perf_evlist *evlist);
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH 2/8] perf, tools, stat: Add support for metrics in interval mode
2016-01-30 17:06 perf, tools: Refactor and support interval and CSV metrics Andi Kleen
2016-01-30 17:06 ` [PATCH 1/8] perf, tools, stat: Abstract stat metrics printing Andi Kleen
@ 2016-01-30 17:06 ` Andi Kleen
2016-02-16 19:57 ` Arnaldo Carvalho de Melo
2016-02-17 12:09 ` [tip:perf/core] perf " tip-bot for Andi Kleen
2016-01-30 17:06 ` [PATCH 3/8] perf, tools, stat: Move noise/running printing into printout Andi Kleen
` (5 subsequent siblings)
7 siblings, 2 replies; 20+ messages in thread
From: Andi Kleen @ 2016-01-30 17:06 UTC (permalink / raw)
To: acme; +Cc: jolsa, eranian, mingo, linux-kernel, Andi Kleen
From: Andi Kleen <ak@linux.intel.com>
Now that we can modify the metrics printout functions easily,
it's straight forward to support metric printing for interval mode.
All that is needed is to print the time stamp on every new line.
Pass the prefix into the context and print it out.
v2: Move wrong hunk to here.
Acked-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
tools/perf/builtin-stat.c | 20 +++++++++++++-------
1 file changed, 13 insertions(+), 7 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b675b5e..c976c63 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -738,6 +738,7 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
struct outstate {
FILE *fh;
bool newline;
+ const char *prefix;
};
#define METRIC_LEN 35
@@ -752,6 +753,7 @@ static void new_line_std(void *ctx)
static void do_new_line_std(struct outstate *os)
{
fputc('\n', os->fh);
+ fputs(os->prefix, os->fh);
if (stat_config.aggr_mode == AGGR_NONE)
fprintf(os->fh, " ");
if (stat_config.aggr_mode == AGGR_CORE)
@@ -845,10 +847,14 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
}
-static void printout(int id, int nr, struct perf_evsel *counter, double uval)
+static void printout(int id, int nr, struct perf_evsel *counter, double uval,
+ char *prefix)
{
- struct outstate os = { .fh = stat_config.output };
struct perf_stat_output_ctx out;
+ struct outstate os = {
+ .fh = stat_config.output,
+ .prefix = prefix ? prefix : ""
+ };
print_metric_t pm = print_metric_std;
void (*nl)(void *);
@@ -863,7 +869,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval)
out.new_line = nl;
out.ctx = &os;
- if (!csv_output && !stat_config.interval)
+ if (!csv_output)
perf_stat__print_shadow_stats(counter, uval,
stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
cpu_map__id_to_cpu(id),
@@ -923,7 +929,7 @@ static void print_aggr(char *prefix)
continue;
}
uval = val * counter->scale;
- printout(id, nr, counter, uval);
+ printout(id, nr, counter, uval, prefix);
if (!csv_output)
print_noise(counter, 1.0);
@@ -954,7 +960,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
fprintf(output, "%s", prefix);
uval = val * counter->scale;
- printout(thread, 0, counter, uval);
+ printout(thread, 0, counter, uval, prefix);
if (!csv_output)
print_noise(counter, 1.0);
@@ -1004,7 +1010,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
}
uval = avg * counter->scale;
- printout(-1, 0, counter, uval);
+ printout(-1, 0, counter, uval, prefix);
print_noise(counter, avg);
@@ -1057,7 +1063,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
}
uval = val * counter->scale;
- printout(cpu, 0, counter, uval);
+ printout(cpu, 0, counter, uval, prefix);
if (!csv_output)
print_noise(counter, 1.0);
print_running(run, ena);
--
2.4.3
^ permalink raw reply related [flat|nested] 20+ messages in thread
* Re: [PATCH 2/8] perf, tools, stat: Add support for metrics in interval mode
2016-01-30 17:06 ` [PATCH 2/8] perf, tools, stat: Add support for metrics in interval mode Andi Kleen
@ 2016-02-16 19:57 ` Arnaldo Carvalho de Melo
2016-02-17 12:09 ` [tip:perf/core] perf " tip-bot for Andi Kleen
1 sibling, 0 replies; 20+ messages in thread
From: Arnaldo Carvalho de Melo @ 2016-02-16 19:57 UTC (permalink / raw)
To: Andi Kleen; +Cc: jolsa, eranian, mingo, linux-kernel, Andi Kleen
Em Sat, Jan 30, 2016 at 09:06:50AM -0800, Andi Kleen escreveu:
> From: Andi Kleen <ak@linux.intel.com>
>
> Now that we can modify the metrics printout functions easily,
> it's straight forward to support metric printing for interval mode.
> All that is needed is to print the time stamp on every new line.
> Pass the prefix into the context and print it out.
>
> v2: Move wrong hunk to here.
> Acked-by: Jiri Olsa <jolsa@redhat.com>
Thanks, applied.
- Arnaldo
^ permalink raw reply [flat|nested] 20+ messages in thread
* [tip:perf/core] perf stat: Add support for metrics in interval mode
2016-01-30 17:06 ` [PATCH 2/8] perf, tools, stat: Add support for metrics in interval mode Andi Kleen
2016-02-16 19:57 ` Arnaldo Carvalho de Melo
@ 2016-02-17 12:09 ` tip-bot for Andi Kleen
1 sibling, 0 replies; 20+ messages in thread
From: tip-bot for Andi Kleen @ 2016-02-17 12:09 UTC (permalink / raw)
To: linux-tip-commits
Cc: mingo, hpa, ak, linux-kernel, eranian, jolsa, tglx, acme
Commit-ID: f94833929032ad23412d3970beed6769a2fdbc19
Gitweb: http://git.kernel.org/tip/f94833929032ad23412d3970beed6769a2fdbc19
Author: Andi Kleen <ak@linux.intel.com>
AuthorDate: Sat, 30 Jan 2016 09:06:50 -0800
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 16 Feb 2016 17:13:01 -0300
perf stat: Add support for metrics in interval mode
Now that we can modify the metrics printout functions easily, it's
straight forward to support metric printing for interval mode. All that
is needed is to print the time stamp on every new line. Pass the prefix
into the context and print it out.
v2: Move wrong hunk to here.
Committer note:
Before:
[root@jouet ~]# perf stat -I 1000 -e instructions,cycles sleep 1
# time counts unit events
1.000168216 538,913 instructions
1.000168216 748,765 cycles
1.000660048 153,741 instructions
1.000660048 214,066 cycles
After:
# perf stat -I 1000 -e instructions,cycles sleep 1
# time counts unit events
1.000215928 519,620 instructions # 0.69 insn per cycle
1.000215928 752,003 cycles
1.000946033 148,502 instructions # 0.33 insn per cycle
1.000946033 160,104 cycles
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1454173616-17710-3-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-stat.c | 20 +++++++++++++-------
1 file changed, 13 insertions(+), 7 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index fabcadb..5710bdb 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -738,6 +738,7 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
struct outstate {
FILE *fh;
bool newline;
+ const char *prefix;
};
#define METRIC_LEN 35
@@ -752,6 +753,7 @@ static void new_line_std(void *ctx)
static void do_new_line_std(struct outstate *os)
{
fputc('\n', os->fh);
+ fputs(os->prefix, os->fh);
if (stat_config.aggr_mode == AGGR_NONE)
fprintf(os->fh, " ");
if (stat_config.aggr_mode == AGGR_CORE)
@@ -845,10 +847,14 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
}
-static void printout(int id, int nr, struct perf_evsel *counter, double uval)
+static void printout(int id, int nr, struct perf_evsel *counter, double uval,
+ char *prefix)
{
- struct outstate os = { .fh = stat_config.output };
struct perf_stat_output_ctx out;
+ struct outstate os = {
+ .fh = stat_config.output,
+ .prefix = prefix ? prefix : ""
+ };
print_metric_t pm = print_metric_std;
void (*nl)(void *);
@@ -863,7 +869,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval)
out.new_line = nl;
out.ctx = &os;
- if (!csv_output && !stat_config.interval)
+ if (!csv_output)
perf_stat__print_shadow_stats(counter, uval,
stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
cpu_map__id_to_cpu(id),
@@ -923,7 +929,7 @@ static void print_aggr(char *prefix)
continue;
}
uval = val * counter->scale;
- printout(id, nr, counter, uval);
+ printout(id, nr, counter, uval, prefix);
if (!csv_output)
print_noise(counter, 1.0);
@@ -954,7 +960,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
fprintf(output, "%s", prefix);
uval = val * counter->scale;
- printout(thread, 0, counter, uval);
+ printout(thread, 0, counter, uval, prefix);
if (!csv_output)
print_noise(counter, 1.0);
@@ -1004,7 +1010,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
}
uval = avg * counter->scale;
- printout(-1, 0, counter, uval);
+ printout(-1, 0, counter, uval, prefix);
print_noise(counter, avg);
@@ -1057,7 +1063,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
}
uval = val * counter->scale;
- printout(cpu, 0, counter, uval);
+ printout(cpu, 0, counter, uval, prefix);
if (!csv_output)
print_noise(counter, 1.0);
print_running(run, ena);
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH 3/8] perf, tools, stat: Move noise/running printing into printout
2016-01-30 17:06 perf, tools: Refactor and support interval and CSV metrics Andi Kleen
2016-01-30 17:06 ` [PATCH 1/8] perf, tools, stat: Abstract stat metrics printing Andi Kleen
2016-01-30 17:06 ` [PATCH 2/8] perf, tools, stat: Add support for metrics in interval mode Andi Kleen
@ 2016-01-30 17:06 ` Andi Kleen
2016-02-16 20:02 ` Arnaldo Carvalho de Melo
2016-02-17 12:10 ` [tip:perf/core] perf stat: Move noise/ running " tip-bot for Andi Kleen
2016-01-30 17:06 ` [PATCH 4/8] perf, tools, stat: Implement CSV metrics output Andi Kleen
` (4 subsequent siblings)
7 siblings, 2 replies; 20+ messages in thread
From: Andi Kleen @ 2016-01-30 17:06 UTC (permalink / raw)
To: acme; +Cc: jolsa, eranian, mingo, linux-kernel, Andi Kleen
From: Andi Kleen <ak@linux.intel.com>
Move the running/noise printing into printout to avoid
duplicated code in the callers.
v2: Merged with other patches. Remove unnecessary hunk.
Readd hunk that ended in earlier patch.
v3: Fix noise/running output in CSV mode
v4: Merge with later patch that also moves not supported printing.
Acked-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
tools/perf/builtin-stat.c | 123 ++++++++++++----------------------------------
1 file changed, 32 insertions(+), 91 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index c976c63..bfb6e07 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -848,7 +848,7 @@ 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)
+ char *prefix, u64 run, u64 ena, double noise)
{
struct perf_stat_output_ctx out;
struct outstate os = {
@@ -860,6 +860,30 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
nl = new_line_std;
+ if (run == 0 || ena == 0) {
+ aggr_printout(counter, id, nr);
+
+ fprintf(stat_config.output, "%*s%s",
+ csv_output ? 0 : 18,
+ counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+ csv_sep);
+
+ fprintf(stat_config.output, "%-*s%s",
+ csv_output ? 0 : unit_width,
+ counter->unit, csv_sep);
+
+ fprintf(stat_config.output, "%*s",
+ csv_output ? 0 : -25,
+ perf_evsel__name(counter));
+
+ if (counter->cgrp)
+ fprintf(stat_config.output, "%s%s",
+ csv_sep, counter->cgrp->name);
+
+ print_running(run, ena);
+ return;
+ }
+
if (nsec_counter(counter))
nsec_printout(id, nr, counter, uval);
else
@@ -874,6 +898,9 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
cpu_map__id_to_cpu(id),
&out);
+
+ print_noise(counter, noise);
+ print_running(run, ena);
}
static void print_aggr(char *prefix)
@@ -904,36 +931,8 @@ static void print_aggr(char *prefix)
if (prefix)
fprintf(output, "%s", prefix);
- if (run == 0 || ena == 0) {
- aggr_printout(counter, id, nr);
-
- fprintf(output, "%*s%s",
- csv_output ? 0 : 18,
- counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
- csv_sep);
-
- fprintf(output, "%-*s%s",
- csv_output ? 0 : unit_width,
- counter->unit, csv_sep);
-
- fprintf(output, "%*s",
- csv_output ? 0 : -25,
- perf_evsel__name(counter));
-
- if (counter->cgrp)
- fprintf(output, "%s%s",
- csv_sep, counter->cgrp->name);
-
- print_running(run, ena);
- fputc('\n', output);
- continue;
- }
uval = val * counter->scale;
- printout(id, nr, counter, uval, prefix);
- if (!csv_output)
- print_noise(counter, 1.0);
-
- print_running(run, ena);
+ printout(id, nr, counter, uval, prefix, run, ena, 1.0);
fputc('\n', output);
}
}
@@ -960,12 +959,7 @@ 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);
-
- if (!csv_output)
- print_noise(counter, 1.0);
-
- print_running(run, ena);
+ printout(thread, 0, counter, uval, prefix, run, ena, 1.0);
fputc('\n', output);
}
}
@@ -979,7 +973,6 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
FILE *output = stat_config.output;
struct perf_stat_evsel *ps = counter->priv;
double avg = avg_stats(&ps->res_stats[0]);
- int scaled = counter->counts->scaled;
double uval;
double avg_enabled, avg_running;
@@ -989,32 +982,8 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
if (prefix)
fprintf(output, "%s", prefix);
- if (scaled == -1 || !counter->supported) {
- fprintf(output, "%*s%s",
- csv_output ? 0 : 18,
- counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
- csv_sep);
- fprintf(output, "%-*s%s",
- csv_output ? 0 : unit_width,
- counter->unit, csv_sep);
- fprintf(output, "%*s",
- csv_output ? 0 : -25,
- perf_evsel__name(counter));
-
- if (counter->cgrp)
- fprintf(output, "%s%s", csv_sep, counter->cgrp->name);
-
- print_running(avg_running, avg_enabled);
- fputc('\n', output);
- return;
- }
-
uval = avg * counter->scale;
- printout(-1, 0, counter, uval, prefix);
-
- print_noise(counter, avg);
-
- print_running(avg_running, avg_enabled);
+ printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
fprintf(output, "\n");
}
@@ -1037,36 +1006,8 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
if (prefix)
fprintf(output, "%s", prefix);
- if (run == 0 || ena == 0) {
- fprintf(output, "CPU%*d%s%*s%s",
- csv_output ? 0 : -4,
- perf_evsel__cpus(counter)->map[cpu], csv_sep,
- csv_output ? 0 : 18,
- counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
- csv_sep);
-
- fprintf(output, "%-*s%s",
- csv_output ? 0 : unit_width,
- counter->unit, csv_sep);
-
- fprintf(output, "%*s",
- csv_output ? 0 : -25,
- perf_evsel__name(counter));
-
- if (counter->cgrp)
- fprintf(output, "%s%s",
- csv_sep, counter->cgrp->name);
-
- print_running(run, ena);
- fputc('\n', output);
- continue;
- }
-
uval = val * counter->scale;
- printout(cpu, 0, counter, uval, prefix);
- if (!csv_output)
- print_noise(counter, 1.0);
- print_running(run, ena);
+ printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
fputc('\n', output);
}
--
2.4.3
^ permalink raw reply related [flat|nested] 20+ messages in thread
* Re: [PATCH 3/8] perf, tools, stat: Move noise/running printing into printout
2016-01-30 17:06 ` [PATCH 3/8] perf, tools, stat: Move noise/running printing into printout Andi Kleen
@ 2016-02-16 20:02 ` Arnaldo Carvalho de Melo
2016-02-17 19:27 ` Andi Kleen
2016-02-17 12:10 ` [tip:perf/core] perf stat: Move noise/ running " tip-bot for Andi Kleen
1 sibling, 1 reply; 20+ messages in thread
From: Arnaldo Carvalho de Melo @ 2016-02-16 20:02 UTC (permalink / raw)
To: Andi Kleen; +Cc: jolsa, eranian, mingo, linux-kernel, Andi Kleen
Em Sat, Jan 30, 2016 at 09:06:51AM -0800, Andi Kleen escreveu:
> From: Andi Kleen <ak@linux.intel.com>
>
> Move the running/noise printing into printout to avoid
> duplicated code in the callers.
>
> v2: Merged with other patches. Remove unnecessary hunk.
> Readd hunk that ended in earlier patch.
> v3: Fix noise/running output in CSV mode
> v4: Merge with later patch that also moves not supported printing.
> Acked-by: Jiri Olsa <jolsa@kernel.org>
So, the description makes it look like this is just elliminating code
duplication, but then, before we had:
[acme@jouet linux]$ perf.old stat -I 500 -e instructions,cycles sleep 1
# time counts unit events
0.500164711 548,376 instructions # 0.72 insn per cycle
0.500164711 756,872 cycles
1.000405470 <not counted> instructions
1.000405470 <not counted> cycles
1.000690913 156,623 instructions # 0.48 insn per cycle
1.000690913 226,630 cycles
[acme@jouet linux]$
And now we have instead:
[acme@jouet linux]$ perf stat -I 500 -e instructions,cycles sleep 1
# time counts unit events
0.500173751 555,962 instructions # 0.77 insn per cycle
0.500173751 722,964 cycles
1.000382613 0 instructions # 0.00 insn per cycle
1.000382613 0 cycles
1.001157068 154,765 instructions # 0.49 insn per cycle
1.001157068 223,609 cycles
[acme@jouet linux]$
So there is a change in behaviour.
- Arnaldo
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH 3/8] perf, tools, stat: Move noise/running printing into printout
2016-02-16 20:02 ` Arnaldo Carvalho de Melo
@ 2016-02-17 19:27 ` Andi Kleen
0 siblings, 0 replies; 20+ messages in thread
From: Andi Kleen @ 2016-02-17 19:27 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Andi Kleen, jolsa, eranian, mingo, linux-kernel, Andi Kleen
On Tue, Feb 16, 2016 at 05:02:56PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Sat, Jan 30, 2016 at 09:06:51AM -0800, Andi Kleen escreveu:
> > From: Andi Kleen <ak@linux.intel.com>
> >
> > Move the running/noise printing into printout to avoid
> > duplicated code in the callers.
> >
> > v2: Merged with other patches. Remove unnecessary hunk.
> > Readd hunk that ended in earlier patch.
> > v3: Fix noise/running output in CSV mode
> > v4: Merge with later patch that also moves not supported printing.
> > Acked-by: Jiri Olsa <jolsa@kernel.org>
>
> So, the description makes it look like this is just elliminating code
> duplication, but then, before we had:
Thanks. Here's a patch to fix it.
----
perf, tools, stat: Handled scaled == -1 case for counters
Arnaldo pointed out that the earlier
"Move noise/running printing into printout"
change changed behavior for not counted counters. This patch fixes it again.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 15e4fcf..86289df 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -860,7 +860,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
nl = new_line_std;
- if (run == 0 || ena == 0) {
+ if (run == 0 || ena == 0 || counter->counts->scaled == -1) {
aggr_printout(counter, id, nr);
fprintf(stat_config.output, "%*s%s",
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [tip:perf/core] perf stat: Move noise/ running printing into printout
2016-01-30 17:06 ` [PATCH 3/8] perf, tools, stat: Move noise/running printing into printout Andi Kleen
2016-02-16 20:02 ` Arnaldo Carvalho de Melo
@ 2016-02-17 12:10 ` tip-bot for Andi Kleen
1 sibling, 0 replies; 20+ messages in thread
From: tip-bot for Andi Kleen @ 2016-02-17 12:10 UTC (permalink / raw)
To: linux-tip-commits
Cc: tglx, ak, mingo, eranian, acme, hpa, linux-kernel, jolsa
Commit-ID: cb110f471025f3278978aaccb18f3164ea2b8189
Gitweb: http://git.kernel.org/tip/cb110f471025f3278978aaccb18f3164ea2b8189
Author: Andi Kleen <ak@linux.intel.com>
AuthorDate: Sat, 30 Jan 2016 09:06:51 -0800
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 16 Feb 2016 17:13:02 -0300
perf stat: Move noise/running printing into printout
Move the running/noise printing into printout to avoid duplicated code
in the callers.
v2: Merged with other patches. Remove unnecessary hunk.
Readd hunk that ended in earlier patch.
v3: Fix noise/running output in CSV mode
v4: Merge with later patch that also moves not supported printing.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1454173616-17710-4-git-send-email-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/builtin-stat.c | 123 ++++++++++++----------------------------------
1 file changed, 32 insertions(+), 91 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 5710bdb..15e4fcf 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -848,7 +848,7 @@ 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)
+ char *prefix, u64 run, u64 ena, double noise)
{
struct perf_stat_output_ctx out;
struct outstate os = {
@@ -860,6 +860,30 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
nl = new_line_std;
+ if (run == 0 || ena == 0) {
+ aggr_printout(counter, id, nr);
+
+ fprintf(stat_config.output, "%*s%s",
+ csv_output ? 0 : 18,
+ counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
+ csv_sep);
+
+ fprintf(stat_config.output, "%-*s%s",
+ csv_output ? 0 : unit_width,
+ counter->unit, csv_sep);
+
+ fprintf(stat_config.output, "%*s",
+ csv_output ? 0 : -25,
+ perf_evsel__name(counter));
+
+ if (counter->cgrp)
+ fprintf(stat_config.output, "%s%s",
+ csv_sep, counter->cgrp->name);
+
+ print_running(run, ena);
+ return;
+ }
+
if (nsec_counter(counter))
nsec_printout(id, nr, counter, uval);
else
@@ -874,6 +898,9 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
cpu_map__id_to_cpu(id),
&out);
+
+ print_noise(counter, noise);
+ print_running(run, ena);
}
static void print_aggr(char *prefix)
@@ -904,36 +931,8 @@ static void print_aggr(char *prefix)
if (prefix)
fprintf(output, "%s", prefix);
- if (run == 0 || ena == 0) {
- aggr_printout(counter, id, nr);
-
- fprintf(output, "%*s%s",
- csv_output ? 0 : 18,
- counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
- csv_sep);
-
- fprintf(output, "%-*s%s",
- csv_output ? 0 : unit_width,
- counter->unit, csv_sep);
-
- fprintf(output, "%*s",
- csv_output ? 0 : -25,
- perf_evsel__name(counter));
-
- if (counter->cgrp)
- fprintf(output, "%s%s",
- csv_sep, counter->cgrp->name);
-
- print_running(run, ena);
- fputc('\n', output);
- continue;
- }
uval = val * counter->scale;
- printout(id, nr, counter, uval, prefix);
- if (!csv_output)
- print_noise(counter, 1.0);
-
- print_running(run, ena);
+ printout(id, nr, counter, uval, prefix, run, ena, 1.0);
fputc('\n', output);
}
}
@@ -960,12 +959,7 @@ 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);
-
- if (!csv_output)
- print_noise(counter, 1.0);
-
- print_running(run, ena);
+ printout(thread, 0, counter, uval, prefix, run, ena, 1.0);
fputc('\n', output);
}
}
@@ -979,7 +973,6 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
FILE *output = stat_config.output;
struct perf_stat_evsel *ps = counter->priv;
double avg = avg_stats(&ps->res_stats[0]);
- int scaled = counter->counts->scaled;
double uval;
double avg_enabled, avg_running;
@@ -989,32 +982,8 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
if (prefix)
fprintf(output, "%s", prefix);
- if (scaled == -1 || !counter->supported) {
- fprintf(output, "%*s%s",
- csv_output ? 0 : 18,
- counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
- csv_sep);
- fprintf(output, "%-*s%s",
- csv_output ? 0 : unit_width,
- counter->unit, csv_sep);
- fprintf(output, "%*s",
- csv_output ? 0 : -25,
- perf_evsel__name(counter));
-
- if (counter->cgrp)
- fprintf(output, "%s%s", csv_sep, counter->cgrp->name);
-
- print_running(avg_running, avg_enabled);
- fputc('\n', output);
- return;
- }
-
uval = avg * counter->scale;
- printout(-1, 0, counter, uval, prefix);
-
- print_noise(counter, avg);
-
- print_running(avg_running, avg_enabled);
+ printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
fprintf(output, "\n");
}
@@ -1037,36 +1006,8 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
if (prefix)
fprintf(output, "%s", prefix);
- if (run == 0 || ena == 0) {
- fprintf(output, "CPU%*d%s%*s%s",
- csv_output ? 0 : -4,
- perf_evsel__cpus(counter)->map[cpu], csv_sep,
- csv_output ? 0 : 18,
- counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
- csv_sep);
-
- fprintf(output, "%-*s%s",
- csv_output ? 0 : unit_width,
- counter->unit, csv_sep);
-
- fprintf(output, "%*s",
- csv_output ? 0 : -25,
- perf_evsel__name(counter));
-
- if (counter->cgrp)
- fprintf(output, "%s%s",
- csv_sep, counter->cgrp->name);
-
- print_running(run, ena);
- fputc('\n', output);
- continue;
- }
-
uval = val * counter->scale;
- printout(cpu, 0, counter, uval, prefix);
- if (!csv_output)
- print_noise(counter, 1.0);
- print_running(run, ena);
+ printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
fputc('\n', output);
}
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH 4/8] perf, tools, stat: Implement CSV metrics output
2016-01-30 17:06 perf, tools: Refactor and support interval and CSV metrics Andi Kleen
` (2 preceding siblings ...)
2016-01-30 17:06 ` [PATCH 3/8] perf, tools, stat: Move noise/running printing into printout Andi Kleen
@ 2016-01-30 17:06 ` Andi Kleen
2016-02-02 9:50 ` Jiri Olsa
2016-01-30 17:06 ` [PATCH 5/8] perf, tools, stat: Support metrics in --per-core/socket mode Andi Kleen
` (3 subsequent siblings)
7 siblings, 1 reply; 20+ messages in thread
From: Andi Kleen @ 2016-01-30 17:06 UTC (permalink / raw)
To: acme; +Cc: jolsa, eranian, mingo, linux-kernel, Andi Kleen
From: Andi Kleen <ak@linux.intel.com>
Now support CSV output for metrics. With the new output callbacks
this is relatively straight forward by creating new callbacks.
The new line callback needs to know the number of fields to skip them
correctly
Example output before:
% perf stat -x, true
0.200687,,task-clock,200687,100.00
0,,context-switches,200687,100.00
0,,cpu-migrations,200687,100.00
40,,page-faults,200687,100.00
730871,,cycles,203601,100.00
551056,,stalled-cycles-frontend,203601,100.00
<not supported>,,stalled-cycles-backend,0,100.00
385523,,instructions,203601,100.00
78028,,branches,203601,100.00
3946,,branch-misses,203601,100.00
After:
% perf stat -x, true
0.341119,,task-clock,0.461,CPUs utilized,0.00%,324342,100.00
0,,context-switches,0.000,K/sec,0.00%,324342,100.00
0,,cpu-migrations,0.000,K/sec,0.00%,324342,100.00
41,,page-faults,0.126,M/sec,0.00%,324342,100.00
674068,,cycles,2.078,GHz,0.00%,330887,100.00
508189,,stalled-cycles-frontend,82.31,frontend cycles idle,0.00%,330887,100.00
<not supported>,,stalled-cycles-backend,,,0.00%,0,100.00
374932,,instructions,0.61,insn per cycle
,,,1.20,stalled cycles per insn,0.00%,330887,100.00
76540,,branches,235.985,M/sec,0.00%,330887,100.00
3091,,branch-misses,4.09,of all branches,0.00%,330887,100.00
Two new fields are added: metric value and metric name before
the running/enabled fields.
v2: Split out function argument changes
v3: Reenable metrics for real.
v4: Fix wrong hunk from refactoring.
v5: Remove extra "noise" printing (Jiri), but add it to the not counted case.
Print empty metrics for not counted.
v6: Avoid outputting metric on empty format.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
tools/perf/builtin-stat.c | 62 +++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 60 insertions(+), 2 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index bfb6e07..86caf70 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -739,6 +739,8 @@ struct outstate {
FILE *fh;
bool newline;
const char *prefix;
+ int nfields;
+ u64 run, ena;
};
#define METRIC_LEN 35
@@ -789,6 +791,43 @@ static void print_metric_std(void *ctx, const char *color, const char *fmt,
fprintf(out, " %-*s", METRIC_LEN - n - 1, unit);
}
+static void new_line_csv(void *ctx)
+{
+ struct outstate *os = ctx;
+ int i;
+
+ fputc('\n', os->fh);
+ if (os->prefix)
+ fprintf(os->fh, "%s%s", os->prefix, csv_sep);
+ for (i = 0; i < os->nfields; i++)
+ fputs(csv_sep, os->fh);
+}
+
+static void print_metric_csv(void *ctx,
+ const char *color __maybe_unused,
+ const char *fmt, const char *unit, double val)
+{
+ struct outstate *os = ctx;
+ FILE *out = os->fh;
+ char buf[64], *vals, *ends;
+
+ if (unit == NULL || fmt == NULL) {
+ fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep);
+ return;
+ }
+ snprintf(buf, sizeof(buf), fmt, val);
+ vals = buf;
+ while (isspace(*vals))
+ vals++;
+ ends = vals;
+ while (isdigit(*ends) || *ends == '.')
+ ends++;
+ *ends = 0;
+ while (isspace(*unit))
+ unit++;
+ fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
+}
+
static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
{
FILE *output = stat_config.output;
@@ -860,6 +899,24 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
nl = new_line_std;
+ if (csv_output) {
+ static int aggr_fields[] = {
+ [AGGR_GLOBAL] = 0,
+ [AGGR_THREAD] = 1,
+ [AGGR_NONE] = 1,
+ [AGGR_SOCKET] = 2,
+ [AGGR_CORE] = 2,
+ };
+
+ pm = print_metric_csv;
+ nl = new_line_csv;
+ os.nfields = 1;
+ os.nfields += aggr_fields[stat_config.aggr_mode];
+ if (counter->cgrp)
+ os.nfields++;
+ os.run = run;
+ os.ena = ena;
+ }
if (run == 0 || ena == 0) {
aggr_printout(counter, id, nr);
@@ -880,6 +937,8 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
fprintf(stat_config.output, "%s%s",
csv_sep, counter->cgrp->name);
+ pm(&os, NULL, NULL, "", 0);
+ print_noise(counter, noise);
print_running(run, ena);
return;
}
@@ -893,8 +952,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
out.new_line = nl;
out.ctx = &os;
- if (!csv_output)
- perf_stat__print_shadow_stats(counter, uval,
+ perf_stat__print_shadow_stats(counter, uval,
stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
cpu_map__id_to_cpu(id),
&out);
--
2.4.3
^ permalink raw reply related [flat|nested] 20+ messages in thread
* Re: [PATCH 4/8] perf, tools, stat: Implement CSV metrics output
2016-01-30 17:06 ` [PATCH 4/8] perf, tools, stat: Implement CSV metrics output Andi Kleen
@ 2016-02-02 9:50 ` Jiri Olsa
2016-02-02 14:02 ` Andi Kleen
0 siblings, 1 reply; 20+ messages in thread
From: Jiri Olsa @ 2016-02-02 9:50 UTC (permalink / raw)
To: Andi Kleen; +Cc: acme, jolsa, eranian, mingo, linux-kernel, Andi Kleen
On Sat, Jan 30, 2016 at 09:06:52AM -0800, Andi Kleen wrote:
> From: Andi Kleen <ak@linux.intel.com>
>
> Now support CSV output for metrics. With the new output callbacks
> this is relatively straight forward by creating new callbacks.
>
> The new line callback needs to know the number of fields to skip them
> correctly
>
> Example output before:
>
> % perf stat -x, true
> 0.200687,,task-clock,200687,100.00
> 0,,context-switches,200687,100.00
> 0,,cpu-migrations,200687,100.00
> 40,,page-faults,200687,100.00
> 730871,,cycles,203601,100.00
> 551056,,stalled-cycles-frontend,203601,100.00
> <not supported>,,stalled-cycles-backend,0,100.00
> 385523,,instructions,203601,100.00
> 78028,,branches,203601,100.00
> 3946,,branch-misses,203601,100.00
>
> After:
>
> % perf stat -x, true
> 0.341119,,task-clock,0.461,CPUs utilized,0.00%,324342,100.00
> 0,,context-switches,0.000,K/sec,0.00%,324342,100.00
> 0,,cpu-migrations,0.000,K/sec,0.00%,324342,100.00
> 41,,page-faults,0.126,M/sec,0.00%,324342,100.00
> 674068,,cycles,2.078,GHz,0.00%,330887,100.00
> 508189,,stalled-cycles-frontend,82.31,frontend cycles idle,0.00%,330887,100.00
> <not supported>,,stalled-cycles-backend,,,0.00%,0,100.00
> 374932,,instructions,0.61,insn per cycle
> ,,,1.20,stalled cycles per insn,0.00%,330887,100.00
> 76540,,branches,235.985,M/sec,0.00%,330887,100.00
> 3091,,branch-misses,4.09,of all branches,0.00%,330887,100.00
$ ./perf stat -x, true
0.279104,,task-clock,0.461,CPUs utilized,279104,100.00
0,,context-switches,0.000,K/sec,279104,100.00
0,,cpu-migrations,0.000,K/sec,279104,100.00
42,,page-faults,0.150,M/sec,279104,100.00
658540,,cycles,2.359,GHz,281617,100.00
<not supported>,,stalled-cycles-frontend,,,,,0,100.00
<not supported>,,stalled-cycles-backend,,,,,0,100.00
428955,,instructions,0.65,insn per cycle
,,,,,,,281617,100.00
^^^^^^^^^^^^^^^^^^^^ it does not look like this one is correct
84032,,branches,301.078,M/sec,281617,100.00
3628,,branch-misses,4.32,of all branches,281617,100.00
>
> Two new fields are added: metric value and metric name before
> the running/enabled fields.
I see, I thought it was meant to be the other way around,
so I need to ask now, wouldn't this break existing parsers?
thanks,
jirka
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH 4/8] perf, tools, stat: Implement CSV metrics output
2016-02-02 9:50 ` Jiri Olsa
@ 2016-02-02 14:02 ` Andi Kleen
0 siblings, 0 replies; 20+ messages in thread
From: Andi Kleen @ 2016-02-02 14:02 UTC (permalink / raw)
To: Jiri Olsa; +Cc: Andi Kleen, acme, jolsa, eranian, mingo, linux-kernel
On Tue, Feb 02, 2016 at 10:50:20AM +0100, Jiri Olsa wrote:
> > Two new fields are added: metric value and metric name before
> > the running/enabled fields.
>
> I see, I thought it was meant to be the other way around,
> so I need to ask now, wouldn't this break existing parsers?
It would, but the new fields weren't around for long and I don't think there
are many users so it's probably ok
(I have a tool that uses them and I'm ok with updating it)
-Andi
--
ak@linux.intel.com -- Speaking for myself only
^ permalink raw reply [flat|nested] 20+ messages in thread
* [PATCH 5/8] perf, tools, stat: Support metrics in --per-core/socket mode
2016-01-30 17:06 perf, tools: Refactor and support interval and CSV metrics Andi Kleen
` (3 preceding siblings ...)
2016-01-30 17:06 ` [PATCH 4/8] perf, tools, stat: Implement CSV metrics output Andi Kleen
@ 2016-01-30 17:06 ` Andi Kleen
2016-01-30 17:06 ` [PATCH 6/8] perf, tools, stat: Document CSV format in manpage Andi Kleen
` (2 subsequent siblings)
7 siblings, 0 replies; 20+ messages in thread
From: Andi Kleen @ 2016-01-30 17:06 UTC (permalink / raw)
To: acme; +Cc: jolsa, eranian, mingo, linux-kernel, Andi Kleen
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 86caf70..815317f 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 *);
@@ -954,13 +973,36 @@ 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);
-
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;
@@ -972,6 +1014,8 @@ 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) {
--
2.4.3
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH 6/8] perf, tools, stat: Document CSV format in manpage
2016-01-30 17:06 perf, tools: Refactor and support interval and CSV metrics Andi Kleen
` (4 preceding siblings ...)
2016-01-30 17:06 ` [PATCH 5/8] perf, tools, stat: Support metrics in --per-core/socket mode Andi Kleen
@ 2016-01-30 17:06 ` Andi Kleen
2016-01-30 17:06 ` [PATCH 7/8] perf, tools, stat: Implement --metric-only mode Andi Kleen
2016-01-30 17:06 ` [PATCH 8/8] perf, tools: Add --metric-only support for -A Andi Kleen
7 siblings, 0 replies; 20+ messages in thread
From: Andi Kleen @ 2016-01-30 17:06 UTC (permalink / raw)
To: acme; +Cc: jolsa, eranian, mingo, linux-kernel, Andi Kleen
From: Andi Kleen <ak@linux.intel.com>
With all the recently added fields in the perf stat CSV output
we should finally document them in the man page. Do this here.
v2: Fix fields in documentation (Jiri)
v3: fix order of fields again (Jiri)
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
tools/perf/Documentation/perf-stat.txt | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 52ef7a9..871802b 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -211,6 +211,26 @@ $ perf stat -- make -j
Wall-clock time elapsed: 719.554352 msecs
+CSV FORMAT
+----------
+
+With -x, perf stat is able to output a not-quite-CSV format output
+Commas in the output are not put into "". To make it easy to parse
+it is recommended to use a different character like -x \;
+
+The fields are in this order:
+
+ - optional usec time stamp in fractions of second (with -I xxx)
+ - counter value
+ - unit of the counter value or empty
+ - event name
+ - optional metric value
+ - optional unit of metric
+ - run time of counter
+ - percentage of measurement time the counter was running
+
+Additional metrics may be printed with all earlier fields being empty.
+
SEE ALSO
--------
linkperf:perf-top[1], linkperf:perf-list[1]
--
2.4.3
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH 7/8] perf, tools, stat: Implement --metric-only mode
2016-01-30 17:06 perf, tools: Refactor and support interval and CSV metrics Andi Kleen
` (5 preceding siblings ...)
2016-01-30 17:06 ` [PATCH 6/8] perf, tools, stat: Document CSV format in manpage Andi Kleen
@ 2016-01-30 17:06 ` Andi Kleen
2016-01-30 17:06 ` [PATCH 8/8] perf, tools: Add --metric-only support for -A Andi Kleen
7 siblings, 0 replies; 20+ messages in thread
From: Andi Kleen @ 2016-01-30 17:06 UTC (permalink / raw)
To: acme; +Cc: jolsa, eranian, mingo, linux-kernel, Andi Kleen
From: Andi Kleen <ak@linux.intel.com>
Add a new mode to only print metrics. Sometimes we don't care about
the raw values, just want the computed metrics. This allows more
compact printing, so with -I each sample is only a single line.
This also allows easier plotting and processing with other tools.
The main target is with using --topdown, but it also works with
-T and standard perf stat. A few metrics are not supported.
To avoiding having to hardcode all the metrics in the code it uses
a two pass approach: first compute dummy metrics and only
print the headers in the print_metric callback. Then use the callback
to print the actual values. There are some additional changes
in the stat printout code to handle all metrics being on a single line.
Example:
% perf stat -a -I 1000 --metric-only
1.000604977 frontend cycles idle backend cycles idle insn per cycle stalled cycles per insn branch-misses of all branches
1.000604977 0.76 2.35%
2.000924680 0.72 2.34%
3.001139592 0.76 2.57%
4.001358452 0.73 2.44%
The output is fairly wide, but that's a trade off for the concise format.
v2: Lots of updates.
v3: Use slightly narrower columns
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
tools/perf/Documentation/perf-stat.txt | 4 +
tools/perf/builtin-stat.c | 210 +++++++++++++++++++++++++++++++--
2 files changed, 204 insertions(+), 10 deletions(-)
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 871802b..5f0377e 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -139,6 +139,10 @@ Print count deltas every N milliseconds (minimum: 10ms)
The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals. Use with caution.
example: 'perf stat -I 1000 -e cycles -a sleep 5'
+--metric-only::
+Only print computed metrics. Print them in a single line.
+Don't show any raw values. Not supported with -A or --per-thread.
+
--per-socket::
Aggregate counts per processor socket for system-wide mode measurements. This
is a useful mode to detect imbalance between sockets. To enable this mode,
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 815317f..7909129 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -122,6 +122,7 @@ static bool sync_run = false;
static unsigned int initial_delay = 0;
static unsigned int unit_width = 4; /* strlen("unit") */
static bool forever = false;
+static bool metric_only = false;
static struct timespec ref_time;
static struct cpu_map *aggr_map;
static aggr_get_id_t aggr_get_id;
@@ -828,6 +829,99 @@ static void print_metric_csv(void *ctx,
fprintf(out, "%s%s%s%s", csv_sep, vals, csv_sep, unit);
}
+#define METRIC_ONLY_LEN 20
+
+/* Filter out some columns that don't work well in metrics only mode */
+
+static bool valid_only_metric(const char *unit)
+{
+ if (!unit)
+ return false;
+ if (strstr(unit, "/sec") ||
+ strstr(unit, "hz") ||
+ strstr(unit, "Hz") ||
+ strstr(unit, "CPUs utilized"))
+ return false;
+ return true;
+}
+
+static const char *fixunit(char *buf, struct perf_evsel *evsel,
+ const char *unit)
+{
+ if (!strncmp(unit, "of all", 6)) {
+ snprintf(buf, 1024, "%s %s", perf_evsel__name(evsel),
+ unit);
+ return buf;
+ }
+ return unit;
+}
+
+static void print_metric_only(void *ctx, const char *color, const char *fmt,
+ const char *unit, double val)
+{
+ struct outstate *os = ctx;
+ FILE *out = os->fh;
+ int n;
+ char buf[1024];
+ unsigned mlen = METRIC_ONLY_LEN;
+
+ if (!valid_only_metric(unit))
+ return;
+ unit = fixunit(buf, os->evsel, unit);
+ if (color)
+ n = color_fprintf(out, color, fmt, val);
+ else
+ n = fprintf(out, fmt, val);
+ if (n > METRIC_ONLY_LEN)
+ n = METRIC_ONLY_LEN;
+ if (mlen < strlen(unit))
+ mlen = strlen(unit) + 1;
+ fprintf(out, "%*s", mlen - n, "");
+}
+
+static void print_metric_only_csv(void *ctx, const char *color __maybe_unused,
+ const char *fmt,
+ const char *unit, double val)
+{
+ struct outstate *os = ctx;
+ FILE *out = os->fh;
+ char buf[64], *vals, *ends;
+ char tbuf[1024];
+
+ if (!valid_only_metric(unit))
+ return;
+ unit = fixunit(tbuf, os->evsel, unit);
+ snprintf(buf, sizeof buf, fmt, val);
+ vals = buf;
+ while (isspace(*vals))
+ vals++;
+ ends = vals;
+ while (isdigit(*ends) || *ends == '.')
+ ends++;
+ *ends = 0;
+ fprintf(out, "%s%s", vals, csv_sep);
+}
+
+static void new_line_metric(void *ctx __maybe_unused)
+{
+}
+
+static void print_metric_header(void *ctx, const char *color __maybe_unused,
+ const char *fmt __maybe_unused,
+ const char *unit, double val __maybe_unused)
+{
+ struct outstate *os = ctx;
+ char tbuf[1024];
+
+ if (!valid_only_metric(unit))
+ return;
+ unit = fixunit(tbuf, os->evsel, unit);
+ if (csv_output)
+ fprintf(os->fh, "%s%s", unit, csv_sep);
+ else
+ fprintf(os->fh, "%-*s ", METRIC_ONLY_LEN, unit);
+}
+
static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
{
FILE *output = stat_config.output;
@@ -916,9 +1010,16 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
print_metric_t pm = print_metric_std;
void (*nl)(void *);
- nl = new_line_std;
+ if (metric_only) {
+ nl = new_line_metric;
+ if (csv_output)
+ pm = print_metric_only_csv;
+ else
+ pm = print_metric_only;
+ } else
+ nl = new_line_std;
- if (csv_output) {
+ if (csv_output && !metric_only) {
static int aggr_fields[] = {
[AGGR_GLOBAL] = 0,
[AGGR_THREAD] = 1,
@@ -937,6 +1038,10 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
os.ena = ena;
}
if (run == 0 || ena == 0) {
+ if (metric_only) {
+ pm(&os, NULL, "", "", 0);
+ return;
+ }
aggr_printout(counter, id, nr);
fprintf(stat_config.output, "%*s%s",
@@ -962,7 +1067,9 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
return;
}
- if (nsec_counter(counter))
+ if (metric_only)
+ /* nothing */;
+ else if (nsec_counter(counter))
nsec_printout(id, nr, counter, uval);
else
abs_printout(id, nr, counter, uval);
@@ -975,8 +1082,11 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
first_shadow_cpu(counter, id),
&out);
- print_noise(counter, noise);
- print_running(run, ena);
+
+ if (!metric_only) {
+ print_noise(counter, noise);
+ print_running(run, ena);
+ }
}
static void aggr_update_shadow(void)
@@ -1010,6 +1120,7 @@ static void print_aggr(char *prefix)
int cpu, s, s2, id, nr;
double uval;
u64 ena, run, val;
+ bool first;
if (!(aggr_map || aggr_get_id))
return;
@@ -1017,7 +1128,11 @@ static void print_aggr(char *prefix)
aggr_update_shadow();
for (s = 0; s < aggr_map->nr; s++) {
+ if (prefix && metric_only)
+ fprintf(output, "%s", prefix);
+
id = aggr_map->map[s];
+ first = true;
evlist__for_each(evsel_list, counter) {
val = ena = run = 0;
nr = 0;
@@ -1030,13 +1145,20 @@ static void print_aggr(char *prefix)
run += perf_counts(counter->counts, cpu, 0)->run;
nr++;
}
- if (prefix)
+ if (first && metric_only) {
+ first = false;
+ aggr_printout(counter, id, nr);
+ }
+ if (prefix && !metric_only)
fprintf(output, "%s", prefix);
uval = val * counter->scale;
printout(id, nr, counter, uval, prefix, run, ena, 1.0);
- fputc('\n', output);
+ if (!metric_only)
+ fputc('\n', output);
}
+ if (metric_only)
+ fputc('\n', output);
}
}
@@ -1081,12 +1203,13 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)
avg_enabled = avg_stats(&ps->res_stats[1]);
avg_running = avg_stats(&ps->res_stats[2]);
- if (prefix)
+ if (prefix && !metric_only)
fprintf(output, "%s", prefix);
uval = avg * counter->scale;
printout(-1, 0, counter, uval, prefix, avg_running, avg_enabled, avg);
- fprintf(output, "\n");
+ if (!metric_only)
+ fprintf(output, "\n");
}
/*
@@ -1115,6 +1238,43 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
}
}
+static int aggr_header_lens[] = {
+ [AGGR_CORE] = 18,
+ [AGGR_SOCKET] = 12,
+ [AGGR_NONE] = 15,
+ [AGGR_THREAD] = 24,
+ [AGGR_GLOBAL] = 0,
+};
+
+static void print_metric_headers(char *prefix)
+{
+ struct perf_stat_output_ctx out;
+ struct perf_evsel *counter;
+ struct outstate os = {
+ .fh = stat_config.output
+ };
+
+ if (prefix)
+ fprintf(stat_config.output, "%s", prefix);
+
+ if (!csv_output)
+ fprintf(stat_config.output, "%*s",
+ aggr_header_lens[stat_config.aggr_mode], "");
+
+ /* Print metrics headers only */
+ evlist__for_each(evsel_list, counter) {
+ os.evsel = counter;
+ out.ctx = &os;
+ out.print_metric = print_metric_header;
+ out.new_line = new_line_metric;
+ os.evsel = counter;
+ perf_stat__print_shadow_stats(counter, 0,
+ 0,
+ &out);
+ }
+ fputc('\n', stat_config.output);
+}
+
static void print_interval(char *prefix, struct timespec *ts)
{
FILE *output = stat_config.output;
@@ -1122,7 +1282,7 @@ static void print_interval(char *prefix, struct timespec *ts)
sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep);
- if (num_print_interval == 0 && !csv_output) {
+ if (num_print_interval == 0 && !csv_output && !metric_only) {
switch (stat_config.aggr_mode) {
case AGGR_SOCKET:
fprintf(output, "# time socket cpus counts %*s events\n", unit_width, "unit");
@@ -1209,6 +1369,17 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
else
print_header(argc, argv);
+ if (metric_only) {
+ static int num_print_iv;
+
+ if (num_print_iv == 0)
+ print_metric_headers(prefix);
+ if (num_print_iv++ == 25)
+ num_print_iv = 0;
+ if (stat_config.aggr_mode == AGGR_GLOBAL && prefix)
+ fprintf(stat_config.output, "%s", prefix);
+ }
+
switch (stat_config.aggr_mode) {
case AGGR_CORE:
case AGGR_SOCKET:
@@ -1221,6 +1392,8 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
case AGGR_GLOBAL:
evlist__for_each(evsel_list, counter)
print_counter_aggr(counter, prefix);
+ if (metric_only)
+ fputc('\n', stat_config.output);
break;
case AGGR_NONE:
evlist__for_each(evsel_list, counter)
@@ -1345,6 +1518,8 @@ static const struct option stat_options[] = {
"aggregate counts per thread", AGGR_THREAD),
OPT_UINTEGER('D', "delay", &initial_delay,
"ms to wait before starting measurement after program start"),
+ OPT_BOOLEAN(0, "metric-only", &metric_only,
+ "Only print computed metrics. No raw values"),
OPT_END()
};
@@ -1966,6 +2141,21 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
goto out;
}
+ if (metric_only && stat_config.aggr_mode == AGGR_THREAD) {
+ fprintf(stderr, "--metric-only is not supported with --per-thread\n");
+ goto out;
+ }
+
+ if (metric_only && stat_config.aggr_mode == AGGR_NONE) {
+ fprintf(stderr, "--metric-only is not supported with -A\n");
+ goto out;
+ }
+
+ if (metric_only && run_count > 1) {
+ fprintf(stderr, "--metric-only is not supported with -r\n");
+ goto out;
+ }
+
if (output_fd < 0) {
fprintf(stderr, "argument to --log-fd must be a > 0\n");
parse_options_usage(stat_usage, stat_options, "log-fd", 0);
--
2.4.3
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH 8/8] perf, tools: Add --metric-only support for -A
2016-01-30 17:06 perf, tools: Refactor and support interval and CSV metrics Andi Kleen
` (6 preceding siblings ...)
2016-01-30 17:06 ` [PATCH 7/8] perf, tools, stat: Implement --metric-only mode Andi Kleen
@ 2016-01-30 17:06 ` Andi Kleen
7 siblings, 0 replies; 20+ messages in thread
From: Andi Kleen @ 2016-01-30 17:06 UTC (permalink / raw)
To: acme; +Cc: jolsa, eranian, mingo, linux-kernel, Andi Kleen
From: Andi Kleen <ak@linux.intel.com>
Add metric only support for -A too. This requires a new print
function that prints the metrics in the right order.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
tools/perf/builtin-stat.c | 48 +++++++++++++++++++++++++++++++++++++++--------
1 file changed, 40 insertions(+), 8 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7909129..91ca8af 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1238,10 +1238,43 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
}
}
+static void print_no_aggr_metric(char *prefix)
+{
+ int cpu;
+ int nrcpus = 0;
+ struct perf_evsel *counter;
+ u64 ena, run, val;
+ double uval;
+
+ evlist__for_each(evsel_list, counter) {
+ nrcpus = perf_evsel__nr_cpus(counter);
+ break;
+ }
+ for (cpu = 0; cpu < nrcpus; cpu++) {
+ bool first = true;
+
+ if (prefix)
+ fputs(prefix, stat_config.output);
+ evlist__for_each(evsel_list, counter) {
+ if (first) {
+ aggr_printout(counter, cpu, 0);
+ first = false;
+ }
+ val = perf_counts(counter->counts, cpu, 0)->val;
+ ena = perf_counts(counter->counts, cpu, 0)->ena;
+ run = perf_counts(counter->counts, cpu, 0)->run;
+
+ uval = val * counter->scale;
+ printout(cpu, 0, counter, uval, prefix, run, ena, 1.0);
+ }
+ fputc('\n', stat_config.output);
+ }
+}
+
static int aggr_header_lens[] = {
[AGGR_CORE] = 18,
[AGGR_SOCKET] = 12,
- [AGGR_NONE] = 15,
+ [AGGR_NONE] = 6,
[AGGR_THREAD] = 24,
[AGGR_GLOBAL] = 0,
};
@@ -1396,8 +1429,12 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
fputc('\n', stat_config.output);
break;
case AGGR_NONE:
- evlist__for_each(evsel_list, counter)
- print_counter(counter, prefix);
+ if (metric_only)
+ print_no_aggr_metric(prefix);
+ else {
+ evlist__for_each(evsel_list, counter)
+ print_counter(counter, prefix);
+ }
break;
case AGGR_UNSET:
default:
@@ -2146,11 +2183,6 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
goto out;
}
- if (metric_only && stat_config.aggr_mode == AGGR_NONE) {
- fprintf(stderr, "--metric-only is not supported with -A\n");
- goto out;
- }
-
if (metric_only && run_count > 1) {
fprintf(stderr, "--metric-only is not supported with -r\n");
goto out;
--
2.4.3
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH 1/8] perf, tools, stat: Abstract stat metrics printing
2016-01-27 0:42 perf, tools: Refactor and support interval and CSV metrics Andi Kleen
@ 2016-01-27 0:42 ` Andi Kleen
0 siblings, 0 replies; 20+ messages in thread
From: Andi Kleen @ 2016-01-27 0:42 UTC (permalink / raw)
To: acme; +Cc: jolsa, mingo, linux-kernel, eranian, Andi Kleen
From: Andi Kleen <ak@linux.intel.com>
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. Improve fallback callbacks. Don't
use void * callback data.
v3: Remove unnecessary hunk. Add typedef for new_line
v4: Remove unnecessary hunk. Don't print metrics for CSV/interval
mode yet. Move printout change to separate patch.
v5: Fix bisect bugs. Avoid bogus frontend cycles printing.
Fix indentation in different aggregation modes.
v6: Delay newline handling
Acked-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
tools/perf/builtin-stat.c | 71 ++++++++++++--
tools/perf/util/stat-shadow.c | 211 +++++++++++++++++++++++-------------------
tools/perf/util/stat.h | 15 ++-
3 files changed, 194 insertions(+), 103 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7f56824..b675b5e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -735,6 +735,58 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
}
}
+struct outstate {
+ FILE *fh;
+ bool newline;
+};
+
+#define METRIC_LEN 35
+
+static void new_line_std(void *ctx)
+{
+ struct outstate *os = ctx;
+
+ os->newline = true;
+}
+
+static void do_new_line_std(struct outstate *os)
+{
+ fputc('\n', os->fh);
+ 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, " ");
+}
+
+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;
+ bool newline = os->newline;
+
+ os->newline = false;
+
+ if (unit == NULL || fmt == NULL) {
+ fprintf(out, "%-*s", METRIC_LEN, "");
+ return;
+ }
+
+ if (newline)
+ do_new_line_std(os);
+
+ 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)
{
FILE *output = stat_config.output;
@@ -795,20 +847,27 @@ 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)
{
- int cpu = cpu_map__id_to_cpu(id);
+ struct outstate os = { .fh = stat_config.output };
+ struct perf_stat_output_ctx out;
+ print_metric_t pm = print_metric_std;
+ void (*nl)(void *);
- if (stat_config.aggr_mode == AGGR_GLOBAL)
- cpu = 0;
+ nl = new_line_std;
if (nsec_counter(counter))
nsec_printout(id, nr, counter, uval);
else
abs_printout(id, nr, counter, uval);
+ out.print_metric = pm;
+ out.new_line = nl;
+ out.ctx = &os;
+
if (!csv_output && !stat_config.interval)
- perf_stat__print_shadow_stats(stat_config.output, counter,
- uval, cpu,
- stat_config.aggr_mode);
+ perf_stat__print_shadow_stats(counter, uval,
+ stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
+ cpu_map__id_to_cpu(id),
+ &out);
}
static void print_aggr(char *prefix)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 6ac0314..4d8f185 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -137,9 +137,10 @@ 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -152,14 +153,17 @@ 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 ");
+ if (ratio)
+ out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+ ratio);
+ else
+ out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
}
-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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -172,14 +176,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -192,14 +195,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -212,14 +214,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -231,15 +232,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -251,15 +250,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -271,15 +268,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -291,15 +286,15 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
+ void *ctxp = out->ctx;
+ print_metric_t print_metric = out->print_metric;
double total, ratio = 0.0, total2;
int ctx = evsel_context(evsel);
@@ -307,119 +302,145 @@ 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, "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]));
+ out->new_line(ctxp);
if (total && avg) {
ratio = total / avg;
- fprintf(out, "\n");
- if (aggr == AGGR_NONE)
- fprintf(out, " ");
- fprintf(out, " # %5.2f stalled cycles per insn", ratio);
+ print_metric(ctxp, NULL, "%7.2f ",
+ "stalled cycles per insn",
+ ratio);
+ } else {
+ print_metric(ctxp, NULL, NULL,
+ "stalled cycles per insn", 0);
}
-
- } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
- runtime_branches_stats[ctx][cpu].n != 0) {
- print_branch_misses(out, cpu, evsel, avg);
+ } 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);
+ else
+ print_metric(ctxp, NULL, NULL, "of all branches", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
+ print_l1_dcache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_l1_icache_stats[ctx][cpu].n != 0)
+ print_l1_icache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
+ print_dtlb_cache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
+ print_itlb_cache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
} 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);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
- runtime_cacherefs_stats[ctx][cpu].n != 0) {
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_ll_cache_stats[ctx][cpu].n != 0)
+ print_ll_cache_misses(cpu, evsel, avg, out);
+ 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]);
if (total)
ratio = avg * 100 / total;
- fprintf(out, " # %8.3f %% of all cache refs ", ratio);
-
+ if (runtime_cacherefs_stats[ctx][cpu].n != 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(out, cpu, evsel, avg);
+ print_stalled_cycles_frontend(cpu, evsel, avg, out);
} 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, out);
} 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, "Ghz", 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, "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]);
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 if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
- runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ 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]);
if (avg)
ratio = total / avg;
- fprintf(out, " # %8.0f cycles / transaction ", ratio);
- } else if (perf_stat_evsel__is(evsel, ELISION_START) &&
- runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+ print_metric(ctxp, NULL, "%8.0f",
+ "cycles / transaction", ratio);
+ else
+ print_metric(ctxp, NULL, NULL, "cycles / transaction",
+ 0);
+ } else if (perf_stat_evsel__is(evsel, ELISION_START)) {
total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
if (avg)
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)) {
if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
- fprintf(out, " # %8.3f CPUs utilized ", avg / ratio);
+ print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+ avg / ratio);
else
- fprintf(out, " ");
+ print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
} else if (runtime_nsecs_stats[cpu].n != 0) {
char unit = 'M';
+ char unit_buf[10];
total = avg_stats(&runtime_nsecs_stats[cpu]);
@@ -429,9 +450,9 @@ 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 086f4e1..f14c0f4 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -68,11 +68,22 @@ 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);
+typedef void (*new_line_t )(void *ctx);
+
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);
+struct perf_stat_output_ctx {
+ void *ctx;
+ print_metric_t print_metric;
+ new_line_t new_line;
+};
+
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+ double avg, int cpu,
+ struct perf_stat_output_ctx *out);
void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
--
2.4.3
^ permalink raw reply related [flat|nested] 20+ messages in thread
* [PATCH 1/8] perf, tools, stat: Abstract stat metrics printing
2016-01-16 1:11 perf, tools: Refactor and support interval and CSV metrics Andi Kleen
@ 2016-01-16 1:11 ` Andi Kleen
0 siblings, 0 replies; 20+ messages in thread
From: Andi Kleen @ 2016-01-16 1:11 UTC (permalink / raw)
To: acme; +Cc: jolsa, eranian, linux-kernel, mingo, Andi Kleen
From: Andi Kleen <ak@linux.intel.com>
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. Improve fallback callbacks. Don't
use void * callback data.
v3: Remove unnecessary hunk. Add typedef for new_line
v4: Remove unnecessary hunk. Don't print metrics for CSV/interval
mode yet. Move printout change to separate patch.
v5: Fix bisect bugs. Avoid bogus frontend cycles printing.
Fix indentation in different aggregation modes.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
---
tools/perf/builtin-stat.c | 59 ++++++++++--
tools/perf/util/stat-shadow.c | 211 +++++++++++++++++++++++-------------------
tools/perf/util/stat.h | 15 ++-
3 files changed, 182 insertions(+), 103 deletions(-)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7f56824..cba9753 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -735,6 +735,46 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
}
}
+struct outstate {
+ FILE *fh;
+};
+
+#define METRIC_LEN 35
+
+static void new_line_std(void *ctx)
+{
+ struct outstate *os = ctx;
+
+ fputc('\n', os->fh);
+ 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, " ");
+}
+
+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 || fmt == 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)
{
FILE *output = stat_config.output;
@@ -795,20 +835,27 @@ 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)
{
- int cpu = cpu_map__id_to_cpu(id);
+ struct outstate os = { .fh = stat_config.output };
+ struct perf_stat_output_ctx out;
+ print_metric_t pm = print_metric_std;
+ void (*nl)(void *);
- if (stat_config.aggr_mode == AGGR_GLOBAL)
- cpu = 0;
+ nl = new_line_std;
if (nsec_counter(counter))
nsec_printout(id, nr, counter, uval);
else
abs_printout(id, nr, counter, uval);
+ out.print_metric = pm;
+ out.new_line = nl;
+ out.ctx = &os;
+
if (!csv_output && !stat_config.interval)
- perf_stat__print_shadow_stats(stat_config.output, counter,
- uval, cpu,
- stat_config.aggr_mode);
+ perf_stat__print_shadow_stats(counter, uval,
+ stat_config.aggr_mode == AGGR_GLOBAL ? 0 :
+ cpu_map__id_to_cpu(id),
+ &out);
}
static void print_aggr(char *prefix)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 6ac0314..4d8f185 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -137,9 +137,10 @@ 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -152,14 +153,17 @@ 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 ");
+ if (ratio)
+ out->print_metric(out->ctx, color, "%7.2f%%", "frontend cycles idle",
+ ratio);
+ else
+ out->print_metric(out->ctx, NULL, NULL, "frontend cycles idle", 0);
}
-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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -172,14 +176,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -192,14 +195,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -212,14 +214,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -231,15 +232,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -251,15 +250,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -271,15 +268,13 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
double total, ratio = 0.0;
const char *color;
@@ -291,15 +286,15 @@ 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 ");
+ out->print_metric(out->ctx, 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,
+ struct perf_stat_output_ctx *out)
{
+ void *ctxp = out->ctx;
+ print_metric_t print_metric = out->print_metric;
double total, ratio = 0.0, total2;
int ctx = evsel_context(evsel);
@@ -307,119 +302,145 @@ 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, "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]));
+ out->new_line(ctxp);
if (total && avg) {
ratio = total / avg;
- fprintf(out, "\n");
- if (aggr == AGGR_NONE)
- fprintf(out, " ");
- fprintf(out, " # %5.2f stalled cycles per insn", ratio);
+ print_metric(ctxp, NULL, "%7.2f ",
+ "stalled cycles per insn",
+ ratio);
+ } else {
+ print_metric(ctxp, NULL, NULL,
+ "stalled cycles per insn", 0);
}
-
- } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
- runtime_branches_stats[ctx][cpu].n != 0) {
- print_branch_misses(out, cpu, evsel, avg);
+ } 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);
+ else
+ print_metric(ctxp, NULL, NULL, "of all branches", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_l1_dcache_stats[ctx][cpu].n != 0)
+ print_l1_dcache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all L1-dcache hits", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_l1_icache_stats[ctx][cpu].n != 0)
+ print_l1_icache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all L1-icache hits", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_dtlb_cache_stats[ctx][cpu].n != 0)
+ print_dtlb_cache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all dTLB cache hits", 0);
} 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);
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_itlb_cache_stats[ctx][cpu].n != 0)
+ print_itlb_cache_misses(cpu, evsel, avg, out);
+ else
+ print_metric(ctxp, NULL, NULL, "of all iTLB cache hits", 0);
} 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);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
- runtime_cacherefs_stats[ctx][cpu].n != 0) {
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
+ if (runtime_ll_cache_stats[ctx][cpu].n != 0)
+ print_ll_cache_misses(cpu, evsel, avg, out);
+ 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]);
if (total)
ratio = avg * 100 / total;
- fprintf(out, " # %8.3f %% of all cache refs ", ratio);
-
+ if (runtime_cacherefs_stats[ctx][cpu].n != 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(out, cpu, evsel, avg);
+ print_stalled_cycles_frontend(cpu, evsel, avg, out);
} 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, out);
} 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, "Ghz", 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, "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]);
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 if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
- runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ 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]);
if (avg)
ratio = total / avg;
- fprintf(out, " # %8.0f cycles / transaction ", ratio);
- } else if (perf_stat_evsel__is(evsel, ELISION_START) &&
- runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ if (runtime_cycles_in_tx_stats[ctx][cpu].n != 0)
+ print_metric(ctxp, NULL, "%8.0f",
+ "cycles / transaction", ratio);
+ else
+ print_metric(ctxp, NULL, NULL, "cycles / transaction",
+ 0);
+ } else if (perf_stat_evsel__is(evsel, ELISION_START)) {
total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
if (avg)
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)) {
if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
- fprintf(out, " # %8.3f CPUs utilized ", avg / ratio);
+ print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
+ avg / ratio);
else
- fprintf(out, " ");
+ print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
} else if (runtime_nsecs_stats[cpu].n != 0) {
char unit = 'M';
+ char unit_buf[10];
total = avg_stats(&runtime_nsecs_stats[cpu]);
@@ -429,9 +450,9 @@ 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 086f4e1..f14c0f4 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -68,11 +68,22 @@ 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);
+typedef void (*new_line_t )(void *ctx);
+
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);
+struct perf_stat_output_ctx {
+ void *ctx;
+ print_metric_t print_metric;
+ new_line_t new_line;
+};
+
+void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
+ double avg, int cpu,
+ struct perf_stat_output_ctx *out);
void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
--
2.4.3
^ permalink raw reply related [flat|nested] 20+ messages in thread