perf script: Allow computing 'perf stat' style metrics

Add support for computing 'perf stat' style metrics in 'perf script'.

When using leader sampling we can get metrics for each sampling period
by computing formulas over the values of the different group members.

This allows things like fine grained IPC tracking through sampling, much
more fine grained than with 'perf stat'.

The metric is still averaged over the sampling period, it is not just
for the sampling point.

This patch adds a new metric output field for 'perf script' that uses
the existing 'perf stat' metrics infrastructure to compute any metrics
supported by 'perf stat'.

For example to sample IPC:

  $ perf record -e '{ref-cycles,cycles,instructions}:S' -a sleep 1
  $ perf script -F metric,ip,sym,time,cpu,comm
  ...
   alsa-sink-ALC32 [000] 42815.856074:      7fd65937d6cc [unknown]
   alsa-sink-ALC32 [000] 42815.856074:      7fd65937d6cc [unknown]
   alsa-sink-ALC32 [000] 42815.856074:      7fd65937d6cc [unknown]
   alsa-sink-ALC32 [000] 42815.856074:    metric:    0.13  insn per cycle
           swapper [000] 42815.857961:  ffffffff81655df0 __schedule
           swapper [000] 42815.857961:  ffffffff81655df0 __schedule
           swapper [000] 42815.857961:  ffffffff81655df0 __schedule
           swapper [000] 42815.857961:    metric:    0.23  insn per cycle
   qemu-system-x86 [000] 42815.858130:  ffffffff8165ad0e _raw_spin_unlock_irqrestore
   qemu-system-x86 [000] 42815.858130:  ffffffff8165ad0e _raw_spin_unlock_irqrestore
   qemu-system-x86 [000] 42815.858130:  ffffffff8165ad0e _raw_spin_unlock_irqrestore
   qemu-system-x86 [000] 42815.858130:    metric:    0.46  insn per cycle
             :4972 [000] 42815.858312:  ffffffffa080e5f2 vmx_vcpu_run
             :4972 [000] 42815.858312:  ffffffffa080e5f2 vmx_vcpu_run
             :4972 [000] 42815.858312:  ffffffffa080e5f2 vmx_vcpu_run
             :4972 [000] 42815.858312:    metric:    0.45  insn per cycle

TopDown:

This requires disabling SMT if you have it enabled, because SMT would
require sampling per core, which is not supported.

  $ perf record -e '{ref-cycles,topdown-fetch-bubbles,\
                     topdown-recovery-bubbles,\
                     topdown-slots-retired,topdown-total-slots,\
                     topdown-slots-issued}:S' -a sleep 1
  $ perf script --header -I -F cpu,ip,sym,event,metric,period
  ...
  [000]     121108               ref-cycles:  ffffffff8165222e copy_user_enhanced_fast_string
  [000]     190350    topdown-fetch-bubbles:  ffffffff8165222e copy_user_enhanced_fast_string
  [000]       2055 topdown-recovery-bubbles:  ffffffff8165222e copy_user_enhanced_fast_string
  [000]     148729    topdown-slots-retired:  ffffffff8165222e copy_user_enhanced_fast_string
  [000]     144324      topdown-total-slots:  ffffffff8165222e copy_user_enhanced_fast_string
  [000]     160852     topdown-slots-issued:  ffffffff8165222e copy_user_enhanced_fast_string
  [000]   metric:     33.0% frontend bound
  [000]   metric:      3.5% bad speculation
  [000]   metric:     25.8% retiring
  [000]   metric:     37.7% backend bound
  [000]     112112               ref-cycles:  ffffffff8165aec8 _raw_spin_lock_irqsave
  [000]     357222    topdown-fetch-bubbles:  ffffffff8165aec8 _raw_spin_lock_irqsave
  [000]       3325 topdown-recovery-bubbles:  ffffffff8165aec8 _raw_spin_lock_irqsave
  [000]     323553    topdown-slots-retired:  ffffffff8165aec8 _raw_spin_lock_irqsave
  [000]     270507      topdown-total-slots:  ffffffff8165aec8 _raw_spin_lock_irqsave
  [000]     341226     topdown-slots-issued:  ffffffff8165aec8 _raw_spin_lock_irqsave
  [000]   metric:     33.0% frontend bound
  [000]   metric:      2.9% bad speculation
  [000]   metric:     29.9% retiring
  [000]   metric:     34.2% backend bound
...

v2:
Use evsel->priv for new fields
Port to new base line, support fp output.
Handle stats in ->stats, not ->priv
Minor cleanups

Extra explanation about the use of the term 'averaging', from Andi in the
thread in the Link: tag below:

<quote Andi>
The current samples contains the sum of event counts for a sampling period.

EventA-1           EventA-2                EventA-3      EventA-4
EventB-1     EventB-2                             EventC-3

                         gap with no events                overflow
|-----------------------------------------------------------------|
period-start                                             period-end
^                                                                 ^
|                                                                 |
previous sample                                      current sample

So EventA = 4 and EventB = 3 at the sample point

I generate a metric, let's say EventA / EventB. It applies to the whole period.

But the metric is over a longer time which does not have the same behavior. For
example the gap above doesn't have any events, while they are clustered at the
beginning and end of the sample period.

But we're summing everything together. The metric doesn't know that the gap is
different than the busy period.

That's what I'm trying to express with averaging.
</quote>

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20171117214300.32746-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 95 insertions, 2 deletions

diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ee7c7aaaae72..39d8b55f0db3 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -22,6 +22,7 @@
 #include "util/cpumap.h"
 #include "util/thread_map.h"
 #include "util/stat.h"
+#include "util/color.h"
 #include "util/string2.h"
 #include "util/thread-stack.h"
 #include "util/time-utils.h"
@@ -90,6 +91,7 @@ enum perf_output_field {
 	PERF_OUTPUT_SYNTH           = 1U << 25,
 	PERF_OUTPUT_PHYS_ADDR       = 1U << 26,
 	PERF_OUTPUT_UREGS	    = 1U << 27,
+	PERF_OUTPUT_METRIC	    = 1U << 28,
 };
 
 struct output_option {
@@ -124,6 +126,7 @@ struct output_option {
 	{.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
 	{.str = "synth", .field = PERF_OUTPUT_SYNTH},
 	{.str = "phys_addr", .field = PERF_OUTPUT_PHYS_ADDR},
+	{.str = "metric", .field = PERF_OUTPUT_METRIC},
 };
 
 enum {
@@ -215,12 +218,20 @@ struct perf_evsel_script {
        char *filename;
        FILE *fp;
        u64  samples;
+       /* For metric output */
+       u64  val;
+       int  gnum;
 };
 
+static inline struct perf_evsel_script *evsel_script(struct perf_evsel *evsel)
+{
+	return (struct perf_evsel_script *)evsel->priv;
+}
+
 static struct perf_evsel_script *perf_evsel_script__new(struct perf_evsel *evsel,
 							struct perf_data *data)
 {
-	struct perf_evsel_script *es = malloc(sizeof(*es));
+	struct perf_evsel_script *es = zalloc(sizeof(*es));
 
 	if (es != NULL) {
 		if (asprintf(&es->filename, "%s.%s.dump", data->file.path, perf_evsel__name(evsel)) < 0)
@@ -228,7 +239,6 @@ static struct perf_evsel_script *perf_evsel_script__new(struct perf_evsel *evsel
 		es->fp = fopen(es->filename, "w");
 		if (es->fp == NULL)
 			goto out_free_filename;
-		es->samples = 0;
 	}
 
 	return es;
@@ -1472,6 +1482,86 @@ static int data_src__fprintf(u64 data_src, FILE *fp)
 	return fprintf(fp, "%-*s", maxlen, out);
 }
 
+struct metric_ctx {
+	struct perf_sample	*sample;
+	struct thread		*thread;
+	struct perf_evsel	*evsel;
+	FILE 			*fp;
+};
+
+static void script_print_metric(void *ctx, const char *color,
+			        const char *fmt,
+			        const char *unit, double val)
+{
+	struct metric_ctx *mctx = ctx;
+
+	if (!fmt)
+		return;
+	perf_sample__fprintf_start(mctx->sample, mctx->thread, mctx->evsel,
+				   mctx->fp);
+	fputs("\tmetric: ", mctx->fp);
+	if (color)
+		color_fprintf(mctx->fp, color, fmt, val);
+	else
+		printf(fmt, val);
+	fprintf(mctx->fp, " %s\n", unit);
+}
+
+static void script_new_line(void *ctx)
+{
+	struct metric_ctx *mctx = ctx;
+
+	perf_sample__fprintf_start(mctx->sample, mctx->thread, mctx->evsel,
+				   mctx->fp);
+	fputs("\tmetric: ", mctx->fp);
+}
+
+static void perf_sample__fprint_metric(struct perf_script *script,
+				       struct thread *thread,
+				       struct perf_evsel *evsel,
+				       struct perf_sample *sample,
+				       FILE *fp)
+{
+	struct perf_stat_output_ctx ctx = {
+		.print_metric = script_print_metric,
+		.new_line = script_new_line,
+		.ctx = &(struct metric_ctx) {
+				.sample = sample,
+				.thread = thread,
+				.evsel  = evsel,
+				.fp     = fp,
+			 },
+		.force_header = false,
+	};
+	struct perf_evsel *ev2;
+	static bool init;
+	u64 val;
+
+	if (!init) {
+		perf_stat__init_shadow_stats();
+		init = true;
+	}
+	if (!evsel->stats)
+		perf_evlist__alloc_stats(script->session->evlist, false);
+	if (evsel_script(evsel->leader)->gnum++ == 0)
+		perf_stat__reset_shadow_stats();
+	val = sample->period * evsel->scale;
+	perf_stat__update_shadow_stats(evsel,
+				       val,
+				       sample->cpu);
+	evsel_script(evsel)->val = val;
+	if (evsel_script(evsel->leader)->gnum == evsel->leader->nr_members) {
+		for_each_group_member (ev2, evsel->leader) {
+			perf_stat__print_shadow_stats(ev2,
+						      evsel_script(ev2)->val,
+						      sample->cpu,
+						      &ctx,
+						      NULL);
+		}
+		evsel_script(evsel->leader)->gnum = 0;
+	}
+}
+
 static void process_event(struct perf_script *script,
 			  struct perf_sample *sample, struct perf_evsel *evsel,
 			  struct addr_location *al,
@@ -1559,6 +1649,9 @@ static void process_event(struct perf_script *script,
 	if (PRINT_FIELD(PHYS_ADDR))
 		fprintf(fp, "%16" PRIx64, sample->phys_addr);
 	fprintf(fp, "\n");
+
+	if (PRINT_FIELD(METRIC))
+		perf_sample__fprint_metric(script, thread, evsel, sample, fp);
 }
 
 static struct scripting_ops	*scripting_ops;