linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: kan.liang@linux.intel.com
To: peterz@infradead.org, acme@kernel.org, mingo@redhat.com,
	linux-kernel@vger.kernel.org
Cc: tglx@linutronix.de, jolsa@kernel.org, eranian@google.com,
	alexander.shishkin@linux.intel.com, ak@linux.intel.com,
	Kan Liang <kan.liang@linux.intel.com>
Subject: [PATCH V4 21/23] perf, tools, stat: Support new per thread TopDown metrics
Date: Tue, 26 Mar 2019 09:08:59 -0700	[thread overview]
Message-ID: <20190326160901.4887-22-kan.liang@linux.intel.com> (raw)
In-Reply-To: <20190326160901.4887-1-kan.liang@linux.intel.com>

From: Andi Kleen <ak@linux.intel.com>

Icelake has support for reporting per thread TopDown metrics.
These are reported differently than the previous TopDown support,
each metric is standalone, but scaled to pipeline "slots".
We don't need to do anything special for HyperThreading anymore.
Teach perf stat --topdown to handle these new metrics and
print them in the same way as the previous TopDown metrics.
The restrictions of only being able to report information per core is
gone.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---

No changes since V3.

 tools/perf/Documentation/perf-stat.txt |  9 ++-
 tools/perf/builtin-stat.c              | 24 +++++++
 tools/perf/util/stat-shadow.c          | 89 ++++++++++++++++++++++++++
 tools/perf/util/stat.c                 |  4 ++
 tools/perf/util/stat.h                 |  8 +++
 5 files changed, 132 insertions(+), 2 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 4bc2085e5197..f4469751ef0a 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -266,8 +266,13 @@ if the workload is actually bound by the CPU and not by something else.
 For best results it is usually a good idea to use it with interval
 mode like -I 1000, as the bottleneck of workloads can change often.
 
-The top down metrics are collected per core instead of per
-CPU thread. Per core mode is automatically enabled
+This enables --metric-only, unless overridden with --no-metric-only.
+
+The following restrictions only apply to older Intel CPUs and Atom,
+on newer CPUs (IceLake and later) TopDown can be collected for any thread:
+
+The top down metrics are collected per core instead of per CPU thread.
+Per core mode is automatically enabled
 and -a (global monitoring) is needed, requiring root rights or
 perf.perf_event_paranoid=-1.
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7b8f09b0b8bf..5068396c241b 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -123,6 +123,14 @@ static const char * topdown_attrs[] = {
 	NULL,
 };
 
+static const char *topdown_metric_attrs[] = {
+	"topdown-retiring",
+	"topdown-bad-spec",
+	"topdown-fe-bound",
+	"topdown-be-bound",
+	NULL,
+};
+
 static const char *smi_cost_attrs = {
 	"{"
 	"msr/aperf/,"
@@ -1215,6 +1223,21 @@ static int add_default_attributes(void)
 		char *str = NULL;
 		bool warn = false;
 
+		if (topdown_filter_events(topdown_metric_attrs, &str, 1) < 0) {
+			pr_err("Out of memory\n");
+			return -1;
+		}
+		if (topdown_metric_attrs[0] && str) {
+			if (!stat_config.interval) {
+				fprintf(stat_config.output,
+					"Topdown accuracy may decreases when measuring long period.\n"
+					"Please print the result regularly, e.g. -I1000\n");
+			}
+			goto setup_metrics;
+		}
+
+		str = NULL;
+
 		if (stat_config.aggr_mode != AGGR_GLOBAL &&
 		    stat_config.aggr_mode != AGGR_CORE) {
 			pr_err("top down event configuration requires --per-core mode\n");
@@ -1236,6 +1259,7 @@ static int add_default_attributes(void)
 		if (topdown_attrs[0] && str) {
 			if (warn)
 				arch_topdown_group_warn();
+setup_metrics:
 			err = parse_events(evsel_list, str, &errinfo);
 			if (err) {
 				fprintf(stderr,
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 83d8094be4fe..6b6ffd64a4c4 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -238,6 +238,18 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 count,
 	else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
 		update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
 				    ctx, cpu, count);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING))
+		update_runtime_stat(st, STAT_TOPDOWN_RETIRING,
+				    ctx, cpu, count);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC))
+		update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC,
+				    ctx, cpu, count);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND))
+		update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND,
+				    ctx, cpu, count);
+	else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND))
+		update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND,
+				    ctx, cpu, count);
 	else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
 		update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
 				    ctx, cpu, count);
@@ -682,6 +694,47 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
 	return sanitize_val(1.0 - sum);
 }
 
+/*
+ * Kernel reports metrics multiplied with slots. To get back
+ * the ratios we need to recreate the sum.
+ */
+
+static double td_metric_ratio(int ctx, int cpu,
+			      enum stat_type type,
+			      struct runtime_stat *stat)
+{
+	double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) +
+		runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) +
+		runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) +
+		runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu);
+	double d = runtime_stat_avg(stat, type, ctx, cpu);
+
+	if (sum)
+		return d / sum;
+	return 0;
+}
+
+/*
+ * ... but only if most of the values are actually available.
+ * We allow two missing.
+ */
+
+static bool full_td(int ctx, int cpu,
+		    struct runtime_stat *stat)
+{
+	int c = 0;
+
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) > 0)
+		c++;
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) > 0)
+		c++;
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) > 0)
+		c++;
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu) > 0)
+		c++;
+	return c >= 2;
+}
+
 static void print_smi_cost(struct perf_stat_config *config,
 			   int cpu, struct perf_evsel *evsel,
 			   struct perf_stat_output_ctx *out,
@@ -970,6 +1023,42 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					be_bound * 100.);
 		else
 			print_metric(config, ctxp, NULL, NULL, name, 0);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) &&
+			full_td(ctx, cpu, st)) {
+		double retiring = td_metric_ratio(ctx, cpu,
+						  STAT_TOPDOWN_RETIRING, st);
+
+		if (retiring > 0.7)
+			color = PERF_COLOR_GREEN;
+		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
+				retiring * 100.);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
+			full_td(ctx, cpu, st)) {
+		double fe_bound = td_metric_ratio(ctx, cpu,
+						  STAT_TOPDOWN_FE_BOUND, st);
+
+		if (fe_bound > 0.2)
+			color = PERF_COLOR_RED;
+		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
+				fe_bound * 100.);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
+			full_td(ctx, cpu, st)) {
+		double be_bound = td_metric_ratio(ctx, cpu,
+						  STAT_TOPDOWN_BE_BOUND, st);
+
+		if (be_bound > 0.2)
+			color = PERF_COLOR_RED;
+		print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
+				be_bound * 100.);
+	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
+			full_td(ctx, cpu, st)) {
+		double bad_spec = td_metric_ratio(ctx, cpu,
+						  STAT_TOPDOWN_BAD_SPEC, st);
+
+		if (bad_spec > 0.1)
+			color = PERF_COLOR_RED;
+		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
+				bad_spec * 100.);
 	} else if (evsel->metric_expr) {
 		generic_metric(config, evsel->metric_expr, evsel->metric_events, evsel->name,
 				evsel->metric_name, avg, cpu, out, st);
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 4d40515307b8..56f86752a14e 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -87,6 +87,10 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
 	ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired),
 	ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles),
 	ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles),
+	ID(TOPDOWN_RETIRING, topdown-retiring),
+	ID(TOPDOWN_BAD_SPEC, topdown-bad-spec),
+	ID(TOPDOWN_FE_BOUND, topdown-fe-bound),
+	ID(TOPDOWN_BE_BOUND, topdown-be-bound),
 	ID(SMI_NUM, msr/smi/),
 	ID(APERF, msr/aperf/),
 };
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 2f9c9159a364..827c560ad19f 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -29,6 +29,10 @@ enum perf_stat_evsel_id {
 	PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED,
 	PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES,
 	PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES,
+	PERF_STAT_EVSEL_ID__TOPDOWN_RETIRING,
+	PERF_STAT_EVSEL_ID__TOPDOWN_BAD_SPEC,
+	PERF_STAT_EVSEL_ID__TOPDOWN_FE_BOUND,
+	PERF_STAT_EVSEL_ID__TOPDOWN_BE_BOUND,
 	PERF_STAT_EVSEL_ID__SMI_NUM,
 	PERF_STAT_EVSEL_ID__APERF,
 	PERF_STAT_EVSEL_ID__MAX,
@@ -81,6 +85,10 @@ enum stat_type {
 	STAT_TOPDOWN_SLOTS_RETIRED,
 	STAT_TOPDOWN_FETCH_BUBBLES,
 	STAT_TOPDOWN_RECOVERY_BUBBLES,
+	STAT_TOPDOWN_RETIRING,
+	STAT_TOPDOWN_BAD_SPEC,
+	STAT_TOPDOWN_FE_BOUND,
+	STAT_TOPDOWN_BE_BOUND,
 	STAT_SMI_NUM,
 	STAT_APERF,
 	STAT_MAX
-- 
2.17.1


  parent reply	other threads:[~2019-03-26 16:11 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-03-26 16:08 [PATCH V4 00/23] perf: Add Icelake support kan.liang
2019-03-26 16:08 ` [PATCH V4 01/23] perf/x86: Support outputting XMM registers kan.liang
2019-04-01 19:18   ` Stephane Eranian
2019-04-01 19:54     ` Liang, Kan
2019-04-01 21:11       ` Stephane Eranian
2019-04-01 22:33         ` Liang, Kan
2019-03-26 16:08 ` [PATCH V4 02/23] perf/x86/intel: Extract memory code PEBS parser for reuse kan.liang
2019-03-26 16:08 ` [PATCH V4 03/23] perf/x86/intel/ds: Extract code of event update in short period kan.liang
2019-03-26 16:08 ` [PATCH V4 04/23] perf/x86/intel: Support adaptive PEBSv4 kan.liang
2019-03-26 22:24   ` Andi Kleen
2019-03-27 14:25     ` Liang, Kan
2019-03-27 14:42       ` Andi Kleen
2019-03-26 16:08 ` [PATCH V4 05/23] perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them kan.liang
2019-03-26 16:08 ` [PATCH V4 06/23] perf/x86: Support constraint ranges kan.liang
2019-03-26 16:08 ` [PATCH V4 07/23] perf/x86/intel: Add Icelake support kan.liang
2019-03-26 16:08 ` [PATCH V4 08/23] perf/x86/intel/cstate: " kan.liang
2019-03-26 16:08 ` [PATCH V4 09/23] perf/x86/intel/rapl: " kan.liang
2019-03-26 16:08 ` [PATCH V4 10/23] perf/x86/msr: " kan.liang
2019-03-26 16:08 ` [PATCH V4 11/23] perf/x86/intel/uncore: Add Intel Icelake uncore support kan.liang
2019-03-26 16:08 ` [PATCH V4 12/23] perf/core: Support a REMOVE transaction kan.liang
2019-03-26 16:08 ` [PATCH V4 13/23] perf/x86/intel: Basic support for metrics counters kan.liang
2019-03-26 16:08 ` [PATCH V4 14/23] perf/x86/intel: Support overflows on SLOTS kan.liang
2019-03-26 16:08 ` [PATCH V4 15/23] perf/x86/intel: Support hardware TopDown metrics kan.liang
2019-03-26 16:08 ` [PATCH V4 16/23] perf/x86/intel: Set correct weight for topdown subevent counters kan.liang
2019-03-26 16:08 ` [PATCH V4 17/23] perf/x86/intel: Export new top down events for Icelake kan.liang
2019-03-26 16:08 ` [PATCH V4 18/23] perf/x86/intel: Disable sampling read slots and topdown kan.liang
2019-03-26 16:08 ` [PATCH V4 19/23] perf/x86/intel: Support CPUID 10.ECX to disable fixed counters kan.liang
2019-03-26 16:08 ` [PATCH V4 20/23] perf, tools: Add support for recording and printing XMM registers kan.liang
2019-03-26 16:08 ` kan.liang [this message]
2019-03-26 16:09 ` [PATCH V4 22/23] perf, tools: Add documentation for topdown metrics kan.liang
2019-03-26 16:09 ` [PATCH V4 23/23] perf vendor events intel: Add JSON files for Icelake kan.liang
2019-04-01 13:01 ` [PATCH V4 00/23] perf: Add Icelake support Liang, Kan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190326160901.4887-22-kan.liang@linux.intel.com \
    --to=kan.liang@linux.intel.com \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=eranian@google.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).