From: kan.liang@linux.intel.com
To: peterz@infradead.org, acme@redhat.com, mingo@kernel.org,
linux-kernel@vger.kernel.org
Cc: jolsa@kernel.org, eranian@google.com,
alexander.shishkin@linux.intel.com, ak@linux.intel.com
Subject: [PATCH V6 12/14] perf, tools, stat: Support new per thread TopDown metrics
Date: Fri, 17 Jul 2020 07:05:52 -0700 [thread overview]
Message-ID: <20200717140554.22863-13-kan.liang@linux.intel.com> (raw)
In-Reply-To: <20200717140554.22863-1-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>
---
tools/perf/Documentation/perf-stat.txt | 9 ++-
tools/perf/builtin-stat.c | 25 ++++++++
tools/perf/util/stat-shadow.c | 89 ++++++++++++++++++++++++++
tools/perf/util/stat.c | 4 ++
tools/perf/util/stat.h | 8 +++
5 files changed, 133 insertions(+), 2 deletions(-)
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index b029ee728a0b..a1a2b9755ae8 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -317,8 +317,13 @@ 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 9be020e0098a..078ea1485317 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -128,6 +128,15 @@ static const char * topdown_attrs[] = {
NULL,
};
+static const char *topdown_metric_attrs[] = {
+ "slots",
+ "topdown-retiring",
+ "topdown-bad-spec",
+ "topdown-fe-bound",
+ "topdown-be-bound",
+ NULL,
+};
+
static const char *smi_cost_attrs = {
"{"
"msr/aperf/,"
@@ -1638,6 +1647,21 @@ 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");
@@ -1659,6 +1683,7 @@ 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 a7c13a88ecb9..933ddb601cb8 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -241,6 +241,18 @@ void perf_stat__update_shadow_stats(struct 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 (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
ctx, cpu, count);
@@ -705,6 +717,47 @@ 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 evsel *evsel,
struct perf_stat_output_ctx *out,
@@ -1034,6 +1087,42 @@ 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, NULL, 1, cpu, out, st);
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index cdb154381a87..bd0decd6d753 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -95,6 +95,10 @@ 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 f75ae679eb28..9705421d99a4 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -28,6 +28,10 @@ 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,
@@ -82,6 +86,10 @@ 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
next prev parent reply other threads:[~2020-07-17 14:07 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-17 14:05 [PATCH V6 00/14] TopDown metrics support for Icelake kan.liang
2020-07-17 14:05 ` [PATCH V6 01/14] perf/x86: Use event_base_rdpmc for the RDPMC userspace support kan.liang
2020-07-17 14:05 ` [PATCH V6 02/14] perf/x86/intel: Name the global status bit in NMI handler kan.liang
2020-07-17 14:05 ` [PATCH V6 03/14] perf/x86/intel: Introduce the fourth fixed counter kan.liang
2020-07-20 16:20 ` Peter Zijlstra
2020-07-20 18:22 ` Liang, Kan
2020-07-17 14:05 ` [PATCH V6 04/14] perf/x86/intel: Move BTS index to 47 kan.liang
2020-07-17 14:05 ` [PATCH V6 05/14] perf/x86/intel: Fix the name of perf METRICS kan.liang
2020-07-17 14:05 ` [PATCH V6 06/14] perf/x86/intel: Use switch in intel_pmu_disable/enable_event kan.liang
2020-07-20 16:22 ` Peter Zijlstra
2020-07-20 19:02 ` Liang, Kan
2020-07-17 14:05 ` [PATCH V6 07/14] perf/x86/intel: Generic support for hardware TopDown metrics kan.liang
2020-07-20 17:41 ` Peter Zijlstra
2020-07-20 18:11 ` Liang, Kan
2020-07-21 9:43 ` Peter Zijlstra
2020-07-21 14:05 ` Liang, Kan
2020-07-21 14:25 ` peterz
2020-07-17 14:05 ` [PATCH V6 08/14] perf/x86: Add a macro for RDPMC offset of fixed counters kan.liang
2020-07-17 14:05 ` [PATCH V6 09/14] perf/x86/intel: Support TopDown metrics on Ice Lake kan.liang
2020-07-21 12:40 ` Peter Zijlstra
2020-07-21 14:23 ` Liang, Kan
2020-07-21 14:31 ` peterz
2020-07-21 15:50 ` Liang, Kan
2020-07-21 17:38 ` Andi Kleen
2020-07-21 19:20 ` Peter Zijlstra
2020-07-17 14:05 ` [PATCH V6 10/14] perf/x86/intel: Support per-thread RDPMC TopDown metrics kan.liang
2020-07-17 14:05 ` [PATCH V6 11/14] perf/x86/intel: Disable sample-read the slots and metrics events kan.liang
2020-07-21 13:10 ` Peter Zijlstra
2020-07-21 16:07 ` Liang, Kan
2020-07-21 19:18 ` Peter Zijlstra
2020-07-22 19:26 ` Liang, Kan
2020-07-17 14:05 ` kan.liang [this message]
2020-07-17 14:05 ` [PATCH V6 13/14] perf, tools, stat: Check Topdown Metric group kan.liang
2020-07-17 14:05 ` [PATCH V6 14/14] perf, tools: Add documentation for topdown metrics kan.liang
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=20200717140554.22863-13-kan.liang@linux.intel.com \
--to=kan.liang@linux.intel.com \
--cc=acme@redhat.com \
--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@kernel.org \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.