All of lore.kernel.org
 help / color / mirror / Atom feed
From: Agustin Vega-Frias <agustinv@codeaurora.org>
To: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Andi Kleen <ak@linux.intel.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>
Cc: timur@codeaurora.org, agustinv@codeaurora.org
Subject: [RFC V2 2/3] perf, tools: Display pmu name when printing unmerged events in stat
Date: Fri,  2 Mar 2018 18:41:31 -0500	[thread overview]
Message-ID: <1520034092-35275-3-git-send-email-agustinv@codeaurora.org> (raw)
In-Reply-To: <1520034092-35275-1-git-send-email-agustinv@codeaurora.org>

To simplify creation of events accross multiple instances of the same type
of PMU stat supports two methods for creating multiple events from a single
event specification:
1. A prefix or glob can be used in the PMU name.
2. Aliases, which are listed immediately after the Kernel PMU events
   by perf list, are used.

When the --no-merge option is passed and these events are displayed
individually the PMU name is lost and it's not possible to see which
count corresponds to which pmu:

    $ ./perf stat -a -e l3cache/read-miss/ --no-merge ls > /dev/null

     Performance counter stats for 'system wide':

                    67      l3cache/read-miss/
                    67      l3cache/read-miss/
                    63      l3cache/read-miss/
                    60      l3cache/read-miss/

           0.001675706 seconds time elapsed

    $ ./perf stat -a -e l3cache_read_miss --no-merge ls > /dev/null

     Performance counter stats for 'system wide':

                    12      l3cache_read_miss
                    17      l3cache_read_miss
                    10      l3cache_read_miss
                     8      l3cache_read_miss

           0.001661305 seconds time elapsed

This change adds the original pmu name to the event. For dynamic pmu
events the pmu name is restored in the event name:

    $ ./perf stat -a -e l3cache/read-miss/ --no-merge ls > /dev/null

     Performance counter stats for 'system wide':

                    63      l3cache_0_3/read-miss/
                    74      l3cache_0_1/read-miss/
                    64      l3cache_0_2/read-miss/
                    74      l3cache_0_0/read-miss/

           0.001675706 seconds time elapsed

For alias events the name is added after the event name:

    $ ./perf stat -a -e l3cache_read_miss --no-merge ls > /dev/null

     Performance counter stats for 'system wide':

                    10      l3cache_read_miss [l3cache_0_3]
                    12      l3cache_read_miss [l3cache_0_1]
                    10      l3cache_read_miss [l3cache_0_2]
                    17      l3cache_read_miss [l3cache_0_0]

           0.001661305 seconds time elapsed

Signed-off-by: Agustin Vega-Frias <agustinv@codeaurora.org>
---
 tools/perf/builtin-stat.c      | 29 ++++++++++++++++++++++++++++-
 tools/perf/util/evsel.c        |  1 +
 tools/perf/util/evsel.h        |  1 +
 tools/perf/util/parse-events.c |  8 +++++++-
 4 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 98bf9d3..d196972 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1225,6 +1225,31 @@ static void aggr_update_shadow(void)
 	}
 }

+static void uniquify_event_name(struct perf_evsel *counter)
+{
+	char *new_name;
+	char *config;
+
+	if (!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+					   strlen(counter->pmu_name)))
+		return;
+
+	config = strchr(counter->name, '/');
+	if (config) {
+		if (asprintf(&new_name,
+			     "%s%s", counter->pmu_name, config) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	} else {
+		if (asprintf(&new_name,
+			     "%s [%s]", counter->name, counter->pmu_name) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	}
+}
+
 static void collect_all_aliases(struct perf_evsel *counter,
 			    void (*cb)(struct perf_evsel *counter, void *data,
 				       bool first),
@@ -1253,7 +1278,9 @@ static bool collect_data(struct perf_evsel *counter,
 	if (counter->merged_stat)
 		return false;
 	cb(counter, data, true);
-	if (!no_merge && counter->auto_merge_stats)
+	if (no_merge)
+		uniquify_event_name(counter);
+	else if (counter->auto_merge_stats)
 		collect_all_aliases(counter, cb, data);
 	return true;
 }
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ef35168..4841000 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -244,6 +244,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->metric_name   = NULL;
 	evsel->metric_events = NULL;
 	evsel->collect_stat  = false;
+	evsel->pmu_name      = NULL;
 }

 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a7487c6..c2ac16a 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -142,6 +142,7 @@ struct perf_evsel {
 	struct perf_evsel	**metric_events;
 	bool			collect_stat;
 	bool			weak_group;
+	const char		*pmu_name;
 };

 union u64_swap {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 34589c4..bafc91e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1247,7 +1247,12 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 	if (!head_config) {
 		attr.type = pmu->type;
 		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
-		return evsel ? 0 : -ENOMEM;
+		if (evsel) {
+			evsel->pmu_name = name;
+			return 0;
+		} else {
+			return -ENOMEM;
+		}
 	}

 	if (perf_pmu__check_alias(pmu, head_config, &info))
@@ -1276,6 +1281,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 		evsel->snapshot = info.snapshot;
 		evsel->metric_expr = info.metric_expr;
 		evsel->metric_name = info.metric_name;
+		evsel->pmu_name = name;
 	}

 	return evsel ? 0 : -ENOMEM;
--
Qualcomm Datacenter Technologies, Inc. on behalf of the Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.

WARNING: multiple messages have this Message-ID (diff)
From: agustinv@codeaurora.org (Agustin Vega-Frias)
To: linux-arm-kernel@lists.infradead.org
Subject: [RFC V2 2/3] perf, tools: Display pmu name when printing unmerged events in stat
Date: Fri,  2 Mar 2018 18:41:31 -0500	[thread overview]
Message-ID: <1520034092-35275-3-git-send-email-agustinv@codeaurora.org> (raw)
In-Reply-To: <1520034092-35275-1-git-send-email-agustinv@codeaurora.org>

To simplify creation of events accross multiple instances of the same type
of PMU stat supports two methods for creating multiple events from a single
event specification:
1. A prefix or glob can be used in the PMU name.
2. Aliases, which are listed immediately after the Kernel PMU events
   by perf list, are used.

When the --no-merge option is passed and these events are displayed
individually the PMU name is lost and it's not possible to see which
count corresponds to which pmu:

    $ ./perf stat -a -e l3cache/read-miss/ --no-merge ls > /dev/null

     Performance counter stats for 'system wide':

                    67      l3cache/read-miss/
                    67      l3cache/read-miss/
                    63      l3cache/read-miss/
                    60      l3cache/read-miss/

           0.001675706 seconds time elapsed

    $ ./perf stat -a -e l3cache_read_miss --no-merge ls > /dev/null

     Performance counter stats for 'system wide':

                    12      l3cache_read_miss
                    17      l3cache_read_miss
                    10      l3cache_read_miss
                     8      l3cache_read_miss

           0.001661305 seconds time elapsed

This change adds the original pmu name to the event. For dynamic pmu
events the pmu name is restored in the event name:

    $ ./perf stat -a -e l3cache/read-miss/ --no-merge ls > /dev/null

     Performance counter stats for 'system wide':

                    63      l3cache_0_3/read-miss/
                    74      l3cache_0_1/read-miss/
                    64      l3cache_0_2/read-miss/
                    74      l3cache_0_0/read-miss/

           0.001675706 seconds time elapsed

For alias events the name is added after the event name:

    $ ./perf stat -a -e l3cache_read_miss --no-merge ls > /dev/null

     Performance counter stats for 'system wide':

                    10      l3cache_read_miss [l3cache_0_3]
                    12      l3cache_read_miss [l3cache_0_1]
                    10      l3cache_read_miss [l3cache_0_2]
                    17      l3cache_read_miss [l3cache_0_0]

           0.001661305 seconds time elapsed

Signed-off-by: Agustin Vega-Frias <agustinv@codeaurora.org>
---
 tools/perf/builtin-stat.c      | 29 ++++++++++++++++++++++++++++-
 tools/perf/util/evsel.c        |  1 +
 tools/perf/util/evsel.h        |  1 +
 tools/perf/util/parse-events.c |  8 +++++++-
 4 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 98bf9d3..d196972 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1225,6 +1225,31 @@ static void aggr_update_shadow(void)
 	}
 }

+static void uniquify_event_name(struct perf_evsel *counter)
+{
+	char *new_name;
+	char *config;
+
+	if (!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+					   strlen(counter->pmu_name)))
+		return;
+
+	config = strchr(counter->name, '/');
+	if (config) {
+		if (asprintf(&new_name,
+			     "%s%s", counter->pmu_name, config) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	} else {
+		if (asprintf(&new_name,
+			     "%s [%s]", counter->name, counter->pmu_name) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	}
+}
+
 static void collect_all_aliases(struct perf_evsel *counter,
 			    void (*cb)(struct perf_evsel *counter, void *data,
 				       bool first),
@@ -1253,7 +1278,9 @@ static bool collect_data(struct perf_evsel *counter,
 	if (counter->merged_stat)
 		return false;
 	cb(counter, data, true);
-	if (!no_merge && counter->auto_merge_stats)
+	if (no_merge)
+		uniquify_event_name(counter);
+	else if (counter->auto_merge_stats)
 		collect_all_aliases(counter, cb, data);
 	return true;
 }
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ef35168..4841000 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -244,6 +244,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->metric_name   = NULL;
 	evsel->metric_events = NULL;
 	evsel->collect_stat  = false;
+	evsel->pmu_name      = NULL;
 }

 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a7487c6..c2ac16a 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -142,6 +142,7 @@ struct perf_evsel {
 	struct perf_evsel	**metric_events;
 	bool			collect_stat;
 	bool			weak_group;
+	const char		*pmu_name;
 };

 union u64_swap {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 34589c4..bafc91e 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1247,7 +1247,12 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 	if (!head_config) {
 		attr.type = pmu->type;
 		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
-		return evsel ? 0 : -ENOMEM;
+		if (evsel) {
+			evsel->pmu_name = name;
+			return 0;
+		} else {
+			return -ENOMEM;
+		}
 	}

 	if (perf_pmu__check_alias(pmu, head_config, &info))
@@ -1276,6 +1281,7 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 		evsel->snapshot = info.snapshot;
 		evsel->metric_expr = info.metric_expr;
 		evsel->metric_name = info.metric_name;
+		evsel->pmu_name = name;
 	}

 	return evsel ? 0 : -ENOMEM;
--
Qualcomm Datacenter Technologies, Inc. on behalf of the Qualcomm Technologies, Inc.
Qualcomm Technologies, Inc. is a member of the Code Aurora Forum, a Linux Foundation Collaborative Project.

  parent reply	other threads:[~2018-03-02 23:41 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-02 23:41 [RFC V2 0/3] perf stat: improvements for handling of multiple PMUs Agustin Vega-Frias
2018-03-02 23:41 ` Agustin Vega-Frias
2018-03-02 23:41 ` [RFC V2 1/3] perf, tools: Support wildcards on pmu name in dynamic pmu events Agustin Vega-Frias
2018-03-02 23:41   ` Agustin Vega-Frias
2018-03-03 14:34   ` Jiri Olsa
2018-03-03 14:34     ` Jiri Olsa
2018-03-04 17:12     ` Andi Kleen
2018-03-04 17:12       ` Andi Kleen
2018-03-04 18:10       ` Jiri Olsa
2018-03-04 18:10         ` Jiri Olsa
2018-03-05 15:08         ` Agustin Vega-Frias
2018-03-05 15:08           ` Agustin Vega-Frias
2018-03-05 17:55           ` Andi Kleen
2018-03-05 17:55             ` Andi Kleen
2018-03-05 19:09           ` Jiri Olsa
2018-03-05 19:09             ` Jiri Olsa
2018-03-05 20:10             ` Agustin Vega-Frias
2018-03-05 20:10               ` Agustin Vega-Frias
2018-03-05 21:51               ` Jiri Olsa
2018-03-05 21:51                 ` Jiri Olsa
2018-03-02 23:41 ` Agustin Vega-Frias [this message]
2018-03-02 23:41   ` [RFC V2 2/3] perf, tools: Display pmu name when printing unmerged events in stat Agustin Vega-Frias
2018-03-02 23:41 ` [RFC V2 3/3] perf pmu: Auto-merge PMU events created by prefix or glob match Agustin Vega-Frias
2018-03-02 23:41   ` Agustin Vega-Frias

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=1520034092-35275-3-git-send-email-agustinv@codeaurora.org \
    --to=agustinv@codeaurora.org \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=jolsa@redhat.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=timur@codeaurora.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.