All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jiri Olsa <jolsa@kernel.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: lkml <linux-kernel@vger.kernel.org>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Andi Kleen <ak@linux.intel.com>, David Ahern <dsahern@gmail.com>,
	Ingo Molnar <mingo@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Stephane Eranian <eranian@google.com>
Subject: [PATCH 11/27] perf stat: Make stats work over the thread dimension
Date: Tue, 23 Jun 2015 00:36:12 +0200	[thread overview]
Message-ID: <1435012588-9007-12-git-send-email-jolsa@kernel.org> (raw)
In-Reply-To: <1435012588-9007-1-git-send-email-jolsa@kernel.org>

Now that we have space for thread dimension counts,
let's store it.

Link: http://lkml.kernel.org/n/tip-vvu96knzwli7ajpjz7qu8jfl@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c                  | 32 +++++++++++++++++-------------
 tools/perf/tests/openat-syscall-all-cpus.c |  6 +++---
 tools/perf/tests/openat-syscall.c          |  4 ++--
 tools/perf/util/evsel.c                    | 12 +++++------
 tools/perf/util/evsel.h                    |  2 +-
 tools/perf/util/stat.c                     |  8 ++++----
 tools/perf/util/stat.h                     |  8 ++++----
 7 files changed, 38 insertions(+), 34 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 055ce83dd6f2..983bcbbe8e0a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -166,11 +166,12 @@ static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 	zfree(&evsel->priv);
 }
 
-static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
+static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+					     int ncpus, int nthreads)
 {
 	struct perf_counts *counts;
 
-	counts = perf_counts__new(perf_evsel__nr_cpus(evsel));
+	counts = perf_counts__new(ncpus, nthreads);
 	if (counts)
 		evsel->prev_raw_counts = counts;
 
@@ -197,11 +198,14 @@ static void perf_evlist__free_stats(struct perf_evlist *evlist)
 static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
 {
 	struct perf_evsel *evsel;
+	int nthreads = thread_map__nr(evsel_list->threads);
 
 	evlist__for_each(evlist, evsel) {
+		int ncpus = perf_evsel__nr_cpus(evsel);
+
 		if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
-		    perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 ||
-		    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0))
+		    perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
+		    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
 			goto out_free;
 	}
 
@@ -294,7 +298,7 @@ static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
 	return 0;
 }
 
-static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
+static int read_cb(struct perf_evsel *evsel, int cpu, int thread,
 		   struct perf_counts_values *count)
 {
 	struct perf_counts_values *aggr = &evsel->counts->aggr;
@@ -314,9 +318,9 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
 	case AGGR_SOCKET:
 	case AGGR_NONE:
 		if (!evsel->snapshot)
-			perf_evsel__compute_deltas(evsel, cpu, count);
+			perf_evsel__compute_deltas(evsel, cpu, thread, count);
 		perf_counts_values__scale(count, scale, NULL);
-		*perf_counts(evsel->counts, cpu) = *count;
+		*perf_counts(evsel->counts, cpu, thread) = *count;
 		if (aggr_mode == AGGR_NONE)
 			perf_stat__update_shadow_stats(evsel, count->values, cpu);
 		break;
@@ -352,7 +356,7 @@ static int read_counter_aggr(struct perf_evsel *counter)
 		return -1;
 
 	if (!counter->snapshot)
-		perf_evsel__compute_deltas(counter, -1, aggr);
+		perf_evsel__compute_deltas(counter, -1, -1, aggr);
 	perf_counts_values__scale(aggr, scale, &counter->counts->scaled);
 
 	for (i = 0; i < 3; i++)
@@ -805,9 +809,9 @@ static void print_aggr(char *prefix)
 				s2 = aggr_get_id(evsel_list->cpus, cpu2);
 				if (s2 != id)
 					continue;
-				val += perf_counts(counter->counts, cpu)->val;
-				ena += perf_counts(counter->counts, cpu)->ena;
-				run += perf_counts(counter->counts, cpu)->run;
+				val += perf_counts(counter->counts, cpu, 0)->val;
+				ena += perf_counts(counter->counts, cpu, 0)->ena;
+				run += perf_counts(counter->counts, cpu, 0)->run;
 				nr++;
 			}
 			if (prefix)
@@ -915,9 +919,9 @@ static void print_counter(struct perf_evsel *counter, char *prefix)
 	int cpu;
 
 	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		val = perf_counts(counter->counts, cpu)->val;
-		ena = perf_counts(counter->counts, cpu)->ena;
-		run = perf_counts(counter->counts, cpu)->run;
+		val = perf_counts(counter->counts, cpu, 0)->val;
+		ena = perf_counts(counter->counts, cpu, 0)->ena;
+		run = perf_counts(counter->counts, cpu, 0)->run;
 
 		if (prefix)
 			fprintf(output, "%s", prefix);
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index e8d944fe1bd0..a572f87e9c8d 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -78,7 +78,7 @@ int test__openat_syscall_event_on_all_cpus(void)
 	 * we use the auto allocation it will allocate just for 1 cpu,
 	 * as we start by cpu 0.
 	 */
-	if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) {
+	if (perf_evsel__alloc_counts(evsel, cpus->nr, 1) < 0) {
 		pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
 		goto out_close_fd;
 	}
@@ -98,9 +98,9 @@ int test__openat_syscall_event_on_all_cpus(void)
 		}
 
 		expected = nr_openat_calls + cpu;
-		if (perf_counts(evsel->counts, cpu)->val != expected) {
+		if (perf_counts(evsel->counts, cpu, 0)->val != expected) {
 			pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
-				 expected, cpus->map[cpu], perf_counts(evsel->counts, cpu)->val);
+				 expected, cpus->map[cpu], perf_counts(evsel->counts, cpu, 0)->val);
 			err = -1;
 		}
 	}
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index bd882f09ebbc..c9a37bc6b33a 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -44,9 +44,9 @@ int test__openat_syscall_event(void)
 		goto out_close_fd;
 	}
 
-	if (perf_counts(evsel->counts, 0)->val != nr_openat_calls) {
+	if (perf_counts(evsel->counts, 0, 0)->val != nr_openat_calls) {
 		pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n",
-			 nr_openat_calls, perf_counts(evsel->counts, 0)->val);
+			 nr_openat_calls, perf_counts(evsel->counts, 0, 0)->val);
 		goto out_close_fd;
 	}
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 8401b042b9d4..cd6ce7066f85 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -898,7 +898,7 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
-void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
 				struct perf_counts_values *count)
 {
 	struct perf_counts_values tmp;
@@ -910,8 +910,8 @@ void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
 		tmp = evsel->prev_raw_counts->aggr;
 		evsel->prev_raw_counts->aggr = *count;
 	} else {
-		tmp = *perf_counts(evsel->prev_raw_counts, cpu);
-		*perf_counts(evsel->prev_raw_counts, cpu) = *count;
+		tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
+		*perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
 	}
 
 	count->val = count->val - tmp.val;
@@ -964,15 +964,15 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 	if (FD(evsel, cpu, thread) < 0)
 		return -EINVAL;
 
-	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0)
+	if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
 		return -ENOMEM;
 
 	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
 		return -errno;
 
-	perf_evsel__compute_deltas(evsel, cpu, &count);
+	perf_evsel__compute_deltas(evsel, cpu, thread, &count);
 	perf_counts_values__scale(&count, scale, NULL);
-	*perf_counts(evsel->counts, cpu) = count;
+	*perf_counts(evsel->counts, cpu, thread) = count;
 	return 0;
 }
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index b420f8f5fc5d..020f7e13634a 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -112,7 +112,7 @@ static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
 void perf_counts_values__scale(struct perf_counts_values *count,
 			       bool scale, s8 *pscaled);
 
-void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread,
 				struct perf_counts_values *count);
 
 int perf_evsel__object_config(size_t object_size,
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 453480aa7650..7bcc19b62dd1 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -95,14 +95,14 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 	}
 }
 
-struct perf_counts *perf_counts__new(int ncpus)
+struct perf_counts *perf_counts__new(int ncpus, int nthreads)
 {
 	struct perf_counts *counts = zalloc(sizeof(*counts));
 
 	if (counts) {
 		struct xyarray *cpu;
 
-		cpu = xyarray__new(ncpus, 1, sizeof(struct perf_counts_values));
+		cpu = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values));
 		if (!cpu) {
 			free(counts);
 			return NULL;
@@ -132,9 +132,9 @@ void perf_evsel__reset_counts(struct perf_evsel *evsel)
 	perf_counts__reset(evsel->counts);
 }
 
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus)
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
-	evsel->counts = perf_counts__new(ncpus);
+	evsel->counts = perf_counts__new(ncpus, nthreads);
 	return evsel->counts != NULL ? 0 : -ENOMEM;
 }
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 6d07612545e0..e0b8dc50fbb6 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -50,9 +50,9 @@ struct perf_counts {
 };
 
 static inline struct perf_counts_values*
-perf_counts(struct perf_counts *counts, int cpu)
+perf_counts(struct perf_counts *counts, int cpu, int thread)
 {
-	return xyarray__entry(counts->cpu, cpu, 0);
+	return xyarray__entry(counts->cpu, cpu, thread);
 }
 
 void update_stats(struct stats *stats, u64 val);
@@ -86,10 +86,10 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
 void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
 				   double avg, int cpu, enum aggr_mode aggr);
 
-struct perf_counts *perf_counts__new(int ncpus);
+struct perf_counts *perf_counts__new(int ncpus, int nthreads);
 void perf_counts__delete(struct perf_counts *counts);
 
 void perf_evsel__reset_counts(struct perf_evsel *evsel);
-int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus);
+int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads);
 void perf_evsel__free_counts(struct perf_evsel *evsel);
 #endif
-- 
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
Please read the FAQ at  http://www.tux.org/lkml/

  parent reply	other threads:[~2015-06-22 22:37 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-06-22 22:36 [PATCHv4 00/27] perf stat: Introduce --per-thread option Jiri Olsa
2015-06-22 22:36 ` [PATCH 01/27] perf tools: Change thread_map::map into struct Jiri Olsa
2015-06-25  7:58   ` [tip:perf/core] perf thread_map: Don' t access the array entries directly tip-bot for Jiri Olsa
2015-06-25  7:58   ` [tip:perf/core] perf thread_map: Change map entries into a struct tip-bot for Jiri Olsa
2015-06-22 22:36 ` [PATCH 02/27] perf tools: Add comm string into struct thread_map Jiri Olsa
2015-06-23 21:01   ` Arnaldo Carvalho de Melo
2015-06-23 21:56     ` Jiri Olsa
2015-06-25 14:39       ` Arnaldo Carvalho de Melo
2015-06-25 16:01         ` Jiri Olsa
2015-06-25 16:13           ` Arnaldo Carvalho de Melo
2015-06-22 22:36 ` [PATCH 03/27] perf tools: Add reference counting for cpu_map object Jiri Olsa
2015-06-23 21:06   ` Arnaldo Carvalho de Melo
2015-06-23 21:54     ` Jiri Olsa
2015-06-26  8:44   ` [tip:perf/urgent] " tip-bot for Jiri Olsa
2015-06-22 22:36 ` [PATCH 04/27] perf tools: Add reference counting for thread_map object Jiri Olsa
2015-06-26  8:44   ` [tip:perf/urgent] " tip-bot for Jiri Olsa
2015-06-22 22:36 ` [PATCH 05/27] perf tools: Propagate cpu maps through the evlist Jiri Olsa
2015-06-26  8:45   ` [tip:perf/urgent] perf evlist: Propagate cpu maps to evsels in an evlist tip-bot for Jiri Olsa
2015-06-22 22:36 ` [PATCH 06/27] perf tools: Propagate thread maps through the evlist Jiri Olsa
2015-06-26  8:45   ` [tip:perf/urgent] perf evlist: " tip-bot for Jiri Olsa
2015-06-22 22:36 ` [PATCH 07/27] perf tools: Make perf_evsel__(nr_)cpus generic Jiri Olsa
2015-06-26  8:45   ` [tip:perf/urgent] " tip-bot for Jiri Olsa
2015-06-22 22:36 ` [PATCH 08/27] perf tests: Add thread_map object tests Jiri Olsa
2015-06-22 22:36 ` [PATCH 09/27] perf stat: Introduce perf_counts function Jiri Olsa
2015-06-23 21:11   ` Arnaldo Carvalho de Melo
2015-06-23 22:03     ` Jiri Olsa
2015-06-22 22:36 ` [PATCH 10/27] perf stat: Use xyarray for cpu evsel counts Jiri Olsa
2015-06-22 22:36 ` Jiri Olsa [this message]
2015-06-22 22:36 ` [PATCH 12/27] perf stat: Rename struct perf_counts::cpu member to values Jiri Olsa
2015-06-22 22:36 ` [PATCH 13/27] perf stat: Introduce perf_evlist__reset_stats Jiri Olsa
2015-06-22 22:36 ` [PATCH 14/27] perf stat: Move perf_evsel__(alloc|free|reset)_stat_priv into stat object Jiri Olsa
2015-06-22 22:36 ` [PATCH 15/27] perf stat: Move perf_evsel__(alloc|free)_prev_raw_counts " Jiri Olsa
2015-06-22 22:36 ` [PATCH 16/27] perf stat: Move perf_evlist__(alloc|free|reset)_stats " Jiri Olsa
2015-06-22 22:36 ` [PATCH 17/27] perf stat: Introduce perf_evsel__alloc_stats function Jiri Olsa
2015-06-22 22:36 ` [PATCH 18/27] perf stat: Introduce perf_evsel__read function Jiri Olsa
2015-06-22 22:36 ` [PATCH 19/27] perf stat: Introduce read_counters function Jiri Olsa
2015-06-22 22:36 ` [PATCH 20/27] perf stat: Separate counters reading and processing Jiri Olsa
2015-06-22 22:36 ` [PATCH 21/27] perf stat: Move zero_per_pkg into counter process code Jiri Olsa
2015-06-22 22:36 ` [PATCH 22/27] perf stat: Move perf_stat initialization " Jiri Olsa
2015-06-22 22:36 ` [PATCH 23/27] perf stat: Remove perf_evsel__read_cb function Jiri Olsa
2015-06-22 22:36 ` [PATCH 24/27] perf stat: Rename print_interval to process_interval Jiri Olsa
2015-06-22 22:36 ` [PATCH 25/27] perf stat: Using init_stats instead of memset Jiri Olsa
2015-06-22 22:36 ` [PATCH 26/27] perf stat: Introduce print_counters function Jiri Olsa
2015-06-22 22:36 ` [PATCH 27/27] perf stat: Introduce --per-thread option Jiri Olsa
2015-06-22 23:06 ` [PATCHv4 00/27] " Arnaldo Carvalho de Melo
2015-06-23  7:22   ` Jiri Olsa
2015-06-23 14:05     ` Arnaldo Carvalho de Melo
2015-06-23 14:08       ` Adrian Hunter
2015-06-23 15:06         ` Arnaldo Carvalho de Melo

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=1435012588-9007-12-git-send-email-jolsa@kernel.org \
    --to=jolsa@kernel.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=ak@linux.intel.com \
    --cc=dsahern@gmail.com \
    --cc=eranian@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.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.