Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1170233 > unrolled thread

[PATCHv4 00/27] perf stat: Introduce --per-thread option

Started byJiri Olsa <jolsa@kernel.org>
First post2015-06-23 00:40 +0200
Last post2015-06-23 01:10 +0200
Articles 20 on this page of 28 — 2 participants

Back to article view | Back to linux.kernel

Contents

  [PATCHv4 00/27] perf stat: Introduce --per-thread option Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 14/27] perf stat: Move perf_evsel__(alloc|free|reset)_stat_priv into stat object Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 17/27] perf stat: Introduce perf_evsel__alloc_stats function Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 07/27] perf tools: Make perf_evsel__(nr_)cpus generic Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 04/27] perf tools: Add reference counting for thread_map object Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 25/27] perf stat: Using init_stats instead of memset Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 23/27] perf stat: Remove perf_evsel__read_cb function Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 18/27] perf stat: Introduce perf_evsel__read function Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 15/27] perf stat: Move perf_evsel__(alloc|free)_prev_raw_counts into stat object Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 02/27] perf tools: Add comm string into struct thread_map Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 21/27] perf stat: Move zero_per_pkg into counter process code Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 27/27] perf stat: Introduce --per-thread option Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 11/27] perf stat: Make stats work over the thread dimension Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 13/27] perf stat: Introduce perf_evlist__reset_stats Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 06/27] perf tools: Propagate thread maps through the evlist Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 05/27] perf tools: Propagate cpu maps through the evlist Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:40 +0200
    [PATCH 20/27] perf stat: Separate counters reading and processing Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:50 +0200
    [PATCH 24/27] perf stat: Rename print_interval to process_interval Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:50 +0200
    [PATCH 22/27] perf stat: Move perf_stat initialization counter process code Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:50 +0200
    [PATCH 19/27] perf stat: Introduce read_counters function Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:50 +0200
    [PATCH 08/27] perf tests: Add thread_map object tests Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:50 +0200
    [PATCH 26/27] perf stat: Introduce print_counters function Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:50 +0200
    [PATCH 09/27] perf stat: Introduce perf_counts function Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:50 +0200
    [PATCH 10/27] perf stat: Use xyarray for cpu evsel counts Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:50 +0200
    [PATCH 16/27] perf stat: Move perf_evlist__(alloc|free|reset)_stats into stat object Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:50 +0200
    [PATCH 12/27] perf stat: Rename struct perf_counts::cpu member to values Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:50 +0200
    [PATCH 03/27] perf tools: Add reference counting for cpu_map object Jiri Olsa <jolsa@kernel.org> - 2015-06-23 00:50 +0200
    Re: [PATCHv4 00/27] perf stat: Introduce --per-thread option Arnaldo Carvalho de Melo <acme@kernel.org> - 2015-06-23 01:10 +0200

Page 1 of 2  [1] 2  Next page →

#1170233 — [PATCHv4 00/27] perf stat: Introduce --per-thread option

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCHv4 00/27] perf stat: Introduce --per-thread option
Message-ID<pEixI-Bm-5@gated-at.bofh.it>
hi,
adding the possibility to display stat data per thread.

Allowing following commands and output:

  $ perf stat  -e cycles,instructions --per-thread -p 30190,30242
  ^C
   Performance counter stats for process id '30190,30242':

               cat-30190                     0      cycles
               yes-30242         3,842,525,421      cycles
               cat-30190                     0      instructions
               yes-30242        10,370,817,010      instructions

         1.143155657 seconds time elapsed


Also works under interval mode:

  $ perf stat  -e cycles,instructions --per-thread -p 30190,30242 -I 1000
  #           time             comm-pid                  counts unit events
       1.000073435              cat-30190                89,058      cycles
       1.000073435              yes-30242         3,360,786,902      cycles                     (100.00%)
       1.000073435              cat-30190                14,066      instructions
       1.000073435              yes-30242         9,069,937,462      instructions
       2.000204830              cat-30190                     0      cycles
       2.000204830              yes-30242         3,351,667,626      cycles
       2.000204830              cat-30190                     0      instructions
       2.000204830              yes-30242         9,045,796,885      instructions
  ^C     2.771286639              cat-30190                     0      cycles
       2.771286639              yes-30242         2,593,884,166      cycles
       2.771286639              cat-30190                     0      instructions
       2.771286639              yes-30242         7,001,171,191      instructions


Available in here:
  git://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git
  perf/per_thread

v4 changes:
  - add thread_map__set_(pid|comm) interface
  - several fixes for task comm string reading
  - added perf_evlist__reset_stats function

v3 changes:
  - some patches already pulled in, rebased on latest acme's perf/core
  - fixed cpu_map__get/thread_map__get to accept NULL map
  - renamed propagate_maps to perf_evlist__propagate_maps
  - renamed --per-task option to --per-thread
  - changed 'task-pid' header output to 'comm-pid'

v2 changes:
  - renamed xyarray__zero to xyarray__reset
  - using atomic_t for cpu_map/thread_map refcnt
  - moving all stat functions into stat object
  - using init_stats to initialize 'struct stats*'
  - change TASK-$pid output into $comm-$pid
  - updated doc with --per-task option


thanks,
jirka
---
Jiri Olsa (27):
      perf tools: Change thread_map::map into struct
      perf tools: Add comm string into struct thread_map
      perf tools: Add reference counting for cpu_map object
      perf tools: Add reference counting for thread_map object
      perf tools: Propagate cpu maps through the evlist
      perf tools: Propagate thread maps through the evlist
      perf tools: Make perf_evsel__(nr_)cpus generic
      perf tests: Add thread_map object tests
      perf stat: Introduce perf_counts function
      perf stat: Use xyarray for cpu evsel counts
      perf stat: Make stats work over the thread dimension
      perf stat: Rename struct perf_counts::cpu member to values
      perf stat: Introduce perf_evlist__reset_stats
      perf stat: Move perf_evsel__(alloc|free|reset)_stat_priv into stat object
      perf stat: Move perf_evsel__(alloc|free)_prev_raw_counts into stat object
      perf stat: Move perf_evlist__(alloc|free|reset)_stats into stat object
      perf stat: Introduce perf_evsel__alloc_stats function
      perf stat: Introduce perf_evsel__read function
      perf stat: Introduce read_counters function
      perf stat: Separate counters reading and processing
      perf stat: Move zero_per_pkg into counter process code
      perf stat: Move perf_stat initialization counter process code
      perf stat: Remove perf_evsel__read_cb function
      perf stat: Rename print_interval to process_interval
      perf stat: Using init_stats instead of memset
      perf stat: Introduce print_counters function
      perf stat: Introduce --per-thread option

 tools/perf/Documentation/perf-stat.txt      |   4 +
 tools/perf/builtin-stat.c                   | 404 ++++++++++++++--------------
 tools/perf/builtin-trace.c                  |   4 +-
 tools/perf/tests/Build                      |   1 +
 tools/perf/tests/builtin-test.c             |   4 +
 tools/perf/tests/code-reading.c             |   4 +-
 tools/perf/tests/keep-tracking.c            |   4 +-
 tools/perf/tests/mmap-basic.c               |   4 +-
 tools/perf/tests/mmap-thread-lookup.c       |   2 +-
 tools/perf/tests/openat-syscall-all-cpus.c  |   8 +-
 tools/perf/tests/openat-syscall-tp-fields.c |   2 +-
 tools/perf/tests/openat-syscall.c           |   6 +-
 tools/perf/tests/switch-tracking.c          |   4 +-
 tools/perf/tests/tests.h                    |   1 +
 tools/perf/tests/thread-map.c               |  28 ++
 tools/perf/util/auxtrace.c                  |   4 +-
 tools/perf/util/cpumap.c                    |  26 +-
 tools/perf/util/cpumap.h                    |   6 +-
 tools/perf/util/event.c                     |   6 +-
 tools/perf/util/evlist.c                    |  39 ++-
 tools/perf/util/evlist.h                    |   1 -
 tools/perf/util/evsel.c                     |  28 +-
 tools/perf/util/evsel.h                     |  40 ++-
 tools/perf/util/parse-events.c              |   5 +-
 tools/perf/util/python-ext-sources          |   1 +
 tools/perf/util/python.c                    |   4 +-
 tools/perf/util/record.c                    |   4 +-
 tools/perf/util/session.c                   |   2 +-
 tools/perf/util/stat.c                      | 132 ++++++++-
 tools/perf/util/stat.h                      |  47 +++-
 tools/perf/util/svghelper.c                 |   2 +-
 tools/perf/util/thread_map.c                | 118 ++++++--
 tools/perf/util/thread_map.h                |  35 ++-
 33 files changed, 661 insertions(+), 319 deletions(-)
 create mode 100644 tools/perf/tests/thread-map.c
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [next] | [standalone]

#1170234 — [PATCH 14/27] perf stat: Move perf_evsel__(alloc|free|reset)_stat_priv into stat object

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 14/27] perf stat: Move perf_evsel__(alloc|free|reset)_stat_priv into stat object
Message-ID<pEixI-Bm-9@gated-at.bofh.it>
In reply to#1170233
Moving perf_evsel__(alloc|free|reset)_stat_priv into stat object,
so it could be used outside stat command in following patches.

Link: http://lkml.kernel.org/n/tip-ti0tocuk8fuw0zb7puyuw4e7@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c | 25 -------------------------
 tools/perf/util/stat.c    | 25 +++++++++++++++++++++++++
 tools/perf/util/stat.h    |  4 ++++
 3 files changed, 29 insertions(+), 25 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 188cd98a4ab3..8a7fd0c60ab1 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -141,31 +141,6 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a,
 	}
 }
 
-static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
-{
-	int i;
-	struct perf_stat *ps = evsel->priv;
-
-	for (i = 0; i < 3; i++)
-		init_stats(&ps->res_stats[i]);
-
-	perf_stat_evsel_id_init(evsel);
-}
-
-static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
-{
-	evsel->priv = zalloc(sizeof(struct perf_stat));
-	if (evsel->priv == NULL)
-		return -ENOMEM;
-	perf_evsel__reset_stat_priv(evsel);
-	return 0;
-}
-
-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,
 					     int ncpus, int nthreads)
 {
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 197a2db5f2c4..b8c329f41f13 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -143,3 +143,28 @@ void perf_evsel__free_counts(struct perf_evsel *evsel)
 	perf_counts__delete(evsel->counts);
 	evsel->counts = NULL;
 }
+
+void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
+{
+	int i;
+	struct perf_stat *ps = evsel->priv;
+
+	for (i = 0; i < 3; i++)
+		init_stats(&ps->res_stats[i]);
+
+	perf_stat_evsel_id_init(evsel);
+}
+
+int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
+{
+	evsel->priv = zalloc(sizeof(struct perf_stat));
+	if (evsel->priv == NULL)
+		return -ENOMEM;
+	perf_evsel__reset_stat_priv(evsel);
+	return 0;
+}
+
+void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
+{
+	zfree(&evsel->priv);
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 295d1e29d3d6..c441cb312565 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -92,4 +92,8 @@ 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 nthreads);
 void perf_evsel__free_counts(struct perf_evsel *evsel);
+
+void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
+int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
+void perf_evsel__free_stat_priv(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/

[toc] | [prev] | [next] | [standalone]

#1170235 — [PATCH 17/27] perf stat: Introduce perf_evsel__alloc_stats function

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 17/27] perf stat: Introduce perf_evsel__alloc_stats function
Message-ID<pEixI-Bm-13@gated-at.bofh.it>
In reply to#1170233
Move all stat allocation logic related to stat
object under single function. This way we can
use it separately for stat object out of evlist
object.

Link: http://lkml.kernel.org/n/tip-hclg66nszn5mx8t9uwrxxw6b@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/stat.c | 20 ++++++++++++++------
 tools/perf/util/stat.h |  2 ++
 2 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 818cb022fcb6..f2a0d1521e26 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -189,17 +189,25 @@ void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
 	evsel->prev_raw_counts = NULL;
 }
 
+int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw)
+{
+	int ncpus = perf_evsel__nr_cpus(evsel);
+	int nthreads = thread_map__nr(evsel->threads);
+
+	if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
+	    perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
+	    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
+		return -ENOMEM;
+
+	return 0;
+}
+
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
 {
 	struct perf_evsel *evsel;
-	int nthreads = thread_map__nr(evlist->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, ncpus, nthreads) < 0 ||
-		    (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
+		if (perf_evsel__alloc_stats(evsel, alloc_raw))
 			goto out_free;
 	}
 
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 5f62db2472c7..9f05c571befe 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -103,6 +103,8 @@ int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
 				      int ncpus, int nthreads);
 void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel);
 
+int perf_evsel__alloc_stats(struct perf_evsel *evsel, bool alloc_raw);
+
 int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw);
 void perf_evlist__free_stats(struct perf_evlist *evlist);
 void perf_evlist__reset_stats(struct perf_evlist *evlist);
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170237 — [PATCH 07/27] perf tools: Make perf_evsel__(nr_)cpus generic

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 07/27] perf tools: Make perf_evsel__(nr_)cpus generic
Message-ID<pEixI-Bm-19@gated-at.bofh.it>
In reply to#1170233
Because we now propagate all evlist's cpu_maps and thread_map
objects through all evsels, the perf_evsel__(nr_)cpus no longer
need to be specific to stat object and check evlist and target
objects.

Link: http://lkml.kernel.org/n/tip-3pp2i969cmewv580k6qvd3up@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c | 10 ----------
 tools/perf/util/evsel.h   | 11 +++++++++++
 2 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index fcf99bdeb19e..3e1636cae76b 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -141,16 +141,6 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a,
 	}
 }
 
-static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
-{
-	return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
-}
-
-static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
-{
-	return perf_evsel__cpus(evsel)->nr;
-}
-
 static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
 {
 	int i;
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 9e16a5c4eb01..4dbf32d94dfb 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -8,6 +8,7 @@
 #include <linux/types.h>
 #include "xyarray.h"
 #include "symbol.h"
+#include "cpumap.h"
 
 struct perf_counts_values {
 	union {
@@ -114,6 +115,16 @@ struct thread_map;
 struct perf_evlist;
 struct record_opts;
 
+static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
+{
+	return evsel->cpus;
+}
+
+static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
+{
+	return perf_evsel__cpus(evsel)->nr;
+}
+
 void perf_counts_values__scale(struct perf_counts_values *count,
 			       bool scale, s8 *pscaled);
 
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170238 — [PATCH 04/27] perf tools: Add reference counting for thread_map object

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 04/27] perf tools: Add reference counting for thread_map object
Message-ID<pEixI-Bm-21@gated-at.bofh.it>
In reply to#1170233
Adding refference counting for thread_map object, so
it could be easily shared among other objects.

Using thread_map__put instead thread_map__delete and making
thread_map__delete static.

Link: http://lkml.kernel.org/n/tip-myadl53clbkjvzeqolwp95w0@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/tests/code-reading.c            |  2 +-
 tools/perf/tests/keep-tracking.c           |  2 +-
 tools/perf/tests/mmap-basic.c              |  2 +-
 tools/perf/tests/mmap-thread-lookup.c      |  2 +-
 tools/perf/tests/openat-syscall-all-cpus.c |  2 +-
 tools/perf/tests/openat-syscall.c          |  2 +-
 tools/perf/tests/switch-tracking.c         |  2 +-
 tools/perf/util/evlist.c                   |  4 ++--
 tools/perf/util/python.c                   |  2 +-
 tools/perf/util/thread_map.c               | 31 ++++++++++++++++++++++++++----
 tools/perf/util/thread_map.h               |  7 +++++--
 11 files changed, 42 insertions(+), 16 deletions(-)

diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 6b3250f54240..39c784a100a9 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -546,7 +546,7 @@ out_err:
 		perf_evlist__delete(evlist);
 	} else {
 		cpu_map__put(cpus);
-		thread_map__delete(threads);
+		thread_map__put(threads);
 	}
 	machines__destroy_kernel_maps(&machines);
 	machine__delete_threads(machine);
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index a330235cefc0..4d4b9837b630 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -145,7 +145,7 @@ out_err:
 		perf_evlist__delete(evlist);
 	} else {
 		cpu_map__put(cpus);
-		thread_map__delete(threads);
+		thread_map__put(threads);
 	}
 
 	return err;
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 5a9ef5833452..666b67a4df9d 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -142,6 +142,6 @@ out_delete_evlist:
 out_free_cpus:
 	cpu_map__put(cpus);
 out_free_threads:
-	thread_map__delete(threads);
+	thread_map__put(threads);
 	return err;
 }
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 7f48efa7e295..145050e2e544 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -143,7 +143,7 @@ static int synth_process(struct machine *machine)
 						perf_event__process,
 						machine, 0, 500);
 
-	thread_map__delete(map);
+	thread_map__put(map);
 	return err;
 }
 
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index 9a7a116e09b8..b8d552b13950 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -111,6 +111,6 @@ out_close_fd:
 out_evsel_delete:
 	perf_evsel__delete(evsel);
 out_thread_map_delete:
-	thread_map__delete(threads);
+	thread_map__put(threads);
 	return err;
 }
diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c
index 9f9491bb8e48..bdfa1f446681 100644
--- a/tools/perf/tests/openat-syscall.c
+++ b/tools/perf/tests/openat-syscall.c
@@ -56,6 +56,6 @@ out_close_fd:
 out_evsel_delete:
 	perf_evsel__delete(evsel);
 out_thread_map_delete:
-	thread_map__delete(threads);
+	thread_map__put(threads);
 	return err;
 }
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 1b06122beb76..e698742d4fec 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -561,7 +561,7 @@ out:
 		perf_evlist__delete(evlist);
 	} else {
 		cpu_map__put(cpus);
-		thread_map__delete(threads);
+		thread_map__put(threads);
 	}
 
 	return err;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 59498f7b3e9b..a8d18a3d2164 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -115,7 +115,7 @@ void perf_evlist__delete(struct perf_evlist *evlist)
 	perf_evlist__munmap(evlist);
 	perf_evlist__close(evlist);
 	cpu_map__put(evlist->cpus);
-	thread_map__delete(evlist->threads);
+	thread_map__put(evlist->threads);
 	evlist->cpus = NULL;
 	evlist->threads = NULL;
 	perf_evlist__purge(evlist);
@@ -1120,7 +1120,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	return 0;
 
 out_delete_threads:
-	thread_map__delete(evlist->threads);
+	thread_map__put(evlist->threads);
 	evlist->threads = NULL;
 	return -1;
 }
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index b106d56df240..626422eda727 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -453,7 +453,7 @@ static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
 
 static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads)
 {
-	thread_map__delete(pthreads->threads);
+	thread_map__put(pthreads->threads);
 	pthreads->ob_type->tp_free((PyObject*)pthreads);
 }
 
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 5b2f2495af26..7b41aacdbc69 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -9,6 +9,7 @@
 #include "strlist.h"
 #include <string.h>
 #include <api/fs/fs.h>
+#include "asm/bug.h"
 #include "thread_map.h"
 #include "util.h"
 #include "debug.h"
@@ -96,6 +97,7 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 			comm_init(threads, i);
 		}
 		threads->nr = items;
+		atomic_set(&threads->refcnt, 1);
 	}
 
 	for (i=0; i<items; i++)
@@ -113,6 +115,7 @@ struct thread_map *thread_map__new_by_tid(pid_t tid)
 		thread_map__set_pid(threads, 0, tid);
 		threads->nr = 1;
 		comm_init(threads, 0);
+		atomic_set(&threads->refcnt, 1);
 	}
 
 	return threads;
@@ -134,6 +137,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 		goto out_free_threads;
 
 	threads->nr = 0;
+	atomic_set(&threads->refcnt, 1);
 
 	while (!readdir_r(proc, &dirent, &next) && next) {
 		char *end;
@@ -264,6 +268,8 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 
 out:
 	strlist__delete(slist);
+	if (threads)
+		atomic_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_namelist:
@@ -284,6 +290,7 @@ struct thread_map *thread_map__new_dummy(void)
 		thread_map__set_pid(threads, 0, -1);
 		threads->nr = 1;
 		comm_init(threads, 0);
+		atomic_set(&threads->refcnt, 1);
 	}
 	return threads;
 }
@@ -327,6 +334,8 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 		comm_init(threads, ntasks - 1);
 	}
 out:
+	if (threads)
+		atomic_set(&threads->refcnt, 1);
 	return threads;
 
 out_free_threads:
@@ -346,16 +355,30 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,
 	return thread_map__new_by_tid_str(tid);
 }
 
-void thread_map__delete(struct thread_map *threads)
+static void thread_map__delete(struct thread_map *threads)
 {
-	int i;
-
 	if (threads) {
+		int i;
+
+		WARN_ONCE(atomic_read(&threads->refcnt) != 0,
+			  "thread map refcnt disbalanced\n");
 		for (i = 0; i < threads->nr; i++)
 			free(thread_map__comm(threads, i));
+		free(threads);
 	}
+}
 
-	free(threads);
+struct thread_map *thread_map__get(struct thread_map *map)
+{
+	if (map)
+		atomic_inc(&map->refcnt);
+	return map;
+}
+
+void thread_map__put(struct thread_map *map)
+{
+	if (map && atomic_dec_and_test(&map->refcnt))
+		thread_map__delete(map);
 }
 
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp)
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 0f67843475e6..70c575b14318 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -3,6 +3,7 @@
 
 #include <sys/types.h>
 #include <stdio.h>
+#include <linux/atomic.h>
 
 struct thread_map_data {
 	pid_t    pid;
@@ -10,6 +11,7 @@ struct thread_map_data {
 };
 
 struct thread_map {
+	atomic_t refcnt;
 	int nr;
 	struct thread_map_data map[];
 };
@@ -20,11 +22,12 @@ struct thread_map *thread_map__new_by_tid(pid_t tid);
 struct thread_map *thread_map__new_by_uid(uid_t uid);
 struct thread_map *thread_map__new(pid_t pid, pid_t tid, uid_t uid);
 
+struct thread_map *thread_map__get(struct thread_map *map);
+void thread_map__put(struct thread_map *map);
+
 struct thread_map *thread_map__new_str(const char *pid,
 		const char *tid, uid_t uid);
 
-void thread_map__delete(struct thread_map *threads);
-
 size_t thread_map__fprintf(struct thread_map *threads, FILE *fp);
 
 static inline int thread_map__nr(struct thread_map *threads)
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170239 — [PATCH 25/27] perf stat: Using init_stats instead of memset

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 25/27] perf stat: Using init_stats instead of memset
Message-ID<pEixI-Bm-25@gated-at.bofh.it>
In reply to#1170233
The init_stats function is meant to init 'struct stats'.

Reported-by: David Ahern <dsahern@gmail.com>
Link: http://lkml.kernel.org/n/tip-secivjava21t7921lkpy0pfj@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index aa706fca410e..39a97ade2cf3 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -284,7 +284,7 @@ static int process_counter(struct perf_evsel *counter)
 	int i, ret;
 
 	aggr->val = aggr->ena = aggr->run = 0;
-	memset(ps->res_stats, 0, sizeof(ps->res_stats));
+	init_stats(ps->res_stats);
 
 	if (counter->per_pkg)
 		zero_per_pkg(counter);
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170241 — [PATCH 23/27] perf stat: Remove perf_evsel__read_cb function

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 23/27] perf stat: Remove perf_evsel__read_cb function
Message-ID<pEixJ-Bm-29@gated-at.bofh.it>
In reply to#1170233
It's no longer used, the stat command uses perf_evsel__read now.

Link: http://lkml.kernel.org/n/tip-5yh5pg1mw9wefhup1vvtssh9@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/evsel.c | 16 ----------------
 tools/perf/util/evsel.h |  7 -------
 2 files changed, 23 deletions(-)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 2e0a4e064f44..2936b3080722 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -939,22 +939,6 @@ void perf_counts_values__scale(struct perf_counts_values *count,
 		*pscaled = scaled;
 }
 
-int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
-			perf_evsel__read_cb_t cb)
-{
-	struct perf_counts_values count;
-
-	memset(&count, 0, sizeof(count));
-
-	if (FD(evsel, cpu, thread) < 0)
-		return -EINVAL;
-
-	if (readn(FD(evsel, cpu, thread), &count, sizeof(count)) < 0)
-		return -errno;
-
-	return cb(evsel, cpu, thread, &count);
-}
-
 int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 		     struct perf_counts_values *count)
 {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a79944a21e8f..4a7ed5656cf0 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -229,13 +229,6 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1,
 	 (a)->attr.type == (b)->attr.type &&	\
 	 (a)->attr.config == (b)->attr.config)
 
-typedef int (perf_evsel__read_cb_t)(struct perf_evsel *evsel,
-				    int cpu, int thread,
-				    struct perf_counts_values *count);
-
-int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
-			perf_evsel__read_cb_t cb);
-
 int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 		     struct perf_counts_values *count);
 
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170242 — [PATCH 18/27] perf stat: Introduce perf_evsel__read function

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 18/27] perf stat: Introduce perf_evsel__read function
Message-ID<pEixJ-Bm-31@gated-at.bofh.it>
In reply to#1170233
Adding simple read function that reads/store data
into given struct perf_counts_values *count object.

Link: http://lkml.kernel.org/n/tip-9r2zmzq0vkw8l300usq824sg@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/evsel.c | 14 ++++++++++++++
 tools/perf/util/evsel.h |  3 +++
 2 files changed, 17 insertions(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index cd6ce7066f85..2e0a4e064f44 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -955,6 +955,20 @@ int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
 	return cb(evsel, cpu, thread, &count);
 }
 
+int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+		     struct perf_counts_values *count)
+{
+	memset(count, 0, sizeof(*count));
+
+	if (FD(evsel, cpu, thread) < 0)
+		return -EINVAL;
+
+	if (readn(FD(evsel, cpu, thread), count, sizeof(*count)) < 0)
+		return -errno;
+
+	return 0;
+}
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale)
 {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 020f7e13634a..a79944a21e8f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -236,6 +236,9 @@ typedef int (perf_evsel__read_cb_t)(struct perf_evsel *evsel,
 int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
 			perf_evsel__read_cb_t cb);
 
+int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+		     struct perf_counts_values *count);
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale);
 
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170243 — [PATCH 15/27] perf stat: Move perf_evsel__(alloc|free)_prev_raw_counts into stat object

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 15/27] perf stat: Move perf_evsel__(alloc|free)_prev_raw_counts into stat object
Message-ID<pEixJ-Bm-33@gated-at.bofh.it>
In reply to#1170233
Moving perf_evsel__(alloc|free)_prev_raw_counts into stat object,
so it could be used in following patches.

Link: http://lkml.kernel.org/n/tip-am4oi22oasuy97bc4mt8i33e@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c | 18 ------------------
 tools/perf/util/stat.c    | 18 ++++++++++++++++++
 tools/perf/util/stat.h    |  4 ++++
 3 files changed, 22 insertions(+), 18 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 8a7fd0c60ab1..0ccba5c6b61d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -141,24 +141,6 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a,
 	}
 }
 
-static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
-					     int ncpus, int nthreads)
-{
-	struct perf_counts *counts;
-
-	counts = perf_counts__new(ncpus, nthreads);
-	if (counts)
-		evsel->prev_raw_counts = counts;
-
-	return counts ? 0 : -ENOMEM;
-}
-
-static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
-{
-	perf_counts__delete(evsel->prev_raw_counts);
-	evsel->prev_raw_counts = NULL;
-}
-
 static void perf_evlist__free_stats(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index b8c329f41f13..6221c3898397 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -168,3 +168,21 @@ void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
 {
 	zfree(&evsel->priv);
 }
+
+int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+				      int ncpus, int nthreads)
+{
+	struct perf_counts *counts;
+
+	counts = perf_counts__new(ncpus, nthreads);
+	if (counts)
+		evsel->prev_raw_counts = counts;
+
+	return counts ? 0 : -ENOMEM;
+}
+
+void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
+{
+	perf_counts__delete(evsel->prev_raw_counts);
+	evsel->prev_raw_counts = NULL;
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index c441cb312565..454b26875aef 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -96,4 +96,8 @@ void perf_evsel__free_counts(struct perf_evsel *evsel);
 void perf_evsel__reset_stat_priv(struct perf_evsel *evsel);
 int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel);
 void perf_evsel__free_stat_priv(struct perf_evsel *evsel);
+
+int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel,
+				      int ncpus, int nthreads);
+void perf_evsel__free_prev_raw_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/

[toc] | [prev] | [next] | [standalone]

#1170245 — [PATCH 02/27] perf tools: Add comm string into struct thread_map

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 02/27] perf tools: Add comm string into struct thread_map
Message-ID<pEixJ-Bm-37@gated-at.bofh.it>
In reply to#1170233
Adding support to hold comm name together with pids in
'struct thread_map'. It will be useful for --per-thread
option to display task pid together with task name.

Getting the task name from /proc/$pid/comm.

Link: http://lkml.kernel.org/n/tip-pf6bgmbujukce0sgliuhj2f4@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/python-ext-sources |  1 +
 tools/perf/util/thread_map.c       | 67 ++++++++++++++++++++++++++++++++++++--
 tools/perf/util/thread_map.h       | 12 +++++++
 3 files changed, 77 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index 5925fec90562..e23ded40c79e 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -20,3 +20,4 @@ util/stat.c
 util/strlist.c
 util/trace-event.c
 ../../lib/rbtree.c
+util/string.c
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 7a4be3754d05..5b2f2495af26 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -8,8 +8,10 @@
 #include <unistd.h>
 #include "strlist.h"
 #include <string.h>
+#include <api/fs/fs.h>
 #include "thread_map.h"
 #include "util.h"
+#include "debug.h"
 
 /* Skip "." and ".." directories */
 static int filter(const struct dirent *dir)
@@ -29,6 +31,51 @@ static struct thread_map *thread_map__realloc(struct thread_map *map, int nr)
 
 #define thread_map__alloc(__nr) thread_map__realloc(NULL, __nr)
 
+static int get_comm(char **comm, pid_t pid)
+{
+	char *path;
+	size_t size;
+	int err;
+
+	if (asprintf(&path, "%s/%d/comm", procfs__mountpoint(), pid) == -1)
+		return -ENOMEM;
+
+	err = filename__read_str(path, comm, &size);
+	if (!err) {
+		/*
+		 * We're reading 16 bytes, while filename__read_str
+		 * allocates data per BUFSIZ bytes, so we can safely
+		 * mark the end of the string.
+		 */
+		(*comm)[size] = 0;
+		rtrim(*comm);
+	}
+
+	free(path);
+	return err;
+}
+
+static void comm_init(struct thread_map *map, int i)
+{
+	pid_t pid = thread_map__pid(map, i);
+	char *comm = NULL;
+
+	/* dummy pid comm initialization */
+	if (pid == -1) {
+		thread_map__set_comm(map, i, strdup("dummy"));
+		return;
+	}
+
+	/*
+	 * The comm name is like extra bonus ;-),
+	 * so just warn if we fail for any reason.
+	 */
+	if (get_comm(&comm, pid))
+		pr_warning("Couldn't resolve comm name for pid %d\n", pid);
+
+	thread_map__set_comm(map, i, comm);
+}
+
 struct thread_map *thread_map__new_by_pid(pid_t pid)
 {
 	struct thread_map *threads;
@@ -44,8 +91,10 @@ struct thread_map *thread_map__new_by_pid(pid_t pid)
 
 	threads = thread_map__alloc(items);
 	if (threads != NULL) {
-		for (i = 0; i < items; i++)
+		for (i = 0; i < items; i++) {
 			thread_map__set_pid(threads, i, atoi(namelist[i]->d_name));
+			comm_init(threads, i);
+		}
 		threads->nr = items;
 	}
 
@@ -63,6 +112,7 @@ struct thread_map *thread_map__new_by_tid(pid_t tid)
 	if (threads != NULL) {
 		thread_map__set_pid(threads, 0, tid);
 		threads->nr = 1;
+		comm_init(threads, 0);
 	}
 
 	return threads;
@@ -126,6 +176,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
 		for (i = 0; i < items; i++) {
 			thread_map__set_pid(threads, threads->nr + i,
 					    atoi(namelist[i]->d_name));
+			comm_init(threads, threads->nr + i);
 		}
 
 		for (i = 0; i < items; i++)
@@ -202,8 +253,9 @@ static struct thread_map *thread_map__new_by_pid_str(const char *pid_str)
 
 		threads = nt;
 
-		for (i = 0; i < items; i++) {
-			thread_map__set_pid(threads, j++, atoi(namelist[i]->d_name));
+		for (i = 0; i < items; i++, j++) {
+			thread_map__set_pid(threads, j, atoi(namelist[i]->d_name));
+			comm_init(threads, j);
 			zfree(&namelist[i]);
 		}
 		threads->nr = total_tasks;
@@ -231,6 +283,7 @@ struct thread_map *thread_map__new_dummy(void)
 	if (threads != NULL) {
 		thread_map__set_pid(threads, 0, -1);
 		threads->nr = 1;
+		comm_init(threads, 0);
 	}
 	return threads;
 }
@@ -271,6 +324,7 @@ static struct thread_map *thread_map__new_by_tid_str(const char *tid_str)
 		threads = nt;
 		thread_map__set_pid(threads, ntasks - 1, tid);
 		threads->nr = ntasks;
+		comm_init(threads, ntasks - 1);
 	}
 out:
 	return threads;
@@ -294,6 +348,13 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,
 
 void thread_map__delete(struct thread_map *threads)
 {
+	int i;
+
+	if (threads) {
+		for (i = 0; i < threads->nr; i++)
+			free(thread_map__comm(threads, i));
+	}
+
 	free(threads);
 }
 
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index b9f40679f589..0f67843475e6 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -6,6 +6,7 @@
 
 struct thread_map_data {
 	pid_t    pid;
+	char	*comm;
 };
 
 struct thread_map {
@@ -41,4 +42,15 @@ thread_map__set_pid(struct thread_map *map, int thread, pid_t pid)
 {
 	map->map[thread].pid = pid;
 }
+
+static inline char *thread_map__comm(struct thread_map *map, int thread)
+{
+	return map->map[thread].comm;
+}
+
+static inline void
+thread_map__set_comm(struct thread_map *map, int thread, char *comm)
+{
+	map->map[thread].comm = comm;
+}
 #endif	/* __PERF_THREAD_MAP_H */
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170246 — [PATCH 21/27] perf stat: Move zero_per_pkg into counter process code

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 21/27] perf stat: Move zero_per_pkg into counter process code
Message-ID<pEixJ-Bm-35@gated-at.bofh.it>
In reply to#1170233
Moving zero_per_pkg into counter process code,
to make the reading path free of processing logic.

Link: http://lkml.kernel.org/n/tip-wi2ces8lzpzip39yes2f9vea@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 74ac92baa2bd..b7c184bd559c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -285,6 +285,9 @@ static int process_counter(struct perf_evsel *counter)
 
 	aggr->val = aggr->ena = aggr->run = 0;
 
+	if (counter->per_pkg)
+		zero_per_pkg(counter);
+
 	ret = process_counter_maps(counter);
 	if (ret)
 		return ret;
@@ -328,9 +331,6 @@ static int read_counter(struct perf_evsel *counter)
 	if (counter->system_wide)
 		nthreads = 1;
 
-	if (counter->per_pkg)
-		zero_per_pkg(counter);
-
 	for (thread = 0; thread < nthreads; thread++) {
 		for (cpu = 0; cpu < ncpus; cpu++) {
 			struct perf_counts_values *count;
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170247 — [PATCH 27/27] perf stat: Introduce --per-thread option

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 27/27] perf stat: Introduce --per-thread option
Message-ID<pEixJ-Bm-39@gated-at.bofh.it>
In reply to#1170233
Currently all the -p option PID arguments tasks values
get aggregated and printed as single values.

Adding --per-tasks option to print values per task.

  $ perf stat  -e cycles,instructions --per-thread -p 30190,30242
  ^C
   Performance counter stats for process id '30190,30242':

               cat-30190                     0      cycles
               yes-30242         3,842,525,421      cycles
               cat-30190                     0      instructions
               yes-30242        10,370,817,010      instructions

         1.143155657 seconds time elapsed

Also works under interval mode:

  $ perf stat  -e cycles,instructions --per-thread -p 30190,30242 -I 1000
  #           time             comm-pid                  counts unit events
       1.000073435              cat-30190                89,058      cycles
       1.000073435              yes-30242         3,360,786,902      cycles                     (100.00%)
       1.000073435              cat-30190                14,066      instructions
       1.000073435              yes-30242         9,069,937,462      instructions
       2.000204830              cat-30190                     0      cycles
       2.000204830              yes-30242         3,351,667,626      cycles
       2.000204830              cat-30190                     0      instructions
       2.000204830              yes-30242         9,045,796,885      instructions
  ^C     2.771286639              cat-30190                     0      cycles
       2.771286639              yes-30242         2,593,884,166      cycles
       2.771286639              cat-30190                     0      instructions
       2.771286639              yes-30242         7,001,171,191      instructions

It works only with -t and -p options, otherwise following
error is printed:

  $ perf stat  -e cycles --per-thread  -I 1000 ls
  The --per-thread option is only available when monitoring via -p -t options.
      -p, --pid <pid>       stat events on existing process id
      -t, --tid <tid>       stat events on existing thread id

Link: http://lkml.kernel.org/n/tip-0v0ixd9k7o9z1u8hqngm1coe@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/Documentation/perf-stat.txt |  4 ++
 tools/perf/builtin-stat.c              | 68 +++++++++++++++++++++++++++++++++-
 tools/perf/util/stat.h                 |  1 +
 3 files changed, 71 insertions(+), 2 deletions(-)

diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 04e150d83e7d..47469abdcc1c 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -144,6 +144,10 @@ is a useful mode to detect imbalance between physical cores.  To enable this mod
 use --per-core in addition to -a. (system-wide).  The output includes the
 core number and the number of online logical processors on that physical processor.
 
+--per-thread::
+Aggregate counts per monitored threads, when monitoring threads (-t option)
+or processes (-p option).
+
 -D msecs::
 --delay msecs::
 After starting the program, wait msecs before measuring. This is useful to
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 56dc8881cb05..64e67b27528d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -231,6 +231,7 @@ process_counter_values(struct perf_evsel *evsel, int cpu, int thread,
 		count = &zero;
 
 	switch (aggr_mode) {
+	case AGGR_THREAD:
 	case AGGR_CORE:
 	case AGGR_SOCKET:
 	case AGGR_NONE:
@@ -602,6 +603,14 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
 			csv_output ? 0 : -4,
 			perf_evsel__cpus(evsel)->map[id], csv_sep);
 		break;
+	case AGGR_THREAD:
+		fprintf(output, "%*s-%*d%s",
+			csv_output ? 0 : 16,
+			thread_map__comm(evsel->threads, id),
+			csv_output ? 0 : -8,
+			thread_map__pid(evsel->threads, id),
+			csv_sep);
+		break;
 	case AGGR_GLOBAL:
 	default:
 		break;
@@ -750,6 +759,40 @@ static void print_aggr(char *prefix)
 	}
 }
 
+static void print_aggr_thread(struct perf_evsel *counter, char *prefix)
+{
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = cpu_map__nr(counter->cpus);
+	int cpu, thread;
+	double uval;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		u64 ena = 0, run = 0, val = 0;
+
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			val += perf_counts(counter->counts, cpu, thread)->val;
+			ena += perf_counts(counter->counts, cpu, thread)->ena;
+			run += perf_counts(counter->counts, cpu, thread)->run;
+		}
+
+		if (prefix)
+			fprintf(output, "%s", prefix);
+
+		uval = val * counter->scale;
+
+		if (nsec_counter(counter))
+			nsec_printout(thread, 0, counter, uval);
+		else
+			abs_printout(thread, 0, counter, uval);
+
+		if (!csv_output)
+			print_noise(counter, 1.0);
+
+		print_running(run, ena);
+		fputc('\n', output);
+	}
+}
+
 /*
  * Print out the results of a single counter:
  * aggregated counts in system-wide mode
@@ -876,6 +919,9 @@ static void print_interval(char *prefix, struct timespec *ts)
 		case AGGR_NONE:
 			fprintf(output, "#           time CPU                counts %*s events\n", unit_width, "unit");
 			break;
+		case AGGR_THREAD:
+			fprintf(output, "#           time             comm-pid                  counts %*s events\n", unit_width, "unit");
+			break;
 		case AGGR_GLOBAL:
 		default:
 			fprintf(output, "#           time             counts %*s events\n", unit_width, "unit");
@@ -944,6 +990,10 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)
 	case AGGR_SOCKET:
 		print_aggr(prefix);
 		break;
+	case AGGR_THREAD:
+		evlist__for_each(evsel_list, counter)
+			print_aggr_thread(counter, prefix);
+		break;
 	case AGGR_GLOBAL:
 		evlist__for_each(evsel_list, counter)
 			print_counter_aggr(counter, prefix);
@@ -1031,6 +1081,7 @@ static int perf_stat_init_aggr_mode(void)
 		break;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
+	case AGGR_THREAD:
 	default:
 		break;
 	}
@@ -1255,6 +1306,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		     "aggregate counts per processor socket", AGGR_SOCKET),
 	OPT_SET_UINT(0, "per-core", &aggr_mode,
 		     "aggregate counts per physical processor core", AGGR_CORE),
+	OPT_SET_UINT(0, "per-thread", &aggr_mode,
+		     "aggregate counts per thread", AGGR_THREAD),
 	OPT_UINTEGER('D', "delay", &initial_delay,
 		     "ms to wait before starting measurement after program start"),
 	OPT_END()
@@ -1346,8 +1399,19 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		run_count = 1;
 	}
 
-	/* no_aggr, cgroup are for system-wide only */
-	if ((aggr_mode != AGGR_GLOBAL || nr_cgroups) &&
+	if ((aggr_mode == AGGR_THREAD) && !target__has_task(&target)) {
+		fprintf(stderr, "The --per-thread option is only available "
+			"when monitoring via -p -t options.\n");
+		parse_options_usage(NULL, options, "p", 1);
+		parse_options_usage(NULL, options, "t", 1);
+		goto out;
+	}
+
+	/*
+	 * no_aggr, cgroup are for system-wide only
+	 * --per-thread is aggregated per thread, we dont mix it with cpu mode
+	 */
+	if (((aggr_mode != AGGR_GLOBAL && aggr_mode != AGGR_THREAD) || nr_cgroups) &&
 	    !target__has_cpu(&target)) {
 		fprintf(stderr, "both cgroup and no-aggregation "
 			"modes only available in system-wide mode\n");
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 9f05c571befe..1cfbe0a980ac 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -30,6 +30,7 @@ enum aggr_mode {
 	AGGR_GLOBAL,
 	AGGR_SOCKET,
 	AGGR_CORE,
+	AGGR_THREAD,
 };
 
 struct perf_counts_values {
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170248 — [PATCH 11/27] perf stat: Make stats work over the thread dimension

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 11/27] perf stat: Make stats work over the thread dimension
Message-ID<pEixJ-Bm-41@gated-at.bofh.it>
In reply to#1170233
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/

[toc] | [prev] | [next] | [standalone]

#1170249 — [PATCH 13/27] perf stat: Introduce perf_evlist__reset_stats

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 13/27] perf stat: Introduce perf_evlist__reset_stats
Message-ID<pEixJ-Bm-43@gated-at.bofh.it>
In reply to#1170233
To fit in with the rest of the helpers (alloc and free).

Link: http://lkml.kernel.org/n/tip-dqgpvhc4b2rius8gv65dfrte@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 983bcbbe8e0a..188cd98a4ab3 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -216,7 +216,7 @@ out_free:
 	return -1;
 }
 
-static void perf_stat__reset_stats(struct perf_evlist *evlist)
+static void perf_evlist__reset_stats(struct perf_evlist *evlist)
 {
 	struct perf_evsel *evsel;
 
@@ -224,7 +224,11 @@ static void perf_stat__reset_stats(struct perf_evlist *evlist)
 		perf_evsel__reset_stat_priv(evsel);
 		perf_evsel__reset_counts(evsel);
 	}
+}
 
+static void perf_stat__reset_stats(void)
+{
+	perf_evlist__reset_stats(evsel_list);
 	perf_stat__reset_shadow_stats();
 }
 
@@ -1473,7 +1477,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
 		status = run_perf_stat(argc, argv);
 		if (forever && status != -1) {
 			print_stat(argc, argv);
-			perf_stat__reset_stats(evsel_list);
+			perf_stat__reset_stats();
 		}
 	}
 
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170250 — [PATCH 06/27] perf tools: Propagate thread maps through the evlist

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 06/27] perf tools: Propagate thread maps through the evlist
Message-ID<pEixJ-Bm-47@gated-at.bofh.it>
In reply to#1170233
Propagate evlist's thread_map object through all the
evsel objects.

It'll be handy to access evsel's threads directly
in following patches. The reason is there's no link
from evsel to evlist which hold threads map now and
evlist is not always available.

Link: http://lkml.kernel.org/n/tip-6vc92bytyy2d6c5entm5s698@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/evlist.c | 4 +++-
 tools/perf/util/evsel.c  | 1 +
 tools/perf/util/evsel.h  | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 214affaf1cf6..6cfdee68e763 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1117,7 +1117,9 @@ static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
 		if (!evsel->cpus || target->cpu_list)
 			evsel->cpus = cpu_map__get(evlist->cpus);
 
-		if (!evsel->cpus)
+		evsel->threads = thread_map__get(evlist->threads);
+
+		if (!evsel->cpus || !evsel->threads)
 			return -ENOMEM;
 	}
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 31b0afb68825..1b2f480a3e82 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -886,6 +886,7 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 	perf_evsel__free_id(evsel);
 	close_cgroup(evsel->cgrp);
 	cpu_map__put(evsel->cpus);
+	thread_map__put(evsel->threads);
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
 	perf_evsel__object.fini(evsel);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index bb0579e8a10a..9e16a5c4eb01 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -82,6 +82,7 @@ struct perf_evsel {
 	struct cgroup_sel	*cgrp;
 	void			*handler;
 	struct cpu_map		*cpus;
+	struct thread_map	*threads;
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170253 — [PATCH 05/27] perf tools: Propagate cpu maps through the evlist

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:40 +0200
Subject[PATCH 05/27] perf tools: Propagate cpu maps through the evlist
Message-ID<pEixK-Bm-53@gated-at.bofh.it>
In reply to#1170233
Propagate evlist's cpu_map object through all the evsel objects,
while keeping already configured evsel->cpus.

It'll be handy to access evsel's cpus directly
in following patches.

Link: http://lkml.kernel.org/n/tip-myadl53clbkjvzeqolwp95w0@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/util/evlist.c | 25 ++++++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index a8d18a3d2164..214affaf1cf6 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1101,6 +1101,29 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages,
 	return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
 }
 
+static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
+				       struct target *target)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel) {
+		/*
+		 * We already have cpus for evsel (via PMU sysfs) so
+		 * keep it, if there's no target cpu list defined.
+		 */
+		if (evsel->cpus && target->cpu_list)
+			cpu_map__put(evsel->cpus);
+
+		if (!evsel->cpus || target->cpu_list)
+			evsel->cpus = cpu_map__get(evlist->cpus);
+
+		if (!evsel->cpus)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
 	evlist->threads = thread_map__new_str(target->pid, target->tid,
@@ -1117,7 +1140,7 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 	if (evlist->cpus == NULL)
 		goto out_delete_threads;
 
-	return 0;
+	return perf_evlist__propagate_maps(evlist, target);
 
 out_delete_threads:
 	thread_map__put(evlist->threads);
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170254 — [PATCH 20/27] perf stat: Separate counters reading and processing

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:50 +0200
Subject[PATCH 20/27] perf stat: Separate counters reading and processing
Message-ID<pEiHn-MJ-1@gated-at.bofh.it>
In reply to#1170233
Separating counters reading and processing so we could use
the processing part in following patches.

Using simple reading via perf_evsel__read function
to read counters now, because part of the processing
was in the read_cb callback.

Link: http://lkml.kernel.org/n/tip-u2z2wndrt664tkk3v3sh9bxz@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c | 56 +++++++++++++++++++++++++++++++++--------------
 1 file changed, 39 insertions(+), 17 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 158859e622d3..74ac92baa2bd 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -217,8 +217,9 @@ 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,
-		   struct perf_counts_values *count)
+static int
+process_counter_values(struct perf_evsel *evsel, int cpu, int thread,
+		       struct perf_counts_values *count)
 {
 	struct perf_counts_values *aggr = &evsel->counts->aggr;
 	static struct perf_counts_values zero;
@@ -239,7 +240,6 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread,
 		if (!evsel->snapshot)
 			perf_evsel__compute_deltas(evsel, cpu, thread, count);
 		perf_counts_values__scale(count, scale, NULL);
-		*perf_counts(evsel->counts, cpu, thread) = *count;
 		if (aggr_mode == AGGR_NONE)
 			perf_stat__update_shadow_stats(evsel, count->values, cpu);
 		break;
@@ -256,23 +256,41 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread,
 	return 0;
 }
 
-static int read_counter(struct perf_evsel *counter);
+static int process_counter_maps(struct perf_evsel *counter)
+{
+	int nthreads = thread_map__nr(counter->threads);
+	int ncpus = perf_evsel__nr_cpus(counter);
+	int cpu, thread;
 
-/*
- * Read out the results of a single counter:
- * aggregate counts across CPUs in system-wide mode
- */
-static int read_counter_aggr(struct perf_evsel *counter)
+	if (counter->system_wide)
+		nthreads = 1;
+
+	for (thread = 0; thread < nthreads; thread++) {
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			if (process_counter_values(counter, cpu, thread,
+						   perf_counts(counter->counts, cpu, thread)))
+				return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int process_counter(struct perf_evsel *counter)
 {
 	struct perf_counts_values *aggr = &counter->counts->aggr;
 	struct perf_stat *ps = counter->priv;
 	u64 *count = counter->counts->aggr.values;
-	int i;
+	int i, ret;
 
 	aggr->val = aggr->ena = aggr->run = 0;
 
-	if (read_counter(counter))
-		return -1;
+	ret = process_counter_maps(counter);
+	if (ret)
+		return ret;
+
+	if (aggr_mode != AGGR_GLOBAL)
+		return 0;
 
 	if (!counter->snapshot)
 		perf_evsel__compute_deltas(counter, -1, -1, aggr);
@@ -315,7 +333,10 @@ static int read_counter(struct perf_evsel *counter)
 
 	for (thread = 0; thread < nthreads; thread++) {
 		for (cpu = 0; cpu < ncpus; cpu++) {
-			if (perf_evsel__read_cb(counter, cpu, thread, read_cb))
+			struct perf_counts_values *count;
+
+			count = perf_counts(counter->counts, cpu, thread);
+			if (perf_evsel__read(counter, cpu, thread, count))
 				return -1;
 		}
 	}
@@ -332,10 +353,11 @@ static void read_counters(bool close)
 		ps = counter->priv;
 		memset(ps->res_stats, 0, sizeof(ps->res_stats));
 
-		if (aggr_mode == AGGR_GLOBAL)
-			read_counter_aggr(counter);
-		else
-			read_counter(counter);
+		if (read_counter(counter))
+			pr_warning("failed to read counter %s\n", counter->name);
+
+		if (process_counter(counter))
+			pr_warning("failed to process counter %s\n", counter->name);
 
 		if (close) {
 			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170255 — [PATCH 24/27] perf stat: Rename print_interval to process_interval

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:50 +0200
Subject[PATCH 24/27] perf stat: Rename print_interval to process_interval
Message-ID<pEiHn-MJ-5@gated-at.bofh.it>
In reply to#1170233
It suits better, because the function also reads counter's data.

Also the 'print_interval' name will be used in following
generalization of counters display.

Link: http://lkml.kernel.org/n/tip-8dwmf838kipxabe0vay8h0zn@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 526f67753664..aa706fca410e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -363,7 +363,7 @@ static void read_counters(bool close)
 	}
 }
 
-static void print_interval(void)
+static void process_interval(void)
 {
 	static int num_print_interval;
 	struct perf_evsel *counter;
@@ -526,7 +526,7 @@ static int __run_perf_stat(int argc, const char **argv)
 		if (interval) {
 			while (!waitpid(child_pid, &status, WNOHANG)) {
 				nanosleep(&ts, NULL);
-				print_interval();
+				process_interval();
 			}
 		}
 		wait(&status);
@@ -544,7 +544,7 @@ static int __run_perf_stat(int argc, const char **argv)
 		while (!done) {
 			nanosleep(&ts, NULL);
 			if (interval)
-				print_interval();
+				process_interval();
 		}
 	}
 
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170256 — [PATCH 22/27] perf stat: Move perf_stat initialization counter process code

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:50 +0200
Subject[PATCH 22/27] perf stat: Move perf_stat initialization counter process code
Message-ID<pEiHn-MJ-7@gated-at.bofh.it>
In reply to#1170233
Moving perf_stat initialization counter process code,
to make the reading path free of processing logic.

Link: http://lkml.kernel.org/n/tip-ne0sgdk0ip9f81tfiqauprc7@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index b7c184bd559c..526f67753664 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -284,6 +284,7 @@ static int process_counter(struct perf_evsel *counter)
 	int i, ret;
 
 	aggr->val = aggr->ena = aggr->run = 0;
+	memset(ps->res_stats, 0, sizeof(ps->res_stats));
 
 	if (counter->per_pkg)
 		zero_per_pkg(counter);
@@ -347,12 +348,8 @@ static int read_counter(struct perf_evsel *counter)
 static void read_counters(bool close)
 {
 	struct perf_evsel *counter;
-	struct perf_stat *ps;
 
 	evlist__for_each(evsel_list, counter) {
-		ps = counter->priv;
-		memset(ps->res_stats, 0, sizeof(ps->res_stats));
-
 		if (read_counter(counter))
 			pr_warning("failed to read counter %s\n", counter->name);
 
-- 
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/

[toc] | [prev] | [next] | [standalone]

#1170257 — [PATCH 19/27] perf stat: Introduce read_counters function

FromJiri Olsa <jolsa@kernel.org>
Date2015-06-23 00:50 +0200
Subject[PATCH 19/27] perf stat: Introduce read_counters function
Message-ID<pEiHn-MJ-9@gated-at.bofh.it>
In reply to#1170233
Moving read counters logic into single read_counters function,
which will be called for both interval and overall processing
legs.

The reason is to split reading and processing (following patches)
counters code, so we could read counters from other sources
(like perf.data) and process them in the same way as 'perf stat'
command does.

Link: http://lkml.kernel.org/n/tip-yi40dw75mmzib0m37u11m767@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c | 47 ++++++++++++++++++++++-------------------------
 1 file changed, 22 insertions(+), 25 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 3e385f9f12ee..158859e622d3 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -323,27 +323,35 @@ static int read_counter(struct perf_evsel *counter)
 	return 0;
 }
 
-static void print_interval(void)
+static void read_counters(bool close)
 {
-	static int num_print_interval;
 	struct perf_evsel *counter;
 	struct perf_stat *ps;
-	struct timespec ts, rs;
-	char prefix[64];
 
-	if (aggr_mode == AGGR_GLOBAL) {
-		evlist__for_each(evsel_list, counter) {
-			ps = counter->priv;
-			memset(ps->res_stats, 0, sizeof(ps->res_stats));
+	evlist__for_each(evsel_list, counter) {
+		ps = counter->priv;
+		memset(ps->res_stats, 0, sizeof(ps->res_stats));
+
+		if (aggr_mode == AGGR_GLOBAL)
 			read_counter_aggr(counter);
-		}
-	} else	{
-		evlist__for_each(evsel_list, counter) {
-			ps = counter->priv;
-			memset(ps->res_stats, 0, sizeof(ps->res_stats));
+		else
 			read_counter(counter);
+
+		if (close) {
+			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
+					     thread_map__nr(evsel_list->threads));
 		}
 	}
+}
+
+static void print_interval(void)
+{
+	static int num_print_interval;
+	struct perf_evsel *counter;
+	struct timespec ts, rs;
+	char prefix[64];
+
+	read_counters(false);
 
 	clock_gettime(CLOCK_MONOTONIC, &ts);
 	diff_timespec(&rs, &ts, &ref_time);
@@ -525,18 +533,7 @@ static int __run_perf_stat(int argc, const char **argv)
 
 	update_stats(&walltime_nsecs_stats, t1 - t0);
 
-	if (aggr_mode == AGGR_GLOBAL) {
-		evlist__for_each(evsel_list, counter) {
-			read_counter_aggr(counter);
-			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
-					     thread_map__nr(evsel_list->threads));
-		}
-	} else {
-		evlist__for_each(evsel_list, counter) {
-			read_counter(counter);
-			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
-		}
-	}
+	read_counters(true);
 
 	return WEXITSTATUS(status);
 }
-- 
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/

[toc] | [prev] | [next] | [standalone]

Page 1 of 2  [1] 2  Next page →

Back to top | Article view | linux.kernel

csiph-web