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

Groups > linux.kernel > #1277494 > unrolled thread

[PATCH 1/2] perf stat: Clear sample_(type|period) for counting

Back to article view | Back to linux.kernel

Contents

  [PATCH 1/2] perf stat: Clear sample_(type|period) for counting Jiri Olsa <jolsa@kernel.org> - 2015-11-25 16:40 +0100
    [tip:perf/core] perf stat: Clear sample_(type|period)   for counting tip-bot for Jiri Olsa <tipbot@zytor.com> - 2015-11-27 08:50 +0100

#1277494 — [PATCH 1/2] perf stat: Clear sample_(type|period) for counting

Clear sample_(type|period) for counting, as it only confuses
debug output with unwanted sampling details:

Before:
  $ sudo perf stat -e 'raw_syscalls:sys_enter' -vv ls
  ------------------------------------------------------------
  perf_event_attr:
    type                             2
    size                             112
    config                           0x11
    { sample_period, sample_freq }   1
    sample_type                      TIME|CPU|PERIOD|RAW
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ...

After:
  $ sudo perf stat -e 'raw_syscalls:sys_enter' -vv ls
  ------------------------------------------------------------
  perf_event_attr:
    type                             2
    size                             112
    config                           0x11
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ...

Link: http://lkml.kernel.org/n/tip-cmf4xlq43o2i28a2nhex7bik@git.kernel.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
---
 tools/perf/builtin-stat.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e77880b5094d..df2fbf046ee2 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -161,6 +161,13 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 
 	attr->inherit = !no_inherit;
 
+	/*
+	 * Some events get initialized with sample_(period/type) set,
+	 * like tracepoints. Clear it up for counting.
+	 */
+	attr->sample_period = 0;
+	attr->sample_type   = 0;
+
 	if (target__has_cpu(&target))
 		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
 
-- 
2.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [next] | [standalone]

#1278588 — [tip:perf/core] perf stat: Clear sample_(type|period) for counting

Commit-ID:  6acd8e9271cdeaec458fd4eec4a6765d16e0e61c
Gitweb:     http://git.kernel.org/tip/6acd8e9271cdeaec458fd4eec4a6765d16e0e61c
Author:     Jiri Olsa <jolsa@kernel.org>
AuthorDate: Wed, 25 Nov 2015 16:36:54 +0100
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Thu, 26 Nov 2015 16:52:28 -0300

perf stat: Clear sample_(type|period) for counting

Clear sample_(type|period) for counting, as it only confuses debug
output with unwanted sampling details:

Before:

  $ sudo perf stat -e 'raw_syscalls:sys_enter' -vv ls
  ------------------------------------------------------------
  perf_event_attr:
    type                             2
    size                             112
    config                           0x11
    { sample_period, sample_freq }   1
    sample_type                      TIME|CPU|PERIOD|RAW
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ...

After:
  $ sudo perf stat -e 'raw_syscalls:sys_enter' -vv ls
  ------------------------------------------------------------
  perf_event_attr:
    type                             2
    size                             112
    config                           0x11
    read_format                      TOTAL_TIME_ENABLED|TOTAL_TIME_RUNNING
    disabled                         1
    inherit                          1
    enable_on_exec                   1
    exclude_guest                    1
  ...

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1448465815-27404-1-git-send-email-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index e77880b..df2fbf0 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -161,6 +161,13 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 
 	attr->inherit = !no_inherit;
 
+	/*
+	 * Some events get initialized with sample_(period/type) set,
+	 * like tracepoints. Clear it up for counting.
+	 */
+	attr->sample_period = 0;
+	attr->sample_type   = 0;
+
 	if (target__has_cpu(&target))
 		return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web