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

Groups > linux.kernel > #1326506 > unrolled thread

[PATCH 0/8] perf config: Document config variables in man page

Back to article view | Back to linux.kernel

Contents

  [PATCH 0/8] perf config: Document config variables in man page Taeung Song <treeze.taeung@gmail.com> - 2016-02-04 10:30 +0100
    [PATCH 1/8] perf config: Document 'ui.show-headers' variable in man page Taeung Song <treeze.taeung@gmail.com> - 2016-02-04 10:30 +0100
    [PATCH 4/8] perf config: Document 'top.children' variable in man page Taeung Song <treeze.taeung@gmail.com> - 2016-02-04 10:30 +0100
    [PATCH 8/8] perf config: Document 'record.build-id' variable in man page Taeung Song <treeze.taeung@gmail.com> - 2016-02-04 10:30 +0100
    [PATCH 7/8] perf config: Document 'kmem.default' variable in man page Taeung Song <treeze.taeung@gmail.com> - 2016-02-04 10:30 +0100
    [PATCH 5/8] perf config: Document 'man.viewer' variable in man page Taeung Song <treeze.taeung@gmail.com> - 2016-02-04 10:30 +0100
    [PATCH 2/8] perf config: Document variables for 'call-graph' section in man page Taeung Song <treeze.taeung@gmail.com> - 2016-02-04 10:30 +0100
    [PATCH 3/8] perf config: Document variables for 'report' section in man page Taeung Song <treeze.taeung@gmail.com> - 2016-02-04 10:30 +0100
    [PATCH 6/8] perf config: Document 'pager.<subcommand>' variables in man page Taeung Song <treeze.taeung@gmail.com> - 2016-02-04 10:30 +0100
    Re: [PATCH 0/8] perf config: Document config variables in man page Arnaldo Carvalho de Melo <acme@kernel.org> - 2016-02-04 16:00 +0100
      Re: [PATCH 0/8] perf config: Document config variables in man page Taeung Song <treeze.taeung@gmail.com> - 2016-02-05 11:50 +0100
      Re: [PATCH 0/8] perf config: Document config variables in man page Taeung Song <treeze.taeung@gmail.com> - 2016-02-05 12:10 +0100
        Re: [PATCH 0/8] perf config: Document config variables in man page Namhyung Kim <namhyung@kernel.org> - 2016-02-05 14:10 +0100
          Re: [PATCH 0/8] perf config: Document config variables in man page Arnaldo Carvalho de Melo <arnaldo.melo@gmail.com> - 2016-02-05 14:40 +0100
            Re: [PATCH 0/8] perf config: Document config variables in man page Namhyung Kim <namhyung@kernel.org> - 2016-02-05 14:50 +0100
            Re: [PATCH 0/8] perf config: Document config variables in man page Taeung Song <treeze.taeung@gmail.com> - 2016-02-05 14:50 +0100

#1326506 — [PATCH 0/8] perf config: Document config variables in man page

Document perf config informations each section
in Documentation/perf-config.txt excluding 'help' section.

Taeung Song (8):
  perf config: Document 'ui.show-headers' variable in man page
  perf config: Document variables for 'call-graph' section in man page
  perf config: Document variables for 'report' section in man page
  perf config: Document 'top.children' variable in man page
  perf config: Document 'man.viewer' variable in man page
  perf config: Document 'pager.<subcommand>' variables in man page
  perf config: Document 'kmem.default' variable in man page
  perf config: Document 'record.build-id' variable in man page

 tools/perf/Documentation/perf-config.txt | 141 +++++++++++++++++++++++++++++++
 1 file changed, 141 insertions(+)

-- 
2.5.0

[toc] | [next] | [standalone]

#1326507 — [PATCH 1/8] perf config: Document 'ui.show-headers' variable in man page

Explain 'ui.show-headers' variable.

Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
---
 tools/perf/Documentation/perf-config.txt | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 74589c6..4278722 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -296,6 +296,12 @@ hist.*::
 	       and 'baz' to 50.00% for each, while 'absolute' would show their
 	       current overhead (33.33%).
 
+ui.*::
+	ui.show-headers::
+		This option controls display of column headers (like 'Overhead' and 'Symbol')
+		in 'report' and 'top'. If this option is false, they are hidden.
+		This option is only applied to TUI.
+
 SEE ALSO
 --------
 linkperf:perf[1]
-- 
2.5.0

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

#1326508 — [PATCH 4/8] perf config: Document 'top.children' variable in man page

Explain 'top.children' variable.

Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
---
 tools/perf/Documentation/perf-config.txt | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 72071ab..0154bc9 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -403,6 +403,13 @@ report.*::
 		     0.07%   0.00%  noploop  ld-2.15.so         [.] strcmp
 		     0.03%   0.00%  noploop  [kernel.kallsyms]  [k] timerqueue_del
 
+top.*::
+	top.children::
+		This option means same as report.children. So if it is true,
+		the output of 'top' command will have 'Children' overhead column
+		as well as 'Self' overhead column by default.
+		The default is true.
+
 SEE ALSO
 --------
 linkperf:perf[1]
-- 
2.5.0

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

#1326509 — [PATCH 8/8] perf config: Document 'record.build-id' variable in man page

Explain 'record.build-id' variable.

Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
---
 tools/perf/Documentation/perf-config.txt | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 1d24d94..88bc921 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -429,6 +429,14 @@ kmem.*::
 		This option decides which allocator is to be analyzed if neither
 		'--slab' nor '--page' option is used. Default is 'slab'.
 
+record.*::
+	record.build-id::
+		This option can be 'cache', 'no-cache' or 'skip'.
+		'cache' is to post-process data and save/update the binaries into
+		the build-id cache (in ~/.debug). This is the default.
+		But if this option is 'no-cache', not update the build-id cache.
+		'skip' mean that skip post-processing and do not update the cache.
+
 SEE ALSO
 --------
 linkperf:perf[1]
-- 
2.5.0

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

#1326510 — [PATCH 7/8] perf config: Document 'kmem.default' variable in man page

Explain 'kmem.default' variable.

Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
---
 tools/perf/Documentation/perf-config.txt | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index fb1be76..1d24d94 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -424,6 +424,11 @@ pager.*::
 		When the subcommand is run on stdio, determine whether it uses
 		pager or not based on this value. Default is 'unspecified'.
 
+kmem.*::
+	kmem.default::
+		This option decides which allocator is to be analyzed if neither
+		'--slab' nor '--page' option is used. Default is 'slab'.
+
 SEE ALSO
 --------
 linkperf:perf[1]
-- 
2.5.0

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

#1326511 — [PATCH 5/8] perf config: Document 'man.viewer' variable in man page

Explain 'man.viewer' variable and how to add
new man viewer tools.

Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
---
 tools/perf/Documentation/perf-config.txt | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 0154bc9..a30d225 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -410,6 +410,15 @@ top.*::
 		as well as 'Self' overhead column by default.
 		The default is true.
 
+man.*::
+	man.viewer::
+		This option can assign a tool to view manual pages when 'help'
+		subcommand was invoked. Supported tools are 'man', 'woman'
+		(with emacs client) and 'konqueror'. Default is 'man'.
+
+		New man viewer tool can be also added using 'man.<tool>.cmd'
+		or use different path using 'man.<tool>.path' config option.
+
 SEE ALSO
 --------
 linkperf:perf[1]
-- 
2.5.0

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

#1326512 — [PATCH 2/8] perf config: Document variables for 'call-graph' section in man page

Explain 'call-graph' section and its variables.

'record-mode', 'dump-size', 'print-type', 'order',
'sort-key', 'threshold' and 'print-limit'.

Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
---
 tools/perf/Documentation/perf-config.txt | 67 ++++++++++++++++++++++++++++++++
 1 file changed, 67 insertions(+)

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 4278722..42310ae 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -302,6 +302,73 @@ ui.*::
 		in 'report' and 'top'. If this option is false, they are hidden.
 		This option is only applied to TUI.
 
+call-graph.*::
+	When sub-commands 'top' and 'report' work with -g/—-children
+	there're options in control of call-graph.
+
+	call-graph.record-mode::
+		The record-mode can be 'fp' (frame pointer), 'dwarf' and 'lbr'.
+		The value of 'dwarf' is effective only if perf detect needed library
+		(libunwind or a recent version of libdw).
+		'lbr' only work for cpus that support it.
+
+	call-graph.dump-size::
+		The size of stack to dump in order to do post-unwinding. Default is 8192 (byte).
+		When using dwarf into record-mode, the default size will be used if omitted.
+
+	call-graph.print-type::
+		The print-types can be graph (graph absolute), fractal (graph relative),
+		flat and folded. This option controls a way to show overhead for each callchain
+		entry. Suppose a following example.
+
+                Overhead  Symbols
+                ........  .......
+                  40.00%  foo
+                          |
+                          ---foo
+                             |
+                             |--50.00%--bar
+                             |          main
+                             |
+                              --50.00%--baz
+                                        main
+
+		This output is a 'fractal' format. The 'foo' came from 'bar' and 'baz' exactly
+		half and half so 'fractal' shows 50.00% for each
+		(meaning that it assumes 100% total overhead of 'foo').
+
+		The 'graph' uses absolute overhead value of 'foo' as total so each of
+		'bar' and 'baz' callchain will have 20.00% of overhead.
+		If 'flat' is used, single column and linear exposure of call chains.
+		'folded' mean call chains are displayed in a line, separated by semicolons.
+
+	call-graph.order::
+		This option controls print order of callchains. The default is
+		'callee' which means callee is printed at top and then followed by its
+		caller and so on. The 'caller' prints it in reverse order.
+
+		If this option is not set and report.children or top.children is
+		set to true (or the equivalent command line option is given),
+		the default value of this option is changed to 'caller' for the
+		execution of 'perf report' or 'perf top'. Other commands will
+		still default to 'callee'.
+
+	call-graph.sort-key::
+		The callchains are merged if they contain same information.
+		The sort-key option determines a way to compare the callchains.
+		A value of 'sort-key' can be 'function' or 'address'.
+		The default is 'function'.
+
+	call-graph.threshold::
+		When there're many callchains it'd print tons of lines. So perf omits
+		small callchains under a certain overhead (threshold) and this option
+		control the threshold. Default is 0.5 (%). The overhead is calculated
+		by value depends on call-graph.print-type.
+
+	call-graph.print-limit::
+		This is a maximum number of lines of callchain printed for a single
+		histogram entry. Default is 0 which means no limitation.
+
 SEE ALSO
 --------
 linkperf:perf[1]
-- 
2.5.0

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

#1326513 — [PATCH 3/8] perf config: Document variables for 'report' section in man page

Explain 'report' section's variables.

'percent-limit', 'queue-size' and 'children'.

Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
---
 tools/perf/Documentation/perf-config.txt | 34 ++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 42310ae..72071ab 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -369,6 +369,40 @@ call-graph.*::
 		This is a maximum number of lines of callchain printed for a single
 		histogram entry. Default is 0 which means no limitation.
 
+report.*::
+	report.percent-limit::
+		This one is mostly same as call-graph.threshold but works for
+		histogram entries. Entries have overhead lower than this percentage
+		will not be printed. Default is 0. If percent-limit is 10,
+		entries which have more than 10% of overhead will be printed only.
+
+	report.queue-size::
+		This option is to setup the maximum allocation size of internal
+		event queue for ordering events. Default is 0, meaning no limit.
+
+	report.children::
+		The children means that functions called from another function.
+		If this option is true, perf report cumulates callchains of children
+		and show (accumulated) total overhead as well as self overhead.
+		Please refer to the perf-report manual. The default is true.
+
+	report.group::
+		This option is to show event group information together.
+		If it is 'true', event group view can be enabled by default i.e.
+
+		# group: {ref-cycles,cycles}
+		# ========
+		#
+		# Samples: 7K of event 'anon group { ref-cycles, cycles }'
+		# Event count (approx.): 6876107743
+		#
+		#         Overhead  Command      Shared Object                      Symbol
+		# ................  .......  .................  ..........................
+		#
+		    99.84%  99.76%  noploop  noploop            [.] main
+		     0.07%   0.00%  noploop  ld-2.15.so         [.] strcmp
+		     0.03%   0.00%  noploop  [kernel.kallsyms]  [k] timerqueue_del
+
 SEE ALSO
 --------
 linkperf:perf[1]
-- 
2.5.0

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

#1326515 — [PATCH 6/8] perf config: Document 'pager.<subcommand>' variables in man page

Explain 'pager.<subcommand>' variables.

Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
---
 tools/perf/Documentation/perf-config.txt | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index a30d225..fb1be76 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -419,6 +419,11 @@ man.*::
 		New man viewer tool can be also added using 'man.<tool>.cmd'
 		or use different path using 'man.<tool>.path' config option.
 
+pager.*::
+	pager.<subcommand>::
+		When the subcommand is run on stdio, determine whether it uses
+		pager or not based on this value. Default is 'unspecified'.
+
 SEE ALSO
 --------
 linkperf:perf[1]
-- 
2.5.0

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

#1326896

Em Thu, Feb 04, 2016 at 06:25:05PM +0900, Taeung Song escreveu:
> Document perf config informations each section
> in Documentation/perf-config.txt excluding 'help' section.

Thanks, applied with some changes,

- Arnaldo

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

#1327600

On 02/04/2016 11:49 PM, Arnaldo Carvalho de Melo wrote:
> Em Thu, Feb 04, 2016 at 06:25:05PM +0900, Taeung Song escreveu:
>> Document perf config informations each section
>> in Documentation/perf-config.txt excluding 'help' section.
>
> Thanks, applied with some changes,
>

Thank you !!

Taeung

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

#1327605

Hi, Arnaldo

I'm sorry I missed a thing out.
Lastly default calchain perfcent limit is changed to 0.005%.
This is a default value of call-graph.threshold.

So I resent a modified patch about this.

Thanks,
Taeung

On 02/04/2016 11:49 PM, Arnaldo Carvalho de Melo wrote:
> Em Thu, Feb 04, 2016 at 06:25:05PM +0900, Taeung Song escreveu:
>> Document perf config informations each section
>> in Documentation/perf-config.txt excluding 'help' section.
>
> Thanks, applied with some changes,
>
> - Arnaldo
>

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

#1327644

Hi Taeung,

On Fri, Feb 05, 2016 at 08:03:30PM +0900, Taeung Song wrote:
> Hi, Arnaldo
> 
> I'm sorry I missed a thing out.
> Lastly default calchain perfcent limit is changed to 0.005%.
> This is a default value of call-graph.threshold.

Nope, AFAICS the patch was not merged.  And I decided to change it to
0.05% but it' still not merged..

Thanks,
Namhyung

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

#1327693

Em Fri, Feb 05, 2016 at 10:04:39PM +0900, Namhyung Kim escreveu:
> Hi Taeung,
> 
> On Fri, Feb 05, 2016 at 08:03:30PM +0900, Taeung Song wrote:
> > Hi, Arnaldo
> > 
> > I'm sorry I missed a thing out.
> > Lastly default calchain perfcent limit is changed to 0.005%.
> > This is a default value of call-graph.threshold.
> 
> Nope, AFAICS the patch was not merged.  And I decided to change it to
> 0.05% but it' still not merged..

Yeah, you sent it as an RFC, I'm just giving it a bit more time for
comments to be made.

- Arnaldo

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

#1327701

Hi Arnaldo,

On Fri, Feb 05, 2016 at 10:39:25AM -0300, Arnaldo Carvalho de Melo wrote:
> Em Fri, Feb 05, 2016 at 10:04:39PM +0900, Namhyung Kim escreveu:
> > Hi Taeung,
> > 
> > On Fri, Feb 05, 2016 at 08:03:30PM +0900, Taeung Song wrote:
> > > Hi, Arnaldo
> > > 
> > > I'm sorry I missed a thing out.
> > > Lastly default calchain perfcent limit is changed to 0.005%.
> > > This is a default value of call-graph.threshold.
> > 
> > Nope, AFAICS the patch was not merged.  And I decided to change it to
> > 0.05% but it' still not merged..
> 
> Yeah, you sent it as an RFC, I'm just giving it a bit more time for
> comments to be made.

Yep, I'll wait for other's opinion.

Thanks,
Namhyung

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

#1327709

On 02/05/2016 10:39 PM, Arnaldo Carvalho de Melo wrote:
> Em Fri, Feb 05, 2016 at 10:04:39PM +0900, Namhyung Kim escreveu:
>> Hi Taeung,
>>
>> On Fri, Feb 05, 2016 at 08:03:30PM +0900, Taeung Song wrote:
>>> Hi, Arnaldo
>>>
>>> I'm sorry I missed a thing out.
>>> Lastly default calchain perfcent limit is changed to 0.005%.
>>> This is a default value of call-graph.threshold.
>>
>> Nope, AFAICS the patch was not merged.  And I decided to change it to
>> 0.05% but it' still not merged..
>
> Yeah, you sent it as an RFC, I'm just giving it a bit more time for
> comments to be made.
>

Sorry, I'll wait for the result..

Thanks,
Taeung

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web