Linux Audio

Check our new training course

Loading...
v5.4
  1perf-config(1)
  2==============
  3
  4NAME
  5----
  6perf-config - Get and set variables in a configuration file.
  7
  8SYNOPSIS
  9--------
 10[verse]
 11'perf config' [<file-option>] [section.name[=value] ...]
 12or
 13'perf config' [<file-option>] -l | --list
 14
 15DESCRIPTION
 16-----------
 17You can manage variables in a configuration file with this command.
 18
 19OPTIONS
 20-------
 21
 22-l::
 23--list::
 24	Show current config variables, name and value, for all sections.
 25
 26--user::
 27	For writing and reading options: write to user
 28	'$HOME/.perfconfig' file or read it.
 29
 30--system::
 31	For writing and reading options: write to system-wide
 32	'$(sysconfdir)/perfconfig' or read it.
 33
 34CONFIGURATION FILE
 35------------------
 36
 37The perf configuration file contains many variables to change various
 38aspects of each of its tools, including output, disk usage, etc.
 39The '$HOME/.perfconfig' file is used to store a per-user configuration.
 40The file '$(sysconfdir)/perfconfig' can be used to
 41store a system-wide default configuration.
 42
 43One an disable reading config files by setting the PERF_CONFIG environment
 44variable to /dev/null, or provide an alternate config file by setting that
 45variable.
 46
 47When reading or writing, the values are read from the system and user
 48configuration files by default, and options '--system' and '--user'
 49can be used to tell the command to read from or write to only that location.
 50
 51Syntax
 52~~~~~~
 53
 54The file consist of sections. A section starts with its name
 55surrounded by square brackets and continues till the next section
 56begins. Each variable must be in a section, and have the form
 57'name = value', for example:
 58
 59	[section]
 60		name1 = value1
 61		name2 = value2
 62
 63Section names are case sensitive and can contain any characters except
 64newline (double quote `"` and backslash have to be escaped as `\"` and `\\`,
 65respectively). Section headers can't span multiple lines.
 66
 67Example
 68~~~~~~~
 69
 70Given a $HOME/.perfconfig like this:
 71
 72#
 73# This is the config file, and
 74# a '#' and ';' character indicates a comment
 75#
 76
 77	[colors]
 78		# Color variables
 79		top = red, default
 80		medium = green, default
 81		normal = lightgray, default
 82		selected = white, lightgray
 83		jump_arrows = blue, default
 84		addr = magenta, default
 85		root = white, blue
 86
 87	[tui]
 88		# Defaults if linked with libslang
 89		report = on
 90		annotate = on
 91		top = on
 92
 93	[buildid]
 94		# Default, disable using /dev/null
 95		dir = ~/.debug
 96
 97	[annotate]
 98		# Defaults
 99		hide_src_code = false
100		use_offset = true
101		jump_arrows = true
102		show_nr_jumps = false
103
104	[help]
105		# Format can be man, info, web or html
106		format = man
107		autocorrect = 0
108
109	[ui]
110		show-headers = true
111
112	[call-graph]
113		# fp (framepointer), dwarf
114		record-mode = fp
115		print-type = graph
116		order = caller
117		sort-key = function
118
119	[report]
120		# Defaults
121		sort_order = comm,dso,symbol
122		percent-limit = 0
123		queue-size = 0
124		children = true
125		group = true
 
126
127	[llvm]
128		dump-obj = true
129		clang-opt = -g
130
131You can hide source code of annotate feature setting the config to false with
132
133	% perf config annotate.hide_src_code=true
134
135If you want to add or modify several config items, you can do like
136
137	% perf config ui.show-headers=false kmem.default=slab
138
139To modify the sort order of report functionality in user config file(i.e. `~/.perfconfig`), do
140
141	% perf config --user report sort-order=srcline
142
143To change colors of selected line to other foreground and background colors
144in system config file (i.e. `$(sysconf)/perfconfig`), do
145
146	% perf config --system colors.selected=yellow,green
147
148To query the record mode of call graph, do
149
150	% perf config call-graph.record-mode
151
152If you want to know multiple config key/value pairs, you can do like
153
154	% perf config report.queue-size call-graph.order report.children
155
156To query the config value of sort order of call graph in user config file (i.e. `~/.perfconfig`), do
157
158	% perf config --user call-graph.sort-order
159
160To query the config value of buildid directory in system config file (i.e. `$(sysconf)/perfconfig`), do
161
162	% perf config --system buildid.dir
163
164Variables
165~~~~~~~~~
166
167colors.*::
168	The variables for customizing the colors used in the output for the
169	'report', 'top' and 'annotate' in the TUI. They should specify the
170	foreground and background colors, separated by a comma, for example:
171
172		medium = green, lightgray
173
174	If you want to use the color configured for you terminal, just leave it
175	as 'default', for example:
176
177		medium = default, lightgray
178
179	Available colors:
180	red, yellow, green, cyan, gray, black, blue,
181	white, default, magenta, lightgray
182
183	colors.top::
184		'top' means a overhead percentage which is more than 5%.
185		And values of this variable specify percentage colors.
186		Basic key values are foreground-color 'red' and
187		background-color 'default'.
188	colors.medium::
189		'medium' means a overhead percentage which has more than 0.5%.
190		Default values are 'green' and 'default'.
191	colors.normal::
192		'normal' means the rest of overhead percentages
193		except 'top', 'medium', 'selected'.
194		Default values are 'lightgray' and 'default'.
195	colors.selected::
196		This selects the colors for the current entry in a list of entries
197		from sub-commands (top, report, annotate).
198		Default values are 'black' and 'lightgray'.
199	colors.jump_arrows::
200		Colors for jump arrows on assembly code listings
201		such as 'jns', 'jmp', 'jane', etc.
202		Default values are 'blue', 'default'.
203	colors.addr::
204		This selects colors for addresses from 'annotate'.
205		Default values are 'magenta', 'default'.
206	colors.root::
207		Colors for headers in the output of a sub-commands (top, report).
208		Default values are 'white', 'blue'.
209
210core.*::
211	core.proc-map-timeout::
212		Sets a timeout (in milliseconds) for parsing /proc/<pid>/maps files.
213		Can be overridden by the --proc-map-timeout option on supported
214		subcommands. The default timeout is 500ms.
215
216tui.*, gtk.*::
217	Subcommands that can be configured here are 'top', 'report' and 'annotate'.
218	These values are booleans, for example:
219
220	[tui]
221		top = true
222
223	will make the TUI be the default for the 'top' subcommand. Those will be
224	available if the required libs were detected at tool build time.
225
226buildid.*::
227	buildid.dir::
228		Each executable and shared library in modern distributions comes with a
229		content based identifier that, if available, will be inserted in a
230		'perf.data' file header to, at analysis time find what is needed to do
231		symbol resolution, code annotation, etc.
232
233		The recording tools also stores a hard link or copy in a per-user
234		directory, $HOME/.debug/, of binaries, shared libraries, /proc/kallsyms
235		and /proc/kcore files to be used at analysis time.
236
237		The buildid.dir variable can be used to either change this directory
238		cache location, or to disable it altogether. If you want to disable it,
239		set buildid.dir to /dev/null. The default is $HOME/.debug
240
 
 
 
 
 
 
 
241annotate.*::
242	These options work only for TUI.
243	These are in control of addresses, jump function, source code
244	in lines of assembly code from a specific program.
245
 
 
 
 
 
 
 
 
 
 
 
 
246	annotate.hide_src_code::
247		If a program which is analyzed has source code,
248		this option lets 'annotate' print a list of assembly code with the source code.
249		For example, let's see a part of a program. There're four lines.
250		If this option is 'true', they can be printed
251		without source code from a program as below.
252
253		│        push   %rbp
254		│        mov    %rsp,%rbp
255		│        sub    $0x10,%rsp
256		│        mov    (%rdi),%rdx
257
258		But if this option is 'false', source code of the part
259		can be also printed as below. Default is 'false'.
260
261		│      struct rb_node *rb_next(const struct rb_node *node)
262		│      {
263		│        push   %rbp
264		│        mov    %rsp,%rbp
265		│        sub    $0x10,%rsp
266		│              struct rb_node *parent;
267268		│              if (RB_EMPTY_NODE(node))
269		│        mov    (%rdi),%rdx
270		│              return n;
271
 
 
272        annotate.use_offset::
273		Basing on a first address of a loaded function, offset can be used.
274		Instead of using original addresses of assembly code,
275		addresses subtracted from a base address can be printed.
276		Let's illustrate an example.
277		If a base address is 0XFFFFFFFF81624d50 as below,
278
279		ffffffff81624d50 <load0>
280
281		an address on assembly code has a specific absolute address as below
282
283		ffffffff816250b8:│  mov    0x8(%r14),%rdi
284
285		but if use_offset is 'true', an address subtracted from a base address is printed.
286		Default is true. This option is only applied to TUI.
287
288		             368:│  mov    0x8(%r14),%rdi
289
 
 
290	annotate.jump_arrows::
291		There can be jump instruction among assembly code.
292		Depending on a boolean value of jump_arrows,
293		arrows can be printed or not which represent
294		where do the instruction jump into as below.
295
296		│     ┌──jmp    1333
297		│     │  xchg   %ax,%ax
298		│1330:│  mov    %r15,%r10
299		│1333:└─→cmp    %r15,%r14
300
301		If jump_arrow is 'false', the arrows isn't printed as below.
302		Default is 'false'.
303
304		│      ↓ jmp    1333
305		│        xchg   %ax,%ax
306		│1330:   mov    %r15,%r10
307		│1333:   cmp    %r15,%r14
308
 
 
309        annotate.show_linenr::
310		When showing source code if this option is 'true',
311		line numbers are printed as below.
312
313		│1628         if (type & PERF_SAMPLE_IDENTIFIER) {
314		│     ↓ jne    508
315		│1628                 data->id = *array;
316		│1629                 array++;
317		│1630         }
318
319		However if this option is 'false', they aren't printed as below.
320		Default is 'false'.
321
322		│             if (type & PERF_SAMPLE_IDENTIFIER) {
323		│     ↓ jne    508
324		│                     data->id = *array;
325		│                     array++;
326		│             }
327
 
 
328        annotate.show_nr_jumps::
329		Let's see a part of assembly code.
330
331		│1382:   movb   $0x1,-0x270(%rbp)
332
333		If use this, the number of branches jumping to that address can be printed as below.
334		Default is 'false'.
335
336		│1 1382:   movb   $0x1,-0x270(%rbp)
337
 
 
338        annotate.show_total_period::
339		To compare two records on an instruction base, with this option
340		provided, display total number of samples that belong to a line
341		in assembly code. If this option is 'true', total periods are printed
342		instead of percent values as below.
343
344		  302 │      mov    %eax,%eax
345
346		But if this option is 'false', percent values for overhead are printed i.e.
347		Default is 'false'.
348
349		99.93 │      mov    %eax,%eax
350
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
351	annotate.offset_level::
352		Default is '1', meaning just jump targets will have offsets show right beside
353		the instruction. When set to '2' 'call' instructions will also have its offsets
354		shown, 3 or higher will show offsets for all instructions.
355
 
 
 
 
 
 
 
 
356hist.*::
357	hist.percentage::
358		This option control the way to calculate overhead of filtered entries -
359		that means the value of this option is effective only if there's a
360		filter (by comm, dso or symbol name). Suppose a following example:
361
362		       Overhead  Symbols
363		       ........  .......
364		        33.33%     foo
365		        33.33%     bar
366		        33.33%     baz
367
368	       This is an original overhead and we'll filter out the first 'foo'
369	       entry. The value of 'relative' would increase the overhead of 'bar'
370	       and 'baz' to 50.00% for each, while 'absolute' would show their
371	       current overhead (33.33%).
372
373ui.*::
374	ui.show-headers::
375		This option controls display of column headers (like 'Overhead' and 'Symbol')
376		in 'report' and 'top'. If this option is false, they are hidden.
377		This option is only applied to TUI.
378
379call-graph.*::
380	When sub-commands 'top' and 'report' work with -g/—-children
381	there're options in control of call-graph.
382
383	call-graph.record-mode::
384		The record-mode can be 'fp' (frame pointer), 'dwarf' and 'lbr'.
385		The value of 'dwarf' is effective only if perf detect needed library
386		(libunwind or a recent version of libdw).
387		'lbr' only work for cpus that support it.
 
 
388
389	call-graph.dump-size::
390		The size of stack to dump in order to do post-unwinding. Default is 8192 (byte).
391		When using dwarf into record-mode, the default size will be used if omitted.
392
393	call-graph.print-type::
394		The print-types can be graph (graph absolute), fractal (graph relative),
395		flat and folded. This option controls a way to show overhead for each callchain
396		entry. Suppose a following example.
397
398                Overhead  Symbols
399                ........  .......
400                  40.00%  foo
401                          |
402                          ---foo
403                             |
404                             |--50.00%--bar
405                             |          main
406                             |
407                              --50.00%--baz
408                                        main
409
410		This output is a 'fractal' format. The 'foo' came from 'bar' and 'baz' exactly
411		half and half so 'fractal' shows 50.00% for each
412		(meaning that it assumes 100% total overhead of 'foo').
413
414		The 'graph' uses absolute overhead value of 'foo' as total so each of
415		'bar' and 'baz' callchain will have 20.00% of overhead.
416		If 'flat' is used, single column and linear exposure of call chains.
417		'folded' mean call chains are displayed in a line, separated by semicolons.
418
419	call-graph.order::
420		This option controls print order of callchains. The default is
421		'callee' which means callee is printed at top and then followed by its
422		caller and so on. The 'caller' prints it in reverse order.
423
424		If this option is not set and report.children or top.children is
425		set to true (or the equivalent command line option is given),
426		the default value of this option is changed to 'caller' for the
427		execution of 'perf report' or 'perf top'. Other commands will
428		still default to 'callee'.
429
430	call-graph.sort-key::
431		The callchains are merged if they contain same information.
432		The sort-key option determines a way to compare the callchains.
433		A value of 'sort-key' can be 'function' or 'address'.
434		The default is 'function'.
435
436	call-graph.threshold::
437		When there're many callchains it'd print tons of lines. So perf omits
438		small callchains under a certain overhead (threshold) and this option
439		control the threshold. Default is 0.5 (%). The overhead is calculated
440		by value depends on call-graph.print-type.
441
442	call-graph.print-limit::
443		This is a maximum number of lines of callchain printed for a single
444		histogram entry. Default is 0 which means no limitation.
445
446report.*::
447	report.sort_order::
448		Allows changing the default sort order from "comm,dso,symbol" to
449		some other default, for instance "sym,dso" may be more fitting for
450		kernel developers.
451	report.percent-limit::
452		This one is mostly the same as call-graph.threshold but works for
453		histogram entries. Entries having an overhead lower than this
454		percentage will not be printed. Default is '0'. If percent-limit
455		is '10', only entries which have more than 10% of overhead will be
456		printed.
457
458	report.queue-size::
459		This option sets up the maximum allocation size of the internal
460		event queue for ordering events. Default is 0, meaning no limit.
461
462	report.children::
463		'Children' means functions called from another function.
464		If this option is true, 'perf report' cumulates callchains of children
465		and show (accumulated) total overhead as well as 'Self' overhead.
466		Please refer to the 'perf report' manual. The default is 'true'.
467
468	report.group::
469		This option is to show event group information together.
470		Example output with this turned on, notice that there is one column
471		per event in the group, ref-cycles and cycles:
472
473		# group: {ref-cycles,cycles}
474		# ========
475		#
476		# Samples: 7K of event 'anon group { ref-cycles, cycles }'
477		# Event count (approx.): 6876107743
478		#
479		#         Overhead  Command      Shared Object               Symbol
480		# ................  .......  .................  ...................
481		#
482		    99.84%  99.76%  noploop  noploop            [.] main
483		     0.07%   0.00%  noploop  ld-2.15.so         [.] strcmp
484		     0.03%   0.00%  noploop  [kernel.kallsyms]  [k] timerqueue_del
485
 
 
 
 
486top.*::
487	top.children::
488		Same as 'report.children'. So if it is enabled, the output of 'top'
489		command will have 'Children' overhead column as well as 'Self' overhead
490		column by default.
491		The default is 'true'.
492
 
 
 
 
 
 
493man.*::
494	man.viewer::
495		This option can assign a tool to view manual pages when 'help'
496		subcommand was invoked. Supported tools are 'man', 'woman'
497		(with emacs client) and 'konqueror'. Default is 'man'.
498
499		New man viewer tool can be also added using 'man.<tool>.cmd'
500		or use different path using 'man.<tool>.path' config option.
501
502pager.*::
503	pager.<subcommand>::
504		When the subcommand is run on stdio, determine whether it uses
505		pager or not based on this value. Default is 'unspecified'.
506
507kmem.*::
508	kmem.default::
509		This option decides which allocator is to be analyzed if neither
510		'--slab' nor '--page' option is used. Default is 'slab'.
511
512record.*::
513	record.build-id::
514		This option can be 'cache', 'no-cache' or 'skip'.
515		'cache' is to post-process data and save/update the binaries into
516		the build-id cache (in ~/.debug). This is the default.
517		But if this option is 'no-cache', it will not update the build-id cache.
518		'skip' skips post-processing and does not update the cache.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
519
520diff.*::
521	diff.order::
522		This option sets the number of columns to sort the result.
523		The default is 0, which means sorting by baseline.
524		Setting it to 1 will sort the result by delta (or other
525		compute method selected).
526
527	diff.compute::
528		This options sets the method for computing the diff result.
529		Possible values are 'delta', 'delta-abs', 'ratio' and
530		'wdiff'.  Default is 'delta'.
531
532trace.*::
533	trace.add_events::
534		Allows adding a set of events to add to the ones specified
535		by the user, or use as a default one if none was specified.
536		The initial use case is to add augmented_raw_syscalls.o to
537		activate the 'perf trace' logic that looks for syscall
538		pointer contents after the normal tracepoint payload.
539
540	trace.args_alignment::
541		Number of columns to align the argument list, default is 70,
542		use 40 for the strace default, zero to no alignment.
543
544	trace.no_inherit::
545		Do not follow children threads.
546
547	trace.show_arg_names::
548		Should syscall argument names be printed? If not then trace.show_zeros
549		will be set.
550
551	trace.show_duration::
552		Show syscall duration.
553
554	trace.show_prefix::
555		If set to 'yes' will show common string prefixes in tables. The default
556		is to remove the common prefix in things like "MAP_SHARED", showing just "SHARED".
557
558	trace.show_timestamp::
559		Show syscall start timestamp.
560
561	trace.show_zeros::
562		Do not suppress syscall arguments that are equal to zero.
563
564llvm.*::
565	llvm.clang-path::
566		Path to clang. If omit, search it from $PATH.
567
568	llvm.clang-bpf-cmd-template::
569		Cmdline template. Below lines show its default value. Environment
570		variable is used to pass options.
571		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
572		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
573		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
574		"-Wno-unused-value -Wno-pointer-sign "		\
575		"-working-directory $WORKING_DIR "		\
576		"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
577
578	llvm.clang-opt::
579		Options passed to clang.
580
581	llvm.kbuild-dir::
582		kbuild directory. If not set, use /lib/modules/`uname -r`/build.
583		If set to "" deliberately, skip kernel header auto-detector.
584
585	llvm.kbuild-opts::
586		Options passed to 'make' when detecting kernel header options.
587
588	llvm.dump-obj::
589		Enable perf dump BPF object files compiled by LLVM.
590
591	llvm.opts::
592		Options passed to llc.
593
594samples.*::
595
596	samples.context::
597		Define how many ns worth of time to show
598		around samples in perf report sample context browser.
599
600scripts.*::
601
602	Any option defines a script that is added to the scripts menu
603	in the interactive perf browser and whose output is displayed.
604	The name of the option is the name, the value is a script command line.
605	The script gets the same options passed as a full perf script,
606	in particular -i perfdata file, --cpu, --tid
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
607
608SEE ALSO
609--------
610linkperf:perf[1]
v6.8
  1perf-config(1)
  2==============
  3
  4NAME
  5----
  6perf-config - Get and set variables in a configuration file.
  7
  8SYNOPSIS
  9--------
 10[verse]
 11'perf config' [<file-option>] [section.name[=value] ...]
 12or
 13'perf config' [<file-option>] -l | --list
 14
 15DESCRIPTION
 16-----------
 17You can manage variables in a configuration file with this command.
 18
 19OPTIONS
 20-------
 21
 22-l::
 23--list::
 24	Show current config variables, name and value, for all sections.
 25
 26--user::
 27	For writing and reading options: write to user
 28	'$HOME/.perfconfig' file or read it.
 29
 30--system::
 31	For writing and reading options: write to system-wide
 32	'$(sysconfdir)/perfconfig' or read it.
 33
 34CONFIGURATION FILE
 35------------------
 36
 37The perf configuration file contains many variables to change various
 38aspects of each of its tools, including output, disk usage, etc.
 39The '$HOME/.perfconfig' file is used to store a per-user configuration.
 40The file '$(sysconfdir)/perfconfig' can be used to
 41store a system-wide default configuration.
 42
 43One an disable reading config files by setting the PERF_CONFIG environment
 44variable to /dev/null, or provide an alternate config file by setting that
 45variable.
 46
 47When reading or writing, the values are read from the system and user
 48configuration files by default, and options '--system' and '--user'
 49can be used to tell the command to read from or write to only that location.
 50
 51Syntax
 52~~~~~~
 53
 54The file consist of sections. A section starts with its name
 55surrounded by square brackets and continues till the next section
 56begins. Each variable must be in a section, and have the form
 57'name = value', for example:
 58
 59	[section]
 60		name1 = value1
 61		name2 = value2
 62
 63Section names are case sensitive and can contain any characters except
 64newline (double quote `"` and backslash have to be escaped as `\"` and `\\`,
 65respectively). Section headers can't span multiple lines.
 66
 67Example
 68~~~~~~~
 69
 70Given a $HOME/.perfconfig like this:
 71
 72#
 73# This is the config file, and
 74# a '#' and ';' character indicates a comment
 75#
 76
 77	[colors]
 78		# Color variables
 79		top = red, default
 80		medium = green, default
 81		normal = lightgray, default
 82		selected = white, lightgray
 83		jump_arrows = blue, default
 84		addr = magenta, default
 85		root = white, blue
 86
 87	[tui]
 88		# Defaults if linked with libslang
 89		report = on
 90		annotate = on
 91		top = on
 92
 93	[buildid]
 94		# Default, disable using /dev/null
 95		dir = ~/.debug
 96
 97	[annotate]
 98		# Defaults
 99		hide_src_code = false
100		use_offset = true
101		jump_arrows = true
102		show_nr_jumps = false
103
104	[help]
105		# Format can be man, info, web or html
106		format = man
107		autocorrect = 0
108
109	[ui]
110		show-headers = true
111
112	[call-graph]
113		# fp (framepointer), dwarf
114		record-mode = fp
115		print-type = graph
116		order = caller
117		sort-key = function
118
119	[report]
120		# Defaults
121		sort_order = comm,dso,symbol
122		percent-limit = 0
123		queue-size = 0
124		children = true
125		group = true
126		skip-empty = true
127
 
 
 
128
129You can hide source code of annotate feature setting the config to false with
130
131	% perf config annotate.hide_src_code=true
132
133If you want to add or modify several config items, you can do like
134
135	% perf config ui.show-headers=false kmem.default=slab
136
137To modify the sort order of report functionality in user config file(i.e. `~/.perfconfig`), do
138
139	% perf config --user report.sort-order=srcline
140
141To change colors of selected line to other foreground and background colors
142in system config file (i.e. `$(sysconf)/perfconfig`), do
143
144	% perf config --system colors.selected=yellow,green
145
146To query the record mode of call graph, do
147
148	% perf config call-graph.record-mode
149
150If you want to know multiple config key/value pairs, you can do like
151
152	% perf config report.queue-size call-graph.order report.children
153
154To query the config value of sort order of call graph in user config file (i.e. `~/.perfconfig`), do
155
156	% perf config --user call-graph.sort-order
157
158To query the config value of buildid directory in system config file (i.e. `$(sysconf)/perfconfig`), do
159
160	% perf config --system buildid.dir
161
162Variables
163~~~~~~~~~
164
165colors.*::
166	The variables for customizing the colors used in the output for the
167	'report', 'top' and 'annotate' in the TUI. They should specify the
168	foreground and background colors, separated by a comma, for example:
169
170		medium = green, lightgray
171
172	If you want to use the color configured for you terminal, just leave it
173	as 'default', for example:
174
175		medium = default, lightgray
176
177	Available colors:
178	red, yellow, green, cyan, gray, black, blue,
179	white, default, magenta, lightgray
180
181	colors.top::
182		'top' means a overhead percentage which is more than 5%.
183		And values of this variable specify percentage colors.
184		Basic key values are foreground-color 'red' and
185		background-color 'default'.
186	colors.medium::
187		'medium' means a overhead percentage which has more than 0.5%.
188		Default values are 'green' and 'default'.
189	colors.normal::
190		'normal' means the rest of overhead percentages
191		except 'top', 'medium', 'selected'.
192		Default values are 'lightgray' and 'default'.
193	colors.selected::
194		This selects the colors for the current entry in a list of entries
195		from sub-commands (top, report, annotate).
196		Default values are 'black' and 'lightgray'.
197	colors.jump_arrows::
198		Colors for jump arrows on assembly code listings
199		such as 'jns', 'jmp', 'jane', etc.
200		Default values are 'blue', 'default'.
201	colors.addr::
202		This selects colors for addresses from 'annotate'.
203		Default values are 'magenta', 'default'.
204	colors.root::
205		Colors for headers in the output of a sub-commands (top, report).
206		Default values are 'white', 'blue'.
207
208core.*::
209	core.proc-map-timeout::
210		Sets a timeout (in milliseconds) for parsing /proc/<pid>/maps files.
211		Can be overridden by the --proc-map-timeout option on supported
212		subcommands. The default timeout is 500ms.
213
214tui.*, gtk.*::
215	Subcommands that can be configured here are 'top', 'report' and 'annotate'.
216	These values are booleans, for example:
217
218	[tui]
219		top = true
220
221	will make the TUI be the default for the 'top' subcommand. Those will be
222	available if the required libs were detected at tool build time.
223
224buildid.*::
225	buildid.dir::
226		Each executable and shared library in modern distributions comes with a
227		content based identifier that, if available, will be inserted in a
228		'perf.data' file header to, at analysis time find what is needed to do
229		symbol resolution, code annotation, etc.
230
231		The recording tools also stores a hard link or copy in a per-user
232		directory, $HOME/.debug/, of binaries, shared libraries, /proc/kallsyms
233		and /proc/kcore files to be used at analysis time.
234
235		The buildid.dir variable can be used to either change this directory
236		cache location, or to disable it altogether. If you want to disable it,
237		set buildid.dir to /dev/null. The default is $HOME/.debug
238
239buildid-cache.*::
240	buildid-cache.debuginfod=URLs
241		Specify debuginfod URLs to be used when retrieving perf.data binaries,
242		it follows the same syntax as the DEBUGINFOD_URLS variable, like:
243
244		  buildid-cache.debuginfod=http://192.168.122.174:8002
245
246annotate.*::
 
247	These are in control of addresses, jump function, source code
248	in lines of assembly code from a specific program.
249
250	annotate.addr2line::
251		addr2line binary to use for file names and line numbers.
252
253	annotate.objdump::
254		objdump binary to use for disassembly and annotations,
255		including in the 'perf test' command.
256
257	annotate.disassembler_style::
258		Use this to change the default disassembler style to some other value
259		supported by binutils, such as "intel", see the '-M' option help in the
260		'objdump' man page.
261
262	annotate.hide_src_code::
263		If a program which is analyzed has source code,
264		this option lets 'annotate' print a list of assembly code with the source code.
265		For example, let's see a part of a program. There're four lines.
266		If this option is 'true', they can be printed
267		without source code from a program as below.
268
269		│        push   %rbp
270		│        mov    %rsp,%rbp
271		│        sub    $0x10,%rsp
272		│        mov    (%rdi),%rdx
273
274		But if this option is 'false', source code of the part
275		can be also printed as below. Default is 'false'.
276
277		│      struct rb_node *rb_next(const struct rb_node *node)
278		│      {
279		│        push   %rbp
280		│        mov    %rsp,%rbp
281		│        sub    $0x10,%rsp
282		│              struct rb_node *parent;
283284		│              if (RB_EMPTY_NODE(node))
285		│        mov    (%rdi),%rdx
286		│              return n;
287
288		This option works with tui, stdio2 browsers.
289
290        annotate.use_offset::
291		Basing on a first address of a loaded function, offset can be used.
292		Instead of using original addresses of assembly code,
293		addresses subtracted from a base address can be printed.
294		Let's illustrate an example.
295		If a base address is 0XFFFFFFFF81624d50 as below,
296
297		ffffffff81624d50 <load0>
298
299		an address on assembly code has a specific absolute address as below
300
301		ffffffff816250b8:│  mov    0x8(%r14),%rdi
302
303		but if use_offset is 'true', an address subtracted from a base address is printed.
304		Default is true. This option is only applied to TUI.
305
306		             368:│  mov    0x8(%r14),%rdi
307
308		This option works with tui, stdio2 browsers.
309
310	annotate.jump_arrows::
311		There can be jump instruction among assembly code.
312		Depending on a boolean value of jump_arrows,
313		arrows can be printed or not which represent
314		where do the instruction jump into as below.
315
316		│     ┌──jmp    1333
317		│     │  xchg   %ax,%ax
318		│1330:│  mov    %r15,%r10
319		│1333:└─→cmp    %r15,%r14
320
321		If jump_arrow is 'false', the arrows isn't printed as below.
322		Default is 'false'.
323
324		│      ↓ jmp    1333
325		│        xchg   %ax,%ax
326		│1330:   mov    %r15,%r10
327		│1333:   cmp    %r15,%r14
328
329		This option works with tui browser.
330
331        annotate.show_linenr::
332		When showing source code if this option is 'true',
333		line numbers are printed as below.
334
335		│1628         if (type & PERF_SAMPLE_IDENTIFIER) {
336		│     ↓ jne    508
337		│1628                 data->id = *array;
338		│1629                 array++;
339		│1630         }
340
341		However if this option is 'false', they aren't printed as below.
342		Default is 'false'.
343
344		│             if (type & PERF_SAMPLE_IDENTIFIER) {
345		│     ↓ jne    508
346		│                     data->id = *array;
347		│                     array++;
348		│             }
349
350		This option works with tui, stdio2 browsers.
351
352        annotate.show_nr_jumps::
353		Let's see a part of assembly code.
354
355		│1382:   movb   $0x1,-0x270(%rbp)
356
357		If use this, the number of branches jumping to that address can be printed as below.
358		Default is 'false'.
359
360		│1 1382:   movb   $0x1,-0x270(%rbp)
361
362		This option works with tui, stdio2 browsers.
363
364        annotate.show_total_period::
365		To compare two records on an instruction base, with this option
366		provided, display total number of samples that belong to a line
367		in assembly code. If this option is 'true', total periods are printed
368		instead of percent values as below.
369
370		  302 │      mov    %eax,%eax
371
372		But if this option is 'false', percent values for overhead are printed i.e.
373		Default is 'false'.
374
375		99.93 │      mov    %eax,%eax
376
377		This option works with tui, stdio2, stdio browsers.
378
379	annotate.show_nr_samples::
380		By default perf annotate shows percentage of samples. This option
381		can be used to print absolute number of samples. Ex, when set as
382		false:
383
384		Percent│
385		 74.03 │      mov    %fs:0x28,%rax
386
387		When set as true:
388
389		Samples│
390		     6 │      mov    %fs:0x28,%rax
391
392		This option works with tui, stdio2, stdio browsers.
393
394	annotate.offset_level::
395		Default is '1', meaning just jump targets will have offsets show right beside
396		the instruction. When set to '2' 'call' instructions will also have its offsets
397		shown, 3 or higher will show offsets for all instructions.
398
399		This option works with tui, stdio2 browsers.
400
401	annotate.demangle::
402		Demangle symbol names to human readable form. Default is 'true'.
403
404	annotate.demangle_kernel::
405		Demangle kernel symbol names to human readable form. Default is 'true'.
406
407hist.*::
408	hist.percentage::
409		This option control the way to calculate overhead of filtered entries -
410		that means the value of this option is effective only if there's a
411		filter (by comm, dso or symbol name). Suppose a following example:
412
413		       Overhead  Symbols
414		       ........  .......
415		        33.33%     foo
416		        33.33%     bar
417		        33.33%     baz
418
419	       This is an original overhead and we'll filter out the first 'foo'
420	       entry. The value of 'relative' would increase the overhead of 'bar'
421	       and 'baz' to 50.00% for each, while 'absolute' would show their
422	       current overhead (33.33%).
423
424ui.*::
425	ui.show-headers::
426		This option controls display of column headers (like 'Overhead' and 'Symbol')
427		in 'report' and 'top'. If this option is false, they are hidden.
428		This option is only applied to TUI.
429
430call-graph.*::
431	The following controls the handling of call-graphs (obtained via the
432	-g/--call-graph options).
433
434	call-graph.record-mode::
435		The mode for user space can be 'fp' (frame pointer), 'dwarf'
436		and 'lbr'.  The value 'dwarf' is effective only if libunwind
437		(or a recent version of libdw) is present on the system;
438		the value 'lbr' only works for certain cpus. The method for
439		kernel space is controlled not by this option but by the
440		kernel config (CONFIG_UNWINDER_*).
441
442	call-graph.dump-size::
443		The size of stack to dump in order to do post-unwinding. Default is 8192 (byte).
444		When using dwarf into record-mode, the default size will be used if omitted.
445
446	call-graph.print-type::
447		The print-types can be graph (graph absolute), fractal (graph relative),
448		flat and folded. This option controls a way to show overhead for each callchain
449		entry. Suppose a following example.
450
451                Overhead  Symbols
452                ........  .......
453                  40.00%  foo
454                          |
455                          ---foo
456                             |
457                             |--50.00%--bar
458                             |          main
459                             |
460                              --50.00%--baz
461                                        main
462
463		This output is a 'fractal' format. The 'foo' came from 'bar' and 'baz' exactly
464		half and half so 'fractal' shows 50.00% for each
465		(meaning that it assumes 100% total overhead of 'foo').
466
467		The 'graph' uses absolute overhead value of 'foo' as total so each of
468		'bar' and 'baz' callchain will have 20.00% of overhead.
469		If 'flat' is used, single column and linear exposure of call chains.
470		'folded' mean call chains are displayed in a line, separated by semicolons.
471
472	call-graph.order::
473		This option controls print order of callchains. The default is
474		'callee' which means callee is printed at top and then followed by its
475		caller and so on. The 'caller' prints it in reverse order.
476
477		If this option is not set and report.children or top.children is
478		set to true (or the equivalent command line option is given),
479		the default value of this option is changed to 'caller' for the
480		execution of 'perf report' or 'perf top'. Other commands will
481		still default to 'callee'.
482
483	call-graph.sort-key::
484		The callchains are merged if they contain same information.
485		The sort-key option determines a way to compare the callchains.
486		A value of 'sort-key' can be 'function' or 'address'.
487		The default is 'function'.
488
489	call-graph.threshold::
490		When there're many callchains it'd print tons of lines. So perf omits
491		small callchains under a certain overhead (threshold) and this option
492		control the threshold. Default is 0.5 (%). The overhead is calculated
493		by value depends on call-graph.print-type.
494
495	call-graph.print-limit::
496		This is a maximum number of lines of callchain printed for a single
497		histogram entry. Default is 0 which means no limitation.
498
499report.*::
500	report.sort_order::
501		Allows changing the default sort order from "comm,dso,symbol" to
502		some other default, for instance "sym,dso" may be more fitting for
503		kernel developers.
504	report.percent-limit::
505		This one is mostly the same as call-graph.threshold but works for
506		histogram entries. Entries having an overhead lower than this
507		percentage will not be printed. Default is '0'. If percent-limit
508		is '10', only entries which have more than 10% of overhead will be
509		printed.
510
511	report.queue-size::
512		This option sets up the maximum allocation size of the internal
513		event queue for ordering events. Default is 0, meaning no limit.
514
515	report.children::
516		'Children' means functions called from another function.
517		If this option is true, 'perf report' cumulates callchains of children
518		and show (accumulated) total overhead as well as 'Self' overhead.
519		Please refer to the 'perf report' manual. The default is 'true'.
520
521	report.group::
522		This option is to show event group information together.
523		Example output with this turned on, notice that there is one column
524		per event in the group, ref-cycles and cycles:
525
526		# group: {ref-cycles,cycles}
527		# ========
528		#
529		# Samples: 7K of event 'anon group { ref-cycles, cycles }'
530		# Event count (approx.): 6876107743
531		#
532		#         Overhead  Command      Shared Object               Symbol
533		# ................  .......  .................  ...................
534		#
535		    99.84%  99.76%  noploop  noploop            [.] main
536		     0.07%   0.00%  noploop  ld-2.15.so         [.] strcmp
537		     0.03%   0.00%  noploop  [kernel.kallsyms]  [k] timerqueue_del
538
539	report.skip-empty::
540		This option can change default stat behavior with empty results.
541		If it's set true, 'perf report --stat' will not show 0 stats.
542
543top.*::
544	top.children::
545		Same as 'report.children'. So if it is enabled, the output of 'top'
546		command will have 'Children' overhead column as well as 'Self' overhead
547		column by default.
548		The default is 'true'.
549
550	top.call-graph::
551		This is identical to 'call-graph.record-mode', except it is
552		applicable only for 'top' subcommand. This option ONLY setup
553		the unwind method. To enable 'perf top' to actually use it,
554		the command line option -g must be specified.
555
556man.*::
557	man.viewer::
558		This option can assign a tool to view manual pages when 'help'
559		subcommand was invoked. Supported tools are 'man', 'woman'
560		(with emacs client) and 'konqueror'. Default is 'man'.
561
562		New man viewer tool can be also added using 'man.<tool>.cmd'
563		or use different path using 'man.<tool>.path' config option.
564
565pager.*::
566	pager.<subcommand>::
567		When the subcommand is run on stdio, determine whether it uses
568		pager or not based on this value. Default is 'unspecified'.
569
570kmem.*::
571	kmem.default::
572		This option decides which allocator is to be analyzed if neither
573		'--slab' nor '--page' option is used. Default is 'slab'.
574
575record.*::
576	record.build-id::
577		This option can be 'cache', 'no-cache', 'skip' or 'mmap'.
578		'cache' is to post-process data and save/update the binaries into
579		the build-id cache (in ~/.debug). This is the default.
580		But if this option is 'no-cache', it will not update the build-id cache.
581		'skip' skips post-processing and does not update the cache.
582		'mmap' skips post-processing and reads build-ids from MMAP events.
583
584	record.call-graph::
585		This is identical to 'call-graph.record-mode', except it is
586		applicable only for 'record' subcommand. This option ONLY setup
587		the unwind method. To enable 'perf record' to actually use it,
588		the command line option -g must be specified.
589
590	record.aio::
591		Use 'n' control blocks in asynchronous (Posix AIO) trace writing
592		mode ('n' default: 1, max: 4).
593
594	record.debuginfod::
595		Specify debuginfod URL to be used when cacheing perf.data binaries,
596		it follows the same syntax as the DEBUGINFOD_URLS variable, like:
597
598		  http://192.168.122.174:8002
599
600		If the URLs is 'system', the value of DEBUGINFOD_URLS system environment
601		variable is used.
602
603diff.*::
604	diff.order::
605		This option sets the number of columns to sort the result.
606		The default is 0, which means sorting by baseline.
607		Setting it to 1 will sort the result by delta (or other
608		compute method selected).
609
610	diff.compute::
611		This options sets the method for computing the diff result.
612		Possible values are 'delta', 'delta-abs', 'ratio' and
613		'wdiff'.  Default is 'delta'.
614
615trace.*::
616	trace.add_events::
617		Allows adding a set of events to add to the ones specified
618		by the user, or use as a default one if none was specified.
619		The initial use case is to add augmented_raw_syscalls.o to
620		activate the 'perf trace' logic that looks for syscall
621		pointer contents after the normal tracepoint payload.
622
623	trace.args_alignment::
624		Number of columns to align the argument list, default is 70,
625		use 40 for the strace default, zero to no alignment.
626
627	trace.no_inherit::
628		Do not follow children threads.
629
630	trace.show_arg_names::
631		Should syscall argument names be printed? If not then trace.show_zeros
632		will be set.
633
634	trace.show_duration::
635		Show syscall duration.
636
637	trace.show_prefix::
638		If set to 'yes' will show common string prefixes in tables. The default
639		is to remove the common prefix in things like "MAP_SHARED", showing just "SHARED".
640
641	trace.show_timestamp::
642		Show syscall start timestamp.
643
644	trace.show_zeros::
645		Do not suppress syscall arguments that are equal to zero.
646
647	trace.tracepoint_beautifiers::
648		Use "libtraceevent" to use that library to augment the tracepoint arguments,
649		"libbeauty", the default, to use the same argument beautifiers used in the
650		strace-like sys_enter+sys_exit lines.
651
652ftrace.*::
653	ftrace.tracer::
654		Can be used to select the default tracer when neither -G nor
655		-F option is not specified. Possible values are 'function' and
656		'function_graph'.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
657
658samples.*::
659
660	samples.context::
661		Define how many ns worth of time to show
662		around samples in perf report sample context browser.
663
664scripts.*::
665
666	Any option defines a script that is added to the scripts menu
667	in the interactive perf browser and whose output is displayed.
668	The name of the option is the name, the value is a script command line.
669	The script gets the same options passed as a full perf script,
670	in particular -i perfdata file, --cpu, --tid
671
672convert.*::
673
674	convert.queue-size::
675		Limit the size of ordered_events queue, so we could control
676		allocation size of perf data files without proper finished
677		round events.
678stat.*::
679
680	stat.big-num::
681		(boolean) Change the default for "--big-num". To make
682		"--no-big-num" the default, set "stat.big-num=false".
683
684intel-pt.*::
685
686	intel-pt.cache-divisor::
687
688	intel-pt.mispred-all::
689		If set, Intel PT decoder will set the mispred flag on all
690		branches.
691
692	intel-pt.max-loops::
693		If set and non-zero, the maximum number of unconditional
694		branches decoded without consuming any trace packets. If
695		the maximum is exceeded there will be a "Never-ending loop"
696		error. The default is 100000.
697
698auxtrace.*::
699
700	auxtrace.dumpdir::
701		s390 only. The directory to save the auxiliary trace buffer
702		can be changed using this option. Ex, auxtrace.dumpdir=/tmp.
703		If the directory does not exist or has the wrong file type,
704		the current directory is used.
705
706itrace.*::
707
708	debug-log-buffer-size::
709		Log size in bytes to output when using the option --itrace=d+e
710		Refer 'itrace' option of linkperf:perf-script[1] or
711		linkperf:perf-report[1]. The default is 16384.
712
713daemon.*::
714
715	daemon.base::
716		Base path for daemon data. All sessions data are stored under
717		this path.
718
719session-<NAME>.*::
720
721	session-<NAME>.run::
722
723		Defines new record session for daemon. The value is record's
724		command line without the 'record' keyword.
725
726SEE ALSO
727--------
728linkperf:perf[1]