xref: /linux/tools/perf/Documentation/perf-config.txt (revision 8a79db5e83a5d52c74e6f3c40d6f312cf899213e)
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
564	trace.tracepoint_beautifiers::
565		Use "libtraceevent" to use that library to augment the tracepoint arguments,
566		"libbeauty", the default, to use the same argument beautifiers used in the
567		strace-like sys_enter+sys_exit lines.
568
569llvm.*::
570	llvm.clang-path::
571		Path to clang. If omit, search it from $PATH.
572
573	llvm.clang-bpf-cmd-template::
574		Cmdline template. Below lines show its default value. Environment
575		variable is used to pass options.
576		"$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
577		"-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE "	\
578		"$CLANG_OPTIONS $PERF_BPF_INC_OPTIONS $KERNEL_INC_OPTIONS " \
579		"-Wno-unused-value -Wno-pointer-sign "		\
580		"-working-directory $WORKING_DIR "		\
581		"-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
582
583	llvm.clang-opt::
584		Options passed to clang.
585
586	llvm.kbuild-dir::
587		kbuild directory. If not set, use /lib/modules/`uname -r`/build.
588		If set to "" deliberately, skip kernel header auto-detector.
589
590	llvm.kbuild-opts::
591		Options passed to 'make' when detecting kernel header options.
592
593	llvm.dump-obj::
594		Enable perf dump BPF object files compiled by LLVM.
595
596	llvm.opts::
597		Options passed to llc.
598
599samples.*::
600
601	samples.context::
602		Define how many ns worth of time to show
603		around samples in perf report sample context browser.
604
605scripts.*::
606
607	Any option defines a script that is added to the scripts menu
608	in the interactive perf browser and whose output is displayed.
609	The name of the option is the name, the value is a script command line.
610	The script gets the same options passed as a full perf script,
611	in particular -i perfdata file, --cpu, --tid
612
613SEE ALSO
614--------
615linkperf:perf[1]
616