1 perf-config(1) 1 perf-config(1)
2 ============== 2 ==============
3 3
4 NAME 4 NAME
5 ---- 5 ----
6 perf-config - Get and set variables in a confi 6 perf-config - Get and set variables in a configuration file.
7 7
8 SYNOPSIS 8 SYNOPSIS
9 -------- 9 --------
10 [verse] 10 [verse]
11 'perf config' [<file-option>] [section.name[=v 11 'perf config' [<file-option>] [section.name[=value] ...]
12 or 12 or
13 'perf config' [<file-option>] -l | --list 13 'perf config' [<file-option>] -l | --list
14 14
15 DESCRIPTION 15 DESCRIPTION
16 ----------- 16 -----------
17 You can manage variables in a configuration fi 17 You can manage variables in a configuration file with this command.
18 18
19 OPTIONS 19 OPTIONS
20 ------- 20 -------
21 21
22 -l:: 22 -l::
23 --list:: 23 --list::
24 Show current config variables, name an 24 Show current config variables, name and value, for all sections.
25 25
26 --user:: 26 --user::
27 For writing and reading options: write 27 For writing and reading options: write to user
28 '$HOME/.perfconfig' file or read it. 28 '$HOME/.perfconfig' file or read it.
29 29
30 --system:: 30 --system::
31 For writing and reading options: write 31 For writing and reading options: write to system-wide
32 '$(sysconfdir)/perfconfig' or read it. 32 '$(sysconfdir)/perfconfig' or read it.
33 33
34 CONFIGURATION FILE 34 CONFIGURATION FILE
35 ------------------ 35 ------------------
36 36
37 The perf configuration file contains many vari 37 The perf configuration file contains many variables to change various
38 aspects of each of its tools, including output 38 aspects of each of its tools, including output, disk usage, etc.
39 The '$HOME/.perfconfig' file is used to store 39 The '$HOME/.perfconfig' file is used to store a per-user configuration.
40 The file '$(sysconfdir)/perfconfig' can be use 40 The file '$(sysconfdir)/perfconfig' can be used to
41 store a system-wide default configuration. 41 store a system-wide default configuration.
42 42
43 One an disable reading config files by setting <<
44 variable to /dev/null, or provide an alternate <<
45 variable. <<
46 <<
47 When reading or writing, the values are read f 43 When reading or writing, the values are read from the system and user
48 configuration files by default, and options '- 44 configuration files by default, and options '--system' and '--user'
49 can be used to tell the command to read from o 45 can be used to tell the command to read from or write to only that location.
50 46
51 Syntax 47 Syntax
52 ~~~~~~ 48 ~~~~~~
53 49
54 The file consist of sections. A section starts 50 The file consist of sections. A section starts with its name
55 surrounded by square brackets and continues ti 51 surrounded by square brackets and continues till the next section
56 begins. Each variable must be in a section, an 52 begins. Each variable must be in a section, and have the form
57 'name = value', for example: 53 'name = value', for example:
58 54
59 [section] 55 [section]
60 name1 = value1 56 name1 = value1
61 name2 = value2 57 name2 = value2
62 58
63 Section names are case sensitive and can conta 59 Section names are case sensitive and can contain any characters except
64 newline (double quote `"` and backslash have t 60 newline (double quote `"` and backslash have to be escaped as `\"` and `\\`,
65 respectively). Section headers can't span mult 61 respectively). Section headers can't span multiple lines.
66 62
67 Example 63 Example
68 ~~~~~~~ 64 ~~~~~~~
69 65
70 Given a $HOME/.perfconfig like this: 66 Given a $HOME/.perfconfig like this:
71 67
72 # 68 #
73 # This is the config file, and 69 # This is the config file, and
74 # a '#' and ';' character indicates a comment 70 # a '#' and ';' character indicates a comment
75 # 71 #
76 72
77 [colors] 73 [colors]
78 # Color variables 74 # Color variables
79 top = red, default 75 top = red, default
80 medium = green, default 76 medium = green, default
81 normal = lightgray, default 77 normal = lightgray, default
82 selected = white, lightgray 78 selected = white, lightgray
83 jump_arrows = blue, default 79 jump_arrows = blue, default
84 addr = magenta, default 80 addr = magenta, default
85 root = white, blue 81 root = white, blue
86 82
87 [tui] 83 [tui]
88 # Defaults if linked with libs 84 # Defaults if linked with libslang
89 report = on 85 report = on
90 annotate = on 86 annotate = on
91 top = on 87 top = on
92 88
93 [buildid] 89 [buildid]
94 # Default, disable using /dev/ 90 # Default, disable using /dev/null
95 dir = ~/.debug 91 dir = ~/.debug
96 92
97 [annotate] 93 [annotate]
98 # Defaults 94 # Defaults
99 hide_src_code = false 95 hide_src_code = false
100 use_offset = true 96 use_offset = true
101 jump_arrows = true 97 jump_arrows = true
102 show_nr_jumps = false 98 show_nr_jumps = false
103 99
104 [help] 100 [help]
105 # Format can be man, info, web 101 # Format can be man, info, web or html
106 format = man 102 format = man
107 autocorrect = 0 103 autocorrect = 0
108 104
109 [ui] 105 [ui]
110 show-headers = true 106 show-headers = true
111 107
112 [call-graph] 108 [call-graph]
113 # fp (framepointer), dwarf 109 # fp (framepointer), dwarf
114 record-mode = fp 110 record-mode = fp
115 print-type = graph 111 print-type = graph
116 order = caller 112 order = caller
117 sort-key = function 113 sort-key = function
118 114
119 [report] 115 [report]
120 # Defaults 116 # Defaults
121 sort_order = comm,dso,symbol 117 sort_order = comm,dso,symbol
122 percent-limit = 0 118 percent-limit = 0
123 queue-size = 0 119 queue-size = 0
124 children = true 120 children = true
125 group = true 121 group = true
126 skip-empty = true <<
127 122
>> 123 [llvm]
>> 124 dump-obj = true
>> 125 clang-opt = -g
128 126
129 You can hide source code of annotate feature s 127 You can hide source code of annotate feature setting the config to false with
130 128
131 % perf config annotate.hide_src_code=t 129 % perf config annotate.hide_src_code=true
132 130
133 If you want to add or modify several config it 131 If you want to add or modify several config items, you can do like
134 132
135 % perf config ui.show-headers=false km 133 % perf config ui.show-headers=false kmem.default=slab
136 134
137 To modify the sort order of report functionali 135 To modify the sort order of report functionality in user config file(i.e. `~/.perfconfig`), do
138 136
139 % perf config --user report.sort-order !! 137 % perf config --user report sort-order=srcline
140 138
141 To change colors of selected line to other for 139 To change colors of selected line to other foreground and background colors
142 in system config file (i.e. `$(sysconf)/perfco 140 in system config file (i.e. `$(sysconf)/perfconfig`), do
143 141
144 % perf config --system colors.selected 142 % perf config --system colors.selected=yellow,green
145 143
146 To query the record mode of call graph, do 144 To query the record mode of call graph, do
147 145
148 % perf config call-graph.record-mode 146 % perf config call-graph.record-mode
149 147
150 If you want to know multiple config key/value 148 If you want to know multiple config key/value pairs, you can do like
151 149
152 % perf config report.queue-size call-g 150 % perf config report.queue-size call-graph.order report.children
153 151
154 To query the config value of sort order of cal 152 To query the config value of sort order of call graph in user config file (i.e. `~/.perfconfig`), do
155 153
156 % perf config --user call-graph.sort-o 154 % perf config --user call-graph.sort-order
157 155
158 To query the config value of buildid directory 156 To query the config value of buildid directory in system config file (i.e. `$(sysconf)/perfconfig`), do
159 157
160 % perf config --system buildid.dir 158 % perf config --system buildid.dir
161 159
162 Variables 160 Variables
163 ~~~~~~~~~ 161 ~~~~~~~~~
164 162
165 colors.*:: 163 colors.*::
166 The variables for customizing the colo 164 The variables for customizing the colors used in the output for the
167 'report', 'top' and 'annotate' in the 165 'report', 'top' and 'annotate' in the TUI. They should specify the
168 foreground and background colors, sepa 166 foreground and background colors, separated by a comma, for example:
169 167
170 medium = green, lightgray 168 medium = green, lightgray
171 169
172 If you want to use the color configure 170 If you want to use the color configured for you terminal, just leave it
173 as 'default', for example: 171 as 'default', for example:
174 172
175 medium = default, lightgray 173 medium = default, lightgray
176 174
177 Available colors: 175 Available colors:
178 red, yellow, green, cyan, gray, black, 176 red, yellow, green, cyan, gray, black, blue,
179 white, default, magenta, lightgray 177 white, default, magenta, lightgray
180 178
181 colors.top:: 179 colors.top::
182 'top' means a overhead percent 180 'top' means a overhead percentage which is more than 5%.
183 And values of this variable sp 181 And values of this variable specify percentage colors.
184 Basic key values are foregroun 182 Basic key values are foreground-color 'red' and
185 background-color 'default'. 183 background-color 'default'.
186 colors.medium:: 184 colors.medium::
187 'medium' means a overhead perc 185 'medium' means a overhead percentage which has more than 0.5%.
188 Default values are 'green' and 186 Default values are 'green' and 'default'.
189 colors.normal:: 187 colors.normal::
190 'normal' means the rest of ove 188 'normal' means the rest of overhead percentages
191 except 'top', 'medium', 'selec 189 except 'top', 'medium', 'selected'.
192 Default values are 'lightgray' 190 Default values are 'lightgray' and 'default'.
193 colors.selected:: 191 colors.selected::
194 This selects the colors for th 192 This selects the colors for the current entry in a list of entries
195 from sub-commands (top, report 193 from sub-commands (top, report, annotate).
196 Default values are 'black' and 194 Default values are 'black' and 'lightgray'.
197 colors.jump_arrows:: 195 colors.jump_arrows::
198 Colors for jump arrows on asse 196 Colors for jump arrows on assembly code listings
199 such as 'jns', 'jmp', 'jane', 197 such as 'jns', 'jmp', 'jane', etc.
200 Default values are 'blue', 'de 198 Default values are 'blue', 'default'.
201 colors.addr:: 199 colors.addr::
202 This selects colors for addres 200 This selects colors for addresses from 'annotate'.
203 Default values are 'magenta', 201 Default values are 'magenta', 'default'.
204 colors.root:: 202 colors.root::
205 Colors for headers in the outp 203 Colors for headers in the output of a sub-commands (top, report).
206 Default values are 'white', 'b 204 Default values are 'white', 'blue'.
207 205
208 core.*:: 206 core.*::
209 core.proc-map-timeout:: 207 core.proc-map-timeout::
210 Sets a timeout (in millisecond 208 Sets a timeout (in milliseconds) for parsing /proc/<pid>/maps files.
211 Can be overridden by the --pro 209 Can be overridden by the --proc-map-timeout option on supported
212 subcommands. The default timeo 210 subcommands. The default timeout is 500ms.
213 211
214 tui.*, gtk.*:: 212 tui.*, gtk.*::
215 Subcommands that can be configured her 213 Subcommands that can be configured here are 'top', 'report' and 'annotate'.
216 These values are booleans, for example 214 These values are booleans, for example:
217 215
218 [tui] 216 [tui]
219 top = true 217 top = true
220 218
221 will make the TUI be the default for t 219 will make the TUI be the default for the 'top' subcommand. Those will be
222 available if the required libs were de 220 available if the required libs were detected at tool build time.
223 221
224 buildid.*:: 222 buildid.*::
225 buildid.dir:: 223 buildid.dir::
226 Each executable and shared lib 224 Each executable and shared library in modern distributions comes with a
227 content based identifier that, 225 content based identifier that, if available, will be inserted in a
228 'perf.data' file header to, at 226 'perf.data' file header to, at analysis time find what is needed to do
229 symbol resolution, code annota 227 symbol resolution, code annotation, etc.
230 228
231 The recording tools also store 229 The recording tools also stores a hard link or copy in a per-user
232 directory, $HOME/.debug/, of b 230 directory, $HOME/.debug/, of binaries, shared libraries, /proc/kallsyms
233 and /proc/kcore files to be us 231 and /proc/kcore files to be used at analysis time.
234 232
235 The buildid.dir variable can b 233 The buildid.dir variable can be used to either change this directory
236 cache location, or to disable 234 cache location, or to disable it altogether. If you want to disable it,
237 set buildid.dir to /dev/null. 235 set buildid.dir to /dev/null. The default is $HOME/.debug
238 236
239 buildid-cache.*:: <<
240 buildid-cache.debuginfod=URLs <<
241 Specify debuginfod URLs to be <<
242 it follows the same syntax as <<
243 <<
244 buildid-cache.debuginfod=htt <<
245 <<
246 annotate.*:: 237 annotate.*::
>> 238 These options work only for TUI.
247 These are in control of addresses, jum 239 These are in control of addresses, jump function, source code
248 in lines of assembly code from a speci 240 in lines of assembly code from a specific program.
249 241
250 annotate.addr2line:: <<
251 addr2line binary to use for fi <<
252 <<
253 annotate.objdump:: <<
254 objdump binary to use for disa <<
255 including in the 'perf test' c <<
256 <<
257 annotate.disassembler_style:: <<
258 Use this to change the default <<
259 supported by binutils, such as <<
260 'objdump' man page. <<
261 <<
262 annotate.hide_src_code:: 242 annotate.hide_src_code::
263 If a program which is analyzed 243 If a program which is analyzed has source code,
264 this option lets 'annotate' pr 244 this option lets 'annotate' print a list of assembly code with the source code.
265 For example, let's see a part 245 For example, let's see a part of a program. There're four lines.
266 If this option is 'true', they 246 If this option is 'true', they can be printed
267 without source code from a pro 247 without source code from a program as below.
268 248
269 │ push %rbp 249 │ push %rbp
270 │ mov %rsp,%rbp 250 │ mov %rsp,%rbp
271 │ sub $0x10,%rsp 251 │ sub $0x10,%rsp
272 │ mov (%rdi),%rdx 252 │ mov (%rdi),%rdx
273 253
274 But if this option is 'false', 254 But if this option is 'false', source code of the part
275 can be also printed as below. 255 can be also printed as below. Default is 'false'.
276 256
277 │ struct rb_node *rb_ne 257 │ struct rb_node *rb_next(const struct rb_node *node)
278 │ { 258 │ {
279 │ push %rbp 259 │ push %rbp
280 │ mov %rsp,%rbp 260 │ mov %rsp,%rbp
281 │ sub $0x10,%rsp 261 │ sub $0x10,%rsp
282 │ struct rb_nod 262 │ struct rb_node *parent;
283 │ 263 │
284 │ if (RB_EMPTY_ 264 │ if (RB_EMPTY_NODE(node))
285 │ mov (%rdi),%rdx 265 │ mov (%rdi),%rdx
286 │ return n; 266 │ return n;
287 267
288 This option works with tui, st <<
289 <<
290 annotate.use_offset:: 268 annotate.use_offset::
291 Basing on a first address of a 269 Basing on a first address of a loaded function, offset can be used.
292 Instead of using original addr 270 Instead of using original addresses of assembly code,
293 addresses subtracted from a ba 271 addresses subtracted from a base address can be printed.
294 Let's illustrate an example. 272 Let's illustrate an example.
295 If a base address is 0XFFFFFFF 273 If a base address is 0XFFFFFFFF81624d50 as below,
296 274
297 ffffffff81624d50 <load0> 275 ffffffff81624d50 <load0>
298 276
299 an address on assembly code ha 277 an address on assembly code has a specific absolute address as below
300 278
301 ffffffff816250b8:│ mov 0 279 ffffffff816250b8:│ mov 0x8(%r14),%rdi
302 280
303 but if use_offset is 'true', a 281 but if use_offset is 'true', an address subtracted from a base address is printed.
304 Default is true. This option i 282 Default is true. This option is only applied to TUI.
305 283
306 368:│ mov 0 284 368:│ mov 0x8(%r14),%rdi
307 285
308 This option works with tui, st <<
309 <<
310 annotate.jump_arrows:: 286 annotate.jump_arrows::
311 There can be jump instruction 287 There can be jump instruction among assembly code.
312 Depending on a boolean value o 288 Depending on a boolean value of jump_arrows,
313 arrows can be printed or not w 289 arrows can be printed or not which represent
314 where do the instruction jump 290 where do the instruction jump into as below.
315 291
316 │ ┌──jmp 1333 292 │ ┌──jmp 1333
317 │ │ xchg %ax,%ax 293 │ │ xchg %ax,%ax
318 │1330:│ mov %r15,%r10 294 │1330:│ mov %r15,%r10
319 │1333:└─→cmp %r15,% 295 │1333:└─→cmp %r15,%r14
320 296
321 If jump_arrow is 'false', the 297 If jump_arrow is 'false', the arrows isn't printed as below.
322 Default is 'false'. 298 Default is 'false'.
323 299
324 │ ↓ jmp 1333 300 │ ↓ jmp 1333
325 │ xchg %ax,%ax 301 │ xchg %ax,%ax
326 │1330: mov %r15,%r10 302 │1330: mov %r15,%r10
327 │1333: cmp %r15,%r14 303 │1333: cmp %r15,%r14
328 304
329 This option works with tui bro <<
330 <<
331 annotate.show_linenr:: 305 annotate.show_linenr::
332 When showing source code if th 306 When showing source code if this option is 'true',
333 line numbers are printed as be 307 line numbers are printed as below.
334 308
335 │1628 if (type & PER 309 │1628 if (type & PERF_SAMPLE_IDENTIFIER) {
336 │ ↓ jne 508 310 │ ↓ jne 508
337 │1628 data-> 311 │1628 data->id = *array;
338 │1629 array+ 312 │1629 array++;
339 │1630 } 313 │1630 }
340 314
341 However if this option is 'fal 315 However if this option is 'false', they aren't printed as below.
342 Default is 'false'. 316 Default is 'false'.
343 317
344 │ if (type & PER 318 │ if (type & PERF_SAMPLE_IDENTIFIER) {
345 │ ↓ jne 508 319 │ ↓ jne 508
346 │ data-> 320 │ data->id = *array;
347 │ array+ 321 │ array++;
348 │ } 322 │ }
349 323
350 This option works with tui, st <<
351 <<
352 annotate.show_nr_jumps:: 324 annotate.show_nr_jumps::
353 Let's see a part of assembly c 325 Let's see a part of assembly code.
354 326
355 │1382: movb $0x1,-0x270( 327 │1382: movb $0x1,-0x270(%rbp)
356 328
357 If use this, the number of bra 329 If use this, the number of branches jumping to that address can be printed as below.
358 Default is 'false'. 330 Default is 'false'.
359 331
360 │1 1382: movb $0x1,-0x27 332 │1 1382: movb $0x1,-0x270(%rbp)
361 333
362 This option works with tui, st <<
363 <<
364 annotate.show_total_period:: 334 annotate.show_total_period::
365 To compare two records on an i 335 To compare two records on an instruction base, with this option
366 provided, display total number 336 provided, display total number of samples that belong to a line
367 in assembly code. If this opti 337 in assembly code. If this option is 'true', total periods are printed
368 instead of percent values as b 338 instead of percent values as below.
369 339
370 302 │ mov %eax,%ea 340 302 │ mov %eax,%eax
371 341
372 But if this option is 'false', 342 But if this option is 'false', percent values for overhead are printed i.e.
373 Default is 'false'. 343 Default is 'false'.
374 344
375 99.93 │ mov %eax,%ea 345 99.93 │ mov %eax,%eax
376 346
377 This option works with tui, st <<
378 <<
379 annotate.show_nr_samples:: <<
380 By default perf annotate shows <<
381 can be used to print absolute <<
382 false: <<
383 <<
384 Percent│ <<
385 74.03 │ mov %fs:0x2 <<
386 <<
387 When set as true: <<
388 <<
389 Samples│ <<
390 6 │ mov %fs:0x2 <<
391 <<
392 This option works with tui, st <<
393 <<
394 annotate.offset_level:: 347 annotate.offset_level::
395 Default is '1', meaning just j 348 Default is '1', meaning just jump targets will have offsets show right beside
396 the instruction. When set to ' 349 the instruction. When set to '2' 'call' instructions will also have its offsets
397 shown, 3 or higher will show o 350 shown, 3 or higher will show offsets for all instructions.
398 351
399 This option works with tui, st <<
400 <<
401 annotate.demangle:: <<
402 Demangle symbol names to human <<
403 <<
404 annotate.demangle_kernel:: <<
405 Demangle kernel symbol names t <<
406 <<
407 hist.*:: 352 hist.*::
408 hist.percentage:: 353 hist.percentage::
409 This option control the way to 354 This option control the way to calculate overhead of filtered entries -
410 that means the value of this o 355 that means the value of this option is effective only if there's a
411 filter (by comm, dso or symbol 356 filter (by comm, dso or symbol name). Suppose a following example:
412 357
413 Overhead Symbols 358 Overhead Symbols
414 ........ ....... 359 ........ .......
415 33.33% foo 360 33.33% foo
416 33.33% bar 361 33.33% bar
417 33.33% baz 362 33.33% baz
418 363
419 This is an original overhead an 364 This is an original overhead and we'll filter out the first 'foo'
420 entry. The value of 'relative' 365 entry. The value of 'relative' would increase the overhead of 'bar'
421 and 'baz' to 50.00% for each, w 366 and 'baz' to 50.00% for each, while 'absolute' would show their
422 current overhead (33.33%). 367 current overhead (33.33%).
423 368
424 ui.*:: 369 ui.*::
425 ui.show-headers:: 370 ui.show-headers::
426 This option controls display o 371 This option controls display of column headers (like 'Overhead' and 'Symbol')
427 in 'report' and 'top'. If this 372 in 'report' and 'top'. If this option is false, they are hidden.
428 This option is only applied to 373 This option is only applied to TUI.
429 374
430 call-graph.*:: 375 call-graph.*::
431 The following controls the handling of !! 376 When sub-commands 'top' and 'report' work with -g/—-children
432 -g/--call-graph options). !! 377 there're options in control of call-graph.
433 378
434 call-graph.record-mode:: 379 call-graph.record-mode::
435 The mode for user space can be !! 380 The record-mode can be 'fp' (frame pointer), 'dwarf' and 'lbr'.
436 and 'lbr'. The value 'dwarf' !! 381 The value of 'dwarf' is effective only if perf detect needed library
437 (or a recent version of libdw) !! 382 (libunwind or a recent version of libdw).
438 the value 'lbr' only works for !! 383 'lbr' only work for cpus that support it.
439 kernel space is controlled not <<
440 kernel config (CONFIG_UNWINDER <<
441 384
442 call-graph.dump-size:: 385 call-graph.dump-size::
443 The size of stack to dump in o 386 The size of stack to dump in order to do post-unwinding. Default is 8192 (byte).
444 When using dwarf into record-m 387 When using dwarf into record-mode, the default size will be used if omitted.
445 388
446 call-graph.print-type:: 389 call-graph.print-type::
447 The print-types can be graph ( 390 The print-types can be graph (graph absolute), fractal (graph relative),
448 flat and folded. This option c 391 flat and folded. This option controls a way to show overhead for each callchain
449 entry. Suppose a following exa 392 entry. Suppose a following example.
450 393
451 Overhead Symbols 394 Overhead Symbols
452 ........ ....... 395 ........ .......
453 40.00% foo 396 40.00% foo
454 | 397 |
455 ---foo 398 ---foo
456 | 399 |
457 |--50.00%--bar 400 |--50.00%--bar
458 | main 401 | main
459 | 402 |
460 --50.00%--baz 403 --50.00%--baz
461 main 404 main
462 405
463 This output is a 'fractal' for 406 This output is a 'fractal' format. The 'foo' came from 'bar' and 'baz' exactly
464 half and half so 'fractal' sho 407 half and half so 'fractal' shows 50.00% for each
465 (meaning that it assumes 100% 408 (meaning that it assumes 100% total overhead of 'foo').
466 409
467 The 'graph' uses absolute over 410 The 'graph' uses absolute overhead value of 'foo' as total so each of
468 'bar' and 'baz' callchain will 411 'bar' and 'baz' callchain will have 20.00% of overhead.
469 If 'flat' is used, single colu 412 If 'flat' is used, single column and linear exposure of call chains.
470 'folded' mean call chains are 413 'folded' mean call chains are displayed in a line, separated by semicolons.
471 414
472 call-graph.order:: 415 call-graph.order::
473 This option controls print ord 416 This option controls print order of callchains. The default is
474 'callee' which means callee is 417 'callee' which means callee is printed at top and then followed by its
475 caller and so on. The 'caller' 418 caller and so on. The 'caller' prints it in reverse order.
476 419
477 If this option is not set and 420 If this option is not set and report.children or top.children is
478 set to true (or the equivalent 421 set to true (or the equivalent command line option is given),
479 the default value of this opti 422 the default value of this option is changed to 'caller' for the
480 execution of 'perf report' or 423 execution of 'perf report' or 'perf top'. Other commands will
481 still default to 'callee'. 424 still default to 'callee'.
482 425
483 call-graph.sort-key:: 426 call-graph.sort-key::
484 The callchains are merged if t 427 The callchains are merged if they contain same information.
485 The sort-key option determines 428 The sort-key option determines a way to compare the callchains.
486 A value of 'sort-key' can be ' 429 A value of 'sort-key' can be 'function' or 'address'.
487 The default is 'function'. 430 The default is 'function'.
488 431
489 call-graph.threshold:: 432 call-graph.threshold::
490 When there're many callchains 433 When there're many callchains it'd print tons of lines. So perf omits
491 small callchains under a certa 434 small callchains under a certain overhead (threshold) and this option
492 control the threshold. Default 435 control the threshold. Default is 0.5 (%). The overhead is calculated
493 by value depends on call-graph 436 by value depends on call-graph.print-type.
494 437
495 call-graph.print-limit:: 438 call-graph.print-limit::
496 This is a maximum number of li 439 This is a maximum number of lines of callchain printed for a single
497 histogram entry. Default is 0 440 histogram entry. Default is 0 which means no limitation.
498 441
499 report.*:: 442 report.*::
500 report.sort_order:: 443 report.sort_order::
501 Allows changing the default so 444 Allows changing the default sort order from "comm,dso,symbol" to
502 some other default, for instan 445 some other default, for instance "sym,dso" may be more fitting for
503 kernel developers. 446 kernel developers.
504 report.percent-limit:: 447 report.percent-limit::
505 This one is mostly the same as 448 This one is mostly the same as call-graph.threshold but works for
506 histogram entries. Entries hav 449 histogram entries. Entries having an overhead lower than this
507 percentage will not be printed 450 percentage will not be printed. Default is '0'. If percent-limit
508 is '10', only entries which ha 451 is '10', only entries which have more than 10% of overhead will be
509 printed. 452 printed.
510 453
511 report.queue-size:: 454 report.queue-size::
512 This option sets up the maximu 455 This option sets up the maximum allocation size of the internal
513 event queue for ordering event 456 event queue for ordering events. Default is 0, meaning no limit.
514 457
515 report.children:: 458 report.children::
516 'Children' means functions cal 459 'Children' means functions called from another function.
517 If this option is true, 'perf 460 If this option is true, 'perf report' cumulates callchains of children
518 and show (accumulated) total o 461 and show (accumulated) total overhead as well as 'Self' overhead.
519 Please refer to the 'perf repo 462 Please refer to the 'perf report' manual. The default is 'true'.
520 463
521 report.group:: 464 report.group::
522 This option is to show event g 465 This option is to show event group information together.
523 Example output with this turne 466 Example output with this turned on, notice that there is one column
524 per event in the group, ref-cy 467 per event in the group, ref-cycles and cycles:
525 468
526 # group: {ref-cycles,cycles} 469 # group: {ref-cycles,cycles}
527 # ======== 470 # ========
528 # 471 #
529 # Samples: 7K of event 'anon g 472 # Samples: 7K of event 'anon group { ref-cycles, cycles }'
530 # Event count (approx.): 68761 473 # Event count (approx.): 6876107743
531 # 474 #
532 # Overhead Command 475 # Overhead Command Shared Object Symbol
533 # ................ ....... . 476 # ................ ....... ................. ...................
534 # 477 #
535 99.84% 99.76% noploop n 478 99.84% 99.76% noploop noploop [.] main
536 0.07% 0.00% noploop l 479 0.07% 0.00% noploop ld-2.15.so [.] strcmp
537 0.03% 0.00% noploop [ 480 0.03% 0.00% noploop [kernel.kallsyms] [k] timerqueue_del
538 481
539 report.skip-empty:: <<
540 This option can change default <<
541 If it's set true, 'perf report <<
542 <<
543 top.*:: 482 top.*::
544 top.children:: 483 top.children::
545 Same as 'report.children'. So 484 Same as 'report.children'. So if it is enabled, the output of 'top'
546 command will have 'Children' o 485 command will have 'Children' overhead column as well as 'Self' overhead
547 column by default. 486 column by default.
548 The default is 'true'. 487 The default is 'true'.
549 488
550 top.call-graph:: <<
551 This is identical to 'call-gra <<
552 applicable only for 'top' subc <<
553 the unwind method. To enable ' <<
554 the command line option -g mus <<
555 <<
556 man.*:: 489 man.*::
557 man.viewer:: 490 man.viewer::
558 This option can assign a tool 491 This option can assign a tool to view manual pages when 'help'
559 subcommand was invoked. Suppor 492 subcommand was invoked. Supported tools are 'man', 'woman'
560 (with emacs client) and 'konqu 493 (with emacs client) and 'konqueror'. Default is 'man'.
561 494
562 New man viewer tool can be als 495 New man viewer tool can be also added using 'man.<tool>.cmd'
563 or use different path using 'm 496 or use different path using 'man.<tool>.path' config option.
564 497
565 pager.*:: 498 pager.*::
566 pager.<subcommand>:: 499 pager.<subcommand>::
567 When the subcommand is run on 500 When the subcommand is run on stdio, determine whether it uses
568 pager or not based on this val 501 pager or not based on this value. Default is 'unspecified'.
569 502
570 kmem.*:: 503 kmem.*::
571 kmem.default:: 504 kmem.default::
572 This option decides which allo 505 This option decides which allocator is to be analyzed if neither
573 '--slab' nor '--page' option i 506 '--slab' nor '--page' option is used. Default is 'slab'.
574 507
575 record.*:: 508 record.*::
576 record.build-id:: 509 record.build-id::
577 This option can be 'cache', 'n !! 510 This option can be 'cache', 'no-cache' or 'skip'.
578 'cache' is to post-process dat 511 'cache' is to post-process data and save/update the binaries into
579 the build-id cache (in ~/.debu 512 the build-id cache (in ~/.debug). This is the default.
580 But if this option is 'no-cach 513 But if this option is 'no-cache', it will not update the build-id cache.
581 'skip' skips post-processing a 514 'skip' skips post-processing and does not update the cache.
582 'mmap' skips post-processing a <<
583 <<
584 record.call-graph:: <<
585 This is identical to 'call-gra <<
586 applicable only for 'record' s <<
587 the unwind method. To enable ' <<
588 the command line option -g mus <<
589 <<
590 record.aio:: <<
591 Use 'n' control blocks in asyn <<
592 mode ('n' default: 1, max: 4). <<
593 <<
594 record.debuginfod:: <<
595 Specify debuginfod URL to be u <<
596 it follows the same syntax as <<
597 <<
598 http://192.168.122.174:8002 <<
599 <<
600 If the URLs is 'system', the v <<
601 variable is used. <<
602 515
603 diff.*:: 516 diff.*::
604 diff.order:: 517 diff.order::
605 This option sets the number of 518 This option sets the number of columns to sort the result.
606 The default is 0, which means 519 The default is 0, which means sorting by baseline.
607 Setting it to 1 will sort the 520 Setting it to 1 will sort the result by delta (or other
608 compute method selected). 521 compute method selected).
609 522
610 diff.compute:: 523 diff.compute::
611 This options sets the method f 524 This options sets the method for computing the diff result.
612 Possible values are 'delta', ' 525 Possible values are 'delta', 'delta-abs', 'ratio' and
613 'wdiff'. Default is 'delta'. 526 'wdiff'. Default is 'delta'.
614 527
615 trace.*:: 528 trace.*::
616 trace.add_events:: 529 trace.add_events::
617 Allows adding a set of events 530 Allows adding a set of events to add to the ones specified
618 by the user, or use as a defau 531 by the user, or use as a default one if none was specified.
619 The initial use case is to add 532 The initial use case is to add augmented_raw_syscalls.o to
620 activate the 'perf trace' logi 533 activate the 'perf trace' logic that looks for syscall
621 pointer contents after the nor 534 pointer contents after the normal tracepoint payload.
622 535
623 trace.args_alignment:: 536 trace.args_alignment::
624 Number of columns to align the 537 Number of columns to align the argument list, default is 70,
625 use 40 for the strace default, 538 use 40 for the strace default, zero to no alignment.
626 539
627 trace.no_inherit:: 540 trace.no_inherit::
628 Do not follow children threads 541 Do not follow children threads.
629 542
630 trace.show_arg_names:: 543 trace.show_arg_names::
631 Should syscall argument names 544 Should syscall argument names be printed? If not then trace.show_zeros
632 will be set. 545 will be set.
633 546
634 trace.show_duration:: 547 trace.show_duration::
635 Show syscall duration. 548 Show syscall duration.
636 549
637 trace.show_prefix:: 550 trace.show_prefix::
638 If set to 'yes' will show comm 551 If set to 'yes' will show common string prefixes in tables. The default
639 is to remove the common prefix 552 is to remove the common prefix in things like "MAP_SHARED", showing just "SHARED".
640 553
641 trace.show_timestamp:: 554 trace.show_timestamp::
642 Show syscall start timestamp. 555 Show syscall start timestamp.
643 556
644 trace.show_zeros:: 557 trace.show_zeros::
645 Do not suppress syscall argume 558 Do not suppress syscall arguments that are equal to zero.
646 559
647 trace.tracepoint_beautifiers:: !! 560 llvm.*::
648 Use "libtraceevent" to use tha !! 561 llvm.clang-path::
649 "libbeauty", the default, to u !! 562 Path to clang. If omit, search it from $PATH.
650 strace-like sys_enter+sys_exit !! 563
651 !! 564 llvm.clang-bpf-cmd-template::
652 ftrace.*:: !! 565 Cmdline template. Below lines show its default value. Environment
653 ftrace.tracer:: !! 566 variable is used to pass options.
654 Can be used to select the defa !! 567 "$CLANG_EXEC -D__KERNEL__ $CLANG_OPTIONS $KERNEL_INC_OPTIONS \
655 -F option is not specified. Po !! 568 -Wno-unused-value -Wno-pointer-sign -working-directory \
656 'function_graph'. !! 569 $WORKING_DIR -c $CLANG_SOURCE -target bpf -O2 -o -"
>> 570
>> 571 llvm.clang-opt::
>> 572 Options passed to clang.
>> 573
>> 574 llvm.kbuild-dir::
>> 575 kbuild directory. If not set, use /lib/modules/`uname -r`/build.
>> 576 If set to "" deliberately, skip kernel header auto-detector.
>> 577
>> 578 llvm.kbuild-opts::
>> 579 Options passed to 'make' when detecting kernel header options.
>> 580
>> 581 llvm.dump-obj::
>> 582 Enable perf dump BPF object files compiled by LLVM.
>> 583
>> 584 llvm.opts::
>> 585 Options passed to llc.
657 586
658 samples.*:: 587 samples.*::
659 588
660 samples.context:: 589 samples.context::
661 Define how many ns worth of ti 590 Define how many ns worth of time to show
662 around samples in perf report 591 around samples in perf report sample context browser.
663 592
664 scripts.*:: 593 scripts.*::
665 594
666 Any option defines a script that is ad 595 Any option defines a script that is added to the scripts menu
667 in the interactive perf browser and wh 596 in the interactive perf browser and whose output is displayed.
668 The name of the option is the name, th 597 The name of the option is the name, the value is a script command line.
669 The script gets the same options passe 598 The script gets the same options passed as a full perf script,
670 in particular -i perfdata file, --cpu, 599 in particular -i perfdata file, --cpu, --tid
671 <<
672 convert.*:: <<
673 <<
674 convert.queue-size:: <<
675 Limit the size of ordered_even <<
676 allocation size of perf data f <<
677 round events. <<
678 stat.*:: <<
679 <<
680 stat.big-num:: <<
681 (boolean) Change the default f <<
682 "--no-big-num" the default, se <<
683 <<
684 intel-pt.*:: <<
685 <<
686 intel-pt.cache-divisor:: <<
687 <<
688 intel-pt.mispred-all:: <<
689 If set, Intel PT decoder will <<
690 branches. <<
691 <<
692 intel-pt.max-loops:: <<
693 If set and non-zero, the maxim <<
694 branches decoded without consu <<
695 the maximum is exceeded there <<
696 error. The default is 100000. <<
697 <<
698 auxtrace.*:: <<
699 <<
700 auxtrace.dumpdir:: <<
701 s390 only. The directory to sa <<
702 can be changed using this opti <<
703 If the directory does not exis <<
704 the current directory is used. <<
705 <<
706 itrace.*:: <<
707 <<
708 debug-log-buffer-size:: <<
709 Log size in bytes to output wh <<
710 Refer 'itrace' option of linkp <<
711 linkperf:perf-report[1]. The d <<
712 <<
713 daemon.*:: <<
714 <<
715 daemon.base:: <<
716 Base path for daemon data. All <<
717 this path. <<
718 <<
719 session-<NAME>.*:: <<
720 <<
721 session-<NAME>.run:: <<
722 <<
723 Defines new record session for <<
724 command line without the 'reco <<
725 600
726 SEE ALSO 601 SEE ALSO
727 -------- 602 --------
728 linkperf:perf[1] 603 linkperf:perf[1]
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.