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; 283 │ 284 │ 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] 729