Lines Matching +full:foo +full:- +full:queue
1 perf-config(1)
5 ----
6 perf-config - Get and set variables in a configuration file.
9 --------
11 'perf config' [<file-option>] [section.name[=value] ...]
13 'perf config' [<file-option>] -l | --list
16 -----------
20 -------
22 -l::
23 --list::
26 --user::
30 --system::
31 For writing and reading options: write to system-wide
35 ------------------
39 The '$HOME/.perfconfig' file is used to store a per-user configuration.
41 store a system-wide default configuration.
48 configuration files by default, and options '--system' and '--user'
110 show-headers = true
112 [call-graph]
114 record-mode = fp
115 print-type = graph
117 sort-key = function
122 percent-limit = 0
123 queue-size = 0
126 skip-empty = true
129 dump-obj = true
130 clang-opt = -g
138 % perf config ui.show-headers=false kmem.default=slab
142 % perf config --user report.sort-order=srcline
147 % perf config --system colors.selected=yellow,green
151 % perf config call-graph.record-mode
155 % perf config report.queue-size call-graph.order report.children
159 % perf config --user call-graph.sort-order
163 % perf config --system buildid.dir
187 Basic key values are foreground-color 'red' and
188 background-color 'default'.
198 from sub-commands (top, report, annotate).
208 Colors for headers in the output of a sub-commands (top, report).
212 core.proc-map-timeout::
214 Can be overridden by the --proc-map-timeout option on supported
234 The recording tools also stores a hard link or copy in a per-user
242 buildid-cache.*::
243 buildid-cache.debuginfod=URLs
247 buildid-cache.debuginfod=http://192.168.122.174:8002
255 supported by binutils, such as "intel", see the '-M' option help in the
333 │1628 data->id = *array;
342 │ data->id = *array;
351 │1382: movb $0x1,-0x270(%rbp)
356 │1 1382: movb $0x1,-0x270(%rbp)
405 This option control the way to calculate overhead of filtered entries -
411 33.33% foo
415 This is an original overhead and we'll filter out the first 'foo'
421 ui.show-headers::
426 call-graph.*::
427 The following controls the handling of call-graphs (obtained via the
428 -g/--call-graph options).
430 call-graph.record-mode::
438 call-graph.dump-size::
439 The size of stack to dump in order to do post-unwinding. Default is 8192 (byte).
440 When using dwarf into record-mode, the default size will be used if omitted.
442 call-graph.print-type::
443 The print-types can be graph (graph absolute), fractal (graph relative),
449 40.00% foo
451 ---foo
453 |--50.00%--bar
456 --50.00%--baz
459 This output is a 'fractal' format. The 'foo' came from 'bar' and 'baz' exactly
461 (meaning that it assumes 100% total overhead of 'foo').
463 The 'graph' uses absolute overhead value of 'foo' as total so each of
468 call-graph.order::
479 call-graph.sort-key::
481 The sort-key option determines a way to compare the callchains.
482 A value of 'sort-key' can be 'function' or 'address'.
485 call-graph.threshold::
489 by value depends on call-graph.print-type.
491 call-graph.print-limit::
500 report.percent-limit::
501 This one is mostly the same as call-graph.threshold but works for
503 percentage will not be printed. Default is '0'. If percent-limit
507 report.queue-size::
509 event queue for ordering events. Default is 0, meaning no limit.
520 per event in the group, ref-cycles and cycles:
522 # group: {ref-cycles,cycles}
525 # Samples: 7K of event 'anon group { ref-cycles, cycles }'
532 0.07% 0.00% noploop ld-2.15.so [.] strcmp
535 report.skip-empty::
537 If it's set true, 'perf report --stat' will not show 0 stats.
546 top.call-graph::
547 This is identical to 'call-graph.record-mode', except it is
550 the command line option -g must be specified.
569 '--slab' nor '--page' option is used. Default is 'slab'.
572 record.build-id::
573 This option can be 'cache', 'no-cache', 'skip' or 'mmap'.
574 'cache' is to post-process data and save/update the binaries into
575 the build-id cache (in ~/.debug). This is the default.
576 But if this option is 'no-cache', it will not update the build-id cache.
577 'skip' skips post-processing and does not update the cache.
578 'mmap' skips post-processing and reads build-ids from MMAP events.
580 record.call-graph::
581 This is identical to 'call-graph.record-mode', except it is
584 the command line option -g must be specified.
599 Possible values are 'delta', 'delta-abs', 'ratio' and
637 strace-like sys_enter+sys_exit lines.
641 Can be used to select the default tracer when neither -G nor
642 -F option is not specified. Possible values are 'function' and
646 llvm.clang-path::
649 llvm.clang-bpf-cmd-template::
652 "$CLANG_EXEC -D__KERNEL__ -D__NR_CPUS__=$NR_CPUS "\
653 "-DLINUX_VERSION_CODE=$LINUX_VERSION_CODE " \
655 "-Wno-unused-value -Wno-pointer-sign " \
656 "-working-directory $WORKING_DIR " \
657 "-c \"$CLANG_SOURCE\" -target bpf $CLANG_EMIT_LLVM -O2 -o - $LLVM_OPTIONS_PIPE"
659 llvm.clang-opt::
662 llvm.kbuild-dir::
663 kbuild directory. If not set, use /lib/modules/`uname -r`/build.
664 If set to "" deliberately, skip kernel header auto-detector.
666 llvm.kbuild-opts::
669 llvm.dump-obj::
687 in particular -i perfdata file, --cpu, --tid
691 convert.queue-size::
692 Limit the size of ordered_events queue, so we could control
697 stat.big-num::
698 (boolean) Change the default for "--big-num". To make
699 "--no-big-num" the default, set "stat.big-num=false".
701 intel-pt.*::
703 intel-pt.cache-divisor::
705 intel-pt.mispred-all::
709 intel-pt.max-loops::
710 If set and non-zero, the maximum number of unconditional
712 the maximum is exceeded there will be a "Never-ending loop"
729 session-<NAME>.*::
731 session-<NAME>.run::
738 --------