@@ -239,7 +239,6 @@ buildid.*::
239239 set buildid.dir to /dev/null. The default is $HOME/.debug
240240
241241annotate.*::
242- These options work only for TUI.
243242 These are in control of addresses, jump function, source code
244243 in lines of assembly code from a specific program.
245244
@@ -269,6 +268,8 @@ annotate.*::
269268 │ mov (%rdi),%rdx
270269 │ return n;
271270
271+ This option works with tui, stdio2 browsers.
272+
272273 annotate.use_offset::
273274 Basing on a first address of a loaded function, offset can be used.
274275 Instead of using original addresses of assembly code,
@@ -287,6 +288,8 @@ annotate.*::
287288
288289 368:│ mov 0x8(%r14),%rdi
289290
291+ This option works with tui, stdio2 browsers.
292+
290293 annotate.jump_arrows::
291294 There can be jump instruction among assembly code.
292295 Depending on a boolean value of jump_arrows,
@@ -306,6 +309,8 @@ annotate.*::
306309 │1330: mov %r15,%r10
307310 │1333: cmp %r15,%r14
308311
312+ This option works with tui browser.
313+
309314 annotate.show_linenr::
310315 When showing source code if this option is 'true',
311316 line numbers are printed as below.
@@ -325,6 +330,8 @@ annotate.*::
325330 │ array++;
326331 │ }
327332
333+ This option works with tui, stdio2 browsers.
334+
328335 annotate.show_nr_jumps::
329336 Let's see a part of assembly code.
330337
@@ -335,6 +342,8 @@ annotate.*::
335342
336343 │1 1382: movb $0x1,-0x270(%rbp)
337344
345+ This option works with tui, stdio2 browsers.
346+
338347 annotate.show_total_period::
339348 To compare two records on an instruction base, with this option
340349 provided, display total number of samples that belong to a line
@@ -348,11 +357,30 @@ annotate.*::
348357
349358 99.93 │ mov %eax,%eax
350359
360+ This option works with tui, stdio2, stdio browsers.
361+
362+ annotate.show_nr_samples::
363+ By default perf annotate shows percentage of samples. This option
364+ can be used to print absolute number of samples. Ex, when set as
365+ false:
366+
367+ Percent│
368+ 74.03 │ mov %fs:0x28,%rax
369+
370+ When set as true:
371+
372+ Samples│
373+ 6 │ mov %fs:0x28,%rax
374+
375+ This option works with tui, stdio2, stdio browsers.
376+
351377 annotate.offset_level::
352378 Default is '1', meaning just jump targets will have offsets show right beside
353379 the instruction. When set to '2' 'call' instructions will also have its offsets
354380 shown, 3 or higher will show offsets for all instructions.
355381
382+ This option works with tui, stdio2 browsers.
383+
356384hist.*::
357385 hist.percentage::
358386 This option control the way to calculate overhead of filtered entries -
@@ -490,6 +518,12 @@ top.*::
490518 column by default.
491519 The default is 'true'.
492520
521+ top.call-graph::
522+ This is identical to 'call-graph.record-mode', except it is
523+ applicable only for 'top' subcommand. This option ONLY setup
524+ the unwind method. To enable 'perf top' to actually use it,
525+ the command line option -g must be specified.
526+
493527man.*::
494528 man.viewer::
495529 This option can assign a tool to view manual pages when 'help'
@@ -517,6 +551,16 @@ record.*::
517551 But if this option is 'no-cache', it will not update the build-id cache.
518552 'skip' skips post-processing and does not update the cache.
519553
554+ record.call-graph::
555+ This is identical to 'call-graph.record-mode', except it is
556+ applicable only for 'record' subcommand. This option ONLY setup
557+ the unwind method. To enable 'perf record' to actually use it,
558+ the command line option -g must be specified.
559+
560+ record.aio::
561+ Use 'n' control blocks in asynchronous (Posix AIO) trace writing
562+ mode ('n' default: 1, max: 4).
563+
520564diff.*::
521565 diff.order::
522566 This option sets the number of columns to sort the result.
@@ -566,6 +610,11 @@ trace.*::
566610 "libbeauty", the default, to use the same argument beautifiers used in the
567611 strace-like sys_enter+sys_exit lines.
568612
613+ ftrace.*::
614+ ftrace.tracer::
615+ Can be used to select the default tracer. Possible values are
616+ 'function' and 'function_graph'.
617+
569618llvm.*::
570619 llvm.clang-path::
571620 Path to clang. If omit, search it from $PATH.
@@ -610,6 +659,29 @@ scripts.*::
610659 The script gets the same options passed as a full perf script,
611660 in particular -i perfdata file, --cpu, --tid
612661
662+ convert.*::
663+
664+ convert.queue-size::
665+ Limit the size of ordered_events queue, so we could control
666+ allocation size of perf data files without proper finished
667+ round events.
668+
669+ intel-pt.*::
670+
671+ intel-pt.cache-divisor::
672+
673+ intel-pt.mispred-all::
674+ If set, Intel PT decoder will set the mispred flag on all
675+ branches.
676+
677+ auxtrace.*::
678+
679+ auxtrace.dumpdir::
680+ s390 only. The directory to save the auxiliary trace buffer
681+ can be changed using this option. Ex, auxtrace.dumpdir=/tmp.
682+ If the directory does not exist or has the wrong file type,
683+ the current directory is used.
684+
613685SEE ALSO
614686--------
615687linkperf:perf[1]
0 commit comments