xref: /linux/tools/perf/Documentation/perf-script.txt (revision bfd5bb6f90af092aa345b15cd78143956a13c2a8)
1perf-script(1)
2=============
3
4NAME
5----
6perf-script - Read perf.data (created by perf record) and display trace output
7
8SYNOPSIS
9--------
10[verse]
11'perf script' [<options>]
12'perf script' [<options>] record <script> [<record-options>] <command>
13'perf script' [<options>] report <script> [script-args]
14'perf script' [<options>] <script> <required-script-args> [<record-options>] <command>
15'perf script' [<options>] <top-script> [script-args]
16
17DESCRIPTION
18-----------
19This command reads the input file and displays the trace recorded.
20
21There are several variants of perf script:
22
23  'perf script' to see a detailed trace of the workload that was
24  recorded.
25
26  You can also run a set of pre-canned scripts that aggregate and
27  summarize the raw trace data in various ways (the list of scripts is
28  available via 'perf script -l').  The following variants allow you to
29  record and run those scripts:
30
31  'perf script record <script> <command>' to record the events required
32  for 'perf script report'.  <script> is the name displayed in the
33  output of 'perf script --list' i.e. the actual script name minus any
34  language extension.  If <command> is not specified, the events are
35  recorded using the -a (system-wide) 'perf record' option.
36
37  'perf script report <script> [args]' to run and display the results
38  of <script>.  <script> is the name displayed in the output of 'perf
39  script --list' i.e. the actual script name minus any language
40  extension.  The perf.data output from a previous run of 'perf script
41  record <script>' is used and should be present for this command to
42  succeed.  [args] refers to the (mainly optional) args expected by
43  the script.
44
45  'perf script <script> <required-script-args> <command>' to both
46  record the events required for <script> and to run the <script>
47  using 'live-mode' i.e. without writing anything to disk.  <script>
48  is the name displayed in the output of 'perf script --list' i.e. the
49  actual script name minus any language extension.  If <command> is
50  not specified, the events are recorded using the -a (system-wide)
51  'perf record' option.  If <script> has any required args, they
52  should be specified before <command>.  This mode doesn't allow for
53  optional script args to be specified; if optional script args are
54  desired, they can be specified using separate 'perf script record'
55  and 'perf script report' commands, with the stdout of the record step
56  piped to the stdin of the report script, using the '-o -' and '-i -'
57  options of the corresponding commands.
58
59  'perf script <top-script>' to both record the events required for
60  <top-script> and to run the <top-script> using 'live-mode'
61  i.e. without writing anything to disk.  <top-script> is the name
62  displayed in the output of 'perf script --list' i.e. the actual
63  script name minus any language extension; a <top-script> is defined
64  as any script name ending with the string 'top'.
65
66  [<record-options>] can be passed to the record steps of 'perf script
67  record' and 'live-mode' variants; this isn't possible however for
68  <top-script> 'live-mode' or 'perf script report' variants.
69
70  See the 'SEE ALSO' section for links to language-specific
71  information on how to write and run your own trace scripts.
72
73OPTIONS
74-------
75<command>...::
76	Any command you can specify in a shell.
77
78-D::
79--dump-raw-trace=::
80        Display verbose dump of the trace data.
81
82-L::
83--Latency=::
84        Show latency attributes (irqs/preemption disabled, etc).
85
86-l::
87--list=::
88        Display a list of available trace scripts.
89
90-s ['lang']::
91--script=::
92        Process trace data with the given script ([lang]:script[.ext]).
93	If the string 'lang' is specified in place of a script name, a
94        list of supported languages will be displayed instead.
95
96-g::
97--gen-script=::
98        Generate perf-script.[ext] starter script for given language,
99        using current perf.data.
100
101-a::
102        Force system-wide collection.  Scripts run without a <command>
103        normally use -a by default, while scripts run with a <command>
104        normally don't - this option allows the latter to be run in
105        system-wide mode.
106
107-i::
108--input=::
109        Input file name. (default: perf.data unless stdin is a fifo)
110
111-d::
112--debug-mode::
113        Do various checks like samples ordering and lost events.
114
115-F::
116--fields::
117        Comma separated list of fields to print. Options are:
118        comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff,
119        srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn,
120        brstackoff, callindent, insn, insnlen, synth, phys_addr, metric, misc.
121        Field list can be prepended with the type, trace, sw or hw,
122        to indicate to which event type the field list applies.
123        e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
124
125		perf script -F <fields>
126
127	is equivalent to:
128
129		perf script -F trace:<fields> -F sw:<fields> -F hw:<fields>
130
131	i.e., the specified fields apply to all event types if the type string
132	is not given.
133
134	In addition to overriding fields, it is also possible to add or remove
135	fields from the defaults. For example
136
137		-F -cpu,+insn
138
139	removes the cpu field and adds the insn field. Adding/removing fields
140	cannot be mixed with normal overriding.
141
142	The arguments are processed in the order received. A later usage can
143	reset a prior request. e.g.:
144
145		-F trace: -F comm,tid,time,ip,sym
146
147	The first -F suppresses trace events (field list is ""), but then the
148	second invocation sets the fields to comm,tid,time,ip,sym. In this case a
149	warning is given to the user:
150
151		"Overriding previous field request for all events."
152
153	Alternatively, consider the order:
154
155		-F comm,tid,time,ip,sym -F trace:
156
157	The first -F sets the fields for all events and the second -F
158	suppresses trace events. The user is given a warning message about
159	the override, and the result of the above is that only S/W and H/W
160	events are displayed with the given fields.
161
162	For the 'wildcard' option if a user selected field is invalid for an
163	event type, a message is displayed to the user that the option is
164	ignored for that type. For example:
165
166		$ perf script -F comm,tid,trace
167		'trace' not valid for hardware events. Ignoring.
168		'trace' not valid for software events. Ignoring.
169
170	Alternatively, if the type is given an invalid field is specified it
171	is an error. For example:
172
173        perf script -v -F sw:comm,tid,trace
174        'trace' not valid for software events.
175
176	At this point usage is displayed, and perf-script exits.
177
178	The flags field is synthesized and may have a value when Instruction
179	Trace decoding. The flags are "bcrosyiABEx" which stand for branch,
180	call, return, conditional, system, asynchronous, interrupt,
181	transaction abort, trace begin, trace end, and in transaction,
182	respectively. Known combinations of flags are printed more nicely e.g.
183	"call" for "bc", "return" for "br", "jcc" for "bo", "jmp" for "b",
184	"int" for "bci", "iret" for "bri", "syscall" for "bcs", "sysret" for "brs",
185	"async" for "by", "hw int" for "bcyi", "tx abrt" for "bA", "tr strt" for "bB",
186	"tr end" for "bE". However the "x" flag will be display separately in those
187	cases e.g. "jcc     (x)" for a condition branch within a transaction.
188
189	The callindent field is synthesized and may have a value when
190	Instruction Trace decoding. For calls and returns, it will display the
191	name of the symbol indented with spaces to reflect the stack depth.
192
193	When doing instruction trace decoding insn and insnlen give the
194	instruction bytes and the instruction length of the current
195	instruction.
196
197	The synth field is used by synthesized events which may be created when
198	Instruction Trace decoding.
199
200	Finally, a user may not set fields to none for all event types.
201	i.e., -F "" is not allowed.
202
203	The brstack output includes branch related information with raw addresses using the
204	/v/v/v/v/cycles syntax in the following order:
205	FROM: branch source instruction
206	TO  : branch target instruction
207        M/P/-: M=branch target mispredicted or branch direction was mispredicted, P=target predicted or direction predicted, -=not supported
208	X/- : X=branch inside a transactional region, -=not in transaction region or not supported
209	A/- : A=TSX abort entry, -=not aborted region or not supported
210	cycles
211
212	The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible.
213
214	When brstackinsn is specified the full assembler sequences of branch sequences for each sample
215	is printed. This is the full execution path leading to the sample. This is only supported when the
216	sample was recorded with perf record -b or -j any.
217
218	The brstackoff field will print an offset into a specific dso/binary.
219
220	With the metric option perf script can compute metrics for
221	sampling periods, similar to perf stat. This requires
222	specifying a group with multiple metrics with the :S option
223	for perf record. perf will sample on the first event, and
224	compute metrics for all the events in the group. Please note
225	that the metric computed is averaged over the whole sampling
226	period, not just for the sample point.
227
228	For sample events it's possible to display misc field with -F +misc option,
229	following letters are displayed for each bit:
230
231	  PERF_RECORD_MISC_KERNEL               K
232	  PERF_RECORD_MISC_USER                 U
233	  PERF_RECORD_MISC_HYPERVISOR           H
234	  PERF_RECORD_MISC_GUEST_KERNEL         G
235	  PERF_RECORD_MISC_GUEST_USER           g
236	  PERF_RECORD_MISC_MMAP_DATA*           M
237	  PERF_RECORD_MISC_COMM_EXEC            E
238	  PERF_RECORD_MISC_SWITCH_OUT           S
239	  PERF_RECORD_MISC_SWITCH_OUT_PREEMPT   Sp
240
241	  $ perf script -F +misc ...
242	   sched-messaging  1414 K     28690.636582:       4590 cycles ...
243	   sched-messaging  1407 U     28690.636600:     325620 cycles ...
244	   sched-messaging  1414 K     28690.636608:      19473 cycles ...
245	  misc field ___________/
246
247-k::
248--vmlinux=<file>::
249        vmlinux pathname
250
251--kallsyms=<file>::
252        kallsyms pathname
253
254--symfs=<directory>::
255        Look for files with symbols relative to this directory.
256
257-G::
258--hide-call-graph::
259        When printing symbols do not display call chain.
260
261--stop-bt::
262        Stop display of callgraph at these symbols
263
264-C::
265--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
266	be provided as a comma-separated list with no space: 0,1. Ranges of
267	CPUs are specified with -: 0-2. Default is to report samples on all
268	CPUs.
269
270-c::
271--comms=::
272	Only display events for these comms. CSV that understands
273	file://filename entries.
274
275--pid=::
276	Only show events for given process ID (comma separated list).
277
278--tid=::
279	Only show events for given thread ID (comma separated list).
280
281-I::
282--show-info::
283	Display extended information about the perf.data file. This adds
284	information which may be very large and thus may clutter the display.
285	It currently includes: cpu and numa topology of the host system.
286	It can only be used with the perf script report mode.
287
288--show-kernel-path::
289	Try to resolve the path of [kernel.kallsyms]
290
291--show-task-events
292	Display task related events (e.g. FORK, COMM, EXIT).
293
294--show-mmap-events
295	Display mmap related events (e.g. MMAP, MMAP2).
296
297--show-namespace-events
298	Display namespace events i.e. events of type PERF_RECORD_NAMESPACES.
299
300--show-switch-events
301	Display context switch events i.e. events of type PERF_RECORD_SWITCH or
302	PERF_RECORD_SWITCH_CPU_WIDE.
303
304--show-lost-events
305	Display lost events i.e. events of type PERF_RECORD_LOST.
306
307--show-round-events
308	Display finished round events i.e. events of type PERF_RECORD_FINISHED_ROUND.
309
310--demangle::
311	Demangle symbol names to human readable form. It's enabled by default,
312	disable with --no-demangle.
313
314--demangle-kernel::
315	Demangle kernel symbol names to human readable form (for C++ kernels).
316
317--header
318	Show perf.data header.
319
320--header-only
321	Show only perf.data header.
322
323--itrace::
324	Options for decoding instruction tracing data. The options are:
325
326include::itrace.txt[]
327
328	To disable decoding entirely, use --no-itrace.
329
330--full-source-path::
331	Show the full path for source files for srcline output.
332
333--max-stack::
334        Set the stack depth limit when parsing the callchain, anything
335        beyond the specified depth will be ignored. This is a trade-off
336        between information loss and faster processing especially for
337        workloads that can have a very long callchain stack.
338        Note that when using the --itrace option the synthesized callchain size
339        will override this value if the synthesized callchain size is bigger.
340
341        Default: 127
342
343--ns::
344	Use 9 decimal places when displaying time (i.e. show the nanoseconds)
345
346-f::
347--force::
348	Don't do ownership validation.
349
350--time::
351	Only analyze samples within given time window: <start>,<stop>. Times
352	have the format seconds.microseconds. If start is not given (i.e., time
353	string is ',x.y') then analysis starts at the beginning of the file. If
354	stop time is not given (i.e, time string is 'x.y,') then analysis goes
355	to end of file.
356
357	Also support time percent with multipe time range. Time string is
358	'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'.
359
360	For example:
361	Select the second 10% time slice:
362	perf script --time 10%/2
363
364	Select from 0% to 10% time slice:
365	perf script --time 0%-10%
366
367	Select the first and second 10% time slices:
368	perf script --time 10%/1,10%/2
369
370	Select from 0% to 10% and 30% to 40% slices:
371	perf script --time 0%-10%,30%-40%
372
373--max-blocks::
374	Set the maximum number of program blocks to print with brstackasm for
375	each sample.
376
377--per-event-dump::
378	Create per event files with a "perf.data.EVENT.dump" name instead of
379        printing to stdout, useful, for instance, for generating flamegraphs.
380
381--inline::
382	If a callgraph address belongs to an inlined function, the inline stack
383	will be printed. Each entry has function name and file/line. Enabled by
384	default, disable with --no-inline.
385
386SEE ALSO
387--------
388linkperf:perf-record[1], linkperf:perf-script-perl[1],
389linkperf:perf-script-python[1]
390