1PERF-SCRIPT(1) perf Manual PERF-SCRIPT(1)
2
3
4
6 perf-script - Read perf.data (created by perf record) and display trace
7 output
8
10 perf script [<options>]
11 perf script [<options>] record <script> [<record-options>] <command>
12 perf script [<options>] report <script> [script-args]
13 perf script [<options>] <script> <required-script-args> [<record-options>] <command>
14 perf script [<options>] <top-script> [script-args]
15
17 This command reads the input file and displays the trace recorded.
18
19 There are several variants of perf script:
20
21 'perf script' to see a detailed trace of the workload that was
22 recorded.
23
24 You can also run a set of pre-canned scripts that aggregate and
25 summarize the raw trace data in various ways (the list of scripts is
26 available via 'perf script -l'). The following variants allow you to
27 record and run those scripts:
28
29 'perf script record <script> <command>' to record the events required
30 for 'perf script report'. <script> is the name displayed in the
31 output of 'perf script --list' i.e. the actual script name minus any
32 language extension. If <command> is not specified, the events are
33 recorded using the -a (system-wide) 'perf record' option.
34
35 'perf script report <script> [args]' to run and display the results
36 of <script>. <script> is the name displayed in the output of 'perf
37 script --list' i.e. the actual script name minus any language
38 extension. The perf.data output from a previous run of 'perf script
39 record <script>' is used and should be present for this command to
40 succeed. [args] refers to the (mainly optional) args expected by
41 the script.
42
43 'perf script <script> <required-script-args> <command>' to both
44 record the events required for <script> and to run the <script>
45 using 'live-mode' i.e. without writing anything to disk. <script>
46 is the name displayed in the output of 'perf script --list' i.e. the
47 actual script name minus any language extension. If <command> is
48 not specified, the events are recorded using the -a (system-wide)
49 'perf record' option. If <script> has any required args, they
50 should be specified before <command>. This mode doesn't allow for
51 optional script args to be specified; if optional script args are
52 desired, they can be specified using separate 'perf script record'
53 and 'perf script report' commands, with the stdout of the record step
54 piped to the stdin of the report script, using the '-o -' and '-i -'
55 options of the corresponding commands.
56
57 'perf script <top-script>' to both record the events required for
58 <top-script> and to run the <top-script> using 'live-mode'
59 i.e. without writing anything to disk. <top-script> is the name
60 displayed in the output of 'perf script --list' i.e. the actual
61 script name minus any language extension; a <top-script> is defined
62 as any script name ending with the string 'top'.
63
64 [<record-options>] can be passed to the record steps of 'perf script
65 record' and 'live-mode' variants; this isn't possible however for
66 <top-script> 'live-mode' or 'perf script report' variants.
67
68 See the 'SEE ALSO' section for links to language-specific
69 information on how to write and run your own trace scripts.
70
72 <command>...
73 Any command you can specify in a shell.
74
75 -D, --dump-raw-trace=
76 Display verbose dump of the trace data.
77
78 -L, --Latency=
79 Show latency attributes (irqs/preemption disabled, etc).
80
81 -l, --list=
82 Display a list of available trace scripts.
83
84 -s [lang], --script=
85 Process trace data with the given script ([lang]:script[.ext]). If
86 the string lang is specified in place of a script name, a list of
87 supported languages will be displayed instead.
88
89 -g, --gen-script=
90 Generate perf-script.[ext] starter script for given language, using
91 current perf.data.
92
93 -a
94 Force system-wide collection. Scripts run without a <command>
95 normally use -a by default, while scripts run with a <command>
96 normally don’t - this option allows the latter to be run in
97 system-wide mode.
98
99 -i, --input=
100 Input file name. (default: perf.data unless stdin is a fifo)
101
102 -d, --debug-mode
103 Do various checks like samples ordering and lost events.
104
105 -F, --fields
106 Comma separated list of fields to print. Options are: comm, tid,
107 pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline,
108 period, iregs, uregs, brstack, brstacksym, flags, bpf-output,
109 brstackinsn, brstackoff, callindent, insn, insnlen, synth,
110 phys_addr, metric, misc, srccode, ipc. Field list can be prepended
111 with the type, trace, sw or hw, to indicate to which event type the
112 field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F
113 trace:time,cpu,trace
114
115 perf script -F <fields>
116
117 is equivalent to:
118
119 perf script -F trace:<fields> -F sw:<fields> -F hw:<fields>
120
121 i.e., the specified fields apply to all event types if the type string
122 is not given.
123
124 In addition to overriding fields, it is also possible to add or remove
125 fields from the defaults. For example
126
127 -F -cpu,+insn
128
129 removes the cpu field and adds the insn field. Adding/removing fields
130 cannot be mixed with normal overriding.
131
132 The arguments are processed in the order received. A later usage can
133 reset a prior request. e.g.:
134
135 -F trace: -F comm,tid,time,ip,sym
136
137 The first -F suppresses trace events (field list is ""), but then the
138 second invocation sets the fields to comm,tid,time,ip,sym. In this case a
139 warning is given to the user:
140
141 "Overriding previous field request for all events."
142
143 Alternatively, consider the order:
144
145 -F comm,tid,time,ip,sym -F trace:
146
147 The first -F sets the fields for all events and the second -F
148 suppresses trace events. The user is given a warning message about
149 the override, and the result of the above is that only S/W and H/W
150 events are displayed with the given fields.
151
152 It's possible tp add/remove fields only for specific event type:
153
154 -Fsw:-cpu,-period
155
156 removes cpu and period from software events.
157
158 For the 'wildcard' option if a user selected field is invalid for an
159 event type, a message is displayed to the user that the option is
160 ignored for that type. For example:
161
162 $ perf script -F comm,tid,trace
163 'trace' not valid for hardware events. Ignoring.
164 'trace' not valid for software events. Ignoring.
165
166 Alternatively, if the type is given an invalid field is specified it
167 is an error. For example:
168
169 perf script -v -F sw:comm,tid,trace
170 'trace' not valid for software events.
171
172 At this point usage is displayed, and perf-script exits.
173
174 The flags field is synthesized and may have a value when Instruction
175 Trace decoding. The flags are "bcrosyiABEx" which stand for branch,
176 call, return, conditional, system, asynchronous, interrupt,
177 transaction abort, trace begin, trace end, and in transaction,
178 respectively. Known combinations of flags are printed more nicely e.g.
179 "call" for "bc", "return" for "br", "jcc" for "bo", "jmp" for "b",
180 "int" for "bci", "iret" for "bri", "syscall" for "bcs", "sysret" for "brs",
181 "async" for "by", "hw int" for "bcyi", "tx abrt" for "bA", "tr strt" for "bB",
182 "tr end" for "bE". However the "x" flag will be display separately in those
183 cases e.g. "jcc (x)" for a condition branch within a transaction.
184
185 The callindent field is synthesized and may have a value when
186 Instruction Trace decoding. For calls and returns, it will display the
187 name of the symbol indented with spaces to reflect the stack depth.
188
189 When doing instruction trace decoding insn and insnlen give the
190 instruction bytes and the instruction length of the current
191 instruction.
192
193 The synth field is used by synthesized events which may be created when
194 Instruction Trace decoding.
195
196 The ipc (instructions per cycle) field is synthesized and may have a value when
197 Instruction Trace decoding.
198
199 Finally, a user may not set fields to none for all event types.
200 i.e., -F "" is not allowed.
201
202 The brstack output includes branch related information with raw addresses using the
203 /v/v/v/v/cycles syntax in the following order:
204 FROM: branch source instruction
205 TO : branch target instruction
206 M/P/-: M=branch target mispredicted or branch direction was mispredicted, P=target predicted or direction predicted, -=not supported
207 X/- : X=branch inside a transactional region, -=not in transaction region or not supported
208 A/- : A=TSX abort entry, -=not aborted region or not supported
209 cycles
210
211 The brstacksym is identical to brstack, except that the FROM and TO addresses are printed in a symbolic form if possible.
212
213 When brstackinsn is specified the full assembler sequences of branch sequences for each sample
214 is printed. This is the full execution path leading to the sample. This is only supported when the
215 sample was recorded with perf record -b or -j any.
216
217 The brstackoff field will print an offset into a specific dso/binary.
218
219 With the metric option perf script can compute metrics for
220 sampling periods, similar to perf stat. This requires
221 specifying a group with multiple events defining metrics with the :S option
222 for perf record. perf will sample on the first event, and
223 print computed metrics for all the events in the group. Please note
224 that the metric computed is averaged over the whole sampling
225 period (since the last sample), not just for the sample point.
226
227 For sample events it's possible to display misc field with -F +misc option,
228 following letters are displayed for each bit:
229
230 PERF_RECORD_MISC_KERNEL K
231 PERF_RECORD_MISC_USER U
232 PERF_RECORD_MISC_HYPERVISOR H
233 PERF_RECORD_MISC_GUEST_KERNEL G
234 PERF_RECORD_MISC_GUEST_USER g
235 PERF_RECORD_MISC_MMAP_DATA* M
236 PERF_RECORD_MISC_COMM_EXEC E
237 PERF_RECORD_MISC_SWITCH_OUT S
238 PERF_RECORD_MISC_SWITCH_OUT_PREEMPT Sp
239
240 $ perf script -F +misc ...
241 sched-messaging 1414 K 28690.636582: 4590 cycles ...
242 sched-messaging 1407 U 28690.636600: 325620 cycles ...
243 sched-messaging 1414 K 28690.636608: 19473 cycles ...
244 misc field ___________/
245
246 -k, --vmlinux=<file>
247 vmlinux pathname
248
249 --kallsyms=<file>
250 kallsyms pathname
251
252 --symfs=<directory>
253 Look for files with symbols relative to this directory.
254
255 -G, --hide-call-graph
256 When printing symbols do not display call chain.
257
258 --stop-bt
259 Stop display of callgraph at these symbols
260
261 -C, --cpu
262 Only report samples for the list of CPUs provided. Multiple CPUs
263 can be provided as a comma-separated list with no space: 0,1.
264 Ranges of CPUs are specified with -: 0-2. Default is to report
265 samples on all CPUs.
266
267 -c, --comms=
268 Only display events for these comms. CSV that understands
269 file://filename entries.
270
271 --pid=
272 Only show events for given process ID (comma separated list).
273
274 --tid=
275 Only show events for given thread ID (comma separated list).
276
277 -I, --show-info
278 Display extended information about the perf.data file. This adds
279 information which may be very large and thus may clutter the
280 display. It currently includes: cpu and numa topology of the host
281 system. It can only be used with the perf script report mode.
282
283 --show-kernel-path
284 Try to resolve the path of [kernel.kallsyms]
285
286 --show-task-events Display task related events (e.g. FORK, COMM, EXIT).
287
288 --show-mmap-events Display mmap related events (e.g. MMAP, MMAP2).
289
290 --show-namespace-events Display namespace events i.e. events of type
291 PERF_RECORD_NAMESPACES.
292
293 --show-switch-events Display context switch events i.e. events of type
294 PERF_RECORD_SWITCH or PERF_RECORD_SWITCH_CPU_WIDE.
295
296 --show-lost-events Display lost events i.e. events of type
297 PERF_RECORD_LOST.
298
299 --show-round-events Display finished round events i.e. events of type
300 PERF_RECORD_FINISHED_ROUND.
301
302 --show-bpf-events Display bpf events i.e. events of type
303 PERF_RECORD_KSYMBOL and PERF_RECORD_BPF_EVENT.
304
305 --demangle
306 Demangle symbol names to human readable form. It’s enabled by
307 default, disable with --no-demangle.
308
309 --demangle-kernel
310 Demangle kernel symbol names to human readable form (for C++
311 kernels).
312
313 --header Show perf.data header.
314
315 --header-only Show only perf.data header.
316
317 --itrace
318 Options for decoding instruction tracing data. The options are:
319
320 i synthesize instructions events
321 b synthesize branches events
322 c synthesize branches events (calls only)
323 r synthesize branches events (returns only)
324 x synthesize transactions events
325 w synthesize ptwrite events
326 p synthesize power events
327 e synthesize error events
328 d create a debug log
329 g synthesize a call chain (use with i or x)
330 l synthesize last branch entries (use with i or x)
331 s skip initial number of events
332
333 The default is all events i.e. the same as --itrace=ibxwpe,
334 except for perf script where it is --itrace=ce
335
336 In addition, the period (default 100000, except for perf script where it is 1)
337 for instructions events can be specified in units of:
338
339 i instructions
340 t ticks
341 ms milliseconds
342 us microseconds
343 ns nanoseconds (default)
344
345 Also the call chain size (default 16, max. 1024) for instructions or
346 transactions events can be specified.
347
348 Also the number of last branch entries (default 64, max. 1024) for
349 instructions or transactions events can be specified.
350
351 It is also possible to skip events generated (instructions, branches, transactions,
352 ptwrite, power) at the beginning. This is useful to ignore initialization code.
353
354 --itrace=i0nss1000000
355
356 skips the first million instructions.
357
358 To disable decoding entirely, use --no-itrace.
359
360 --full-source-path
361 Show the full path for source files for srcline output.
362
363 --max-stack
364 Set the stack depth limit when parsing the callchain, anything
365 beyond the specified depth will be ignored. This is a trade-off
366 between information loss and faster processing especially for
367 workloads that can have a very long callchain stack. Note that when
368 using the --itrace option the synthesized callchain size will
369 override this value if the synthesized callchain size is bigger.
370
371 Default: 127
372
373 --ns
374 Use 9 decimal places when displaying time (i.e. show the
375 nanoseconds)
376
377 -f, --force
378 Don’t do ownership validation.
379
380 --time
381 Only analyze samples within given time window: <start>,<stop>.
382 Times have the format seconds.nanoseconds. If start is not given
383 (i.e. time string is ,x.y) then analysis starts at the beginning of
384 the file. If stop time is not given (i.e. time string is x.y,) then
385 analysis goes to end of file. Multiple ranges can be separated by
386 spaces, which requires the argument to be quoted e.g. --time
387 "1234.567,1234.789 1235,"
388
389 Also support time percent with multiple time ranges. Time string is
390 'a%/n,b%/m,...' or 'a%-b%,c%-%d,...'.
391
392 For example:
393 Select the second 10% time slice:
394 perf script --time 10%/2
395
396 Select from 0% to 10% time slice:
397 perf script --time 0%-10%
398
399 Select the first and second 10% time slices:
400 perf script --time 10%/1,10%/2
401
402 Select from 0% to 10% and 30% to 40% slices:
403 perf script --time 0%-10%,30%-40%
404
405 --max-blocks
406 Set the maximum number of program blocks to print with brstackinsn
407 for each sample.
408
409 --reltime
410 Print time stamps relative to trace start.
411
412 --per-event-dump
413 Create per event files with a "perf.data.EVENT.dump" name instead
414 of printing to stdout, useful, for instance, for generating
415 flamegraphs.
416
417 --inline
418 If a callgraph address belongs to an inlined function, the inline
419 stack will be printed. Each entry has function name and file/line.
420 Enabled by default, disable with --no-inline.
421
422 --insn-trace
423 Show instruction stream for intel_pt traces. Combine with --xed to
424 show disassembly.
425
426 --xed
427 Run xed disassembler on output. Requires installing the xed
428 disassembler.
429
430 --call-trace
431 Show call stream for intel_pt traces. The CPUs are interleaved, but
432 can be filtered with -C.
433
434 --call-ret-trace
435 Show call and return stream for intel_pt traces.
436
437 --graph-function
438 For itrace only show specified functions and their callees for
439 itrace. Multiple functions can be separated by comma.
440
442 perf-record(1), perf-script-perl(1), perf-script-python(1)
443
444
445
446perf 11/12/2019 PERF-SCRIPT(1)