Loading...
1perf-report(1)
2==============
3
4NAME
5----
6perf-report - Read perf.data (created by perf record) and display the profile
7
8SYNOPSIS
9--------
10[verse]
11'perf report' [-i <file> | --input=file]
12
13DESCRIPTION
14-----------
15This command displays the performance counter profile information recorded
16via perf record.
17
18OPTIONS
19-------
20-i::
21--input=::
22 Input file name. (default: perf.data unless stdin is a fifo)
23
24-v::
25--verbose::
26 Be more verbose. (show symbol address, etc)
27
28-d::
29--dsos=::
30 Only consider symbols in these dsos. CSV that understands
31 file://filename entries.
32-n::
33--show-nr-samples::
34 Show the number of samples for each symbol
35
36--showcpuutilization::
37 Show sample percentage for different cpu modes.
38
39-T::
40--threads::
41 Show per-thread event counters
42-c::
43--comms=::
44 Only consider symbols in these comms. CSV that understands
45 file://filename entries.
46-S::
47--symbols=::
48 Only consider these symbols. CSV that understands
49 file://filename entries.
50
51--symbol-filter=::
52 Only show symbols that match (partially) with this filter.
53
54-U::
55--hide-unresolved::
56 Only display entries resolved to a symbol.
57
58-s::
59--sort=::
60 Sort by key(s): pid, comm, dso, symbol, parent.
61
62-p::
63--parent=<regex>::
64 regex filter to identify parent, see: '--sort parent'
65
66-x::
67--exclude-other::
68 Only display entries with parent-match.
69
70-w::
71--column-widths=<width[,width...]>::
72 Force each column width to the provided list, for large terminal
73 readability.
74
75-t::
76--field-separator=::
77
78 Use a special separator character and don't pad with spaces, replacing
79 all occurrences of this separator in symbol names (and other output)
80 with a '.' character, that thus it's the only non valid separator.
81
82-D::
83--dump-raw-trace::
84 Dump raw trace in ASCII.
85
86-g [type,min[,limit],order]::
87--call-graph::
88 Display call chains using type, min percent threshold, optional print
89 limit and order.
90 type can be either:
91 - flat: single column, linear exposure of call chains.
92 - graph: use a graph tree, displaying absolute overhead rates.
93 - fractal: like graph, but displays relative rates. Each branch of
94 the tree is considered as a new profiled object. +
95
96 order can be either:
97 - callee: callee based call graph.
98 - caller: inverted caller based call graph.
99
100 Default: fractal,0.5,callee.
101
102-G::
103--inverted::
104 alias for inverted caller based call graph.
105
106--pretty=<key>::
107 Pretty printing style. key: normal, raw
108
109--stdio:: Use the stdio interface.
110
111--tui:: Use the TUI interface, that is integrated with annotate and allows
112 zooming into DSOs or threads, among other features. Use of --tui
113 requires a tty, if one is not present, as when piping to other
114 commands, the stdio interface is used.
115
116--gtk:: Use the GTK2 interface.
117
118-k::
119--vmlinux=<file>::
120 vmlinux pathname
121
122--kallsyms=<file>::
123 kallsyms pathname
124
125-m::
126--modules::
127 Load module symbols. WARNING: This should only be used with -k and
128 a LIVE kernel.
129
130-f::
131--force::
132 Don't complain, do it.
133
134--symfs=<directory>::
135 Look for files with symbols relative to this directory.
136
137-C::
138--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
139 be provided as a comma-separated list with no space: 0,1. Ranges of
140 CPUs are specified with -: 0-2. Default is to report samples on all
141 CPUs.
142
143-M::
144--disassembler-style=:: Set disassembler style for objdump.
145
146--source::
147 Interleave source code with assembly code. Enabled by default,
148 disable with --no-source.
149
150--asm-raw::
151 Show raw instruction encoding of assembly instructions.
152
153--show-total-period:: Show a column with the sum of periods.
154
155-I::
156--show-info::
157 Display extended information about the perf.data file. This adds
158 information which may be very large and thus may clutter the display.
159 It currently includes: cpu and numa topology of the host system.
160
161-b::
162--branch-stack::
163 Use the addresses of sampled taken branches instead of the instruction
164 address to build the histograms. To generate meaningful output, the
165 perf.data file must have been obtained using perf record -b or
166 perf record --branch-filter xxx where xxx is a branch filter option.
167 perf report is able to auto-detect whether a perf.data file contains
168 branch stacks and it will automatically switch to the branch view mode,
169 unless --no-branch-stack is used.
170
171SEE ALSO
172--------
173linkperf:perf-stat[1], linkperf:perf-annotate[1]
1perf-report(1)
2==============
3
4NAME
5----
6perf-report - Read perf.data (created by perf record) and display the profile
7
8SYNOPSIS
9--------
10[verse]
11'perf report' [-i <file> | --input=file]
12
13DESCRIPTION
14-----------
15This command displays the performance counter profile information recorded
16via perf record.
17
18OPTIONS
19-------
20-i::
21--input=::
22 Input file name. (default: perf.data unless stdin is a fifo)
23
24-v::
25--verbose::
26 Be more verbose. (show symbol address, etc)
27
28-n::
29--show-nr-samples::
30 Show the number of samples for each symbol
31
32--show-cpu-utilization::
33 Show sample percentage for different cpu modes.
34
35-T::
36--threads::
37 Show per-thread event counters. The input data file should be recorded
38 with -s option.
39-c::
40--comms=::
41 Only consider symbols in these comms. CSV that understands
42 file://filename entries. This option will affect the percentage of
43 the overhead column. See --percentage for more info.
44--pid=::
45 Only show events for given process ID (comma separated list).
46
47--tid=::
48 Only show events for given thread ID (comma separated list).
49-d::
50--dsos=::
51 Only consider symbols in these dsos. CSV that understands
52 file://filename entries. This option will affect the percentage of
53 the overhead column. See --percentage for more info.
54-S::
55--symbols=::
56 Only consider these symbols. CSV that understands
57 file://filename entries. This option will affect the percentage of
58 the overhead column. See --percentage for more info.
59
60--symbol-filter=::
61 Only show symbols that match (partially) with this filter.
62
63-U::
64--hide-unresolved::
65 Only display entries resolved to a symbol.
66
67-s::
68--sort=::
69 Sort histogram entries by given key(s) - multiple keys can be specified
70 in CSV format. Following sort keys are available:
71 pid, comm, dso, symbol, parent, cpu, socket, srcline, weight, local_weight.
72
73 Each key has following meaning:
74
75 - comm: command (name) of the task which can be read via /proc/<pid>/comm
76 - pid: command and tid of the task
77 - dso: name of library or module executed at the time of sample
78 - symbol: name of function executed at the time of sample
79 - parent: name of function matched to the parent regex filter. Unmatched
80 entries are displayed as "[other]".
81 - cpu: cpu number the task ran at the time of sample
82 - socket: processor socket number the task ran at the time of sample
83 - srcline: filename and line number executed at the time of sample. The
84 DWARF debugging info must be provided.
85 - srcfile: file name of the source file of the same. Requires dwarf
86 information.
87 - weight: Event specific weight, e.g. memory latency or transaction
88 abort cost. This is the global weight.
89 - local_weight: Local weight version of the weight above.
90 - transaction: Transaction abort flags.
91 - overhead: Overhead percentage of sample
92 - overhead_sys: Overhead percentage of sample running in system mode
93 - overhead_us: Overhead percentage of sample running in user mode
94 - overhead_guest_sys: Overhead percentage of sample running in system mode
95 on guest machine
96 - overhead_guest_us: Overhead percentage of sample running in user mode on
97 guest machine
98 - sample: Number of sample
99 - period: Raw number of event count of sample
100
101 By default, comm, dso and symbol keys are used.
102 (i.e. --sort comm,dso,symbol)
103
104 If --branch-stack option is used, following sort keys are also
105 available:
106
107 - dso_from: name of library or module branched from
108 - dso_to: name of library or module branched to
109 - symbol_from: name of function branched from
110 - symbol_to: name of function branched to
111 - srcline_from: source file and line branched from
112 - srcline_to: source file and line branched to
113 - mispredict: "N" for predicted branch, "Y" for mispredicted branch
114 - in_tx: branch in TSX transaction
115 - abort: TSX transaction abort.
116 - cycles: Cycles in basic block
117
118 And default sort keys are changed to comm, dso_from, symbol_from, dso_to
119 and symbol_to, see '--branch-stack'.
120
121 If the --mem-mode option is used, the following sort keys are also available
122 (incompatible with --branch-stack):
123 symbol_daddr, dso_daddr, locked, tlb, mem, snoop, dcacheline.
124
125 - symbol_daddr: name of data symbol being executed on at the time of sample
126 - dso_daddr: name of library or module containing the data being executed
127 on at the time of the sample
128 - locked: whether the bus was locked at the time of the sample
129 - tlb: type of tlb access for the data at the time of the sample
130 - mem: type of memory access for the data at the time of the sample
131 - snoop: type of snoop (if any) for the data at the time of the sample
132 - dcacheline: the cacheline the data address is on at the time of the sample
133
134 And the default sort keys are changed to local_weight, mem, sym, dso,
135 symbol_daddr, dso_daddr, snoop, tlb, locked, see '--mem-mode'.
136
137 If the data file has tracepoint event(s), following (dynamic) sort keys
138 are also available:
139 trace, trace_fields, [<event>.]<field>[/raw]
140
141 - trace: pretty printed trace output in a single column
142 - trace_fields: fields in tracepoints in separate columns
143 - <field name>: optional event and field name for a specific field
144
145 The last form consists of event and field names. If event name is
146 omitted, it searches all events for matching field name. The matched
147 field will be shown only for the event has the field. The event name
148 supports substring match so user doesn't need to specify full subsystem
149 and event name everytime. For example, 'sched:sched_switch' event can
150 be shortened to 'switch' as long as it's not ambiguous. Also event can
151 be specified by its index (starting from 1) preceded by the '%'.
152 So '%1' is the first event, '%2' is the second, and so on.
153
154 The field name can have '/raw' suffix which disables pretty printing
155 and shows raw field value like hex numbers. The --raw-trace option
156 has the same effect for all dynamic sort keys.
157
158 The default sort keys are changed to 'trace' if all events in the data
159 file are tracepoint.
160
161-F::
162--fields=::
163 Specify output field - multiple keys can be specified in CSV format.
164 Following fields are available:
165 overhead, overhead_sys, overhead_us, overhead_children, sample and period.
166 Also it can contain any sort key(s).
167
168 By default, every sort keys not specified in -F will be appended
169 automatically.
170
171-p::
172--parent=<regex>::
173 A regex filter to identify parent. The parent is a caller of this
174 function and searched through the callchain, thus it requires callchain
175 information recorded. The pattern is in the exteneded regex format and
176 defaults to "\^sys_|^do_page_fault", see '--sort parent'.
177
178-x::
179--exclude-other::
180 Only display entries with parent-match.
181
182-w::
183--column-widths=<width[,width...]>::
184 Force each column width to the provided list, for large terminal
185 readability. 0 means no limit (default behavior).
186
187-t::
188--field-separator=::
189 Use a special separator character and don't pad with spaces, replacing
190 all occurrences of this separator in symbol names (and other output)
191 with a '.' character, that thus it's the only non valid separator.
192
193-D::
194--dump-raw-trace::
195 Dump raw trace in ASCII.
196
197-g::
198--call-graph=<print_type,threshold[,print_limit],order,sort_key[,branch],value>::
199 Display call chains using type, min percent threshold, print limit,
200 call order, sort key, optional branch and value. Note that ordering of
201 parameters is not fixed so any parement can be given in an arbitraty order.
202 One exception is the print_limit which should be preceded by threshold.
203
204 print_type can be either:
205 - flat: single column, linear exposure of call chains.
206 - graph: use a graph tree, displaying absolute overhead rates. (default)
207 - fractal: like graph, but displays relative rates. Each branch of
208 the tree is considered as a new profiled object.
209 - folded: call chains are displayed in a line, separated by semicolons
210 - none: disable call chain display.
211
212 threshold is a percentage value which specifies a minimum percent to be
213 included in the output call graph. Default is 0.5 (%).
214
215 print_limit is only applied when stdio interface is used. It's to limit
216 number of call graph entries in a single hist entry. Note that it needs
217 to be given after threshold (but not necessarily consecutive).
218 Default is 0 (unlimited).
219
220 order can be either:
221 - callee: callee based call graph.
222 - caller: inverted caller based call graph.
223 Default is 'caller' when --children is used, otherwise 'callee'.
224
225 sort_key can be:
226 - function: compare on functions (default)
227 - address: compare on individual code addresses
228
229 branch can be:
230 - branch: include last branch information in callgraph when available.
231 Usually more convenient to use --branch-history for this.
232
233 value can be:
234 - percent: diplay overhead percent (default)
235 - period: display event period
236 - count: display event count
237
238--children::
239 Accumulate callchain of children to parent entry so that then can
240 show up in the output. The output will have a new "Children" column
241 and will be sorted on the data. It requires callchains are recorded.
242 See the `overhead calculation' section for more details. Enabled by
243 default, disable with --no-children.
244
245--max-stack::
246 Set the stack depth limit when parsing the callchain, anything
247 beyond the specified depth will be ignored. This is a trade-off
248 between information loss and faster processing especially for
249 workloads that can have a very long callchain stack.
250 Note that when using the --itrace option the synthesized callchain size
251 will override this value if the synthesized callchain size is bigger.
252
253 Default: 127
254
255-G::
256--inverted::
257 alias for inverted caller based call graph.
258
259--ignore-callees=<regex>::
260 Ignore callees of the function(s) matching the given regex.
261 This has the effect of collecting the callers of each such
262 function into one place in the call-graph tree.
263
264--pretty=<key>::
265 Pretty printing style. key: normal, raw
266
267--stdio:: Use the stdio interface.
268
269--stdio-color::
270 'always', 'never' or 'auto', allowing configuring color output
271 via the command line, in addition to via "color.ui" .perfconfig.
272 Use '--stdio-color always' to generate color even when redirecting
273 to a pipe or file. Using just '--stdio-color' is equivalent to
274 using 'always'.
275
276--tui:: Use the TUI interface, that is integrated with annotate and allows
277 zooming into DSOs or threads, among other features. Use of --tui
278 requires a tty, if one is not present, as when piping to other
279 commands, the stdio interface is used.
280
281--gtk:: Use the GTK2 interface.
282
283-k::
284--vmlinux=<file>::
285 vmlinux pathname
286
287--kallsyms=<file>::
288 kallsyms pathname
289
290-m::
291--modules::
292 Load module symbols. WARNING: This should only be used with -k and
293 a LIVE kernel.
294
295-f::
296--force::
297 Don't do ownership validation.
298
299--symfs=<directory>::
300 Look for files with symbols relative to this directory.
301
302-C::
303--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
304 be provided as a comma-separated list with no space: 0,1. Ranges of
305 CPUs are specified with -: 0-2. Default is to report samples on all
306 CPUs.
307
308-M::
309--disassembler-style=:: Set disassembler style for objdump.
310
311--source::
312 Interleave source code with assembly code. Enabled by default,
313 disable with --no-source.
314
315--asm-raw::
316 Show raw instruction encoding of assembly instructions.
317
318--show-total-period:: Show a column with the sum of periods.
319
320-I::
321--show-info::
322 Display extended information about the perf.data file. This adds
323 information which may be very large and thus may clutter the display.
324 It currently includes: cpu and numa topology of the host system.
325
326-b::
327--branch-stack::
328 Use the addresses of sampled taken branches instead of the instruction
329 address to build the histograms. To generate meaningful output, the
330 perf.data file must have been obtained using perf record -b or
331 perf record --branch-filter xxx where xxx is a branch filter option.
332 perf report is able to auto-detect whether a perf.data file contains
333 branch stacks and it will automatically switch to the branch view mode,
334 unless --no-branch-stack is used.
335
336--branch-history::
337 Add the addresses of sampled taken branches to the callstack.
338 This allows to examine the path the program took to each sample.
339 The data collection must have used -b (or -j) and -g.
340
341--objdump=<path>::
342 Path to objdump binary.
343
344--group::
345 Show event group information together.
346
347--demangle::
348 Demangle symbol names to human readable form. It's enabled by default,
349 disable with --no-demangle.
350
351--demangle-kernel::
352 Demangle kernel symbol names to human readable form (for C++ kernels).
353
354--mem-mode::
355 Use the data addresses of samples in addition to instruction addresses
356 to build the histograms. To generate meaningful output, the perf.data
357 file must have been obtained using perf record -d -W and using a
358 special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See
359 'perf mem' for simpler access.
360
361--percent-limit::
362 Do not show entries which have an overhead under that percent.
363 (Default: 0). Note that this option also sets the percent limit (threshold)
364 of callchains. However the default value of callchain threshold is
365 different than the default value of hist entries. Please see the
366 --call-graph option for details.
367
368--percentage::
369 Determine how to display the overhead percentage of filtered entries.
370 Filters can be applied by --comms, --dsos and/or --symbols options and
371 Zoom operations on the TUI (thread, dso, etc).
372
373 "relative" means it's relative to filtered entries only so that the
374 sum of shown entries will be always 100%. "absolute" means it retains
375 the original value before and after the filter is applied.
376
377--header::
378 Show header information in the perf.data file. This includes
379 various information like hostname, OS and perf version, cpu/mem
380 info, perf command line, event list and so on. Currently only
381 --stdio output supports this feature.
382
383--header-only::
384 Show only perf.data header (forces --stdio).
385
386--time::
387 Only analyze samples within given time window: <start>,<stop>. Times
388 have the format seconds.microseconds. If start is not given (i.e., time
389 string is ',x.y') then analysis starts at the beginning of the file. If
390 stop time is not given (i.e, time string is 'x.y,') then analysis goes
391 to end of file.
392
393--itrace::
394 Options for decoding instruction tracing data. The options are:
395
396include::itrace.txt[]
397
398 To disable decoding entirely, use --no-itrace.
399
400--full-source-path::
401 Show the full path for source files for srcline output.
402
403--show-ref-call-graph::
404 When multiple events are sampled, it may not be needed to collect
405 callgraphs for all of them. The sample sites are usually nearby,
406 and it's enough to collect the callgraphs on a reference event.
407 So user can use "call-graph=no" event modifier to disable callgraph
408 for other events to reduce the overhead.
409 However, perf report cannot show callgraphs for the event which
410 disable the callgraph.
411 This option extends the perf report to show reference callgraphs,
412 which collected by reference event, in no callgraph event.
413
414--socket-filter::
415 Only report the samples on the processor socket that match with this filter
416
417--raw-trace::
418 When displaying traceevent output, do not use print fmt or plugins.
419
420--hierarchy::
421 Enable hierarchical output.
422
423include::callchain-overhead-calculation.txt[]
424
425SEE ALSO
426--------
427linkperf:perf-stat[1], linkperf:perf-annotate[1]