1 perf-top(1) 1 perf-top(1)
2 =========== 2 ===========
3 3
4 NAME 4 NAME
5 ---- 5 ----
6 perf-top - System profiling tool. 6 perf-top - System profiling tool.
7 7
8 SYNOPSIS 8 SYNOPSIS
9 -------- 9 --------
10 [verse] 10 [verse]
11 'perf top' [-e <EVENT> | --event=EVENT] [<opti 11 'perf top' [-e <EVENT> | --event=EVENT] [<options>]
12 12
13 DESCRIPTION 13 DESCRIPTION
14 ----------- 14 -----------
15 This command generates and displays a performa 15 This command generates and displays a performance counter profile in real time.
16 16
17 17
18 OPTIONS 18 OPTIONS
19 ------- 19 -------
20 -a:: 20 -a::
21 --all-cpus:: 21 --all-cpus::
22 System-wide collection. (default) 22 System-wide collection. (default)
23 23
24 -c <count>:: 24 -c <count>::
25 --count=<count>:: 25 --count=<count>::
26 Event period to sample. 26 Event period to sample.
27 27
28 -C <cpu-list>:: 28 -C <cpu-list>::
29 --cpu=<cpu>:: 29 --cpu=<cpu>::
30 Monitor only on the list of CPUs provided. Mul 30 Monitor only on the list of CPUs provided. Multiple CPUs can be provided as a
31 comma-separated list with no space: 0,1. Range 31 comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
32 Default is to monitor all CPUS. 32 Default is to monitor all CPUS.
33 33
34 -d <seconds>:: 34 -d <seconds>::
35 --delay=<seconds>:: 35 --delay=<seconds>::
36 Number of seconds to delay between ref 36 Number of seconds to delay between refreshes.
37 37
38 -e <event>:: 38 -e <event>::
39 --event=<event>:: 39 --event=<event>::
40 Select the PMU event. Selection can be 40 Select the PMU event. Selection can be a symbolic event name
41 (use 'perf list' to list all events) o 41 (use 'perf list' to list all events) or a raw PMU event in the form
42 of rN where N is a hexadecimal value t 42 of rN where N is a hexadecimal value that represents the raw register
43 encoding with the layout of the event 43 encoding with the layout of the event control registers as described
44 by entries in /sys/bus/event_source/de 44 by entries in /sys/bus/event_source/devices/cpu/format/*.
45 45
46 --filter=<filter>:: <<
47 Event filter. This option should foll <<
48 syntax see linkperf:perf-record[1]. <<
49 <<
50 -E <entries>:: 46 -E <entries>::
51 --entries=<entries>:: 47 --entries=<entries>::
52 Display this many functions. 48 Display this many functions.
53 49
54 -f <count>:: 50 -f <count>::
55 --count-filter=<count>:: 51 --count-filter=<count>::
56 Only display functions with more event 52 Only display functions with more events than this.
57 53
58 --group-sort-idx:: 54 --group-sort-idx::
59 Sort the output by the event at the in 55 Sort the output by the event at the index n in group. If n is invalid,
60 sort by the first event. It can suppor 56 sort by the first event. It can support multiple groups with different
61 amount of events. WARNING: This should 57 amount of events. WARNING: This should be used on grouped events.
62 58
63 -F <freq>:: 59 -F <freq>::
64 --freq=<freq>:: 60 --freq=<freq>::
65 Profile at this frequency. Use 'max' t 61 Profile at this frequency. Use 'max' to use the currently maximum
66 allowed frequency, i.e. the value in t 62 allowed frequency, i.e. the value in the kernel.perf_event_max_sample_rate
67 sysctl. 63 sysctl.
68 64
69 -i:: 65 -i::
70 --inherit:: 66 --inherit::
71 Child tasks do not inherit counters. 67 Child tasks do not inherit counters.
72 68
73 -k <path>:: 69 -k <path>::
74 --vmlinux=<path>:: 70 --vmlinux=<path>::
75 Path to vmlinux. Required for annotat 71 Path to vmlinux. Required for annotation functionality.
76 72
77 --ignore-vmlinux:: 73 --ignore-vmlinux::
78 Ignore vmlinux files. 74 Ignore vmlinux files.
79 75
80 --kallsyms=<file>:: 76 --kallsyms=<file>::
81 kallsyms pathname 77 kallsyms pathname
82 78
83 -m <pages>:: 79 -m <pages>::
84 --mmap-pages=<pages>:: 80 --mmap-pages=<pages>::
85 Number of mmap data pages (must be a p 81 Number of mmap data pages (must be a power of two) or size
86 specification in bytes with appended u !! 82 specification with appended unit character - B/K/M/G. The
87 The size is rounded up to the nearest !! 83 size is rounded up to have nearest pages power of two value.
88 84
89 -p <pid>:: 85 -p <pid>::
90 --pid=<pid>:: 86 --pid=<pid>::
91 Profile events on existing Process ID 87 Profile events on existing Process ID (comma separated list).
92 88
93 -t <tid>:: 89 -t <tid>::
94 --tid=<tid>:: 90 --tid=<tid>::
95 Profile events on existing thread ID ( 91 Profile events on existing thread ID (comma separated list).
96 92
97 -u:: 93 -u::
98 --uid=:: 94 --uid=::
99 Record events in threads owned by uid. 95 Record events in threads owned by uid. Name or number.
100 96
101 -r <priority>:: 97 -r <priority>::
102 --realtime=<priority>:: 98 --realtime=<priority>::
103 Collect data with this RT SCHED_FIFO p 99 Collect data with this RT SCHED_FIFO priority.
104 100
105 --sym-annotate=<symbol>:: 101 --sym-annotate=<symbol>::
106 Annotate this symbol. 102 Annotate this symbol.
107 103
108 -K:: 104 -K::
109 --hide_kernel_symbols:: 105 --hide_kernel_symbols::
110 Hide kernel symbols. 106 Hide kernel symbols.
111 107
112 -U:: 108 -U::
113 --hide_user_symbols:: 109 --hide_user_symbols::
114 Hide user symbols. 110 Hide user symbols.
115 111
116 --demangle-kernel:: 112 --demangle-kernel::
117 Demangle kernel symbols. 113 Demangle kernel symbols.
118 114
119 -D:: 115 -D::
120 --dump-symtab:: 116 --dump-symtab::
121 Dump the symbol table used for profili 117 Dump the symbol table used for profiling.
122 118
123 -v:: 119 -v::
124 --verbose:: 120 --verbose::
125 Be more verbose (show counter open err 121 Be more verbose (show counter open errors, etc).
126 122
127 -z:: 123 -z::
128 --zero:: 124 --zero::
129 Zero history across display updates. 125 Zero history across display updates.
130 126
131 -s:: 127 -s::
132 --sort:: 128 --sort::
133 Sort by key(s): pid, comm, dso, symbol 129 Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight,
134 local_weight, abort, in_tx, transactio 130 local_weight, abort, in_tx, transaction, overhead, sample, period.
135 Please see description of --sort in th 131 Please see description of --sort in the perf-report man page.
136 132
137 --fields=:: 133 --fields=::
138 Specify output field - multiple keys c 134 Specify output field - multiple keys can be specified in CSV format.
139 Following fields are available: 135 Following fields are available:
140 overhead, overhead_sys, overhead_us, o 136 overhead, overhead_sys, overhead_us, overhead_children, sample and period.
141 Also it can contain any sort key(s). 137 Also it can contain any sort key(s).
142 138
143 By default, every sort keys not specif 139 By default, every sort keys not specified in --field will be appended
144 automatically. 140 automatically.
145 141
146 -n:: 142 -n::
147 --show-nr-samples:: 143 --show-nr-samples::
148 Show a column with the number of sampl 144 Show a column with the number of samples.
149 145
150 --show-total-period:: 146 --show-total-period::
151 Show a column with the sum of periods. 147 Show a column with the sum of periods.
152 148
153 --dsos:: 149 --dsos::
154 Only consider symbols in these dsos. 150 Only consider symbols in these dsos. This option will affect the
155 percentage of the overhead column. Se 151 percentage of the overhead column. See --percentage for more info.
156 152
157 --comms:: 153 --comms::
158 Only consider symbols in these comms. 154 Only consider symbols in these comms. This option will affect the
159 percentage of the overhead column. Se 155 percentage of the overhead column. See --percentage for more info.
160 156
161 --symbols:: 157 --symbols::
162 Only consider these symbols. This opt 158 Only consider these symbols. This option will affect the
163 percentage of the overhead column. Se 159 percentage of the overhead column. See --percentage for more info.
164 160
165 -M:: 161 -M::
166 --disassembler-style=:: Set disassembler style 162 --disassembler-style=:: Set disassembler style for objdump.
167 163
168 --addr2line=<path>:: <<
169 Path to addr2line binary. <<
170 <<
171 --objdump=<path>:: <<
172 Path to objdump binary. <<
173 <<
174 --prefix=PREFIX:: 164 --prefix=PREFIX::
175 --prefix-strip=N:: 165 --prefix-strip=N::
176 Remove first N entries from source fil 166 Remove first N entries from source file path names in executables
177 and add PREFIX. This allows to display 167 and add PREFIX. This allows to display source code compiled on systems
178 with different file system layout. 168 with different file system layout.
179 169
180 --source:: 170 --source::
181 Interleave source code with assembly c 171 Interleave source code with assembly code. Enabled by default,
182 disable with --no-source. 172 disable with --no-source.
183 173
184 --asm-raw:: 174 --asm-raw::
185 Show raw instruction encoding of assem 175 Show raw instruction encoding of assembly instructions.
186 176
187 -g:: 177 -g::
188 Enables call-graph (stack chain/backtr 178 Enables call-graph (stack chain/backtrace) recording.
189 179
190 --call-graph [mode,type,min[,limit],order[,key 180 --call-graph [mode,type,min[,limit],order[,key][,branch]]::
191 Setup and enable call-graph (stack cha 181 Setup and enable call-graph (stack chain/backtrace) recording,
192 implies -g. See `--call-graph` sectio 182 implies -g. See `--call-graph` section in perf-record and
193 perf-report man pages for details. 183 perf-report man pages for details.
194 184
195 --children:: 185 --children::
196 Accumulate callchain of children to pa 186 Accumulate callchain of children to parent entry so that then can
197 show up in the output. The output wil 187 show up in the output. The output will have a new "Children" column
198 and will be sorted on the data. It re 188 and will be sorted on the data. It requires -g/--call-graph option
199 enabled. See the `overhead calculatio 189 enabled. See the `overhead calculation' section for more details.
200 Enabled by default, disable with --no- 190 Enabled by default, disable with --no-children.
201 191
202 --max-stack:: 192 --max-stack::
203 Set the stack depth limit when parsing 193 Set the stack depth limit when parsing the callchain, anything
204 beyond the specified depth will be ign 194 beyond the specified depth will be ignored. This is a trade-off
205 between information loss and faster pr 195 between information loss and faster processing especially for
206 workloads that can have a very long ca 196 workloads that can have a very long callchain stack.
207 197
208 Default: /proc/sys/kernel/perf_event_m 198 Default: /proc/sys/kernel/perf_event_max_stack when present, 127 otherwise.
209 199
210 --ignore-callees=<regex>:: 200 --ignore-callees=<regex>::
211 Ignore callees of the function(s) matc 201 Ignore callees of the function(s) matching the given regex.
212 This has the effect of collecting the 202 This has the effect of collecting the callers of each such
213 function into one place in the call-gr 203 function into one place in the call-graph tree.
214 204
215 --percent-limit:: 205 --percent-limit::
216 Do not show entries which have an over 206 Do not show entries which have an overhead under that percent.
217 (Default: 0). 207 (Default: 0).
218 208
219 --percentage:: 209 --percentage::
220 Determine how to display the overhead 210 Determine how to display the overhead percentage of filtered entries.
221 Filters can be applied by --comms, --d 211 Filters can be applied by --comms, --dsos and/or --symbols options and
222 Zoom operations on the TUI (thread, ds 212 Zoom operations on the TUI (thread, dso, etc).
223 213
224 "relative" means it's relative to filt 214 "relative" means it's relative to filtered entries only so that the
225 sum of shown entries will be always 10 215 sum of shown entries will be always 100%. "absolute" means it retains
226 the original value before and after th 216 the original value before and after the filter is applied.
227 217
228 -w:: 218 -w::
229 --column-widths=<width[,width...]>:: 219 --column-widths=<width[,width...]>::
230 Force each column width to the provide 220 Force each column width to the provided list, for large terminal
231 readability. 0 means no limit (defaul 221 readability. 0 means no limit (default behavior).
232 222
233 --proc-map-timeout:: 223 --proc-map-timeout::
234 When processing pre-existing threads / 224 When processing pre-existing threads /proc/XXX/mmap, it may take
235 a long time, because the file may be h 225 a long time, because the file may be huge. A time out is needed
236 in such cases. 226 in such cases.
237 This option sets the time out limit. T 227 This option sets the time out limit. The default value is 500 ms.
238 228
239 229
240 -b:: 230 -b::
241 --branch-any:: 231 --branch-any::
242 Enable taken branch stack sampling. An 232 Enable taken branch stack sampling. Any type of taken branch may be sampled.
243 This is a shortcut for --branch-filter 233 This is a shortcut for --branch-filter any. See --branch-filter for more infos.
244 234
245 -j:: 235 -j::
246 --branch-filter:: 236 --branch-filter::
247 Enable taken branch stack sampling. Ea 237 Enable taken branch stack sampling. Each sample captures a series of consecutive
248 taken branches. The number of branches 238 taken branches. The number of branches captured with each sample depends on the
249 underlying hardware, the type of branc 239 underlying hardware, the type of branches of interest, and the executed code.
250 It is possible to select the types of 240 It is possible to select the types of branches captured by enabling filters.
251 For a full list of modifiers please se 241 For a full list of modifiers please see the perf record manpage.
252 242
253 The option requires at least one branc 243 The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
254 The privilege levels may be omitted, i 244 The privilege levels may be omitted, in which case, the privilege levels of the associated
255 event are applied to the branch filter 245 event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege
256 levels are subject to permissions. Wh 246 levels are subject to permissions. When sampling on multiple events, branch stack sampling
257 is enabled for all the sampling events 247 is enabled for all the sampling events. The sampled branch type is the same for all events.
258 The various filters must be specified 248 The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
259 Note that this feature may not be avai 249 Note that this feature may not be available on all processors.
260 250
261 --branch-history:: <<
262 Add the addresses of sampled taken bra <<
263 This allows to examine the path the pr <<
264 <<
265 --raw-trace:: 251 --raw-trace::
266 When displaying traceevent output, do 252 When displaying traceevent output, do not use print fmt or plugins.
267 253
268 -H:: <<
269 --hierarchy:: 254 --hierarchy::
270 Enable hierarchical output. In the hi !! 255 Enable hierarchy output.
271 samples based on the criteria and then <<
272 level sort key. <<
273 <<
274 For example, in normal output: <<
275 <<
276 perf report -s dso,sym <<
277 # <<
278 # Overhead Shared Object Symbo <<
279 # ........ ................. ..... <<
280 50.00% [kernel.kallsyms] [k] k <<
281 20.00% perf [.] f <<
282 15.00% [kernel.kallsyms] [k] k <<
283 10.00% perf [.] b <<
284 5.00% libc.so [.] l <<
285 <<
286 In hierarchy output: <<
287 <<
288 perf report -s dso,sym --hierarchy <<
289 # <<
290 # Overhead Shared Object / Symbol <<
291 # .......... ...................... <<
292 65.00% [kernel.kallsyms] <<
293 50.00% [k] kfunc1 <<
294 15.00% [k] kfunc2 <<
295 30.00% perf <<
296 20.00% [.] foo <<
297 10.00% [.] bar <<
298 5.00% libc.so <<
299 5.00% [.] libcall <<
300 256
301 --overwrite:: 257 --overwrite::
302 Enable this to use just the most recen 258 Enable this to use just the most recent records, which helps in high core count
303 machines such as Knights Landing/Mill, 259 machines such as Knights Landing/Mill, but right now is disabled by default as
304 the pausing used in this technique is 260 the pausing used in this technique is leading to loss of metadata events such
305 as PERF_RECORD_MMAP which makes 'perf 261 as PERF_RECORD_MMAP which makes 'perf top' unable to resolve samples, leading
306 to lots of unknown samples appearing o 262 to lots of unknown samples appearing on the UI. Enable this if you are in such
307 machines and profiling a workload that 263 machines and profiling a workload that doesn't creates short lived threads and/or
308 doesn't uses many executable mmap oper 264 doesn't uses many executable mmap operations. Work is being planed to solve
309 this situation, till then, this will r 265 this situation, till then, this will remain disabled by default.
310 266
311 --force:: 267 --force::
312 Don't do ownership validation. 268 Don't do ownership validation.
313 269
314 --num-thread-synthesize:: 270 --num-thread-synthesize::
315 The number of threads to run when synt 271 The number of threads to run when synthesizing events for existing processes.
316 By default, the number of threads equa 272 By default, the number of threads equals to the number of online CPUs.
317 273
318 --namespaces:: 274 --namespaces::
319 Record events of type PERF_RECORD_NAME 275 Record events of type PERF_RECORD_NAMESPACES and display it with the
320 'cgroup_id' sort key. 276 'cgroup_id' sort key.
321 277
322 -G name:: 278 -G name::
323 --cgroup name:: 279 --cgroup name::
324 monitor only in the container (cgroup) called 280 monitor only in the container (cgroup) called "name". This option is available only
325 in per-cpu mode. The cgroup filesystem must be 281 in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
326 container "name" are monitored when they run o 282 container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
327 can be provided. Each cgroup is applied to the 283 can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
328 to first event, second cgroup to second event 284 to first event, second cgroup to second event and so on. It is possible to provide
329 an empty cgroup (monitor all the time) using, 285 an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
330 corresponding events, i.e., they always refer 286 corresponding events, i.e., they always refer to events defined earlier on the command
331 line. If the user wants to track multiple even 287 line. If the user wants to track multiple events for a specific cgroup, the user can
332 use '-e e1 -e e2 -G foo,foo' or just use '-e e 288 use '-e e1 -e e2 -G foo,foo' or just use '-e e1 -e e2 -G foo'.
333 289
334 --all-cgroups:: 290 --all-cgroups::
335 Record events of type PERF_RECORD_CGRO 291 Record events of type PERF_RECORD_CGROUP and display it with the
336 'cgroup' sort key. 292 'cgroup' sort key.
337 293
338 --switch-on EVENT_NAME:: 294 --switch-on EVENT_NAME::
339 Only consider events after this event 295 Only consider events after this event is found.
340 296
341 E.g.: 297 E.g.:
342 298
343 Find out where broadcast packets ar 299 Find out where broadcast packets are handled
344 300
345 perf probe -L icmp_rcv 301 perf probe -L icmp_rcv
346 302
347 Insert a probe there: 303 Insert a probe there:
348 304
349 perf probe icmp_rcv:59 305 perf probe icmp_rcv:59
350 306
351 Start perf top and ask it to only c 307 Start perf top and ask it to only consider the cycles events when a
352 broadcast packet arrives This will 308 broadcast packet arrives This will show a menu with two entries and
353 will start counting when a broadcas 309 will start counting when a broadcast packet arrives:
354 310
355 perf top -e cycles,probe:icmp_ 311 perf top -e cycles,probe:icmp_rcv --switch-on=probe:icmp_rcv
356 312
357 Alternatively one can ask for a gro 313 Alternatively one can ask for a group and then two overhead columns
358 will appear, the first for cycles a 314 will appear, the first for cycles and the second for the switch-on event.
359 315
360 perf top -e '{cycles,probe:icm 316 perf top -e '{cycles,probe:icmp_rcv}' --switch-on=probe:icmp_rcv
361 317
362 This may be interesting to measure a w 318 This may be interesting to measure a workload only after some initialization
363 phase is over, i.e. insert a perf prob 319 phase is over, i.e. insert a perf probe at that point and use the above
364 examples replacing probe:icmp_rcv with 320 examples replacing probe:icmp_rcv with the just-after-init probe.
365 321
366 --switch-off EVENT_NAME:: 322 --switch-off EVENT_NAME::
367 Stop considering events after this eve 323 Stop considering events after this event is found.
368 324
369 --show-on-off-events:: 325 --show-on-off-events::
370 Show the --switch-on/off events too. T 326 Show the --switch-on/off events too. This has no effect in 'perf top' now
371 but probably we'll make the default no 327 but probably we'll make the default not to show the switch-on/off events
372 on the --group mode and if there is on 328 on the --group mode and if there is only one event besides the off/on ones,
373 go straight to the histogram browser, 329 go straight to the histogram browser, just like 'perf top' with no events
374 explicitly specified does. 330 explicitly specified does.
375 331
376 --stitch-lbr:: 332 --stitch-lbr::
377 Show callgraph with stitched LBRs, whi 333 Show callgraph with stitched LBRs, which may have more complete
378 callgraph. The option must be used wit 334 callgraph. The option must be used with --call-graph lbr recording.
379 Disabled by default. In common cases w 335 Disabled by default. In common cases with call stack overflows,
380 it can recreate better call stacks tha 336 it can recreate better call stacks than the default lbr call stack
381 output. But this approach is not foolp 337 output. But this approach is not foolproof. There can be cases
382 where it creates incorrect call stacks 338 where it creates incorrect call stacks from incorrect matches.
383 The known limitations include exceptio 339 The known limitations include exception handing such as
384 setjmp/longjmp will have calls/returns 340 setjmp/longjmp will have calls/returns not match.
385 341
386 ifdef::HAVE_LIBPFM[] 342 ifdef::HAVE_LIBPFM[]
387 --pfm-events events:: 343 --pfm-events events::
388 Select a PMU event using libpfm4 syntax (see h 344 Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net)
389 including support for event filters. For examp 345 including support for event filters. For example '--pfm-events
390 inst_retired:any_p:u:c=1:i'. More than one eve 346 inst_retired:any_p:u:c=1:i'. More than one event can be passed to the
391 option using the comma separator. Hardware eve 347 option using the comma separator. Hardware events and generic hardware
392 events cannot be mixed together. The latter mu 348 events cannot be mixed together. The latter must be used with the -e
393 option. The -e option and this one can be mixe 349 option. The -e option and this one can be mixed and matched. Events
394 can be grouped using the {} notation. 350 can be grouped using the {} notation.
395 endif::HAVE_LIBPFM[] 351 endif::HAVE_LIBPFM[]
396 352
397 INTERACTIVE PROMPTING KEYS 353 INTERACTIVE PROMPTING KEYS
398 -------------------------- 354 --------------------------
399 355
400 [d]:: 356 [d]::
401 Display refresh delay. 357 Display refresh delay.
402 358
403 [e]:: 359 [e]::
404 Number of entries to display. 360 Number of entries to display.
405 361
406 [E]:: 362 [E]::
407 Event to display when multiple counter 363 Event to display when multiple counters are active.
408 364
409 [f]:: 365 [f]::
410 Profile display filter (>= hit count). 366 Profile display filter (>= hit count).
411 367
412 [F]:: 368 [F]::
413 Annotation display filter (>= % of tot 369 Annotation display filter (>= % of total).
414 370
415 [s]:: 371 [s]::
416 Annotate symbol. 372 Annotate symbol.
417 373
418 [S]:: 374 [S]::
419 Stop annotation, return to full profil 375 Stop annotation, return to full profile display.
420 376
421 [K]:: 377 [K]::
422 Hide kernel symbols. 378 Hide kernel symbols.
423 379
424 [U]:: 380 [U]::
425 Hide user symbols. 381 Hide user symbols.
426 382
427 [z]:: 383 [z]::
428 Toggle event count zeroing across disp 384 Toggle event count zeroing across display updates.
429 385
430 [qQ]:: 386 [qQ]::
431 Quit. 387 Quit.
432 388
433 Pressing any unmapped key displays a menu, and 389 Pressing any unmapped key displays a menu, and prompts for input.
434 390
435 include::callchain-overhead-calculation.txt[] 391 include::callchain-overhead-calculation.txt[]
436 392
437 SEE ALSO 393 SEE ALSO
438 -------- 394 --------
439 linkperf:perf-stat[1], linkperf:perf-list[1], 395 linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-report[1]
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.