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