Loading...
1perf-trace(1)
2=============
3
4NAME
5----
6perf-trace - strace inspired tool
7
8SYNOPSIS
9--------
10[verse]
11'perf trace'
12'perf trace record'
13
14DESCRIPTION
15-----------
16This command will show the events associated with the target, initially
17syscalls, but other system events like pagefaults, task lifetime events,
18scheduling events, etc.
19
20This is a live mode tool in addition to working with perf.data files like
21the other perf tools. Files can be generated using the 'perf record' command
22but the session needs to include the raw_syscalls events (-e 'raw_syscalls:*').
23Alternatively, 'perf trace record' can be used as a shortcut to
24automatically include the raw_syscalls events when writing events to a file.
25
26The following options apply to perf trace; options to perf trace record are
27found in the perf record man page.
28
29OPTIONS
30-------
31
32-a::
33--all-cpus::
34 System-wide collection from all CPUs.
35
36-e::
37--expr::
38--event::
39 List of syscalls and other perf events (tracepoints, HW cache events,
40 etc) to show. Globbing is supported, e.g.: "epoll_*", "*msg*", etc.
41 See 'perf list' for a complete list of events.
42 Prefixing with ! shows all syscalls but the ones specified. You may
43 need to escape it.
44
45-D msecs::
46--delay msecs::
47After starting the program, wait msecs before measuring. This is useful to
48filter out the startup phase of the program, which is often very different.
49
50-o::
51--output=::
52 Output file name.
53
54-p::
55--pid=::
56 Record events on existing process ID (comma separated list).
57
58-t::
59--tid=::
60 Record events on existing thread ID (comma separated list).
61
62-u::
63--uid=::
64 Record events in threads owned by uid. Name or number.
65
66-G::
67--cgroup::
68 Record events in threads in a cgroup.
69
70 Look for cgroups to set at the /sys/fs/cgroup/perf_event directory, then
71 remove the /sys/fs/cgroup/perf_event/ part and try:
72
73 perf trace -G A -e sched:*switch
74
75 Will set all raw_syscalls:sys_{enter,exit}, pgfault, vfs_getname, etc
76 _and_ sched:sched_switch to the 'A' cgroup, while:
77
78 perf trace -e sched:*switch -G A
79
80 will only set the sched:sched_switch event to the 'A' cgroup, all the
81 other events (raw_syscalls:sys_{enter,exit}, etc are left "without"
82 a cgroup (on the root cgroup, sys wide, etc).
83
84 Multiple cgroups:
85
86 perf trace -G A -e sched:*switch -G B
87
88 the syscall ones go to the 'A' cgroup, the sched:sched_switch goes
89 to the 'B' cgroup.
90
91--filter-pids=::
92 Filter out events for these pids and for 'trace' itself (comma separated list).
93
94-v::
95--verbose=::
96 Verbosity level.
97
98--no-inherit::
99 Child tasks do not inherit counters.
100
101-m::
102--mmap-pages=::
103 Number of mmap data pages (must be a power of two) or size
104 specification with appended unit character - B/K/M/G. The
105 size is rounded up to have nearest pages power of two value.
106
107-C::
108--cpu::
109Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
110comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
111In per-thread mode with inheritance mode on (default), Events are captured only when
112the thread executes on the designated CPUs. Default is to monitor all CPUs.
113
114--duration::
115 Show only events that had a duration greater than N.M ms.
116
117--sched::
118 Accrue thread runtime and provide a summary at the end of the session.
119
120--failure::
121 Show only syscalls that failed, i.e. that returned < 0.
122
123-i::
124--input::
125 Process events from a given perf data file.
126
127-T::
128--time::
129 Print full timestamp rather time relative to first sample.
130
131--comm::
132 Show process COMM right beside its ID, on by default, disable with --no-comm.
133
134-s::
135--summary::
136 Show only a summary of syscalls by thread with min, max, and average times
137 (in msec) and relative stddev.
138
139-S::
140--with-summary::
141 Show all syscalls followed by a summary by thread with min, max, and
142 average times (in msec) and relative stddev.
143
144--tool_stats::
145 Show tool stats such as number of times fd->pathname was discovered thru
146 hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc.
147
148-f::
149--force::
150 Don't complain, do it.
151
152-F=[all|min|maj]::
153--pf=[all|min|maj]::
154 Trace pagefaults. Optionally, you can specify whether you want minor,
155 major or all pagefaults. Default value is maj.
156
157--syscalls::
158 Trace system calls. This options is enabled by default, disable with
159 --no-syscalls.
160
161--call-graph [mode,type,min[,limit],order[,key][,branch]]::
162 Setup and enable call-graph (stack chain/backtrace) recording.
163 See `--call-graph` section in perf-record and perf-report
164 man pages for details. The ones that are most useful in 'perf trace'
165 are 'dwarf' and 'lbr', where available, try: 'perf trace --call-graph dwarf'.
166
167 Using this will, for the root user, bump the value of --mmap-pages to 4
168 times the maximum for non-root users, based on the kernel.perf_event_mlock_kb
169 sysctl. This is done only if the user doesn't specify a --mmap-pages value.
170
171--kernel-syscall-graph::
172 Show the kernel callchains on the syscall exit path.
173
174--max-stack::
175 Set the stack depth limit when parsing the callchain, anything
176 beyond the specified depth will be ignored. Note that at this point
177 this is just about the presentation part, i.e. the kernel is still
178 not limiting, the overhead of callchains needs to be set via the
179 knobs in --call-graph dwarf.
180
181 Implies '--call-graph dwarf' when --call-graph not present on the
182 command line, on systems where DWARF unwinding was built in.
183
184 Default: /proc/sys/kernel/perf_event_max_stack when present for
185 live sessions (without --input/-i), 127 otherwise.
186
187--min-stack::
188 Set the stack depth limit when parsing the callchain, anything
189 below the specified depth will be ignored. Disabled by default.
190
191 Implies '--call-graph dwarf' when --call-graph not present on the
192 command line, on systems where DWARF unwinding was built in.
193
194--print-sample::
195 Print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info for the
196 raw_syscalls:sys_{enter,exit} tracepoints, for debugging.
197
198--proc-map-timeout::
199 When processing pre-existing threads /proc/XXX/mmap, it may take a long time,
200 because the file may be huge. A time out is needed in such cases.
201 This option sets the time out limit. The default value is 500 ms.
202
203PAGEFAULTS
204----------
205
206When tracing pagefaults, the format of the trace is as follows:
207
208<min|maj>fault [<ip.symbol>+<ip.offset>] => <addr.dso@addr.offset> (<map type><addr level>).
209
210- min/maj indicates whether fault event is minor or major;
211- ip.symbol shows symbol for instruction pointer (the code that generated the
212 fault); if no debug symbols available, perf trace will print raw IP;
213- addr.dso shows DSO for the faulted address;
214- map type is either 'd' for non-executable maps or 'x' for executable maps;
215- addr level is either 'k' for kernel dso or '.' for user dso.
216
217For symbols resolution you may need to install debugging symbols.
218
219Please be aware that duration is currently always 0 and doesn't reflect actual
220time it took for fault to be handled!
221
222When --verbose specified, perf trace tries to print all available information
223for both IP and fault address in the form of dso@symbol+offset.
224
225EXAMPLES
226--------
227
228Trace only major pagefaults:
229
230 $ perf trace --no-syscalls -F
231
232Trace syscalls, major and minor pagefaults:
233
234 $ perf trace -F all
235
236 1416.547 ( 0.000 ms): python/20235 majfault [CRYPTO_push_info_+0x0] => /lib/x86_64-linux-gnu/libcrypto.so.1.0.0@0x61be0 (x.)
237
238 As you can see, there was major pagefault in python process, from
239 CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so.
240
241SEE ALSO
242--------
243linkperf:perf-record[1], linkperf:perf-script[1]
1perf-trace(1)
2=============
3
4NAME
5----
6perf-trace - strace inspired tool
7
8SYNOPSIS
9--------
10[verse]
11'perf trace'
12'perf trace record'
13
14DESCRIPTION
15-----------
16This command will show the events associated with the target, initially
17syscalls, but other system events like pagefaults, task lifetime events,
18scheduling events, etc.
19
20This is a live mode tool in addition to working with perf.data files like
21the other perf tools. Files can be generated using the 'perf record' command
22but the session needs to include the raw_syscalls events (-e 'raw_syscalls:*').
23Alternatively, 'perf trace record' can be used as a shortcut to
24automatically include the raw_syscalls events when writing events to a file.
25
26The following options apply to perf trace; options to perf trace record are
27found in the perf record man page.
28
29OPTIONS
30-------
31
32-a::
33--all-cpus::
34 System-wide collection from all CPUs.
35
36-e::
37--expr::
38--event::
39 List of syscalls and other perf events (tracepoints, HW cache events,
40 etc) to show. Globbing is supported, e.g.: "epoll_*", "*msg*", etc.
41 See 'perf list' for a complete list of events.
42 Prefixing with ! shows all syscalls but the ones specified. You may
43 need to escape it.
44
45-D msecs::
46--delay msecs::
47After starting the program, wait msecs before measuring. This is useful to
48filter out the startup phase of the program, which is often very different.
49
50-o::
51--output=::
52 Output file name.
53
54-p::
55--pid=::
56 Record events on existing process ID (comma separated list).
57
58-t::
59--tid=::
60 Record events on existing thread ID (comma separated list).
61
62-u::
63--uid=::
64 Record events in threads owned by uid. Name or number.
65
66-G::
67--cgroup::
68 Record events in threads in a cgroup.
69
70 Look for cgroups to set at the /sys/fs/cgroup/perf_event directory, then
71 remove the /sys/fs/cgroup/perf_event/ part and try:
72
73 perf trace -G A -e sched:*switch
74
75 Will set all raw_syscalls:sys_{enter,exit}, pgfault, vfs_getname, etc
76 _and_ sched:sched_switch to the 'A' cgroup, while:
77
78 perf trace -e sched:*switch -G A
79
80 will only set the sched:sched_switch event to the 'A' cgroup, all the
81 other events (raw_syscalls:sys_{enter,exit}, etc are left "without"
82 a cgroup (on the root cgroup, sys wide, etc).
83
84 Multiple cgroups:
85
86 perf trace -G A -e sched:*switch -G B
87
88 the syscall ones go to the 'A' cgroup, the sched:sched_switch goes
89 to the 'B' cgroup.
90
91--filter-pids=::
92 Filter out events for these pids and for 'trace' itself (comma separated list).
93
94-v::
95--verbose=::
96 Verbosity level.
97
98--no-inherit::
99 Child tasks do not inherit counters.
100
101-m::
102--mmap-pages=::
103 Number of mmap data pages (must be a power of two) or size
104 specification with appended unit character - B/K/M/G. The
105 size is rounded up to have nearest pages power of two value.
106
107-C::
108--cpu::
109Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
110comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
111In per-thread mode with inheritance mode on (default), Events are captured only when
112the thread executes on the designated CPUs. Default is to monitor all CPUs.
113
114--duration::
115 Show only events that had a duration greater than N.M ms.
116
117--sched::
118 Accrue thread runtime and provide a summary at the end of the session.
119
120--failure::
121 Show only syscalls that failed, i.e. that returned < 0.
122
123-i::
124--input::
125 Process events from a given perf data file.
126
127-T::
128--time::
129 Print full timestamp rather time relative to first sample.
130
131--comm::
132 Show process COMM right beside its ID, on by default, disable with --no-comm.
133
134-s::
135--summary::
136 Show only a summary of syscalls by thread with min, max, and average times
137 (in msec) and relative stddev.
138
139-S::
140--with-summary::
141 Show all syscalls followed by a summary by thread with min, max, and
142 average times (in msec) and relative stddev.
143
144--tool_stats::
145 Show tool stats such as number of times fd->pathname was discovered thru
146 hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc.
147
148-f::
149--force::
150 Don't complain, do it.
151
152-F=[all|min|maj]::
153--pf=[all|min|maj]::
154 Trace pagefaults. Optionally, you can specify whether you want minor,
155 major or all pagefaults. Default value is maj.
156
157--syscalls::
158 Trace system calls. This options is enabled by default, disable with
159 --no-syscalls.
160
161--call-graph [mode,type,min[,limit],order[,key][,branch]]::
162 Setup and enable call-graph (stack chain/backtrace) recording.
163 See `--call-graph` section in perf-record and perf-report
164 man pages for details. The ones that are most useful in 'perf trace'
165 are 'dwarf' and 'lbr', where available, try: 'perf trace --call-graph dwarf'.
166
167 Using this will, for the root user, bump the value of --mmap-pages to 4
168 times the maximum for non-root users, based on the kernel.perf_event_mlock_kb
169 sysctl. This is done only if the user doesn't specify a --mmap-pages value.
170
171--kernel-syscall-graph::
172 Show the kernel callchains on the syscall exit path.
173
174--max-events=N::
175 Stop after processing N events. Note that strace-like events are considered
176 only at exit time or when a syscall is interrupted, i.e. in those cases this
177 option is equivalent to the number of lines printed.
178
179--switch-on EVENT_NAME::
180 Only consider events after this event is found.
181
182--switch-off EVENT_NAME::
183 Stop considering events after this event is found.
184
185--show-on-off-events::
186 Show the --switch-on/off events too.
187
188--max-stack::
189 Set the stack depth limit when parsing the callchain, anything
190 beyond the specified depth will be ignored. Note that at this point
191 this is just about the presentation part, i.e. the kernel is still
192 not limiting, the overhead of callchains needs to be set via the
193 knobs in --call-graph dwarf.
194
195 Implies '--call-graph dwarf' when --call-graph not present on the
196 command line, on systems where DWARF unwinding was built in.
197
198 Default: /proc/sys/kernel/perf_event_max_stack when present for
199 live sessions (without --input/-i), 127 otherwise.
200
201--min-stack::
202 Set the stack depth limit when parsing the callchain, anything
203 below the specified depth will be ignored. Disabled by default.
204
205 Implies '--call-graph dwarf' when --call-graph not present on the
206 command line, on systems where DWARF unwinding was built in.
207
208--print-sample::
209 Print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info for the
210 raw_syscalls:sys_{enter,exit} tracepoints, for debugging.
211
212--proc-map-timeout::
213 When processing pre-existing threads /proc/XXX/mmap, it may take a long time,
214 because the file may be huge. A time out is needed in such cases.
215 This option sets the time out limit. The default value is 500 ms.
216
217--sort-events::
218 Do sorting on batches of events, use when noticing out of order events that
219 may happen, for instance, when a thread gets migrated to a different CPU
220 while processing a syscall.
221
222--map-dump::
223 Dump BPF maps setup by events passed via -e, for instance the augmented_raw_syscalls
224 living in tools/perf/examples/bpf/augmented_raw_syscalls.c. For now this
225 dumps just boolean map values and integer keys, in time this will print in hex
226 by default and use BTF when available, as well as use functions to do pretty
227 printing using the existing 'perf trace' syscall arg beautifiers to map integer
228 arguments to strings (pid to comm, syscall id to syscall name, etc).
229
230
231PAGEFAULTS
232----------
233
234When tracing pagefaults, the format of the trace is as follows:
235
236<min|maj>fault [<ip.symbol>+<ip.offset>] => <addr.dso@addr.offset> (<map type><addr level>).
237
238- min/maj indicates whether fault event is minor or major;
239- ip.symbol shows symbol for instruction pointer (the code that generated the
240 fault); if no debug symbols available, perf trace will print raw IP;
241- addr.dso shows DSO for the faulted address;
242- map type is either 'd' for non-executable maps or 'x' for executable maps;
243- addr level is either 'k' for kernel dso or '.' for user dso.
244
245For symbols resolution you may need to install debugging symbols.
246
247Please be aware that duration is currently always 0 and doesn't reflect actual
248time it took for fault to be handled!
249
250When --verbose specified, perf trace tries to print all available information
251for both IP and fault address in the form of dso@symbol+offset.
252
253EXAMPLES
254--------
255
256Trace only major pagefaults:
257
258 $ perf trace --no-syscalls -F
259
260Trace syscalls, major and minor pagefaults:
261
262 $ perf trace -F all
263
264 1416.547 ( 0.000 ms): python/20235 majfault [CRYPTO_push_info_+0x0] => /lib/x86_64-linux-gnu/libcrypto.so.1.0.0@0x61be0 (x.)
265
266 As you can see, there was major pagefault in python process, from
267 CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so.
268
269Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
270
271 $ perf trace -e open* --max-events 4
272 [root@jouet perf]# trace -e open* --max-events 4
273 2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
274 2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
275 3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
276 4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
277 $
278
279Trace the first minor page fault when running a workload:
280
281 # perf trace -F min --max-stack=7 --max-events 1 sleep 1
282 0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
283 __clear_user ([kernel.kallsyms])
284 load_elf_binary ([kernel.kallsyms])
285 search_binary_handler ([kernel.kallsyms])
286 __do_execve_file.isra.33 ([kernel.kallsyms])
287 __x64_sys_execve ([kernel.kallsyms])
288 do_syscall_64 ([kernel.kallsyms])
289 entry_SYSCALL_64 ([kernel.kallsyms])
290 #
291
292Trace the next min page page fault to take place on the first CPU:
293
294 # perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
295 0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
296 js::gc::FreeSpan::initAsEmpty (inlined)
297 js::gc::Arena::setAsNotAllocated (inlined)
298 js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
299 js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
300 js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
301 js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
302 js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
303 js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
304 js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
305 JSThinInlineString::new_<(js::AllowGC)1> (inlined)
306 AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
307 js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
308 [0x18b26e6bc2bd] (/tmp/perf-17136.map)
309 #
310
311Trace the next two sched:sched_switch events, four block:*_plug events, the
312next block:*_unplug and the next three net:*dev_queue events, this last one
313with a backtrace of at most 16 entries, system wide:
314
315 # perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
316 0.000 :0/0 sched:sched_switch:swapper/2:0 [120] S ==> rcu_sched:10 [120]
317 0.015 rcu_sched/10 sched:sched_switch:rcu_sched:10 [120] R ==> swapper/2:0 [120]
318 254.198 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=66
319 __dev_queue_xmit ([kernel.kallsyms])
320 273.977 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=78
321 __dev_queue_xmit ([kernel.kallsyms])
322 274.007 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ff00 len=78
323 __dev_queue_xmit ([kernel.kallsyms])
324 2930.140 kworker/u16:58/2722 block:block_plug:[kworker/u16:58]
325 2930.162 kworker/u16:58/2722 block:block_unplug:[kworker/u16:58] 1
326 4466.094 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
327 8050.123 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
328 8050.271 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
329 #
330
331SEE ALSO
332--------
333linkperf:perf-record[1], linkperf:perf-script[1]