]>
Commit | Line | Data |
---|---|---|
514f1c67 ACM |
1 | perf-trace(1) |
2 | ============= | |
3 | ||
4 | NAME | |
5 | ---- | |
6 | perf-trace - strace inspired tool | |
7 | ||
8 | SYNOPSIS | |
9 | -------- | |
10 | [verse] | |
11 | 'perf trace' | |
5e2485b1 | 12 | 'perf trace record' |
514f1c67 ACM |
13 | |
14 | DESCRIPTION | |
15 | ----------- | |
16 | This command will show the events associated with the target, initially | |
17 | syscalls, but other system events like pagefaults, task lifetime events, | |
18 | scheduling events, etc. | |
19 | ||
5e2485b1 DA |
20 | This is a live mode tool in addition to working with perf.data files like |
21 | the other perf tools. Files can be generated using the 'perf record' command | |
22 | but the session needs to include the raw_syscalls events (-e 'raw_syscalls:*'). | |
96355f2c | 23 | Alternatively, 'perf trace record' can be used as a shortcut to |
5e2485b1 DA |
24 | automatically include the raw_syscalls events when writing events to a file. |
25 | ||
26 | The following options apply to perf trace; options to perf trace record are | |
27 | found in the perf record man page. | |
514f1c67 ACM |
28 | |
29 | OPTIONS | |
30 | ------- | |
31 | ||
ac9be8ee | 32 | -a:: |
514f1c67 ACM |
33 | --all-cpus:: |
34 | System-wide collection from all CPUs. | |
35 | ||
2ae3a312 ACM |
36 | -e:: |
37 | --expr:: | |
017037ff ACM |
38 | --event:: |
39 | List of syscalls and other perf events (tracepoints, HW cache events, | |
27702bcf | 40 | etc) to show. Globbing is supported, e.g.: "epoll_*", "*msg*", etc. |
017037ff | 41 | See 'perf list' for a complete list of events. |
b059efdf ACM |
42 | Prefixing with ! shows all syscalls but the ones specified. You may |
43 | need to escape it. | |
2ae3a312 | 44 | |
e36b7821 AB |
45 | -D msecs:: |
46 | --delay msecs:: | |
47 | After starting the program, wait msecs before measuring. This is useful to | |
48 | filter out the startup phase of the program, which is often very different. | |
49 | ||
c24ff998 ACM |
50 | -o:: |
51 | --output=:: | |
52 | Output file name. | |
53 | ||
514f1c67 ACM |
54 | -p:: |
55 | --pid=:: | |
56 | Record events on existing process ID (comma separated list). | |
57 | ||
ac9be8ee | 58 | -t:: |
514f1c67 ACM |
59 | --tid=:: |
60 | Record events on existing thread ID (comma separated list). | |
61 | ||
ac9be8ee | 62 | -u:: |
514f1c67 ACM |
63 | --uid=:: |
64 | Record events in threads owned by uid. Name or number. | |
65 | ||
f078c385 ACM |
66 | --filter-pids=:: |
67 | Filter out events for these pids and for 'trace' itself (comma separated list). | |
68 | ||
7c304ee0 ACM |
69 | -v:: |
70 | --verbose=:: | |
71 | Verbosity level. | |
72 | ||
514f1c67 ACM |
73 | --no-inherit:: |
74 | Child tasks do not inherit counters. | |
75 | ||
ac9be8ee | 76 | -m:: |
514f1c67 | 77 | --mmap-pages=:: |
27050f53 JO |
78 | Number of mmap data pages (must be a power of two) or size |
79 | specification with appended unit character - B/K/M/G. The | |
80 | size is rounded up to have nearest pages power of two value. | |
514f1c67 | 81 | |
ac9be8ee | 82 | -C:: |
514f1c67 ACM |
83 | --cpu:: |
84 | Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a | |
85 | comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2. | |
86 | In per-thread mode with inheritance mode on (default), Events are captured only when | |
87 | the thread executes on the designated CPUs. Default is to monitor all CPUs. | |
88 | ||
9b9d28a0 | 89 | --duration:: |
ae9ed035 ACM |
90 | Show only events that had a duration greater than N.M ms. |
91 | ||
9b9d28a0 | 92 | --sched:: |
1302d88e ACM |
93 | Accrue thread runtime and provide a summary at the end of the session. |
94 | ||
9b9d28a0 SJ |
95 | -i:: |
96 | --input:: | |
6810fc91 DA |
97 | Process events from a given perf data file. |
98 | ||
9b9d28a0 SJ |
99 | -T:: |
100 | --time:: | |
4bb09192 DA |
101 | Print full timestamp rather time relative to first sample. |
102 | ||
50c95cbd ACM |
103 | --comm:: |
104 | Show process COMM right beside its ID, on by default, disable with --no-comm. | |
105 | ||
fd2eabaf | 106 | -s:: |
bf2575c1 | 107 | --summary:: |
fd2eabaf DA |
108 | Show only a summary of syscalls by thread with min, max, and average times |
109 | (in msec) and relative stddev. | |
110 | ||
111 | -S:: | |
112 | --with-summary:: | |
113 | Show all syscalls followed by a summary by thread with min, max, and | |
114 | average times (in msec) and relative stddev. | |
bf2575c1 | 115 | |
c522739d ACM |
116 | --tool_stats:: |
117 | Show tool stats such as number of times fd->pathname was discovered thru | |
118 | hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc. | |
119 | ||
9b9d28a0 SJ |
120 | -f:: |
121 | --force:: | |
122 | Don't complain, do it. | |
123 | ||
598d02c5 SF |
124 | -F=[all|min|maj]:: |
125 | --pf=[all|min|maj]:: | |
126 | Trace pagefaults. Optionally, you can specify whether you want minor, | |
127 | major or all pagefaults. Default value is maj. | |
128 | ||
e281a960 | 129 | --syscalls:: |
739cf305 RB |
130 | Trace system calls. This options is enabled by default, disable with |
131 | --no-syscalls. | |
e281a960 | 132 | |
566a0885 MW |
133 | --call-graph [mode,type,min[,limit],order[,key][,branch]]:: |
134 | Setup and enable call-graph (stack chain/backtrace) recording. | |
135 | See `--call-graph` section in perf-record and perf-report | |
136 | man pages for details. The ones that are most useful in 'perf trace' | |
137 | are 'dwarf' and 'lbr', where available, try: 'perf trace --call-graph dwarf'. | |
138 | ||
f3e459d1 ACM |
139 | Using this will, for the root user, bump the value of --mmap-pages to 4 |
140 | times the maximum for non-root users, based on the kernel.perf_event_mlock_kb | |
141 | sysctl. This is done only if the user doesn't specify a --mmap-pages value. | |
142 | ||
44621819 ACM |
143 | --kernel-syscall-graph:: |
144 | Show the kernel callchains on the syscall exit path. | |
145 | ||
c6d4a494 ACM |
146 | --max-stack:: |
147 | Set the stack depth limit when parsing the callchain, anything | |
148 | beyond the specified depth will be ignored. Note that at this point | |
149 | this is just about the presentation part, i.e. the kernel is still | |
150 | not limiting, the overhead of callchains needs to be set via the | |
151 | knobs in --call-graph dwarf. | |
152 | ||
05614993 ACM |
153 | Implies '--call-graph dwarf' when --call-graph not present on the |
154 | command line, on systems where DWARF unwinding was built in. | |
155 | ||
fe176085 ACM |
156 | Default: /proc/sys/kernel/perf_event_max_stack when present for |
157 | live sessions (without --input/-i), 127 otherwise. | |
c6d4a494 | 158 | |
5cf9c84e ACM |
159 | --min-stack:: |
160 | Set the stack depth limit when parsing the callchain, anything | |
161 | below the specified depth will be ignored. Disabled by default. | |
162 | ||
05614993 ACM |
163 | Implies '--call-graph dwarf' when --call-graph not present on the |
164 | command line, on systems where DWARF unwinding was built in. | |
165 | ||
591421e1 ACM |
166 | --print-sample:: |
167 | Print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info for the | |
168 | raw_syscalls:sys_{enter,exit} tracepoints, for debugging. | |
169 | ||
9d9cad76 KL |
170 | --proc-map-timeout:: |
171 | When processing pre-existing threads /proc/XXX/mmap, it may take a long time, | |
172 | because the file may be huge. A time out is needed in such cases. | |
173 | This option sets the time out limit. The default value is 500 ms. | |
174 | ||
598d02c5 SF |
175 | PAGEFAULTS |
176 | ---------- | |
177 | ||
178 | When tracing pagefaults, the format of the trace is as follows: | |
179 | ||
180 | <min|maj>fault [<ip.symbol>+<ip.offset>] => <addr.dso@addr.offset> (<map type><addr level>). | |
181 | ||
182 | - min/maj indicates whether fault event is minor or major; | |
183 | - ip.symbol shows symbol for instruction pointer (the code that generated the | |
184 | fault); if no debug symbols available, perf trace will print raw IP; | |
185 | - addr.dso shows DSO for the faulted address; | |
186 | - map type is either 'd' for non-executable maps or 'x' for executable maps; | |
187 | - addr level is either 'k' for kernel dso or '.' for user dso. | |
188 | ||
189 | For symbols resolution you may need to install debugging symbols. | |
190 | ||
191 | Please be aware that duration is currently always 0 and doesn't reflect actual | |
192 | time it took for fault to be handled! | |
193 | ||
194 | When --verbose specified, perf trace tries to print all available information | |
195 | for both IP and fault address in the form of dso@symbol+offset. | |
196 | ||
197 | EXAMPLES | |
198 | -------- | |
199 | ||
e281a960 SF |
200 | Trace only major pagefaults: |
201 | ||
202 | $ perf trace --no-syscalls -F | |
203 | ||
598d02c5 SF |
204 | Trace syscalls, major and minor pagefaults: |
205 | ||
206 | $ perf trace -F all | |
207 | ||
208 | 1416.547 ( 0.000 ms): python/20235 majfault [CRYPTO_push_info_+0x0] => /lib/x86_64-linux-gnu/libcrypto.so.1.0.0@0x61be0 (x.) | |
209 | ||
210 | As you can see, there was major pagefault in python process, from | |
211 | CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so. | |
212 | ||
514f1c67 ACM |
213 | SEE ALSO |
214 | -------- | |
215 | linkperf:perf-record[1], linkperf:perf-script[1] |