6 perf-trace - strace inspired tool
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.
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:*').
23 Alternatively, 'perf trace record' can be used as a shortcut to
24 automatically include the raw_syscalls events when writing events to a file.
26 The following options apply to perf trace; options to perf trace record are
27 found in the perf record man page.
34 System-wide collection from all CPUs.
38 List of events to show, currently only syscall names.
39 Prefixing with ! shows all syscalls but the ones specified. You may
48 Record events on existing process ID (comma separated list).
52 Record events on existing thread ID (comma separated list).
56 Record events in threads owned by uid. Name or number.
59 Filter out events for these pids and for 'trace' itself (comma separated list).
67 Child tasks do not inherit counters.
71 Number of mmap data pages (must be a power of two) or size
72 specification with appended unit character - B/K/M/G. The
73 size is rounded up to have nearest pages power of two value.
77 Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
78 comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
79 In per-thread mode with inheritance mode on (default), Events are captured only when
80 the thread executes on the designated CPUs. Default is to monitor all CPUs.
83 Show only events that had a duration greater than N.M ms.
86 Accrue thread runtime and provide a summary at the end of the session.
90 Process events from a given perf data file.
94 Print full timestamp rather time relative to first sample.
97 Show process COMM right beside its ID, on by default, disable with --no-comm.
101 Show only a summary of syscalls by thread with min, max, and average times
102 (in msec) and relative stddev.
106 Show all syscalls followed by a summary by thread with min, max, and
107 average times (in msec) and relative stddev.
110 Show tool stats such as number of times fd->pathname was discovered thru
111 hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc.
115 Trace pagefaults. Optionally, you can specify whether you want minor,
116 major or all pagefaults. Default value is maj.
119 Trace system calls. This options is enabled by default.
122 Trace other events, see 'perf list' for a complete list.
127 When tracing pagefaults, the format of the trace is as follows:
129 <min|maj>fault [<ip.symbol>+<ip.offset>] => <addr.dso@addr.offset> (<map type><addr level>).
131 - min/maj indicates whether fault event is minor or major;
132 - ip.symbol shows symbol for instruction pointer (the code that generated the
133 fault); if no debug symbols available, perf trace will print raw IP;
134 - addr.dso shows DSO for the faulted address;
135 - map type is either 'd' for non-executable maps or 'x' for executable maps;
136 - addr level is either 'k' for kernel dso or '.' for user dso.
138 For symbols resolution you may need to install debugging symbols.
140 Please be aware that duration is currently always 0 and doesn't reflect actual
141 time it took for fault to be handled!
143 When --verbose specified, perf trace tries to print all available information
144 for both IP and fault address in the form of dso@symbol+offset.
149 Trace only major pagefaults:
151 $ perf trace --no-syscalls -F
153 Trace syscalls, major and minor pagefaults:
157 1416.547 ( 0.000 ms): python/20235 majfault [CRYPTO_push_info_+0x0] => /lib/x86_64-linux-gnu/libcrypto.so.1.0.0@0x61be0 (x.)
159 As you can see, there was major pagefault in python process, from
160 CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so.
164 linkperf:perf-record[1], linkperf:perf-script[1]