'\" t
.\"     Title: perf-trace
.\"    Author: [see the "AUTHOR(S)" section]
.\" Generator: Asciidoctor 2.0.10
.\"      Date: 2020-12-22
.\"    Manual: perf Manual
.\"    Source: perf
.\"  Language: English
.\"
.TH "PERF_5.10\-TRACE" "1" "2020-12-22" "perf" "perf Manual"
.ie \n(.g .ds Aq \(aq
.el       .ds Aq '
.ss \n[.ss] 0
.nh
.ad l
.de URL
\fI\\$2\fP <\\$1>\\$3
..
.als MTO URL
.if \n[.g] \{\
.  mso www.tmac
.  am URL
.    ad l
.  .
.  am MTO
.    ad l
.  .
.  LINKSTYLE blue R < >
.\}
.SH "NAME"
perf\-trace \- strace inspired tool
.SH "SYNOPSIS"
.sp
.sp
.nf
\fIperf trace\fP
\fIperf trace record\fP
.fi
.br
.SH "DESCRIPTION"
.sp
This command will show the events associated with the target, initially
syscalls, but other system events like pagefaults, task lifetime events,
scheduling events, etc.
.sp
This is a live mode tool in addition to working with perf.data files like
the other perf tools. Files can be generated using the \fIperf record\fP command
but the session needs to include the raw_syscalls events (\-e \fIraw_syscalls:*\fP).
Alternatively, \fIperf trace record\fP can be used as a shortcut to
automatically include the raw_syscalls events when writing events to a file.
.sp
The following options apply to perf trace; options to perf trace record are
found in the perf record man page.
.SH "OPTIONS"
.sp
\-a, \-\-all\-cpus
.RS 4
System\-wide collection from all CPUs.
.RE
.sp
\-e, \-\-expr, \-\-event
.RS 4
List of syscalls and other perf events (tracepoints, HW cache events,
etc) to show. Globbing is supported, e.g.: "epoll_*", "\fBmsg\fP", etc.
See \fIperf list\fP for a complete list of events.
Prefixing with ! shows all syscalls but the ones specified.  You may
need to escape it.
.RE
.sp
\-\-filter=<filter>
.RS 4
       Event filter. This option should follow an event selector (\-e) which
selects tracepoint event(s).
.RE
.sp
\-D msecs, \-\-delay msecs
.RS 4
After starting the program, wait msecs before measuring. This is useful to
filter out the startup phase of the program, which is often very different.
.RE
.sp
\-o, \-\-output=
.RS 4
Output file name.
.RE
.sp
\-p, \-\-pid=
.RS 4
Record events on existing process ID (comma separated list).
.RE
.sp
\-t, \-\-tid=
.RS 4
Record events on existing thread ID (comma separated list).
.RE
.sp
\-u, \-\-uid=
.RS 4
Record events in threads owned by uid. Name or number.
.RE
.sp
\-G, \-\-cgroup
.RS 4
Record events in threads in a cgroup.
.sp
.if n .RS 4
.nf
Look for cgroups to set at the /sys/fs/cgroup/perf_event directory, then
remove the /sys/fs/cgroup/perf_event/ part and try:
.fi
.if n .RE
.sp
.if n .RS 4
.nf
perf trace \-G A \-e sched:*switch
.fi
.if n .RE
.sp
.if n .RS 4
.nf
Will set all raw_syscalls:sys_{enter,exit}, pgfault, vfs_getname, etc
_and_ sched:sched_switch to the \(aqA\(aq cgroup, while:
.fi
.if n .RE
.sp
.if n .RS 4
.nf
perf trace \-e sched:*switch \-G A
.fi
.if n .RE
.sp
.if n .RS 4
.nf
will only set the sched:sched_switch event to the \(aqA\(aq cgroup, all the
other events (raw_syscalls:sys_{enter,exit}, etc are left "without"
a cgroup (on the root cgroup, sys wide, etc).
.fi
.if n .RE
.sp
.if n .RS 4
.nf
Multiple cgroups:
.fi
.if n .RE
.sp
.if n .RS 4
.nf
perf trace \-G A \-e sched:*switch \-G B
.fi
.if n .RE
.sp
.if n .RS 4
.nf
the syscall ones go to the \(aqA\(aq cgroup, the sched:sched_switch goes
to the \(aqB\(aq cgroup.
.fi
.if n .RE
.RE
.sp
\-\-filter\-pids=
.RS 4
Filter out events for these pids and for \fItrace\fP itself (comma separated list).
.RE
.sp
\-v, \-\-verbose=
.RS 4
Verbosity level.
.RE
.sp
\-\-no\-inherit
.RS 4
Child tasks do not inherit counters.
.RE
.sp
\-m, \-\-mmap\-pages=
.RS 4
Number of mmap data pages (must be a power of two) or size
specification with appended unit character \- B/K/M/G. The
size is rounded up to have nearest pages power of two value.
.RE
.sp
\-C, \-\-cpu
.RS 4
Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
comma\-separated list with no space: 0,1. Ranges of CPUs are specified with \-: 0\-2.
In per\-thread mode with inheritance mode on (default), Events are captured only when
the thread executes on the designated CPUs. Default is to monitor all CPUs.
.RE
.sp
\-\-duration
.RS 4
Show only events that had a duration greater than N.M ms.
.RE
.sp
\-\-sched
.RS 4
Accrue thread runtime and provide a summary at the end of the session.
.RE
.sp
\-\-failure
.RS 4
Show only syscalls that failed, i.e. that returned < 0.
.RE
.sp
\-i, \-\-input
.RS 4
Process events from a given perf data file.
.RE
.sp
\-T, \-\-time
.RS 4
Print full timestamp rather time relative to first sample.
.RE
.sp
\-\-comm
.RS 4
Show process COMM right beside its ID, on by default, disable with \-\-no\-comm.
.RE
.sp
\-s, \-\-summary
.RS 4
Show only a summary of syscalls by thread with min, max, and average times
(in msec) and relative stddev.
.RE
.sp
\-S, \-\-with\-summary
.RS 4
Show all syscalls followed by a summary by thread with min, max, and
average times (in msec) and relative stddev.
.RE
.sp
\-\-errno\-summary
.RS 4
To be used with \-s or \-S, to show stats for the errnos experienced by
syscalls, using only this option will trigger \-\-summary.
.RE
.sp
\-\-tool_stats
.RS 4
Show tool stats such as number of times fd\(->pathname was discovered thru
hooking the open syscall return + vfs_getname or via reading /proc/pid/fd, etc.
.RE
.sp
\-f, \-\-force
.RS 4
Don\(cqt complain, do it.
.RE
.sp
\-F=[all|min|maj], \-\-pf=[all|min|maj]
.RS 4
Trace pagefaults. Optionally, you can specify whether you want minor,
major or all pagefaults. Default value is maj.
.RE
.sp
\-\-syscalls
.RS 4
Trace system calls. This options is enabled by default, disable with
\-\-no\-syscalls.
.RE
.sp
\-\-call\-graph [mode,type,min[,limit],order[,key][,branch]]
.RS 4
Setup and enable call\-graph (stack chain/backtrace) recording.
See \f(CR\-\-call\-graph\fP section in perf\-record and perf\-report
man pages for details. The ones that are most useful in \fIperf trace\fP
are \fIdwarf\fP and \fIlbr\fP, where available, try: \fIperf trace \-\-call\-graph dwarf\fP.
.sp
.if n .RS 4
.nf
Using this will, for the root user, bump the value of \-\-mmap\-pages to 4
times the maximum for non\-root users, based on the kernel.perf_event_mlock_kb
sysctl. This is done only if the user doesn\(aqt specify a \-\-mmap\-pages value.
.fi
.if n .RE
.RE
.sp
\-\-kernel\-syscall\-graph
.RS 4
Show the kernel callchains on the syscall exit path.
.RE
.sp
\-\-max\-events=N
.RS 4
Stop after processing N events. Note that strace\-like events are considered
only at exit time or when a syscall is interrupted, i.e. in those cases this
option is equivalent to the number of lines printed.
.RE
.sp
\-\-switch\-on EVENT_NAME
.RS 4
Only consider events after this event is found.
.RE
.sp
\-\-switch\-off EVENT_NAME
.RS 4
Stop considering events after this event is found.
.RE
.sp
\-\-show\-on\-off\-events
.RS 4
Show the \-\-switch\-on/off events too.
.RE
.sp
\-\-max\-stack
.RS 4
Set the stack depth limit when parsing the callchain, anything
beyond the specified depth will be ignored. Note that at this point
this is just about the presentation part, i.e. the kernel is still
not limiting, the overhead of callchains needs to be set via the
knobs in \-\-call\-graph dwarf.
.sp
.if n .RS 4
.nf
Implies \(aq\-\-call\-graph dwarf\(aq when \-\-call\-graph not present on the
command line, on systems where DWARF unwinding was built in.
.fi
.if n .RE
.sp
.if n .RS 4
.nf
Default: /proc/sys/kernel/perf_event_max_stack when present for
         live sessions (without \-\-input/\-i), 127 otherwise.
.fi
.if n .RE
.RE
.sp
\-\-min\-stack
.RS 4
Set the stack depth limit when parsing the callchain, anything
below the specified depth will be ignored. Disabled by default.
.sp
.if n .RS 4
.nf
Implies \(aq\-\-call\-graph dwarf\(aq when \-\-call\-graph not present on the
command line, on systems where DWARF unwinding was built in.
.fi
.if n .RE
.RE
.sp
\-\-print\-sample
.RS 4
Print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info for the
raw_syscalls:sys_{enter,exit} tracepoints, for debugging.
.RE
.sp
\-\-proc\-map\-timeout
.RS 4
When processing pre\-existing threads /proc/XXX/mmap, it may take a long time,
because the file may be huge. A time out is needed in such cases.
This option sets the time out limit. The default value is 500 ms.
.RE
.sp
\-\-sort\-events
.RS 4
Do sorting on batches of events, use when noticing out of order events that
may happen, for instance, when a thread gets migrated to a different CPU
while processing a syscall.
.RE
.sp
\-\-libtraceevent_print
.RS 4
Use libtraceevent to print tracepoint arguments. By default \fIperf trace\fP uses
the same beautifiers used in the strace\-like enter+exit lines to augment the
tracepoint arguments.
.RE
.sp
\-\-map\-dump
.RS 4
Dump BPF maps setup by events passed via \-e, for instance the augmented_raw_syscalls
living in tools/perf/examples/bpf/augmented_raw_syscalls.c. For now this
dumps just boolean map values and integer keys, in time this will print in hex
by default and use BTF when available, as well as use functions to do pretty
printing using the existing \fIperf trace\fP syscall arg beautifiers to map integer
arguments to strings (pid to comm, syscall id to syscall name, etc).
.RE
.SH "PAGEFAULTS"
.sp
When tracing pagefaults, the format of the trace is as follows:
.sp
<min|maj>fault [<ip.symbol>+<ip.offset>] \(rA <addr.dso@addr.offset> (<map type><addr level>).
.sp
.RS 4
.ie n \{\
\h'-04'\(bu\h'+03'\c
.\}
.el \{\
.  sp -1
.  IP \(bu 2.3
.\}
min/maj indicates whether fault event is minor or major;
.RE
.sp
.RS 4
.ie n \{\
\h'-04'\(bu\h'+03'\c
.\}
.el \{\
.  sp -1
.  IP \(bu 2.3
.\}
ip.symbol shows symbol for instruction pointer (the code that generated the
fault); if no debug symbols available, perf trace will print raw IP;
.RE
.sp
.RS 4
.ie n \{\
\h'-04'\(bu\h'+03'\c
.\}
.el \{\
.  sp -1
.  IP \(bu 2.3
.\}
addr.dso shows DSO for the faulted address;
.RE
.sp
.RS 4
.ie n \{\
\h'-04'\(bu\h'+03'\c
.\}
.el \{\
.  sp -1
.  IP \(bu 2.3
.\}
map type is either \fId\fP for non\-executable maps or \fIx\fP for executable maps;
.RE
.sp
.RS 4
.ie n \{\
\h'-04'\(bu\h'+03'\c
.\}
.el \{\
.  sp -1
.  IP \(bu 2.3
.\}
addr level is either \fIk\fP for kernel dso or \fI.\fP for user dso.
.RE
.sp
For symbols resolution you may need to install debugging symbols.
.sp
Please be aware that duration is currently always 0 and doesn\(cqt reflect actual
time it took for fault to be handled!
.sp
When \-\-verbose specified, perf trace tries to print all available information
for both IP and fault address in the form of dso@symbol+offset.
.SH "EXAMPLES"
.sp
Trace only major pagefaults:
.sp
.if n .RS 4
.nf
$ perf trace \-\-no\-syscalls \-F
.fi
.if n .RE
.sp
Trace syscalls, major and minor pagefaults:
.sp
.if n .RS 4
.nf
$ perf trace \-F all
.fi
.if n .RE
.sp
.if n .RS 4
.nf
1416.547 ( 0.000 ms): python/20235 majfault [CRYPTO_push_info_+0x0] => /lib/x86_64\-linux\-gnu/libcrypto.so.1.0.0@0x61be0 (x.)
.fi
.if n .RE
.sp
.if n .RS 4
.nf
As you can see, there was major pagefault in python process, from
CRYPTO_push_info_ routine which faulted somewhere in libcrypto.so.
.fi
.if n .RE
.sp
Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
.sp
.if n .RS 4
.nf
$ perf trace \-e open* \-\-max\-events 4
[root@jouet perf]# trace \-e open* \-\-max\-events 4
2272.992 ( 0.037 ms): gnome\-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
2277.481 ( 0.139 ms): gnome\-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
3026.398 ( 0.076 ms): gnome\-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
$
.fi
.if n .RE
.sp
Trace the first minor page fault when running a workload:
.sp
.if n .RS 4
.nf
# perf trace \-F min \-\-max\-stack=7 \-\-max\-events 1 sleep 1
   0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
                                     __clear_user ([kernel.kallsyms])
                                     load_elf_binary ([kernel.kallsyms])
                                     search_binary_handler ([kernel.kallsyms])
                                     __do_execve_file.isra.33 ([kernel.kallsyms])
                                     __x64_sys_execve ([kernel.kallsyms])
                                     do_syscall_64 ([kernel.kallsyms])
                                     entry_SYSCALL_64 ([kernel.kallsyms])
#
.fi
.if n .RE
.sp
Trace the next min page page fault to take place on the first CPU:
.sp
.if n .RS 4
.nf
# perf trace \-F min \-\-call\-graph=dwarf \-\-max\-events 1 \-\-cpu 0
   0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
                                     js::gc::FreeSpan::initAsEmpty (inlined)
                                     js::gc::Arena::setAsNotAllocated (inlined)
                                     js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
                                     js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
                                     js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
                                     js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
                                     js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
                                     js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
                                     js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
                                     JSThinInlineString::new_<(js::AllowGC)1> (inlined)
                                     AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
                                     js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
                                     [0x18b26e6bc2bd] (/tmp/perf\-17136.map)
#
.fi
.if n .RE
.sp
Trace the next two sched:sched_switch events, four block:*_plug events, the
next block:*_unplug and the next three net:*dev_queue events, this last one
with a backtrace of at most 16 entries, system wide:
.sp
.if n .RS 4
.nf
# perf trace \-e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max\-stack=16/
   0.000 :0/0 sched:sched_switch:swapper/2:0 [120] S ==> rcu_sched:10 [120]
   0.015 rcu_sched/10 sched:sched_switch:rcu_sched:10 [120] R ==> swapper/2:0 [120]
 254.198 irq/50\-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=66
                                     __dev_queue_xmit ([kernel.kallsyms])
 273.977 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051f600 len=78
                                     __dev_queue_xmit ([kernel.kallsyms])
 274.007 :0/0 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ff00 len=78
                                     __dev_queue_xmit ([kernel.kallsyms])
2930.140 kworker/u16:58/2722 block:block_plug:[kworker/u16:58]
2930.162 kworker/u16:58/2722 block:block_unplug:[kworker/u16:58] 1
4466.094 jbd2/dm\-2\-8/748 block:block_plug:[jbd2/dm\-2\-8]
8050.123 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
8050.271 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
#
.fi
.if n .RE
.SH "SEE ALSO"
.sp
perf\-record(1), perf\-script(1)