blob: f732eaa6a500b655a9b0503378bc5de99bc21294 [file] [log] [blame]
Ingo Molnare33e0a42009-04-20 15:58:01 +02001perf-record(1)
Ingo Molnarc1c23652009-05-30 12:38:51 +02002==============
Ingo Molnare33e0a42009-04-20 15:58:01 +02003
4NAME
5----
Ingo Molnar23ac9cb2009-05-27 09:33:18 +02006perf-record - Run a command and record its profile into perf.data
Ingo Molnare33e0a42009-04-20 15:58:01 +02007
8SYNOPSIS
9--------
10[verse]
11'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] <command>
Mike Galbraith9e0967532009-05-28 16:25:34 +020012'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] -- <command> [<options>]
Ingo Molnare33e0a42009-04-20 15:58:01 +020013
14DESCRIPTION
15-----------
16This command runs a command and gathers a performance counter profile
Ingo Molnar23ac9cb2009-05-27 09:33:18 +020017from it, into perf.data - without displaying anything.
Ingo Molnare33e0a42009-04-20 15:58:01 +020018
19This file can then be inspected later on, using 'perf report'.
20
21
22OPTIONS
23-------
24<command>...::
25 Any command you can specify in a shell.
26
27-e::
28--event=::
Frederic Weisbecker1b290d62009-11-23 15:42:35 +010029 Select the PMU event. Selection can be:
Ingo Molnare33e0a42009-04-20 15:58:01 +020030
Frederic Weisbecker1b290d62009-11-23 15:42:35 +010031 - a symbolic event name (use 'perf list' to list all events)
32
33 - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
34 hexadecimal event descriptor.
35
36 - a hardware breakpoint event in the form of '\mem:addr[:access]'
37 where addr is the address in memory you want to break in.
38 Access is the memory access type (read, write, execute) it can
39 be passed as follows: '\mem:addr[:[r][w][x]]'.
40 If you want to profile read-write accesses in 0x1000, just set
41 'mem:0x1000:rw'.
Shawn Bohrer08dbd7e2010-11-30 19:57:16 -060042
43--filter=<filter>::
44 Event filter.
45
Ingo Molnare33e0a42009-04-20 15:58:01 +020046-a::
Shawn Bohrer08dbd7e2010-11-30 19:57:16 -060047--all-cpus::
48 System-wide collection from all CPUs.
Ingo Molnare33e0a42009-04-20 15:58:01 +020049
50-l::
Arnaldo Carvalho de Melo386c0b72009-08-05 10:04:53 -030051 Scale counter values.
52
53-p::
54--pid=::
David Ahernb52956c2012-02-08 09:32:52 -070055 Record events on existing process ID (comma separated list).
Shawn Bohrer08dbd7e2010-11-30 19:57:16 -060056
57-t::
58--tid=::
David Ahernb52956c2012-02-08 09:32:52 -070059 Record events on existing thread ID (comma separated list).
Arnaldo Carvalho de Melo386c0b72009-08-05 10:04:53 -030060
Arnaldo Carvalho de Melo0d37aa32012-01-19 14:08:15 -020061-u::
62--uid=::
63 Record events in threads owned by uid. Name or number.
64
Arnaldo Carvalho de Melo386c0b72009-08-05 10:04:53 -030065-r::
66--realtime=::
67 Collect data with this RT SCHED_FIFO priority.
Jiri Olsa563aecb2013-06-05 13:35:06 +020068
Kirill Smelkovacac03f2011-01-12 17:59:36 +030069-D::
70--no-delay::
71 Collect data without buffering.
Arnaldo Carvalho de Melo386c0b72009-08-05 10:04:53 -030072
Arnaldo Carvalho de Melo386c0b72009-08-05 10:04:53 -030073-c::
74--count=::
75 Event period to sample.
76
77-o::
78--output=::
79 Output file name.
80
81-i::
Stephane Eranian2e6cdf92010-05-12 10:40:01 +020082--no-inherit::
83 Child tasks do not inherit counters.
Arnaldo Carvalho de Melo386c0b72009-08-05 10:04:53 -030084-F::
85--freq=::
86 Profile at this frequency.
87
88-m::
89--mmap-pages=::
Nelson Elhage41d0d932011-12-19 08:39:32 -050090 Number of mmap data pages. Must be a power of two.
Arnaldo Carvalho de Melo386c0b72009-08-05 10:04:53 -030091
92-g::
93--call-graph::
94 Do call-graph (stack chain/backtrace) recording.
95
Arnaldo Carvalho de Melob44308f2010-10-26 15:20:09 -020096-q::
97--quiet::
98 Don't print any message, useful for scripting.
99
Arnaldo Carvalho de Melo386c0b72009-08-05 10:04:53 -0300100-v::
101--verbose::
102 Be more verbose (show counter open errors, etc).
103
104-s::
105--stat::
106 Per thread counts.
107
108-d::
109--data::
110 Sample addresses.
111
Arnaldo Carvalho de Melo9c90a612010-12-02 10:25:28 -0200112-T::
113--timestamp::
114 Sample timestamps. Use it with 'perf report -D' to see the timestamps,
115 for instance.
116
Arnaldo Carvalho de Melo386c0b72009-08-05 10:04:53 -0300117-n::
118--no-samples::
119 Don't sample.
Ingo Molnare33e0a42009-04-20 15:58:01 +0200120
Frederic Weisbeckerec7ba4e2009-08-31 03:32:03 +0200121-R::
122--raw-samples::
Frederic Weisbeckerbdef3b02010-04-14 20:05:17 +0200123Collect raw sample records from all opened counters (default for tracepoint counters).
Frederic Weisbeckerec7ba4e2009-08-31 03:32:03 +0200124
Stephane Eranianc45c6ea2010-05-28 12:00:01 +0200125-C::
126--cpu::
Shawn Bohrer08dbd7e2010-11-30 19:57:16 -0600127Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
128comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
Stephane Eranianc45c6ea2010-05-28 12:00:01 +0200129In per-thread mode with inheritance mode on (default), samples are captured only when
130the thread executes on the designated CPUs. Default is to monitor all CPUs.
131
Stephane Eraniana1ac1d32010-06-17 11:39:01 +0200132-N::
133--no-buildid-cache::
134Do not update the builid cache. This saves some overhead in situations
135where the information in the perf.data file (which includes buildids)
136is sufficient.
137
Stephane Eranian023695d2011-02-14 11:20:01 +0200138-G name,...::
139--cgroup name,...::
140monitor only in the container (cgroup) called "name". This option is available only
141in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
142container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
143can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
144to first event, second cgroup to second event and so on. It is possible to provide
145an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
146corresponding events, i.e., they always refer to events defined earlier on the command
147line.
148
Roberto Agostino Vitillobdfebd82012-02-09 23:21:02 +0100149-b::
Stephane Eraniana5aabda2012-03-08 23:47:45 +0100150--branch-any::
151Enable taken branch stack sampling. Any type of taken branch may be sampled.
152This is a shortcut for --branch-filter any. See --branch-filter for more infos.
153
154-j::
155--branch-filter::
Roberto Agostino Vitillobdfebd82012-02-09 23:21:02 +0100156Enable taken branch stack sampling. Each sample captures a series of consecutive
157taken branches. The number of branches captured with each sample depends on the
158underlying hardware, the type of branches of interest, and the executed code.
159It is possible to select the types of branches captured by enabling filters. The
160following filters are defined:
161
Stephane Eraniana5aabda2012-03-08 23:47:45 +0100162 - any: any type of branches
Roberto Agostino Vitillobdfebd82012-02-09 23:21:02 +0100163 - any_call: any function call or system call
164 - any_ret: any function return or system call return
Anshuman Khandual2e49a942012-05-18 14:16:50 +0530165 - ind_call: any indirect branch
Roberto Agostino Vitillobdfebd82012-02-09 23:21:02 +0100166 - u: only when the branch target is at the user level
167 - k: only when the branch target is in the kernel
168 - hv: only when the target is at the hypervisor level
Andi Kleen0126d492013-09-20 07:40:42 -0700169 - in_tx: only when the target is in a hardware transaction
170 - no_tx: only when the target is not in a hardware transaction
171 - abort_tx: only when the target is a hardware transaction abort
Roberto Agostino Vitillobdfebd82012-02-09 23:21:02 +0100172
173+
Stephane Eraniana5aabda2012-03-08 23:47:45 +0100174The option requires at least one branch type among any, any_call, any_ret, ind_call.
Masanari Iida9c768202012-11-30 14:10:25 +0900175The privilege levels may be omitted, in which case, the privilege levels of the associated
Stephane Eraniana5aabda2012-03-08 23:47:45 +0100176event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege
177levels are subject to permissions. When sampling on multiple events, branch stack sampling
178is enabled for all the sampling events. The sampled branch type is the same for all events.
179The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
180Note that this feature may not be available on all processors.
Roberto Agostino Vitillobdfebd82012-02-09 23:21:02 +0100181
Andi Kleen05484292013-01-24 16:10:29 +0100182--weight::
183Enable weightened sampling. An additional weight is recorded per sample and can be
184displayed with the weight and local_weight sort keys. This currently works for TSX
185abort events and some memory events in precise mode on modern Intel CPUs.
186
Andi Kleen475eeab2013-09-20 07:40:43 -0700187--transaction::
188Record transaction flags for transaction related events.
189
Ingo Molnare33e0a42009-04-20 15:58:01 +0200190SEE ALSO
191--------
Thomas Gleixner386b05e2009-06-06 14:56:33 +0200192linkperf:perf-stat[1], linkperf:perf-list[1]