tools/perf/Documentation/perf-record.txt

   1 perf-record(1)
   2 ==============
   3
   4 NAME
   5 ----
   6 perf-record - Run a command and record its profile into perf.data
   7
   8 SYNOPSIS
   9 --------
  10 [verse]
  11 'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] <command>
  12 'perf record' [-e <EVENT> | --event=EVENT] [-l] [-a] -- <command> [<options>]
  13
  14 DESCRIPTION
  15 -----------
  16 This command runs a command and gathers a performance counter profile
  17 from it, into perf.data - without displaying anything.
  18
  19 This file can then be inspected later on, using 'perf report'.
  20
  21
  22 OPTIONS
  23 -------
  24 <command>...::
  25         Any command you can specify in a shell.
  26
  27 -e::
  28 --event=::
  29         Select the PMU event. Selection can be:
  30
  31         - 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'.
  42
  43 --filter=<filter>::
  44         Event filter.
  45
  46 -a::
  47 --all-cpus::
  48         System-wide collection from all CPUs.
  49
  50 -l::
  51         Scale counter values.
  52
  53 -p::
  54 --pid=::
  55         Record events on existing process ID (comma separated list).
  56
  57 -t::
  58 --tid=::
  59         Record events on existing thread ID (comma separated list).
  60
  61 -u::
  62 --uid=::
  63         Record events in threads owned by uid. Name or number.
  64
  65 -r::
  66 --realtime=::
  67         Collect data with this RT SCHED_FIFO priority.
  68
  69 -D::
  70 --no-delay::
  71         Collect data without buffering.
  72
  73 -c::
  74 --count=::
  75         Event period to sample.
  76
  77 -o::
  78 --output=::
  79         Output file name.
  80
  81 -i::
  82 --no-inherit::
  83         Child tasks do not inherit counters.
  84 -F::
  85 --freq=::
  86         Profile at this frequency.
  87
  88 -m::
  89 --mmap-pages=::
  90         Number of mmap data pages (must be a power of two) or size
  91         specification with appended unit character - B/K/M/G. The
  92         size is rounded up to have nearest pages power of two value.
  93
  94 -g::
  95 --call-graph::
  96         Do call-graph (stack chain/backtrace) recording.
  97
  98 -q::
  99 --quiet::
 100         Don't print any message, useful for scripting.
 101
 102 -v::
 103 --verbose::
 104         Be more verbose (show counter open errors, etc).
 105
 106 -s::
 107 --stat::
 108         Per thread counts.
 109
 110 -d::
 111 --data::
 112         Sample addresses.
 113
 114 -T::
 115 --timestamp::
 116         Sample timestamps. Use it with 'perf report -D' to see the timestamps,
 117         for instance.
 118
 119 -n::
 120 --no-samples::
 121         Don't sample.
 122
 123 -R::
 124 --raw-samples::
 125 Collect raw sample records from all opened counters (default for tracepoint counters).
 126
 127 -C::
 128 --cpu::
 129 Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
 130 comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
 131 In per-thread mode with inheritance mode on (default), samples are captured only when
 132 the thread executes on the designated CPUs. Default is to monitor all CPUs.
 133
 134 -N::
 135 --no-buildid-cache::
 136 Do not update the builid cache. This saves some overhead in situations
 137 where the information in the perf.data file (which includes buildids)
 138 is sufficient.
 139
 140 -G name,...::
 141 --cgroup name,...::
 142 monitor only in the container (cgroup) called "name". This option is available only
 143 in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
 144 container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
 145 can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
 146 to first event, second cgroup to second event and so on. It is possible to provide
 147 an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
 148 corresponding events, i.e., they always refer to events defined earlier on the command
 149 line.
 150
 151 -b::
 152 --branch-any::
 153 Enable taken branch stack sampling. Any type of taken branch may be sampled.
 154 This is a shortcut for --branch-filter any. See --branch-filter for more infos.
 155
 156 -j::
 157 --branch-filter::
 158 Enable taken branch stack sampling. Each sample captures a series of consecutive
 159 taken branches. The number of branches captured with each sample depends on the
 160 underlying hardware, the type of branches of interest, and the executed code.
 161 It is possible to select the types of branches captured by enabling filters. The
 162 following filters are defined:
 163
 164         - any:  any type of branches
 165         - any_call: any function call or system call
 166         - any_ret: any function return or system call return
 167         - ind_call: any indirect branch
 168         - u:  only when the branch target is at the user level
 169         - k: only when the branch target is in the kernel
 170         - hv: only when the target is at the hypervisor level
 171         - in_tx: only when the target is in a hardware transaction
 172         - no_tx: only when the target is not in a hardware transaction
 173         - abort_tx: only when the target is a hardware transaction abort
 174
 175 +
 176 The option requires at least one branch type among any, any_call, any_ret, ind_call.
 177 The privilege levels may be omitted, in which case, the privilege levels of the associated
 178 event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege
 179 levels are subject to permissions.  When sampling on multiple events, branch stack sampling
 180 is enabled for all the sampling events. The sampled branch type is the same for all events.
 181 The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
 182 Note that this feature may not be available on all processors.
 183
 184 --weight::
 185 Enable weightened sampling. An additional weight is recorded per sample and can be
 186 displayed with the weight and local_weight sort keys.  This currently works for TSX
 187 abort events and some memory events in precise mode on modern Intel CPUs.
 188
 189 --transaction::
 190 Record transaction flags for transaction related events.
 191
 192 SEE ALSO
 193 --------
 194 linkperf:perf-stat[1], linkperf:perf-list[1]