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. 56 57 -t:: 58 --tid=:: 59 Record events on existing thread ID. 60 61 -r:: 62 --realtime=:: 63 Collect data with this RT SCHED_FIFO priority. 64 -D:: 65 --no-delay:: 66 Collect data without buffering. 67 -A:: 68 --append:: 69 Append to the output file to do incremental profiling. 70 71 -f:: 72 --force:: 73 Overwrite existing data file. (deprecated) 74 75 -c:: 76 --count=:: 77 Event period to sample. 78 79 -o:: 80 --output=:: 81 Output file name. 82 83 -i:: 84 --no-inherit:: 85 Child tasks do not inherit counters. 86 -F:: 87 --freq=:: 88 Profile at this frequency. 89 90 -m:: 91 --mmap-pages=:: 92 Number of mmap data pages. 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 SEE ALSO 152 -------- 153 linkperf:perf-stat[1], linkperf:perf-list[1] 154
