6 perf-stat - Run a command and gather performance counter statistics
11 'perf stat' [-e <EVENT> | --event=EVENT] [-a] <command>
12 'perf stat' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
16 This command runs a command and gathers performance counter statistics
23 Any command you can specify in a shell.
28 Select the PMU event. Selection can be a symbolic event name
29 (use 'perf list' to list all events) or a raw PMU
30 event (eventsel+umask) in the form of rNNN where NNN is a
31 hexadecimal event descriptor.
35 child tasks do not inherit counters
38 stat events on existing process id
42 stat events on existing thread id
47 system-wide collection from all CPUs
51 scale/normalize counter values
55 repeat command and print average + stddev (max: 100)
59 print large numbers with thousands' separators according to locale
63 Count only on the list of CPUs provided. Multiple CPUs can be provided as a
64 comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
65 In per-thread mode, this option is ignored. The -a option is still necessary
66 to activate system-wide monitoring. Default is to count on all CPUs.
70 Do not aggregate counts across all monitored CPUs in system-wide mode (-a).
71 This option is only valid in system-wide mode.
75 null run - don't start any counters
79 be more verbose (show counter open errors, etc)
82 --field-separator SEP::
83 print counts using a CSV-style output to make it easy to import directly into
84 spreadsheets. Columns are separated by the string specified in SEP.
88 monitor only in the container (cgroup) called "name". This option is available only
89 in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
90 container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
91 can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
92 to first event, second cgroup to second event and so on. It is possible to provide
93 an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
94 corresponding events, i.e., they always refer to events defined earlier on the command
100 $ perf stat -- make -j
102 Performance counter stats for 'make -j':
104 8117.370256 task clock ticks # 11.281 CPU utilization factor
105 678 context switches # 0.000 M/sec
106 133 CPU migrations # 0.000 M/sec
107 235724 pagefaults # 0.029 M/sec
108 24821162526 CPU cycles # 3057.784 M/sec
109 18687303457 instructions # 2302.138 M/sec
110 172158895 cache references # 21.209 M/sec
111 27075259 cache misses # 3.335 M/sec
113 Wall-clock time elapsed: 719.554352 msecs
117 linkperf:perf-top[1], linkperf:perf-list[1]