perf-stat.txt 4.3 KB
Newer Older
I
Ingo Molnar 已提交
1
perf-stat(1)
2
============
I
Ingo Molnar 已提交
3 4 5 6 7 8 9 10

NAME
----
perf-stat - Run a command and gather performance counter statistics

SYNOPSIS
--------
[verse]
S
Shawn Bohrer 已提交
11 12
'perf stat' [-e <EVENT> | --event=EVENT] [-a] <command>
'perf stat' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
I
Ingo Molnar 已提交
13 14 15 16 17 18 19 20 21 22 23 24

DESCRIPTION
-----------
This command runs a command and gathers performance counter statistics
from it.


OPTIONS
-------
<command>...::
	Any command you can specify in a shell.

I
Ingo Molnar 已提交
25

I
Ingo Molnar 已提交
26 27
-e::
--event=::
28 29 30 31
	Select the PMU event. Selection can be a symbolic event name
	(use 'perf list' to list all events) or a raw PMU
	event (eventsel+umask) in the form of rNNN where NNN is a
	 hexadecimal event descriptor.
I
Ingo Molnar 已提交
32

I
Ingo Molnar 已提交
33
-i::
34 35
--no-inherit::
        child tasks do not inherit counters
I
Ingo Molnar 已提交
36 37
-p::
--pid=<pid>::
38
        stat events on existing process id (comma separated list)
S
Shawn Bohrer 已提交
39 40 41

-t::
--tid=<tid>::
42
        stat events on existing thread id (comma separated list)
S
Shawn Bohrer 已提交
43

I
Ingo Molnar 已提交
44

I
Ingo Molnar 已提交
45
-a::
S
Shawn Bohrer 已提交
46 47
--all-cpus::
        system-wide collection from all CPUs
I
Ingo Molnar 已提交
48

49
-c::
S
Shawn Bohrer 已提交
50 51 52 53 54
--scale::
	scale/normalize counter values

-r::
--repeat=<n>::
55
	repeat command and print average + stddev (max: 100). 0 means forever.
I
Ingo Molnar 已提交
56

57
-B::
S
Shawn Bohrer 已提交
58
--big-num::
59 60
        print large numbers with thousands' separators according to locale

61 62
-C::
--cpu=::
S
Shawn Bohrer 已提交
63 64
Count 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.
65 66 67
In per-thread mode, this option is ignored. The -a option is still necessary
to activate system-wide monitoring. Default is to count on all CPUs.

68 69 70 71 72
-A::
--no-aggr::
Do not aggregate counts across all monitored CPUs in system-wide mode (-a).
This option is only valid in system-wide mode.

S
Shawn Bohrer 已提交
73 74 75 76 77 78 79 80
-n::
--null::
        null run - don't start any counters

-v::
--verbose::
        be more verbose (show counter open errors, etc)

S
Stephane Eranian 已提交
81 82 83 84 85
-x SEP::
--field-separator SEP::
print counts using a CSV-style output to make it easy to import directly into
spreadsheets. Columns are separated by the string specified in SEP.

S
Stephane Eranian 已提交
86 87 88 89 90 91 92 93 94 95 96
-G name::
--cgroup name::
monitor only in the container (cgroup) called "name". This option is available only
in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
to first event, second cgroup to second event and so on. It is possible to provide
an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
corresponding events, i.e., they always refer to events defined earlier on the command
line.

97
-o file::
98
--output file::
99 100 101 102 103
Print the output into the designated file.

--append::
Append to the output file designated with the -o option. Ignored if -o is not specified.

104 105 106 107 108 109 110
--log-fd::

Log output to fd, instead of stderr.  Complementary to --output, and mutually exclusive
with it.  --append may be used here.  Examples:
     3>results  perf stat --log-fd 3          -- $cmd
     3>>results perf stat --log-fd 3 --append -- $cmd

111 112 113 114 115
--pre::
--post::
	Pre and post measurement hooks, e.g.:

perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- make -s -j64 O=defconfig-build/ bzImage
116

117 118
-I msecs::
--interval-print msecs::
119
	Print count deltas every N milliseconds (minimum: 100ms)
120
	example: perf stat -I 1000 -e cycles -a sleep 5
121

122 123 124 125 126 127 128
--aggr-socket::
Aggregate counts per processor socket for system-wide mode measurements.  This
is a useful mode to detect imbalance between sockets.  To enable this mode,
use --aggr-socket in addition to -a. (system-wide).  The output includes the
socket number and the number of online processors on that socket. This is
useful to gauge the amount of aggregation.

I
Ingo Molnar 已提交
129 130 131
EXAMPLES
--------

I
Ingo Molnar 已提交
132
$ perf stat -- make -j
I
Ingo Molnar 已提交
133

I
Ingo Molnar 已提交
134
 Performance counter stats for 'make -j':
I
Ingo Molnar 已提交
135

I
Ingo Molnar 已提交
136 137 138 139 140 141 142 143
    8117.370256  task clock ticks     #      11.281 CPU utilization factor
            678  context switches     #       0.000 M/sec
            133  CPU migrations       #       0.000 M/sec
         235724  pagefaults           #       0.029 M/sec
    24821162526  CPU cycles           #    3057.784 M/sec
    18687303457  instructions         #    2302.138 M/sec
      172158895  cache references     #      21.209 M/sec
       27075259  cache misses         #       3.335 M/sec
I
Ingo Molnar 已提交
144

I
Ingo Molnar 已提交
145
 Wall-clock time elapsed:   719.554352 msecs
I
Ingo Molnar 已提交
146 147 148

SEE ALSO
--------
149
linkperf:perf-top[1], linkperf:perf-list[1]