xref: /openbmc/linux/tools/perf/Documentation/perf-stat.txt (revision 4f727ecefefbd180de10e25b3e74c03dce3f1e75)
1perf-stat(1)
2============
3
4NAME
5----
6perf-stat - Run a command and gather performance counter statistics
7
8SYNOPSIS
9--------
10[verse]
11'perf stat' [-e <EVENT> | --event=EVENT] [-a] <command>
12'perf stat' [-e <EVENT> | --event=EVENT] [-a] -- <command> [<options>]
13'perf stat' [-e <EVENT> | --event=EVENT] [-a] record [-o file] -- <command> [<options>]
14'perf stat' report [-i file]
15
16DESCRIPTION
17-----------
18This command runs a command and gathers performance counter statistics
19from it.
20
21
22OPTIONS
23-------
24<command>...::
25	Any command you can specify in a shell.
26
27record::
28	See STAT RECORD.
29
30report::
31	See STAT REPORT.
32
33-e::
34--event=::
35	Select the PMU event. Selection can be:
36
37	- a symbolic event name (use 'perf list' to list all events)
38
39	- a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
40	  hexadecimal event descriptor.
41
42	- a symbolically formed event like 'pmu/param1=0x3,param2/' where
43	  param1 and param2 are defined as formats for the PMU in
44	  /sys/bus/event_source/devices/<pmu>/format/*
45
46	  'percore' is a event qualifier that sums up the event counts for both
47	  hardware threads in a core. For example:
48	  perf stat -A -a -e cpu/event,percore=1/,otherevent ...
49
50	- a symbolically formed event like 'pmu/config=M,config1=N,config2=K/'
51	  where M, N, K are numbers (in decimal, hex, octal format).
52	  Acceptable values for each of 'config', 'config1' and 'config2'
53	  parameters are defined by corresponding entries in
54	  /sys/bus/event_source/devices/<pmu>/format/*
55
56	Note that the last two syntaxes support prefix and glob matching in
57	the PMU name to simplify creation of events across multiple instances
58	of the same type of PMU in large systems (e.g. memory controller PMUs).
59	Multiple PMU instances are typical for uncore PMUs, so the prefix
60	'uncore_' is also ignored when performing this match.
61
62
63-i::
64--no-inherit::
65        child tasks do not inherit counters
66-p::
67--pid=<pid>::
68        stat events on existing process id (comma separated list)
69
70-t::
71--tid=<tid>::
72        stat events on existing thread id (comma separated list)
73
74
75-a::
76--all-cpus::
77        system-wide collection from all CPUs (default if no target is specified)
78
79--no-scale::
80	Don't scale/normalize counter values
81
82-d::
83--detailed::
84	print more detailed statistics, can be specified up to 3 times
85
86	   -d:          detailed events, L1 and LLC data cache
87        -d -d:     more detailed events, dTLB and iTLB events
88     -d -d -d:     very detailed events, adding prefetch events
89
90-r::
91--repeat=<n>::
92	repeat command and print average + stddev (max: 100). 0 means forever.
93
94-B::
95--big-num::
96        print large numbers with thousands' separators according to locale
97
98-C::
99--cpu=::
100Count only on the list of CPUs provided. Multiple CPUs can be provided as a
101comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
102In per-thread mode, this option is ignored. The -a option is still necessary
103to activate system-wide monitoring. Default is to count on all CPUs.
104
105-A::
106--no-aggr::
107Do not aggregate counts across all monitored CPUs.
108
109-n::
110--null::
111        null run - don't start any counters
112
113-v::
114--verbose::
115        be more verbose (show counter open errors, etc)
116
117-x SEP::
118--field-separator SEP::
119print counts using a CSV-style output to make it easy to import directly into
120spreadsheets. Columns are separated by the string specified in SEP.
121
122--table:: Display time for each run (-r option), in a table format, e.g.:
123
124  $ perf stat --null -r 5 --table perf bench sched pipe
125
126   Performance counter stats for 'perf bench sched pipe' (5 runs):
127
128             # Table of individual measurements:
129             5.189 (-0.293) #
130             5.189 (-0.294) #
131             5.186 (-0.296) #
132             5.663 (+0.181) ##
133             6.186 (+0.703) ####
134
135             # Final result:
136             5.483 +- 0.198 seconds time elapsed  ( +-  3.62% )
137
138-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. If the user wants to track multiple events for a specific cgroup, the user can
148use '-e e1 -e e2 -G foo,foo' or just use '-e e1 -e e2 -G foo'.
149
150If wanting to monitor, say, 'cycles' for a cgroup and also for system wide, this
151command line can be used: 'perf stat -e cycles -G cgroup_name -a -e cycles'.
152
153-o file::
154--output file::
155Print the output into the designated file.
156
157--append::
158Append to the output file designated with the -o option. Ignored if -o is not specified.
159
160--log-fd::
161
162Log output to fd, instead of stderr.  Complementary to --output, and mutually exclusive
163with it.  --append may be used here.  Examples:
164     3>results  perf stat --log-fd 3          -- $cmd
165     3>>results perf stat --log-fd 3 --append -- $cmd
166
167--pre::
168--post::
169	Pre and post measurement hooks, e.g.:
170
171perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' -- make -s -j64 O=defconfig-build/ bzImage
172
173-I msecs::
174--interval-print msecs::
175Print count deltas every N milliseconds (minimum: 1ms)
176The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals.  Use with caution.
177	example: 'perf stat -I 1000 -e cycles -a sleep 5'
178
179--interval-count times::
180Print count deltas for fixed number of times.
181This option should be used together with "-I" option.
182	example: 'perf stat -I 1000 --interval-count 2 -e cycles -a'
183
184--interval-clear::
185Clear the screen before next interval.
186
187--timeout msecs::
188Stop the 'perf stat' session and print count deltas after N milliseconds (minimum: 10 ms).
189This option is not supported with the "-I" option.
190	example: 'perf stat --time 2000 -e cycles -a'
191
192--metric-only::
193Only print computed metrics. Print them in a single line.
194Don't show any raw values. Not supported with --per-thread.
195
196--per-socket::
197Aggregate counts per processor socket for system-wide mode measurements.  This
198is a useful mode to detect imbalance between sockets.  To enable this mode,
199use --per-socket in addition to -a. (system-wide).  The output includes the
200socket number and the number of online processors on that socket. This is
201useful to gauge the amount of aggregation.
202
203--per-core::
204Aggregate counts per physical processor for system-wide mode measurements.  This
205is a useful mode to detect imbalance between physical cores.  To enable this mode,
206use --per-core in addition to -a. (system-wide).  The output includes the
207core number and the number of online logical processors on that physical processor.
208
209--per-thread::
210Aggregate counts per monitored threads, when monitoring threads (-t option)
211or processes (-p option).
212
213-D msecs::
214--delay msecs::
215After starting the program, wait msecs before measuring. This is useful to
216filter out the startup phase of the program, which is often very different.
217
218-T::
219--transaction::
220
221Print statistics of transactional execution if supported.
222
223STAT RECORD
224-----------
225Stores stat data into perf data file.
226
227-o file::
228--output file::
229Output file name.
230
231STAT REPORT
232-----------
233Reads and reports stat data from perf data file.
234
235-i file::
236--input file::
237Input file name.
238
239--per-socket::
240Aggregate counts per processor socket for system-wide mode measurements.
241
242--per-core::
243Aggregate counts per physical processor for system-wide mode measurements.
244
245-M::
246--metrics::
247Print metrics or metricgroups specified in a comma separated list.
248For a group all metrics from the group are added.
249The events from the metrics are automatically measured.
250See perf list output for the possble metrics and metricgroups.
251
252-A::
253--no-aggr::
254Do not aggregate counts across all monitored CPUs.
255
256--topdown::
257Print top down level 1 metrics if supported by the CPU. This allows to
258determine bottle necks in the CPU pipeline for CPU bound workloads,
259by breaking the cycles consumed down into frontend bound, backend bound,
260bad speculation and retiring.
261
262Frontend bound means that the CPU cannot fetch and decode instructions fast
263enough. Backend bound means that computation or memory access is the bottle
264neck. Bad Speculation means that the CPU wasted cycles due to branch
265mispredictions and similar issues. Retiring means that the CPU computed without
266an apparently bottleneck. The bottleneck is only the real bottleneck
267if the workload is actually bound by the CPU and not by something else.
268
269For best results it is usually a good idea to use it with interval
270mode like -I 1000, as the bottleneck of workloads can change often.
271
272The top down metrics are collected per core instead of per
273CPU thread. Per core mode is automatically enabled
274and -a (global monitoring) is needed, requiring root rights or
275perf.perf_event_paranoid=-1.
276
277Topdown uses the full Performance Monitoring Unit, and needs
278disabling of the NMI watchdog (as root):
279echo 0 > /proc/sys/kernel/nmi_watchdog
280for best results. Otherwise the bottlenecks may be inconsistent
281on workload with changing phases.
282
283This enables --metric-only, unless overridden with --no-metric-only.
284
285To interpret the results it is usually needed to know on which
286CPUs the workload runs on. If needed the CPUs can be forced using
287taskset.
288
289--no-merge::
290Do not merge results from same PMUs.
291
292When multiple events are created from a single event specification,
293stat will, by default, aggregate the event counts and show the result
294in a single row. This option disables that behavior and shows
295the individual events and counts.
296
297Multiple events are created from a single event specification when:
2981. Prefix or glob matching is used for the PMU name.
2992. Aliases, which are listed immediately after the Kernel PMU events
300   by perf list, are used.
301
302--smi-cost::
303Measure SMI cost if msr/aperf/ and msr/smi/ events are supported.
304
305During the measurement, the /sys/device/cpu/freeze_on_smi will be set to
306freeze core counters on SMI.
307The aperf counter will not be effected by the setting.
308The cost of SMI can be measured by (aperf - unhalted core cycles).
309
310In practice, the percentages of SMI cycles is very useful for performance
311oriented analysis. --metric_only will be applied by default.
312The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf
313
314Users who wants to get the actual value can apply --no-metric-only.
315
316EXAMPLES
317--------
318
319$ perf stat -- make
320
321   Performance counter stats for 'make':
322
323        83723.452481      task-clock:u (msec)       #    1.004 CPUs utilized
324                   0      context-switches:u        #    0.000 K/sec
325                   0      cpu-migrations:u          #    0.000 K/sec
326           3,228,188      page-faults:u             #    0.039 M/sec
327     229,570,665,834      cycles:u                  #    2.742 GHz
328     313,163,853,778      instructions:u            #    1.36  insn per cycle
329      69,704,684,856      branches:u                #  832.559 M/sec
330       2,078,861,393      branch-misses:u           #    2.98% of all branches
331
332        83.409183620 seconds time elapsed
333
334        74.684747000 seconds user
335         8.739217000 seconds sys
336
337TIMINGS
338-------
339As displayed in the example above we can display 3 types of timings.
340We always display the time the counters were enabled/alive:
341
342        83.409183620 seconds time elapsed
343
344For workload sessions we also display time the workloads spent in
345user/system lands:
346
347        74.684747000 seconds user
348         8.739217000 seconds sys
349
350Those times are the very same as displayed by the 'time' tool.
351
352CSV FORMAT
353----------
354
355With -x, perf stat is able to output a not-quite-CSV format output
356Commas in the output are not put into "". To make it easy to parse
357it is recommended to use a different character like -x \;
358
359The fields are in this order:
360
361	- optional usec time stamp in fractions of second (with -I xxx)
362	- optional CPU, core, or socket identifier
363	- optional number of logical CPUs aggregated
364	- counter value
365	- unit of the counter value or empty
366	- event name
367	- run time of counter
368	- percentage of measurement time the counter was running
369	- optional variance if multiple values are collected with -r
370	- optional metric value
371	- optional unit of metric
372
373Additional metrics may be printed with all earlier fields being empty.
374
375SEE ALSO
376--------
377linkperf:perf-top[1], linkperf:perf-list[1]
378