1 perf-stat(1)
2 ============
3
4 NAME
5 ----
6 perf-stat - Run a command and gather performance counter statistics
7
8 SYNOPSIS
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
16 DESCRIPTION
17 -----------
18 This command runs a command and gathers performance counter statistics
19 from it.
20
21
22 OPTIONS
23 -------
24 <command>...::
25 Any command you can specify in a shell.
26
27 record::
28 See STAT RECORD.
29
30 report::
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 in the form of rN where N is a hexadecimal value
40 that represents the raw register encoding with the layout of the
41 event control registers as described by entries in
42 /sys/bus/event_source/devices/cpu/format/*.
43
44 - a symbolic or raw PMU event followed by an optional colon
45 and a list of event modifiers, e.g., cpu-cycles:p. See the
46 linkperf:perf-list[1] man page for details on event modifiers.
47
48 - a symbolically formed event like 'pmu/param1=0x3,param2/' where
49 param1 and param2 are defined as formats for the PMU in
50 /sys/bus/event_source/devices/<pmu>/format/*
51
52 'percore' is a event qualifier that sums up the event counts for both
53 hardware threads in a core. For example:
54 perf stat -A -a -e cpu/event,percore=1/,otherevent ...
55
56 - a symbolically formed event like 'pmu/config=M,config1=N,config2=K/'
57 where M, N, K are numbers (in decimal, hex, octal format).
58 Acceptable values for each of 'config', 'config1' and 'config2'
59 parameters are defined by corresponding entries in
60 /sys/bus/event_source/devices/<pmu>/format/*
61
62 Note that the last two syntaxes support prefix and glob matching in
63 the PMU name to simplify creation of events across multiple instances
64 of the same type of PMU in large systems (e.g. memory controller PMUs).
65 Multiple PMU instances are typical for uncore PMUs, so the prefix
66 'uncore_' is also ignored when performing this match.
67
68
69 -i::
70 --no-inherit::
71 child tasks do not inherit counters
72 -p::
73 --pid=<pid>::
74 stat events on existing process id (comma separated list)
75
76 -t::
77 --tid=<tid>::
78 stat events on existing thread id (comma separated list)
79
80 -b::
81 --bpf-prog::
82 stat events on existing bpf program id (comma separated list),
83 requiring root rights. bpftool-prog could be used to find program
84 id all bpf programs in the system. For example:
85
86 # bpftool prog | head -n 1
87 17247: tracepoint name sys_enter tag 192d548b9d754067 gpl
88
89 # perf stat -e cycles,instructions --bpf-prog 17247 --timeout 1000
90
91 Performance counter stats for 'BPF program(s) 17247':
92
93 85,967 cycles
94 28,982 instructions # 0.34 insn per cycle
95
96 1.102235068 seconds time elapsed
97
98 --bpf-counters::
99 Use BPF programs to aggregate readings from perf_events. This
100 allows multiple perf-stat sessions that are counting the same metric (cycles,
101 instructions, etc.) to share hardware counters.
102 To use BPF programs on common events by default, use
103 "perf config stat.bpf-counter-events=<list_of_events>".
104
105 --bpf-attr-map::
106 With option "--bpf-counters", different perf-stat sessions share
107 information about shared BPF programs and maps via a pinned hashmap.
108 Use "--bpf-attr-map" to specify the path of this pinned hashmap.
109 The default path is /sys/fs/bpf/perf_attr_map.
110
111 ifdef::HAVE_LIBPFM[]
112 --pfm-events events::
113 Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net)
114 including support for event filters. For example '--pfm-events
115 inst_retired:any_p:u:c=1:i'. More than one event can be passed to the
116 option using the comma separator. Hardware events and generic hardware
117 events cannot be mixed together. The latter must be used with the -e
118 option. The -e option and this one can be mixed and matched. Events
119 can be grouped using the {} notation.
120 endif::HAVE_LIBPFM[]
121
122 -a::
123 --all-cpus::
124 system-wide collection from all CPUs (default if no target is specified)
125
126 --no-scale::
127 Don't scale/normalize counter values
128
129 -d::
130 --detailed::
131 print more detailed statistics, can be specified up to 3 times
132
133 -d: detailed events, L1 and LLC data cache
134 -d -d: more detailed events, dTLB and iTLB events
135 -d -d -d: very detailed events, adding prefetch events
136
137 -r::
138 --repeat=<n>::
139 repeat command and print average + stddev (max: 100). 0 means forever.
140
141 -B::
142 --big-num::
143 print large numbers with thousands' separators according to locale.
144 Enabled by default. Use "--no-big-num" to disable.
145 Default setting can be changed with "perf config stat.big-num=false".
146
147 -C::
148 --cpu=::
149 Count only on the list of CPUs provided. Multiple CPUs can be provided as a
150 comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
151 In per-thread mode, this option is ignored. The -a option is still necessary
152 to activate system-wide monitoring. Default is to count on all CPUs.
153
154 -A::
155 --no-aggr::
156 Do not aggregate counts across all monitored CPUs.
157
158 -n::
159 --null::
160 null run - Don't start any counters.
161
162 This can be useful to measure just elapsed wall-clock time - or to assess the
163 raw overhead of perf stat itself, without running any counters.
164
165 -v::
166 --verbose::
167 be more verbose (show counter open errors, etc)
168
169 -x SEP::
170 --field-separator SEP::
171 print counts using a CSV-style output to make it easy to import directly into
172 spreadsheets. Columns are separated by the string specified in SEP.
173
174 --table:: Display time for each run (-r option), in a table format, e.g.:
175
176 $ perf stat --null -r 5 --table perf bench sched pipe
177
178 Performance counter stats for 'perf bench sched pipe' (5 runs):
179
180 # Table of individual measurements:
181 5.189 (-0.293) #
182 5.189 (-0.294) #
183 5.186 (-0.296) #
184 5.663 (+0.181) ##
185 6.186 (+0.703) ####
186
187 # Final result:
188 5.483 +- 0.198 seconds time elapsed ( +- 3.62% )
189
190 -G name::
191 --cgroup name::
192 monitor only in the container (cgroup) called "name". This option is available only
193 in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
194 container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
195 can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
196 to first event, second cgroup to second event and so on. It is possible to provide
197 an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
198 corresponding events, i.e., they always refer to events defined earlier on the command
199 line. If the user wants to track multiple events for a specific cgroup, the user can
200 use '-e e1 -e e2 -G foo,foo' or just use '-e e1 -e e2 -G foo'.
201
202 If wanting to monitor, say, 'cycles' for a cgroup and also for system wide, this
203 command line can be used: 'perf stat -e cycles -G cgroup_name -a -e cycles'.
204
205 --for-each-cgroup name::
206 Expand event list for each cgroup in "name" (allow multiple cgroups separated
207 by comma). It also support regex patterns to match multiple groups. This has same
208 effect that repeating -e option and -G option for each event x name. This option
209 cannot be used with -G/--cgroup option.
210
211 -o file::
212 --output file::
213 Print the output into the designated file.
214
215 --append::
216 Append to the output file designated with the -o option. Ignored if -o is not specified.
217
218 --log-fd::
219
220 Log output to fd, instead of stderr. Complementary to --output, and mutually exclusive
221 with it. --append may be used here. Examples:
222 3>results perf stat --log-fd 3 \-- $cmd
223 3>>results perf stat --log-fd 3 --append \-- $cmd
224
225 --control=fifo:ctl-fifo[,ack-fifo]::
226 --control=fd:ctl-fd[,ack-fd]::
227 ctl-fifo / ack-fifo are opened and used as ctl-fd / ack-fd as follows.
228 Listen on ctl-fd descriptor for command to control measurement ('enable': enable events,
229 'disable': disable events). Measurements can be started with events disabled using
230 --delay=-1 option. Optionally send control command completion ('ack\n') to ack-fd descriptor
231 to synchronize with the controlling process. Example of bash shell script to enable and
232 disable events during measurements:
233
234 #!/bin/bash
235
236 ctl_dir=/tmp/
237
238 ctl_fifo=${ctl_dir}perf_ctl.fifo
239 test -p ${ctl_fifo} && unlink ${ctl_fifo}
240 mkfifo ${ctl_fifo}
241 exec {ctl_fd}<>${ctl_fifo}
242
243 ctl_ack_fifo=${ctl_dir}perf_ctl_ack.fifo
244 test -p ${ctl_ack_fifo} && unlink ${ctl_ack_fifo}
245 mkfifo ${ctl_ack_fifo}
246 exec {ctl_fd_ack}<>${ctl_ack_fifo}
247
248 perf stat -D -1 -e cpu-cycles -a -I 1000 \
249 --control fd:${ctl_fd},${ctl_fd_ack} \
250 \-- sleep 30 &
251 perf_pid=$!
252
253 sleep 5 && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e1 && echo "enabled(${e1})"
254 sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d1 && echo "disabled(${d1})"
255
256 exec {ctl_fd_ack}>&-
257 unlink ${ctl_ack_fifo}
258
259 exec {ctl_fd}>&-
260 unlink ${ctl_fifo}
261
262 wait -n ${perf_pid}
263 exit $?
264
265
266 --pre::
267 --post::
268 Pre and post measurement hooks, e.g.:
269
270 perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' \-- make -s -j64 O=defconfig-build/ bzImage
271
272 -I msecs::
273 --interval-print msecs::
274 Print count deltas every N milliseconds (minimum: 1ms)
275 The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals. Use with caution.
276 example: 'perf stat -I 1000 -e cycles -a sleep 5'
277
278 If the metric exists, it is calculated by the counts generated in this interval and the metric is printed after #.
279
280 --interval-count times::
281 Print count deltas for fixed number of times.
282 This option should be used together with "-I" option.
283 example: 'perf stat -I 1000 --interval-count 2 -e cycles -a'
284
285 --interval-clear::
286 Clear the screen before next interval.
287
288 --timeout msecs::
289 Stop the 'perf stat' session and print count deltas after N milliseconds (minimum: 10 ms).
290 This option is not supported with the "-I" option.
291 example: 'perf stat --time 2000 -e cycles -a'
292
293 --metric-only::
294 Only print computed metrics. Print them in a single line.
295 Don't show any raw values. Not supported with --per-thread.
296
297 --per-socket::
298 Aggregate counts per processor socket for system-wide mode measurements. This
299 is a useful mode to detect imbalance between sockets. To enable this mode,
300 use --per-socket in addition to -a. (system-wide). The output includes the
301 socket number and the number of online processors on that socket. This is
302 useful to gauge the amount of aggregation.
303
304 --per-die::
305 Aggregate counts per processor die for system-wide mode measurements. This
306 is a useful mode to detect imbalance between dies. To enable this mode,
307 use --per-die in addition to -a. (system-wide). The output includes the
308 die number and the number of online processors on that die. This is
309 useful to gauge the amount of aggregation.
310
311 --per-cluster::
312 Aggregate counts per processor cluster for system-wide mode measurement. This
313 is a useful mode to detect imbalance between clusters. To enable this mode,
314 use --per-cluster in addition to -a. (system-wide). The output includes the
315 cluster number and the number of online processors on that cluster. This is
316 useful to gauge the amount of aggregation. The information of cluster ID and
317 related CPUs can be gotten from /sys/devices/system/cpu/cpuX/topology/cluster_{id, cpus}.
318
319 --per-cache::
320 Aggregate counts per cache instance for system-wide mode measurements. By
321 default, the aggregation happens for the cache level at the highest index
322 in the system. To specify a particular level, mention the cache level
323 alongside the option in the format [Ll][1-9][0-9]*. For example:
324 Using option "--per-cache=l3" or "--per-cache=L3" will aggregate the
325 information at the boundary of the level 3 cache in the system.
326
327 --per-core::
328 Aggregate counts per physical processor for system-wide mode measurements. This
329 is a useful mode to detect imbalance between physical cores. To enable this mode,
330 use --per-core in addition to -a. (system-wide). The output includes the
331 core number and the number of online logical processors on that physical processor.
332
333 --per-thread::
334 Aggregate counts per monitored threads, when monitoring threads (-t option)
335 or processes (-p option).
336
337 --per-node::
338 Aggregate counts per NUMA nodes for system-wide mode measurements. This
339 is a useful mode to detect imbalance between NUMA nodes. To enable this
340 mode, use --per-node in addition to -a. (system-wide).
341
342 -D msecs::
343 --delay msecs::
344 After starting the program, wait msecs before measuring (-1: start with events
345 disabled). This is useful to filter out the startup phase of the program,
346 which is often very different.
347
348 -T::
349 --transaction::
350
351 Print statistics of transactional execution if supported.
352
353 --metric-no-group::
354 By default, events to compute a metric are placed in weak groups. The
355 group tries to enforce scheduling all or none of the events. The
356 --metric-no-group option places events outside of groups and may
357 increase the chance of the event being scheduled - leading to more
358 accuracy. However, as events may not be scheduled together accuracy
359 for metrics like instructions per cycle can be lower - as both metrics
360 may no longer be being measured at the same time.
361
362 --metric-no-merge::
363 By default metric events in different weak groups can be shared if one
364 group contains all the events needed by another. In such cases one
365 group will be eliminated reducing event multiplexing and making it so
366 that certain groups of metrics sum to 100%. A downside to sharing a
367 group is that the group may require multiplexing and so accuracy for a
368 small group that need not have multiplexing is lowered. This option
369 forbids the event merging logic from sharing events between groups and
370 may be used to increase accuracy in this case.
371
372 --metric-no-threshold::
373 Metric thresholds may increase the number of events necessary to
374 compute whether a metric has exceeded its threshold expression. This
375 may not be desirable, for example, as the events can introduce
376 multiplexing. This option disables the adding of threshold expression
377 events for a metric. However, if there are sufficient events to
378 compute the threshold then the threshold is still computed and used to
379 color the metric's computed value.
380
381 --quiet::
382 Don't print output, warnings or messages. This is useful with perf stat
383 record below to only write data to the perf.data file.
384
385 STAT RECORD
386 -----------
387 Stores stat data into perf data file.
388
389 -o file::
390 --output file::
391 Output file name.
392
393 STAT REPORT
394 -----------
395 Reads and reports stat data from perf data file.
396
397 -i file::
398 --input file::
399 Input file name.
400
401 --per-socket::
402 Aggregate counts per processor socket for system-wide mode measurements.
403
404 --per-die::
405 Aggregate counts per processor die for system-wide mode measurements.
406
407 --per-cluster::
408 Aggregate counts perf processor cluster for system-wide mode measurements.
409
410 --per-cache::
411 Aggregate counts per cache instance for system-wide mode measurements. By
412 default, the aggregation happens for the cache level at the highest index
413 in the system. To specify a particular level, mention the cache level
414 alongside the option in the format [Ll][1-9][0-9]*. For example: Using
415 option "--per-cache=l3" or "--per-cache=L3" will aggregate the
416 information at the boundary of the level 3 cache in the system.
417
418 --per-core::
419 Aggregate counts per physical processor for system-wide mode measurements.
420
421 -M::
422 --metrics::
423 Print metrics or metricgroups specified in a comma separated list.
424 For a group all metrics from the group are added.
425 The events from the metrics are automatically measured.
426 See perf list output for the possible metrics and metricgroups.
427
428 When threshold information is available for a metric, the
429 color red is used to signify a metric has exceeded a threshold
430 while green shows it hasn't. The default color means that
431 no threshold information was available or the threshold
432 couldn't be computed.
433
434 -A::
435 --no-aggr::
436 --no-merge::
437 Do not aggregate/merge counts across monitored CPUs or PMUs.
438
439 When multiple events are created from a single event specification,
440 stat will, by default, aggregate the event counts and show the result
441 in a single row. This option disables that behavior and shows the
442 individual events and counts.
443
444 Multiple events are created from a single event specification when:
445
446 1. PID monitoring isn't requested and the system has more than one
447 CPU. For example, a system with 8 SMT threads will have one event
448 opened on each thread and aggregation is performed across them.
449
450 2. Prefix or glob wildcard matching is used for the PMU name. For
451 example, multiple memory controller PMUs may exist typically with a
452 suffix of _0, _1, etc. By default the event counts will all be
453 combined if the PMU is specified without the suffix such as
454 uncore_imc rather than uncore_imc_0.
455
456 3. Aliases, which are listed immediately after the Kernel PMU events
457 by perf list, are used.
458
459 --hybrid-merge::
460 Merge core event counts from all core PMUs. In hybrid or big.LITTLE
461 systems by default each core PMU will report its count
462 separately. This option forces core PMU counts to be combined to give
463 a behavior closer to having a single CPU type in the system.
464
465 --topdown::
466 Print top-down metrics supported by the CPU. This allows to determine
467 bottle necks in the CPU pipeline for CPU bound workloads, by breaking
468 the cycles consumed down into frontend bound, backend bound, bad
469 speculation and retiring.
470
471 Frontend bound means that the CPU cannot fetch and decode instructions fast
472 enough. Backend bound means that computation or memory access is the bottle
473 neck. Bad Speculation means that the CPU wasted cycles due to branch
474 mispredictions and similar issues. Retiring means that the CPU computed without
475 an apparently bottleneck. The bottleneck is only the real bottleneck
476 if the workload is actually bound by the CPU and not by something else.
477
478 For best results it is usually a good idea to use it with interval
479 mode like -I 1000, as the bottleneck of workloads can change often.
480
481 This enables --metric-only, unless overridden with --no-metric-only.
482
483 The following restrictions only apply to older Intel CPUs and Atom,
484 on newer CPUs (IceLake and later) TopDown can be collected for any thread:
485
486 The top down metrics are collected per core instead of per
487 CPU thread. Per core mode is automatically enabled
488 and -a (global monitoring) is needed, requiring root rights or
489 perf.perf_event_paranoid=-1.
490
491 Topdown uses the full Performance Monitoring Unit, and needs
492 disabling of the NMI watchdog (as root):
493 echo 0 > /proc/sys/kernel/nmi_watchdog
494 for best results. Otherwise the bottlenecks may be inconsistent
495 on workload with changing phases.
496
497 To interpret the results it is usually needed to know on which
498 CPUs the workload runs on. If needed the CPUs can be forced using
499 taskset.
500
501 --record-tpebs::
502 Enable automatic sampling on Intel TPEBS retire_latency events (event with :R
503 modifier). Without this option, perf would not capture dynamic retire_latency
504 at runtime. Currently, a zero value is assigned to the retire_latency event when
505 this option is not set. The TPEBS hardware feature starts from Intel Granite
506 Rapids microarchitecture. This option only exists in X86_64 and is meaningful on
507 Intel platforms with TPEBS feature.
508
509 --td-level::
510 Print the top-down statistics that equal the input level. It allows
511 users to print the interested top-down metrics level instead of the
512 level 1 top-down metrics.
513
514 As the higher levels gather more metrics and use more counters they
515 will be less accurate. By convention a metric can be examined by
516 appending '_group' to it and this will increase accuracy compared to
517 gathering all metrics for a level. For example, level 1 analysis may
518 highlight 'tma_frontend_bound'. This metric may be drilled into with
519 'tma_frontend_bound_group' with
520 'perf stat -M tma_frontend_bound_group...'.
521
522 Error out if the input is higher than the supported max level.
523
524 --smi-cost::
525 Measure SMI cost if msr/aperf/ and msr/smi/ events are supported.
526
527 During the measurement, the /sys/device/cpu/freeze_on_smi will be set to
528 freeze core counters on SMI.
529 The aperf counter will not be effected by the setting.
530 The cost of SMI can be measured by (aperf - unhalted core cycles).
531
532 In practice, the percentages of SMI cycles is very useful for performance
533 oriented analysis. --metric_only will be applied by default.
534 The output is SMI cycles%, equals to (aperf - unhalted core cycles) / aperf
535
536 Users who wants to get the actual value can apply --no-metric-only.
537
538 --all-kernel::
539 Configure all used events to run in kernel space.
540
541 --all-user::
542 Configure all used events to run in user space.
543
544 --percore-show-thread::
545 The event modifier "percore" has supported to sum up the event counts
546 for all hardware threads in a core and show the counts per core.
547
548 This option with event modifier "percore" enabled also sums up the event
549 counts for all hardware threads in a core but show the sum counts per
550 hardware thread. This is essentially a replacement for the any bit and
551 convenient for post processing.
552
553 --summary::
554 Print summary for interval mode (-I).
555
556 --no-csv-summary::
557 Don't print 'summary' at the first column for CVS summary output.
558 This option must be used with -x and --summary.
559
560 This option can be enabled in perf config by setting the variable
561 'stat.no-csv-summary'.
562
563 $ perf config stat.no-csv-summary=true
564
565 --cputype::
566 Only enable events on applying cpu with this type for hybrid platform
567 (e.g. core or atom)"
568
569 EXAMPLES
570 --------
571
572 $ perf stat \-- make
573
574 Performance counter stats for 'make':
575
576 83723.452481 task-clock:u (msec) # 1.004 CPUs utilized
577 0 context-switches:u # 0.000 K/sec
578 0 cpu-migrations:u # 0.000 K/sec
579 3,228,188 page-faults:u # 0.039 M/sec
580 229,570,665,834 cycles:u # 2.742 GHz
581 313,163,853,778 instructions:u # 1.36 insn per cycle
582 69,704,684,856 branches:u # 832.559 M/sec
583 2,078,861,393 branch-misses:u # 2.98% of all branches
584
585 83.409183620 seconds time elapsed
586
587 74.684747000 seconds user
588 8.739217000 seconds sys
589
590 TIMINGS
591 -------
592 As displayed in the example above we can display 3 types of timings.
593 We always display the time the counters were enabled/alive:
594
595 83.409183620 seconds time elapsed
596
597 For workload sessions we also display time the workloads spent in
598 user/system lands:
599
600 74.684747000 seconds user
601 8.739217000 seconds sys
602
603 Those times are the very same as displayed by the 'time' tool.
604
605 CSV FORMAT
606 ----------
607
608 With -x, perf stat is able to output a not-quite-CSV format output
609 Commas in the output are not put into "". To make it easy to parse
610 it is recommended to use a different character like -x \;
611
612 The fields are in this order:
613
614 - optional usec time stamp in fractions of second (with -I xxx)
615 - optional CPU, core, or socket identifier
616 - optional number of logical CPUs aggregated
617 - counter value
618 - unit of the counter value or empty
619 - event name
620 - run time of counter
621 - percentage of measurement time the counter was running
622 - optional variance if multiple values are collected with -r
623 - optional metric value
624 - optional unit of metric
625
626 Additional metrics may be printed with all earlier fields being empty.
627
628 include::intel-hybrid.txt[]
629
630 JSON FORMAT
631 -----------
632
633 With -j, perf stat is able to print out a JSON format output
634 that can be used for parsing.
635
636 - timestamp : optional usec time stamp in fractions of second (with -I)
637 - optional aggregate options:
638 - core : core identifier (with --per-core)
639 - die : die identifier (with --per-die)
640 - socket : socket identifier (with --per-socket)
641 - node : node identifier (with --per-node)
642 - thread : thread identifier (with --per-thread)
643 - counter-value : counter value
644 - unit : unit of the counter value or empty
645 - event : event name
646 - variance : optional variance if multiple values are collected (with -r)
647 - runtime : run time of counter
648 - metric-value : optional metric value
649 - metric-unit : optional unit of metric
650
651 SEE ALSO
652 --------
653 linkperf:perf-top[1], linkperf:perf-list[1]
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.