6 perf-record - Run a command and record its profile into perf.data
11 'perf record' [-e <EVENT> | --event=EVENT] [-a] <command>
12 'perf record' [-e <EVENT> | --event=EVENT] [-a] \-- <command> [<options>]
16 This command runs a command and gathers a performance counter profile
17 from it, into perf.data - without displaying anything.
19 This file can then be inspected later on, using 'perf report'.
25 Any command you can specify in a shell.
29 Select the PMU event. Selection can be:
31 - a symbolic event name (use 'perf list' to list all events)
33 - a raw PMU event in the form of rN where N is a hexadecimal value
34 that represents the raw register encoding with the layout of the
35 event control registers as described by entries in
36 /sys/bus/event_source/devices/cpu/format/*.
38 - a symbolic or raw PMU event followed by an optional colon
39 and a list of event modifiers, e.g., cpu-cycles:p. See the
40 linkperf:perf-list[1] man page for details on event modifiers.
42 - a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where
43 'param1', 'param2', etc are defined as formats for the PMU in
44 /sys/bus/event_source/devices/<pmu>/format/*.
46 - a symbolically formed event like 'pmu/config=M,config1=N,config3=K/'
48 where M, N, K are numbers (in decimal, hex, octal format). Acceptable
49 values for each of 'config', 'config1' and 'config2' are defined by
50 corresponding entries in /sys/bus/event_source/devices/<pmu>/format/*
51 param1 and param2 are defined as formats for the PMU in:
52 /sys/bus/event_source/devices/<pmu>/format/*
54 There are also some parameters which are not defined in .../<pmu>/format/*.
55 These params can be used to overload default config values per event.
56 Here are some common parameters:
57 - 'period': Set event sampling period
58 - 'freq': Set event sampling frequency
59 - 'time': Disable/enable time stamping. Acceptable values are 1 for
60 enabling time stamping. 0 for disabling time stamping.
62 - 'call-graph': Disable/enable callgraph. Acceptable str are "fp" for
63 FP mode, "dwarf" for DWARF mode, "lbr" for LBR mode and
64 "no" for disable callgraph.
65 - 'stack-size': user stack size for dwarf mode
66 - 'name' : User defined event name. Single quotes (') may be used to
67 escape symbols in the name from parsing by shell and tool
68 like this: name=\'CPU_CLK_UNHALTED.THREAD:cmask=0x1\'.
69 - 'aux-output': Generate AUX records instead of events. This requires
70 that an AUX area event is also provided.
71 - 'aux-sample-size': Set sample size for AUX area sampling. If the
72 '--aux-sample' option has been used, set aux-sample-size=0 to disable
73 AUX area sampling for the event.
75 See the linkperf:perf-list[1] man page for more parameters.
77 Note: If user explicitly sets options which conflict with the params,
78 the value set by the parameters will be overridden.
80 Also not defined in .../<pmu>/format/* are PMU driver specific
81 configuration parameters. Any configuration parameter preceded by
82 the letter '@' is not interpreted in user space and sent down directly
83 to the PMU driver. For example:
85 perf record -e some_event/@cfg1,@cfg2=config/ ...
87 will see 'cfg1' and 'cfg2=config' pushed to the PMU driver associated
88 with the event for further processing. There is no restriction on
89 what the configuration parameters are, as long as their semantic is
90 understood and supported by the PMU driver.
92 - a hardware breakpoint event in the form of '\mem:addr[/len][:access]'
93 where addr is the address in memory you want to break in.
94 Access is the memory access type (read, write, execute) it can
95 be passed as follows: '\mem:addr[:[r][w][x]]'. len is the range,
96 number of bytes from specified addr, which the breakpoint will cover.
97 If you want to profile read-write accesses in 0x1000, just set
99 If you want to profile write accesses in [0x1000~1008), just set
102 - a group of events surrounded by a pair of brace ("{event1,event2,...}").
103 Each event is separated by commas and the group should be quoted to
104 prevent the shell interpretation. You also need to use --group on
105 "perf report" to view group events together.
108 Event filter. This option should follow an event selector (-e).
109 If the event is a tracepoint, the filter string will be parsed by
110 the kernel. If the event is a hardware trace PMU (e.g. Intel PT
111 or CoreSight), it'll be processed as an address filter. Otherwise
112 it means a general filter using BPF which can be applied for any
117 In the case of tracepoints, multiple '--filter' options are combined
122 A hardware trace PMU advertises its ability to accept a number of
123 address filters by specifying a non-zero value in
124 /sys/bus/event_source/devices/<pmu>/nr_addr_filters.
126 Address filters have the format:
128 filter|start|stop|tracestop <start> [/ <size>] [@<file name>]
131 - 'filter': defines a region that will be traced.
132 - 'start': defines an address at which tracing will begin.
133 - 'stop': defines an address at which tracing will stop.
134 - 'tracestop': defines a region in which tracing will stop.
136 <file name> is the name of the object file, <start> is the offset to the
137 code to trace in that file, and <size> is the size of the region to
138 trace. 'start' and 'stop' filters need not specify a <size>.
140 If no object file is specified then the kernel is assumed, in which case
141 the start address must be a current kernel memory address.
143 <start> can also be specified by providing the name of a symbol. If the
144 symbol name is not unique, it can be disambiguated by inserting #n where
145 'n' selects the n'th symbol in address order. Alternately #0, #g or #G
146 select only a global symbol. <size> can also be specified by providing
147 the name of a symbol, in which case the size is calculated to the end
148 of that symbol. For 'filter' and 'tracestop' filters, if <size> is
149 omitted and <start> is a symbol, then the size is calculated to the end
152 If <size> is omitted and <start> is '*', then the start and size will
153 be calculated from the first and last symbols, i.e. to trace the whole
156 If symbol names (or '*') are provided, they must be surrounded by white
159 The filter passed to the kernel is not necessarily the same as entered.
160 To see the filter that is passed, use the -v option.
162 The kernel may not be able to configure a trace region if it is not
163 within a single mapping. MMAP events (or /proc/<pid>/maps) can be
164 examined to determine if that is a possibility.
166 Multiple filters can be separated with space or comma.
170 A BPF filter can access the sample data and make a decision based on the
171 data. Users need to set an appropriate sample type to use the BPF
172 filter. BPF filters need root privilege.
174 The sample data field can be specified in lower case letter. Multiple
175 filters can be separated with comma. For example,
177 --filter 'period > 1000, cpu == 1'
179 --filter 'mem_op == load || mem_op == store, mem_lvl > l1'
181 The former filter only accept samples with period greater than 1000 AND
182 CPU number is 1. The latter one accepts either load and store memory
183 operations but it should have memory level above the L1. Since the
184 mem_op and mem_lvl fields come from the (memory) data_source, it'd only
185 work with some events which set the data_source field.
187 Also user should request to collect that information (with -d option in
188 the above case). Otherwise, the following message will be shown.
190 $ sudo perf record -e cycles --filter 'mem_op == load'
191 Error: cycles event does not have PERF_SAMPLE_DATA_SRC
192 Hint: please add -d option to perf record.
193 failed to set filter "BPF" on event cycles with 22 (Invalid argument)
195 Essentially the BPF filter expression is:
197 <term> <operator> <value> (("," | "||") <term> <operator> <value>)*
199 The <term> can be one of:
200 ip, id, tid, pid, cpu, time, addr, period, txn, weight, phys_addr,
201 code_pgsz, data_pgsz, weight1, weight2, weight3, ins_lat, retire_lat,
202 p_stage_cyc, mem_op, mem_lvl, mem_snoop, mem_remote, mem_lock,
203 mem_dtlb, mem_blk, mem_hops
205 The <operator> can be one of:
206 ==, !=, >, >=, <, <=, &
208 The <value> can be one of:
209 <number> (for any term)
210 na, load, store, pfetch, exec (for mem_op)
211 l1, l2, l3, l4, cxl, io, any_cache, lfb, ram, pmem (for mem_lvl)
212 na, none, hit, miss, hitm, fwd, peer (for mem_snoop)
213 remote (for mem_remote)
214 na, locked (for mem_locked)
215 na, l1_hit, l1_miss, l2_hit, l2_miss, any_hit, any_miss, walk, fault (for mem_dtlb)
216 na, by_data, by_addr (for mem_blk)
217 hops0, hops1, hops2, hops3 (for mem_hops)
220 Don't record events issued by perf itself. This option should follow
221 an event selector (-e) which selects tracepoint event(s). It adds a
222 filter expression 'common_pid != $PERFPID' to filters. If other
223 '--filter' exists, the new filter expression will be combined with
228 System-wide collection from all CPUs (default if no target is specified).
232 Record events on existing process ID (comma separated list).
236 Record events on existing thread ID (comma separated list).
237 This option also disables inheritance by default. Enable it by adding
242 Record events in threads owned by uid. Name or number.
246 Collect data with this RT SCHED_FIFO priority.
249 Collect data without buffering.
253 Event period to sample.
261 Child tasks do not inherit counters.
265 Profile at this frequency. Use 'max' to use the currently maximum
266 allowed frequency, i.e. the value in the kernel.perf_event_max_sample_rate
267 sysctl. Will throttle down to the currently maximum allowed frequency.
271 Fail if the specified frequency can't be used.
275 Number of mmap data pages (must be a power of two) or size
276 specification with appended unit character - B/K/M/G. The
277 size is rounded up to have nearest pages power of two value.
278 Also, by adding a comma, the number of mmap pages for AUX
279 area tracing can be specified.
282 Enables call-graph (stack chain/backtrace) recording for both
283 kernel space and user space.
286 Setup and enable call-graph (stack chain/backtrace) recording,
287 implies -g. Default is "fp" (for user space).
289 The unwinding method used for kernel space is dependent on the
290 unwinder used by the active kernel configuration, i.e
291 CONFIG_UNWINDER_FRAME_POINTER (fp) or CONFIG_UNWINDER_ORC (orc)
293 Any option specified here controls the method used for user space.
295 Valid options are "fp" (frame pointer), "dwarf" (DWARF's CFI -
296 Call Frame Information) or "lbr" (Hardware Last Branch Record
299 In some systems, where binaries are build with gcc
300 --fomit-frame-pointer, using the "fp" method will produce bogus
301 call graphs, using "dwarf", if available (perf tools linked to
302 the libunwind or libdw library) should be used instead.
303 Using the "lbr" method doesn't require any compiler options. It
304 will produce call graphs from the hardware LBR registers. The
305 main limitation is that it is only available on new Intel
306 platforms, such as Haswell. It can only get user call chain. It
307 doesn't work with branch stack sampling at the same time.
309 When "dwarf" recording is used, perf also records (user) stack dump
310 when sampled. Default size of the stack dump is 8192 (bytes).
311 User can change the size by passing the size after comma like
312 "--call-graph dwarf,4096".
314 When "fp" recording is used, perf tries to save stack enties
315 up to the number specified in sysctl.kernel.perf_event_max_stack
316 by default. User can change the number by passing it after comma
317 like "--call-graph fp,32".
321 Don't print any warnings or messages, useful for scripting.
325 Be more verbose (show counter open errors, etc).
329 Record per-thread event counts. Use it with 'perf report -T' to see
334 Record the sample virtual addresses.
337 Record the sample physical addresses.
340 Record the sampled data address data page size.
343 Record the sampled code address (ip) page size
347 Record the sample timestamps. Use it with 'perf report -D' to see the
348 timestamps, for instance.
352 Record the sample period.
355 Record the sample cpu.
357 --sample-identifier::
358 Record the sample identifier i.e. PERF_SAMPLE_IDENTIFIER bit set in
359 the sample_type member of the struct perf_event_attr argument to the
360 perf_event_open system call.
368 Collect raw sample records from all opened counters (default for tracepoint counters).
372 Collect samples only on the list of CPUs provided. Multiple CPUs can be provided as a
373 comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0-2.
374 In per-thread mode with inheritance mode on (default), samples are captured only when
375 the thread executes on the designated CPUs. Default is to monitor all CPUs.
377 User space tasks can migrate between CPUs, so when tracing selected CPUs,
378 a dummy event is created to track sideband for all CPUs.
382 Do not save the build ids of binaries in the perf.data files. This skips
383 post processing after recording, which sometimes makes the final step in
384 the recording process to take a long time, as it needs to process all
385 events looking for mmap records. The downside is that it can misresolve
386 symbols if the workload binaries used when recording get locally rebuilt
387 or upgraded, because the only key available in this case is the
388 pathname. You can also set the "record.build-id" config variable to
389 'skip to have this behaviour permanently.
393 Do not update the buildid cache. This saves some overhead in situations
394 where the information in the perf.data file (which includes buildids)
395 is sufficient. You can also set the "record.build-id" config variable to
396 'no-cache' to have the same effect.
400 monitor only in the container (cgroup) called "name". This option is available only
401 in per-cpu mode. The cgroup filesystem must be mounted. All threads belonging to
402 container "name" are monitored when they run on the monitored CPUs. Multiple cgroups
403 can be provided. Each cgroup is applied to the corresponding event, i.e., first cgroup
404 to first event, second cgroup to second event and so on. It is possible to provide
405 an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
406 corresponding events, i.e., they always refer to events defined earlier on the command
407 line. If the user wants to track multiple events for a specific cgroup, the user can
408 use '-e e1 -e e2 -G foo,foo' or just use '-e e1 -e e2 -G foo'.
410 If wanting to monitor, say, 'cycles' for a cgroup and also for system wide, this
411 command line can be used: 'perf stat -e cycles -G cgroup_name -a -e cycles'.
415 Enable taken branch stack sampling. Any type of taken branch may be sampled.
416 This is a shortcut for --branch-filter any. See --branch-filter for more infos.
420 Enable taken branch stack sampling. Each sample captures a series of consecutive
421 taken branches. The number of branches captured with each sample depends on the
422 underlying hardware, the type of branches of interest, and the executed code.
423 It is possible to select the types of branches captured by enabling filters. The
424 following filters are defined:
426 - any: any type of branches
427 - any_call: any function call or system call
428 - any_ret: any function return or system call return
429 - ind_call: any indirect branch
430 - ind_jmp: any indirect jump
431 - call: direct calls, including far (to/from kernel) calls
432 - u: only when the branch target is at the user level
433 - k: only when the branch target is in the kernel
434 - hv: only when the target is at the hypervisor level
435 - in_tx: only when the target is in a hardware transaction
436 - no_tx: only when the target is not in a hardware transaction
437 - abort_tx: only when the target is a hardware transaction abort
438 - cond: conditional branches
439 - call_stack: save call stack
440 - no_flags: don't save branch flags e.g prediction, misprediction etc
441 - no_cycles: don't save branch cycles
442 - hw_index: save branch hardware index
443 - save_type: save branch type during sampling in case binary is not available later
444 For the platforms with Intel Arch LBR support (12th-Gen+ client or
445 4th-Gen Xeon+ server), the save branch type is unconditionally enabled
446 when the taken branch stack sampling is enabled.
447 - priv: save privilege state during sampling in case binary is not available later
450 The option requires at least one branch type among any, any_call, any_ret, ind_call, cond.
451 The privilege levels may be omitted, in which case, the privilege levels of the associated
452 event are applied to the branch filter. Both kernel (k) and hypervisor (hv) privilege
453 levels are subject to permissions. When sampling on multiple events, branch stack sampling
454 is enabled for all the sampling events. The sampled branch type is the same for all events.
455 The various filters must be specified as a comma separated list: --branch-filter any_ret,u,k
456 Note that this feature may not be available on all processors.
460 Enable weightened sampling. An additional weight is recorded per sample and can be
461 displayed with the weight and local_weight sort keys. This currently works for TSX
462 abort events and some memory events in precise mode on modern Intel CPUs.
465 Record events of type PERF_RECORD_NAMESPACES. This enables 'cgroup_id' sort key.
468 Record events of type PERF_RECORD_CGROUP. This enables 'cgroup' sort key.
471 Record transaction flags for transaction related events.
474 Use per-thread mmaps. By default per-cpu mmaps are created. This option
475 overrides that and uses per-thread mmaps. A side-effect of that is that
476 inheritance is automatically disabled. --per-thread is ignored with a warning
477 if combined with -a or -C options.
481 After starting the program, wait msecs before measuring (-1: start with events
482 disabled), or enable events only for specified ranges of msecs (e.g.
483 -D 10-20,30-40 means wait 10 msecs, enable for 10 msecs, wait 10 msecs, enable
484 for 10 msecs, then stop). Note, delaying enabling of events is useful to filter
485 out the startup phase of the program, which is often very different.
489 Capture machine state (registers) at interrupt, i.e., on counter overflows for
490 each sample. List of captured registers depends on the architecture. This option
491 is off by default. It is possible to select the registers to sample using their
492 symbolic names, e.g. on x86, ax, si. To list the available registers use
493 --intr-regs=\?. To name registers, pass a comma separated list such as
494 --intr-regs=ax,bx. The list of register is architecture dependent.
497 Similar to -I, but capture user registers at sample time. To list the available
498 user registers use --user-regs=\?.
501 Record running and enabled time for read events (:S)
505 Sets the clock id to use for the various time fields in the perf_event_type
506 records. See clock_gettime(). In particular CLOCK_MONOTONIC and
507 CLOCK_MONOTONIC_RAW are supported, some events might also allow
508 CLOCK_BOOTTIME, CLOCK_REALTIME and CLOCK_TAI.
512 Select AUX area tracing Snapshot Mode. This option is valid only with an
513 AUX area tracing event. Optionally, certain snapshot capturing parameters
514 can be specified in a string that follows this option:
516 - 'e': take one last snapshot on exit; guarantees that there is at least one
517 snapshot in the output file;
518 - <size>: if the PMU supports this, specify the desired snapshot size.
520 In Snapshot Mode trace data is captured only when signal SIGUSR2 is received
521 and on exit if the above 'e' option is given.
523 --aux-sample[=OPTIONS]::
524 Select AUX area sampling. At least one of the events selected by the -e option
525 must be an AUX area event. Samples on other events will be created containing
526 data from the AUX area. Optionally sample size may be specified, otherwise it
530 When processing pre-existing threads /proc/XXX/mmap, it may take a long time,
531 because the file may be huge. A time out is needed in such cases.
532 This option sets the time out limit. The default value is 500 ms.
535 Record context switch events i.e. events of type PERF_RECORD_SWITCH or
536 PERF_RECORD_SWITCH_CPU_WIDE. In some cases (e.g. Intel PT, CoreSight or Arm SPE)
537 switch events will be enabled automatically, which can be suppressed by
538 by the option --no-switch-events.
541 Specify vmlinux path which has debuginfo.
542 (enabled when BPF prologue is on)
545 Record build-id of all DSOs regardless whether it's actually hit or not.
548 Record build ids in mmap2 events, disables build id cache (implies --no-buildid).
551 Use <n> control blocks in asynchronous (Posix AIO) trace writing mode (default: 1, max: 4).
552 Asynchronous mode is supported only when linking Perf tool with libc library
553 providing implementation for Posix AIO API.
556 Set affinity mask of trace reading thread according to the policy defined by 'mode' value:
558 - node - thread affinity mask is set to NUMA node cpu mask of the processed mmap buffer
559 - cpu - thread affinity mask is set to cpu of the processed mmap buffer
561 --mmap-flush=number::
563 Specify minimal number of bytes that is extracted from mmap data pages and
564 processed for output. One can specify the number using B/K/M/G suffixes.
566 The maximal allowed value is a quarter of the size of mmaped data pages.
568 The default option value is 1 byte which means that every time that the output
569 writing thread finds some new data in the mmaped buffer the data is extracted,
570 possibly compressed (-z) and written to the output, perf.data or pipe.
572 Larger data chunks are compressed more effectively in comparison to smaller
573 chunks so extraction of larger chunks from the mmap data pages is preferable
574 from the perspective of output size reduction.
576 Also at some cases executing less output write syscalls with bigger data size
577 can take less time than executing more output write syscalls with smaller data
578 size thus lowering runtime profiling overhead.
581 --compression-level[=n]::
582 Produce compressed trace using specified level n (default: 1 - fastest compression,
586 Configure all used events to run in kernel space.
589 Configure all used events to run in user space.
591 --kernel-callchains::
592 Collect callchains only from kernel space. I.e. this option sets
593 perf_event_attr.exclude_callchain_user to 1.
596 Collect callchains only from user space. I.e. this option sets
597 perf_event_attr.exclude_callchain_kernel to 1.
599 Don't use both --kernel-callchains and --user-callchains at the same time or no
600 callchains will be collected.
603 Append timestamp to output file name.
605 --timestamp-boundary::
606 Record timestamp boundary (time of first/last samples).
608 --switch-output[=mode]::
609 Generate multiple perf.data files, timestamp prefixed, switching to a new one
610 based on 'mode' value:
612 - "signal" - when receiving a SIGUSR2 (default value) or
613 - <size> - when reaching the size threshold, size is expected to
614 be a number with appended unit character - B/K/M/G
615 - <time> - when reaching the time threshold, size is expected to
616 be a number with appended unit character - s/m/h/d
618 Note: the precision of the size threshold hugely depends
619 on your configuration - the number and size of your ring
620 buffers (-m). It is generally more precise for higher sizes
621 (like >5M), for lower values expect different sizes.
623 A possible use case is to, given an external event, slice the perf.data file
624 that gets then processed, possibly via a perf script, to decide if that
625 particular perf.data snapshot should be kept or not.
627 Implies --timestamp-filename, --no-buildid and --no-buildid-cache.
628 The reason for the latter two is to reduce the data file switching
629 overhead. You can still switch them on with:
631 --switch-output --no-no-buildid --no-no-buildid-cache
633 --switch-output-event::
634 Events that will cause the switch of the perf.data file, auto-selecting
635 --switch-output=signal, the results are similar as internally the side band
636 thread will also send a SIGUSR2 to the main one.
638 Uses the same syntax as --event, it will just not be recorded, serving only to
639 switch the perf.data file as soon as the --switch-output event is processed by
640 a separate sideband thread.
642 This sideband thread is also used to other purposes, like processing the
643 PERF_RECORD_BPF_EVENT records as they happen, asking the kernel for extra BPF
646 --switch-max-files=N::
648 When rotating perf.data with --switch-output, only keep N files.
651 Parse options then exit. --dry-run can be used to detect errors in cmdline
654 'perf record --dry-run -e' can act as a BPF script compiler if llvm.dump-obj
655 in config file is set to true.
658 Collect and synthesize given type of events (comma separated). Note that
659 this option controls the synthesis from the /proc filesystem which represent
660 task status for pre-existing threads.
662 Kernel (and some other) events are recorded regardless of the
663 choice in this option. For example, --synth=no would have MMAP events for
668 - 'task' - synthesize FORK and COMM events for each task
669 - 'mmap' - synthesize MMAP events for each process (implies 'task')
670 - 'cgroup' - synthesize CGROUP events for each cgroup
671 - 'all' - synthesize all events (default)
672 - 'no' - do not synthesize any of the above events
675 Instead of collecting non-sample events (for example, fork, comm, mmap) at
676 the beginning of record, collect them during finalizing an output file.
677 The collected non-sample events reflects the status of the system when
681 Makes all events use an overwritable ring buffer. An overwritable ring
682 buffer works like a flight recorder: when it gets full, the kernel will
683 overwrite the oldest records, that thus will never make it to the
686 When '--overwrite' and '--switch-output' are used perf records and drops
687 events until it receives a signal, meaning that something unusual was
688 detected that warrants taking a snapshot of the most current events,
689 those fitting in the ring buffer at that moment.
691 'overwrite' attribute can also be set or canceled for an event using
692 config terms. For example: 'cycles/overwrite/' and 'instructions/no-overwrite/'.
694 Implies --tail-synthesize.
697 Make a copy of /proc/kcore and place it into a directory with the perf data file.
700 Limit the sample data max size, <size> is expected to be a number with
701 appended unit character - B/K/M/G
703 --num-thread-synthesize::
704 The number of threads to run when synthesizing events for existing processes.
705 By default, the number of threads equals 1.
708 --pfm-events events::
709 Select a PMU event using libpfm4 syntax (see http://perfmon2.sf.net)
710 including support for event filters. For example '--pfm-events
711 inst_retired:any_p:u:c=1:i'. More than one event can be passed to the
712 option using the comma separator. Hardware events and generic hardware
713 events cannot be mixed together. The latter must be used with the -e
714 option. The -e option and this one can be mixed and matched. Events
715 can be grouped using the {} notation.
718 --control=fifo:ctl-fifo[,ack-fifo]::
719 --control=fd:ctl-fd[,ack-fd]::
720 ctl-fifo / ack-fifo are opened and used as ctl-fd / ack-fd as follows.
721 Listen on ctl-fd descriptor for command to control measurement.
725 - 'enable' : enable events
726 - 'disable' : disable events
727 - 'enable name' : enable event 'name'
728 - 'disable name' : disable event 'name'
729 - 'snapshot' : AUX area tracing snapshot).
730 - 'stop' : stop perf record
732 - 'evlist [-v|-g|-F] : display all events
734 -F Show just the sample frequency used for each event.
736 -g Show event group information.
738 Measurements can be started with events disabled using --delay=-1 option. Optionally
739 send control command completion ('ack\n') to ack-fd descriptor to synchronize with the
740 controlling process. Example of bash shell script to enable and disable events during
747 ctl_fifo=${ctl_dir}perf_ctl.fifo
748 test -p ${ctl_fifo} && unlink ${ctl_fifo}
750 exec {ctl_fd}<>${ctl_fifo}
752 ctl_ack_fifo=${ctl_dir}perf_ctl_ack.fifo
753 test -p ${ctl_ack_fifo} && unlink ${ctl_ack_fifo}
754 mkfifo ${ctl_ack_fifo}
755 exec {ctl_fd_ack}<>${ctl_ack_fifo}
757 perf record -D -1 -e cpu-cycles -a \
758 --control fd:${ctl_fd},${ctl_fd_ack} \
762 sleep 5 && echo 'enable' >&${ctl_fd} && read -u ${ctl_fd_ack} e1 && echo "enabled(${e1})"
763 sleep 10 && echo 'disable' >&${ctl_fd} && read -u ${ctl_fd_ack} d1 && echo "disabled(${d1})"
766 unlink ${ctl_ack_fifo}
775 Write collected trace data into several data files using parallel threads.
776 <spec> value can be user defined list of masks. Masks separated by colon
777 define CPUs to be monitored by a thread and affinity mask of that thread
778 is separated by slash:
780 <cpus mask 1>/<affinity mask 1>:<cpus mask 2>/<affinity mask 2>:...
782 CPUs or affinity masks must not overlap with other corresponding masks.
783 Invalid CPUs are ignored, but masks containing only invalid CPUs are not
786 For example user specification like the following:
790 specifies parallel threads layout that consists of two threads,
791 the first thread monitors CPUs 0 and 2-4 with the affinity mask 2-4,
792 the second monitors CPUs 1 and 5-7 with the affinity mask 5-7.
794 <spec> value can also be a string meaning predefined parallel threads
797 - cpu - create new data streaming thread for every monitored cpu
798 - core - create new thread to monitor CPUs grouped by a core
799 - package - create new thread to monitor CPUs grouped by a package
800 - numa - create new threed to monitor CPUs grouped by a NUMA domain
802 Predefined layouts can be used on systems with large number of CPUs in
803 order not to spawn multiple per-cpu streaming threads but still avoid LOST
804 events in data directory files. Option specified with no or empty value
805 defaults to CPU layout. Masks defined or provided by the option value are
806 filtered through the mask provided by -C option.
808 --debuginfod[=URLs]::
809 Specify debuginfod URL to be used when cacheing perf.data binaries,
810 it follows the same syntax as the DEBUGINFOD_URLS variable, like:
812 http://192.168.122.174:8002
814 If the URLs is not specified, the value of DEBUGINFOD_URLS
815 system environment variable is used.
818 Enable off-cpu profiling with BPF. The BPF program will collect
819 task scheduling information with (user) stacktrace and save them
820 as sample data of a software event named "offcpu-time". The
821 sample period will have the time the task slept in nanoseconds.
823 Note that BPF can collect stack traces using frame pointer ("fp")
824 only, as of now. So the applications built without the frame
825 pointer might see bogus addresses.
827 include::intel-hybrid.txt[]
831 linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]