2010-11-17 01:45:39 +08:00
|
|
|
perf-script(1)
|
2010-05-05 22:23:27 +08:00
|
|
|
=============
|
2009-09-11 18:12:54 +08:00
|
|
|
|
|
|
|
NAME
|
|
|
|
----
|
2010-11-17 01:45:39 +08:00
|
|
|
perf-script - Read perf.data (created by perf record) and display trace output
|
2009-09-11 18:12:54 +08:00
|
|
|
|
|
|
|
SYNOPSIS
|
|
|
|
--------
|
|
|
|
[verse]
|
2010-11-17 01:45:39 +08:00
|
|
|
'perf script' [<options>]
|
|
|
|
'perf script' [<options>] record <script> [<record-options>] <command>
|
|
|
|
'perf script' [<options>] report <script> [script-args]
|
|
|
|
'perf script' [<options>] <script> <required-script-args> [<record-options>] <command>
|
|
|
|
'perf script' [<options>] <top-script> [script-args]
|
2009-09-11 18:12:54 +08:00
|
|
|
|
|
|
|
DESCRIPTION
|
|
|
|
-----------
|
|
|
|
This command reads the input file and displays the trace recorded.
|
|
|
|
|
2010-11-17 01:45:39 +08:00
|
|
|
There are several variants of perf script:
|
2009-12-15 16:53:40 +08:00
|
|
|
|
2010-11-17 01:45:39 +08:00
|
|
|
'perf script' to see a detailed trace of the workload that was
|
2009-12-15 16:53:40 +08:00
|
|
|
recorded.
|
|
|
|
|
2010-01-27 16:28:03 +08:00
|
|
|
You can also run a set of pre-canned scripts that aggregate and
|
|
|
|
summarize the raw trace data in various ways (the list of scripts is
|
2010-11-17 01:45:39 +08:00
|
|
|
available via 'perf script -l'). The following variants allow you to
|
2010-01-27 16:28:03 +08:00
|
|
|
record and run those scripts:
|
|
|
|
|
2010-11-17 01:45:39 +08:00
|
|
|
'perf script record <script> <command>' to record the events required
|
|
|
|
for 'perf script report'. <script> is the name displayed in the
|
|
|
|
output of 'perf script --list' i.e. the actual script name minus any
|
2010-11-10 22:19:35 +08:00
|
|
|
language extension. If <command> is not specified, the events are
|
|
|
|
recorded using the -a (system-wide) 'perf record' option.
|
2009-12-15 16:53:40 +08:00
|
|
|
|
2010-11-17 01:45:39 +08:00
|
|
|
'perf script report <script> [args]' to run and display the results
|
2010-11-10 22:19:35 +08:00
|
|
|
of <script>. <script> is the name displayed in the output of 'perf
|
2009-12-15 16:53:40 +08:00
|
|
|
trace --list' i.e. the actual script name minus any language
|
2010-11-17 01:45:39 +08:00
|
|
|
extension. The perf.data output from a previous run of 'perf script
|
2009-12-15 16:53:40 +08:00
|
|
|
record <script>' is used and should be present for this command to
|
2010-11-10 22:19:35 +08:00
|
|
|
succeed. [args] refers to the (mainly optional) args expected by
|
|
|
|
the script.
|
|
|
|
|
2010-11-17 01:45:39 +08:00
|
|
|
'perf script <script> <required-script-args> <command>' to both
|
2010-11-10 22:19:35 +08:00
|
|
|
record the events required for <script> and to run the <script>
|
|
|
|
using 'live-mode' i.e. without writing anything to disk. <script>
|
2010-11-17 01:45:39 +08:00
|
|
|
is the name displayed in the output of 'perf script --list' i.e. the
|
2010-11-10 22:19:35 +08:00
|
|
|
actual script name minus any language extension. If <command> is
|
|
|
|
not specified, the events are recorded using the -a (system-wide)
|
|
|
|
'perf record' option. If <script> has any required args, they
|
|
|
|
should be specified before <command>. This mode doesn't allow for
|
|
|
|
optional script args to be specified; if optional script args are
|
2010-11-17 01:45:39 +08:00
|
|
|
desired, they can be specified using separate 'perf script record'
|
|
|
|
and 'perf script report' commands, with the stdout of the record step
|
2010-11-10 22:19:35 +08:00
|
|
|
piped to the stdin of the report script, using the '-o -' and '-i -'
|
|
|
|
options of the corresponding commands.
|
|
|
|
|
2010-11-17 01:45:39 +08:00
|
|
|
'perf script <top-script>' to both record the events required for
|
2010-11-10 22:19:35 +08:00
|
|
|
<top-script> and to run the <top-script> using 'live-mode'
|
|
|
|
i.e. without writing anything to disk. <top-script> is the name
|
2010-11-17 01:45:39 +08:00
|
|
|
displayed in the output of 'perf script --list' i.e. the actual
|
2010-11-10 22:19:35 +08:00
|
|
|
script name minus any language extension; a <top-script> is defined
|
|
|
|
as any script name ending with the string 'top'.
|
|
|
|
|
2010-11-17 01:45:39 +08:00
|
|
|
[<record-options>] can be passed to the record steps of 'perf script
|
2010-11-10 22:19:35 +08:00
|
|
|
record' and 'live-mode' variants; this isn't possible however for
|
2010-11-17 01:45:39 +08:00
|
|
|
<top-script> 'live-mode' or 'perf script report' variants.
|
2009-12-15 16:53:40 +08:00
|
|
|
|
2010-01-27 16:28:03 +08:00
|
|
|
See the 'SEE ALSO' section for links to language-specific
|
|
|
|
information on how to write and run your own trace scripts.
|
|
|
|
|
2009-09-11 18:12:54 +08:00
|
|
|
OPTIONS
|
|
|
|
-------
|
2010-11-10 22:19:35 +08:00
|
|
|
<command>...::
|
|
|
|
Any command you can specify in a shell.
|
|
|
|
|
2009-09-11 18:12:54 +08:00
|
|
|
-D::
|
2010-11-17 01:45:39 +08:00
|
|
|
--dump-raw-script=::
|
2009-09-11 18:12:54 +08:00
|
|
|
Display verbose dump of the trace data.
|
|
|
|
|
2009-12-15 16:53:40 +08:00
|
|
|
-L::
|
|
|
|
--Latency=::
|
|
|
|
Show latency attributes (irqs/preemption disabled, etc).
|
|
|
|
|
|
|
|
-l::
|
|
|
|
--list=::
|
|
|
|
Display a list of available trace scripts.
|
|
|
|
|
2010-01-27 16:27:52 +08:00
|
|
|
-s ['lang']::
|
2009-11-25 15:15:51 +08:00
|
|
|
--script=::
|
|
|
|
Process trace data with the given script ([lang]:script[.ext]).
|
2010-01-27 16:27:52 +08:00
|
|
|
If the string 'lang' is specified in place of a script name, a
|
|
|
|
list of supported languages will be displayed instead.
|
2009-11-25 15:15:51 +08:00
|
|
|
|
|
|
|
-g::
|
|
|
|
--gen-script=::
|
2010-11-17 01:45:39 +08:00
|
|
|
Generate perf-script.[ext] starter script for given language,
|
2009-11-25 15:15:51 +08:00
|
|
|
using current perf.data.
|
|
|
|
|
2010-11-10 22:19:35 +08:00
|
|
|
-a::
|
|
|
|
Force system-wide collection. Scripts run without a <command>
|
|
|
|
normally use -a by default, while scripts run with a <command>
|
|
|
|
normally don't - this option allows the latter to be run in
|
|
|
|
system-wide mode.
|
|
|
|
|
2010-12-01 09:57:22 +08:00
|
|
|
-i::
|
|
|
|
--input=::
|
2011-12-07 17:02:54 +08:00
|
|
|
Input file name. (default: perf.data unless stdin is a fifo)
|
2010-12-01 09:57:22 +08:00
|
|
|
|
|
|
|
-d::
|
|
|
|
--debug-mode::
|
|
|
|
Do various checks like samples ordering and lost events.
|
2010-11-10 22:19:35 +08:00
|
|
|
|
perf script: Support custom field selection for output
Allow a user to select which fields to print to stdout for event data.
Options include comm (command name), tid (thread id), pid (process id),
time (perf timestamp), cpu, event (for event name), and trace (for
trace data).
Default is set to maintain compatibility with current output; this
feature does alter output format slightly -- no '-' between command
and pid/tid.
Thanks to Frederic Weisbecker for detailed suggestions on this approach.
Examples (output compressed)
1. trace, default format
perf record -ga -e sched:sched_switch
perf script
swapper 0 [000] 537.037184: sched_switch: prev_comm=swapper prev_pid=0...
sshd 1675 [000] 537.037309: sched_switch: prev_comm=sshd prev_pid=1675...
netstat 1692 [001] 537.038664: sched_switch: prev_comm=netstat prev_pid=1692...
2. trace, custom format
perf record -ga -e sched:sched_switch
perf script -f comm,pid,time,trace <--- omitting cpu and event name
swapper 0 537.037184: prev_comm=swapper prev_pid=0 prev_prio=120 ...
sshd 1675 537.037309: prev_comm=sshd prev_pid=1675 prev_prio=120 ...
netstat 1692 537.038664: prev_comm=netstat prev_pid=1692 prev_prio=120 ...
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1299734608-5223-5-git-send-email-daahern@cisco.com>
Signed-off-by: David Ahern <daahern@cisco.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-03-10 13:23:26 +08:00
|
|
|
-f::
|
2011-03-31 02:30:43 +08:00
|
|
|
--fields::
|
perf script: Support custom field selection for output
Allow a user to select which fields to print to stdout for event data.
Options include comm (command name), tid (thread id), pid (process id),
time (perf timestamp), cpu, event (for event name), and trace (for
trace data).
Default is set to maintain compatibility with current output; this
feature does alter output format slightly -- no '-' between command
and pid/tid.
Thanks to Frederic Weisbecker for detailed suggestions on this approach.
Examples (output compressed)
1. trace, default format
perf record -ga -e sched:sched_switch
perf script
swapper 0 [000] 537.037184: sched_switch: prev_comm=swapper prev_pid=0...
sshd 1675 [000] 537.037309: sched_switch: prev_comm=sshd prev_pid=1675...
netstat 1692 [001] 537.038664: sched_switch: prev_comm=netstat prev_pid=1692...
2. trace, custom format
perf record -ga -e sched:sched_switch
perf script -f comm,pid,time,trace <--- omitting cpu and event name
swapper 0 537.037184: prev_comm=swapper prev_pid=0 prev_prio=120 ...
sshd 1675 537.037309: prev_comm=sshd prev_pid=1675 prev_prio=120 ...
netstat 1692 537.038664: prev_comm=netstat prev_pid=1692 prev_prio=120 ...
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1299734608-5223-5-git-send-email-daahern@cisco.com>
Signed-off-by: David Ahern <daahern@cisco.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-03-10 13:23:26 +08:00
|
|
|
Comma separated list of fields to print. Options are:
|
2014-08-25 22:45:42 +08:00
|
|
|
comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period.
|
2011-05-31 03:08:23 +08:00
|
|
|
Field list can be prepended with the type, trace, sw or hw,
|
2011-03-10 13:23:28 +08:00
|
|
|
to indicate to which event type the field list applies.
|
2011-05-28 04:28:43 +08:00
|
|
|
e.g., -f sw:comm,tid,time,ip,sym and -f trace:time,cpu,trace
|
2011-03-10 13:23:27 +08:00
|
|
|
|
2011-03-31 02:30:43 +08:00
|
|
|
perf script -f <fields>
|
|
|
|
|
|
|
|
is equivalent to:
|
|
|
|
|
|
|
|
perf script -f trace:<fields> -f sw:<fields> -f hw:<fields>
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2011-03-31 02:30:43 +08:00
|
|
|
i.e., the specified fields apply to all event types if the type string
|
|
|
|
is not given.
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2011-03-31 02:30:43 +08:00
|
|
|
The arguments are processed in the order received. A later usage can
|
|
|
|
reset a prior request. e.g.:
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2011-05-28 04:28:43 +08:00
|
|
|
-f trace: -f comm,tid,time,ip,sym
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2011-03-31 02:30:43 +08:00
|
|
|
The first -f suppresses trace events (field list is ""), but then the
|
2011-05-28 04:28:43 +08:00
|
|
|
second invocation sets the fields to comm,tid,time,ip,sym. In this case a
|
2011-03-31 02:30:43 +08:00
|
|
|
warning is given to the user:
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2011-03-31 02:30:43 +08:00
|
|
|
"Overriding previous field request for all events."
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2014-09-09 23:18:50 +08:00
|
|
|
Alternatively, consider the order:
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2011-05-28 04:28:43 +08:00
|
|
|
-f comm,tid,time,ip,sym -f trace:
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2011-03-31 02:30:43 +08:00
|
|
|
The first -f sets the fields for all events and the second -f
|
|
|
|
suppresses trace events. The user is given a warning message about
|
|
|
|
the override, and the result of the above is that only S/W and H/W
|
|
|
|
events are displayed with the given fields.
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2011-03-31 02:30:43 +08:00
|
|
|
For the 'wildcard' option if a user selected field is invalid for an
|
|
|
|
event type, a message is displayed to the user that the option is
|
|
|
|
ignored for that type. For example:
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2011-03-31 02:30:43 +08:00
|
|
|
$ perf script -f comm,tid,trace
|
|
|
|
'trace' not valid for hardware events. Ignoring.
|
|
|
|
'trace' not valid for software events. Ignoring.
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2011-03-31 02:30:43 +08:00
|
|
|
Alternatively, if the type is given an invalid field is specified it
|
|
|
|
is an error. For example:
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2011-03-31 02:30:43 +08:00
|
|
|
perf script -v -f sw:comm,tid,trace
|
|
|
|
'trace' not valid for software events.
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2011-03-31 02:30:43 +08:00
|
|
|
At this point usage is displayed, and perf-script exits.
|
2014-12-18 04:24:45 +08:00
|
|
|
|
2011-03-31 02:30:43 +08:00
|
|
|
Finally, a user may not set fields to none for all event types.
|
|
|
|
i.e., -f "" is not allowed.
|
|
|
|
|
2011-03-10 13:23:27 +08:00
|
|
|
-k::
|
|
|
|
--vmlinux=<file>::
|
|
|
|
vmlinux pathname
|
|
|
|
|
|
|
|
--kallsyms=<file>::
|
|
|
|
kallsyms pathname
|
|
|
|
|
|
|
|
--symfs=<directory>::
|
|
|
|
Look for files with symbols relative to this directory.
|
|
|
|
|
|
|
|
-G::
|
|
|
|
--hide-call-graph::
|
|
|
|
When printing symbols do not display call chain.
|
perf script: Support custom field selection for output
Allow a user to select which fields to print to stdout for event data.
Options include comm (command name), tid (thread id), pid (process id),
time (perf timestamp), cpu, event (for event name), and trace (for
trace data).
Default is set to maintain compatibility with current output; this
feature does alter output format slightly -- no '-' between command
and pid/tid.
Thanks to Frederic Weisbecker for detailed suggestions on this approach.
Examples (output compressed)
1. trace, default format
perf record -ga -e sched:sched_switch
perf script
swapper 0 [000] 537.037184: sched_switch: prev_comm=swapper prev_pid=0...
sshd 1675 [000] 537.037309: sched_switch: prev_comm=sshd prev_pid=1675...
netstat 1692 [001] 537.038664: sched_switch: prev_comm=netstat prev_pid=1692...
2. trace, custom format
perf record -ga -e sched:sched_switch
perf script -f comm,pid,time,trace <--- omitting cpu and event name
swapper 0 537.037184: prev_comm=swapper prev_pid=0 prev_prio=120 ...
sshd 1675 537.037309: prev_comm=sshd prev_pid=1675 prev_prio=120 ...
netstat 1692 537.038664: prev_comm=netstat prev_pid=1692 prev_prio=120 ...
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1299734608-5223-5-git-send-email-daahern@cisco.com>
Signed-off-by: David Ahern <daahern@cisco.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-03-10 13:23:26 +08:00
|
|
|
|
2011-11-14 02:30:08 +08:00
|
|
|
-C::
|
2011-07-04 19:57:50 +08:00
|
|
|
--cpu:: Only report samples for 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. Default is to report samples on all
|
|
|
|
CPUs.
|
|
|
|
|
2011-11-22 01:02:52 +08:00
|
|
|
-c::
|
|
|
|
--comms=::
|
|
|
|
Only display events for these comms. CSV that understands
|
|
|
|
file://filename entries.
|
|
|
|
|
2015-03-24 23:52:41 +08:00
|
|
|
--pid=::
|
|
|
|
Only show events for given process ID (comma separated list).
|
|
|
|
|
|
|
|
--tid=::
|
|
|
|
Only show events for given thread ID (comma separated list).
|
|
|
|
|
perf tools: Make perf.data more self-descriptive (v8)
The goal of this patch is to include more information about the host
environment into the perf.data so it is more self-descriptive. Overtime,
profiles are captured on various machines and it becomes hard to track
what was recorded, on what machine and when.
This patch provides a way to solve this by extending the perf.data file
with basic information about the host machine. To add those extensions,
we leverage the feature bits capabilities of the perf.data format. The
change is backward compatible with existing perf.data files.
We define the following useful new extensions:
- HEADER_HOSTNAME: the hostname
- HEADER_OSRELEASE: the kernel release number
- HEADER_ARCH: the hw architecture
- HEADER_CPUDESC: generic CPU description
- HEADER_NRCPUS: number of online/avail cpus
- HEADER_CMDLINE: perf command line
- HEADER_VERSION: perf version
- HEADER_TOPOLOGY: cpu topology
- HEADER_EVENT_DESC: full event description (attrs)
- HEADER_CPUID: easy-to-parse low level CPU identication
The small granularity for the entries is to make it easier to extend
without breaking backward compatiblity. Many entries are provided as
ASCII strings.
Perf report/script have been modified to print the basic information as
easy-to-parse ASCII strings. Extended information about CPU and NUMA
topology may be requested with the -I option.
Thanks to David Ahern for reviewing and testing the many versions of
this patch.
$ perf report --stdio
# ========
# captured on : Mon Sep 26 15:22:14 2011
# hostname : quad
# os release : 3.1.0-rc4-tip
# perf version : 3.1.0-rc4
# arch : x86_64
# nrcpus online : 4
# nrcpus avail : 4
# cpudesc : Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz
# cpuid : GenuineIntel,6,15,11
# total memory : 8105360 kB
# cmdline : /home/eranian/perfmon/official/tip/build/tools/perf/perf record date
# event : name = cycles, type = 0, config = 0x0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern = 0, id = { 29, 30, 31,
# HEADER_CPU_TOPOLOGY info available, use -I to display
# HEADER_NUMA_TOPOLOGY info available, use -I to display
# ========
#
...
$ perf report --stdio -I
# ========
# captured on : Mon Sep 26 15:22:14 2011
# hostname : quad
# os release : 3.1.0-rc4-tip
# perf version : 3.1.0-rc4
# arch : x86_64
# nrcpus online : 4
# nrcpus avail : 4
# cpudesc : Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz
# cpuid : GenuineIntel,6,15,11
# total memory : 8105360 kB
# cmdline : /home/eranian/perfmon/official/tip/build/tools/perf/perf record date
# event : name = cycles, type = 0, config = 0x0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern = 0, id = { 29, 30, 31,
# sibling cores : 0-3
# sibling threads : 0
# sibling threads : 1
# sibling threads : 2
# sibling threads : 3
# node0 meminfo : total = 8320608 kB, free = 7571024 kB
# node0 cpu list : 0-3
# ========
#
...
Reviewed-by: David Ahern <dsahern@gmail.com>
Tested-by: David Ahern <dsahern@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/r/20110930134040.GA5575@quad
Signed-off-by: Stephane Eranian <eranian@google.com>
[ committer notes: Use --show-info in the tools as was in the docs, rename
perf_header_fprintf_info to perf_file_section__fprintf_info, fixup
conflict with f69b64f7 "perf: Support setting the disassembler style" ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-09-30 21:40:40 +08:00
|
|
|
-I::
|
|
|
|
--show-info::
|
|
|
|
Display extended information about the perf.data file. This adds
|
|
|
|
information which may be very large and thus may clutter the display.
|
|
|
|
It currently includes: cpu and numa topology of the host system.
|
|
|
|
It can only be used with the perf script report mode.
|
|
|
|
|
2012-01-30 12:43:20 +08:00
|
|
|
--show-kernel-path::
|
|
|
|
Try to resolve the path of [kernel.kallsyms]
|
|
|
|
|
2013-11-26 16:51:12 +08:00
|
|
|
--show-task-events
|
|
|
|
Display task related events (e.g. FORK, COMM, EXIT).
|
|
|
|
|
2013-11-26 16:54:26 +08:00
|
|
|
--show-mmap-events
|
|
|
|
Display mmap related events (e.g. MMAP, MMAP2).
|
|
|
|
|
2013-12-09 18:02:50 +08:00
|
|
|
--header
|
|
|
|
Show perf.data header.
|
|
|
|
|
|
|
|
--header-only
|
|
|
|
Show only perf.data header.
|
|
|
|
|
2009-09-11 18:12:54 +08:00
|
|
|
SEE ALSO
|
|
|
|
--------
|
2010-11-17 01:45:39 +08:00
|
|
|
linkperf:perf-record[1], linkperf:perf-script-perl[1],
|
|
|
|
linkperf:perf-script-python[1]
|