Files
linux-apfs/tools/perf/Documentation/perf-top.txt
T

205 lines
4.1 KiB
Plaintext
Raw Normal View History

2009-04-20 15:52:29 +02:00
perf-top(1)
2008-04-15 22:39:31 +02:00
===========
2009-04-20 15:52:29 +02:00
NAME
----
2009-08-04 10:24:41 +02:00
perf-top - System profiling tool.
2009-04-20 15:52:29 +02:00
SYNOPSIS
--------
[verse]
2009-08-04 10:24:41 +02:00
'perf top' [-e <EVENT> | --event=EVENT] [<options>]
2009-04-20 15:52:29 +02:00
DESCRIPTION
-----------
2010-11-30 19:57:21 -06:00
This command generates and displays a performance counter profile in real time.
2009-04-20 15:52:29 +02:00
OPTIONS
-------
2009-08-04 10:24:41 +02:00
-a::
--all-cpus::
System-wide collection. (default)
2009-04-20 15:52:29 +02:00
2009-08-04 10:24:41 +02:00
-c <count>::
--count=<count>::
Event period to sample.
-C <cpu-list>::
--cpu=<cpu>::
2010-11-30 19:57:21 -06:00
Monitor 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.
Default is to monitor all CPUS.
2009-08-04 10:24:41 +02:00
-d <seconds>::
--delay=<seconds>::
Number of seconds to delay between refreshes.
-e <event>::
--event=<event>::
2009-06-06 14:56:33 +02:00
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
2009-08-04 10:24:41 +02:00
hexadecimal event descriptor.
2009-04-20 15:52:29 +02:00
2009-08-04 10:24:41 +02:00
-E <entries>::
--entries=<entries>::
Display this many functions.
-f <count>::
--count-filter=<count>::
Only display functions with more events than this.
2010-11-30 19:57:21 -06:00
--group::
Put the counters into a counter group.
2009-08-04 10:24:41 +02:00
-F <freq>::
--freq=<freq>::
Profile at this frequency.
-i::
--inherit::
2012-12-11 16:48:41 -03:00
Child tasks do not inherit counters.
2009-08-04 10:24:41 +02:00
-k <path>::
--vmlinux=<path>::
Path to vmlinux. Required for annotation functionality.
-m <pages>::
--mmap-pages=<pages>::
Number of mmap data pages (must be a power of two) or size
specification with appended unit character - B/K/M/G. The
size is rounded up to have nearest pages power of two value.
2009-08-04 10:24:41 +02:00
-p <pid>::
--pid=<pid>::
Profile events on existing Process ID (comma separated list).
2010-11-30 19:57:21 -06:00
-t <tid>::
--tid=<tid>::
Profile events on existing thread ID (comma separated list).
2009-08-04 10:24:41 +02:00
2012-01-19 14:08:15 -02:00
-u::
--uid=::
Record events in threads owned by uid. Name or number.
2009-08-04 10:24:41 +02:00
-r <priority>::
--realtime=<priority>::
Collect data with this RT SCHED_FIFO priority.
-s <symbol>::
--sym-annotate=<symbol>::
2010-02-03 16:52:08 -02:00
Annotate this symbol.
2009-08-04 10:24:41 +02:00
2010-11-30 19:57:21 -06:00
-K::
--hide_kernel_symbols::
Hide kernel symbols.
-U::
--hide_user_symbols::
Hide user symbols.
-D::
--dump-symtab::
Dump the symbol table used for profiling.
2009-08-04 10:24:41 +02:00
-v::
--verbose::
Be more verbose (show counter open errors, etc).
-z::
--zero::
Zero history across display updates.
-s::
--sort::
Sort by key(s): pid, comm, dso, symbol, parent, srcline, weight,
local_weight, abort, in_tx, transaction
-n::
--show-nr-samples::
Show a column with the number of samples.
--show-total-period::
Show a column with the sum of periods.
--dsos::
Only consider symbols in these dsos.
--comms::
Only consider symbols in these comms.
--symbols::
Only consider these symbols.
2011-10-06 12:48:31 -03:00
-M::
--disassembler-style=:: Set disassembler style for objdump.
--source::
Interleave source code with assembly code. Enabled by default,
disable with --no-source.
--asm-raw::
Show raw instruction encoding of assembly instructions.
2013-11-14 20:51:30 -07:00
-g::
2013-10-26 16:25:34 +02:00
Enables call-graph (stack chain/backtrace) recording.
2011-10-05 19:30:22 -03:00
--call-graph::
2013-10-26 16:25:34 +02:00
Setup and enable call-graph (stack chain/backtrace) recording,
2013-11-14 20:51:30 -07:00
implies -g.
2011-10-05 19:30:22 -03:00
--max-stack::
Set the stack depth limit when parsing the callchain, anything
beyond the specified depth will be ignored. This is a trade-off
between information loss and faster processing especially for
workloads that can have a very long callchain stack.
Default: 127
--ignore-callees=<regex>::
Ignore callees of the function(s) matching the given regex.
This has the effect of collecting the callers of each such
function into one place in the call-graph tree.
2013-05-14 11:09:05 +09:00
--percent-limit::
Do not show entries which have an overhead under that percent.
(Default: 0).
2009-08-04 10:24:41 +02:00
INTERACTIVE PROMPTING KEYS
--------------------------
[d]::
Display refresh delay.
[e]::
Number of entries to display.
[E]::
Event to display when multiple counters are active.
[f]::
Profile display filter (>= hit count).
[F]::
Annotation display filter (>= % of total).
[s]::
Annotate symbol.
[S]::
Stop annotation, return to full profile display.
[z]::
Toggle event count zeroing across display updates.
[qQ]::
Quit.
Pressing any unmapped key displays a menu, and prompts for input.
2009-04-20 15:52:29 +02:00
SEE ALSO
--------
2009-06-06 14:56:33 +02:00
linkperf:perf-stat[1], linkperf:perf-list[1]