2009-09-19 13:36:04 +02:00
perf-timechart(1)
=================
NAME
----
perf-timechart - Tool to visualize total system behavior during a workload
SYNOPSIS
--------
[verse]
2013-11-01 20:25:50 +04:00
'perf timechart' [<timechart options>] {record} [<record options>]
2009-09-19 13:36:04 +02:00
DESCRIPTION
-----------
There are two variants of perf timechart:
'perf timechart record <command>' to record the system level events
of an arbitrary workload.
'perf timechart' to turn a trace into a Scalable Vector Graphics file,
that can be viewed with popular SVG viewers such as 'Inkscape'.
2013-11-01 20:25:50 +04:00
TIMECHART OPTIONS
-----------------
2009-09-19 13:36:04 +02:00
-o::
--output=::
Select the output file (default: output.svg)
-i::
--input=::
2011-12-07 10:02:54 +01:00
Select the input file (default: perf.data unless stdin is a fifo)
2009-09-20 18:14:16 +02:00
-w::
--width=::
Select the width of the SVG file (default: 1000)
2009-10-20 07:09:39 +09:00
-P::
2009-09-24 15:40:13 +02:00
--power-only::
Only output the CPU power section of the diagram
2013-11-01 20:25:48 +04:00
-T::
--tasks-only::
Don't output processor state transitions
2009-10-20 07:09:39 +09:00
-p::
--process::
Select the processes to display, by name or PID
2009-09-19 13:36:04 +02:00
2010-12-09 13:27:07 -07:00
--symfs=<directory>::
Look for files with symbols relative to this directory.
2009-09-19 13:36:04 +02:00
2013-10-03 14:45:16 +05:30
EXAMPLES
--------
$ perf timechart record git pull
[ perf record: Woken up 13 times to write data ]
[ perf record: Captured and wrote 4.253 MB perf.data (~185801 samples) ]
$ perf timechart
Written 10.2 seconds of trace to output.svg.
2013-12-17 19:53:49 +04:00
Record system-wide timechart:
$ perf timechart record
then generate timechart and highlight 'gcc' tasks:
$ perf timechart --highlight gcc
2013-11-01 20:25:46 +04:00
-n::
--proc-num::
Print task info for at least given number of tasks.
2013-12-02 18:37:36 +04:00
-t::
--topology::
Sort CPUs according to topology.
2013-12-17 19:53:49 +04:00
--highlight=<duration_nsecs|task_name>::
Highlight tasks (using different color) that run more than given
duration or tasks with given name. If number is given it's interpreted
as number of nanoseconds. If non-numeric string is given it's
interpreted as task name.
2013-11-01 20:25:46 +04:00
2013-11-01 20:25:50 +04:00
RECORD OPTIONS
--------------
-P::
--power-only::
Record only power-related events
-T::
--tasks-only::
Record only tasks-related events
2013-11-01 20:25:51 +04:00
-g::
--callchain::
Do call-graph (stack chain/backtrace) recording
2013-11-01 20:25:50 +04:00
2009-09-19 13:36:04 +02:00
SEE ALSO
--------
linkperf:perf-record[1]