1 perf-timechart(1) 1 perf-timechart(1)
2 ================= 2 =================
3 3
4 NAME 4 NAME
5 ---- 5 ----
6 perf-timechart - Tool to visualize total syste 6 perf-timechart - Tool to visualize total system behavior during a workload
7 7
8 SYNOPSIS 8 SYNOPSIS
9 -------- 9 --------
10 [verse] 10 [verse]
11 'perf timechart' [<timechart options>] {record !! 11 'perf timechart' {record}
12 12
13 DESCRIPTION 13 DESCRIPTION
14 ----------- 14 -----------
15 There are two variants of perf timechart: 15 There are two variants of perf timechart:
16 16
17 'perf timechart record <command>' to record 17 'perf timechart record <command>' to record the system level events
18 of an arbitrary workload. By default timecha !! 18 of an arbitrary workload.
19 and CPU events (task switches, running times <<
20 but it's possible to record IO (disk, networ <<
21 19
22 'perf timechart' to turn a trace into a Scal 20 'perf timechart' to turn a trace into a Scalable Vector Graphics file,
23 that can be viewed with popular SVG viewers !! 21 that can be viewed with popular SVG viewers such as 'Inkscape'.
24 on the events in the perf.data file, timecha <<
25 events or IO events. <<
26 22
27 In IO mode, every bar has two charts: upper !! 23 OPTIONS
28 Upper bar shows incoming events (disk reads, !! 24 -------
29 Lower bar shows outgoing events (disk writes <<
30 There are also poll bars which show how much <<
31 in poll/epoll/select syscalls. <<
32 <<
33 TIMECHART OPTIONS <<
34 ----------------- <<
35 -o:: 25 -o::
36 --output=:: 26 --output=::
37 Select the output file (default: outpu 27 Select the output file (default: output.svg)
38 -i:: 28 -i::
39 --input=:: 29 --input=::
40 Select the input file (default: perf.d 30 Select the input file (default: perf.data unless stdin is a fifo)
41 -w:: 31 -w::
42 --width=:: 32 --width=::
43 Select the width of the SVG file (defa 33 Select the width of the SVG file (default: 1000)
44 -P:: 34 -P::
45 --power-only:: 35 --power-only::
46 Only output the CPU power section of t 36 Only output the CPU power section of the diagram
47 -T:: <<
48 --tasks-only:: <<
49 Don't output processor state transitio <<
50 -p:: 37 -p::
51 --process:: 38 --process::
52 Select the processes to display, by na 39 Select the processes to display, by name or PID
53 -f:: !! 40
54 --force:: <<
55 Don't complain, do it. <<
56 --symfs=<directory>:: 41 --symfs=<directory>::
57 Look for files with symbols relative t 42 Look for files with symbols relative to this directory.
58 -n:: <<
59 --proc-num:: <<
60 Print task info for at least given num <<
61 -t:: <<
62 --topology:: <<
63 Sort CPUs according to topology. <<
64 --highlight=<duration_nsecs|task_name>:: <<
65 Highlight tasks (using different color <<
66 duration or tasks with given name. If <<
67 as number of nanoseconds. If non-numer <<
68 interpreted as task name. <<
69 --io-skip-eagain:: <<
70 Don't draw EAGAIN IO events. <<
71 --io-min-time=<nsecs>:: <<
72 Draw small events as if they lasted mi <<
73 to see very small and fast IO. It's po <<
74 suffix to specify time in milliseconds <<
75 Default value is 1ms. <<
76 --io-merge-dist=<nsecs>:: <<
77 Merge events that are merge-dist nanos <<
78 Reduces number of figures on the SVG a <<
79 It's possible to specify ms or us suff <<
80 milliseconds or microseconds. <<
81 Default value is 1us. <<
82 <<
83 RECORD OPTIONS <<
84 -------------- <<
85 -P:: <<
86 --power-only:: <<
87 Record only power-related events <<
88 -T:: <<
89 --tasks-only:: <<
90 Record only tasks-related events <<
91 -I:: <<
92 --io-only:: <<
93 Record only io-related events <<
94 -g:: <<
95 --callchain:: <<
96 Do call-graph (stack chain/backtrace) <<
97 <<
98 EXAMPLES <<
99 -------- <<
100 <<
101 $ perf timechart record git pull <<
102 <<
103 [ perf record: Woken up 13 times to write da <<
104 [ perf record: Captured and wrote 4.253 MB p <<
105 <<
106 $ perf timechart <<
107 <<
108 Written 10.2 seconds of trace to output.svg. <<
109 <<
110 Record system-wide timechart: <<
111 <<
112 $ perf timechart record <<
113 <<
114 then generate timechart and highlight 'gcc' <<
115 <<
116 $ perf timechart --highlight gcc <<
117 <<
118 Record system-wide IO events: <<
119 <<
120 $ perf timechart record -I <<
121 <<
122 then generate timechart: <<
123 <<
124 $ perf timechart <<
125 43
126 SEE ALSO 44 SEE ALSO
127 -------- 45 --------
128 linkperf:perf-record[1] 46 linkperf:perf-record[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.