xref: /linux/tools/perf/Documentation/perf-report.txt (revision b43ab901d671e3e3cad425ea5e9a3c74e266dcdd)
1perf-report(1)
2==============
3
4NAME
5----
6perf-report - Read perf.data (created by perf record) and display the profile
7
8SYNOPSIS
9--------
10[verse]
11'perf report' [-i <file> | --input=file]
12
13DESCRIPTION
14-----------
15This command displays the performance counter profile information recorded
16via perf record.
17
18OPTIONS
19-------
20-i::
21--input=::
22        Input file name. (default: perf.data unless stdin is a fifo)
23
24-v::
25--verbose::
26        Be more verbose. (show symbol address, etc)
27
28-d::
29--dsos=::
30	Only consider symbols in these dsos. CSV that understands
31	file://filename entries.
32-n::
33--show-nr-samples::
34	Show the number of samples for each symbol
35
36--showcpuutilization::
37        Show sample percentage for different cpu modes.
38
39-T::
40--threads::
41	Show per-thread event counters
42-c::
43--comms=::
44	Only consider symbols in these comms. CSV that understands
45	file://filename entries.
46-S::
47--symbols=::
48	Only consider these symbols. CSV that understands
49	file://filename entries.
50
51-U::
52--hide-unresolved::
53        Only display entries resolved to a symbol.
54
55-s::
56--sort=::
57	Sort by key(s): pid, comm, dso, symbol, parent.
58
59-p::
60--parent=<regex>::
61        regex filter to identify parent, see: '--sort parent'
62
63-x::
64--exclude-other::
65        Only display entries with parent-match.
66
67-w::
68--column-widths=<width[,width...]>::
69	Force each column width to the provided list, for large terminal
70	readability.
71
72-t::
73--field-separator=::
74
75	Use a special separator character and don't pad with spaces, replacing
76	all occurrences of this separator in symbol names (and other output)
77	with a '.' character, that thus it's the only non valid separator.
78
79-D::
80--dump-raw-trace::
81        Dump raw trace in ASCII.
82
83-g [type,min[,limit],order]::
84--call-graph::
85        Display call chains using type, min percent threshold, optional print
86	limit and order.
87	type can be either:
88	- flat: single column, linear exposure of call chains.
89	- graph: use a graph tree, displaying absolute overhead rates.
90	- fractal: like graph, but displays relative rates. Each branch of
91		 the tree is considered as a new profiled object. +
92
93	order can be either:
94	- callee: callee based call graph.
95	- caller: inverted caller based call graph.
96
97	Default: fractal,0.5,callee.
98
99-G::
100--inverted::
101        alias for inverted caller based call graph.
102
103--pretty=<key>::
104        Pretty printing style.  key: normal, raw
105
106--stdio:: Use the stdio interface.
107
108--tui:: Use the TUI interface, that is integrated with annotate and allows
109        zooming into DSOs or threads, among other features. Use of --tui
110	requires a tty, if one is not present, as when piping to other
111	commands, the stdio interface is used.
112
113-k::
114--vmlinux=<file>::
115        vmlinux pathname
116
117--kallsyms=<file>::
118        kallsyms pathname
119
120-m::
121--modules::
122        Load module symbols. WARNING: This should only be used with -k and
123        a LIVE kernel.
124
125-f::
126--force::
127        Don't complain, do it.
128
129--symfs=<directory>::
130        Look for files with symbols relative to this directory.
131
132-C::
133--cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
134	be provided as a comma-separated list with no space: 0,1. Ranges of
135	CPUs are specified with -: 0-2. Default is to report samples on all
136	CPUs.
137
138-M::
139--disassembler-style=:: Set disassembler style for objdump.
140
141--source::
142	Interleave source code with assembly code. Enabled by default,
143	disable with --no-source.
144
145--asm-raw::
146	Show raw instruction encoding of assembly instructions.
147
148--show-total-period:: Show a column with the sum of periods.
149
150-I::
151--show-info::
152	Display extended information about the perf.data file. This adds
153	information which may be very large and thus may clutter the display.
154	It currently includes: cpu and numa topology of the host system.
155
156SEE ALSO
157--------
158linkperf:perf-stat[1], linkperf:perf-annotate[1]
159