1TRACE-CMD-EXTRACT(1) libtracefs Manual TRACE-CMD-EXTRACT(1)
2
6 trace-cmd-extract - extract out the data from the Ftrace Linux tracer.
7
9 trace-cmd extract [OPTIONS]
10
12 The trace-cmd(1) extract is usually used after trace-cmd-start(1) and
13 trace-cmd-stop(1). It can be used after the Ftrace tracer has been
14 started manually through the Ftrace pseudo file system.
15 The extract command creates a trace.dat file that can be used by
17 trace-cmd-report(1) to read from. It reads the kernel internal ring
18 buffer to produce the trace.dat file.
19
21 -p plugin
22 Although extract does not start any traces, some of the plugins
23 require just reading the output in ASCII format. These are the
24 latency tracers, since the latency tracers have a separate internal
25 buffer. The plugin option is therefore only necessary for the
26 wakeup, wakeup-rt, irqsoff, preemptoff and preemptirqsoff plugins.
27 With out this option, the extract command will extract from the internal
29 Ftrace buffers.
30 -O option
32 If a latency tracer is being extracted, and the -p option is used,
33 then there are some Ftrace options that can change the format. This
34 will update those options before extracting. To see the list of
35 options see trace-cmd-list. To enable an option, write its name, to
36 disable the option append the characters no to it. For example:
37 noprint-parent will disable the print-parent option that prints the
38 parent function in printing a function event.
39 -o outputfile
41 By default, the extract command will create a trace.dat file. This
42 option will change where the file is written to.
43 -s
45 Extract from the snapshot buffer (if the kernel supports it).
46 --date
48 This is the same as the trace-cmd-record(1) --date option, but it
49 does cause the extract routine to disable all tracing. That is, the
50 end of the extract will perform something similar to
51 trace-cmd-reset(1).
52 -B buffer-name
54 If the kernel supports multiple buffers, this will extract the
55 trace for only the given buffer. It does not affect any other
56 buffer. This may be used multiple times to specify different
57 buffers. When this option is used, the top level instance will not
58 be extracted unless -t is given.
59 -a
61 Extract all existing buffer instances. When this option is used,
62 the top level instance will not be extracted unless -t is given.
63 -t
65 Extracts the top level instance buffer. Without the -B or -a option
66 this is the same as the default. But if -B or -a is used, this is
67 required if the top level instance buffer should also be extracted.
68 --verbose[=level]
70 Set the log level. Supported log levels are "none", "critical",
71 "error", "warning", "info", "debug", "all" or their identifiers
72 "0", "1", "2", "3", "4", "5", "6". Setting the log level to
73 specific value enables all logs from that and all previous levels.
74 The level will default to "info" if one is not specified.
75 Example: enable all critical, error and warning logs
77 trace-cmd extract --verbose=warning
79
81 trace-cmd(1), trace-cmd-record(1), trace-cmd-report(1),
82 trace-cmd-start(1), trace-cmd-stop(1), trace-cmd-reset(1),
83 trace-cmd-split(1), trace-cmd-list(1), trace-cmd-listen(1)
84
86 Written by Steven Rostedt, <rostedt@goodmis.org[1]>
87
89 https://git.kernel.org/pub/scm/utils/trace-cmd/trace-cmd.git/
90
92 Copyright (C) 2010 Red Hat, Inc. Free use of this software is granted
93 under the terms of the GNU Public License (GPL).
94
96 1. rostedt@goodmis.org
97 mailto:rostedt@goodmis.org
98libtracefs 04/15/2022 TRACE-CMD-EXTRACT(1)