trace-cmd-extract - Man Page

trace-cmd extract [Options]

The trace-cmd(1) extract is usually used after trace-cmd-start(1) and trace-cmd-stop(1). It can be used after the Ftrace tracer has been started manually through the Ftrace pseudo file system.

The extract command creates a trace.dat file that can be used by trace-cmd-report(1) to read from. It reads the kernel internal ring buffer to produce the trace.dat file.

-p plugin

Although extract does not start any traces, some of the plugins require just reading the output in ASCII format. These are the latency tracers, since the latency tracers have a separate internal buffer. The plugin option is therefore only necessary for the wakeup, wakeup-rt, irqsoff, preemptoff and preemptirqsoff plugins.

With out this option, the extract command will extract from the internal
Ftrace buffers.

-O option

If a latency tracer is being extracted, and the -p option is used, then there are some Ftrace options that can change the format. This will update those options before extracting. To see the list of options see trace-cmd-list. To enable an option, write its name, to disable the option append the characters no to it. For example: noprint-parent will disable the print-parent option that prints the parent function in printing a function event.

-o outputfile

By default, the extract command will create a trace.dat file. This option will change where the file is written to.

-s

Extract from the snapshot buffer (if the kernel supports it).

--date

This is the same as the trace-cmd-record(1) --date option, but it does cause the extract routine to disable all tracing. That is, the end of the extract will perform something similar to trace-cmd-reset(1).

-B buffer-name

If the kernel supports multiple buffers, this will extract the trace for only the given buffer. It does not affect any other buffer. This may be used multiple times to specify different buffers. When this option is used, the top level instance will not be extracted unless -t is given.

-a

Extract all existing buffer instances. When this option is used, the top level instance will not be extracted unless -t is given.

-t

Extracts the top level instance buffer. Without the -B or -a option this is the same as the default. But if -B or -a is used, this is required if the top level instance buffer should also be extracted.

--verbose[=level]

Set the log level. Supported log levels are "none", "critical", "error", "warning", "info", "debug", "all" or their identifiers "0", "1", "2", "3", "4", "5", "6". Setting the log level to specific value enables all logs from that and all previous levels. The level will default to "info" if one is not specified.

Example: enable all critical, error and warning logs

trace-cmd extract --verbose=warning

trace-cmd(1), trace-cmd-record(1), trace-cmd-report(1), trace-cmd-start(1), trace-cmd-stop(1), trace-cmd-reset(1), trace-cmd-split(1), trace-cmd-list(1), trace-cmd-listen(1)

Written by Steven Rostedt, <rostedt@goodmis.org^[1]>

https://git.kernel.org/pub/scm/utils/trace-cmd/trace-cmd.git/

Copyright (C) 2010 Red Hat, Inc. Free use of this software is granted under the terms of the GNU Public License (GPL).

1.

rostedt@goodmis.org
mailto:rostedt@goodmis.org

trace-cmd(1), trace-cmd-agent(1), trace-cmd-attach(1), trace-cmd-check-events(1), trace-cmd-clear(1), trace-cmd.dat.v6(5), trace-cmd.dat.v7(5), trace-cmd-hist(1), trace-cmd-list(1), trace-cmd-listen(1), trace-cmd-mem(1), trace-cmd-options(1), trace-cmd-record(1), trace-cmd-report(1), trace-cmd-reset(1), trace-cmd-restore(1), trace-cmd-set(1), trace-cmd-show(1), trace-cmd-snapshot(1), trace-cmd-split(1), trace-cmd-stack(1), trace-cmd-start(1), trace-cmd-stat(1), trace-cmd-stop(1).