TRACE-CMD-DUMP(1)

📦
version 3.4 · 13 versions
, in arch rolling

💅 TRACE-CMD-DUMP(1) — the libtracefs manual, bestie edition 🎀

okay so you found the trace-cmd-dump page in the libtracefs manual and you're like "what is this" — don't worry, I got you. This is the manual page for trace-cmd-dump, and by the end you're gonna be obsessed. ✨

✨ NAME ✨

trace-cmd-dump — show a meta data from a trace file, created by trace-cmd record

(it's literally the look-inside-the-box tool, no cap 🫶)

🌸 SYNOPSIS 🌸

trace-cmd dump [OPTIONS] [input-file]

🦋 DESCRIPTION 🦋

so the trace-cmd(1) dump command will display the meta data from a trace file created by trace-cmd record. that's the whole vibe. it's giving "peek behind the curtain" 💜

👑 OPTIONS 👑

  • -i input-file — by default, trace-cmd dump will read the file trace.dat. but bestie, the -i option opens up the given input-file instead. and like, note this: the input file may also be specified as the last item on the command line. two ways to do the same thing, we love options 🙈
  • -v, --validate — check if the input file is a valid trace file, created by trace-cmd. vibe check for your file 💅
  • --summary — print a meta data summary — initial format and a short description of each file section. this is the default action, if no arguments are specified. so like, if you do nothing, this is what you get ✨
  • --head-page — print the header page information, stored in the file.
  • --head-event — print the event header information, stored in the file.
  • --ftrace-events — print formats of ftrace specific events.
  • --systems — print information of event systems, stored in the file — name and number of events for each system.
  • --events — print formats of all events, stored in the file.
  • --kallsyms — print information of the mapping of function addresses to the function names.
  • --printk — print trace_printk() format strings, stored in the file.
  • --cmd-lines — print mapping a PID to a process name.
  • --options — print all options, stored in the file.
  • --flyrecord — print the offset and the size of tracing data per each CPU.
  • --clock — print the trace clock, used for timestamp of the tracing events, stored in the file.
  • --all — print all meta data from the file. the "give me everything" button, main character energy 🔥
  • --help — print usage information.
  • --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 report --verbose=warning

🧚 EXAMPLES 🧚

okay these are the receipts, let me just show you:

# trace-cmd dump --summary -i trace.dat

 Tracing meta data in file trace.dat:
        [Initial format]
                6       [Version]
                0       [Little endian]
                8       [Bytes in a long]
                4096    [Page size, bytes]
        [Header info, 205 bytes]
        [Header event, 205 bytes]
        [Ftrace format, 15 events]
        [Events format, 2 systems]
        [Kallsyms, 7144493 bytes]
        [Trace printk, 2131 bytes]
        [Saved command lines, 117 bytes]
        8 [CPUs with tracing data]
        [12 options]
        [Flyrecord tracing data]
# trace-cmd dump --flyrecord -i trace.dat
        [Flyrecord tracing data]
                 7176192 0      [offset, size of cpu 0]
                 7176192 0      [offset, size of cpu 1]
                 7176192 0      [offset, size of cpu 2]
                 7176192 4096   [offset, size of cpu 3]
                 7180288 4096   [offset, size of cpu 4]
                 7184384 0      [offset, size of cpu 5]
                 7184384 0      [offset, size of cpu 6]
                 7184384 0      [offset, size of cpu 7]
# trace-cmd dump --summary --systems -i trace.dat

 Tracing meta data in file trace.dat:
        [Initial format]
                6       [Version]
                0       [Little endian]
                8       [Bytes in a long]
                4096    [Page size, bytes]
        [Header info, 205 bytes]
        [Header event, 205 bytes]
        [Ftrace format, 15 events]
        [Events format, 3 systems]
                sched 23 [system, events]
                irq 5 [system, events]
                kvm 70 [system, events]
        [Kallsyms, 7144493 bytes]
        [Trace printk, 2131 bytes]
        [Saved command lines, 157 bytes]
        8 [CPUs with tracing data]
        [11 options]
        [Flyrecord tracing data]
# trace-cmd dump --summary --systems -i trace.dat
File trace.dat is a valid trace-cmd file

like, that last one just tells you your file is valid and honestly? slay 💀✨

💖 SEE ALSO 💖

trace-cmd(1), trace-cmd.dat(1)

🌈 AUTHOR 🌈

Steven Rostedt <rostedt@goodmis.org[1]>, author of trace-cmd. Tzvetomir Stoyanov <tz.stoyanov@gmail.com[2]>, author of this man page.

(we stan both of them, legends only 👑)

🍓 RESOURCES 🍓

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

⭐ COPYING ⭐

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

🔥 NOTES 🔥

  1. rostedt@goodmis.org mailto:rostedt@goodmis.org
  2. tz.stoyanov@gmail.com mailto:tz.stoyanov@gmail.com

and that's the whole page bestie 🫶 this was libtracefs, dated 03/09/2026 — ily, go dump some trace files, periodt 💜🎀

📦 where this page comes from