LTTNG-CALIBRATE(1)              LTTng Manual              LTTNG-CALIBRATE(1)

NAME         top

       lttng-calibrate - Quantify LTTng overhead

SYNOPSIS         top

       lttng [GENERAL OPTIONS] calibrate

DESCRIPTION         top

       The lttng calibrate commands quantifies the overhead of LTTng

       The lttng calibrate command can be used to find out the combined
       average overhead of the LTTng tracers and the instrumentation
       mechanisms used. This overhead can be calibrated in terms of time or
       using any of the PMU performance counter available on the system.

       For now, the only implemented calibration is the Linux kernel
       function instrumentation (kretprobes).

   Calibrate Linux kernel function instrumentation
       As an example, we use an i7 processor with 4 general-purpose PMU
       registers. This information is available by issuing dmesg, looking
       for generic registers.

       The following sequence of commands gathers a trace executing a
       kretprobe hooked on an empty function, gathering PMU counters LLC
       (Last Level Cache) misses information (use lttng add-context --list
       to get the list of available PMU counters).

           lttng create calibrate-function
           lttng enable-event calibrate --kernel \
           lttng add-context --kernel --type=perf:cpu:LLC-load-misses \
                                      --type=perf:cpu:LLC-store-misses \
           lttng start

           for a in $(seq 1 10); do
               lttng calibrate --kernel --function

           lttng destroy
           babeltrace $(ls -1drt ~/lttng-traces/calibrate-function-* | tail -n 1)

       The output from babeltrace(1) can be saved to a text file and opened
       in a spreadsheet (for example, in LibreOffice) to focus on the
       per-PMU counter delta between consecutive calibrate_entry and
       calibrate_return events. Note that these counters are per-CPU, so
       scheduling events would need to be present to account for migration
       between CPUs. Therefore, for calibration purposes, only events
       staying on the same CPU must be considered.

       Here’s an example of the average result, for the i7, on 10 samples:

       │PMU counter              Average Standard deviation │
       │                         │         │                    │
       │perf_LLC_load_misses     │ 5.0     │ 0.577              │
       │                         │         │                    │
       │perf_LLC_store_misses    │ 1.6     │ 0.516              │
       │                         │         │                    │
       │perf_LLC_prefetch_misses │ 9.0     │ 14.742             │

       As we can notice, the load and store misses are relatively stable
       across runs (their standard deviation is relatively low) compared to
       the prefetch misses. We could conclude from this information that LLC
       load and store misses can be accounted for quite precisely, but
       prefetches within a function seems to behave too erratically (not
       much causality link between the code executed and the CPU prefetch
       activity) to be accounted for.

OPTIONS         top

       General options are described in lttng(1).

       One of:

       -k, --kernel
           Quantify LTTng overhead in the Linux kernel domain.

       -u, --userspace
           Quantify LTTng overhead in the user space domain.

           Use dynamic function entry/return probes to calibrate (default).

           This option requires the --kernel option.

   Program information
       -h, --help
           Show command help.

           This option, like lttng-help(1), attempts to launch /usr/bin/man
           to view the command’s man page. The path to the man pager can be
           overridden by the LTTNG_MAN_BIN_PATH environment variable.

           List available command options.


           Set to 1 to abort the process after the first error is

           Overrides the $HOME environment variable. Useful when the user
           running the commands has a non-writable home directory.

           Absolute path to the man pager to use for viewing help
           information about LTTng commands (using lttng-help(1) or lttng
           COMMAND --help).

           Path in which the session.xsd session configuration XML schema
           may be found.

           Full session daemon binary path.

           The --sessiond-path option has precedence over this environment

       Note that the lttng-create(1) command can spawn an LTTng session
       daemon automatically if none is running. See lttng-sessiond(8) for
       the environment variables influencing the execution of the session

FILES         top

           User LTTng runtime configuration.

           This is where the per-user current tracing session is stored
           between executions of lttng(1). The current tracing session can
           be set with lttng-set-session(1). See lttng-create(1) for more
           information about tracing sessions.

           Default output directory of LTTng traces. This can be overridden
           with the --output option of the lttng-create(1) command.

           User LTTng runtime and configuration directory.

           Default location of saved user tracing sessions (see
           lttng-save(1) and lttng-load(1)).

           System-wide location of saved tracing sessions (see lttng-save(1)
           and lttng-load(1)).

           $LTTNG_HOME defaults to $HOME when not explicitly set.

EXIT STATUS         top


           Command error

           Undefined command

           Fatal error

           Command warning (something went wrong during the command)

BUGS         top

       If you encounter any issue or usability problem, please report it on
       the LTTng bug tracker <>.

RESOURCES         top

       ·   LTTng project website <>

       ·   LTTng documentation <>

       ·   Git repositories <>

       ·   GitHub organization <>

       ·   Continuous integration <>

       ·   Mailing list <> for support and

       ·   IRC channel <irc://>: #lttng on

COPYRIGHTS         top

       This program is part of the LTTng-tools project.

       LTTng-tools is distributed under the GNU General Public License
       version 2 <>.
       See the LICENSE <
       tools/blob/master/LICENSE> file for details.

THANKS         top

       Special thanks to Michel Dagenais and the DORSAL laboratory
       <> at École Polytechnique de Montréal
       for the LTTng journey.

       Also thanks to the Ericsson teams working on tracing which helped us
       greatly with detailed bug reports and unusual test cases.

AUTHORS         top

       LTTng-tools was originally written by Mathieu Desnoyers, Julien
       Desfossez, and David Goulet. More people have since contributed to

       LTTng-tools is currently maintained by Jérémie Galarneau

SEE ALSO         top


COLOPHON         top

       This page is part of the LTTng-Tools (    LTTng tools) project.
       Information about the project can be found at ⟨⟩.
       It is not known how to report bugs for this man page; if you know,
       please send a mail to  This page was obtained
       from the project's upstream Git repository
       ⟨git://⟩ on 2019-11-19.  (At that time,
       the date of the most recent commit that was found in the repository
       was 2019-11-14.)  If you discover any rendering problems in this HTML
       version of the page, or you believe there is a better or more up-to-
       date source for the page, or you have corrections or improvements to
       the information in this COLOPHON (which is not part of the original
       manual page), send a mail to

LTTng 2.9.0-pre                  10/04/2016               LTTNG-CALIBRATE(1)