1 The LTTng Documentation
2 =======================
3 Philippe Proulx <pproulx@efficios.com>
7 include::../common/copyright.txt[]
10 include::../common/welcome.txt[]
13 include::../common/audience.txt[]
17 === What's in this documentation?
19 The LTTng Documentation is divided into the following sections:
21 * **<<nuts-and-bolts,Nuts and bolts>>** explains the
22 rudiments of software tracing and the rationale behind the
25 You can skip this section if you’re familiar with software tracing and
26 with the LTTng project.
28 * **<<installing-lttng,Installation>>** describes the steps to
29 install the LTTng packages on common Linux distributions and from
32 You can skip this section if you already properly installed LTTng on
35 * **<<getting-started,Quick start>>** is a concise guide to
36 getting started quickly with LTTng kernel and user space tracing.
38 We recommend this section if you're new to LTTng or to software tracing
41 You can skip this section if you're not new to LTTng.
43 * **<<core-concepts,Core concepts>>** explains the concepts at
46 It's a good idea to become familiar with the core concepts
47 before attempting to use the toolkit.
49 * **<<plumbing,Components of LTTng>>** describes the various components
50 of the LTTng machinery, like the daemons, the libraries, and the
51 command-line interface.
52 * **<<instrumenting,Instrumentation>>** shows different ways to
53 instrument user applications and the Linux kernel.
55 Instrumenting source code is essential to provide a meaningful
58 You can skip this section if you do not have a programming background.
60 * **<<controlling-tracing,Tracing control>>** is divided into topics
61 which demonstrate how to use the vast array of features that
62 LTTng{nbsp}{revision} offers.
63 * **<<reference,Reference>>** contains reference tables.
64 * **<<glossary,Glossary>>** is a specialized dictionary of terms related
65 to LTTng or to the field of software tracing.
68 include::../common/convention.txt[]
71 include::../common/acknowledgements.txt[]
75 == What's new in LTTng {revision}?
77 LTTng{nbsp}{revision} bears the name _KeKriek_. From
78 http://brasseriedunham.com/[Brasserie Dunham], the _**KeKriek**_ is a
79 sour mashed golden wheat ale fermented with local sour cherries from
80 Tougas orchards. Fresh sweet cherry notes with some tartness, lively
81 carbonation with a dry finish.
83 New features and changes in LTTng{nbsp}{revision}:
85 * **Tracing control**:
86 ** You can put more than one wildcard special character (`*`), and not
87 only at the end, when you <<enabling-disabling-events,create an event
88 rule>>, in both the instrumentation point name and the literal
90 link:/man/1/lttng-enable-event/v{revision}/#doc-filter-syntax[filter expressions]:
95 # lttng enable-event --kernel 'x86_*_local_timer_*' \
96 --filter='name == "*a*b*c*d*e" && count >= 23'
103 $ lttng enable-event --userspace '*_my_org:*msg*'
107 ** New trigger and notification API for
108 <<liblttng-ctl-lttng,`liblttng-ctl`>>. This new subsystem allows you
109 to register triggers which emit a notification when a given
110 condition is satisfied. As of LTTng{nbsp}{revision}, only
111 <<channel,channel>> buffer usage conditions are available.
112 Documentation is available in the
113 https://github.com/lttng/lttng-tools/tree/stable-{revision}/include/lttng[`liblttng-ctl`
115 <<notif-trigger-api,Get notified when a channel's buffer usage is too
118 ** You can now embed the whole textual LTTng-tools man pages into the
119 executables at build time with the `--enable-embedded-help`
120 configuration option. Thanks to this option, you don't need the
121 http://www.methods.co.nz/asciidoc/[AsciiDoc] and
122 https://directory.fsf.org/wiki/Xmlto[xmlto] tools at build time, and
123 a manual pager at run time, to get access to this documentation.
125 * **User space tracing**:
126 ** New blocking mode: an LTTng-UST tracepoint can now block until
127 <<channel,sub-buffer>> space is available instead of discarding event
128 records in <<channel-overwrite-mode-vs-discard-mode,discard mode>>.
129 With this feature, you can be sure that no event records are
130 discarded during your application's execution at the expense of
133 For example, the following command lines create a user space tracing
134 channel with an infinite blocking timeout and run an application
135 instrumented with LTTng-UST which is explicitly allowed to block:
141 $ lttng enable-channel --userspace --blocking-timeout=inf blocking-channel
142 $ lttng enable-event --userspace --channel=blocking-channel --all
144 $ LTTNG_UST_ALLOW_BLOCKING=1 my-app
148 See the complete <<blocking-timeout-example,blocking timeout example>>.
150 * **Linux kernel tracing**:
151 ** Linux 4.10, 4.11, and 4.12 support.
152 ** The thread state dump events recorded by LTTng-modules now contain
153 the task's CPU identifier. This improves the precision of the
154 scheduler model for analyses.
155 ** Extended man:socketpair(2) system call tracing data.
161 What is LTTng? As its name suggests, the _Linux Trace Toolkit: next
162 generation_ is a modern toolkit for tracing Linux systems and
163 applications. So your first question might be:
170 As the history of software engineering progressed and led to what
171 we now take for granted--complex, numerous and
172 interdependent software applications running in parallel on
173 sophisticated operating systems like Linux--the authors of such
174 components, software developers, began feeling a natural
175 urge to have tools that would ensure the robustness and good performance
176 of their masterpieces.
178 One major achievement in this field is, inarguably, the
179 https://www.gnu.org/software/gdb/[GNU debugger (GDB)],
180 an essential tool for developers to find and fix bugs. But even the best
181 debugger won't help make your software run faster, and nowadays, faster
182 software means either more work done by the same hardware, or cheaper
183 hardware for the same work.
185 A _profiler_ is often the tool of choice to identify performance
186 bottlenecks. Profiling is suitable to identify _where_ performance is
187 lost in a given software. The profiler outputs a profile, a statistical
188 summary of observed events, which you may use to discover which
189 functions took the most time to execute. However, a profiler won't
190 report _why_ some identified functions are the bottleneck. Bottlenecks
191 might only occur when specific conditions are met, conditions that are
192 sometimes impossible to capture by a statistical profiler, or impossible
193 to reproduce with an application altered by the overhead of an
194 event-based profiler. For a thorough investigation of software
195 performance issues, a history of execution is essential, with the
196 recorded values of variables and context fields you choose, and
197 with as little influence as possible on the instrumented software. This
198 is where tracing comes in handy.
200 _Tracing_ is a technique used to understand what goes on in a running
201 software system. The software used for tracing is called a _tracer_,
202 which is conceptually similar to a tape recorder. When recording,
203 specific instrumentation points placed in the software source code
204 generate events that are saved on a giant tape: a _trace_ file. You
205 can trace user applications and the operating system at the same time,
206 opening the possibility of resolving a wide range of problems that would
207 otherwise be extremely challenging.
209 Tracing is often compared to _logging_. However, tracers and loggers are
210 two different tools, serving two different purposes. Tracers are
211 designed to record much lower-level events that occur much more
212 frequently than log messages, often in the range of thousands per
213 second, with very little execution overhead. Logging is more appropriate
214 for a very high-level analysis of less frequent events: user accesses,
215 exceptional conditions (errors and warnings, for example), database
216 transactions, instant messaging communications, and such. Simply put,
217 logging is one of the many use cases that can be satisfied with tracing.
219 The list of recorded events inside a trace file can be read manually
220 like a log file for the maximum level of detail, but it is generally
221 much more interesting to perform application-specific analyses to
222 produce reduced statistics and graphs that are useful to resolve a
223 given problem. Trace viewers and analyzers are specialized tools
226 In the end, this is what LTTng is: a powerful, open source set of
227 tools to trace the Linux kernel and user applications at the same time.
228 LTTng is composed of several components actively maintained and
229 developed by its link:/community/#where[community].
232 [[lttng-alternatives]]
233 === Alternatives to noch:{LTTng}
235 Excluding proprietary solutions, a few competing software tracers
238 * https://github.com/dtrace4linux/linux[dtrace4linux] is a port of
239 Sun Microsystems's DTrace to Linux. The cmd:dtrace tool interprets
240 user scripts and is responsible for loading code into the
241 Linux kernel for further execution and collecting the outputted data.
242 * https://en.wikipedia.org/wiki/Berkeley_Packet_Filter[eBPF] is a
243 subsystem in the Linux kernel in which a virtual machine can execute
244 programs passed from the user space to the kernel. You can attach
245 such programs to tracepoints and KProbes thanks to a system call, and
246 they can output data to the user space when executed thanks to
247 different mechanisms (pipe, VM register values, and eBPF maps, to name
249 * https://www.kernel.org/doc/Documentation/trace/ftrace.txt[ftrace]
250 is the de facto function tracer of the Linux kernel. Its user
251 interface is a set of special files in sysfs.
252 * https://perf.wiki.kernel.org/[perf] is
253 a performance analyzing tool for Linux which supports hardware
254 performance counters, tracepoints, as well as other counters and
255 types of probes. perf's controlling utility is the cmd:perf command
257 * http://linux.die.net/man/1/strace[strace]
258 is a command-line utility which records system calls made by a
259 user process, as well as signal deliveries and changes of process
260 state. strace makes use of https://en.wikipedia.org/wiki/Ptrace[ptrace]
261 to fulfill its function.
262 * http://www.sysdig.org/[sysdig], like SystemTap, uses scripts to
263 analyze Linux kernel events. You write scripts, or _chisels_ in
264 sysdig's jargon, in Lua and sysdig executes them while the system is
265 being traced or afterwards. sysdig's interface is the cmd:sysdig
266 command-line tool as well as the curses-based cmd:csysdig tool.
267 * https://sourceware.org/systemtap/[SystemTap] is a Linux kernel and
268 user space tracer which uses custom user scripts to produce plain text
269 traces. SystemTap converts the scripts to the C language, and then
270 compiles them as Linux kernel modules which are loaded to produce
271 trace data. SystemTap's primary user interface is the cmd:stap
274 The main distinctive features of LTTng is that it produces correlated
275 kernel and user space traces, as well as doing so with the lowest
276 overhead amongst other solutions. It produces trace files in the
277 http://diamon.org/ctf[CTF] format, a file format optimized
278 for the production and analyses of multi-gigabyte data.
280 LTTng is the result of more than 10 years of active open source
281 development by a community of passionate developers.
282 LTTng{nbsp}{revision} is currently available on major desktop and server
285 The main interface for tracing control is a single command-line tool
286 named cmd:lttng. The latter can create several tracing sessions, enable
287 and disable events on the fly, filter events efficiently with custom
288 user expressions, start and stop tracing, and much more. LTTng can
289 record the traces on the file system or send them over the network, and
290 keep them totally or partially. You can view the traces once tracing
291 becomes inactive or in real-time.
293 <<installing-lttng,Install LTTng now>> and
294 <<getting-started,start tracing>>!
300 **LTTng** is a set of software <<plumbing,components>> which interact to
301 <<instrumenting,instrument>> the Linux kernel and user applications, and
302 to <<controlling-tracing,control tracing>> (start and stop
303 tracing, enable and disable event rules, and the rest). Those
304 components are bundled into the following packages:
306 * **LTTng-tools**: Libraries and command-line interface to
308 * **LTTng-modules**: Linux kernel modules to instrument and
310 * **LTTng-UST**: Libraries and Java/Python packages to instrument and
311 trace user applications.
313 Most distributions mark the LTTng-modules and LTTng-UST packages as
314 optional when installing LTTng-tools (which is always required). In the
315 following sections, we always provide the steps to install all three,
318 * You only need to install LTTng-modules if you intend to trace the
320 * You only need to install LTTng-UST if you intend to trace user
324 .Availability of LTTng{nbsp}{revision} for major Linux distributions as of 22 January 2018.
326 |Distribution |Available in releases |Alternatives
328 |https://www.ubuntu.com/[Ubuntu]
329 |Ubuntu{nbsp}14.04 _Trusty Tahr_ and Ubuntu{nbsp}16.04 _Xenial Xerus_:
330 <<ubuntu-ppa,use the LTTng Stable{nbsp}{revision} PPA>>.
331 |link:/docs/v2.9#doc-ubuntu[LTTng{nbsp}2.9 for Ubuntu{nbsp}17.04 _Zesty Zapus_ and Ubuntu{nbsp}17.10 _Artful Aardvark_].
333 <<building-from-source,Build LTTng{nbsp}{revision} from source>> for
334 other Ubuntu releases.
336 |https://getfedora.org/[Fedora]
337 |<<fedora,Fedora{nbsp}27>>.
338 |link:/docs/v2.9#doc-fedora[LTTng{nbsp}2.9 for Fedora{nbsp}26].
340 <<building-from-source,Build LTTng{nbsp}{revision} from source>> for
341 other Fedora releases.
343 |https://www.debian.org/[Debian]
344 |<<debian,Debian "buster" (testing) and Debian "sid" (unstable)>>.
345 |link:/docs/v2.9#doc-debian[LTTng{nbsp}2.9 for Debian "stretch" (stable)].
347 <<building-from-source,Build LTTng{nbsp}{revision} from source>>.
349 |https://www.archlinux.org/[Arch Linux]
350 |<<arch-linux,Current Arch Linux build>>.
351 |<<building-from-source,Build LTTng{nbsp}{revision} from source>>.
353 |https://alpinelinux.org/[Alpine Linux]
354 |<<alpine-linux,Alpine Linux{nbsp}3.7 and Alpine Linux{nbsp}"edge">>.
355 |<<building-from-source,Build LTTng{nbsp}{revision} from source>>.
357 |https://www.redhat.com/[RHEL] and https://www.suse.com/[SLES]
358 |See http://packages.efficios.com/[EfficiOS Enterprise Packages].
361 |https://buildroot.org/[Buildroot]
363 |link:/docs/v2.9#doc-buildroot[LTTng{nbsp}2.9 for Buildroot{nbsp}2017.02,
364 Buildroot{nbsp}2017.05, Buildroot{nbsp}2017.08, and Buildroot{nbsp}2017.11].
366 <<building-from-source,Build LTTng{nbsp}{revision} from source>>.
368 |http://www.openembedded.org/wiki/Main_Page[OpenEmbedded] and
369 https://www.yoctoproject.org/[Yocto]
371 |link:/docs/v2.9#doc-oe-yocto[LTTng{nbsp}2.9 for Yocto Project{nbsp}2.3 _Pyro_
372 and Yocto Project{nbsp}2.4 _Rocko_]
373 (`openembedded-core` layer).
375 <<building-from-source,Build LTTng{nbsp}{revision} from source>>.
380 === [[ubuntu-official-repositories]]Ubuntu
383 ==== noch:{LTTng} Stable {revision} PPA
385 The https://launchpad.net/~lttng/+archive/ubuntu/stable-{revision}[LTTng
386 Stable{nbsp}{revision} PPA] offers the latest stable
387 LTTng{nbsp}{revision} packages for:
389 * Ubuntu{nbsp}14.04 _Trusty Tahr_
390 * Ubuntu{nbsp}16.04 _Xenial Xerus_
392 To install LTTng{nbsp}{revision} from the LTTng Stable{nbsp}{revision} PPA:
394 . Add the LTTng Stable{nbsp}{revision} PPA repository and update the
400 # apt-add-repository ppa:lttng/stable-2.10
405 . Install the main LTTng{nbsp}{revision} packages:
410 # apt-get install lttng-tools
411 # apt-get install lttng-modules-dkms
412 # apt-get install liblttng-ust-dev
416 . **If you need to instrument and trace
417 <<java-application,Java applications>>**, install the LTTng-UST
423 # apt-get install liblttng-ust-agent-java
427 . **If you need to instrument and trace
428 <<python-application,Python{nbsp}3 applications>>**, install the
429 LTTng-UST Python agent:
434 # apt-get install python3-lttngust
442 To install LTTng{nbsp}{revision} on Fedora{nbsp}27:
444 . Install the LTTng-tools{nbsp}{revision} and LTTng-UST{nbsp}{revision}
450 # yum install lttng-tools
451 # yum install lttng-ust
455 . Download, build, and install the latest LTTng-modules{nbsp}{revision}:
461 wget http://lttng.org/files/lttng-modules/lttng-modules-latest-2.10.tar.bz2 &&
462 tar -xf lttng-modules-latest-2.10.tar.bz2 &&
463 cd lttng-modules-2.10.* &&
465 sudo make modules_install &&
471 .Java and Python application instrumentation and tracing
473 If you need to instrument and trace <<java-application,Java
474 applications>> on Fedora, you need to build and install
475 LTTng-UST{nbsp}{revision} <<building-from-source,from source>> and pass
476 the `--enable-java-agent-jul`, `--enable-java-agent-log4j`, or
477 `--enable-java-agent-all` options to the `configure` script, depending
478 on which Java logging framework you use.
480 If you need to instrument and trace <<python-application,Python
481 applications>> on Fedora, you need to build and install
482 LTTng-UST{nbsp}{revision} from source and pass the
483 `--enable-python-agent` option to the `configure` script.
490 To install LTTng{nbsp}{revision} on Debian "buster" (testing)
491 or Debian "sid" (unstable):
493 . Install the main LTTng{nbsp}{revision} packages:
498 # apt-get install lttng-modules-dkms
499 # apt-get install liblttng-ust-dev
500 # apt-get install lttng-tools
504 . **If you need to instrument and trace <<java-application,Java
505 applications>>**, install the LTTng-UST Java agent:
510 # apt-get install liblttng-ust-agent-java
514 . **If you need to instrument and trace <<python-application,Python
515 applications>>**, install the LTTng-UST Python agent:
520 # apt-get install python3-lttngust
528 LTTng-UST{nbsp}{revision} is available in Arch Linux's _Community_
529 repository, while LTTng-tools{nbsp}{revision} and
530 LTTng-modules{nbsp}{revision} are available in the
531 https://aur.archlinux.org/[AUR].
533 To install LTTng{nbsp}{revision} on Arch Linux, using
534 https://github.com/rmarquis/pacaur[pacaur] for the AUR packages:
536 . Install the main LTTng{nbsp}{revision} packages:
541 # pacman -Sy lttng-ust
542 $ pacaur -Sy lttng-tools
543 $ pacaur -Sy lttng-modules
547 . **If you need to instrument and trace <<python-application,Python
548 applications>>**, install the LTTng-UST Python agent:
553 # pacman -Sy python-lttngust
554 # pacman -Sy python2-lttngust
562 To install LTTng-tools{nbsp}{revision} and LTTng-UST{nbsp}{revision} on
563 Alpine Linux{nbsp}3.7 or Alpine Linux{nbsp}"edge":
565 . **If you're installing for Alpine Linux{nbsp}"edge"**, make sure your
566 system is https://wiki.alpinelinux.org/wiki/Edge[configured for
568 . **If you're installing for Alpine Linux{nbsp}"edge"**, enable the _testing_
569 repository by uncommenting the corresponding line in
570 path:{/etc/apk/repositories}.
571 . Add the LTTng packages:
576 # apk add lttng-tools
577 # apk add lttng-ust-dev
581 To install LTTng-modules{nbsp}{revision} (Linux kernel tracing support)
582 on Alpine Linux{nbsp}3.7 or Alpine Linux{nbsp}"edge":
584 . Add the vanilla Linux kernel:
589 # apk add linux-vanilla linux-vanilla-dev
593 . Reboot with the vanilla Linux kernel.
594 . Download, build, and install the latest LTTng-modules{nbsp}{revision}:
600 wget http://lttng.org/files/lttng-modules/lttng-modules-latest-2.10.tar.bz2 &&
601 tar -xf lttng-modules-latest-2.10.tar.bz2 &&
602 cd lttng-modules-2.10.* &&
604 sudo make modules_install &&
610 [[enterprise-distributions]]
611 === RHEL, SUSE, and other enterprise distributions
613 To install LTTng on enterprise Linux distributions, such as Red Hat
614 Enterprise Linux (RHEL) and SUSE Linux Enterprise Server (SUSE), please
615 see http://packages.efficios.com/[EfficiOS Enterprise Packages].
618 [[building-from-source]]
619 === Build from source
621 To build and install LTTng{nbsp}{revision} from source:
623 . Using your distribution's package manager, or from source, install
624 the following dependencies of LTTng-tools and LTTng-UST:
627 * https://sourceforge.net/projects/libuuid/[libuuid]
628 * http://directory.fsf.org/wiki/Popt[popt]
629 * http://liburcu.org/[Userspace RCU]
630 * http://www.xmlsoft.org/[libxml2]
633 . Download, build, and install the latest LTTng-modules{nbsp}{revision}:
639 wget http://lttng.org/files/lttng-modules/lttng-modules-latest-2.10.tar.bz2 &&
640 tar -xf lttng-modules-latest-2.10.tar.bz2 &&
641 cd lttng-modules-2.10.* &&
643 sudo make modules_install &&
648 . Download, build, and install the latest LTTng-UST{nbsp}{revision}:
654 wget http://lttng.org/files/lttng-ust/lttng-ust-latest-2.10.tar.bz2 &&
655 tar -xf lttng-ust-latest-2.10.tar.bz2 &&
656 cd lttng-ust-2.10.* &&
666 .Java and Python application tracing
668 If you need to instrument and trace <<java-application,Java
669 applications>>, pass the `--enable-java-agent-jul`,
670 `--enable-java-agent-log4j`, or `--enable-java-agent-all` options to the
671 `configure` script, depending on which Java logging framework you use.
673 If you need to instrument and trace <<python-application,Python
674 applications>>, pass the `--enable-python-agent` option to the
675 `configure` script. You can set the `PYTHON` environment variable to the
676 path to the Python interpreter for which to install the LTTng-UST Python
684 By default, LTTng-UST libraries are installed to
685 dir:{/usr/local/lib}, which is the de facto directory in which to
686 keep self-compiled and third-party libraries.
688 When <<building-tracepoint-providers-and-user-application,linking an
689 instrumented user application with `liblttng-ust`>>:
691 * Append `/usr/local/lib` to the env:LD_LIBRARY_PATH environment
693 * Pass the `-L/usr/local/lib` and `-Wl,-rpath,/usr/local/lib` options to
694 man:gcc(1), man:g++(1), or man:clang(1).
698 . Download, build, and install the latest LTTng-tools{nbsp}{revision}:
704 wget http://lttng.org/files/lttng-tools/lttng-tools-latest-2.10.tar.bz2 &&
705 tar -xf lttng-tools-latest-2.10.tar.bz2 &&
706 cd lttng-tools-2.10.* &&
714 TIP: The https://github.com/eepp/vlttng[vlttng tool] can do all the
715 previous steps automatically for a given version of LTTng and confine
716 the installed files in a specific directory. This can be useful to test
717 LTTng without installing it on your system.
723 This is a short guide to get started quickly with LTTng kernel and user
726 Before you follow this guide, make sure to <<installing-lttng,install>>
729 This tutorial walks you through the steps to:
731 . <<tracing-the-linux-kernel,Trace the Linux kernel>>.
732 . <<tracing-your-own-user-application,Trace a user application>> written
734 . <<viewing-and-analyzing-your-traces,View and analyze the
738 [[tracing-the-linux-kernel]]
739 === Trace the Linux kernel
741 The following command lines start with the `#` prompt because you need
742 root privileges to trace the Linux kernel. You can also trace the kernel
743 as a regular user if your Unix user is a member of the
744 <<tracing-group,tracing group>>.
746 . Create a <<tracing-session,tracing session>> which writes its traces
747 to dir:{/tmp/my-kernel-trace}:
752 # lttng create my-kernel-session --output=/tmp/my-kernel-trace
756 . List the available kernel tracepoints and system calls:
761 # lttng list --kernel
762 # lttng list --kernel --syscall
766 . Create <<event,event rules>> which match the desired instrumentation
767 point names, for example the `sched_switch` and `sched_process_fork`
768 tracepoints, and the man:open(2) and man:close(2) system calls:
773 # lttng enable-event --kernel sched_switch,sched_process_fork
774 # lttng enable-event --kernel --syscall open,close
778 You can also create an event rule which matches _all_ the Linux kernel
779 tracepoints (this will generate a lot of data when tracing):
784 # lttng enable-event --kernel --all
788 . <<basic-tracing-session-control,Start tracing>>:
797 . Do some operation on your system for a few seconds. For example,
798 load a website, or list the files of a directory.
799 . <<basic-tracing-session-control,Stop tracing>> and destroy the
810 The man:lttng-destroy(1) command does not destroy the trace data; it
811 only destroys the state of the tracing session.
813 . For the sake of this example, make the recorded trace accessible to
819 # chown -R $(whoami) /tmp/my-kernel-trace
823 See <<viewing-and-analyzing-your-traces,View and analyze the
824 recorded events>> to view the recorded events.
827 [[tracing-your-own-user-application]]
828 === Trace a user application
830 This section steps you through a simple example to trace a
831 _Hello world_ program written in C.
833 To create the traceable user application:
835 . Create the tracepoint provider header file, which defines the
836 tracepoints and the events they can generate:
842 #undef TRACEPOINT_PROVIDER
843 #define TRACEPOINT_PROVIDER hello_world
845 #undef TRACEPOINT_INCLUDE
846 #define TRACEPOINT_INCLUDE "./hello-tp.h"
848 #if !defined(_HELLO_TP_H) || defined(TRACEPOINT_HEADER_MULTI_READ)
851 #include <lttng/tracepoint.h>
861 ctf_string(my_string_field, my_string_arg)
862 ctf_integer(int, my_integer_field, my_integer_arg)
866 #endif /* _HELLO_TP_H */
868 #include <lttng/tracepoint-event.h>
872 . Create the tracepoint provider package source file:
878 #define TRACEPOINT_CREATE_PROBES
879 #define TRACEPOINT_DEFINE
881 #include "hello-tp.h"
885 . Build the tracepoint provider package:
890 $ gcc -c -I. hello-tp.c
894 . Create the _Hello World_ application source file:
901 #include "hello-tp.h"
903 int main(int argc, char *argv[])
907 puts("Hello, World!\nPress Enter to continue...");
910 * The following getchar() call is only placed here for the purpose
911 * of this demonstration, to pause the application in order for
912 * you to have time to list its tracepoints. It is not
918 * A tracepoint() call.
920 * Arguments, as defined in hello-tp.h:
922 * 1. Tracepoint provider name (required)
923 * 2. Tracepoint name (required)
924 * 3. my_integer_arg (first user-defined argument)
925 * 4. my_string_arg (second user-defined argument)
927 * Notice the tracepoint provider and tracepoint names are
928 * NOT strings: they are in fact parts of variables that the
929 * macros in hello-tp.h create.
931 tracepoint(hello_world, my_first_tracepoint, 23, "hi there!");
933 for (x = 0; x < argc; ++x) {
934 tracepoint(hello_world, my_first_tracepoint, x, argv[x]);
937 puts("Quitting now!");
938 tracepoint(hello_world, my_first_tracepoint, x * x, "x^2");
945 . Build the application:
954 . Link the application with the tracepoint provider package,
955 `liblttng-ust`, and `libdl`:
960 $ gcc -o hello hello.o hello-tp.o -llttng-ust -ldl
964 Here's the whole build process:
967 .User space tracing tutorial's build steps.
968 image::ust-flow.png[]
970 To trace the user application:
972 . Run the application with a few arguments:
977 $ ./hello world and beyond
986 Press Enter to continue...
990 . Start an LTTng <<lttng-sessiond,session daemon>>:
995 $ lttng-sessiond --daemonize
999 Note that a session daemon might already be running, for example as
1000 a service that the distribution's service manager started.
1002 . List the available user space tracepoints:
1007 $ lttng list --userspace
1011 You see the `hello_world:my_first_tracepoint` tracepoint listed
1012 under the `./hello` process.
1014 . Create a <<tracing-session,tracing session>>:
1019 $ lttng create my-user-space-session
1023 . Create an <<event,event rule>> which matches the
1024 `hello_world:my_first_tracepoint` event name:
1029 $ lttng enable-event --userspace hello_world:my_first_tracepoint
1033 . <<basic-tracing-session-control,Start tracing>>:
1042 . Go back to the running `hello` application and press Enter. The
1043 program executes all `tracepoint()` instrumentation points and exits.
1044 . <<basic-tracing-session-control,Stop tracing>> and destroy the
1055 The man:lttng-destroy(1) command does not destroy the trace data; it
1056 only destroys the state of the tracing session.
1058 By default, LTTng saves the traces in
1059 +$LTTNG_HOME/lttng-traces/__name__-__date__-__time__+,
1060 where +__name__+ is the tracing session name. The
1061 env:LTTNG_HOME environment variable defaults to `$HOME` if not set.
1063 See <<viewing-and-analyzing-your-traces,View and analyze the
1064 recorded events>> to view the recorded events.
1067 [[viewing-and-analyzing-your-traces]]
1068 === View and analyze the recorded events
1070 Once you have completed the <<tracing-the-linux-kernel,Trace the Linux
1071 kernel>> and <<tracing-your-own-user-application,Trace a user
1072 application>> tutorials, you can inspect the recorded events.
1074 Many tools are available to read LTTng traces:
1076 * **cmd:babeltrace** is a command-line utility which converts trace
1077 formats; it supports the format that LTTng produces, CTF, as well as a
1078 basic text output which can be ++grep++ed. The cmd:babeltrace command
1079 is part of the http://diamon.org/babeltrace[Babeltrace] project.
1080 * Babeltrace also includes
1081 **https://www.python.org/[Python] bindings** so
1082 that you can easily open and read an LTTng trace with your own script,
1083 benefiting from the power of Python.
1084 * http://tracecompass.org/[**Trace Compass**]
1085 is a graphical user interface for viewing and analyzing any type of
1086 logs or traces, including LTTng's.
1087 * https://github.com/lttng/lttng-analyses[**LTTng analyses**] is a
1088 project which includes many high-level analyses of LTTng kernel
1089 traces, like scheduling statistics, interrupt frequency distribution,
1090 top CPU usage, and more.
1092 NOTE: This section assumes that the traces recorded during the previous
1093 tutorials were saved to their default location, in the
1094 dir:{$LTTNG_HOME/lttng-traces} directory. The env:LTTNG_HOME
1095 environment variable defaults to `$HOME` if not set.
1098 [[viewing-and-analyzing-your-traces-bt]]
1099 ==== Use the cmd:babeltrace command-line tool
1101 The simplest way to list all the recorded events of a trace is to pass
1102 its path to cmd:babeltrace with no options:
1106 $ babeltrace ~/lttng-traces/my-user-space-session*
1109 cmd:babeltrace finds all traces recursively within the given path and
1110 prints all their events, merging them in chronological order.
1112 You can pipe the output of cmd:babeltrace into a tool like man:grep(1) for
1117 $ babeltrace /tmp/my-kernel-trace | grep _switch
1120 You can pipe the output of cmd:babeltrace into a tool like man:wc(1) to
1121 count the recorded events:
1125 $ babeltrace /tmp/my-kernel-trace | grep _open | wc --lines
1129 [[viewing-and-analyzing-your-traces-bt-python]]
1130 ==== Use the Babeltrace Python bindings
1132 The <<viewing-and-analyzing-your-traces-bt,text output of cmd:babeltrace>>
1133 is useful to isolate events by simple matching using man:grep(1) and
1134 similar utilities. However, more elaborate filters, such as keeping only
1135 event records with a field value falling within a specific range, are
1136 not trivial to write using a shell. Moreover, reductions and even the
1137 most basic computations involving multiple event records are virtually
1138 impossible to implement.
1140 Fortunately, Babeltrace ships with Python 3 bindings which makes it easy
1141 to read the event records of an LTTng trace sequentially and compute the
1142 desired information.
1144 The following script accepts an LTTng Linux kernel trace path as its
1145 first argument and prints the short names of the top 5 running processes
1146 on CPU 0 during the whole trace:
1151 from collections import Counter
1157 if len(sys.argv) != 2:
1158 msg = 'Usage: python3 {} TRACEPATH'.format(sys.argv[0])
1159 print(msg, file=sys.stderr)
1162 # A trace collection contains one or more traces
1163 col = babeltrace.TraceCollection()
1165 # Add the trace provided by the user (LTTng traces always have
1167 if col.add_trace(sys.argv[1], 'ctf') is None:
1168 raise RuntimeError('Cannot add trace')
1170 # This counter dict contains execution times:
1172 # task command name -> total execution time (ns)
1173 exec_times = Counter()
1175 # This contains the last `sched_switch` timestamp
1179 for event in col.events:
1180 # Keep only `sched_switch` events
1181 if event.name != 'sched_switch':
1184 # Keep only events which happened on CPU 0
1185 if event['cpu_id'] != 0:
1189 cur_ts = event.timestamp
1195 # Previous task command (short) name
1196 prev_comm = event['prev_comm']
1198 # Initialize entry in our dict if not yet done
1199 if prev_comm not in exec_times:
1200 exec_times[prev_comm] = 0
1202 # Compute previous command execution time
1203 diff = cur_ts - last_ts
1205 # Update execution time of this command
1206 exec_times[prev_comm] += diff
1208 # Update last timestamp
1212 for name, ns in exec_times.most_common(5):
1214 print('{:20}{} s'.format(name, s))
1219 if __name__ == '__main__':
1220 sys.exit(0 if top5proc() else 1)
1227 $ python3 top5proc.py /tmp/my-kernel-trace/kernel
1233 swapper/0 48.607245889 s
1234 chromium 7.192738188 s
1235 pavucontrol 0.709894415 s
1236 Compositor 0.660867933 s
1237 Xorg.bin 0.616753786 s
1240 Note that `swapper/0` is the "idle" process of CPU 0 on Linux; since we
1241 weren't using the CPU that much when tracing, its first position in the
1246 == [[understanding-lttng]]Core concepts
1248 From a user's perspective, the LTTng system is built on a few concepts,
1249 or objects, on which the <<lttng-cli,cmd:lttng command-line tool>>
1250 operates by sending commands to the <<lttng-sessiond,session daemon>>.
1251 Understanding how those objects relate to eachother is key in mastering
1254 The core concepts are:
1256 * <<tracing-session,Tracing session>>
1257 * <<domain,Tracing domain>>
1258 * <<channel,Channel and ring buffer>>
1259 * <<"event","Instrumentation point, event rule, event, and event record">>
1265 A _tracing session_ is a stateful dialogue between you and
1266 a <<lttng-sessiond,session daemon>>. You can
1267 <<creating-destroying-tracing-sessions,create a new tracing
1268 session>> with the `lttng create` command.
1270 Anything that you do when you control LTTng tracers happens within a
1271 tracing session. In particular, a tracing session:
1274 * Has its own set of trace files.
1275 * Has its own state of activity (started or stopped).
1276 * Has its own <<tracing-session-mode,mode>> (local, network streaming,
1278 * Has its own <<channel,channels>> which have their own
1279 <<event,event rules>>.
1282 .A _tracing session_ contains <<channel,channels>> that are members of <<domain,tracing domains>> and contain <<event,event rules>>.
1283 image::concepts.png[]
1285 Those attributes and objects are completely isolated between different
1288 A tracing session is analogous to a cash machine session:
1289 the operations you do on the banking system through the cash machine do
1290 not alter the data of other users of the same system. In the case of
1291 the cash machine, a session lasts as long as your bank card is inside.
1292 In the case of LTTng, a tracing session lasts from the `lttng create`
1293 command to the `lttng destroy` command.
1296 .Each Unix user has its own set of tracing sessions.
1297 image::many-sessions.png[]
1300 [[tracing-session-mode]]
1301 ==== Tracing session mode
1303 LTTng can send the generated trace data to different locations. The
1304 _tracing session mode_ dictates where to send it. The following modes
1305 are available in LTTng{nbsp}{revision}:
1308 LTTng writes the traces to the file system of the machine being traced
1311 Network streaming mode::
1312 LTTng sends the traces over the network to a
1313 <<lttng-relayd,relay daemon>> running on a remote system.
1316 LTTng does not write the traces by default. Instead, you can request
1317 LTTng to <<taking-a-snapshot,take a snapshot>>, that is, a copy of the
1318 current tracing buffers, and to write it to the target's file system
1319 or to send it over the network to a <<lttng-relayd,relay daemon>>
1320 running on a remote system.
1323 This mode is similar to the network streaming mode, but a live
1324 trace viewer can connect to the distant relay daemon to
1325 <<lttng-live,view event records as LTTng generates them>> by
1332 A _tracing domain_ is a namespace for event sources. A tracing domain
1333 has its own properties and features.
1335 There are currently five available tracing domains:
1339 * `java.util.logging` (JUL)
1343 You must specify a tracing domain when using some commands to avoid
1344 ambiguity. For example, since all the domains support named tracepoints
1345 as event sources (instrumentation points that you manually insert in the
1346 source code), you need to specify a tracing domain when
1347 <<enabling-disabling-events,creating an event rule>> because all the
1348 tracing domains could have tracepoints with the same names.
1350 Some features are reserved to specific tracing domains. Dynamic function
1351 entry and return instrumentation points, for example, are currently only
1352 supported in the Linux kernel tracing domain, but support for other
1353 tracing domains could be added in the future.
1355 You can create <<channel,channels>> in the Linux kernel and user space
1356 tracing domains. The other tracing domains have a single default
1361 === Channel and ring buffer
1363 A _channel_ is an object which is responsible for a set of ring buffers.
1364 Each ring buffer is divided into multiple sub-buffers. When an LTTng
1365 tracer emits an event, it can record it to one or more
1366 sub-buffers. The attributes of a channel determine what to do when
1367 there's no space left for a new event record because all sub-buffers
1368 are full, where to send a full sub-buffer, and other behaviours.
1370 A channel is always associated to a <<domain,tracing domain>>. The
1371 `java.util.logging` (JUL), log4j, and Python tracing domains each have
1372 a default channel which you cannot configure.
1374 A channel also owns <<event,event rules>>. When an LTTng tracer emits
1375 an event, it records it to the sub-buffers of all
1376 the enabled channels with a satisfied event rule, as long as those
1377 channels are part of active <<tracing-session,tracing sessions>>.
1380 [[channel-buffering-schemes]]
1381 ==== Per-user vs. per-process buffering schemes
1383 A channel has at least one ring buffer _per CPU_. LTTng always
1384 records an event to the ring buffer associated to the CPU on which it
1387 Two _buffering schemes_ are available when you
1388 <<enabling-disabling-channels,create a channel>> in the
1389 user space <<domain,tracing domain>>:
1391 Per-user buffering::
1392 Allocate one set of ring buffers--one per CPU--shared by all the
1393 instrumented processes of each Unix user.
1397 .Per-user buffering scheme.
1398 image::per-user-buffering.png[]
1401 Per-process buffering::
1402 Allocate one set of ring buffers--one per CPU--for each
1403 instrumented process.
1407 .Per-process buffering scheme.
1408 image::per-process-buffering.png[]
1411 The per-process buffering scheme tends to consume more memory than the
1412 per-user option because systems generally have more instrumented
1413 processes than Unix users running instrumented processes. However, the
1414 per-process buffering scheme ensures that one process having a high
1415 event throughput won't fill all the shared sub-buffers of the same
1418 The Linux kernel tracing domain has only one available buffering scheme
1419 which is to allocate a single set of ring buffers for the whole system.
1420 This scheme is similar to the per-user option, but with a single, global
1421 user "running" the kernel.
1424 [[channel-overwrite-mode-vs-discard-mode]]
1425 ==== Overwrite vs. discard event loss modes
1427 When an event occurs, LTTng records it to a specific sub-buffer (yellow
1428 arc in the following animation) of a specific channel's ring buffer.
1429 When there's no space left in a sub-buffer, the tracer marks it as
1430 consumable (red) and another, empty sub-buffer starts receiving the
1431 following event records. A <<lttng-consumerd,consumer daemon>>
1432 eventually consumes the marked sub-buffer (returns to white).
1435 [role="docsvg-channel-subbuf-anim"]
1440 In an ideal world, sub-buffers are consumed faster than they are filled,
1441 as is the case in the previous animation. In the real world,
1442 however, all sub-buffers can be full at some point, leaving no space to
1443 record the following events.
1445 By default, LTTng-modules and LTTng-UST are _non-blocking_ tracers: when
1446 no empty sub-buffer is available, it is acceptable to lose event records
1447 when the alternative would be to cause substantial delays in the
1448 instrumented application's execution. LTTng privileges performance over
1449 integrity; it aims at perturbing the traced system as little as possible
1450 in order to make tracing of subtle race conditions and rare interrupt
1453 Starting from LTTng{nbsp}2.10, the LTTng user space tracer, LTTng-UST,
1454 supports a _blocking mode_. See the <<blocking-timeout-example,blocking
1455 timeout example>> to learn how to use the blocking mode.
1457 When it comes to losing event records because no empty sub-buffer is
1458 available, or because the <<opt-blocking-timeout,blocking timeout>> is
1459 reached, the channel's _event loss mode_ determines what to do. The
1460 available event loss modes are:
1463 Drop the newest event records until a the tracer releases a
1466 This is the only available mode when you specify a
1467 <<opt-blocking-timeout,blocking timeout>>.
1470 Clear the sub-buffer containing the oldest event records and start
1471 writing the newest event records there.
1473 This mode is sometimes called _flight recorder mode_ because it's
1475 https://en.wikipedia.org/wiki/Flight_recorder[flight recorder]:
1476 always keep a fixed amount of the latest data.
1478 Which mechanism you should choose depends on your context: prioritize
1479 the newest or the oldest event records in the ring buffer?
1481 Beware that, in overwrite mode, the tracer abandons a _whole sub-buffer_
1482 as soon as a there's no space left for a new event record, whereas in
1483 discard mode, the tracer only discards the event record that doesn't
1486 In discard mode, LTTng increments a count of lost event records when an
1487 event record is lost and saves this count to the trace. In overwrite
1488 mode, since LTTng 2.8, LTTng increments a count of lost sub-buffers when
1489 a sub-buffer is lost and saves this count to the trace. In this mode,
1490 the exact number of lost event records in those lost sub-buffers is not
1491 saved to the trace. Trace analyses can use the trace's saved discarded
1492 event record and sub-buffer counts to decide whether or not to perform
1493 the analyses even if trace data is known to be missing.
1495 There are a few ways to decrease your probability of losing event
1497 <<channel-subbuf-size-vs-subbuf-count,Sub-buffer count and size>> shows
1498 how you can fine-une the sub-buffer count and size of a channel to
1499 virtually stop losing event records, though at the cost of greater
1503 [[channel-subbuf-size-vs-subbuf-count]]
1504 ==== Sub-buffer count and size
1506 When you <<enabling-disabling-channels,create a channel>>, you can
1507 set its number of sub-buffers and their size.
1509 Note that there is noticeable CPU overhead introduced when
1510 switching sub-buffers (marking a full one as consumable and switching
1511 to an empty one for the following events to be recorded). Knowing this,
1512 the following list presents a few practical situations along with how
1513 to configure the sub-buffer count and size for them:
1515 * **High event throughput**: In general, prefer bigger sub-buffers to
1516 lower the risk of losing event records.
1518 Having bigger sub-buffers also ensures a lower
1519 <<channel-switch-timer,sub-buffer switching frequency>>.
1521 The number of sub-buffers is only meaningful if you create the channel
1522 in overwrite mode: in this case, if a sub-buffer overwrite happens, the
1523 other sub-buffers are left unaltered.
1525 * **Low event throughput**: In general, prefer smaller sub-buffers
1526 since the risk of losing event records is low.
1528 Because events occur less frequently, the sub-buffer switching frequency
1529 should remain low and thus the tracer's overhead should not be a
1532 * **Low memory system**: If your target system has a low memory
1533 limit, prefer fewer first, then smaller sub-buffers.
1535 Even if the system is limited in memory, you want to keep the
1536 sub-buffers as big as possible to avoid a high sub-buffer switching
1539 Note that LTTng uses http://diamon.org/ctf/[CTF] as its trace format,
1540 which means event data is very compact. For example, the average
1541 LTTng kernel event record weights about 32{nbsp}bytes. Thus, a
1542 sub-buffer size of 1{nbsp}MiB is considered big.
1544 The previous situations highlight the major trade-off between a few big
1545 sub-buffers and more, smaller sub-buffers: sub-buffer switching
1546 frequency vs. how much data is lost in overwrite mode. Assuming a
1547 constant event throughput and using the overwrite mode, the two
1548 following configurations have the same ring buffer total size:
1551 [role="docsvg-channel-subbuf-size-vs-count-anim"]
1556 * **2 sub-buffers of 4{nbsp}MiB each**: Expect a very low sub-buffer
1557 switching frequency, but if a sub-buffer overwrite happens, half of
1558 the event records so far (4{nbsp}MiB) are definitely lost.
1559 * **8 sub-buffers of 1{nbsp}MiB each**: Expect 4{nbsp}times the tracer's
1560 overhead as the previous configuration, but if a sub-buffer
1561 overwrite happens, only the eighth of event records so far are
1564 In discard mode, the sub-buffers count parameter is pointless: use two
1565 sub-buffers and set their size according to the requirements of your
1569 [[channel-switch-timer]]
1570 ==== Switch timer period
1572 The _switch timer period_ is an important configurable attribute of
1573 a channel to ensure periodic sub-buffer flushing.
1575 When the _switch timer_ expires, a sub-buffer switch happens. You can
1576 set the switch timer period attribute when you
1577 <<enabling-disabling-channels,create a channel>> to ensure that event
1578 data is consumed and committed to trace files or to a distant relay
1579 daemon periodically in case of a low event throughput.
1582 [role="docsvg-channel-switch-timer"]
1587 This attribute is also convenient when you use big sub-buffers to cope
1588 with a sporadic high event throughput, even if the throughput is
1592 [[channel-read-timer]]
1593 ==== Read timer period
1595 By default, the LTTng tracers use a notification mechanism to signal a
1596 full sub-buffer so that a consumer daemon can consume it. When such
1597 notifications must be avoided, for example in real-time applications,
1598 you can use the channel's _read timer_ instead. When the read timer
1599 fires, the <<lttng-consumerd,consumer daemon>> checks for full,
1600 consumable sub-buffers.
1603 [[tracefile-rotation]]
1604 ==== Trace file count and size
1606 By default, trace files can grow as large as needed. You can set the
1607 maximum size of each trace file that a channel writes when you
1608 <<enabling-disabling-channels,create a channel>>. When the size of
1609 a trace file reaches the channel's fixed maximum size, LTTng creates
1610 another file to contain the next event records. LTTng appends a file
1611 count to each trace file name in this case.
1613 If you set the trace file size attribute when you create a channel, the
1614 maximum number of trace files that LTTng creates is _unlimited_ by
1615 default. To limit them, you can also set a maximum number of trace
1616 files. When the number of trace files reaches the channel's fixed
1617 maximum count, the oldest trace file is overwritten. This mechanism is
1618 called _trace file rotation_.
1622 === Instrumentation point, event rule, event, and event record
1624 An _event rule_ is a set of conditions which must be **all** satisfied
1625 for LTTng to record an occuring event.
1627 You set the conditions when you <<enabling-disabling-events,create
1630 You always attach an event rule to <<channel,channel>> when you create
1633 When an event passes the conditions of an event rule, LTTng records it
1634 in one of the attached channel's sub-buffers.
1636 The available conditions, as of LTTng{nbsp}{revision}, are:
1638 * The event rule _is enabled_.
1639 * The instrumentation point's type _is{nbsp}T_.
1640 * The instrumentation point's name (sometimes called _event name_)
1641 _matches{nbsp}N_, but _is not{nbsp}E_.
1642 * The instrumentation point's log level _is as severe as{nbsp}L_, or
1643 _is exactly{nbsp}L_.
1644 * The fields of the event's payload _satisfy_ a filter
1645 expression{nbsp}__F__.
1647 As you can see, all the conditions but the dynamic filter are related to
1648 the event rule's status or to the instrumentation point, not to the
1649 occurring events. This is why, without a filter, checking if an event
1650 passes an event rule is not a dynamic task: when you create or modify an
1651 event rule, all the tracers of its tracing domain enable or disable the
1652 instrumentation points themselves once. This is possible because the
1653 attributes of an instrumentation point (type, name, and log level) are
1654 defined statically. In other words, without a dynamic filter, the tracer
1655 _does not evaluate_ the arguments of an instrumentation point unless it
1656 matches an enabled event rule.
1658 Note that, for LTTng to record an event, the <<channel,channel>> to
1659 which a matching event rule is attached must also be enabled, and the
1660 tracing session owning this channel must be active.
1663 .Logical path from an instrumentation point to an event record.
1664 image::event-rule.png[]
1666 .Event, event record, or event rule?
1668 With so many similar terms, it's easy to get confused.
1670 An **event** is the consequence of the execution of an _instrumentation
1671 point_, like a tracepoint that you manually place in some source code,
1672 or a Linux kernel KProbe. An event is said to _occur_ at a specific
1673 time. Different actions can be taken upon the occurrence of an event,
1674 like record the event's payload to a buffer.
1676 An **event record** is the representation of an event in a sub-buffer. A
1677 tracer is responsible for capturing the payload of an event, current
1678 context variables, the event's ID, and the event's timestamp. LTTng
1679 can append this sub-buffer to a trace file.
1681 An **event rule** is a set of conditions which must all be satisfied for
1682 LTTng to record an occuring event. Events still occur without
1683 satisfying event rules, but LTTng does not record them.
1688 == Components of noch:{LTTng}
1690 The second _T_ in _LTTng_ stands for _toolkit_: it would be wrong
1691 to call LTTng a simple _tool_ since it is composed of multiple
1692 interacting components. This section describes those components,
1693 explains their respective roles, and shows how they connect together to
1694 form the LTTng ecosystem.
1696 The following diagram shows how the most important components of LTTng
1697 interact with user applications, the Linux kernel, and you:
1700 .Control and trace data paths between LTTng components.
1701 image::plumbing.png[]
1703 The LTTng project incorporates:
1705 * **LTTng-tools**: Libraries and command-line interface to
1706 control tracing sessions.
1707 ** <<lttng-sessiond,Session daemon>> (man:lttng-sessiond(8)).
1708 ** <<lttng-consumerd,Consumer daemon>> (man:lttng-consumerd(8)).
1709 ** <<lttng-relayd,Relay daemon>> (man:lttng-relayd(8)).
1710 ** <<liblttng-ctl-lttng,Tracing control library>> (`liblttng-ctl`).
1711 ** <<lttng-cli,Tracing control command-line tool>> (man:lttng(1)).
1712 * **LTTng-UST**: Libraries and Java/Python packages to trace user
1714 ** <<lttng-ust,User space tracing library>> (`liblttng-ust`) and its
1715 headers to instrument and trace any native user application.
1716 ** <<prebuilt-ust-helpers,Preloadable user space tracing helpers>>:
1717 *** `liblttng-ust-libc-wrapper`
1718 *** `liblttng-ust-pthread-wrapper`
1719 *** `liblttng-ust-cyg-profile`
1720 *** `liblttng-ust-cyg-profile-fast`
1721 *** `liblttng-ust-dl`
1722 ** User space tracepoint provider source files generator command-line
1723 tool (man:lttng-gen-tp(1)).
1724 ** <<lttng-ust-agents,LTTng-UST Java agent>> to instrument and trace
1725 Java applications using `java.util.logging` or
1726 Apache log4j 1.2 logging.
1727 ** <<lttng-ust-agents,LTTng-UST Python agent>> to instrument
1728 Python applications using the standard `logging` package.
1729 * **LTTng-modules**: <<lttng-modules,Linux kernel modules>> to trace
1731 ** LTTng kernel tracer module.
1732 ** Tracing ring buffer kernel modules.
1733 ** Probe kernel modules.
1734 ** LTTng logger kernel module.
1738 === Tracing control command-line interface
1741 .The tracing control command-line interface.
1742 image::plumbing-lttng-cli.png[]
1744 The _man:lttng(1) command-line tool_ is the standard user interface to
1745 control LTTng <<tracing-session,tracing sessions>>. The cmd:lttng tool
1746 is part of LTTng-tools.
1748 The cmd:lttng tool is linked with
1749 <<liblttng-ctl-lttng,`liblttng-ctl`>> to communicate with
1750 one or more <<lttng-sessiond,session daemons>> behind the scenes.
1752 The cmd:lttng tool has a Git-like interface:
1756 $ lttng <GENERAL OPTIONS> <COMMAND> <COMMAND OPTIONS>
1759 The <<controlling-tracing,Tracing control>> section explores the
1760 available features of LTTng using the cmd:lttng tool.
1763 [[liblttng-ctl-lttng]]
1764 === Tracing control library
1767 .The tracing control library.
1768 image::plumbing-liblttng-ctl.png[]
1770 The _LTTng control library_, `liblttng-ctl`, is used to communicate
1771 with a <<lttng-sessiond,session daemon>> using a C API that hides the
1772 underlying protocol's details. `liblttng-ctl` is part of LTTng-tools.
1774 The <<lttng-cli,cmd:lttng command-line tool>>
1775 is linked with `liblttng-ctl`.
1777 You can use `liblttng-ctl` in C or $$C++$$ source code by including its
1782 #include <lttng/lttng.h>
1785 Some objects are referenced by name (C string), such as tracing
1786 sessions, but most of them require to create a handle first using
1787 `lttng_create_handle()`.
1789 The best available developer documentation for `liblttng-ctl` is, as of
1790 LTTng{nbsp}{revision}, its installed header files. Every function and
1791 structure is thoroughly documented.
1795 === User space tracing library
1798 .The user space tracing library.
1799 image::plumbing-liblttng-ust.png[]
1801 The _user space tracing library_, `liblttng-ust` (see man:lttng-ust(3)),
1802 is the LTTng user space tracer. It receives commands from a
1803 <<lttng-sessiond,session daemon>>, for example to
1804 enable and disable specific instrumentation points, and writes event
1805 records to ring buffers shared with a
1806 <<lttng-consumerd,consumer daemon>>.
1807 `liblttng-ust` is part of LTTng-UST.
1809 Public C header files are installed beside `liblttng-ust` to
1810 instrument any <<c-application,C or $$C++$$ application>>.
1812 <<lttng-ust-agents,LTTng-UST agents>>, which are regular Java and Python
1813 packages, use their own library providing tracepoints which is
1814 linked with `liblttng-ust`.
1816 An application or library does not have to initialize `liblttng-ust`
1817 manually: its constructor does the necessary tasks to properly register
1818 to a session daemon. The initialization phase also enables the
1819 instrumentation points matching the <<event,event rules>> that you
1823 [[lttng-ust-agents]]
1824 === User space tracing agents
1827 .The user space tracing agents.
1828 image::plumbing-lttng-ust-agents.png[]
1830 The _LTTng-UST Java and Python agents_ are regular Java and Python
1831 packages which add LTTng tracing capabilities to the
1832 native logging frameworks. The LTTng-UST agents are part of LTTng-UST.
1834 In the case of Java, the
1835 https://docs.oracle.com/javase/7/docs/api/java/util/logging/package-summary.html[`java.util.logging`
1836 core logging facilities] and
1837 https://logging.apache.org/log4j/1.2/[Apache log4j 1.2] are supported.
1838 Note that Apache Log4{nbsp}2 is not supported.
1840 In the case of Python, the standard
1841 https://docs.python.org/3/library/logging.html[`logging`] package
1842 is supported. Both Python 2 and Python 3 modules can import the
1843 LTTng-UST Python agent package.
1845 The applications using the LTTng-UST agents are in the
1846 `java.util.logging` (JUL),
1847 log4j, and Python <<domain,tracing domains>>.
1849 Both agents use the same mechanism to trace the log statements. When an
1850 agent is initialized, it creates a log handler that attaches to the root
1851 logger. The agent also registers to a <<lttng-sessiond,session daemon>>.
1852 When the application executes a log statement, it is passed to the
1853 agent's log handler by the root logger. The agent's log handler calls a
1854 native function in a tracepoint provider package shared library linked
1855 with <<lttng-ust,`liblttng-ust`>>, passing the formatted log message and
1856 other fields, like its logger name and its log level. This native
1857 function contains a user space instrumentation point, hence tracing the
1860 The log level condition of an
1861 <<event,event rule>> is considered when tracing
1862 a Java or a Python application, and it's compatible with the standard
1863 JUL, log4j, and Python log levels.
1867 === LTTng kernel modules
1870 .The LTTng kernel modules.
1871 image::plumbing-lttng-modules.png[]
1873 The _LTTng kernel modules_ are a set of Linux kernel modules
1874 which implement the kernel tracer of the LTTng project. The LTTng
1875 kernel modules are part of LTTng-modules.
1877 The LTTng kernel modules include:
1879 * A set of _probe_ modules.
1881 Each module attaches to a specific subsystem
1882 of the Linux kernel using its tracepoint instrument points. There are
1883 also modules to attach to the entry and return points of the Linux
1884 system call functions.
1886 * _Ring buffer_ modules.
1888 A ring buffer implementation is provided as kernel modules. The LTTng
1889 kernel tracer writes to the ring buffer; a
1890 <<lttng-consumerd,consumer daemon>> reads from the ring buffer.
1892 * The _LTTng kernel tracer_ module.
1893 * The _LTTng logger_ module.
1895 The LTTng logger module implements the special path:{/proc/lttng-logger}
1896 file so that any executable can generate LTTng events by opening and
1897 writing to this file.
1899 See <<proc-lttng-logger-abi,LTTng logger>>.
1901 Generally, you do not have to load the LTTng kernel modules manually
1902 (using man:modprobe(8), for example): a root <<lttng-sessiond,session
1903 daemon>> loads the necessary modules when starting. If you have extra
1904 probe modules, you can specify to load them to the session daemon on
1907 The LTTng kernel modules are installed in
1908 +/usr/lib/modules/__release__/extra+ by default, where +__release__+ is
1909 the kernel release (see `uname --kernel-release`).
1916 .The session daemon.
1917 image::plumbing-sessiond.png[]
1919 The _session daemon_, man:lttng-sessiond(8), is a daemon responsible for
1920 managing tracing sessions and for controlling the various components of
1921 LTTng. The session daemon is part of LTTng-tools.
1923 The session daemon sends control requests to and receives control
1926 * The <<lttng-ust,user space tracing library>>.
1928 Any instance of the user space tracing library first registers to
1929 a session daemon. Then, the session daemon can send requests to
1930 this instance, such as:
1933 ** Get the list of tracepoints.
1934 ** Share an <<event,event rule>> so that the user space tracing library
1935 can enable or disable tracepoints. Amongst the possible conditions
1936 of an event rule is a filter expression which `liblttng-ust` evalutes
1937 when an event occurs.
1938 ** Share <<channel,channel>> attributes and ring buffer locations.
1941 The session daemon and the user space tracing library use a Unix
1942 domain socket for their communication.
1944 * The <<lttng-ust-agents,user space tracing agents>>.
1946 Any instance of a user space tracing agent first registers to
1947 a session daemon. Then, the session daemon can send requests to
1948 this instance, such as:
1951 ** Get the list of loggers.
1952 ** Enable or disable a specific logger.
1955 The session daemon and the user space tracing agent use a TCP connection
1956 for their communication.
1958 * The <<lttng-modules,LTTng kernel tracer>>.
1959 * The <<lttng-consumerd,consumer daemon>>.
1961 The session daemon sends requests to the consumer daemon to instruct
1962 it where to send the trace data streams, amongst other information.
1964 * The <<lttng-relayd,relay daemon>>.
1966 The session daemon receives commands from the
1967 <<liblttng-ctl-lttng,tracing control library>>.
1969 The root session daemon loads the appropriate
1970 <<lttng-modules,LTTng kernel modules>> on startup. It also spawns
1971 a <<lttng-consumerd,consumer daemon>> as soon as you create
1972 an <<event,event rule>>.
1974 The session daemon does not send and receive trace data: this is the
1975 role of the <<lttng-consumerd,consumer daemon>> and
1976 <<lttng-relayd,relay daemon>>. It does, however, generate the
1977 http://diamon.org/ctf/[CTF] metadata stream.
1979 Each Unix user can have its own session daemon instance. The
1980 tracing sessions managed by different session daemons are completely
1983 The root user's session daemon is the only one which is
1984 allowed to control the LTTng kernel tracer, and its spawned consumer
1985 daemon is the only one which is allowed to consume trace data from the
1986 LTTng kernel tracer. Note, however, that any Unix user which is a member
1987 of the <<tracing-group,tracing group>> is allowed
1988 to create <<channel,channels>> in the
1989 Linux kernel <<domain,tracing domain>>, and thus to trace the Linux
1992 The <<lttng-cli,cmd:lttng command-line tool>> automatically starts a
1993 session daemon when using its `create` command if none is currently
1994 running. You can also start the session daemon manually.
2001 .The consumer daemon.
2002 image::plumbing-consumerd.png[]
2004 The _consumer daemon_, man:lttng-consumerd(8), is a daemon which shares
2005 ring buffers with user applications or with the LTTng kernel modules to
2006 collect trace data and send it to some location (on disk or to a
2007 <<lttng-relayd,relay daemon>> over the network). The consumer daemon
2008 is part of LTTng-tools.
2010 You do not start a consumer daemon manually: a consumer daemon is always
2011 spawned by a <<lttng-sessiond,session daemon>> as soon as you create an
2012 <<event,event rule>>, that is, before you start tracing. When you kill
2013 its owner session daemon, the consumer daemon also exits because it is
2014 the session daemon's child process. Command-line options of
2015 man:lttng-sessiond(8) target the consumer daemon process.
2017 There are up to two running consumer daemons per Unix user, whereas only
2018 one session daemon can run per user. This is because each process can be
2019 either 32-bit or 64-bit: if the target system runs a mixture of 32-bit
2020 and 64-bit processes, it is more efficient to have separate
2021 corresponding 32-bit and 64-bit consumer daemons. The root user is an
2022 exception: it can have up to _three_ running consumer daemons: 32-bit
2023 and 64-bit instances for its user applications, and one more
2024 reserved for collecting kernel trace data.
2032 image::plumbing-relayd.png[]
2034 The _relay daemon_, man:lttng-relayd(8), is a daemon acting as a bridge
2035 between remote session and consumer daemons, local trace files, and a
2036 remote live trace viewer. The relay daemon is part of LTTng-tools.
2038 The main purpose of the relay daemon is to implement a receiver of
2039 <<sending-trace-data-over-the-network,trace data over the network>>.
2040 This is useful when the target system does not have much file system
2041 space to record trace files locally.
2043 The relay daemon is also a server to which a
2044 <<lttng-live,live trace viewer>> can
2045 connect. The live trace viewer sends requests to the relay daemon to
2046 receive trace data as the target system emits events. The
2047 communication protocol is named _LTTng live_; it is used over TCP
2050 Note that you can start the relay daemon on the target system directly.
2051 This is the setup of choice when the use case is to view events as
2052 the target system emits them without the need of a remote system.
2056 == [[using-lttng]]Instrumentation
2058 There are many examples of tracing and monitoring in our everyday life:
2060 * You have access to real-time and historical weather reports and
2061 forecasts thanks to weather stations installed around the country.
2062 * You know your heart is safe thanks to an electrocardiogram.
2063 * You make sure not to drive your car too fast and to have enough fuel
2064 to reach your destination thanks to gauges visible on your dashboard.
2066 All the previous examples have something in common: they rely on
2067 **instruments**. Without the electrodes attached to the surface of your
2068 body's skin, cardiac monitoring is futile.
2070 LTTng, as a tracer, is no different from those real life examples. If
2071 you're about to trace a software system or, in other words, record its
2072 history of execution, you better have **instrumentation points** in the
2073 subject you're tracing, that is, the actual software.
2075 Various ways were developed to instrument a piece of software for LTTng
2076 tracing. The most straightforward one is to manually place
2077 instrumentation points, called _tracepoints_, in the software's source
2078 code. It is also possible to add instrumentation points dynamically in
2079 the Linux kernel <<domain,tracing domain>>.
2081 If you're only interested in tracing the Linux kernel, your
2082 instrumentation needs are probably already covered by LTTng's built-in
2083 <<lttng-modules,Linux kernel tracepoints>>. You may also wish to trace a
2084 user application which is already instrumented for LTTng tracing.
2085 In such cases, you can skip this whole section and read the topics of
2086 the <<controlling-tracing,Tracing control>> section.
2088 Many methods are available to instrument a piece of software for LTTng
2091 * <<c-application,User space instrumentation for C and $$C++$$
2093 * <<prebuilt-ust-helpers,Prebuilt user space tracing helpers>>.
2094 * <<java-application,User space Java agent>>.
2095 * <<python-application,User space Python agent>>.
2096 * <<proc-lttng-logger-abi,LTTng logger>>.
2097 * <<instrumenting-linux-kernel,LTTng kernel tracepoints>>.
2101 === [[cxx-application]]User space instrumentation for C and $$C++$$ applications
2103 The procedure to instrument a C or $$C++$$ user application with
2104 the <<lttng-ust,LTTng user space tracing library>>, `liblttng-ust`, is:
2106 . <<tracepoint-provider,Create the source files of a tracepoint provider
2108 . <<probing-the-application-source-code,Add tracepoints to
2109 the application's source code>>.
2110 . <<building-tracepoint-providers-and-user-application,Build and link
2111 a tracepoint provider package and the user application>>.
2113 If you need quick, man:printf(3)-like instrumentation, you can skip
2114 those steps and use <<tracef,`tracef()`>> or <<tracelog,`tracelog()`>>
2117 IMPORTANT: You need to <<installing-lttng,install>> LTTng-UST to
2118 instrument a user application with `liblttng-ust`.
2121 [[tracepoint-provider]]
2122 ==== Create the source files of a tracepoint provider package
2124 A _tracepoint provider_ is a set of compiled functions which provide
2125 **tracepoints** to an application, the type of instrumentation point
2126 supported by LTTng-UST. Those functions can emit events with
2127 user-defined fields and serialize those events as event records to one
2128 or more LTTng-UST <<channel,channel>> sub-buffers. The `tracepoint()`
2129 macro, which you <<probing-the-application-source-code,insert in a user
2130 application's source code>>, calls those functions.
2132 A _tracepoint provider package_ is an object file (`.o`) or a shared
2133 library (`.so`) which contains one or more tracepoint providers.
2134 Its source files are:
2136 * One or more <<tpp-header,tracepoint provider header>> (`.h`).
2137 * A <<tpp-source,tracepoint provider package source>> (`.c`).
2139 A tracepoint provider package is dynamically linked with `liblttng-ust`,
2140 the LTTng user space tracer, at run time.
2143 .User application linked with `liblttng-ust` and containing a tracepoint provider.
2144 image::ust-app.png[]
2146 NOTE: If you need quick, man:printf(3)-like instrumentation, you can
2147 skip creating and using a tracepoint provider and use
2148 <<tracef,`tracef()`>> or <<tracelog,`tracelog()`>> instead.
2152 ===== Create a tracepoint provider header file template
2154 A _tracepoint provider header file_ contains the tracepoint
2155 definitions of a tracepoint provider.
2157 To create a tracepoint provider header file:
2159 . Start from this template:
2163 .Tracepoint provider header file template (`.h` file extension).
2165 #undef TRACEPOINT_PROVIDER
2166 #define TRACEPOINT_PROVIDER provider_name
2168 #undef TRACEPOINT_INCLUDE
2169 #define TRACEPOINT_INCLUDE "./tp.h"
2171 #if !defined(_TP_H) || defined(TRACEPOINT_HEADER_MULTI_READ)
2174 #include <lttng/tracepoint.h>
2177 * Use TRACEPOINT_EVENT(), TRACEPOINT_EVENT_CLASS(),
2178 * TRACEPOINT_EVENT_INSTANCE(), and TRACEPOINT_LOGLEVEL() here.
2183 #include <lttng/tracepoint-event.h>
2189 * `provider_name` with the name of your tracepoint provider.
2190 * `"tp.h"` with the name of your tracepoint provider header file.
2192 . Below the `#include <lttng/tracepoint.h>` line, put your
2193 <<defining-tracepoints,tracepoint definitions>>.
2195 Your tracepoint provider name must be unique amongst all the possible
2196 tracepoint provider names used on the same target system. We
2197 suggest to include the name of your project or company in the name,
2198 for example, `org_lttng_my_project_tpp`.
2200 TIP: [[lttng-gen-tp]]You can use the man:lttng-gen-tp(1) tool to create
2201 this boilerplate for you. When using cmd:lttng-gen-tp, all you need to
2202 write are the <<defining-tracepoints,tracepoint definitions>>.
2205 [[defining-tracepoints]]
2206 ===== Create a tracepoint definition
2208 A _tracepoint definition_ defines, for a given tracepoint:
2210 * Its **input arguments**. They are the macro parameters that the
2211 `tracepoint()` macro accepts for this particular tracepoint
2212 in the user application's source code.
2213 * Its **output event fields**. They are the sources of event fields
2214 that form the payload of any event that the execution of the
2215 `tracepoint()` macro emits for this particular tracepoint.
2217 You can create a tracepoint definition by using the
2218 `TRACEPOINT_EVENT()` macro below the `#include <lttng/tracepoint.h>`
2220 <<tpp-header,tracepoint provider header file template>>.
2222 The syntax of the `TRACEPOINT_EVENT()` macro is:
2225 .`TRACEPOINT_EVENT()` macro syntax.
2228 /* Tracepoint provider name */
2231 /* Tracepoint name */
2234 /* Input arguments */
2239 /* Output event fields */
2248 * `provider_name` with your tracepoint provider name.
2249 * `tracepoint_name` with your tracepoint name.
2250 * `arguments` with the <<tpp-def-input-args,input arguments>>.
2251 * `fields` with the <<tpp-def-output-fields,output event field>>
2254 This tracepoint emits events named `provider_name:tracepoint_name`.
2257 .Event name's length limitation
2259 The concatenation of the tracepoint provider name and the
2260 tracepoint name must not exceed **254 characters**. If it does, the
2261 instrumented application compiles and runs, but LTTng throws multiple
2262 warnings and you could experience serious issues.
2265 [[tpp-def-input-args]]The syntax of the `TP_ARGS()` macro is:
2268 .`TP_ARGS()` macro syntax.
2277 * `type` with the C type of the argument.
2278 * `arg_name` with the argument name.
2280 You can repeat `type` and `arg_name` up to 10 times to have
2281 more than one argument.
2283 .`TP_ARGS()` usage with three arguments.
2295 The `TP_ARGS()` and `TP_ARGS(void)` forms are valid to create a
2296 tracepoint definition with no input arguments.
2298 [[tpp-def-output-fields]]The `TP_FIELDS()` macro contains a list of
2299 `ctf_*()` macros. Each `ctf_*()` macro defines one event field. See
2300 man:lttng-ust(3) for a complete description of the available `ctf_*()`
2301 macros. A `ctf_*()` macro specifies the type, size, and byte order of
2304 Each `ctf_*()` macro takes an _argument expression_ parameter. This is a
2305 C expression that the tracer evalutes at the `tracepoint()` macro site
2306 in the application's source code. This expression provides a field's
2307 source of data. The argument expression can include input argument names
2308 listed in the `TP_ARGS()` macro.
2310 Each `ctf_*()` macro also takes a _field name_ parameter. Field names
2311 must be unique within a given tracepoint definition.
2313 Here's a complete tracepoint definition example:
2315 .Tracepoint definition.
2317 The following tracepoint definition defines a tracepoint which takes
2318 three input arguments and has four output event fields.
2322 #include "my-custom-structure.h"
2328 const struct my_custom_structure*, my_custom_structure,
2333 ctf_string(query_field, query)
2334 ctf_float(double, ratio_field, ratio)
2335 ctf_integer(int, recv_size, my_custom_structure->recv_size)
2336 ctf_integer(int, send_size, my_custom_structure->send_size)
2341 You can refer to this tracepoint definition with the `tracepoint()`
2342 macro in your application's source code like this:
2346 tracepoint(my_provider, my_tracepoint,
2347 my_structure, some_ratio, the_query);
2351 NOTE: The LTTng tracer only evaluates tracepoint arguments at run time
2352 if they satisfy an enabled <<event,event rule>>.
2355 [[using-tracepoint-classes]]
2356 ===== Use a tracepoint class
2358 A _tracepoint class_ is a class of tracepoints which share the same
2359 output event field definitions. A _tracepoint instance_ is one
2360 instance of such a defined tracepoint class, with its own tracepoint
2363 The <<defining-tracepoints,`TRACEPOINT_EVENT()` macro>> is actually a
2364 shorthand which defines both a tracepoint class and a tracepoint
2365 instance at the same time.
2367 When you build a tracepoint provider package, the C or $$C++$$ compiler
2368 creates one serialization function for each **tracepoint class**. A
2369 serialization function is responsible for serializing the event fields
2370 of a tracepoint to a sub-buffer when tracing.
2372 For various performance reasons, when your situation requires multiple
2373 tracepoint definitions with different names, but with the same event
2374 fields, we recommend that you manually create a tracepoint class
2375 and instantiate as many tracepoint instances as needed. One positive
2376 effect of such a design, amongst other advantages, is that all
2377 tracepoint instances of the same tracepoint class reuse the same
2378 serialization function, thus reducing
2379 https://en.wikipedia.org/wiki/Cache_pollution[cache pollution].
2381 .Use a tracepoint class and tracepoint instances.
2383 Consider the following three tracepoint definitions:
2395 ctf_integer(int, userid, userid)
2396 ctf_integer(size_t, len, len)
2408 ctf_integer(int, userid, userid)
2409 ctf_integer(size_t, len, len)
2421 ctf_integer(int, userid, userid)
2422 ctf_integer(size_t, len, len)
2427 In this case, we create three tracepoint classes, with one implicit
2428 tracepoint instance for each of them: `get_account`, `get_settings`, and
2429 `get_transaction`. However, they all share the same event field names
2430 and types. Hence three identical, yet independent serialization
2431 functions are created when you build the tracepoint provider package.
2433 A better design choice is to define a single tracepoint class and three
2434 tracepoint instances:
2438 /* The tracepoint class */
2439 TRACEPOINT_EVENT_CLASS(
2440 /* Tracepoint provider name */
2443 /* Tracepoint class name */
2446 /* Input arguments */
2452 /* Output event fields */
2454 ctf_integer(int, userid, userid)
2455 ctf_integer(size_t, len, len)
2459 /* The tracepoint instances */
2460 TRACEPOINT_EVENT_INSTANCE(
2461 /* Tracepoint provider name */
2464 /* Tracepoint class name */
2467 /* Tracepoint name */
2470 /* Input arguments */
2476 TRACEPOINT_EVENT_INSTANCE(
2485 TRACEPOINT_EVENT_INSTANCE(
2498 [[assigning-log-levels]]
2499 ===== Assign a log level to a tracepoint definition
2501 You can assign an optional _log level_ to a
2502 <<defining-tracepoints,tracepoint definition>>.
2504 Assigning different levels of severity to tracepoint definitions can
2505 be useful: when you <<enabling-disabling-events,create an event rule>>,
2506 you can target tracepoints having a log level as severe as a specific
2509 The concept of LTTng-UST log levels is similar to the levels found
2510 in typical logging frameworks:
2512 * In a logging framework, the log level is given by the function
2513 or method name you use at the log statement site: `debug()`,
2514 `info()`, `warn()`, `error()`, and so on.
2515 * In LTTng-UST, you statically assign the log level to a tracepoint
2516 definition; any `tracepoint()` macro invocation which refers to
2517 this definition has this log level.
2519 You can assign a log level to a tracepoint definition with the
2520 `TRACEPOINT_LOGLEVEL()` macro. You must use this macro _after_ the
2521 <<defining-tracepoints,`TRACEPOINT_EVENT()`>> or
2522 <<using-tracepoint-classes,`TRACEPOINT_INSTANCE()`>> macro for a given
2525 The syntax of the `TRACEPOINT_LOGLEVEL()` macro is:
2528 .`TRACEPOINT_LOGLEVEL()` macro syntax.
2530 TRACEPOINT_LOGLEVEL(provider_name, tracepoint_name, log_level)
2535 * `provider_name` with the tracepoint provider name.
2536 * `tracepoint_name` with the tracepoint name.
2537 * `log_level` with the log level to assign to the tracepoint
2538 definition named `tracepoint_name` in the `provider_name`
2539 tracepoint provider.
2541 See man:lttng-ust(3) for a list of available log level names.
2543 .Assign the `TRACE_DEBUG_UNIT` log level to a tracepoint definition.
2547 /* Tracepoint definition */
2556 ctf_integer(int, userid, userid)
2557 ctf_integer(size_t, len, len)
2561 /* Log level assignment */
2562 TRACEPOINT_LOGLEVEL(my_app, get_transaction, TRACE_DEBUG_UNIT)
2568 ===== Create a tracepoint provider package source file
2570 A _tracepoint provider package source file_ is a C source file which
2571 includes a <<tpp-header,tracepoint provider header file>> to expand its
2572 macros into event serialization and other functions.
2574 You can always use the following tracepoint provider package source
2578 .Tracepoint provider package source file template.
2580 #define TRACEPOINT_CREATE_PROBES
2585 Replace `tp.h` with the name of your <<tpp-header,tracepoint provider
2586 header file>> name. You may also include more than one tracepoint
2587 provider header file here to create a tracepoint provider package
2588 holding more than one tracepoint providers.
2591 [[probing-the-application-source-code]]
2592 ==== Add tracepoints to an application's source code
2594 Once you <<tpp-header,create a tracepoint provider header file>>, you
2595 can use the `tracepoint()` macro in your application's
2596 source code to insert the tracepoints that this header
2597 <<defining-tracepoints,defines>>.
2599 The `tracepoint()` macro takes at least two parameters: the tracepoint
2600 provider name and the tracepoint name. The corresponding tracepoint
2601 definition defines the other parameters.
2603 .`tracepoint()` usage.
2605 The following <<defining-tracepoints,tracepoint definition>> defines a
2606 tracepoint which takes two input arguments and has two output event
2610 .Tracepoint provider header file.
2612 #include "my-custom-structure.h"
2619 const char*, cmd_name
2622 ctf_string(cmd_name, cmd_name)
2623 ctf_integer(int, number_of_args, argc)
2628 You can refer to this tracepoint definition with the `tracepoint()`
2629 macro in your application's source code like this:
2632 .Application's source file.
2636 int main(int argc, char* argv[])
2638 tracepoint(my_provider, my_tracepoint, argc, argv[0]);
2644 Note how the application's source code includes
2645 the tracepoint provider header file containing the tracepoint
2646 definitions to use, path:{tp.h}.
2649 .`tracepoint()` usage with a complex tracepoint definition.
2651 Consider this complex tracepoint definition, where multiple event
2652 fields refer to the same input arguments in their argument expression
2656 .Tracepoint provider header file.
2658 /* For `struct stat` */
2659 #include <sys/types.h>
2660 #include <sys/stat.h>
2672 ctf_integer(int, my_constant_field, 23 + 17)
2673 ctf_integer(int, my_int_arg_field, my_int_arg)
2674 ctf_integer(int, my_int_arg_field2, my_int_arg * my_int_arg)
2675 ctf_integer(int, sum4_field, my_str_arg[0] + my_str_arg[1] +
2676 my_str_arg[2] + my_str_arg[3])
2677 ctf_string(my_str_arg_field, my_str_arg)
2678 ctf_integer_hex(off_t, size_field, st->st_size)
2679 ctf_float(double, size_dbl_field, (double) st->st_size)
2680 ctf_sequence_text(char, half_my_str_arg_field, my_str_arg,
2681 size_t, strlen(my_str_arg) / 2)
2686 You can refer to this tracepoint definition with the `tracepoint()`
2687 macro in your application's source code like this:
2690 .Application's source file.
2692 #define TRACEPOINT_DEFINE
2699 stat("/etc/fstab", &s);
2700 tracepoint(my_provider, my_tracepoint, 23, "Hello, World!", &s);
2706 If you look at the event record that LTTng writes when tracing this
2707 program, assuming the file size of path:{/etc/fstab} is 301{nbsp}bytes,
2708 it should look like this:
2710 .Event record fields
2712 |Field's name |Field's value
2713 |`my_constant_field` |40
2714 |`my_int_arg_field` |23
2715 |`my_int_arg_field2` |529
2717 |`my_str_arg_field` |`Hello, World!`
2718 |`size_field` |0x12d
2719 |`size_dbl_field` |301.0
2720 |`half_my_str_arg_field` |`Hello,`
2724 Sometimes, the arguments you pass to `tracepoint()` are expensive to
2725 compute--they use the call stack, for example. To avoid this
2726 computation when the tracepoint is disabled, you can use the
2727 `tracepoint_enabled()` and `do_tracepoint()` macros.
2729 The syntax of the `tracepoint_enabled()` and `do_tracepoint()` macros
2733 .`tracepoint_enabled()` and `do_tracepoint()` macros syntax.
2735 tracepoint_enabled(provider_name, tracepoint_name)
2736 do_tracepoint(provider_name, tracepoint_name, ...)
2741 * `provider_name` with the tracepoint provider name.
2742 * `tracepoint_name` with the tracepoint name.
2744 `tracepoint_enabled()` returns a non-zero value if the tracepoint named
2745 `tracepoint_name` from the provider named `provider_name` is enabled
2748 `do_tracepoint()` is like `tracepoint()`, except that it doesn't check
2749 if the tracepoint is enabled. Using `tracepoint()` with
2750 `tracepoint_enabled()` is dangerous since `tracepoint()` also contains
2751 the `tracepoint_enabled()` check, thus a race condition is
2752 possible in this situation:
2755 .Possible race condition when using `tracepoint_enabled()` with `tracepoint()`.
2757 if (tracepoint_enabled(my_provider, my_tracepoint)) {
2758 stuff = prepare_stuff();
2761 tracepoint(my_provider, my_tracepoint, stuff);
2764 If the tracepoint is enabled after the condition, then `stuff` is not
2765 prepared: the emitted event will either contain wrong data, or the whole
2766 application could crash (segmentation fault, for example).
2768 NOTE: Neither `tracepoint_enabled()` nor `do_tracepoint()` have an
2769 `STAP_PROBEV()` call. If you need it, you must emit
2773 [[building-tracepoint-providers-and-user-application]]
2774 ==== Build and link a tracepoint provider package and an application
2776 Once you have one or more <<tpp-header,tracepoint provider header
2777 files>> and a <<tpp-source,tracepoint provider package source file>>,
2778 you can create the tracepoint provider package by compiling its source
2779 file. From here, multiple build and run scenarios are possible. The
2780 following table shows common application and library configurations
2781 along with the required command lines to achieve them.
2783 In the following diagrams, we use the following file names:
2786 Executable application.
2789 Application's object file.
2792 Tracepoint provider package object file.
2795 Tracepoint provider package archive file.
2798 Tracepoint provider package shared object file.
2801 User library object file.
2804 User library shared object file.
2806 We use the following symbols in the diagrams of table below:
2809 .Symbols used in the build scenario diagrams.
2810 image::ust-sit-symbols.png[]
2812 We assume that path:{.} is part of the env:LD_LIBRARY_PATH environment
2813 variable in the following instructions.
2815 [role="growable ust-scenarios",cols="asciidoc,asciidoc"]
2816 .Common tracepoint provider package scenarios.
2818 |Scenario |Instructions
2821 The instrumented application is statically linked with
2822 the tracepoint provider package object.
2824 image::ust-sit+app-linked-with-tp-o+app-instrumented.png[]
2827 include::../common/ust-sit-step-tp-o.txt[]
2829 To build the instrumented application:
2831 . In path:{app.c}, before including path:{tpp.h}, add the following line:
2836 #define TRACEPOINT_DEFINE
2840 . Compile the application source file:
2849 . Build the application:
2854 $ gcc -o app app.o tpp.o -llttng-ust -ldl
2858 To run the instrumented application:
2860 * Start the application:
2870 The instrumented application is statically linked with the
2871 tracepoint provider package archive file.
2873 image::ust-sit+app-linked-with-tp-a+app-instrumented.png[]
2876 To create the tracepoint provider package archive file:
2878 . Compile the <<tpp-source,tracepoint provider package source file>>:
2887 . Create the tracepoint provider package archive file:
2892 $ ar rcs tpp.a tpp.o
2896 To build the instrumented application:
2898 . In path:{app.c}, before including path:{tpp.h}, add the following line:
2903 #define TRACEPOINT_DEFINE
2907 . Compile the application source file:
2916 . Build the application:
2921 $ gcc -o app app.o tpp.a -llttng-ust -ldl
2925 To run the instrumented application:
2927 * Start the application:
2937 The instrumented application is linked with the tracepoint provider
2938 package shared object.
2940 image::ust-sit+app-linked-with-tp-so+app-instrumented.png[]
2943 include::../common/ust-sit-step-tp-so.txt[]
2945 To build the instrumented application:
2947 . In path:{app.c}, before including path:{tpp.h}, add the following line:
2952 #define TRACEPOINT_DEFINE
2956 . Compile the application source file:
2965 . Build the application:
2970 $ gcc -o app app.o -ldl -L. -ltpp
2974 To run the instrumented application:
2976 * Start the application:
2986 The tracepoint provider package shared object is preloaded before the
2987 instrumented application starts.
2989 image::ust-sit+tp-so-preloaded+app-instrumented.png[]
2992 include::../common/ust-sit-step-tp-so.txt[]
2994 To build the instrumented application:
2996 . In path:{app.c}, before including path:{tpp.h}, add the
3002 #define TRACEPOINT_DEFINE
3003 #define TRACEPOINT_PROBE_DYNAMIC_LINKAGE
3007 . Compile the application source file:
3016 . Build the application:
3021 $ gcc -o app app.o -ldl
3025 To run the instrumented application with tracing support:
3027 * Preload the tracepoint provider package shared object and
3028 start the application:
3033 $ LD_PRELOAD=./libtpp.so ./app
3037 To run the instrumented application without tracing support:
3039 * Start the application:
3049 The instrumented application dynamically loads the tracepoint provider
3050 package shared object.
3052 See the <<dlclose-warning,warning about `dlclose()`>>.
3054 image::ust-sit+app-dlopens-tp-so+app-instrumented.png[]
3057 include::../common/ust-sit-step-tp-so.txt[]
3059 To build the instrumented application:
3061 . In path:{app.c}, before including path:{tpp.h}, add the
3067 #define TRACEPOINT_DEFINE
3068 #define TRACEPOINT_PROBE_DYNAMIC_LINKAGE
3072 . Compile the application source file:
3081 . Build the application:
3086 $ gcc -o app app.o -ldl
3090 To run the instrumented application:
3092 * Start the application:
3102 The application is linked with the instrumented user library.
3104 The instrumented user library is statically linked with the tracepoint
3105 provider package object file.
3107 image::ust-sit+app-linked-with-lib+lib-linked-with-tp-o+lib-instrumented.png[]
3110 include::../common/ust-sit-step-tp-o-fpic.txt[]
3112 To build the instrumented user library:
3114 . In path:{emon.c}, before including path:{tpp.h}, add the
3120 #define TRACEPOINT_DEFINE
3124 . Compile the user library source file:
3129 $ gcc -I. -fpic -c emon.c
3133 . Build the user library shared object:
3138 $ gcc -shared -o libemon.so emon.o tpp.o -llttng-ust -ldl
3142 To build the application:
3144 . Compile the application source file:
3153 . Build the application:
3158 $ gcc -o app app.o -L. -lemon
3162 To run the application:
3164 * Start the application:
3174 The application is linked with the instrumented user library.
3176 The instrumented user library is linked with the tracepoint provider
3177 package shared object.
3179 image::ust-sit+app-linked-with-lib+lib-linked-with-tp-so+lib-instrumented.png[]
3182 include::../common/ust-sit-step-tp-so.txt[]
3184 To build the instrumented user library:
3186 . In path:{emon.c}, before including path:{tpp.h}, add the
3192 #define TRACEPOINT_DEFINE
3196 . Compile the user library source file:
3201 $ gcc -I. -fpic -c emon.c
3205 . Build the user library shared object:
3210 $ gcc -shared -o libemon.so emon.o -ldl -L. -ltpp
3214 To build the application:
3216 . Compile the application source file:
3225 . Build the application:
3230 $ gcc -o app app.o -L. -lemon
3234 To run the application:
3236 * Start the application:
3246 The tracepoint provider package shared object is preloaded before the
3249 The application is linked with the instrumented user library.
3251 image::ust-sit+tp-so-preloaded+app-linked-with-lib+lib-instrumented.png[]
3254 include::../common/ust-sit-step-tp-so.txt[]
3256 To build the instrumented user library:
3258 . In path:{emon.c}, before including path:{tpp.h}, add the
3264 #define TRACEPOINT_DEFINE
3265 #define TRACEPOINT_PROBE_DYNAMIC_LINKAGE
3269 . Compile the user library source file:
3274 $ gcc -I. -fpic -c emon.c
3278 . Build the user library shared object:
3283 $ gcc -shared -o libemon.so emon.o -ldl
3287 To build the application:
3289 . Compile the application source file:
3298 . Build the application:
3303 $ gcc -o app app.o -L. -lemon
3307 To run the application with tracing support:
3309 * Preload the tracepoint provider package shared object and
3310 start the application:
3315 $ LD_PRELOAD=./libtpp.so ./app
3319 To run the application without tracing support:
3321 * Start the application:
3331 The application is linked with the instrumented user library.
3333 The instrumented user library dynamically loads the tracepoint provider
3334 package shared object.
3336 See the <<dlclose-warning,warning about `dlclose()`>>.
3338 image::ust-sit+app-linked-with-lib+lib-dlopens-tp-so+lib-instrumented.png[]
3341 include::../common/ust-sit-step-tp-so.txt[]
3343 To build the instrumented user library:
3345 . In path:{emon.c}, before including path:{tpp.h}, add the
3351 #define TRACEPOINT_DEFINE
3352 #define TRACEPOINT_PROBE_DYNAMIC_LINKAGE
3356 . Compile the user library source file:
3361 $ gcc -I. -fpic -c emon.c
3365 . Build the user library shared object:
3370 $ gcc -shared -o libemon.so emon.o -ldl
3374 To build the application:
3376 . Compile the application source file:
3385 . Build the application:
3390 $ gcc -o app app.o -L. -lemon
3394 To run the application:
3396 * Start the application:
3406 The application dynamically loads the instrumented user library.
3408 The instrumented user library is linked with the tracepoint provider
3409 package shared object.
3411 See the <<dlclose-warning,warning about `dlclose()`>>.
3413 image::ust-sit+app-dlopens-lib+lib-linked-with-tp-so+lib-instrumented.png[]
3416 include::../common/ust-sit-step-tp-so.txt[]
3418 To build the instrumented user library:
3420 . In path:{emon.c}, before including path:{tpp.h}, add the
3426 #define TRACEPOINT_DEFINE
3430 . Compile the user library source file:
3435 $ gcc -I. -fpic -c emon.c
3439 . Build the user library shared object:
3444 $ gcc -shared -o libemon.so emon.o -ldl -L. -ltpp
3448 To build the application:
3450 . Compile the application source file:
3459 . Build the application:
3464 $ gcc -o app app.o -ldl -L. -lemon
3468 To run the application:
3470 * Start the application:
3480 The application dynamically loads the instrumented user library.
3482 The instrumented user library dynamically loads the tracepoint provider
3483 package shared object.
3485 See the <<dlclose-warning,warning about `dlclose()`>>.
3487 image::ust-sit+app-dlopens-lib+lib-dlopens-tp-so+lib-instrumented.png[]
3490 include::../common/ust-sit-step-tp-so.txt[]
3492 To build the instrumented user library:
3494 . In path:{emon.c}, before including path:{tpp.h}, add the
3500 #define TRACEPOINT_DEFINE
3501 #define TRACEPOINT_PROBE_DYNAMIC_LINKAGE
3505 . Compile the user library source file:
3510 $ gcc -I. -fpic -c emon.c
3514 . Build the user library shared object:
3519 $ gcc -shared -o libemon.so emon.o -ldl
3523 To build the application:
3525 . Compile the application source file:
3534 . Build the application:
3539 $ gcc -o app app.o -ldl -L. -lemon
3543 To run the application:
3545 * Start the application:
3555 The tracepoint provider package shared object is preloaded before the
3558 The application dynamically loads the instrumented user library.
3560 image::ust-sit+tp-so-preloaded+app-dlopens-lib+lib-instrumented.png[]
3563 include::../common/ust-sit-step-tp-so.txt[]
3565 To build the instrumented user library:
3567 . In path:{emon.c}, before including path:{tpp.h}, add the
3573 #define TRACEPOINT_DEFINE
3574 #define TRACEPOINT_PROBE_DYNAMIC_LINKAGE
3578 . Compile the user library source file:
3583 $ gcc -I. -fpic -c emon.c
3587 . Build the user library shared object:
3592 $ gcc -shared -o libemon.so emon.o -ldl
3596 To build the application:
3598 . Compile the application source file:
3607 . Build the application:
3612 $ gcc -o app app.o -L. -lemon
3616 To run the application with tracing support:
3618 * Preload the tracepoint provider package shared object and
3619 start the application:
3624 $ LD_PRELOAD=./libtpp.so ./app
3628 To run the application without tracing support:
3630 * Start the application:
3640 The application is statically linked with the tracepoint provider
3641 package object file.
3643 The application is linked with the instrumented user library.
3645 image::ust-sit+app-linked-with-tp-o+app-linked-with-lib+lib-instrumented.png[]
3648 include::../common/ust-sit-step-tp-o.txt[]
3650 To build the instrumented user library:
3652 . In path:{emon.c}, before including path:{tpp.h}, add the
3658 #define TRACEPOINT_DEFINE
3662 . Compile the user library source file:
3667 $ gcc -I. -fpic -c emon.c
3671 . Build the user library shared object:
3676 $ gcc -shared -o libemon.so emon.o
3680 To build the application:
3682 . Compile the application source file:
3691 . Build the application:
3696 $ gcc -o app app.o tpp.o -llttng-ust -ldl -L. -lemon
3700 To run the instrumented application:
3702 * Start the application:
3712 The application is statically linked with the tracepoint provider
3713 package object file.
3715 The application dynamically loads the instrumented user library.
3717 image::ust-sit+app-linked-with-tp-o+app-dlopens-lib+lib-instrumented.png[]
3720 include::../common/ust-sit-step-tp-o.txt[]
3722 To build the application:
3724 . In path:{app.c}, before including path:{tpp.h}, add the following line:
3729 #define TRACEPOINT_DEFINE
3733 . Compile the application source file:
3742 . Build the application:
3747 $ gcc -Wl,--export-dynamic -o app app.o tpp.o \
3752 The `--export-dynamic` option passed to the linker is necessary for the
3753 dynamically loaded library to ``see'' the tracepoint symbols defined in
3756 To build the instrumented user library:
3758 . Compile the user library source file:
3763 $ gcc -I. -fpic -c emon.c
3767 . Build the user library shared object:
3772 $ gcc -shared -o libemon.so emon.o
3776 To run the application:
3778 * Start the application:
3790 .Do not use man:dlclose(3) on a tracepoint provider package
3792 Never use man:dlclose(3) on any shared object which:
3794 * Is linked with, statically or dynamically, a tracepoint provider
3796 * Calls man:dlopen(3) itself to dynamically open a tracepoint provider
3797 package shared object.
3799 This is currently considered **unsafe** due to a lack of reference
3800 counting from LTTng-UST to the shared object.
3802 A known workaround (available since glibc 2.2) is to use the
3803 `RTLD_NODELETE` flag when calling man:dlopen(3) initially. This has the
3804 effect of not unloading the loaded shared object, even if man:dlclose(3)
3807 You can also preload the tracepoint provider package shared object with
3808 the env:LD_PRELOAD environment variable to overcome this limitation.
3812 [[using-lttng-ust-with-daemons]]
3813 ===== Use noch:{LTTng-UST} with daemons
3815 If your instrumented application calls man:fork(2), man:clone(2),
3816 or BSD's man:rfork(2), without a following man:exec(3)-family
3817 system call, you must preload the path:{liblttng-ust-fork.so} shared
3818 object when you start the application.
3822 $ LD_PRELOAD=liblttng-ust-fork.so ./my-app
3825 If your tracepoint provider package is
3826 a shared library which you also preload, you must put both
3827 shared objects in env:LD_PRELOAD:
3831 $ LD_PRELOAD=liblttng-ust-fork.so:/path/to/tp.so ./my-app
3837 ===== Use noch:{LTTng-UST} with applications which close file descriptors that don't belong to them
3839 If your instrumented application closes one or more file descriptors
3840 which it did not open itself, you must preload the
3841 path:{liblttng-ust-fd.so} shared object when you start the application:
3845 $ LD_PRELOAD=liblttng-ust-fd.so ./my-app
3848 Typical use cases include closing all the file descriptors after
3849 man:fork(2) or man:rfork(2) and buggy applications doing
3853 [[lttng-ust-pkg-config]]
3854 ===== Use noch:{pkg-config}
3856 On some distributions, LTTng-UST ships with a
3857 https://www.freedesktop.org/wiki/Software/pkg-config/[pkg-config]
3858 metadata file. If this is your case, then you can use cmd:pkg-config to
3859 build an application on the command line:
3863 $ gcc -o my-app my-app.o tp.o $(pkg-config --cflags --libs lttng-ust)
3867 [[instrumenting-32-bit-app-on-64-bit-system]]
3868 ===== [[advanced-instrumenting-techniques]]Build a 32-bit instrumented application for a 64-bit target system
3870 In order to trace a 32-bit application running on a 64-bit system,
3871 LTTng must use a dedicated 32-bit
3872 <<lttng-consumerd,consumer daemon>>.
3874 The following steps show how to build and install a 32-bit consumer
3875 daemon, which is _not_ part of the default 64-bit LTTng build, how to
3876 build and install the 32-bit LTTng-UST libraries, and how to build and
3877 link an instrumented 32-bit application in that context.
3879 To build a 32-bit instrumented application for a 64-bit target system,
3880 assuming you have a fresh target system with no installed Userspace RCU
3883 . Download, build, and install a 32-bit version of Userspace RCU:
3888 $ cd $(mktemp -d) &&
3889 wget http://lttng.org/files/urcu/userspace-rcu-latest-0.9.tar.bz2 &&
3890 tar -xf userspace-rcu-latest-0.9.tar.bz2 &&
3891 cd userspace-rcu-0.9.* &&
3892 ./configure --libdir=/usr/local/lib32 CFLAGS=-m32 &&
3894 sudo make install &&
3899 . Using your distribution's package manager, or from source, install
3900 the following 32-bit versions of the following dependencies of
3901 LTTng-tools and LTTng-UST:
3904 * https://sourceforge.net/projects/libuuid/[libuuid]
3905 * http://directory.fsf.org/wiki/Popt[popt]
3906 * http://www.xmlsoft.org/[libxml2]
3909 . Download, build, and install a 32-bit version of the latest
3910 LTTng-UST{nbsp}{revision}:
3915 $ cd $(mktemp -d) &&
3916 wget http://lttng.org/files/lttng-ust/lttng-ust-latest-2.10.tar.bz2 &&
3917 tar -xf lttng-ust-latest-2.10.tar.bz2 &&
3918 cd lttng-ust-2.10.* &&
3919 ./configure --libdir=/usr/local/lib32 \
3920 CFLAGS=-m32 CXXFLAGS=-m32 \
3921 LDFLAGS='-L/usr/local/lib32 -L/usr/lib32' &&
3923 sudo make install &&
3930 Depending on your distribution,
3931 32-bit libraries could be installed at a different location than
3932 `/usr/lib32`. For example, Debian is known to install
3933 some 32-bit libraries in `/usr/lib/i386-linux-gnu`.
3935 In this case, make sure to set `LDFLAGS` to all the
3936 relevant 32-bit library paths, for example:
3940 $ LDFLAGS='-L/usr/lib/i386-linux-gnu -L/usr/lib32'
3944 . Download the latest LTTng-tools{nbsp}{revision}, build, and install
3945 the 32-bit consumer daemon:
3950 $ cd $(mktemp -d) &&
3951 wget http://lttng.org/files/lttng-tools/lttng-tools-latest-2.10.tar.bz2 &&
3952 tar -xf lttng-tools-latest-2.10.tar.bz2 &&
3953 cd lttng-tools-2.10.* &&
3954 ./configure --libdir=/usr/local/lib32 CFLAGS=-m32 CXXFLAGS=-m32 \
3955 LDFLAGS='-L/usr/local/lib32 -L/usr/lib32' \
3956 --disable-bin-lttng --disable-bin-lttng-crash \
3957 --disable-bin-lttng-relayd --disable-bin-lttng-sessiond &&
3959 cd src/bin/lttng-consumerd &&
3960 sudo make install &&
3965 . From your distribution or from source,
3966 <<installing-lttng,install>> the 64-bit versions of
3967 LTTng-UST and Userspace RCU.
3968 . Download, build, and install the 64-bit version of the
3969 latest LTTng-tools{nbsp}{revision}:
3974 $ cd $(mktemp -d) &&
3975 wget http://lttng.org/files/lttng-tools/lttng-tools-latest-2.10.tar.bz2 &&
3976 tar -xf lttng-tools-latest-2.10.tar.bz2 &&
3977 cd lttng-tools-2.10.* &&
3978 ./configure --with-consumerd32-libdir=/usr/local/lib32 \
3979 --with-consumerd32-bin=/usr/local/lib32/lttng/libexec/lttng-consumerd &&
3981 sudo make install &&
3986 . Pass the following options to man:gcc(1), man:g++(1), or man:clang(1)
3987 when linking your 32-bit application:
3990 -m32 -L/usr/lib32 -L/usr/local/lib32 \
3991 -Wl,-rpath,/usr/lib32,-rpath,/usr/local/lib32
3994 For example, let's rebuild the quick start example in
3995 <<tracing-your-own-user-application,Trace a user application>> as an
3996 instrumented 32-bit application:
4001 $ gcc -m32 -c -I. hello-tp.c
4002 $ gcc -m32 -c hello.c
4003 $ gcc -m32 -o hello hello.o hello-tp.o \
4004 -L/usr/lib32 -L/usr/local/lib32 \
4005 -Wl,-rpath,/usr/lib32,-rpath,/usr/local/lib32 \
4010 No special action is required to execute the 32-bit application and
4011 to trace it: use the command-line man:lttng(1) tool as usual.
4018 man:tracef(3) is a small LTTng-UST API designed for quick,
4019 man:printf(3)-like instrumentation without the burden of
4020 <<tracepoint-provider,creating>> and
4021 <<building-tracepoint-providers-and-user-application,building>>
4022 a tracepoint provider package.
4024 To use `tracef()` in your application:
4026 . In the C or C++ source files where you need to use `tracef()`,
4027 include `<lttng/tracef.h>`:
4032 #include <lttng/tracef.h>
4036 . In the application's source code, use `tracef()` like you would use
4044 tracef("my message: %d (%s)", my_integer, my_string);
4050 . Link your application with `liblttng-ust`:
4055 $ gcc -o app app.c -llttng-ust
4059 To trace the events that `tracef()` calls emit:
4061 * <<enabling-disabling-events,Create an event rule>> which matches the
4062 `lttng_ust_tracef:*` event name:
4067 $ lttng enable-event --userspace 'lttng_ust_tracef:*'
4072 .Limitations of `tracef()`
4074 The `tracef()` utility function was developed to make user space tracing
4075 super simple, albeit with notable disadvantages compared to
4076 <<defining-tracepoints,user-defined tracepoints>>:
4078 * All the emitted events have the same tracepoint provider and
4079 tracepoint names, respectively `lttng_ust_tracef` and `event`.
4080 * There is no static type checking.
4081 * The only event record field you actually get, named `msg`, is a string
4082 potentially containing the values you passed to `tracef()`
4083 using your own format string. This also means that you cannot filter
4084 events with a custom expression at run time because there are no
4086 * Since `tracef()` uses the C standard library's man:vasprintf(3)
4087 function behind the scenes to format the strings at run time, its
4088 expected performance is lower than with user-defined tracepoints,
4089 which do not require a conversion to a string.
4091 Taking this into consideration, `tracef()` is useful for some quick
4092 prototyping and debugging, but you should not consider it for any
4093 permanent and serious applicative instrumentation.
4099 ==== Use `tracelog()`
4101 The man:tracelog(3) API is very similar to <<tracef,`tracef()`>>, with
4102 the difference that it accepts an additional log level parameter.
4104 The goal of `tracelog()` is to ease the migration from logging to
4107 To use `tracelog()` in your application:
4109 . In the C or C++ source files where you need to use `tracelog()`,
4110 include `<lttng/tracelog.h>`:
4115 #include <lttng/tracelog.h>
4119 . In the application's source code, use `tracelog()` like you would use
4120 man:printf(3), except for the first parameter which is the log
4128 tracelog(TRACE_WARNING, "my message: %d (%s)",
4129 my_integer, my_string);
4135 See man:lttng-ust(3) for a list of available log level names.
4137 . Link your application with `liblttng-ust`:
4142 $ gcc -o app app.c -llttng-ust
4146 To trace the events that `tracelog()` calls emit with a log level
4147 _as severe as_ a specific log level:
4149 * <<enabling-disabling-events,Create an event rule>> which matches the
4150 `lttng_ust_tracelog:*` event name and a minimum level
4156 $ lttng enable-event --userspace 'lttng_ust_tracelog:*'
4157 --loglevel=TRACE_WARNING
4161 To trace the events that `tracelog()` calls emit with a
4162 _specific log level_:
4164 * Create an event rule which matches the `lttng_ust_tracelog:*`
4165 event name and a specific log level:
4170 $ lttng enable-event --userspace 'lttng_ust_tracelog:*'
4171 --loglevel-only=TRACE_INFO
4176 [[prebuilt-ust-helpers]]
4177 === Prebuilt user space tracing helpers
4179 The LTTng-UST package provides a few helpers in the form or preloadable
4180 shared objects which automatically instrument system functions and
4183 The helper shared objects are normally found in dir:{/usr/lib}. If you
4184 built LTTng-UST <<building-from-source,from source>>, they are probably
4185 located in dir:{/usr/local/lib}.
4187 The installed user space tracing helpers in LTTng-UST{nbsp}{revision}
4190 path:{liblttng-ust-libc-wrapper.so}::
4191 path:{liblttng-ust-pthread-wrapper.so}::
4192 <<liblttng-ust-libc-pthread-wrapper,C{nbsp}standard library
4193 memory and POSIX threads function tracing>>.
4195 path:{liblttng-ust-cyg-profile.so}::
4196 path:{liblttng-ust-cyg-profile-fast.so}::
4197 <<liblttng-ust-cyg-profile,Function entry and exit tracing>>.
4199 path:{liblttng-ust-dl.so}::
4200 <<liblttng-ust-dl,Dynamic linker tracing>>.
4202 To use a user space tracing helper with any user application:
4204 * Preload the helper shared object when you start the application:
4209 $ LD_PRELOAD=liblttng-ust-libc-wrapper.so my-app
4213 You can preload more than one helper:
4218 $ LD_PRELOAD=liblttng-ust-libc-wrapper.so:liblttng-ust-dl.so my-app
4224 [[liblttng-ust-libc-pthread-wrapper]]
4225 ==== Instrument C standard library memory and POSIX threads functions
4227 The path:{liblttng-ust-libc-wrapper.so} and
4228 path:{liblttng-ust-pthread-wrapper.so} helpers
4229 add instrumentation to some C standard library and POSIX
4233 .Functions instrumented by preloading path:{liblttng-ust-libc-wrapper.so}.
4235 |TP provider name |TP name |Instrumented function
4237 .6+|`lttng_ust_libc` |`malloc` |man:malloc(3)
4238 |`calloc` |man:calloc(3)
4239 |`realloc` |man:realloc(3)
4240 |`free` |man:free(3)
4241 |`memalign` |man:memalign(3)
4242 |`posix_memalign` |man:posix_memalign(3)
4246 .Functions instrumented by preloading path:{liblttng-ust-pthread-wrapper.so}.
4248 |TP provider name |TP name |Instrumented function
4250 .4+|`lttng_ust_pthread` |`pthread_mutex_lock_req` |man:pthread_mutex_lock(3p) (request time)
4251 |`pthread_mutex_lock_acq` |man:pthread_mutex_lock(3p) (acquire time)
4252 |`pthread_mutex_trylock` |man:pthread_mutex_trylock(3p)
4253 |`pthread_mutex_unlock` |man:pthread_mutex_unlock(3p)
4256 When you preload the shared object, it replaces the functions listed
4257 in the previous tables by wrappers which contain tracepoints and call
4258 the replaced functions.
4261 [[liblttng-ust-cyg-profile]]
4262 ==== Instrument function entry and exit
4264 The path:{liblttng-ust-cyg-profile*.so} helpers can add instrumentation
4265 to the entry and exit points of functions.
4267 man:gcc(1) and man:clang(1) have an option named
4268 https://gcc.gnu.org/onlinedocs/gcc/Instrumentation-Options.html[`-finstrument-functions`]
4269 which generates instrumentation calls for entry and exit to functions.
4270 The LTTng-UST function tracing helpers,
4271 path:{liblttng-ust-cyg-profile.so} and
4272 path:{liblttng-ust-cyg-profile-fast.so}, take advantage of this feature
4273 to add tracepoints to the two generated functions (which contain
4274 `cyg_profile` in their names, hence the helper's name).
4276 To use the LTTng-UST function tracing helper, the source files to
4277 instrument must be built using the `-finstrument-functions` compiler
4280 There are two versions of the LTTng-UST function tracing helper:
4282 * **path:{liblttng-ust-cyg-profile-fast.so}** is a lightweight variant
4283 that you should only use when it can be _guaranteed_ that the
4284 complete event stream is recorded without any lost event record.
4285 Any kind of duplicate information is left out.
4287 Assuming no event record is lost, having only the function addresses on
4288 entry is enough to create a call graph, since an event record always
4289 contains the ID of the CPU that generated it.
4291 You can use a tool like man:addr2line(1) to convert function addresses
4292 back to source file names and line numbers.
4294 * **path:{liblttng-ust-cyg-profile.so}** is a more robust variant
4295 which also works in use cases where event records might get discarded or
4296 not recorded from application startup.
4297 In these cases, the trace analyzer needs more information to be
4298 able to reconstruct the program flow.
4300 See man:lttng-ust-cyg-profile(3) to learn more about the instrumentation
4301 points of this helper.
4303 All the tracepoints that this helper provides have the
4304 log level `TRACE_DEBUG_FUNCTION` (see man:lttng-ust(3)).
4306 TIP: It's sometimes a good idea to limit the number of source files that
4307 you compile with the `-finstrument-functions` option to prevent LTTng
4308 from writing an excessive amount of trace data at run time. When using
4309 man:gcc(1), you can use the
4310 `-finstrument-functions-exclude-function-list` option to avoid
4311 instrument entries and exits of specific function names.
4316 ==== Instrument the dynamic linker
4318 The path:{liblttng-ust-dl.so} helper adds instrumentation to the
4319 man:dlopen(3) and man:dlclose(3) function calls.
4321 See man:lttng-ust-dl(3) to learn more about the instrumentation points
4326 [[java-application]]
4327 === User space Java agent
4329 You can instrument any Java application which uses one of the following
4332 * The https://docs.oracle.com/javase/7/docs/api/java/util/logging/package-summary.html[**`java.util.logging`**]
4333 (JUL) core logging facilities.
4334 * http://logging.apache.org/log4j/1.2/[**Apache log4j 1.2**], since
4335 LTTng 2.6. Note that Apache Log4j{nbsp}2 is not supported.
4338 .LTTng-UST Java agent imported by a Java application.
4339 image::java-app.png[]
4341 Note that the methods described below are new in LTTng{nbsp}{revision}.
4342 Previous LTTng versions use another technique.
4344 NOTE: We use http://openjdk.java.net/[OpenJDK]{nbsp}8 for development
4345 and https://ci.lttng.org/[continuous integration], thus this version is
4346 directly supported. However, the LTTng-UST Java agent is also tested
4347 with OpenJDK{nbsp}7.
4352 ==== Use the LTTng-UST Java agent for `java.util.logging`
4354 To use the LTTng-UST Java agent in a Java application which uses
4355 `java.util.logging` (JUL):
4357 . In the Java application's source code, import the LTTng-UST
4358 log handler package for `java.util.logging`:
4363 import org.lttng.ust.agent.jul.LttngLogHandler;
4367 . Create an LTTng-UST JUL log handler:
4372 Handler lttngUstLogHandler = new LttngLogHandler();
4376 . Add this handler to the JUL loggers which should emit LTTng events:
4381 Logger myLogger = Logger.getLogger("some-logger");
4383 myLogger.addHandler(lttngUstLogHandler);
4387 . Use `java.util.logging` log statements and configuration as usual.
4388 The loggers with an attached LTTng-UST log handler can emit
4391 . Before exiting the application, remove the LTTng-UST log handler from
4392 the loggers attached to it and call its `close()` method:
4397 myLogger.removeHandler(lttngUstLogHandler);
4398 lttngUstLogHandler.close();
4402 This is not strictly necessary, but it is recommended for a clean
4403 disposal of the handler's resources.
4405 . Include the LTTng-UST Java agent's common and JUL-specific JAR files,
4406 path:{lttng-ust-agent-common.jar} and path:{lttng-ust-agent-jul.jar},
4408 https://docs.oracle.com/javase/tutorial/essential/environment/paths.html[class
4409 path] when you build the Java application.
4411 The JAR files are typically located in dir:{/usr/share/java}.
4413 IMPORTANT: The LTTng-UST Java agent must be
4414 <<installing-lttng,installed>> for the logging framework your
4417 .Use the LTTng-UST Java agent for `java.util.logging`.
4422 import java.io.IOException;
4423 import java.util.logging.Handler;
4424 import java.util.logging.Logger;
4425 import org.lttng.ust.agent.jul.LttngLogHandler;
4429 private static final int answer = 42;
4431 public static void main(String[] argv) throws Exception
4434 Logger logger = Logger.getLogger("jello");
4436 // Create an LTTng-UST log handler
4437 Handler lttngUstLogHandler = new LttngLogHandler();
4439 // Add the LTTng-UST log handler to our logger
4440 logger.addHandler(lttngUstLogHandler);
4443 logger.info("some info");
4444 logger.warning("some warning");
4446 logger.finer("finer information; the answer is " + answer);
4448 logger.severe("error!");
4450 // Not mandatory, but cleaner
4451 logger.removeHandler(lttngUstLogHandler);
4452 lttngUstLogHandler.close();
4461 $ javac -cp /usr/share/java/jarpath/lttng-ust-agent-common.jar:/usr/share/java/jarpath/lttng-ust-agent-jul.jar Test.java
4464 <<creating-destroying-tracing-sessions,Create a tracing session>>,
4465 <<enabling-disabling-events,create an event rule>> matching the
4466 `jello` JUL logger, and <<basic-tracing-session-control,start tracing>>:
4471 $ lttng enable-event --jul jello
4475 Run the compiled class:
4479 $ java -cp /usr/share/java/jarpath/lttng-ust-agent-common.jar:/usr/share/java/jarpath/lttng-ust-agent-jul.jar:. Test
4482 <<basic-tracing-session-control,Stop tracing>> and inspect the
4492 In the resulting trace, an <<event,event record>> generated by a Java
4493 application using `java.util.logging` is named `lttng_jul:event` and
4494 has the following fields:
4497 Log record's message.
4503 Name of the class in which the log statement was executed.
4506 Name of the method in which the log statement was executed.
4509 Logging time (timestamp in milliseconds).
4512 Log level integer value.
4515 ID of the thread in which the log statement was executed.
4517 You can use the opt:lttng-enable-event(1):--loglevel or
4518 opt:lttng-enable-event(1):--loglevel-only option of the
4519 man:lttng-enable-event(1) command to target a range of JUL log levels
4520 or a specific JUL log level.
4525 ==== Use the LTTng-UST Java agent for Apache log4j
4527 To use the LTTng-UST Java agent in a Java application which uses
4530 . In the Java application's source code, import the LTTng-UST
4531 log appender package for Apache log4j:
4536 import org.lttng.ust.agent.log4j.LttngLogAppender;
4540 . Create an LTTng-UST log4j log appender:
4545 Appender lttngUstLogAppender = new LttngLogAppender();
4549 . Add this appender to the log4j loggers which should emit LTTng events:
4554 Logger myLogger = Logger.getLogger("some-logger");
4556 myLogger.addAppender(lttngUstLogAppender);
4560 . Use Apache log4j log statements and configuration as usual. The
4561 loggers with an attached LTTng-UST log appender can emit LTTng events.
4563 . Before exiting the application, remove the LTTng-UST log appender from
4564 the loggers attached to it and call its `close()` method:
4569 myLogger.removeAppender(lttngUstLogAppender);
4570 lttngUstLogAppender.close();
4574 This is not strictly necessary, but it is recommended for a clean
4575 disposal of the appender's resources.
4577 . Include the LTTng-UST Java agent's common and log4j-specific JAR
4578 files, path:{lttng-ust-agent-common.jar} and
4579 path:{lttng-ust-agent-log4j.jar}, in the
4580 https://docs.oracle.com/javase/tutorial/essential/environment/paths.html[class
4581 path] when you build the Java application.
4583 The JAR files are typically located in dir:{/usr/share/java}.
4585 IMPORTANT: The LTTng-UST Java agent must be
4586 <<installing-lttng,installed>> for the logging framework your
4589 .Use the LTTng-UST Java agent for Apache log4j.
4594 import org.apache.log4j.Appender;
4595 import org.apache.log4j.Logger;
4596 import org.lttng.ust.agent.log4j.LttngLogAppender;
4600 private static final int answer = 42;
4602 public static void main(String[] argv) throws Exception
4605 Logger logger = Logger.getLogger("jello");
4607 // Create an LTTng-UST log appender
4608 Appender lttngUstLogAppender = new LttngLogAppender();
4610 // Add the LTTng-UST log appender to our logger
4611 logger.addAppender(lttngUstLogAppender);
4614 logger.info("some info");
4615 logger.warn("some warning");
4617 logger.debug("debug information; the answer is " + answer);
4619 logger.fatal("error!");
4621 // Not mandatory, but cleaner
4622 logger.removeAppender(lttngUstLogAppender);
4623 lttngUstLogAppender.close();
4629 Build this example (`$LOG4JPATH` is the path to the Apache log4j JAR
4634 $ javac -cp /usr/share/java/jarpath/lttng-ust-agent-common.jar:/usr/share/java/jarpath/lttng-ust-agent-log4j.jar:$LOG4JPATH Test.java
4637 <<creating-destroying-tracing-sessions,Create a tracing session>>,
4638 <<enabling-disabling-events,create an event rule>> matching the
4639 `jello` log4j logger, and <<basic-tracing-session-control,start tracing>>:
4644 $ lttng enable-event --log4j jello
4648 Run the compiled class:
4652 $ java -cp /usr/share/java/jarpath/lttng-ust-agent-common.jar:/usr/share/java/jarpath/lttng-ust-agent-log4j.jar:$LOG4JPATH:. Test
4655 <<basic-tracing-session-control,Stop tracing>> and inspect the
4665 In the resulting trace, an <<event,event record>> generated by a Java
4666 application using log4j is named `lttng_log4j:event` and
4667 has the following fields:
4670 Log record's message.
4676 Name of the class in which the log statement was executed.
4679 Name of the method in which the log statement was executed.
4682 Name of the file in which the executed log statement is located.
4685 Line number at which the log statement was executed.
4691 Log level integer value.
4694 Name of the Java thread in which the log statement was executed.
4696 You can use the opt:lttng-enable-event(1):--loglevel or
4697 opt:lttng-enable-event(1):--loglevel-only option of the
4698 man:lttng-enable-event(1) command to target a range of Apache log4j log levels
4699 or a specific log4j log level.
4703 [[java-application-context]]
4704 ==== Provide application-specific context fields in a Java application
4706 A Java application-specific context field is a piece of state provided
4707 by the application which <<adding-context,you can add>>, using the
4708 man:lttng-add-context(1) command, to each <<event,event record>>
4709 produced by the log statements of this application.
4711 For example, a given object might have a current request ID variable.
4712 You can create a context information retriever for this object and
4713 assign a name to this current request ID. You can then, using the
4714 man:lttng-add-context(1) command, add this context field by name to
4715 the JUL or log4j <<channel,channel>>.
4717 To provide application-specific context fields in a Java application:
4719 . In the Java application's source code, import the LTTng-UST
4720 Java agent context classes and interfaces:
4725 import org.lttng.ust.agent.context.ContextInfoManager;
4726 import org.lttng.ust.agent.context.IContextInfoRetriever;
4730 . Create a context information retriever class, that is, a class which
4731 implements the `IContextInfoRetriever` interface:
4736 class MyContextInfoRetriever implements IContextInfoRetriever
4739 public Object retrieveContextInfo(String key)
4741 if (key.equals("intCtx")) {
4743 } else if (key.equals("strContext")) {
4744 return "context value!";
4753 This `retrieveContextInfo()` method is the only member of the
4754 `IContextInfoRetriever` interface. Its role is to return the current
4755 value of a state by name to create a context field. The names of the
4756 context fields and which state variables they return depends on your
4759 All primitive types and objects are supported as context fields.
4760 When `retrieveContextInfo()` returns an object, the context field
4761 serializer calls its `toString()` method to add a string field to
4762 event records. The method can also return `null`, which means that
4763 no context field is available for the required name.
4765 . Register an instance of your context information retriever class to
4766 the context information manager singleton:
4771 IContextInfoRetriever cir = new MyContextInfoRetriever();
4772 ContextInfoManager cim = ContextInfoManager.getInstance();
4773 cim.registerContextInfoRetriever("retrieverName", cir);
4777 . Before exiting the application, remove your context information
4778 retriever from the context information manager singleton:
4783 ContextInfoManager cim = ContextInfoManager.getInstance();
4784 cim.unregisterContextInfoRetriever("retrieverName");
4788 This is not strictly necessary, but it is recommended for a clean
4789 disposal of some manager's resources.
4791 . Build your Java application with LTTng-UST Java agent support as
4792 usual, following the procedure for either the <<jul,JUL>> or
4793 <<log4j,Apache log4j>> framework.
4796 .Provide application-specific context fields in a Java application.
4801 import java.util.logging.Handler;
4802 import java.util.logging.Logger;
4803 import org.lttng.ust.agent.jul.LttngLogHandler;
4804 import org.lttng.ust.agent.context.ContextInfoManager;
4805 import org.lttng.ust.agent.context.IContextInfoRetriever;
4809 // Our context information retriever class
4810 private static class MyContextInfoRetriever
4811 implements IContextInfoRetriever
4814 public Object retrieveContextInfo(String key) {
4815 if (key.equals("intCtx")) {
4817 } else if (key.equals("strContext")) {
4818 return "context value!";
4825 private static final int answer = 42;
4827 public static void main(String args[]) throws Exception
4829 // Get the context information manager instance
4830 ContextInfoManager cim = ContextInfoManager.getInstance();
4832 // Create and register our context information retriever
4833 IContextInfoRetriever cir = new MyContextInfoRetriever();
4834 cim.registerContextInfoRetriever("myRetriever", cir);
4837 Logger logger = Logger.getLogger("jello");
4839 // Create an LTTng-UST log handler
4840 Handler lttngUstLogHandler = new LttngLogHandler();
4842 // Add the LTTng-UST log handler to our logger
4843 logger.addHandler(lttngUstLogHandler);
4846 logger.info("some info");
4847 logger.warning("some warning");
4849 logger.finer("finer information; the answer is " + answer);
4851 logger.severe("error!");
4853 // Not mandatory, but cleaner
4854 logger.removeHandler(lttngUstLogHandler);
4855 lttngUstLogHandler.close();
4856 cim.unregisterContextInfoRetriever("myRetriever");
4865 $ javac -cp /usr/share/java/jarpath/lttng-ust-agent-common.jar:/usr/share/java/jarpath/lttng-ust-agent-jul.jar Test.java
4868 <<creating-destroying-tracing-sessions,Create a tracing session>>
4869 and <<enabling-disabling-events,create an event rule>> matching the
4875 $ lttng enable-event --jul jello
4878 <<adding-context,Add the application-specific context fields>> to the
4883 $ lttng add-context --jul --type='$app.myRetriever:intCtx'
4884 $ lttng add-context --jul --type='$app.myRetriever:strContext'
4887 <<basic-tracing-session-control,Start tracing>>:
4894 Run the compiled class:
4898 $ java -cp /usr/share/java/jarpath/lttng-ust-agent-common.jar:/usr/share/java/jarpath/lttng-ust-agent-jul.jar:. Test
4901 <<basic-tracing-session-control,Stop tracing>> and inspect the
4913 [[python-application]]
4914 === User space Python agent
4916 You can instrument a Python 2 or Python 3 application which uses the
4917 standard https://docs.python.org/3/library/logging.html[`logging`]
4920 Each log statement emits an LTTng event once the
4921 application module imports the
4922 <<lttng-ust-agents,LTTng-UST Python agent>> package.
4925 .A Python application importing the LTTng-UST Python agent.
4926 image::python-app.png[]
4928 To use the LTTng-UST Python agent:
4930 . In the Python application's source code, import the LTTng-UST Python
4940 The LTTng-UST Python agent automatically adds its logging handler to the
4941 root logger at import time.
4943 Any log statement that the application executes before this import does
4944 not emit an LTTng event.
4946 IMPORTANT: The LTTng-UST Python agent must be
4947 <<installing-lttng,installed>>.
4949 . Use log statements and logging configuration as usual.
4950 Since the LTTng-UST Python agent adds a handler to the _root_
4951 logger, you can trace any log statement from any logger.
4953 .Use the LTTng-UST Python agent.
4964 logging.basicConfig()
4965 logger = logging.getLogger('my-logger')
4968 logger.debug('debug message')
4969 logger.info('info message')
4970 logger.warn('warn message')
4971 logger.error('error message')
4972 logger.critical('critical message')
4976 if __name__ == '__main__':
4980 NOTE: `logging.basicConfig()`, which adds to the root logger a basic
4981 logging handler which prints to the standard error stream, is not
4982 strictly required for LTTng-UST tracing to work, but in versions of
4983 Python preceding 3.2, you could see a warning message which indicates
4984 that no handler exists for the logger `my-logger`.
4986 <<creating-destroying-tracing-sessions,Create a tracing session>>,
4987 <<enabling-disabling-events,create an event rule>> matching the
4988 `my-logger` Python logger, and <<basic-tracing-session-control,start
4994 $ lttng enable-event --python my-logger
4998 Run the Python script:
5005 <<basic-tracing-session-control,Stop tracing>> and inspect the recorded
5015 In the resulting trace, an <<event,event record>> generated by a Python
5016 application is named `lttng_python:event` and has the following fields:
5019 Logging time (string).
5022 Log record's message.
5028 Name of the function in which the log statement was executed.
5031 Line number at which the log statement was executed.
5034 Log level integer value.
5037 ID of the Python thread in which the log statement was executed.
5040 Name of the Python thread in which the log statement was executed.
5042 You can use the opt:lttng-enable-event(1):--loglevel or
5043 opt:lttng-enable-event(1):--loglevel-only option of the
5044 man:lttng-enable-event(1) command to target a range of Python log levels
5045 or a specific Python log level.
5047 When an application imports the LTTng-UST Python agent, the agent tries
5048 to register to a <<lttng-sessiond,session daemon>>. Note that you must
5049 <<start-sessiond,start the session daemon>> _before_ you run the Python
5050 application. If a session daemon is found, the agent tries to register
5051 to it during 5{nbsp}seconds, after which the application continues
5052 without LTTng tracing support. You can override this timeout value with
5053 the env:LTTNG_UST_PYTHON_REGISTER_TIMEOUT environment variable
5056 If the session daemon stops while a Python application with an imported
5057 LTTng-UST Python agent runs, the agent retries to connect and to
5058 register to a session daemon every 3{nbsp}seconds. You can override this
5059 delay with the env:LTTNG_UST_PYTHON_REGISTER_RETRY_DELAY environment
5064 [[proc-lttng-logger-abi]]
5067 The `lttng-tracer` Linux kernel module, part of
5068 <<lttng-modules,LTTng-modules>>, creates the special LTTng logger file
5069 path:{/proc/lttng-logger} when it's loaded. Any application can write
5070 text data to this file to emit an LTTng event.
5073 .An application writes to the LTTng logger file to emit an LTTng event.
5074 image::lttng-logger.png[]
5076 The LTTng logger is the quickest method--not the most efficient,
5077 however--to add instrumentation to an application. It is designed
5078 mostly to instrument shell scripts:
5082 $ echo "Some message, some $variable" > /proc/lttng-logger
5085 Any event that the LTTng logger emits is named `lttng_logger` and
5086 belongs to the Linux kernel <<domain,tracing domain>>. However, unlike
5087 other instrumentation points in the kernel tracing domain, **any Unix
5088 user** can <<enabling-disabling-events,create an event rule>> which
5089 matches its event name, not only the root user or users in the
5090 <<tracing-group,tracing group>>.
5092 To use the LTTng logger:
5094 * From any application, write text data to the path:{/proc/lttng-logger}
5097 The `msg` field of `lttng_logger` event records contains the
5100 NOTE: The maximum message length of an LTTng logger event is
5101 1024{nbsp}bytes. Writing more than this makes the LTTng logger emit more
5102 than one event to contain the remaining data.
5104 You should not use the LTTng logger to trace a user application which
5105 can be instrumented in a more efficient way, namely:
5107 * <<c-application,C and $$C++$$ applications>>.
5108 * <<java-application,Java applications>>.
5109 * <<python-application,Python applications>>.
5111 .Use the LTTng logger.
5116 echo 'Hello, World!' > /proc/lttng-logger
5118 df --human-readable --print-type / > /proc/lttng-logger
5121 <<creating-destroying-tracing-sessions,Create a tracing session>>,
5122 <<enabling-disabling-events,create an event rule>> matching the
5123 `lttng_logger` Linux kernel tracepoint, and
5124 <<basic-tracing-session-control,start tracing>>:
5129 $ lttng enable-event --kernel lttng_logger
5133 Run the Bash script:
5140 <<basic-tracing-session-control,Stop tracing>> and inspect the recorded
5151 [[instrumenting-linux-kernel]]
5152 === LTTng kernel tracepoints
5154 NOTE: This section shows how to _add_ instrumentation points to the
5155 Linux kernel. The kernel's subsystems are already thoroughly
5156 instrumented at strategic places for LTTng when you
5157 <<installing-lttng,install>> the <<lttng-modules,LTTng-modules>>
5161 There are two methods to instrument the Linux kernel:
5163 . <<linux-add-lttng-layer,Add an LTTng layer>> over an existing ftrace
5164 tracepoint which uses the `TRACE_EVENT()` API.
5166 Choose this if you want to instrumentation a Linux kernel tree with an
5167 instrumentation point compatible with ftrace, perf, and SystemTap.
5169 . Use an <<linux-lttng-tracepoint-event,LTTng-only approach>> to
5170 instrument an out-of-tree kernel module.
5172 Choose this if you don't need ftrace, perf, or SystemTap support.
5176 [[linux-add-lttng-layer]]
5177 ==== [[instrumenting-linux-kernel-itself]][[mainline-trace-event]][[lttng-adaptation-layer]]Add an LTTng layer to an existing ftrace tracepoint
5179 This section shows how to add an LTTng layer to existing ftrace
5180 instrumentation using the `TRACE_EVENT()` API.
5182 This section does not document the `TRACE_EVENT()` macro. You can
5183 read the following articles to learn more about this API:
5185 * http://lwn.net/Articles/379903/[Using the TRACE_EVENT() macro (Part 1)]
5186 * http://lwn.net/Articles/381064/[Using the TRACE_EVENT() macro (Part 2)]
5187 * http://lwn.net/Articles/383362/[Using the TRACE_EVENT() macro (Part 3)]
5189 The following procedure assumes that your ftrace tracepoints are
5190 correctly defined in their own header and that they are created in
5191 one source file using the `CREATE_TRACE_POINTS` definition.
5193 To add an LTTng layer over an existing ftrace tracepoint:
5195 . Make sure the following kernel configuration options are
5201 * `CONFIG_HIGH_RES_TIMERS`
5202 * `CONFIG_TRACEPOINTS`
5205 . Build the Linux source tree with your custom ftrace tracepoints.
5206 . Boot the resulting Linux image on your target system.
5208 Confirm that the tracepoints exist by looking for their names in the
5209 dir:{/sys/kernel/debug/tracing/events/subsys} directory, where `subsys`
5210 is your subsystem's name.
5212 . Get a copy of the latest LTTng-modules{nbsp}{revision}:
5217 $ cd $(mktemp -d) &&
5218 wget http://lttng.org/files/lttng-modules/lttng-modules-latest-2.10.tar.bz2 &&
5219 tar -xf lttng-modules-latest-2.10.tar.bz2 &&
5220 cd lttng-modules-2.10.*
5224 . In dir:{instrumentation/events/lttng-module}, relative to the root
5225 of the LTTng-modules source tree, create a header file named
5226 +__subsys__.h+ for your custom subsystem +__subsys__+ and write your
5227 LTTng-modules tracepoint definitions using the LTTng-modules
5230 Start with this template:
5234 .path:{instrumentation/events/lttng-module/my_subsys.h}
5237 #define TRACE_SYSTEM my_subsys
5239 #if !defined(_LTTNG_MY_SUBSYS_H) || defined(TRACE_HEADER_MULTI_READ)
5240 #define _LTTNG_MY_SUBSYS_H
5242 #include "../../../probes/lttng-tracepoint-event.h"
5243 #include <linux/tracepoint.h>
5245 LTTNG_TRACEPOINT_EVENT(
5247 * Format is identical to TRACE_EVENT()'s version for the three
5248 * following macro parameters:
5251 TP_PROTO(int my_int, const char *my_string),
5252 TP_ARGS(my_int, my_string),
5254 /* LTTng-modules specific macros */
5256 ctf_integer(int, my_int_field, my_int)
5257 ctf_string(my_bar_field, my_bar)
5261 #endif /* !defined(_LTTNG_MY_SUBSYS_H) || defined(TRACE_HEADER_MULTI_READ) */
5263 #include "../../../probes/define_trace.h"
5267 The entries in the `TP_FIELDS()` section are the list of fields for the
5268 LTTng tracepoint. This is similar to the `TP_STRUCT__entry()` part of
5269 ftrace's `TRACE_EVENT()` macro.
5271 See <<lttng-modules-tp-fields,Tracepoint fields macros>> for a
5272 complete description of the available `ctf_*()` macros.
5274 . Create the LTTng-modules probe's kernel module C source file,
5275 +probes/lttng-probe-__subsys__.c+, where +__subsys__+ is your
5280 .path:{probes/lttng-probe-my-subsys.c}
5282 #include <linux/module.h>
5283 #include "../lttng-tracer.h"
5286 * Build-time verification of mismatch between mainline
5287 * TRACE_EVENT() arguments and the LTTng-modules adaptation
5288 * layer LTTNG_TRACEPOINT_EVENT() arguments.
5290 #include <trace/events/my_subsys.h>
5292 /* Create LTTng tracepoint probes */
5293 #define LTTNG_PACKAGE_BUILD
5294 #define CREATE_TRACE_POINTS
5295 #define TRACE_INCLUDE_PATH ../instrumentation/events/lttng-module
5297 #include "../instrumentation/events/lttng-module/my_subsys.h"
5299 MODULE_LICENSE("GPL and additional rights");
5300 MODULE_AUTHOR("Your name <your-email>");
5301 MODULE_DESCRIPTION("LTTng my_subsys probes");
5302 MODULE_VERSION(__stringify(LTTNG_MODULES_MAJOR_VERSION) "."
5303 __stringify(LTTNG_MODULES_MINOR_VERSION) "."
5304 __stringify(LTTNG_MODULES_PATCHLEVEL_VERSION)
5305 LTTNG_MODULES_EXTRAVERSION);
5309 . Edit path:{probes/KBuild} and add your new kernel module object
5310 next to the existing ones:
5314 .path:{probes/KBuild}
5318 obj-m += lttng-probe-module.o
5319 obj-m += lttng-probe-power.o
5321 obj-m += lttng-probe-my-subsys.o
5327 . Build and install the LTTng kernel modules:
5332 $ make KERNELDIR=/path/to/linux
5333 # make modules_install && depmod -a
5337 Replace `/path/to/linux` with the path to the Linux source tree where
5338 you defined and used tracepoints with ftrace's `TRACE_EVENT()` macro.
5340 Note that you can also use the
5341 <<lttng-tracepoint-event-code,`LTTNG_TRACEPOINT_EVENT_CODE()` macro>>
5342 instead of `LTTNG_TRACEPOINT_EVENT()` to use custom local variables and
5343 C code that need to be executed before the event fields are recorded.
5345 The best way to learn how to use the previous LTTng-modules macros is to
5346 inspect the existing LTTng-modules tracepoint definitions in the
5347 dir:{instrumentation/events/lttng-module} header files. Compare them
5348 with the Linux kernel mainline versions in the
5349 dir:{include/trace/events} directory of the Linux source tree.
5353 [[lttng-tracepoint-event-code]]
5354 ===== Use custom C code to access the data for tracepoint fields
5356 Although we recommended to always use the
5357 <<lttng-adaptation-layer,`LTTNG_TRACEPOINT_EVENT()`>> macro to describe
5358 the arguments and fields of an LTTng-modules tracepoint when possible,
5359 sometimes you need a more complex process to access the data that the
5360 tracer records as event record fields. In other words, you need local
5361 variables and multiple C{nbsp}statements instead of simple
5362 argument-based expressions that you pass to the
5363 <<lttng-modules-tp-fields,`ctf_*()` macros of `TP_FIELDS()`>>.
5365 You can use the `LTTNG_TRACEPOINT_EVENT_CODE()` macro instead of
5366 `LTTNG_TRACEPOINT_EVENT()` to declare custom local variables and define
5367 a block of C{nbsp}code to be executed before LTTng records the fields.
5368 The structure of this macro is:
5371 .`LTTNG_TRACEPOINT_EVENT_CODE()` macro syntax.
5373 LTTNG_TRACEPOINT_EVENT_CODE(
5375 * Format identical to the LTTNG_TRACEPOINT_EVENT()
5376 * version for the following three macro parameters:
5379 TP_PROTO(int my_int, const char *my_string),
5380 TP_ARGS(my_int, my_string),
5382 /* Declarations of custom local variables */
5385 unsigned long b = 0;
5386 const char *name = "(undefined)";
5387 struct my_struct *my_struct;
5391 * Custom code which uses both tracepoint arguments
5392 * (in TP_ARGS()) and local variables (in TP_locvar()).
5394 * Local variables are actually members of a structure pointed
5395 * to by the special variable tp_locvar.
5399 tp_locvar->a = my_int + 17;
5400 tp_locvar->my_struct = get_my_struct_at(tp_locvar->a);
5401 tp_locvar->b = my_struct_compute_b(tp_locvar->my_struct);
5402 tp_locvar->name = my_struct_get_name(tp_locvar->my_struct);
5403 put_my_struct(tp_locvar->my_struct);
5412 * Format identical to the LTTNG_TRACEPOINT_EVENT()
5413 * version for this, except that tp_locvar members can be
5414 * used in the argument expression parameters of
5415 * the ctf_*() macros.
5418 ctf_integer(unsigned long, my_struct_b, tp_locvar->b)
5419 ctf_integer(int, my_struct_a, tp_locvar->a)
5420 ctf_string(my_string_field, my_string)
5421 ctf_string(my_struct_name, tp_locvar->name)
5426 IMPORTANT: The C code defined in `TP_code()` must not have any side
5427 effects when executed. In particular, the code must not allocate
5428 memory or get resources without deallocating this memory or putting
5429 those resources afterwards.
5432 [[instrumenting-linux-kernel-tracing]]
5433 ==== Load and unload a custom probe kernel module
5435 You must load a <<lttng-adaptation-layer,created LTTng-modules probe
5436 kernel module>> in the kernel before it can emit LTTng events.
5438 To load the default probe kernel modules and a custom probe kernel
5441 * Use the opt:lttng-sessiond(8):--extra-kmod-probes option to give extra
5442 probe modules to load when starting a root <<lttng-sessiond,session
5446 .Load the `my_subsys`, `usb`, and the default probe modules.
5450 # lttng-sessiond --extra-kmod-probes=my_subsys,usb
5455 You only need to pass the subsystem name, not the whole kernel module
5458 To load _only_ a given custom probe kernel module:
5460 * Use the opt:lttng-sessiond(8):--kmod-probes option to give the probe
5461 modules to load when starting a root session daemon:
5464 .Load only the `my_subsys` and `usb` probe modules.
5468 # lttng-sessiond --kmod-probes=my_subsys,usb
5473 To confirm that a probe module is loaded:
5480 $ lsmod | grep lttng_probe_usb
5484 To unload the loaded probe modules:
5486 * Kill the session daemon with `SIGTERM`:
5491 # pkill lttng-sessiond
5495 You can also use man:modprobe(8)'s `--remove` option if the session
5496 daemon terminates abnormally.
5499 [[controlling-tracing]]
5502 Once an application or a Linux kernel is
5503 <<instrumenting,instrumented>> for LTTng tracing,
5506 This section is divided in topics on how to use the various
5507 <<plumbing,components of LTTng>>, in particular the <<lttng-cli,cmd:lttng
5508 command-line tool>>, to _control_ the LTTng daemons and tracers.
5510 NOTE: In the following subsections, we refer to an man:lttng(1) command
5511 using its man page name. For example, instead of _Run the `create`
5512 command to..._, we use _Run the man:lttng-create(1) command to..._.
5516 === Start a session daemon
5518 In some situations, you need to run a <<lttng-sessiond,session daemon>>
5519 (man:lttng-sessiond(8)) _before_ you can use the man:lttng(1)
5522 You will see the following error when you run a command while no session
5526 Error: No session daemon is available
5529 The only command that automatically runs a session daemon is
5530 man:lttng-create(1), which you use to
5531 <<creating-destroying-tracing-sessions,create a tracing session>>. While
5532 this is most of the time the first operation that you do, sometimes it's
5533 not. Some examples are:
5535 * <<list-instrumentation-points,List the available instrumentation points>>.
5536 * <<saving-loading-tracing-session,Load a tracing session configuration>>.
5538 [[tracing-group]] Each Unix user must have its own running session
5539 daemon to trace user applications. The session daemon that the root user
5540 starts is the only one allowed to control the LTTng kernel tracer. Users
5541 that are part of the _tracing group_ can control the root session
5542 daemon. The default tracing group name is `tracing`; you can set it to
5543 something else with the opt:lttng-sessiond(8):--group option when you
5544 start the root session daemon.
5546 To start a user session daemon:
5548 * Run man:lttng-sessiond(8):
5553 $ lttng-sessiond --daemonize
5557 To start the root session daemon:
5559 * Run man:lttng-sessiond(8) as the root user:
5564 # lttng-sessiond --daemonize
5568 In both cases, remove the opt:lttng-sessiond(8):--daemonize option to
5569 start the session daemon in foreground.
5571 To stop a session daemon, use man:kill(1) on its process ID (standard
5574 Note that some Linux distributions could manage the LTTng session daemon
5575 as a service. In this case, you should use the service manager to
5576 start, restart, and stop session daemons.
5579 [[creating-destroying-tracing-sessions]]
5580 === Create and destroy a tracing session
5582 Almost all the LTTng control operations happen in the scope of
5583 a <<tracing-session,tracing session>>, which is the dialogue between the
5584 <<lttng-sessiond,session daemon>> and you.
5586 To create a tracing session with a generated name:
5588 * Use the man:lttng-create(1) command:
5597 The created tracing session's name is `auto` followed by the
5600 To create a tracing session with a specific name:
5602 * Use the optional argument of the man:lttng-create(1) command:
5607 $ lttng create my-session
5611 Replace `my-session` with the specific tracing session name.
5613 LTTng appends the creation date to the created tracing session's name.
5615 LTTng writes the traces of a tracing session in
5616 +$LTTNG_HOME/lttng-trace/__name__+ by default, where +__name__+ is the
5617 name of the tracing session. Note that the env:LTTNG_HOME environment
5618 variable defaults to `$HOME` if not set.
5620 To output LTTng traces to a non-default location:
5622 * Use the opt:lttng-create(1):--output option of the man:lttng-create(1) command:
5627 $ lttng create my-session --output=/tmp/some-directory
5631 You may create as many tracing sessions as you wish.
5633 To list all the existing tracing sessions for your Unix user:
5635 * Use the man:lttng-list(1) command:
5644 When you create a tracing session, it is set as the _current tracing
5645 session_. The following man:lttng(1) commands operate on the current
5646 tracing session when you don't specify one:
5648 [role="list-3-cols"]
5665 To change the current tracing session:
5667 * Use the man:lttng-set-session(1) command:
5672 $ lttng set-session new-session
5676 Replace `new-session` by the name of the new current tracing session.
5678 When you are done tracing in a given tracing session, you can destroy
5679 it. This operation frees the resources taken by the tracing session
5680 to destroy; it does not destroy the trace data that LTTng wrote for
5681 this tracing session.
5683 To destroy the current tracing session:
5685 * Use the man:lttng-destroy(1) command:
5695 [[list-instrumentation-points]]
5696 === List the available instrumentation points
5698 The <<lttng-sessiond,session daemon>> can query the running instrumented
5699 user applications and the Linux kernel to get a list of available
5700 instrumentation points. For the Linux kernel <<domain,tracing domain>>,
5701 they are tracepoints and system calls. For the user space tracing
5702 domain, they are tracepoints. For the other tracing domains, they are
5705 To list the available instrumentation points:
5707 * Use the man:lttng-list(1) command with the requested tracing domain's
5711 * opt:lttng-list(1):--kernel: Linux kernel tracepoints (your Unix user
5712 must be a root user, or it must be a member of the
5713 <<tracing-group,tracing group>>).
5714 * opt:lttng-list(1):--kernel with opt:lttng-list(1):--syscall: Linux
5715 kernel system calls (your Unix user must be a root user, or it must be
5716 a member of the tracing group).
5717 * opt:lttng-list(1):--userspace: user space tracepoints.
5718 * opt:lttng-list(1):--jul: `java.util.logging` loggers.
5719 * opt:lttng-list(1):--log4j: Apache log4j loggers.
5720 * opt:lttng-list(1):--python: Python loggers.
5723 .List the available user space tracepoints.
5727 $ lttng list --userspace
5731 .List the available Linux kernel system call tracepoints.
5735 $ lttng list --kernel --syscall
5740 [[enabling-disabling-events]]
5741 === Create and enable an event rule
5743 Once you <<creating-destroying-tracing-sessions,create a tracing
5744 session>>, you can create <<event,event rules>> with the
5745 man:lttng-enable-event(1) command.
5747 You specify each condition with a command-line option. The available
5748 condition options are shown in the following table.
5750 [role="growable",cols="asciidoc,asciidoc,default"]
5751 .Condition command-line options for the man:lttng-enable-event(1) command.
5753 |Option |Description |Applicable tracing domains
5759 . +--probe=__ADDR__+
5760 . +--function=__ADDR__+
5763 Instead of using the default _tracepoint_ instrumentation type, use:
5765 . A Linux system call.
5766 . A Linux https://lwn.net/Articles/132196/[KProbe] (symbol or address).
5767 . The entry and return points of a Linux function (symbol or address).
5771 |First positional argument.
5774 Tracepoint or system call name. In the case of a Linux KProbe or
5775 function, this is a custom name given to the event rule. With the
5776 JUL, log4j, and Python domains, this is a logger name.
5778 With a tracepoint, logger, or system call name, the last character
5779 can be `*` to match anything that remains.
5786 . +--loglevel=__LEVEL__+
5787 . +--loglevel-only=__LEVEL__+
5790 . Match only tracepoints or log statements with a logging level at
5791 least as severe as +__LEVEL__+.
5792 . Match only tracepoints or log statements with a logging level
5793 equal to +__LEVEL__+.
5795 See man:lttng-enable-event(1) for the list of available logging level
5798 |User space, JUL, log4j, and Python.
5800 |+--exclude=__EXCLUSIONS__+
5803 When you use a `*` character at the end of the tracepoint or logger
5804 name (first positional argument), exclude the specific names in the
5805 comma-delimited list +__EXCLUSIONS__+.
5808 User space, JUL, log4j, and Python.
5810 |+--filter=__EXPR__+
5813 Match only events which satisfy the expression +__EXPR__+.
5815 See man:lttng-enable-event(1) to learn more about the syntax of a
5822 You attach an event rule to a <<channel,channel>> on creation. If you do
5823 not specify the channel with the opt:lttng-enable-event(1):--channel
5824 option, and if the event rule to create is the first in its
5825 <<domain,tracing domain>> for a given tracing session, then LTTng
5826 creates a _default channel_ for you. This default channel is reused in
5827 subsequent invocations of the man:lttng-enable-event(1) command for the
5828 same tracing domain.
5830 An event rule is always enabled at creation time.
5832 The following examples show how you can combine the previous
5833 command-line options to create simple to more complex event rules.
5835 .Create an event rule targetting a Linux kernel tracepoint (default channel).
5839 $ lttng enable-event --kernel sched_switch
5843 .Create an event rule matching four Linux kernel system calls (default channel).
5847 $ lttng enable-event --kernel --syscall open,write,read,close
5851 .Create event rules matching tracepoints with filter expressions (default channel).
5855 $ lttng enable-event --kernel sched_switch --filter='prev_comm == "bash"'
5860 $ lttng enable-event --kernel --all \
5861 --filter='$ctx.tid == 1988 || $ctx.tid == 1534'
5866 $ lttng enable-event --jul my_logger \
5867 --filter='$app.retriever:cur_msg_id > 3'
5870 IMPORTANT: Make sure to always quote the filter string when you
5871 use man:lttng(1) from a shell.
5874 .Create an event rule matching any user space tracepoint of a given tracepoint provider with a log level range (default channel).
5878 $ lttng enable-event --userspace my_app:'*' --loglevel=TRACE_INFO
5881 IMPORTANT: Make sure to always quote the wildcard character when you
5882 use man:lttng(1) from a shell.
5885 .Create an event rule matching multiple Python loggers with a wildcard and with exclusions (default channel).
5889 $ lttng enable-event --python my-app.'*' \
5890 --exclude='my-app.module,my-app.hello'
5894 .Create an event rule matching any Apache log4j logger with a specific log level (default channel).
5898 $ lttng enable-event --log4j --all --loglevel-only=LOG4J_WARN
5902 .Create an event rule attached to a specific channel matching a specific user space tracepoint provider and tracepoint.
5906 $ lttng enable-event --userspace my_app:my_tracepoint --channel=my-channel
5910 The event rules of a given channel form a whitelist: as soon as an
5911 emitted event passes one of them, LTTng can record the event. For
5912 example, an event named `my_app:my_tracepoint` emitted from a user space
5913 tracepoint with a `TRACE_ERROR` log level passes both of the following
5918 $ lttng enable-event --userspace my_app:my_tracepoint
5919 $ lttng enable-event --userspace my_app:my_tracepoint \
5920 --loglevel=TRACE_INFO
5923 The second event rule is redundant: the first one includes
5927 [[disable-event-rule]]
5928 === Disable an event rule
5930 To disable an event rule that you <<enabling-disabling-events,created>>
5931 previously, use the man:lttng-disable-event(1) command. This command
5932 disables _all_ the event rules (of a given tracing domain and channel)
5933 which match an instrumentation point. The other conditions are not
5934 supported as of LTTng{nbsp}{revision}.
5936 The LTTng tracer does not record an emitted event which passes
5937 a _disabled_ event rule.
5939 .Disable an event rule matching a Python logger (default channel).
5943 $ lttng disable-event --python my-logger
5947 .Disable an event rule matching all `java.util.logging` loggers (default channel).
5951 $ lttng disable-event --jul '*'
5955 .Disable _all_ the event rules of the default channel.
5957 The opt:lttng-disable-event(1):--all-events option is not, like the
5958 opt:lttng-enable-event(1):--all option of man:lttng-enable-event(1), the
5959 equivalent of the event name `*` (wildcard): it disables _all_ the event
5960 rules of a given channel.
5964 $ lttng disable-event --jul --all-events
5968 NOTE: You cannot delete an event rule once you create it.
5972 === Get the status of a tracing session
5974 To get the status of the current tracing session, that is, its
5975 parameters, its channels, event rules, and their attributes:
5977 * Use the man:lttng-status(1) command:
5987 To get the status of any tracing session:
5989 * Use the man:lttng-list(1) command with the tracing session's name:
5994 $ lttng list my-session
5998 Replace `my-session` with the desired tracing session's name.
6001 [[basic-tracing-session-control]]
6002 === Start and stop a tracing session
6004 Once you <<creating-destroying-tracing-sessions,create a tracing
6006 <<enabling-disabling-events,create one or more event rules>>,
6007 you can start and stop the tracers for this tracing session.
6009 To start tracing in the current tracing session:
6011 * Use the man:lttng-start(1) command:
6020 LTTng is very flexible: you can launch user applications before
6021 or after the you start the tracers. The tracers only record the events
6022 if they pass enabled event rules and if they occur while the tracers are
6025 To stop tracing in the current tracing session:
6027 * Use the man:lttng-stop(1) command:
6036 If there were <<channel-overwrite-mode-vs-discard-mode,lost event
6037 records>> or lost sub-buffers since the last time you ran
6038 man:lttng-start(1), warnings are printed when you run the
6039 man:lttng-stop(1) command.
6042 [[enabling-disabling-channels]]
6043 === Create a channel
6045 Once you create a tracing session, you can create a <<channel,channel>>
6046 with the man:lttng-enable-channel(1) command.
6048 Note that LTTng automatically creates a default channel when, for a
6049 given <<domain,tracing domain>>, no channels exist and you
6050 <<enabling-disabling-events,create>> the first event rule. This default
6051 channel is named `channel0` and its attributes are set to reasonable
6052 values. Therefore, you only need to create a channel when you need
6053 non-default attributes.
6055 You specify each non-default channel attribute with a command-line
6056 option when you use the man:lttng-enable-channel(1) command. The
6057 available command-line options are:
6059 [role="growable",cols="asciidoc,asciidoc"]
6060 .Command-line options for the man:lttng-enable-channel(1) command.
6062 |Option |Description
6068 <<channel-overwrite-mode-vs-discard-mode,event loss mode>> instead of
6069 the default _discard_ mode.
6071 |`--buffers-pid` (user space tracing domain only)
6074 Use the per-process <<channel-buffering-schemes,buffering scheme>>
6075 instead of the default per-user buffering scheme.
6077 |+--subbuf-size=__SIZE__+
6080 Allocate sub-buffers of +__SIZE__+ bytes (power of two), for each CPU,
6081 either for each Unix user (default), or for each instrumented process.
6083 See <<channel-subbuf-size-vs-subbuf-count,Sub-buffer count and size>>.
6085 |+--num-subbuf=__COUNT__+
6088 Allocate +__COUNT__+ sub-buffers (power of two), for each CPU, either
6089 for each Unix user (default), or for each instrumented process.
6091 See <<channel-subbuf-size-vs-subbuf-count,Sub-buffer count and size>>.
6093 |+--tracefile-size=__SIZE__+
6096 Set the maximum size of each trace file that this channel writes within
6097 a stream to +__SIZE__+ bytes instead of no maximum.
6099 See <<tracefile-rotation,Trace file count and size>>.
6101 |+--tracefile-count=__COUNT__+
6104 Limit the number of trace files that this channel creates to
6105 +__COUNT__+ channels instead of no limit.
6107 See <<tracefile-rotation,Trace file count and size>>.
6109 |+--switch-timer=__PERIODUS__+
6112 Set the <<channel-switch-timer,switch timer period>>
6113 to +__PERIODUS__+{nbsp}µs.
6115 |+--read-timer=__PERIODUS__+
6118 Set the <<channel-read-timer,read timer period>>
6119 to +__PERIODUS__+{nbsp}µs.
6121 |[[opt-blocking-timeout]]+--blocking-timeout=__TIMEOUTUS__+
6124 Set the timeout of user space applications which load LTTng-UST
6125 in blocking mode to +__TIMEOUTUS__+:
6128 Never block (non-blocking mode).
6131 Block forever until space is available in a sub-buffer to record
6134 __n__, a positive value::
6135 Wait for at most __n__ µs when trying to write into a sub-buffer.
6137 Note that, for this option to have any effect on an instrumented
6138 user space application, you need to run the application with a set
6139 env:LTTNG_UST_ALLOW_BLOCKING environment variable.
6141 |+--output=__TYPE__+ (Linux kernel tracing domain only)
6144 Set the channel's output type to +__TYPE__+, either `mmap` or `splice`.
6148 You can only create a channel in the Linux kernel and user space
6149 <<domain,tracing domains>>: other tracing domains have their own channel
6150 created on the fly when <<enabling-disabling-events,creating event
6155 Because of a current LTTng limitation, you must create all channels
6156 _before_ you <<basic-tracing-session-control,start tracing>> in a given
6157 tracing session, that is, before the first time you run
6160 Since LTTng automatically creates a default channel when you use the
6161 man:lttng-enable-event(1) command with a specific tracing domain, you
6162 cannot, for example, create a Linux kernel event rule, start tracing,
6163 and then create a user space event rule, because no user space channel
6164 exists yet and it's too late to create one.
6166 For this reason, make sure to configure your channels properly
6167 before starting the tracers for the first time!
6170 The following examples show how you can combine the previous
6171 command-line options to create simple to more complex channels.
6173 .Create a Linux kernel channel with default attributes.
6177 $ lttng enable-channel --kernel my-channel
6181 .Create a user space channel with 4 sub-buffers or 1{nbsp}MiB each, per CPU, per instrumented process.
6185 $ lttng enable-channel --userspace --num-subbuf=4 --subbuf-size=1M \
6186 --buffers-pid my-channel
6190 .[[blocking-timeout-example]]Create a default user space channel with an infinite blocking timeout.
6192 <<creating-destroying-tracing-sessions,Create a tracing-session>>,
6193 create the channel, <<enabling-disabling-events,create an event rule>>,
6194 and <<basic-tracing-session-control,start tracing>>:
6199 $ lttng enable-channel --userspace --blocking-timeout=inf blocking-channel
6200 $ lttng enable-event --userspace --channel=blocking-channel --all
6204 Run an application instrumented with LTTng-UST and allow it to block:
6208 $ LTTNG_UST_ALLOW_BLOCKING=1 my-app
6212 .Create a Linux kernel channel which rotates 8 trace files of 4{nbsp}MiB each for each stream
6216 $ lttng enable-channel --kernel --tracefile-count=8 \
6217 --tracefile-size=4194304 my-channel
6221 .Create a user space channel in overwrite (or _flight recorder_) mode.
6225 $ lttng enable-channel --userspace --overwrite my-channel
6229 You can <<enabling-disabling-events,create>> the same event rule in
6230 two different channels:
6234 $ lttng enable-event --userspace --channel=my-channel app:tp
6235 $ lttng enable-event --userspace --channel=other-channel app:tp
6238 If both channels are enabled, when a tracepoint named `app:tp` is
6239 reached, LTTng records two events, one for each channel.
6243 === Disable a channel
6245 To disable a specific channel that you <<enabling-disabling-channels,created>>
6246 previously, use the man:lttng-disable-channel(1) command.
6248 .Disable a specific Linux kernel channel.
6252 $ lttng disable-channel --kernel my-channel
6256 The state of a channel precedes the individual states of event rules
6257 attached to it: event rules which belong to a disabled channel, even if
6258 they are enabled, are also considered disabled.
6262 === Add context fields to a channel
6264 Event record fields in trace files provide important information about
6265 events that occured previously, but sometimes some external context may
6266 help you solve a problem faster. Examples of context fields are:
6268 * The **process ID**, **thread ID**, **process name**, and
6269 **process priority** of the thread in which the event occurs.
6270 * The **hostname** of the system on which the event occurs.
6271 * The current values of many possible **performance counters** using
6273 ** CPU cycles, stalled cycles, idle cycles, and the other cycle types.
6275 ** Branch instructions, misses, and loads.
6277 * Any context defined at the application level (supported for the
6278 JUL and log4j <<domain,tracing domains>>).
6280 To get the full list of available context fields, see
6281 `lttng add-context --list`. Some context fields are reserved for a
6282 specific <<domain,tracing domain>> (Linux kernel or user space).
6284 You add context fields to <<channel,channels>>. All the events
6285 that a channel with added context fields records contain those fields.
6287 To add context fields to one or all the channels of a given tracing
6290 * Use the man:lttng-add-context(1) command.
6292 .Add context fields to all the channels of the current tracing session.
6294 The following command line adds the virtual process identifier and
6295 the per-thread CPU cycles count fields to all the user space channels
6296 of the current tracing session.
6300 $ lttng add-context --userspace --type=vpid --type=perf:thread:cpu-cycles
6304 .Add performance counter context fields by raw ID
6306 See man:lttng-add-context(1) for the exact format of the context field
6307 type, which is partly compatible with the format used in
6312 $ lttng add-context --userspace --type=perf:thread:raw:r0110:test
6313 $ lttng add-context --kernel --type=perf:cpu:raw:r0013c:x86unhalted
6317 .Add a context field to a specific channel.
6319 The following command line adds the thread identifier context field
6320 to the Linux kernel channel named `my-channel` in the current
6325 $ lttng add-context --kernel --channel=my-channel --type=tid
6329 .Add an application-specific context field to a specific channel.
6331 The following command line adds the `cur_msg_id` context field of the
6332 `retriever` context retriever for all the instrumented
6333 <<java-application,Java applications>> recording <<event,event records>>
6334 in the channel named `my-channel`:
6338 $ lttng add-context --kernel --channel=my-channel \
6339 --type='$app:retriever:cur_msg_id'
6342 IMPORTANT: Make sure to always quote the `$` character when you
6343 use man:lttng-add-context(1) from a shell.
6346 NOTE: You cannot remove context fields from a channel once you add it.
6351 === Track process IDs
6353 It's often useful to allow only specific process IDs (PIDs) to emit
6354 events. For example, you may wish to record all the system calls made by
6355 a given process (Ă la http://linux.die.net/man/1/strace[strace]).
6357 The man:lttng-track(1) and man:lttng-untrack(1) commands serve this
6358 purpose. Both commands operate on a whitelist of process IDs. You _add_
6359 entries to this whitelist with the man:lttng-track(1) command and remove
6360 entries with the man:lttng-untrack(1) command. Any process which has one
6361 of the PIDs in the whitelist is allowed to emit LTTng events which pass
6362 an enabled <<event,event rule>>.
6364 NOTE: The PID tracker tracks the _numeric process IDs_. Should a
6365 process with a given tracked ID exit and another process be given this
6366 ID, then the latter would also be allowed to emit events.
6368 .Track and untrack process IDs.
6370 For the sake of the following example, assume the target system has 16
6374 <<creating-destroying-tracing-sessions,create a tracing session>>,
6375 the whitelist contains all the possible PIDs:
6378 .All PIDs are tracked.
6379 image::track-all.png[]
6381 When the whitelist is full and you use the man:lttng-track(1) command to
6382 specify some PIDs to track, LTTng first clears the whitelist, then it
6383 tracks the specific PIDs. After:
6387 $ lttng track --pid=3,4,7,10,13
6393 .PIDs 3, 4, 7, 10, and 13 are tracked.
6394 image::track-3-4-7-10-13.png[]
6396 You can add more PIDs to the whitelist afterwards:
6400 $ lttng track --pid=1,15,16
6406 .PIDs 1, 15, and 16 are added to the whitelist.
6407 image::track-1-3-4-7-10-13-15-16.png[]
6409 The man:lttng-untrack(1) command removes entries from the PID tracker's
6410 whitelist. Given the previous example, the following command:
6414 $ lttng untrack --pid=3,7,10,13
6417 leads to this whitelist:
6420 .PIDs 3, 7, 10, and 13 are removed from the whitelist.
6421 image::track-1-4-15-16.png[]
6423 LTTng can track all possible PIDs again using the opt:track(1):--all
6428 $ lttng track --pid --all
6431 The result is, again:
6434 .All PIDs are tracked.
6435 image::track-all.png[]
6438 .Track only specific PIDs
6440 A very typical use case with PID tracking is to start with an empty
6441 whitelist, then <<basic-tracing-session-control,start the tracers>>, and
6442 then add PIDs manually while tracers are active. You can accomplish this
6443 by using the opt:lttng-untrack(1):--all option of the
6444 man:lttng-untrack(1) command to clear the whitelist after you
6445 <<creating-destroying-tracing-sessions,create a tracing session>>:
6449 $ lttng untrack --pid --all
6455 .No PIDs are tracked.
6456 image::untrack-all.png[]
6458 If you trace with this whitelist configuration, the tracer records no
6459 events for this <<domain,tracing domain>> because no processes are
6460 tracked. You can use the man:lttng-track(1) command as usual to track
6461 specific PIDs, for example:
6465 $ lttng track --pid=6,11
6471 .PIDs 6 and 11 are tracked.
6472 image::track-6-11.png[]
6477 [[saving-loading-tracing-session]]
6478 === Save and load tracing session configurations
6480 Configuring a <<tracing-session,tracing session>> can be long. Some of
6481 the tasks involved are:
6483 * <<enabling-disabling-channels,Create channels>> with
6484 specific attributes.
6485 * <<adding-context,Add context fields>> to specific channels.
6486 * <<enabling-disabling-events,Create event rules>> with specific log
6487 level and filter conditions.
6489 If you use LTTng to solve real world problems, chances are you have to
6490 record events using the same tracing session setup over and over,
6491 modifying a few variables each time in your instrumented program
6492 or environment. To avoid constant tracing session reconfiguration,
6493 the man:lttng(1) command-line tool can save and load tracing session
6494 configurations to/from XML files.
6496 To save a given tracing session configuration:
6498 * Use the man:lttng-save(1) command:
6503 $ lttng save my-session
6507 Replace `my-session` with the name of the tracing session to save.
6509 LTTng saves tracing session configurations to
6510 dir:{$LTTNG_HOME/.lttng/sessions} by default. Note that the
6511 env:LTTNG_HOME environment variable defaults to `$HOME` if not set. Use
6512 the opt:lttng-save(1):--output-path option to change this destination
6515 LTTng saves all configuration parameters, for example:
6517 * The tracing session name.
6518 * The trace data output path.
6519 * The channels with their state and all their attributes.
6520 * The context fields you added to channels.
6521 * The event rules with their state, log level and filter conditions.
6523 To load a tracing session:
6525 * Use the man:lttng-load(1) command:
6530 $ lttng load my-session
6534 Replace `my-session` with the name of the tracing session to load.
6536 When LTTng loads a configuration, it restores your saved tracing session
6537 as if you just configured it manually.
6539 See man:lttng(1) for the complete list of command-line options. You
6540 can also save and load all many sessions at a time, and decide in which
6541 directory to output the XML files.
6544 [[sending-trace-data-over-the-network]]
6545 === Send trace data over the network
6547 LTTng can send the recorded trace data to a remote system over the
6548 network instead of writing it to the local file system.
6550 To send the trace data over the network:
6552 . On the _remote_ system (which can also be the target system),
6553 start an LTTng <<lttng-relayd,relay daemon>> (man:lttng-relayd(8)):
6562 . On the _target_ system, create a tracing session configured to
6563 send trace data over the network:
6568 $ lttng create my-session --set-url=net://remote-system
6572 Replace `remote-system` by the host name or IP address of the
6573 remote system. See man:lttng-create(1) for the exact URL format.
6575 . On the target system, use the man:lttng(1) command-line tool as usual.
6576 When tracing is active, the target's consumer daemon sends sub-buffers
6577 to the relay daemon running on the remote system instead of flushing
6578 them to the local file system. The relay daemon writes the received
6579 packets to the local file system.
6581 The relay daemon writes trace files to
6582 +$LTTNG_HOME/lttng-traces/__hostname__/__session__+ by default, where
6583 +__hostname__+ is the host name of the target system and +__session__+
6584 is the tracing session name. Note that the env:LTTNG_HOME environment
6585 variable defaults to `$HOME` if not set. Use the
6586 opt:lttng-relayd(8):--output option of man:lttng-relayd(8) to write
6587 trace files to another base directory.
6592 === View events as LTTng emits them (noch:{LTTng} live)
6594 LTTng live is a network protocol implemented by the <<lttng-relayd,relay
6595 daemon>> (man:lttng-relayd(8)) to allow compatible trace viewers to
6596 display events as LTTng emits them on the target system while tracing is
6599 The relay daemon creates a _tee_: it forwards the trace data to both
6600 the local file system and to connected live viewers:
6603 .The relay daemon creates a _tee_, forwarding the trace data to both trace files and a connected live viewer.
6608 . On the _target system_, create a <<tracing-session,tracing session>>
6614 $ lttng create my-session --live
6618 This spawns a local relay daemon.
6620 . Start the live viewer and configure it to connect to the relay
6621 daemon. For example, with http://diamon.org/babeltrace[Babeltrace]:
6626 $ babeltrace --input-format=lttng-live \
6627 net://localhost/host/hostname/my-session
6634 * `hostname` with the host name of the target system.
6635 * `my-session` with the name of the tracing session to view.
6638 . Configure the tracing session as usual with the man:lttng(1)
6639 command-line tool, and <<basic-tracing-session-control,start tracing>>.
6641 You can list the available live tracing sessions with Babeltrace:
6645 $ babeltrace --input-format=lttng-live net://localhost
6648 You can start the relay daemon on another system. In this case, you need
6649 to specify the relay daemon's URL when you create the tracing session
6650 with the opt:lttng-create(1):--set-url option. You also need to replace
6651 `localhost` in the procedure above with the host name of the system on
6652 which the relay daemon is running.
6654 See man:lttng-create(1) and man:lttng-relayd(8) for the complete list of
6655 command-line options.
6659 [[taking-a-snapshot]]
6660 === Take a snapshot of the current sub-buffers of a tracing session
6662 The normal behavior of LTTng is to append full sub-buffers to growing
6663 trace data files. This is ideal to keep a full history of the events
6664 that occurred on the target system, but it can
6665 represent too much data in some situations. For example, you may wish
6666 to trace your application continuously until some critical situation
6667 happens, in which case you only need the latest few recorded
6668 events to perform the desired analysis, not multi-gigabyte trace files.
6670 With the man:lttng-snapshot(1) command, you can take a snapshot of the
6671 current sub-buffers of a given <<tracing-session,tracing session>>.
6672 LTTng can write the snapshot to the local file system or send it over
6677 . Create a tracing session in _snapshot mode_:
6682 $ lttng create my-session --snapshot
6686 The <<channel-overwrite-mode-vs-discard-mode,event loss mode>> of
6687 <<channel,channels>> created in this mode is automatically set to
6688 _overwrite_ (flight recorder mode).
6690 . Configure the tracing session as usual with the man:lttng(1)
6691 command-line tool, and <<basic-tracing-session-control,start tracing>>.
6693 . **Optional**: When you need to take a snapshot,
6694 <<basic-tracing-session-control,stop tracing>>.
6696 You can take a snapshot when the tracers are active, but if you stop
6697 them first, you are sure that the data in the sub-buffers does not
6698 change before you actually take the snapshot.
6705 $ lttng snapshot record --name=my-first-snapshot
6709 LTTng writes the current sub-buffers of all the current tracing
6710 session's channels to trace files on the local file system. Those trace
6711 files have `my-first-snapshot` in their name.
6713 There is no difference between the format of a normal trace file and the
6714 format of a snapshot: viewers of LTTng traces also support LTTng
6717 By default, LTTng writes snapshot files to the path shown by
6718 `lttng snapshot list-output`. You can change this path or decide to send
6719 snapshots over the network using either:
6721 . An output path or URL that you specify when you create the
6723 . An snapshot output path or URL that you add using
6724 `lttng snapshot add-output`
6725 . An output path or URL that you provide directly to the
6726 `lttng snapshot record` command.
6728 Method 3 overrides method 2, which overrides method 1. When you
6729 specify a URL, a relay daemon must listen on a remote system (see
6730 <<sending-trace-data-over-the-network,Send trace data over the network>>).
6735 === Use the machine interface
6737 With any command of the man:lttng(1) command-line tool, you can set the
6738 opt:lttng(1):--mi option to `xml` (before the command name) to get an
6739 XML machine interface output, for example:
6743 $ lttng --mi=xml enable-event --kernel --syscall open
6746 A schema definition (XSD) is
6747 https://github.com/lttng/lttng-tools/blob/stable-2.10/src/common/mi-lttng-3.0.xsd[available]
6748 to ease the integration with external tools as much as possible.
6752 [[metadata-regenerate]]
6753 === Regenerate the metadata of an LTTng trace
6755 An LTTng trace, which is a http://diamon.org/ctf[CTF] trace, has both
6756 data stream files and a metadata file. This metadata file contains,
6757 amongst other things, information about the offset of the clock sources
6758 used to timestamp <<event,event records>> when tracing.
6760 If, once a <<tracing-session,tracing session>> is
6761 <<basic-tracing-session-control,started>>, a major
6762 https://en.wikipedia.org/wiki/Network_Time_Protocol[NTP] correction
6763 happens, the trace's clock offset also needs to be updated. You
6764 can use the `metadata` item of the man:lttng-regenerate(1) command
6767 The main use case of this command is to allow a system to boot with
6768 an incorrect wall time and trace it with LTTng before its wall time
6769 is corrected. Once the system is known to be in a state where its
6770 wall time is correct, it can run `lttng regenerate metadata`.
6772 To regenerate the metadata of an LTTng trace:
6774 * Use the `metadata` item of the man:lttng-regenerate(1) command:
6779 $ lttng regenerate metadata
6785 `lttng regenerate metadata` has the following limitations:
6787 * Tracing session <<creating-destroying-tracing-sessions,created>>
6789 * User space <<channel,channels>>, if any, are using
6790 <<channel-buffering-schemes,per-user buffering>>.
6795 [[regenerate-statedump]]
6796 === Regenerate the state dump of a tracing session
6798 The LTTng kernel and user space tracers generate state dump
6799 <<event,event records>> when the application starts or when you
6800 <<basic-tracing-session-control,start a tracing session>>. An analysis
6801 can use the state dump event records to set an initial state before it
6802 builds the rest of the state from the following event records.
6803 http://tracecompass.org/[Trace Compass] is a notable example of an
6804 application which uses the state dump of an LTTng trace.
6806 When you <<taking-a-snapshot,take a snapshot>>, it's possible that the
6807 state dump event records are not included in the snapshot because they
6808 were recorded to a sub-buffer that has been consumed or overwritten
6811 You can use the `lttng regenerate statedump` command to emit the state
6812 dump event records again.
6814 To regenerate the state dump of the current tracing session, provided
6815 create it in snapshot mode, before you take a snapshot:
6817 . Use the `statedump` item of the man:lttng-regenerate(1) command:
6822 $ lttng regenerate statedump
6826 . <<basic-tracing-session-control,Stop the tracing session>>:
6835 . <<taking-a-snapshot,Take a snapshot>>:
6840 $ lttng snapshot record --name=my-snapshot
6844 Depending on the event throughput, you should run steps 1 and 2
6845 as closely as possible.
6847 NOTE: To record the state dump events, you need to
6848 <<enabling-disabling-events,create event rules>> which enable them.
6849 LTTng-UST state dump tracepoints start with `lttng_ust_statedump:`.
6850 LTTng-modules state dump tracepoints start with `lttng_statedump_`.
6854 [[persistent-memory-file-systems]]
6855 === Record trace data on persistent memory file systems
6857 https://en.wikipedia.org/wiki/Non-volatile_random-access_memory[Non-volatile random-access memory]
6858 (NVRAM) is random-access memory that retains its information when power
6859 is turned off (non-volatile). Systems with such memory can store data
6860 structures in RAM and retrieve them after a reboot, without flushing
6861 to typical _storage_.
6863 Linux supports NVRAM file systems thanks to either
6864 http://pramfs.sourceforge.net/[PRAMFS] or
6865 https://www.kernel.org/doc/Documentation/filesystems/dax.txt[DAX]{nbsp}+{nbsp}http://lkml.iu.edu/hypermail/linux/kernel/1504.1/03463.html[pmem]
6866 (requires Linux 4.1+).
6868 This section does not describe how to operate such file systems;
6869 we assume that you have a working persistent memory file system.
6871 When you create a <<tracing-session,tracing session>>, you can specify
6872 the path of the shared memory holding the sub-buffers. If you specify a
6873 location on an NVRAM file system, then you can retrieve the latest
6874 recorded trace data when the system reboots after a crash.
6876 To record trace data on a persistent memory file system and retrieve the
6877 trace data after a system crash:
6879 . Create a tracing session with a sub-buffer shared memory path located
6880 on an NVRAM file system:
6885 $ lttng create my-session --shm-path=/path/to/shm
6889 . Configure the tracing session as usual with the man:lttng(1)
6890 command-line tool, and <<basic-tracing-session-control,start tracing>>.
6892 . After a system crash, use the man:lttng-crash(1) command-line tool to
6893 view the trace data recorded on the NVRAM file system:
6898 $ lttng-crash /path/to/shm
6902 The binary layout of the ring buffer files is not exactly the same as
6903 the trace files layout. This is why you need to use man:lttng-crash(1)
6904 instead of your preferred trace viewer directly.
6906 To convert the ring buffer files to LTTng trace files:
6908 * Use the opt:lttng-crash(1):--extract option of man:lttng-crash(1):
6913 $ lttng-crash --extract=/path/to/trace /path/to/shm
6919 [[notif-trigger-api]]
6920 === Get notified when a channel's buffer usage is too high or too low
6922 With LTTng's $$C/C++$$ notification and trigger API, your user
6923 application can get notified when the buffer usage of one or more
6924 <<channel,channels>> becomes too low or too high. You can use this API
6925 and enable or disable <<event,event rules>> during tracing to avoid
6926 <<channel-overwrite-mode-vs-discard-mode,discarded event records>>.
6928 .Have a user application get notified when an LTTng channel's buffer usage is too high.
6930 In this example, we create and build an application which gets notified
6931 when the buffer usage of a specific LTTng channel is higher than
6932 75{nbsp}%. We only print that it is the case in the example, but we
6933 could as well use the API of <<liblttng-ctl-lttng,`liblttng-ctl`>> to
6934 disable event rules when this happens.
6936 . Create the application's C source file:
6944 #include <lttng/domain.h>
6945 #include <lttng/action/action.h>
6946 #include <lttng/action/notify.h>
6947 #include <lttng/condition/condition.h>
6948 #include <lttng/condition/buffer-usage.h>
6949 #include <lttng/condition/evaluation.h>
6950 #include <lttng/notification/channel.h>
6951 #include <lttng/notification/notification.h>
6952 #include <lttng/trigger/trigger.h>
6953 #include <lttng/endpoint.h>
6955 int main(int argc, char *argv[])
6957 int exit_status = 0;
6958 struct lttng_notification_channel *notification_channel;
6959 struct lttng_condition *condition;
6960 struct lttng_action *action;
6961 struct lttng_trigger *trigger;
6962 const char *tracing_session_name;
6963 const char *channel_name;
6966 tracing_session_name = argv[1];
6967 channel_name = argv[2];
6970 * Create a notification channel. A notification channel
6971 * connects the user application to the LTTng session daemon.
6972 * This notification channel can be used to listen to various
6973 * types of notifications.
6975 notification_channel = lttng_notification_channel_create(
6976 lttng_session_daemon_notification_endpoint);
6979 * Create a "high buffer usage" condition. In this case, the
6980 * condition is reached when the buffer usage is greater than or
6981 * equal to 75 %. We create the condition for a specific tracing
6982 * session name, channel name, and for the user space tracing
6985 * The "low buffer usage" condition type also exists.
6987 condition = lttng_condition_buffer_usage_high_create();
6988 lttng_condition_buffer_usage_set_threshold_ratio(condition, .75);
6989 lttng_condition_buffer_usage_set_session_name(
6990 condition, tracing_session_name);
6991 lttng_condition_buffer_usage_set_channel_name(condition,
6993 lttng_condition_buffer_usage_set_domain_type(condition,
6997 * Create an action (get a notification) to take when the
6998 * condition created above is reached.
7000 action = lttng_action_notify_create();
7003 * Create a trigger. A trigger associates a condition to an
7004 * action: the action is executed when the condition is reached.
7006 trigger = lttng_trigger_create(condition, action);
7008 /* Register the trigger to LTTng. */
7009 lttng_register_trigger(trigger);
7012 * Now that we have registered a trigger, a notification will be
7013 * emitted everytime its condition is met. To receive this
7014 * notification, we must subscribe to notifications that match
7015 * the same condition.
7017 lttng_notification_channel_subscribe(notification_channel,
7021 * Notification loop. You can put this in a dedicated thread to
7022 * avoid blocking the main thread.
7025 struct lttng_notification *notification;
7026 enum lttng_notification_channel_status status;
7027 const struct lttng_evaluation *notification_evaluation;
7028 const struct lttng_condition *notification_condition;
7029 double buffer_usage;
7031 /* Receive the next notification. */
7032 status = lttng_notification_channel_get_next_notification(
7033 notification_channel, ¬ification);
7036 case LTTNG_NOTIFICATION_CHANNEL_STATUS_OK:
7038 case LTTNG_NOTIFICATION_CHANNEL_STATUS_NOTIFICATIONS_DROPPED:
7040 * The session daemon can drop notifications if
7041 * a monitoring application is not consuming the
7042 * notifications fast enough.
7045 case LTTNG_NOTIFICATION_CHANNEL_STATUS_CLOSED:
7047 * The notification channel has been closed by the
7048 * session daemon. This is typically caused by a session
7049 * daemon shutting down.
7053 /* Unhandled conditions or errors. */
7059 * A notification provides, amongst other things:
7061 * * The condition that caused this notification to be
7063 * * The condition evaluation, which provides more
7064 * specific information on the evaluation of the
7067 * The condition evaluation provides the buffer usage
7068 * value at the moment the condition was reached.
7070 notification_condition = lttng_notification_get_condition(
7072 notification_evaluation = lttng_notification_get_evaluation(
7075 /* We're subscribed to only one condition. */
7076 assert(lttng_condition_get_type(notification_condition) ==
7077 LTTNG_CONDITION_TYPE_BUFFER_USAGE_HIGH);
7080 * Get the exact sampled buffer usage from the
7081 * condition evaluation.
7083 lttng_evaluation_buffer_usage_get_usage_ratio(
7084 notification_evaluation, &buffer_usage);
7087 * At this point, instead of printing a message, we
7088 * could do something to reduce the channel's buffer
7089 * usage, like disable specific events.
7091 printf("Buffer usage is %f %% in tracing session \"%s\", "
7092 "user space channel \"%s\".\n", buffer_usage * 100,
7093 tracing_session_name, channel_name);
7094 lttng_notification_destroy(notification);
7098 lttng_action_destroy(action);
7099 lttng_condition_destroy(condition);
7100 lttng_trigger_destroy(trigger);
7101 lttng_notification_channel_destroy(notification_channel);
7107 . Build the `notif-app` application, linking it to `liblttng-ctl`:
7112 $ gcc -o notif-app notif-app.c -llttng-ctl
7116 . <<creating-destroying-tracing-sessions,Create a tracing session>>,
7117 <<enabling-disabling-events,create an event rule>> matching all the
7118 user space tracepoints, and
7119 <<basic-tracing-session-control,start tracing>>:
7124 $ lttng create my-session
7125 $ lttng enable-event --userspace --all
7130 If you create the channel manually with the man:lttng-enable-channel(1)
7131 command, you can control how frequently are the current values of the
7132 channel's properties sampled to evaluate user conditions with the
7133 opt:lttng-enable-channel(1):--monitor-timer option.
7135 . Run the `notif-app` application. This program accepts the
7136 <<tracing-session,tracing session>> name and the user space channel
7137 name as its two first arguments. The channel which LTTng automatically
7138 creates with the man:lttng-enable-event(1) command above is named
7144 $ ./notif-app my-session channel0
7148 . In another terminal, run an application with a very high event
7149 throughput so that the 75{nbsp}% buffer usage condition is reached.
7151 In the first terminal, the application should print lines like this:
7154 Buffer usage is 81.45197 % in tracing session "my-session", user space
7158 If you don't see anything, try modifying the condition in
7159 path:{notif-app.c} to a lower value (0.1, for example), rebuilding it
7160 (step 2) and running it again (step 4).
7167 [[lttng-modules-ref]]
7168 === noch:{LTTng-modules}
7172 [[lttng-tracepoint-enum]]
7173 ==== `LTTNG_TRACEPOINT_ENUM()` usage
7175 Use the `LTTNG_TRACEPOINT_ENUM()` macro to define an enumeration:
7179 LTTNG_TRACEPOINT_ENUM(name, TP_ENUM_VALUES(entries))
7184 * `name` with the name of the enumeration (C identifier, unique
7185 amongst all the defined enumerations).
7186 * `entries` with a list of enumeration entries.
7188 The available enumeration entry macros are:
7190 +ctf_enum_value(__name__, __value__)+::
7191 Entry named +__name__+ mapped to the integral value +__value__+.
7193 +ctf_enum_range(__name__, __begin__, __end__)+::
7194 Entry named +__name__+ mapped to the range of integral values between
7195 +__begin__+ (included) and +__end__+ (included).
7197 +ctf_enum_auto(__name__)+::
7198 Entry named +__name__+ mapped to the integral value following the
7199 last mapping's value.
7201 The last value of a `ctf_enum_value()` entry is its +__value__+
7204 The last value of a `ctf_enum_range()` entry is its +__end__+ parameter.
7206 If `ctf_enum_auto()` is the first entry in the list, its integral
7209 Use the `ctf_enum()` <<lttng-modules-tp-fields,field definition macro>>
7210 to use a defined enumeration as a tracepoint field.
7212 .Define an enumeration with `LTTNG_TRACEPOINT_ENUM()`.
7216 LTTNG_TRACEPOINT_ENUM(
7219 ctf_enum_auto("AUTO: EXPECT 0")
7220 ctf_enum_value("VALUE: 23", 23)
7221 ctf_enum_value("VALUE: 27", 27)
7222 ctf_enum_auto("AUTO: EXPECT 28")
7223 ctf_enum_range("RANGE: 101 TO 303", 101, 303)
7224 ctf_enum_auto("AUTO: EXPECT 304")
7232 [[lttng-modules-tp-fields]]
7233 ==== Tracepoint fields macros (for `TP_FIELDS()`)
7235 [[tp-fast-assign]][[tp-struct-entry]]The available macros to define
7236 tracepoint fields, which must be listed within `TP_FIELDS()` in
7237 `LTTNG_TRACEPOINT_EVENT()`, are:
7239 [role="func-desc growable",cols="asciidoc,asciidoc"]
7240 .Available macros to define LTTng-modules tracepoint fields
7242 |Macro |Description and parameters
7245 +ctf_integer(__t__, __n__, __e__)+
7247 +ctf_integer_nowrite(__t__, __n__, __e__)+
7249 +ctf_user_integer(__t__, __n__, __e__)+
7251 +ctf_user_integer_nowrite(__t__, __n__, __e__)+
7253 Standard integer, displayed in base 10.
7256 Integer C type (`int`, `long`, `size_t`, ...).
7262 Argument expression.
7265 +ctf_integer_hex(__t__, __n__, __e__)+
7267 +ctf_user_integer_hex(__t__, __n__, __e__)+
7269 Standard integer, displayed in base 16.
7278 Argument expression.
7280 |+ctf_integer_oct(__t__, __n__, __e__)+
7282 Standard integer, displayed in base 8.
7291 Argument expression.
7294 +ctf_integer_network(__t__, __n__, __e__)+
7296 +ctf_user_integer_network(__t__, __n__, __e__)+
7298 Integer in network byte order (big-endian), displayed in base 10.
7307 Argument expression.
7310 +ctf_integer_network_hex(__t__, __n__, __e__)+
7312 +ctf_user_integer_network_hex(__t__, __n__, __e__)+
7314 Integer in network byte order, displayed in base 16.
7323 Argument expression.
7326 +ctf_enum(__N__, __t__, __n__, __e__)+
7328 +ctf_enum_nowrite(__N__, __t__, __n__, __e__)+
7330 +ctf_user_enum(__N__, __t__, __n__, __e__)+
7332 +ctf_user_enum_nowrite(__N__, __t__, __n__, __e__)+
7337 Name of a <<lttng-tracepoint-enum,previously defined enumeration>>.
7340 Integer C type (`int`, `long`, `size_t`, ...).
7346 Argument expression.
7349 +ctf_string(__n__, __e__)+
7351 +ctf_string_nowrite(__n__, __e__)+
7353 +ctf_user_string(__n__, __e__)+
7355 +ctf_user_string_nowrite(__n__, __e__)+
7357 Null-terminated string; undefined behavior if +__e__+ is `NULL`.
7363 Argument expression.
7366 +ctf_array(__t__, __n__, __e__, __s__)+
7368 +ctf_array_nowrite(__t__, __n__, __e__, __s__)+
7370 +ctf_user_array(__t__, __n__, __e__, __s__)+
7372 +ctf_user_array_nowrite(__t__, __n__, __e__, __s__)+
7374 Statically-sized array of integers.
7377 Array element C type.
7383 Argument expression.
7389 +ctf_array_bitfield(__t__, __n__, __e__, __s__)+
7391 +ctf_array_bitfield_nowrite(__t__, __n__, __e__, __s__)+
7393 +ctf_user_array_bitfield(__t__, __n__, __e__, __s__)+
7395 +ctf_user_array_bitfield_nowrite(__t__, __n__, __e__, __s__)+
7397 Statically-sized array of bits.
7399 The type of +__e__+ must be an integer type. +__s__+ is the number
7400 of elements of such type in +__e__+, not the number of bits.
7403 Array element C type.
7409 Argument expression.
7415 +ctf_array_text(__t__, __n__, __e__, __s__)+
7417 +ctf_array_text_nowrite(__t__, __n__, __e__, __s__)+
7419 +ctf_user_array_text(__t__, __n__, __e__, __s__)+
7421 +ctf_user_array_text_nowrite(__t__, __n__, __e__, __s__)+
7423 Statically-sized array, printed as text.
7425 The string does not need to be null-terminated.
7428 Array element C type (always `char`).
7434 Argument expression.
7440 +ctf_sequence(__t__, __n__, __e__, __T__, __E__)+
7442 +ctf_sequence_nowrite(__t__, __n__, __e__, __T__, __E__)+
7444 +ctf_user_sequence(__t__, __n__, __e__, __T__, __E__)+
7446 +ctf_user_sequence_nowrite(__t__, __n__, __e__, __T__, __E__)+
7448 Dynamically-sized array of integers.
7450 The type of +__E__+ must be unsigned.
7453 Array element C type.
7459 Argument expression.
7462 Length expression C type.
7468 +ctf_sequence_hex(__t__, __n__, __e__, __T__, __E__)+
7470 +ctf_user_sequence_hex(__t__, __n__, __e__, __T__, __E__)+
7472 Dynamically-sized array of integers, displayed in base 16.
7474 The type of +__E__+ must be unsigned.
7477 Array element C type.
7483 Argument expression.
7486 Length expression C type.
7491 |+ctf_sequence_network(__t__, __n__, __e__, __T__, __E__)+
7493 Dynamically-sized array of integers in network byte order (big-endian),
7494 displayed in base 10.
7496 The type of +__E__+ must be unsigned.
7499 Array element C type.
7505 Argument expression.
7508 Length expression C type.
7514 +ctf_sequence_bitfield(__t__, __n__, __e__, __T__, __E__)+
7516 +ctf_sequence_bitfield_nowrite(__t__, __n__, __e__, __T__, __E__)+
7518 +ctf_user_sequence_bitfield(__t__, __n__, __e__, __T__, __E__)+
7520 +ctf_user_sequence_bitfield_nowrite(__t__, __n__, __e__, __T__, __E__)+
7522 Dynamically-sized array of bits.
7524 The type of +__e__+ must be an integer type. +__s__+ is the number
7525 of elements of such type in +__e__+, not the number of bits.
7527 The type of +__E__+ must be unsigned.
7530 Array element C type.
7536 Argument expression.
7539 Length expression C type.
7545 +ctf_sequence_text(__t__, __n__, __e__, __T__, __E__)+
7547 +ctf_sequence_text_nowrite(__t__, __n__, __e__, __T__, __E__)+
7549 +ctf_user_sequence_text(__t__, __n__, __e__, __T__, __E__)+
7551 +ctf_user_sequence_text_nowrite(__t__, __n__, __e__, __T__, __E__)+
7553 Dynamically-sized array, displayed as text.
7555 The string does not need to be null-terminated.
7557 The type of +__E__+ must be unsigned.
7559 The behaviour is undefined if +__e__+ is `NULL`.
7562 Sequence element C type (always `char`).
7568 Argument expression.
7571 Length expression C type.
7577 Use the `_user` versions when the argument expression, `e`, is
7578 a user space address. In the cases of `ctf_user_integer*()` and
7579 `ctf_user_float*()`, `&e` must be a user space address, thus `e` must
7582 The `_nowrite` versions omit themselves from the session trace, but are
7583 otherwise identical. This means the `_nowrite` fields won't be written
7584 in the recorded trace. Their primary purpose is to make some
7585 of the event context available to the
7586 <<enabling-disabling-events,event filters>> without having to
7587 commit the data to sub-buffers.
7593 Terms related to LTTng and to tracing in general:
7596 The http://diamon.org/babeltrace[Babeltrace] project, which includes
7597 the cmd:babeltrace command, some libraries, and Python bindings.
7599 <<channel-buffering-schemes,buffering scheme>>::
7600 A layout of sub-buffers applied to a given channel.
7602 <<channel,channel>>::
7603 An entity which is responsible for a set of ring buffers.
7605 <<event,Event rules>> are always attached to a specific channel.
7608 A reference of time for a tracer.
7610 <<lttng-consumerd,consumer daemon>>::
7611 A process which is responsible for consuming the full sub-buffers
7612 and write them to a file system or send them over the network.
7614 <<channel-overwrite-mode-vs-discard-mode,discard mode>>:: The event loss
7615 mode in which the tracer _discards_ new event records when there's no
7616 sub-buffer space left to store them.
7619 The consequence of the execution of an instrumentation
7620 point, like a tracepoint that you manually place in some source code,
7621 or a Linux kernel KProbe.
7623 An event is said to _occur_ at a specific time. Different actions can
7624 be taken upon the occurrence of an event, like record the event's payload
7627 <<channel-overwrite-mode-vs-discard-mode,event loss mode>>::
7628 The mechanism by which event records of a given channel are lost
7629 (not recorded) when there is no sub-buffer space left to store them.
7631 [[def-event-name]]event name::
7632 The name of an event, which is also the name of the event record.
7633 This is also called the _instrumentation point name_.
7636 A record, in a trace, of the payload of an event which occured.
7638 <<event,event rule>>::
7639 Set of conditions which must be satisfied for one or more occuring
7640 events to be recorded.
7642 `java.util.logging`::
7644 https://docs.oracle.com/javase/7/docs/api/java/util/logging/package-summary.html[core logging facilities].
7646 <<instrumenting,instrumentation>>::
7647 The use of LTTng probes to make a piece of software traceable.
7649 instrumentation point::
7650 A point in the execution path of a piece of software that, when
7651 reached by this execution, can emit an event.
7653 instrumentation point name::
7654 See _<<def-event-name,event name>>_.
7657 A http://logging.apache.org/log4j/1.2/[logging library] for Java
7658 developed by the Apache Software Foundation.
7661 Level of severity of a log statement or user space
7662 instrumentation point.
7665 The _Linux Trace Toolkit: next generation_ project.
7667 <<lttng-cli,cmd:lttng>>::
7668 A command-line tool provided by the LTTng-tools project which you
7669 can use to send and receive control messages to and from a
7673 The https://github.com/lttng/lttng-analyses[LTTng analyses] project,
7674 which is a set of analyzing programs that are used to obtain a
7675 higher level view of an LTTng trace.
7677 cmd:lttng-consumerd::
7678 The name of the consumer daemon program.
7681 A utility provided by the LTTng-tools project which can convert
7682 ring buffer files (usually
7683 <<persistent-memory-file-systems,saved on a persistent memory file system>>)
7686 LTTng Documentation::
7689 <<lttng-live,LTTng live>>::
7690 A communication protocol between the relay daemon and live viewers
7691 which makes it possible to see events "live", as they are received by
7694 <<lttng-modules,LTTng-modules>>::
7695 The https://github.com/lttng/lttng-modules[LTTng-modules] project,
7696 which contains the Linux kernel modules to make the Linux kernel
7697 instrumentation points available for LTTng tracing.
7700 The name of the relay daemon program.
7702 cmd:lttng-sessiond::
7703 The name of the session daemon program.
7706 The https://github.com/lttng/lttng-tools[LTTng-tools] project, which
7707 contains the various programs and libraries used to
7708 <<controlling-tracing,control tracing>>.
7710 <<lttng-ust,LTTng-UST>>::
7711 The https://github.com/lttng/lttng-ust[LTTng-UST] project, which
7712 contains libraries to instrument user applications.
7714 <<lttng-ust-agents,LTTng-UST Java agent>>::
7715 A Java package provided by the LTTng-UST project to allow the
7716 LTTng instrumentation of `java.util.logging` and Apache log4j 1.2
7719 <<lttng-ust-agents,LTTng-UST Python agent>>::
7720 A Python package provided by the LTTng-UST project to allow the
7721 LTTng instrumentation of Python logging statements.
7723 <<channel-overwrite-mode-vs-discard-mode,overwrite mode>>::
7724 The event loss mode in which new event records overwrite older
7725 event records when there's no sub-buffer space left to store them.
7727 <<channel-buffering-schemes,per-process buffering>>::
7728 A buffering scheme in which each instrumented process has its own
7729 sub-buffers for a given user space channel.
7731 <<channel-buffering-schemes,per-user buffering>>::
7732 A buffering scheme in which all the processes of a Unix user share the
7733 same sub-buffer for a given user space channel.
7735 <<lttng-relayd,relay daemon>>::
7736 A process which is responsible for receiving the trace data sent by
7737 a distant consumer daemon.
7740 A set of sub-buffers.
7742 <<lttng-sessiond,session daemon>>::
7743 A process which receives control commands from you and orchestrates
7744 the tracers and various LTTng daemons.
7746 <<taking-a-snapshot,snapshot>>::
7747 A copy of the current data of all the sub-buffers of a given tracing
7748 session, saved as trace files.
7751 One part of an LTTng ring buffer which contains event records.
7754 The time information attached to an event when it is emitted.
7757 A set of files which are the concatenations of one or more
7758 flushed sub-buffers.
7761 The action of recording the events emitted by an application
7762 or by a system, or to initiate such recording by controlling
7766 The http://tracecompass.org[Trace Compass] project and application.
7769 An instrumentation point using the tracepoint mechanism of the Linux
7770 kernel or of LTTng-UST.
7772 tracepoint definition::
7773 The definition of a single tracepoint.
7776 The name of a tracepoint.
7778 tracepoint provider::
7779 A set of functions providing tracepoints to an instrumented user
7782 Not to be confused with a _tracepoint provider package_: many tracepoint
7783 providers can exist within a tracepoint provider package.
7785 tracepoint provider package::
7786 One or more tracepoint providers compiled as an object file or as
7790 A software which records emitted events.
7792 <<domain,tracing domain>>::
7793 A namespace for event sources.
7795 <<tracing-group,tracing group>>::
7796 The Unix group in which a Unix user can be to be allowed to trace the
7799 <<tracing-session,tracing session>>::
7800 A stateful dialogue between you and a <<lttng-sessiond,session
7804 An application running in user space, as opposed to a Linux kernel
7805 module, for example.