1 .. SPDX-License-Identifier: BSD-3-Clause
2 Copyright(C) 2020 Marvell International Ltd.
10 *Tracing* is a technique used to understand what goes on in a running software
11 system. The software used for tracing is called a *tracer*, which is
12 conceptually similar to a tape recorder.
13 When recording, specific instrumentation points placed in the software source
14 code generate events that are saved on a giant tape: a trace file.
15 The trace file then later can be opened in *trace viewers* to visualize and
16 analyze the trace events with timestamps and multi-core views.
17 Such a mechanism will be useful for resolving a wide range of problems such as
18 multi-core synchronization issues, latency measurements, finding out the
19 post analysis information like CPU idle time, etc that would otherwise be
20 extremely challenging to get.
22 Tracing is often compared to *logging*. However, tracers and loggers are two
23 different tools, serving two different purposes.
24 Tracers are designed to record much lower-level events that occur much more
25 frequently than log messages, often in the range of thousands per second, with
26 very little execution overhead.
27 Logging is more appropriate for a very high-level analysis of less frequent
28 events: user accesses, exceptional conditions (errors and warnings, for
29 example), database transactions, instant messaging communications, and such.
30 Simply put, logging is one of the many use cases that can be satisfied with
33 DPDK tracing library features
34 -----------------------------
36 - A framework to add tracepoints in control and fast path APIs with minimum
37 impact on performance.
38 Typical trace overhead is ~20 cycles and instrumentation overhead is 1 cycle.
39 - Enable and disable the tracepoints at runtime.
40 - Save the trace buffer to the filesystem at any point in time.
41 - Support ``overwrite`` and ``discard`` trace mode operations.
42 - String-based tracepoint object lookup.
43 - Enable and disable a set of tracepoints based on regular expression and/or
45 - Generate trace in ``Common Trace Format (CTF)``. ``CTF`` is an open-source
46 trace format and is compatible with ``LTTng``.
47 For detailed information, refer to
48 `Common Trace Format <https://diamon.org/ctf/>`_.
50 How to add a tracepoint?
51 ------------------------
53 This section steps you through the details of adding a simple tracepoint.
55 .. _create_tracepoint_header_file:
57 Create the tracepoint header file
58 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
62 #include <rte_trace_point.h>
66 RTE_TRACE_POINT_ARGS(const char *str),
67 rte_trace_point_emit_string(str);
70 The above macro creates ``app_trace_string`` tracepoint.
71 The user can choose any name for the tracepoint.
72 However, when adding a tracepoint in the DPDK library, the
73 ``rte_<library_name>_trace_[<domain>_]<name>`` naming convention must be
75 The examples are ``rte_eal_trace_generic_str``, ``rte_mempool_trace_create``.
77 The ``RTE_TRACE_POINT`` macro expands from above definition as the following
82 static __rte_always_inline void
83 app_trace_string(const char *str)
85 /* Trace subsystem hooks */
87 rte_trace_point_emit_string(str);
90 The consumer of this tracepoint can invoke
91 ``app_trace_string(const char *str)`` to emit the trace event to the trace
94 Register the tracepoint
95 ~~~~~~~~~~~~~~~~~~~~~~~
99 #include <rte_trace_point_register.h>
101 #include <my_tracepoint.h>
103 RTE_TRACE_POINT_REGISTER(app_trace_string, app.trace.string)
105 The above code snippet registers the ``app_trace_string`` tracepoint to
106 trace library. Here, the ``my_tracepoint.h`` is the header file
107 that the user created in the first step :ref:`create_tracepoint_header_file`.
109 The second argument for the ``RTE_TRACE_POINT_REGISTER`` is the name for the
110 tracepoint. This string will be used for tracepoint lookup or regular
111 expression and/or glob based tracepoint operations.
112 There is no requirement for the tracepoint function and its name to be similar.
113 However, it is recommended to have a similar name for a better naming
118 The ``rte_trace_point_register.h`` header must be included before any
119 inclusion of the ``rte_trace_point.h`` header.
123 The ``RTE_TRACE_POINT_REGISTER`` defines the placeholder for the
124 ``rte_trace_point_t`` tracepoint object. The user must export a
125 ``__<trace_function_name>`` symbol in the library ``.map`` file for this
126 tracepoint to be used out of the library, in shared builds.
127 For example, ``__app_trace_string`` will be the exported symbol in the
133 In order to avoid performance impact in fast path code, the library introduced
134 ``RTE_TRACE_POINT_FP``. When adding the tracepoint in fast path code,
135 the user must use ``RTE_TRACE_POINT_FP`` instead of ``RTE_TRACE_POINT``.
137 ``RTE_TRACE_POINT_FP`` is compiled out by default and it can be enabled using
138 ``CONFIG_RTE_ENABLE_TRACE_FP`` configuration parameter.
139 The ``enable_trace_fp`` option shall be used for the same for meson build.
144 Event record mode is an attribute of trace buffers. Trace library exposes the
148 When the trace buffer is full, new trace events overwrites the existing
149 captured events in the trace buffer.
151 When the trace buffer is full, new trace events will be discarded.
153 The mode can be configured either using EAL command line parameter
154 ``--trace-mode`` on application boot up or use ``rte_trace_mode_set()`` API to
155 configure at runtime.
160 On ``rte_trace_save()`` or ``rte_eal_cleanup()`` invocation, the library saves
161 the trace buffers to the filesystem. By default, the trace files are stored in
162 ``$HOME/dpdk-traces/rte-yyyy-mm-dd-[AP]M-hh-mm-ss/``.
163 It can be overridden by the ``--trace-dir=<directory path>`` EAL command line
166 For more information, refer to :doc:`../linux_gsg/linux_eal_parameters` for
167 trace EAL command line options.
169 View and analyze the recorded events
170 ------------------------------------
172 Once the trace directory is available, the user can view/inspect the recorded
175 There are many tools you can use to read DPDK traces:
177 1. ``babeltrace`` is a command-line utility that converts trace formats; it
178 supports the format that DPDK trace library produces, CTF, as well as a
179 basic text output that can be grep'ed.
180 The babeltrace command is part of the Open Source Babeltrace project.
182 2. ``Trace Compass`` is a graphical user interface for viewing and analyzing
183 any type of logs or traces, including DPDK traces.
185 Use the babeltrace command-line tool
186 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
188 The simplest way to list all the recorded events of a trace is to pass its path
189 to babeltrace with no options::
191 babeltrace </path-to-trace-events/rte-yyyy-mm-dd-[AP]M-hh-mm-ss/>
193 ``babeltrace`` finds all traces recursively within the given path and prints
194 all their events, merging them in chronological order.
196 You can pipe the output of the babeltrace into a tool like grep(1) for further
197 filtering. Below example grep the events for ``ethdev`` only::
199 babeltrace /tmp/my-dpdk-trace | grep ethdev
201 You can pipe the output of babeltrace into a tool like wc(1) to count the
202 recorded events. Below example count the number of ``ethdev`` events::
204 babeltrace /tmp/my-dpdk-trace | grep ethdev | wc --lines
206 Use the tracecompass GUI tool
207 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
209 ``Tracecompass`` is another tool to view/analyze the DPDK traces which gives
210 a graphical view of events. Like ``babeltrace``, tracecompass also provides
211 an interface to search for a particular event.
212 To use ``tracecompass``, following are the minimum required steps:
214 - Install ``tracecompass`` to the localhost. Variants are available for Linux,
216 - Launch ``tracecompass`` which will open a graphical window with trace
217 management interfaces.
218 - Open a trace using ``File->Open Trace`` option and select metadata file which
219 is to be viewed/analyzed.
221 For more details, refer
222 `Trace Compass <https://www.eclipse.org/tracecompass/>`_.
227 This section steps you through the details of generating trace and viewing it.
229 - Start the dpdk-test::
231 echo "quit" | ./build/app/test/dpdk-test --no-huge --trace=.*
233 - View the traces with babeltrace viewer::
235 babeltrace $HOME/dpdk-traces/rte-yyyy-mm-dd-[AP]M-hh-mm-ss/
237 Implementation details
238 ----------------------
240 As DPDK trace library is designed to generate traces that uses ``Common Trace
241 Format (CTF)``. ``CTF`` specification consists of the following units to create
244 - ``Stream`` Sequence of packets.
245 - ``Packet`` Header and one or more events.
246 - ``Event`` Header and payload.
248 For detailed information, refer to
249 `Common Trace Format <https://diamon.org/ctf/>`_.
251 The implementation details broadly divided into the following areas:
253 Trace metadata creation
254 ~~~~~~~~~~~~~~~~~~~~~~~
256 Based on the ``CTF`` specification, one of a CTF trace's streams is mandatory:
257 the metadata stream. It contains exactly what you would expect: data about the
258 trace itself. The metadata stream contains a textual description of the binary
259 layouts of all the other streams.
261 This description is written using the Trace Stream Description Language (TSDL),
262 a declarative language that exists only in the realm of CTF.
263 The purpose of the metadata stream is to make CTF readers know how to parse a
264 trace's binary streams of events without CTF specifying any fixed layout.
265 The only stream layout known in advance is, in fact, the metadata stream's one.
267 The internal ``trace_metadata_create()`` function generates the metadata.
272 The trace memory will be allocated through an internal function
273 ``__rte_trace_mem_per_thread_alloc()``. The trace memory will be allocated
274 per thread to enable lock less trace-emit function.
275 The memory for the trace memory for DPDK lcores will be allocated on
276 ``rte_eal_init()`` if the trace is enabled through a EAL option.
277 For non DPDK threads, on the first trace emission, the memory will be
283 .. _table_trace_mem_layout:
285 .. table:: Trace memory layout.
287 +-------------------+
289 +-------------------+
291 +-------------------+
293 +-------------------+
295 +-------------------+
297 +-------------------+
299 +-------------------+
301 +-------------------+
303 +-------------------+
308 .. _table_packet_header:
310 .. table:: Packet header layout.
312 +-------------------+
314 +-------------------+
316 +-------------------+
321 .. _table_packet_context:
323 .. table:: Packet context layout.
325 +----------------------+
326 | uint32_t thread_id |
327 +----------------------+
328 | char thread_name[32] |
329 +----------------------+
334 .. _table_trace_header:
336 .. table:: Trace header layout.
338 +----------------------+
340 +----------------------+
342 +----------------------+
344 The trace header is 64 bits, it consists of 48 bits of timestamp and 16 bits
347 The ``packet.header`` and ``packet.context`` will be written in the slow path
348 at the time of trace memory creation. The ``trace.header`` and trace payload
349 will be emitted when the tracepoint function is invoked.