1 Common Trace Format (CTF) Specification (v1.8.2)
3 Mathieu Desnoyers, EfficiOS Inc.
5 The goal of the present document is to specify a trace format that suits the
6 needs of the embedded, telecom, high-performance and kernel communities. It is
7 based on the Common Trace Format Requirements (v1.4) document. It is designed to
8 allow traces to be natively generated by the Linux kernel, Linux user-space
9 applications written in C/C++, and hardware components. One major element of
10 CTF is the Trace Stream Description Language (TSDL) which flexibility
11 enables description of various binary trace stream layouts.
13 The latest version of this document can be found at:
15 git tree: git://git.efficios.com/ctf.git
16 gitweb: http://git.efficios.com/?p=ctf.git
18 A reference implementation of a library to read and write this trace format is
19 being implemented within the BabelTrace project, a converter between trace
20 formats. The development tree is available at:
22 git tree: git://git.efficios.com/babeltrace.git
23 gitweb: http://git.efficios.com/?p=babeltrace.git
25 The CE Workgroup of the Linux Foundation, Ericsson, and EfficiOS have
31 1. Preliminary definitions
32 2. High-level representation of a trace
36 4.1.1 Type inheritance
46 4.2.2 Variants (Discriminated/Tagged Unions)
50 5. Event Packet Header
51 5.1 Event Packet Header Description
52 5.2 Event Packet Context Description
55 6.1.1 Type 1 - Few event IDs
56 6.1.2 Type 2 - Many event IDs
57 6.2 Stream Event Context and Event Context
61 7. Trace Stream Description Language (TSDL)
63 7.2 Declaration vs Definition
66 7.3.2 Static and Dynamic Scopes
71 1. Preliminary definitions
73 - Event Trace: An ordered sequence of events.
74 - Event Stream: An ordered sequence of events, containing a subset of the
76 - Event Packet: A sequence of physically contiguous events within an event
78 - Event: This is the basic entry in a trace. (aka: a trace record).
79 - An event identifier (ID) relates to the class (a type) of event within
81 e.g. event: irq_entry.
82 - An event (or event record) relates to a specific instance of an event
84 e.g. event: irq_entry, at time X, on CPU Y
85 - Source Architecture: Architecture writing the trace.
86 - Reader Architecture: Architecture reading the trace.
89 2. High-level representation of a trace
91 A trace is divided into multiple event streams. Each event stream contains a
92 subset of the trace event types.
94 The final output of the trace, after its generation and optional transport over
95 the network, is expected to be either on permanent or temporary storage in a
96 virtual file system. Because each event stream is appended to while a trace is
97 being recorded, each is associated with a distinct set of files for
98 output. Therefore, a stored trace can be represented as a directory
99 containing zero, one or more files per stream.
101 Meta-data description associated with the trace contains information on
102 trace event types expressed in the Trace Stream Description Language
103 (TSDL). This language describes:
107 - Per-trace event header description.
108 - Per-stream event header description.
109 - Per-stream event context description.
111 - Event type to stream mapping.
112 - Event type to name mapping.
113 - Event type to ID mapping.
114 - Event context description.
115 - Event fields description.
120 An event stream can be divided into contiguous event packets of variable
121 size. An event packet can contain a certain amount of padding at the
122 end. The stream header is repeated at the beginning of each event
123 packet. The rationale for the event stream design choices is explained
124 in Appendix B. Stream Header Rationale.
126 The event stream header will therefore be referred to as the "event packet
127 header" throughout the rest of this document.
132 Types are organized as type classes. Each type class belong to either of two
133 kind of types: basic types or compound types.
137 A basic type is a scalar type, as described in this section. It includes
138 integers, GNU/C bitfields, enumerations, and floating point values.
140 4.1.1 Type inheritance
142 Type specifications can be inherited to allow deriving types from a
143 type class. For example, see the uint32_t named type derived from the "integer"
144 type class below ("Integers" section). Types have a precise binary
145 representation in the trace. A type class has methods to read and write these
146 types, but must be derived into a type to be usable in an event field.
150 We define "byte-packed" types as aligned on the byte size, namely 8-bit.
151 We define "bit-packed" types as following on the next bit, as defined by the
154 Each basic type must specify its alignment, in bits. Examples of
155 possible alignments are: bit-packed (align = 1), byte-packed (align =
156 8), or word-aligned (e.g. align = 32 or align = 64). The choice depends
157 on the architecture preference and compactness vs performance trade-offs
158 of the implementation. Architectures providing fast unaligned write
159 byte-packed basic types to save space, aligning each type on byte
160 boundaries (8-bit). Architectures with slow unaligned writes align types
161 on specific alignment values. If no specific alignment is declared for a
162 type, it is assumed to be bit-packed for integers with size not multiple
163 of 8 bits and for gcc bitfields. All other basic types are byte-packed
164 by default. It is however recommended to always specify the alignment
165 explicitly. Alignment values must be power of two. Compound types are
166 aligned as specified in their individual specification.
168 The base offset used for field alignment is the start of the packet
169 containing the field. For instance, a field aligned on 32-bit needs to
170 be at an offset multiple of 32-bit from the start of the packet that
173 TSDL meta-data attribute representation of a specific alignment:
175 align = value; /* value in bits */
179 By default, byte order of a basic type is the byte order described in
180 the trace description. It can be overridden by specifying a
181 "byte_order" attribute for a basic type. Typical use-case is to specify
182 the network byte order (big endian: "be") to save data captured from the
183 network into the trace without conversion.
185 TSDL meta-data representation:
187 byte_order = native OR network OR be OR le; /* network and be are aliases */
189 The "native" keyword selects the byte order described in the trace
190 description. The "network" byte order is an alias for big endian.
192 Even though the trace description section is not per se a type, for sake
193 of clarity, it should be noted that "native" and "network" byte orders
194 are only allowed within type declaration. The byte_order specified in
195 the trace description section only accepts "be" or "le" values.
199 Type size, in bits, for integers and floats is that returned by "sizeof()" in C
200 multiplied by CHAR_BIT.
201 We require the size of "char" and "unsigned char" types (CHAR_BIT) to be fixed
202 to 8 bits for cross-endianness compatibility.
204 TSDL meta-data representation:
206 size = value; (value is in bits)
210 Signed integers are represented in two-complement. Integer alignment,
211 size, signedness and byte ordering are defined in the TSDL meta-data.
212 Integers aligned on byte size (8-bit) and with length multiple of byte
213 size (8-bit) correspond to the C99 standard integers. In addition,
214 integers with alignment and/or size that are _not_ a multiple of the
215 byte size are permitted; these correspond to the C99 standard bitfields,
216 with the added specification that the CTF integer bitfields have a fixed
217 binary representation. Integer size needs to be a positive integer.
218 Integers of size 0 are forbidden. A MIT-licensed reference
219 implementation of the CTF portable bitfields is available at:
221 http://git.efficios.com/?p=babeltrace.git;a=blob;f=include/babeltrace/bitfield.h
223 Binary representation of integers:
225 - On little and big endian:
226 - Within a byte, high bits correspond to an integer high bits, and low bits
227 correspond to low bits.
229 - Integer across multiple bytes are placed from the less significant to the
231 - Consecutive integers are placed from lower bits to higher bits (even within
234 - Integer across multiple bytes are placed from the most significant to the
236 - Consecutive integers are placed from higher bits to lower bits (even within
239 This binary representation is derived from the bitfield implementation in GCC
240 for little and big endian. However, contrary to what GCC does, integers can
241 cross units boundaries (no padding is required). Padding can be explicitly
242 added (see 4.1.6 GNU/C bitfields) to follow the GCC layout if needed.
244 TSDL meta-data representation:
247 signed = true OR false; /* default false */
248 byte_order = native OR network OR be OR le; /* default native */
249 size = value; /* value in bits, no default */
250 align = value; /* value in bits */
251 /* based used for pretty-printing output, default: decimal. */
252 base = decimal OR dec OR d OR i OR u OR 10 OR hexadecimal OR hex OR x OR X OR p OR 16
253 OR octal OR oct OR o OR 8 OR binary OR b OR 2;
254 /* character encoding, default: none */
255 encoding = none or UTF8 or ASCII;
258 Example of type inheritance (creation of a uint32_t named type):
266 Definition of a named 5-bit signed bitfield:
274 The character encoding field can be used to specify that the integer
275 must be printed as a text character when read. e.g.:
285 4.1.6 GNU/C bitfields
287 The GNU/C bitfields follow closely the integer representation, with a
288 particularity on alignment: if a bitfield cannot fit in the current unit, the
289 unit is padded and the bitfield starts at the following unit. The unit size is
290 defined by the size of the type "unit_type".
292 TSDL meta-data representation:
296 As an example, the following structure declared in C compiled by GCC:
303 The example structure is aligned on the largest element (short). The second
304 bitfield would be aligned on the next unit boundary, because it would not fit in
309 The floating point values byte ordering is defined in the TSDL meta-data.
311 Floating point values follow the IEEE 754-2008 standard interchange formats.
312 Description of the floating point values include the exponent and mantissa size
313 in bits. Some requirements are imposed on the floating point values:
315 - FLT_RADIX must be 2.
316 - mant_dig is the number of digits represented in the mantissa. It is specified
317 by the ISO C99 standard, section 5.2.4, as FLT_MANT_DIG, DBL_MANT_DIG and
318 LDBL_MANT_DIG as defined by <float.h>.
319 - exp_dig is the number of digits represented in the exponent. Given that
320 mant_dig is one bit more than its actual size in bits (leading 1 is not
321 needed) and also given that the sign bit always takes one bit, exp_dig can be
324 - sizeof(float) * CHAR_BIT - FLT_MANT_DIG
325 - sizeof(double) * CHAR_BIT - DBL_MANT_DIG
326 - sizeof(long double) * CHAR_BIT - LDBL_MANT_DIG
328 TSDL meta-data representation:
333 byte_order = native OR network OR be OR le;
337 Example of type inheritance:
339 typealias floating_point {
340 exp_dig = 8; /* sizeof(float) * CHAR_BIT - FLT_MANT_DIG */
341 mant_dig = 24; /* FLT_MANT_DIG */
346 TODO: define NaN, +inf, -inf behavior.
348 Bit-packed, byte-packed or larger alignments can be used for floating
349 point values, similarly to integers.
353 Enumerations are a mapping between an integer type and a table of strings. The
354 numerical representation of the enumeration follows the integer type specified
355 by the meta-data. The enumeration mapping table is detailed in the enumeration
356 description within the meta-data. The mapping table maps inclusive value
357 ranges (or single values) to strings. Instead of being limited to simple
358 "value -> string" mappings, these enumerations map
359 "[ start_value ... end_value ] -> string", which map inclusive ranges of
360 values to strings. An enumeration from the C language can be represented in
361 this format by having the same start_value and end_value for each
362 mapping, which is in fact a range of size 1. This single-value range is
363 supported without repeating the start and end values with the value =
364 string declaration. Enumerations need to contain at least one entry.
366 enum name : integer_type {
367 somestring = start_value1 ... end_value1,
368 "other string" = start_value2 ... end_value2,
369 yet_another_string, /* will be assigned to end_value2 + 1 */
370 "some other string" = value,
374 If the values are omitted, the enumeration starts at 0 and increment of 1 for
375 each entry. An entry with omitted value that follows a range entry takes
376 as value the end_value of the previous range + 1:
378 enum name : unsigned int {
386 Overlapping ranges within a single enumeration are implementation defined.
388 A nameless enumeration can be declared as a field type or as part of a typedef:
390 enum : integer_type {
394 Enumerations omitting the container type ": integer_type" use the "int"
395 type (for compatibility with C99). The "int" type must be previously
398 typealias integer { size = 32; align = 32; signed = true; } := int;
407 Compound are aggregation of type declarations. Compound types include
408 structures, variant, arrays, sequences, and strings.
412 Structures are aligned on the largest alignment required by basic types
413 contained within the structure. (This follows the ISO/C standard for structures)
415 TSDL meta-data representation of a named structure:
418 field_type field_name;
419 field_type field_name;
426 integer { /* Nameless type */
431 uint64_t second_field_name; /* Named type declared in the meta-data */
434 The fields are placed in a sequence next to each other. They each
435 possess a field name, which is a unique identifier within the structure.
436 The identifier is not allowed to use any reserved keyword
437 (see Section C.1.2). Replacing reserved keywords with
438 underscore-prefixed field names is recommended. Fields starting with an
439 underscore should have their leading underscore removed by the CTF trace
442 A nameless structure can be declared as a field type or as part of a typedef:
448 Alignment for a structure compound type can be forced to a minimum value
449 by adding an "align" specifier after the declaration of a structure
450 body. This attribute is read as: align(value). The value is specified in
451 bits. The structure will be aligned on the maximum value between this
452 attribute and the alignment required by the basic types contained within
459 4.2.2 Variants (Discriminated/Tagged Unions)
461 A CTF variant is a selection between different types. A CTF variant must
462 always be defined within the scope of a structure or within fields
463 contained within a structure (defined recursively). A "tag" enumeration
464 field must appear in either the same static scope, prior to the variant
465 field (in field declaration order), in an upper static scope, or in an
466 upper dynamic scope (see Section 7.3.2). The type selection is indicated
467 by the mapping from the enumeration value to the string used as variant
468 type selector. The field to use as tag is specified by the "tag_field",
469 specified between "< >" after the "variant" keyword for unnamed
470 variants, and after "variant name" for named variants. It is not
471 required that each enumeration mapping appears as variant type tag
472 field. It is also not required that each variant type tag appears as
473 enumeration mapping. However, it is required that any enumeration
474 mapping encountered within a stream has a matching variant type tag
477 The alignment of the variant is the alignment of the type as selected by
478 the tag value for the specific instance of the variant. The size of the
479 variant is the size as selected by the tag value for the specific
480 instance of the variant.
482 The alignment of the type containing the variant is independent of the
483 variant alignment. For instance, if a structure contains two fields, a
484 32-bit integer, aligned on 32 bits, and a variant, which contains two
485 choices: either a 32-bit field, aligned on 32 bits, or a 64-bit field,
486 aligned on 64 bits, the alignment of the outmost structure will be
487 32-bit (the alignment of its largest field, disregarding the alignment
488 of the variant). The alignment of the variant will depend on the
489 selector: if the variant's 32-bit field is selected, its alignment will
490 be 32-bit, or 64-bit otherwise. It is important to note that variants
491 are specifically tailored for compactness in a stream. Therefore, the
492 relative offsets of compound type fields can vary depending on
493 the offset at which the compound type starts if it contains a variant
494 that itself contains a type with alignment larger than the largest field
495 contained within the compound type. This is caused by the fact that the
496 compound type may contain the enumeration that select the variant's
497 choice, and therefore the alignment to be applied to the compound type
498 cannot be determined before encountering the enumeration.
500 Each variant type selector possess a field name, which is a unique
501 identifier within the variant. The identifier is not allowed to use any
502 reserved keyword (see Section C.1.2). Replacing reserved keywords with
503 underscore-prefixed field names is recommended. Fields starting with an
504 underscore should have their leading underscore removed by the CTF trace
508 A named variant declaration followed by its definition within a structure
519 enum : integer_type { sel1, sel2, sel3, ... } tag_field;
521 variant name <tag_field> v;
524 An unnamed variant definition within a structure is expressed by the following
528 enum : integer_type { sel1, sel2, sel3, ... } tag_field;
530 variant <tag_field> {
538 Example of a named variant within a sequence that refers to a single tag field:
547 enum : uint2_t { a, b, c } choice;
549 variant example <choice> v[seqlen];
552 Example of an unnamed variant:
555 enum : uint2_t { a, b, c, d } choice;
556 /* Unrelated fields can be added between the variant and its tag */
569 Example of an unnamed variant within an array:
572 enum : uint2_t { a, b, c } choice;
580 Example of a variant type definition within a structure, where the defined type
581 is then declared within an array of structures. This variant refers to a tag
582 located in an upper static scope. This example clearly shows that a variant
583 type definition referring to the tag "x" uses the closest preceding field from
584 the static scope of the type definition.
587 enum : uint2_t { a, b, c, d } x;
589 typedef variant <x> { /*
590 * "x" refers to the preceding "x" enumeration in the
591 * static scope of the type definition.
599 enum : int { x, y, z } x; /* This enumeration is not used by "v". */
600 example_variant v; /*
601 * "v" uses the "enum : uint2_t { a, b, c, d }"
609 Arrays are fixed-length. Their length is declared in the type
610 declaration within the meta-data. They contain an array of "inner type"
611 elements, which can refer to any type not containing the type of the
612 array being declared (no circular dependency). The length is the number
613 of elements in an array.
615 TSDL meta-data representation of a named array:
617 typedef elem_type name[length];
619 A nameless array can be declared as a field type within a structure, e.g.:
621 uint8_t field_name[10];
623 Arrays are always aligned on their element alignment requirement.
627 Sequences are dynamically-sized arrays. They refer to a "length"
628 unsigned integer field, which must appear in either the same static scope,
629 prior to the sequence field (in field declaration order), in an upper
630 static scope, or in an upper dynamic scope (see Section 7.3.2). This
631 length field represents the number of elements in the sequence. The
632 sequence per se is an array of "inner type" elements.
634 TSDL meta-data representation for a sequence type definition:
637 unsigned int length_field;
638 typedef elem_type typename[length_field];
639 typename seq_field_name;
642 A sequence can also be declared as a field type, e.g.:
645 unsigned int length_field;
646 long seq_field_name[length_field];
649 Multiple sequences can refer to the same length field, and these length
650 fields can be in a different upper dynamic scope:
652 e.g., assuming the stream.event.header defines:
657 event.header := struct {
666 long seq_a[stream.event.header.seq_len];
667 char seq_b[stream.event.header.seq_len];
671 The sequence elements follow the "array" specifications.
675 Strings are an array of bytes of variable size and are terminated by a '\0'
676 "NULL" character. Their encoding is described in the TSDL meta-data. In
677 absence of encoding attribute information, the default encoding is
680 TSDL meta-data representation of a named string type:
683 encoding = UTF8 OR ASCII;
686 A nameless string type can be declared as a field type:
688 string field_name; /* Use default UTF8 encoding */
690 Strings are always aligned on byte size.
692 5. Event Packet Header
694 The event packet header consists of two parts: the "event packet header"
695 is the same for all streams of a trace. The second part, the "event
696 packet context", is described on a per-stream basis. Both are described
697 in the TSDL meta-data.
699 Event packet header (all fields are optional, specified by TSDL meta-data):
701 - Magic number (CTF magic number: 0xC1FC1FC1) specifies that this is a
702 CTF packet. This magic number is optional, but when present, it should
703 come at the very beginning of the packet.
704 - Trace UUID, used to ensure the event packet match the meta-data used.
705 (note: we cannot use a meta-data checksum in every cases instead of a
706 UUID because meta-data can be appended to while tracing is active)
707 This field is optional.
708 - Stream ID, used as reference to stream description in meta-data.
709 This field is optional if there is only one stream description in the
710 meta-data, but becomes required if there are more than one stream in
711 the TSDL meta-data description.
713 Event packet context (all fields are optional, specified by TSDL meta-data):
715 - Event packet content size (in bits).
716 - Event packet size (in bits, includes padding).
717 - Event packet content checksum. Checksum excludes the event packet
719 - Per-stream event packet sequence count (to deal with UDP packet loss). The
720 number of significant sequence counter bits should also be present, so
721 wrap-arounds are dealt with correctly.
722 - Time-stamp at the beginning and time-stamp at the end of the event packet.
723 Both timestamps are written in the packet header, but sampled respectively
724 while (or before) writing the first event and while (or after) writing the
725 last event in the packet. The inclusive range between these timestamps should
726 include all event timestamps assigned to events contained within the packet.
727 The timestamp at the beginning of an event packet is guaranteed to be
728 below or equal the timestamp at the end of that event packet.
729 The timestamp at the end of an event packet is guaranteed to be below
730 or equal the timestamps at the end of any following packet within the
731 same stream. See Section 8. Clocks for more detail.
732 - Events discarded count
733 - Snapshot of a per-stream free-running counter, counting the number of
734 events discarded that were supposed to be written in the stream after
735 the last event in the event packet.
736 * Note: producer-consumer buffer full condition can fill the current
737 event packet with padding so we know exactly where events have been
738 discarded. However, if the buffer full condition chooses not
739 to fill the current event packet with padding, all we know
740 about the timestamp range in which the events have been
741 discarded is that it is somewhere between the beginning and
742 the end of the packet.
743 - Lossless compression scheme used for the event packet content. Applied
744 directly to raw data. New types of compression can be added in following
745 versions of the format.
746 0: no compression scheme
750 - Cypher used for the event packet content. Applied after compression.
753 - Checksum scheme used for the event packet content. Applied after encryption.
759 5.1 Event Packet Header Description
761 The event packet header layout is indicated by the trace packet.header
762 field. Here is a recommended structure type for the packet header with
763 the fields typically expected (although these fields are each optional):
765 struct event_packet_header {
773 packet.header := struct event_packet_header;
776 If the magic number is not present, tools such as "file" will have no
777 mean to discover the file type.
779 If the uuid is not present, no validation that the meta-data actually
780 corresponds to the stream is performed.
782 If the stream_id packet header field is missing, the trace can only
783 contain a single stream. Its "id" field can be left out, and its events
784 don't need to declare a "stream_id" field.
787 5.2 Event Packet Context Description
789 Event packet context example. These are declared within the stream declaration
790 in the meta-data. All these fields are optional. If the packet size field is
791 missing, the whole stream only contains a single packet. If the content
792 size field is missing, the packet is filled (no padding). The content
793 and packet sizes include all headers.
795 An example event packet context type:
797 struct event_packet_context {
798 uint64_t timestamp_begin;
799 uint64_t timestamp_end;
801 uint32_t stream_packet_count;
802 uint32_t events_discarded;
804 uint64_t/uint32_t/uint16_t content_size;
805 uint64_t/uint32_t/uint16_t packet_size;
806 uint8_t compression_scheme;
807 uint8_t encryption_scheme;
808 uint8_t checksum_scheme;
814 The overall structure of an event is:
816 1 - Event Header (as specified by the stream meta-data)
817 2 - Stream Event Context (as specified by the stream meta-data)
818 3 - Event Context (as specified by the event meta-data)
819 4 - Event Payload (as specified by the event meta-data)
821 This structure defines an implicit dynamic scoping, where variants
822 located in inner structures (those with a higher number in the listing
823 above) can refer to the fields of outer structures (with lower number in
824 the listing above). See Section 7.3 TSDL Scopes for more detail.
826 The total length of an event is defined as the difference between the
827 end of its Event Payload and the end of the previous event's Event
828 Payload. Therefore, it includes the event header alignment padding, and
829 all its fields and their respective alignment padding. Events of length
834 Event headers can be described within the meta-data. We hereby propose, as an
835 example, two types of events headers. Type 1 accommodates streams with less than
836 31 event IDs. Type 2 accommodates streams with 31 or more event IDs.
838 One major factor can vary between streams: the number of event IDs assigned to
839 a stream. Luckily, this information tends to stay relatively constant (modulo
840 event registration while trace is being recorded), so we can specify different
841 representations for streams containing few event IDs and streams containing
842 many event IDs, so we end up representing the event ID and time-stamp as
843 densely as possible in each case.
845 The header is extended in the rare occasions where the information cannot be
846 represented in the ranges available in the standard event header. They are also
847 used in the rare occasions where the data required for a field could not be
848 collected: the flag corresponding to the missing field within the missing_fields
849 array is then set to 1.
851 Types uintX_t represent an X-bit unsigned integer, as declared with
854 typealias integer { size = X; align = X; signed = false; } := uintX_t;
858 typealias integer { size = X; align = 1; signed = false; } := uintX_t;
860 For more information about timestamp fields, see Section 8. Clocks.
862 6.1.1 Type 1 - Few event IDs
864 - Aligned on 32-bit (or 8-bit if byte-packed, depending on the architecture
866 - Native architecture byte ordering.
867 - For "compact" selection
868 - Fixed size: 32 bits.
869 - For "extended" selection
870 - Size depends on the architecture and variant alignment.
872 struct event_header_1 {
875 * id 31 is reserved to indicate an extended header.
877 enum : uint5_t { compact = 0 ... 30, extended = 31 } id;
883 uint32_t id; /* 32-bit event IDs */
884 uint64_t timestamp; /* 64-bit timestamps */
887 } align(32); /* or align(8) */
890 6.1.2 Type 2 - Many event IDs
892 - Aligned on 16-bit (or 8-bit if byte-packed, depending on the architecture
894 - Native architecture byte ordering.
895 - For "compact" selection
896 - Size depends on the architecture and variant alignment.
897 - For "extended" selection
898 - Size depends on the architecture and variant alignment.
900 struct event_header_2 {
902 * id: range: 0 - 65534.
903 * id 65535 is reserved to indicate an extended header.
905 enum : uint16_t { compact = 0 ... 65534, extended = 65535 } id;
911 uint32_t id; /* 32-bit event IDs */
912 uint64_t timestamp; /* 64-bit timestamps */
915 } align(16); /* or align(8) */
918 6.2 Stream Event Context and Event Context
920 The event context contains information relative to the current event.
921 The choice and meaning of this information is specified by the TSDL
922 stream and event meta-data descriptions. The stream context is applied
923 to all events within the stream. The stream context structure follows
924 the event header. The event context is applied to specific events. Its
925 structure follows the stream context structure.
927 An example of stream-level event context is to save the event payload size with
928 each event, or to save the current PID with each event. These are declared
929 within the stream declaration within the meta-data:
933 event.context := struct {
935 uint16_t payload_size;
939 An example of event-specific event context is to declare a bitmap of missing
940 fields, only appended after the stream event context if the extended event
941 header is selected. NR_FIELDS is the number of fields within the event (a
949 uint1_t missing_fields[NR_FIELDS]; /* missing event fields bitmap */
958 An event payload contains fields specific to a given event type. The fields
959 belonging to an event type are described in the event-specific meta-data
960 within a structure type.
964 No padding at the end of the event payload. This differs from the ISO/C standard
965 for structures, but follows the CTF standard for structures. In a trace, even
966 though it makes sense to align the beginning of a structure, it really makes no
967 sense to add padding at the end of the structure, because structures are usually
968 not followed by a structure of the same type.
970 This trick can be done by adding a zero-length "end" field at the end of the C
971 structures, and by using the offset of this field rather than using sizeof()
972 when calculating the size of a structure (see Appendix "A. Helper macros").
976 The event payload is aligned on the largest alignment required by types
977 contained within the payload. (This follows the ISO/C standard for structures)
980 7. Trace Stream Description Language (TSDL)
982 The Trace Stream Description Language (TSDL) allows expression of the
983 binary trace streams layout in a C99-like Domain Specific Language
989 The trace stream layout description is located in the trace meta-data.
990 The meta-data is itself located in a stream identified by its name:
993 The meta-data description can be expressed in two different formats:
994 text-only and packet-based. The text-only description facilitates
995 generation of meta-data and provides a convenient way to enter the
996 meta-data information by hand. The packet-based meta-data provides the
997 CTF stream packet facilities (checksumming, compression, encryption,
998 network-readiness) for meta-data stream generated and transported by a
1001 The text-only meta-data file is a plain-text TSDL description. This file
1002 must begin with the following characters to identify the file as a CTF
1003 TSDL text-based metadata file (without the double-quotes) :
1007 It must be followed by a space, and the version of the specification
1008 followed by the CTF trace, e.g.:
1012 These characters allow automated discovery of file type and CTF
1013 specification version. They are interpreted as a the beginning of a
1014 comment by the TSDL metadata parser. The comment can be continued to
1015 contain extra commented characters before it is closed.
1017 The packet-based meta-data is made of "meta-data packets", which each
1018 start with a meta-data packet header. The packet-based meta-data
1019 description is detected by reading the magic number "0x75D11D57" at the
1020 beginning of the file. This magic number is also used to detect the
1021 endianness of the architecture by trying to read the CTF magic number
1022 and its counterpart in reversed endianness. The events within the
1023 meta-data stream have no event header nor event context. Each event only
1024 contains a special "sequence" payload, which is a sequence of bits which
1025 length is implicitly calculated by using the
1026 "trace.packet.header.content_size" field, minus the packet header size.
1027 The formatting of this sequence of bits is a plain-text representation
1028 of the TSDL description. Each meta-data packet start with a special
1029 packet header, specific to the meta-data stream, which contains,
1032 struct metadata_packet_header {
1033 uint32_t magic; /* 0x75D11D57 */
1034 uint8_t uuid[16]; /* Unique Universal Identifier */
1035 uint32_t checksum; /* 0 if unused */
1036 uint32_t content_size; /* in bits */
1037 uint32_t packet_size; /* in bits */
1038 uint8_t compression_scheme; /* 0 if unused */
1039 uint8_t encryption_scheme; /* 0 if unused */
1040 uint8_t checksum_scheme; /* 0 if unused */
1041 uint8_t major; /* CTF spec version major number */
1042 uint8_t minor; /* CTF spec version minor number */
1045 The packet-based meta-data can be converted to a text-only meta-data by
1046 concatenating all the strings it contains.
1048 In the textual representation of the meta-data, the text contained
1049 within "/*" and "*/", as well as within "//" and end of line, are
1050 treated as comments. Boolean values can be represented as true, TRUE,
1051 or 1 for true, and false, FALSE, or 0 for false. Within the string-based
1052 meta-data description, the trace UUID is represented as a string of
1053 hexadecimal digits and dashes "-". In the event packet header, the trace
1054 UUID is represented as an array of bytes.
1057 7.2 Declaration vs Definition
1059 A declaration associates a layout to a type, without specifying where
1060 this type is located in the event structure hierarchy (see Section 6).
1061 This therefore includes typedef, typealias, as well as all type
1062 specifiers. In certain circumstances (typedef, structure field and
1063 variant field), a declaration is followed by a declarator, which specify
1064 the newly defined type name (for typedef), or the field name (for
1065 declarations located within structure and variants). Array and sequence,
1066 declared with square brackets ("[" "]"), are part of the declarator,
1067 similarly to C99. The enumeration base type is specified by
1068 ": enum_base", which is part of the type specifier. The variant tag
1069 name, specified between "<" ">", is also part of the type specifier.
1071 A definition associates a type to a location in the event structure
1072 hierarchy (see Section 6). This association is denoted by ":=", as shown
1078 TSDL uses three different types of scoping: a lexical scope is used for
1079 declarations and type definitions, and static and dynamic scopes are
1080 used for variants references to tag fields (with relative and absolute
1081 path lookups) and for sequence references to length fields.
1085 Each of "trace", "env", "stream", "event", "struct" and "variant" have
1086 their own nestable declaration scope, within which types can be declared
1087 using "typedef" and "typealias". A root declaration scope also contains
1088 all declarations located outside of any of the aforementioned
1089 declarations. An inner declaration scope can refer to type declared
1090 within its container lexical scope prior to the inner declaration scope.
1091 Redefinition of a typedef or typealias is not valid, although hiding an
1092 upper scope typedef or typealias is allowed within a sub-scope.
1094 7.3.2 Static and Dynamic Scopes
1096 A local static scope consists in the scope generated by the declaration
1097 of fields within a compound type. A static scope is a local static scope
1098 augmented with the nested sub-static-scopes it contains.
1100 A dynamic scope consists in the static scope augmented with the
1101 implicit event structure definition hierarchy presented at Section 6.
1103 Multiple declarations of the same field name within a local static scope
1104 is not valid. It is however valid to re-use the same field name in
1105 different local scopes.
1107 Nested static and dynamic scopes form lookup paths. These are used for
1108 variant tag and sequence length references. They are used at the variant
1109 and sequence definition site to look up the location of the tag field
1110 associated with a variant, and to lookup up the location of the length
1111 field associated with a sequence.
1113 Variants and sequences can refer to a tag field either using a relative
1114 path or an absolute path. The relative path is relative to the scope in
1115 which the variant or sequence performing the lookup is located.
1116 Relative paths are only allowed to lookup within the same static scope,
1117 which includes its nested static scopes. Lookups targeting parent static
1118 scopes need to be performed with an absolute path.
1120 Absolute path lookups use the full path including the dynamic scope
1121 followed by a "." and then the static scope. Therefore, variants (or
1122 sequences) in lower levels in the dynamic scope (e.g. event context) can
1123 refer to a tag (or length) field located in upper levels (e.g. in the
1124 event header) by specifying, in this case, the associated tag with
1125 <stream.event.header.field_name>. This allows, for instance, the event
1126 context to define a variant referring to the "id" field of the event
1129 The dynamic scope prefixes are thus:
1131 - Trace Environment: <env. >,
1132 - Trace Packet Header: <trace.packet.header. >,
1133 - Stream Packet Context: <stream.packet.context. >,
1134 - Event Header: <stream.event.header. >,
1135 - Stream Event Context: <stream.event.context. >,
1136 - Event Context: <event.context. >,
1137 - Event Payload: <event.fields. >.
1140 The target dynamic scope must be specified explicitly when referring to
1141 a field outside of the static scope (absolute scope reference). No
1142 conflict can occur between relative and dynamic paths, because the
1143 keywords "trace", "stream", and "event" are reserved, and thus
1144 not permitted as field names. It is recommended that field names
1145 clashing with CTF and C99 reserved keywords use an underscore prefix to
1146 eliminate the risk of generating a description containing an invalid
1147 field name. Consequently, fields starting with an underscore should have
1148 their leading underscore removed by the CTF trace readers.
1151 The information available in the dynamic scopes can be thought of as the
1152 current tracing context. At trace production, information about the
1153 current context is saved into the specified scope field levels. At trace
1154 consumption, for each event, the current trace context is therefore
1155 readable by accessing the upper dynamic scopes.
1160 The grammar representing the TSDL meta-data is presented in Appendix C.
1161 TSDL Grammar. This section presents a rather lighter reading that
1162 consists in examples of TSDL meta-data, with template values.
1164 The stream "id" can be left out if there is only one stream in the
1165 trace. The event "id" field can be left out if there is only one event
1169 major = value; /* CTF spec version major number */
1170 minor = value; /* CTF spec version minor number */
1171 uuid = "aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa"; /* Trace UUID */
1172 byte_order = be OR le; /* Endianness (required) */
1173 packet.header := struct {
1181 * The "env" (environment) scope contains assignment expressions. The
1182 * field names and content are implementation-defined.
1185 pid = value; /* example */
1186 proc_name = "name"; /* example */
1192 /* Type 1 - Few event IDs; Type 2 - Many event IDs. See section 6.1. */
1193 event.header := event_header_1 OR event_header_2;
1194 event.context := struct {
1197 packet.context := struct {
1203 name = "event_name";
1204 id = value; /* Numeric identifier within the stream */
1205 stream_id = stream_id;
1207 model.emf.uri = "string";
1217 name = "event_name";
1224 /* More detail on types in section 4. Types */
1229 * Type declarations behave similarly to the C standard.
1232 typedef aliased_type_specifiers new_type_declarators;
1234 /* e.g.: typedef struct example new_type_name[10]; */
1239 * The "typealias" declaration can be used to give a name (including
1240 * pointer declarator specifier) to a type. It should also be used to
1241 * map basic C types (float, int, unsigned long, ...) to a CTF type.
1242 * Typealias is a superset of "typedef": it also allows assignment of a
1243 * simple variable identifier to a type.
1246 typealias type_class {
1248 } := type_specifiers type_declarator;
1252 * typealias integer {
1256 * } := struct page *;
1258 * typealias integer {
1273 enum name : integer_type {
1279 * Unnamed types, contained within compound type fields, typedef or typealias.
1294 enum : integer_type {
1298 typedef type new_type[length];
1301 type field_name[length];
1304 typedef type new_type[length_type];
1307 type field_name[length_type];
1319 integer_type field_name:size; /* GNU/C bitfield */
1329 Clock metadata allows to describe the clock topology of the system, as
1330 well as to detail each clock parameter. In absence of clock description,
1331 it is assumed that all fields named "timestamp" use the same clock
1332 source, which increments once per nanosecond.
1334 Describing a clock and how it is used by streams is threefold: first,
1335 the clock and clock topology should be described in a "clock"
1336 description block, e.g.:
1339 name = cycle_counter_sync;
1340 uuid = "62189bee-96dc-11e0-91a8-cfa3d89f3923";
1341 description = "Cycle counter synchronized across CPUs";
1342 freq = 1000000000; /* frequency, in Hz */
1343 /* precision in seconds is: 1000 * (1/freq) */
1346 * clock value offset from Epoch is:
1347 * offset_s + (offset * (1/freq))
1349 offset_s = 1326476837;
1354 The mandatory "name" field specifies the name of the clock identifier,
1355 which can later be used as a reference. The optional field "uuid" is the
1356 unique identifier of the clock. It can be used to correlate different
1357 traces that use the same clock. An optional textual description string
1358 can be added with the "description" field. The "freq" field is the
1359 initial frequency of the clock, in Hz. If the "freq" field is not
1360 present, the frequency is assumed to be 1000000000 (providing clock
1361 increment of 1 ns). The optional "precision" field details the
1362 uncertainty on the clock measurements, in (1/freq) units. The "offset_s"
1363 and "offset" fields indicate the offset from POSIX.1 Epoch, 1970-01-01
1364 00:00:00 +0000 (UTC), to the zero of value of the clock. The "offset_s"
1365 field is in seconds. The "offset" field is in (1/freq) units. If any of
1366 the "offset_s" or "offset" field is not present, it is assigned the 0
1367 value. The field "absolute" is TRUE if the clock is a global reference
1368 across different clock uuid (e.g. NTP time). Otherwise, "absolute" is
1369 FALSE, and the clock can be considered as synchronized only with other
1370 clocks that have the same uuid.
1373 Secondly, a reference to this clock should be added within an integer
1377 size = 64; align = 1; signed = false;
1378 map = clock.cycle_counter_sync.value;
1381 Thirdly, stream declarations can reference the clock they use as a
1384 struct packet_context {
1385 uint64_ccnt_t ccnt_begin;
1386 uint64_ccnt_t ccnt_end;
1392 event.header := struct {
1393 uint64_ccnt_t timestamp;
1396 packet.context := struct packet_context;
1399 For a N-bit integer type referring to a clock, if the integer overflows
1400 compared to the N low order bits of the clock prior value found in the
1401 same stream, then it is assumed that one, and only one, overflow
1402 occurred. It is therefore important that events encoding time on a small
1403 number of bits happen frequently enough to detect when more than one
1404 N-bit overflow occurs.
1406 In a packet context, clock field names ending with "_begin" and "_end"
1407 have a special meaning: this refers to the time-stamps at, respectively,
1408 the beginning and the end of each packet.
1413 The two following macros keep track of the size of a GNU/C structure without
1414 padding at the end by placing HEADER_END as the last field. A one byte end field
1415 is used for C90 compatibility (C99 flexible arrays could be used here). Note
1416 that this does not affect the effective structure size, which should always be
1417 calculated with the header_sizeof() helper.
1419 #define HEADER_END char end_field
1420 #define header_sizeof(type) offsetof(typeof(type), end_field)
1423 B. Stream Header Rationale
1425 An event stream is divided in contiguous event packets of variable size. These
1426 subdivisions allow the trace analyzer to perform a fast binary search by time
1427 within the stream (typically requiring to index only the event packet headers)
1428 without reading the whole stream. These subdivisions have a variable size to
1429 eliminate the need to transfer the event packet padding when partially filled
1430 event packets must be sent when streaming a trace for live viewing/analysis.
1431 An event packet can contain a certain amount of padding at the end. Dividing
1432 streams into event packets is also useful for network streaming over UDP and
1433 flight recorder mode tracing (a whole event packet can be swapped out of the
1434 buffer atomically for reading).
1436 The stream header is repeated at the beginning of each event packet to allow
1437 flexibility in terms of:
1439 - streaming support,
1440 - allowing arbitrary buffers to be discarded without making the trace
1442 - allow UDP packet loss handling by either dealing with missing event packet
1443 or asking for re-transmission.
1444 - transparently support flight recorder mode,
1445 - transparently support crash dump.
1451 * Common Trace Format (CTF) Trace Stream Description Language (TSDL) Grammar.
1453 * Inspired from the C99 grammar:
1454 * http://www.open-std.org/jtc1/sc22/wg14/www/docs/n1124.pdf (Annex A)
1455 * and c++1x grammar (draft)
1456 * http://www.open-std.org/jtc1/sc22/wg21/docs/papers/2011/n3291.pdf (Annex A)
1458 * Specialized for CTF needs by including only constant and declarations from
1459 * C99 (excluding function declarations), and by adding support for variants,
1460 * sequences and CTF-specific specifiers. Enumeration container types
1461 * semantic is inspired from c++1x enum-base.
1466 1.1) Lexical elements
1513 identifier identifier-nondigit
1516 identifier-nondigit:
1518 universal-character-name
1519 any other implementation-defined characters
1523 [a-zA-Z] /* regular expression */
1526 [0-9] /* regular expression */
1528 1.4) Universal character names
1530 universal-character-name:
1532 \U hex-quad hex-quad
1535 hexadecimal-digit hexadecimal-digit hexadecimal-digit hexadecimal-digit
1541 enumeration-constant
1545 decimal-constant integer-suffix-opt
1546 octal-constant integer-suffix-opt
1547 hexadecimal-constant integer-suffix-opt
1551 decimal-constant digit
1555 octal-constant octal-digit
1557 hexadecimal-constant:
1558 hexadecimal-prefix hexadecimal-digit
1559 hexadecimal-constant hexadecimal-digit
1569 unsigned-suffix long-suffix-opt
1570 unsigned-suffix long-long-suffix
1571 long-suffix unsigned-suffix-opt
1572 long-long-suffix unsigned-suffix-opt
1586 enumeration-constant:
1592 L' c-char-sequence '
1596 c-char-sequence c-char
1599 any member of source charset except single-quote ('), backslash
1600 (\), or new-line character.
1604 simple-escape-sequence
1605 octal-escape-sequence
1606 hexadecimal-escape-sequence
1607 universal-character-name
1609 simple-escape-sequence: one of
1610 \' \" \? \\ \a \b \f \n \r \t \v
1612 octal-escape-sequence:
1614 \ octal-digit octal-digit
1615 \ octal-digit octal-digit octal-digit
1617 hexadecimal-escape-sequence:
1618 \x hexadecimal-digit
1619 hexadecimal-escape-sequence hexadecimal-digit
1621 1.6) String literals
1624 " s-char-sequence-opt "
1625 L" s-char-sequence-opt "
1629 s-char-sequence s-char
1632 any member of source charset except double-quote ("), backslash
1633 (\), or new-line character.
1639 [ ] ( ) { } . -> * + - < > : ; ... = ,
1642 2) Phrase structure grammar
1648 ( unary-expression )
1652 postfix-expression [ unary-expression ]
1653 postfix-expression . identifier
1654 postfix-expressoin -> identifier
1658 unary-operator postfix-expression
1660 unary-operator: one of
1663 assignment-operator:
1666 type-assignment-operator:
1669 constant-expression-range:
1670 unary-expression ... unary-expression
1675 declaration-specifiers declarator-list-opt ;
1678 declaration-specifiers:
1679 storage-class-specifier declaration-specifiers-opt
1680 type-specifier declaration-specifiers-opt
1681 type-qualifier declaration-specifiers-opt
1685 declarator-list , declarator
1687 abstract-declarator-list:
1689 abstract-declarator-list , abstract-declarator
1691 storage-class-specifier:
1714 align ( unary-expression )
1717 struct identifier-opt { struct-or-variant-declaration-list-opt } align-attribute-opt
1718 struct identifier align-attribute-opt
1720 struct-or-variant-declaration-list:
1721 struct-or-variant-declaration
1722 struct-or-variant-declaration-list struct-or-variant-declaration
1724 struct-or-variant-declaration:
1725 specifier-qualifier-list struct-or-variant-declarator-list ;
1726 declaration-specifiers-opt storage-class-specifier declaration-specifiers-opt declarator-list ;
1727 typealias declaration-specifiers abstract-declarator-list type-assignment-operator declaration-specifiers abstract-declarator-list ;
1728 typealias declaration-specifiers abstract-declarator-list type-assignment-operator declarator-list ;
1730 specifier-qualifier-list:
1731 type-specifier specifier-qualifier-list-opt
1732 type-qualifier specifier-qualifier-list-opt
1734 struct-or-variant-declarator-list:
1735 struct-or-variant-declarator
1736 struct-or-variant-declarator-list , struct-or-variant-declarator
1738 struct-or-variant-declarator:
1740 declarator-opt : unary-expression
1743 variant identifier-opt variant-tag-opt { struct-or-variant-declaration-list }
1744 variant identifier variant-tag
1747 < unary-expression >
1750 enum identifier-opt { enumerator-list }
1751 enum identifier-opt { enumerator-list , }
1753 enum identifier-opt : declaration-specifiers { enumerator-list }
1754 enum identifier-opt : declaration-specifiers { enumerator-list , }
1758 enumerator-list , enumerator
1761 enumeration-constant
1762 enumeration-constant assignment-operator unary-expression
1763 enumeration-constant assignment-operator constant-expression-range
1769 pointer-opt direct-declarator
1774 direct-declarator [ unary-expression ]
1776 abstract-declarator:
1777 pointer-opt direct-abstract-declarator
1779 direct-abstract-declarator:
1781 ( abstract-declarator )
1782 direct-abstract-declarator [ unary-expression ]
1783 direct-abstract-declarator [ ]
1786 * type-qualifier-list-opt
1787 * type-qualifier-list-opt pointer
1789 type-qualifier-list:
1791 type-qualifier-list type-qualifier
1796 2.3) CTF-specific declarations
1799 clock { ctf-assignment-expression-list-opt }
1800 event { ctf-assignment-expression-list-opt }
1801 stream { ctf-assignment-expression-list-opt }
1802 env { ctf-assignment-expression-list-opt }
1803 trace { ctf-assignment-expression-list-opt }
1804 callsite { ctf-assignment-expression-list-opt }
1805 typealias declaration-specifiers abstract-declarator-list type-assignment-operator declaration-specifiers abstract-declarator-list
1806 typealias declaration-specifiers abstract-declarator-list type-assignment-operator declarator-list
1809 floating_point { ctf-assignment-expression-list-opt }
1810 integer { ctf-assignment-expression-list-opt }
1811 string { ctf-assignment-expression-list-opt }
1814 ctf-assignment-expression-list:
1815 ctf-assignment-expression ;
1816 ctf-assignment-expression-list ctf-assignment-expression ;
1818 ctf-assignment-expression:
1819 unary-expression assignment-operator unary-expression
1820 unary-expression type-assignment-operator type-specifier
1821 declaration-specifiers-opt storage-class-specifier declaration-specifiers-opt declarator-list
1822 typealias declaration-specifiers abstract-declarator-list type-assignment-operator declaration-specifiers abstract-declarator-list
1823 typealias declaration-specifiers abstract-declarator-list type-assignment-operator declarator-list