-RFC: Common Trace Format (CTF) Proposal (v1.6)
+RFC: Common Trace Format (CTF) Proposal (pre-v1.7)
Mathieu Desnoyers, EfficiOS Inc.
values to strings. An enumeration from the C language can be represented in
this format by having the same start_value and end_value for each element, which
is in fact a range of size 1. This single-value range is supported without
-repeating the start and end values with the value = string declaration. If the
-<integer_type> is omitted, the type chosen by the C compiler to hold the
-enumeration is used. The <integer_type> specifier can only be omitted for
-enumerations containing only simple "value -> string" mappings (compatible with
-C).
+repeating the start and end values with the value = string declaration.
-enum <integer_type> name {
+If a numeric value is encountered between < >, it represents the integer type
+size used to hold the enumeration, in bits.
+
+enum <integer_type OR size> name {
string = start_value1 ... end_value1,
"other string" = start_value2 ... end_value2,
yet_another_string, /* will be assigned to end_value2 + 1 */
If the values are omitted, the enumeration starts at 0 and increment of 1 for
each entry:
-enum name {
+enum <32> name {
ZERO,
ONE,
TWO,
...
}
-4.2.2 Arrays
+4.2.2 Variants (Discriminated/Tagged Unions)
+
+A CTF variant is a selection between different types. A CTF variant must always
+be defined within the scope of a structure or within fields contained within a
+structure (defined recursively). A "tag" enumeration field must appear in either
+the same lexical scope or an uppermost scope, prior to the variant field (in
+field declaration order). The type selection is indicated by the mapping from
+the enumeration value to the string used as variant type selector. The field to
+use as tag is specified by the "tag_field", specified between "< >" after the
+"variant" keyword for unnamed variants, and after "variant name" for named
+variants.
+
+The alignment of the variant is the alignment of the type as selected by the tag
+value for the specific instance of the variant. The alignment of the type
+containing the variant is independent of the variant alignment. The size of the
+variant is the size as selected by the tag value for the specific instance of
+the variant.
+
+A named variant declaration followed by its definition within a structure
+declaration:
+
+variant name {
+ field_type sel1;
+ field_type sel2;
+ field_type sel3;
+ ...
+};
+
+struct {
+ enum <integer_type or size> { sel1, sel2, sel3, ... } tag_field;
+ ...
+ variant name <tag_field> v;
+}
+
+An unnamed variant definition within a structure is expressed by the following
+metadata:
+
+struct {
+ enum <integer_type or size> { sel1, sel2, sel3, ... } tag_field;
+ ...
+ variant <tag_field> {
+ field_type sel1;
+ field_type sel2;
+ field_type sel3;
+ ...
+ } v;
+}
+
+Example of a named variant within a sequence that refers to a single tag field:
+
+variant example {
+ uint32_t a;
+ uint64_t b;
+ short c;
+};
+
+struct {
+ enum <uint2_t> { a, b, c } choice;
+ variant example <choice> v[unsigned int];
+}
+
+Example of an unnamed variant:
+
+struct {
+ enum <uint2_t> { a, b, c, d } choice;
+ /* Unrelated fields can be added between the variant and its tag */
+ int32_t somevalue;
+ variant <choice> {
+ uint32_t a;
+ uint64_t b;
+ short c;
+ struct {
+ unsigned int field1;
+ uint64_t field2;
+ } d;
+ } s;
+}
+
+Example of an unnamed variant within an array:
+
+struct {
+ enum <uint2_t> { a, b, c } choice;
+ variant <choice> {
+ uint32_t a;
+ uint64_t b;
+ short c;
+ } v[10];
+}
+
+Example of a variant type definition within a structure, where the defined type
+is then declared within an array of structures. This variant refers to a tag
+located in an upper lexical scope. This example clearly shows that a variant
+type definition referring to the tag "x" uses the closest preceding field from
+the lexical scope of the type definition.
+
+struct {
+ enum <uint2_t> { a, b, c, d } x;
+
+ typedef variant <x> { /*
+ * "x" refers to the preceding "x" enumeration in the
+ * lexical scope of the type definition.
+ */
+ uint32_t a;
+ uint64_t b;
+ short c;
+ } example_variant;
+
+ struct {
+ enum <int> { x, y, z } x; /* This enumeration is not used by "v". */
+ example_variant v; /*
+ * "v" uses the "enum <uint2_t> { a, b, c, d }"
+ * tag.
+ */
+ } a[10];
+}
+
+4.2.3 Arrays
Arrays are fixed-length. Their length is declared in the type declaration within
the metadata. They contain an array of "inner type" elements, which can refer to
uint8_t field_name[10];
-4.2.3 Sequences
+4.2.4 Sequences
Sequences are dynamically-sized arrays. They start with an integer that specify
the length of the sequence, followed by an array of "inner type" elements.
The length type follows the integer types specifications, and the sequence
elements follow the "array" specifications.
-4.2.4 Strings
+4.2.5 Strings
Strings are an array of bytes of variable size and are terminated by a '\0'
"NULL" character. Their encoding is described in the metadata. In absence of
uint8_t checksum;
};
+
6. Event Structure
The overall structure of an event is:
- - Event Header (as specifed by the stream metadata)
- - Extended Event Header (as specified by the event header)
- - Event Context (as specified by the stream metadata)
- - Event Payload (as specified by the event metadata)
+1 - Stream Packet Context (as specified by the stream metadata)
+2 - Event Header (as specifed by the stream metadata)
+3 - Stream Event Context (as specified by the stream metadata)
+4 - Event Context (as specified by the event metadata)
+5 - Event Payload (as specified by the event metadata)
+
+6.1 Lexical Scope
+
+The lexical scope of each structure (stream packet context, header, stream event
+context, event context and payload) is extended in the following way: lower
+levels (e.g. 3) can refer to fields defined in prior levels (e.g. 2 and 1). The
+field in the closest level has priority in case of field name conflict.
+
+This allows, for instance, the event context to define a variant refering to the
+"id" field of the event header as selector.
+6.2 Event Header
-6.1 Event Header
+Event headers can be described within the metadata. We hereby propose, as an
+example, two types of events headers. Type 1 accommodates streams with less than
+31 event IDs. Type 2 accommodates streams with 31 or more event IDs.
One major factor can vary between streams: the number of event IDs assigned to
a stream. Luckily, this information tends to stay relatively constant (modulo
many event IDs, so we end up representing the event ID and timestamp as densely
as possible in each case.
-We therefore provide two types of events headers. Type 1 accommodates streams
-with less than 31 event IDs. Type 2 accommodates streams with 31 or more event
-IDs.
-
-The "extended headers" are used in the rare occasions where the information
-cannot be represented in the ranges available in the event header. They are also
+The header is extended in the rare occasions where the information cannot be
+represented in the ranges available in the standard event header. They are also
used in the rare occasions where the data required for a field could not be
collected: the flag corresponding to the missing field within the missing_fields
array is then set to 1.
Types uintX_t represent an X-bit unsigned integer.
-6.1.1 Type 1 - Few event IDs
+6.2.1 Type 1 - Few event IDs
- Aligned on 32-bit (or 8-bit if byte-packed, depending on the architecture
preference).
- - Fixed size: 32 bits.
- Native architecture byte ordering.
+ - For "compact" selection
+ - Fixed size: 32 bits.
+ - For "extended" selection
+ - Size depends on the architecture and variant alignment.
struct event_header_1 {
- uint5_t id; /*
- * id: range: 0 - 30.
- * id 31 is reserved to indicate a following
- * extended header.
- */
- uint27_t timestamp;
+ /*
+ * id: range: 0 - 30.
+ * id 31 is reserved to indicate an extended header.
+ */
+ enum <uint5_t> { compact = 0 ... 30, extended = 31 } id;
+ variant <id> {
+ struct {
+ uint27_t timestamp;
+ } compact;
+ struct {
+ uint32_t id; /* 32-bit event IDs */
+ uint64_t timestamp; /* 64-bit timestamps */
+ } extended;
+ } v;
};
-The end of a type 1 header is aligned on a 32-bit boundary (or packed).
-
-6.1.2 Extended Type 1 Event Header
-
- - Follows struct event_header_1, which is aligned on 32-bit, so no need to
- realign.
- - Variable size (depends on the number of fields per event).
- - Native architecture byte ordering.
- - NR_FIELDS is the number of fields within the event.
+6.2.2 Type 2 - Many event IDs
-struct event_header_1_ext {
- uint32_t id; /* 32-bit event IDs */
- uint64_t timestamp; /* 64-bit timestamps */
- uint1_t missing_fields[NR_FIELDS]; /* missing event fields bitmap */
-};
-
-
-6.1.3 Type 2 - Many event IDs
-
- - Aligned on 32-bit (or 8-bit if byte-packed, depending on the architecture
+ - Aligned on 16-bit (or 8-bit if byte-packed, depending on the architecture
preference).
- - Fixed size: 48 bits.
- Native architecture byte ordering.
+ - For "compact" selection
+ - Size depends on the architecture and variant alignment.
+ - For "extended" selection
+ - Size depends on the architecture and variant alignment.
struct event_header_2 {
- uint32_t timestamp;
- uint16_t id; /*
- * id: range: 0 - 65534.
- * id 65535 is reserved to indicate a following
- * extended header.
- */
-};
-
-The end of a type 2 header is aligned on a 16-bit boundary (or 8-bit if
-byte-packed).
-
-
-6.1.4 Extended Type 2 Event Header
-
- - Follows struct event_header_2, which alignment end on a 16-bit boundary, so
- we need to align on 64-bit integer architecture alignment (or 8-bit if
- byte-packed).
- - Variable size (depends on the number of fields per event).
- - Native architecture byte ordering.
- - NR_FIELDS is the number of fields within the event.
-
-struct event_header_2_ext {
- uint64_t timestamp; /* 64-bit timestamps */
- uint32_t id; /* 32-bit event IDs */
- uint1_t missing_fields[NR_FIELDS]; /* missing event fields bitmap */
+ /*
+ * id: range: 0 - 65534.
+ * id 65535 is reserved to indicate an extended header.
+ */
+ enum <uint16_t> { compact = 0 ... 65534, extended = 65535 } id;
+ variant <id> {
+ struct {
+ uint32_t timestamp;
+ } compact;
+ struct {
+ uint32_t id; /* 32-bit event IDs */
+ uint64_t timestamp; /* 64-bit timestamps */
+ } extended;
+ } v;
};
6.2 Event Context
The event context contains information relative to the current event. The choice
-and meaning of this information is specified by the metadata "stream"
-information. For this trace format, event context is usually empty, except when
-the metadata "stream" information specifies otherwise by declaring a non-empty
-structure for the event context. An example of event context is to save the
-event payload size with each event, or to save the current PID with each event.
-These are declared within the stream declaration within the metadata.
+and meaning of this information is specified by the metadata "stream" and
+"event" information. The "stream" context is applied to all events within the
+stream. The "stream" context structure follows the event header. The "event"
+context is applied to specific events. Its structure follows the "stream"
+context stucture.
-An example event context type:
+An example of stream-level event context is to save the event payload size with
+each event, or to save the current PID with each event. These are declared
+within the stream declaration within the metadata:
- struct event_context {
+ stream {
+ ...
+ event {
+ ...
+ context = struct {
uint pid;
uint16_t payload_size;
};
+ }
+ };
+An example of event-specific event context is to declare a bitmap of missing
+fields, only appended after the stream event context if the extended event
+header is selected. NR_FIELDS is the number of fields within the event (a
+numeric value).
+
+ event {
+ context = struct {
+ variant <id> {
+ struct { } compact;
+ struct {
+ uint1_t missing_fields[NR_FIELDS]; /* missing event fields bitmap */
+ } extended;
+ } v;
+ };
+ ...
+ }
6.3 Event Payload
contained within the payload. (This follows the ISO/C standard for structures)
-
7. Metadata
The meta-data is located in a stream named "metadata". It is made of "event
and trace UUID.
The metadata can be parsed by reading through the metadata strings, skipping
-newlines and null-characters. Type names may contain spaces.
+newlines and null-characters. Type names are made of a single identifier, and
+can be surrounded by prefix/postfix. Text contained within "/*" and "*/", as
+well as within "//" and end of line, are treated as comments. Boolean values can
+be represented as true, TRUE, or 1 for true, and false, FALSE, or 0 for false.
+
+The grammar representing the CTF metadata is presented in
+Appendix C. CTF Metadata Grammar.
trace {
major = value; /* Trace format version */
stream {
id = stream_id;
- event {
- /* Type 1 - Few event IDs; Type 2 - Many event IDs. See section 6.1. */
- header_type = event_header_1 OR event_header_2;
- /*
- * Extended event header type. Only present if specified in event header
- * on a per-event basis.
- */
- header_type_ext = event_header_1_ext OR event_header_2_ext;
- context_type = struct {
- ...
- };
+ /* Type 1 - Few event IDs; Type 2 - Many event IDs. See section 6.2. */
+ event.header = event_header_1 OR event_header_2;
+ event.context = struct {
+ ...
};
- packet {
- context_type = struct {
- ...
- };
+ packet.context = struct {
+ ...
};
};
name = event_name;
id = value; /* Numeric identifier within the stream */
stream = stream_id;
+ context = struct {
+ ...
+ };
fields = struct {
...
};
/*
* Named types:
*
- * A named type can only have a prefix and postfix if it aliases a CTF basic
- * type. A type name aliasing another type name cannot have prefix nor postfix,
- * but the type aliased can have a prefix and/or postfix.
+ * Type declarations behave similarly to the C standard, with the following
+ * added feature: new_type can be preceded by a colon to allow creation of a
+ * type name with prefix/postfix.
*/
typedef aliased_type_prefix aliased_type new_type aliased_type_postfix;
typedef type_class {
...
-} new_type_prefix new_type new_type_postfix;
+} : new_type_prefix new_type new_type_postfix;
/*
* e.g.:
* size = 32;
* align = 32;
* signed = false;
- * } struct page *;
+ * } : struct page *;
*/
struct name {
...
};
-enum <integer_type> name {
+variant name {
+ ...
+};
+
+enum <integer_type or size> name {
...
};
...
}
-enum <integer_type> {
+variant {
+ ...
+}
+
+enum <integer_type or size> {
...
}
string field_name;
}
+
A. Helper macros
The two following macros keep track of the size of a GNU/C structure without
The event stream header will therefore be referred to as the "event packet
header" throughout the rest of this document.
+
+C. CTF Metadata Grammar
+
+TODO
projects / ctf.git / blobdiff