xref: /openbmc/linux/tools/perf/Documentation/perf.data-file-format.txt (revision 93707cbabcc8baf2b2b5f4a99c1f08ee83eb7abd)
1perf.data format
2
3Uptodate as of v4.7
4
5This document describes the on-disk perf.data format, generated by perf record
6or perf inject and consumed by the other perf tools.
7
8On a high level perf.data contains the events generated by the PMUs, plus metadata.
9
10All fields are in native-endian of the machine that generated the perf.data.
11
12When perf is writing to a pipe it uses a special version of the file
13format that does not rely on seeking to adjust data offsets.  This
14format is described in "Pipe-mode data" section. The pipe data version can be
15augmented with additional events using perf inject.
16
17The file starts with a perf_header:
18
19struct perf_header {
20	char magic[8];		/* PERFILE2 */
21	uint64_t size;		/* size of the header */
22	uint64_t attr_size;	/* size of an attribute in attrs */
23	struct perf_file_section attrs;
24	struct perf_file_section data;
25	struct perf_file_section event_types;
26	uint64_t flags;
27	uint64_t flags1[3];
28};
29
30The magic number identifies the perf file and the version. Current perf versions
31use PERFILE2. Old perf versions generated a version 1 format (PERFFILE). Version 1
32is not described here. The magic number also identifies the endian. When the
33magic value is 64bit byte swapped compared the file is in non-native
34endian.
35
36A perf_file_section contains a pointer to another section of the perf file.
37The header contains three such pointers: for attributes, data and event types.
38
39struct perf_file_section {
40	uint64_t offset;	/* offset from start of file */
41	uint64_t size;		/* size of the section */
42};
43
44Flags section:
45
46The header is followed by different optional headers, described by the bits set
47in flags. Only headers for which the bit is set are included. Each header
48consists of a perf_file_section located after the initial header.
49The respective perf_file_section points to the data of the additional
50header and defines its size.
51
52Some headers consist of strings, which are defined like this:
53
54struct perf_header_string {
55       uint32_t len;
56       char string[len]; /* zero terminated */
57};
58
59Some headers consist of a sequence of strings, which start with a
60
61struct perf_header_string_list {
62     uint32_t nr;
63     struct perf_header_string strings[nr]; /* variable length records */
64};
65
66The bits are the flags bits in a 256 bit bitmap starting with
67flags. These define the valid bits:
68
69	HEADER_RESERVED		= 0,	/* always cleared */
70	HEADER_FIRST_FEATURE	= 1,
71	HEADER_TRACING_DATA	= 1,
72
73Describe me.
74
75	HEADER_BUILD_ID = 2,
76
77The header consists of an sequence of build_id_event. The size of each record
78is defined by header.size (see perf_event.h). Each event defines a ELF build id
79for a executable file name for a pid. An ELF build id is a unique identifier
80assigned by the linker to an executable.
81
82struct build_id_event {
83	struct perf_event_header header;
84	pid_t			 pid;
85	uint8_t			 build_id[24];
86	char			 filename[header.size - offsetof(struct build_id_event, filename)];
87};
88
89	HEADER_HOSTNAME = 3,
90
91A perf_header_string with the hostname where the data was collected
92(uname -n)
93
94	HEADER_OSRELEASE = 4,
95
96A perf_header_string with the os release where the data was collected
97(uname -r)
98
99	HEADER_VERSION = 5,
100
101A perf_header_string with the perf user tool version where the
102data was collected. This is the same as the version of the source tree
103the perf tool was built from.
104
105	HEADER_ARCH = 6,
106
107A perf_header_string with the CPU architecture (uname -m)
108
109	HEADER_NRCPUS = 7,
110
111A structure defining the number of CPUs.
112
113struct nr_cpus {
114       uint32_t nr_cpus_online;
115       uint32_t nr_cpus_available; /* CPUs not yet onlined */
116};
117
118	HEADER_CPUDESC = 8,
119
120A perf_header_string with description of the CPU. On x86 this is the model name
121in /proc/cpuinfo
122
123	HEADER_CPUID = 9,
124
125A perf_header_string with the exact CPU type. On x86 this is
126vendor,family,model,stepping. For example: GenuineIntel,6,69,1
127
128	HEADER_TOTAL_MEM = 10,
129
130An uint64_t with the total memory in bytes.
131
132	HEADER_CMDLINE = 11,
133
134A perf_header_string with the perf command line used to collect the data.
135
136	HEADER_EVENT_DESC = 12,
137
138Another description of the perf_event_attrs, more detailed than header.attrs
139including IDs and names. See perf_event.h or the man page for a description
140of a struct perf_event_attr.
141
142struct {
143       uint32_t nr; /* number of events */
144       uint32_t attr_size; /* size of each perf_event_attr */
145       struct {
146	      struct perf_event_attr attr;  /* size of attr_size */
147	      uint32_t nr_ids;
148	      struct perf_header_string event_string;
149	      uint64_t ids[nr_ids];
150       } events[nr]; /* Variable length records */
151};
152
153	HEADER_CPU_TOPOLOGY = 13,
154
155String lists defining the core and CPU threads topology.
156
157struct {
158       struct perf_header_string_list cores; /* Variable length */
159       struct perf_header_string_list threads; /* Variable length */
160};
161
162Example:
163	sibling cores   : 0-3
164	sibling threads : 0-1
165	sibling threads : 2-3
166
167	HEADER_NUMA_TOPOLOGY = 14,
168
169	A list of NUMA node descriptions
170
171struct {
172       uint32_t nr;
173       struct {
174	      uint32_t nodenr;
175	      uint64_t mem_total;
176	      uint64_t mem_free;
177	      struct perf_header_string cpus;
178       } nodes[nr]; /* Variable length records */
179};
180
181	HEADER_BRANCH_STACK = 15,
182
183Not implemented in perf.
184
185	HEADER_PMU_MAPPINGS = 16,
186
187	A list of PMU structures, defining the different PMUs supported by perf.
188
189struct {
190       uint32_t nr;
191       struct pmu {
192	      uint32_t pmu_type;
193	      struct perf_header_string pmu_name;
194       } [nr]; /* Variable length records */
195};
196
197	HEADER_GROUP_DESC = 17,
198
199	Description of counter groups ({...} in perf syntax)
200
201struct {
202         uint32_t nr;
203         struct {
204		struct perf_header_string string;
205		uint32_t leader_idx;
206		uint32_t nr_members;
207	 } [nr]; /* Variable length records */
208};
209
210	HEADER_AUXTRACE = 18,
211
212Define additional auxtrace areas in the perf.data. auxtrace is used to store
213undecoded hardware tracing information, such as Intel Processor Trace data.
214
215/**
216 * struct auxtrace_index_entry - indexes a AUX area tracing event within a
217 *                               perf.data file.
218 * @file_offset: offset within the perf.data file
219 * @sz: size of the event
220 */
221struct auxtrace_index_entry {
222	u64			file_offset;
223	u64			sz;
224};
225
226#define PERF_AUXTRACE_INDEX_ENTRY_COUNT 256
227
228/**
229 * struct auxtrace_index - index of AUX area tracing events within a perf.data
230 *                         file.
231 * @list: linking a number of arrays of entries
232 * @nr: number of entries
233 * @entries: array of entries
234 */
235struct auxtrace_index {
236	struct list_head	list;
237	size_t			nr;
238	struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
239};
240
241	HEADER_STAT = 19,
242
243This is merely a flag signifying that the data section contains data
244recorded from perf stat record.
245
246	HEADER_CACHE = 20,
247
248Description of the cache hierarchy. Based on the Linux sysfs format
249in /sys/devices/system/cpu/cpu*/cache/
250
251	u32 version	Currently always 1
252	u32 number_of_cache_levels
253
254struct {
255	u32	level;
256	u32	line_size;
257	u32	sets;
258	u32	ways;
259	struct perf_header_string type;
260	struct perf_header_string size;
261	struct perf_header_string map;
262}[number_of_cache_levels];
263
264	HEADER_SAMPLE_TIME = 21,
265
266Two uint64_t for the time of first sample and the time of last sample.
267
268	other bits are reserved and should ignored for now
269	HEADER_FEAT_BITS	= 256,
270
271Attributes
272
273This is an array of perf_event_attrs, each attr_size bytes long, which defines
274each event collected. See perf_event.h or the man page for a detailed
275description.
276
277Data
278
279This section is the bulk of the file. It consist of a stream of perf_events
280describing events. This matches the format generated by the kernel.
281See perf_event.h or the manpage for a detailed description.
282
283Some notes on parsing:
284
285Ordering
286
287The events are not necessarily in time stamp order, as they can be
288collected in parallel on different CPUs. If the events should be
289processed in time order they need to be sorted first. It is possible
290to only do a partial sort using the FINISHED_ROUND event header (see
291below). perf record guarantees that there is no reordering over a
292FINISHED_ROUND.
293
294ID vs IDENTIFIER
295
296When the event stream contains multiple events each event is identified
297by an ID. This can be either through the PERF_SAMPLE_ID or the
298PERF_SAMPLE_IDENTIFIER header. The PERF_SAMPLE_IDENTIFIER header is
299at a fixed offset from the event header, which allows reliable
300parsing of the header. Relying on ID may be ambiguous.
301IDENTIFIER is only supported by newer Linux kernels.
302
303Perf record specific events:
304
305In addition to the kernel generated event types perf record adds its
306own event types (in addition it also synthesizes some kernel events,
307for example MMAP events)
308
309	PERF_RECORD_USER_TYPE_START		= 64,
310	PERF_RECORD_HEADER_ATTR			= 64,
311
312struct attr_event {
313	struct perf_event_header header;
314	struct perf_event_attr attr;
315	uint64_t id[];
316};
317
318	PERF_RECORD_HEADER_EVENT_TYPE		= 65, /* deprecated */
319
320#define MAX_EVENT_NAME 64
321
322struct perf_trace_event_type {
323	uint64_t	event_id;
324	char	name[MAX_EVENT_NAME];
325};
326
327struct event_type_event {
328	struct perf_event_header header;
329	struct perf_trace_event_type event_type;
330};
331
332
333	PERF_RECORD_HEADER_TRACING_DATA		= 66,
334
335Describe me
336
337struct tracing_data_event {
338	struct perf_event_header header;
339	uint32_t size;
340};
341
342	PERF_RECORD_HEADER_BUILD_ID		= 67,
343
344Define a ELF build ID for a referenced executable.
345
346       struct build_id_event;   /* See above */
347
348	PERF_RECORD_FINISHED_ROUND		= 68,
349
350No event reordering over this header. No payload.
351
352	PERF_RECORD_ID_INDEX			= 69,
353
354Map event ids to CPUs and TIDs.
355
356struct id_index_entry {
357	uint64_t id;
358	uint64_t idx;
359	uint64_t cpu;
360	uint64_t tid;
361};
362
363struct id_index_event {
364	struct perf_event_header header;
365	uint64_t nr;
366	struct id_index_entry entries[nr];
367};
368
369	PERF_RECORD_AUXTRACE_INFO		= 70,
370
371Auxtrace type specific information. Describe me
372
373struct auxtrace_info_event {
374	struct perf_event_header header;
375	uint32_t type;
376	uint32_t reserved__; /* For alignment */
377	uint64_t priv[];
378};
379
380	PERF_RECORD_AUXTRACE			= 71,
381
382Defines auxtrace data. Followed by the actual data. The contents of
383the auxtrace data is dependent on the event and the CPU. For example
384for Intel Processor Trace it contains Processor Trace data generated
385by the CPU.
386
387struct auxtrace_event {
388	struct perf_event_header header;
389	uint64_t size;
390	uint64_t offset;
391	uint64_t reference;
392	uint32_t idx;
393	uint32_t tid;
394	uint32_t cpu;
395	uint32_t reserved__; /* For alignment */
396};
397
398struct aux_event {
399	struct perf_event_header header;
400	uint64_t	aux_offset;
401	uint64_t	aux_size;
402	uint64_t	flags;
403};
404
405	PERF_RECORD_AUXTRACE_ERROR		= 72,
406
407Describes an error in hardware tracing
408
409enum auxtrace_error_type {
410	PERF_AUXTRACE_ERROR_ITRACE  = 1,
411	PERF_AUXTRACE_ERROR_MAX
412};
413
414#define MAX_AUXTRACE_ERROR_MSG 64
415
416struct auxtrace_error_event {
417	struct perf_event_header header;
418	uint32_t type;
419	uint32_t code;
420	uint32_t cpu;
421	uint32_t pid;
422	uint32_t tid;
423	uint32_t reserved__; /* For alignment */
424	uint64_t ip;
425	char msg[MAX_AUXTRACE_ERROR_MSG];
426};
427
428	PERF_RECORD_HEADER_FEATURE		= 80,
429
430Describes a header feature. These are records used in pipe-mode that
431contain information that otherwise would be in perf.data file's header.
432
433Event types
434
435Define the event attributes with their IDs.
436
437An array bound by the perf_file_section size.
438
439	struct {
440		struct perf_event_attr attr;   /* Size defined by header.attr_size */
441		struct perf_file_section ids;
442	}
443
444ids points to a array of uint64_t defining the ids for event attr attr.
445
446Pipe-mode data
447
448Pipe-mode avoid seeks in the file by removing the perf_file_section and flags
449from the struct perf_header. The trimmed header is:
450
451struct perf_pipe_file_header {
452	u64				magic;
453	u64				size;
454};
455
456The information about attrs, data, and event_types is instead in the
457synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA,
458PERF_RECORD_HEADER_EVENT_TYPE, and PERF_RECORD_HEADER_FEATURE
459that are generated by perf record in pipe-mode.
460
461
462References:
463
464include/uapi/linux/perf_event.h
465
466This is the canonical description of the kernel generated perf_events
467and the perf_event_attrs.
468
469perf_events manpage
470
471A manpage describing perf_event and perf_event_attr is here:
472http://web.eece.maine.edu/~vweaver/projects/perf_events/programming.html
473This tends to be slightly behind the kernel include, but has better
474descriptions.  An (typically older) version of the man page may be
475included with the standard Linux man pages, available with "man
476perf_events"
477
478pmu-tools
479
480https://github.com/andikleen/pmu-tools/tree/master/parser
481
482A definition of the perf.data format in python "construct" format is available
483in pmu-tools parser. This allows to read perf.data from python and dump it.
484
485quipper
486
487The quipper C++ parser is available at
488https://chromium.googlesource.com/chromiumos/platform2
489
490It is under the chromiumos-wide-profiling/ subdirectory. This library can
491convert a perf data file to a protobuf and vice versa.
492
493Unfortunately this parser tends to be many versions behind and may not be able
494to parse data files generated by recent perf.
495