xref: /linux/tools/perf/Documentation/perf.data-file-format.txt (revision e7e86d7697c6ed1dbbde18d7185c35b6967945ed)
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
46For each of the optional features a perf_file_section is placed after the data
47section if the feature bit is set in the perf_header flags bitset. The
48respective perf_file_section points to the data of the additional header and
49defines its size.
50
51Some headers consist of strings, which are defined like this:
52
53struct perf_header_string {
54       uint32_t len;
55       char string[len]; /* zero terminated */
56};
57
58Some headers consist of a sequence of strings, which start with a
59
60struct perf_header_string_list {
61     uint32_t nr;
62     struct perf_header_string strings[nr]; /* variable length records */
63};
64
65The bits are the flags bits in a 256 bit bitmap starting with
66flags. These define the valid bits:
67
68	HEADER_RESERVED		= 0,	/* always cleared */
69	HEADER_FIRST_FEATURE	= 1,
70	HEADER_TRACING_DATA	= 1,
71
72Describe me.
73
74	HEADER_BUILD_ID = 2,
75
76The header consists of an sequence of build_id_event. The size of each record
77is defined by header.size (see perf_event.h). Each event defines a ELF build id
78for a executable file name for a pid. An ELF build id is a unique identifier
79assigned by the linker to an executable.
80
81struct build_id_event {
82	struct perf_event_header header;
83	pid_t			 pid;
84	uint8_t			 build_id[24];
85	char			 filename[header.size - offsetof(struct build_id_event, filename)];
86};
87
88	HEADER_HOSTNAME = 3,
89
90A perf_header_string with the hostname where the data was collected
91(uname -n)
92
93	HEADER_OSRELEASE = 4,
94
95A perf_header_string with the os release where the data was collected
96(uname -r)
97
98	HEADER_VERSION = 5,
99
100A perf_header_string with the perf user tool version where the
101data was collected. This is the same as the version of the source tree
102the perf tool was built from.
103
104	HEADER_ARCH = 6,
105
106A perf_header_string with the CPU architecture (uname -m)
107
108	HEADER_NRCPUS = 7,
109
110A structure defining the number of CPUs.
111
112struct nr_cpus {
113       uint32_t nr_cpus_available; /* CPUs not yet onlined */
114       uint32_t nr_cpus_online;
115};
116
117	HEADER_CPUDESC = 8,
118
119A perf_header_string with description of the CPU. On x86 this is the model name
120in /proc/cpuinfo
121
122	HEADER_CPUID = 9,
123
124A perf_header_string with the exact CPU type. On x86 this is
125vendor,family,model,stepping. For example: GenuineIntel,6,69,1
126
127	HEADER_TOTAL_MEM = 10,
128
129An uint64_t with the total memory in kilobytes.
130
131	HEADER_CMDLINE = 11,
132
133A perf_header_string_list with the perf arg-vector used to collect the data.
134
135	HEADER_EVENT_DESC = 12,
136
137Another description of the perf_event_attrs, more detailed than header.attrs
138including IDs and names. See perf_event.h or the man page for a description
139of a struct perf_event_attr.
140
141struct {
142       uint32_t nr; /* number of events */
143       uint32_t attr_size; /* size of each perf_event_attr */
144       struct {
145	      struct perf_event_attr attr;  /* size of attr_size */
146	      uint32_t nr_ids;
147	      struct perf_header_string event_string;
148	      uint64_t ids[nr_ids];
149       } events[nr]; /* Variable length records */
150};
151
152	HEADER_CPU_TOPOLOGY = 13,
153
154struct {
155	/*
156	 * First revision of HEADER_CPU_TOPOLOGY
157	 *
158	 * See 'struct perf_header_string_list' definition earlier
159	 * in this file.
160	 */
161
162       struct perf_header_string_list cores; /* Variable length */
163       struct perf_header_string_list threads; /* Variable length */
164
165       /*
166        * Second revision of HEADER_CPU_TOPOLOGY, older tools
167        * will not consider what comes next
168        */
169
170       struct {
171	      uint32_t core_id;
172	      uint32_t socket_id;
173       } cpus[nr]; /* Variable length records */
174       /* 'nr' comes from previously processed HEADER_NRCPUS's nr_cpu_avail */
175
176        /*
177	 * Third revision of HEADER_CPU_TOPOLOGY, older tools
178	 * will not consider what comes next
179	 */
180
181	struct perf_header_string_list dies; /* Variable length */
182	uint32_t die_id[nr_cpus_avail]; /* from previously processed HEADER_NR_CPUS, VLA */
183};
184
185Example:
186	sibling sockets : 0-8
187	sibling dies	: 0-3
188	sibling dies	: 4-7
189	sibling threads : 0-1
190	sibling threads : 2-3
191	sibling threads : 4-5
192	sibling threads : 6-7
193
194	HEADER_NUMA_TOPOLOGY = 14,
195
196	A list of NUMA node descriptions
197
198struct {
199       uint32_t nr;
200       struct {
201	      uint32_t nodenr;
202	      uint64_t mem_total;
203	      uint64_t mem_free;
204	      struct perf_header_string cpus;
205       } nodes[nr]; /* Variable length records */
206};
207
208	HEADER_BRANCH_STACK = 15,
209
210Not implemented in perf.
211
212	HEADER_PMU_MAPPINGS = 16,
213
214	A list of PMU structures, defining the different PMUs supported by perf.
215
216struct {
217       uint32_t nr;
218       struct pmu {
219	      uint32_t pmu_type;
220	      struct perf_header_string pmu_name;
221       } [nr]; /* Variable length records */
222};
223
224	HEADER_GROUP_DESC = 17,
225
226	Description of counter groups ({...} in perf syntax)
227
228struct {
229         uint32_t nr;
230         struct {
231		struct perf_header_string string;
232		uint32_t leader_idx;
233		uint32_t nr_members;
234	 } [nr]; /* Variable length records */
235};
236
237	HEADER_AUXTRACE = 18,
238
239Define additional auxtrace areas in the perf.data. auxtrace is used to store
240undecoded hardware tracing information, such as Intel Processor Trace data.
241
242/**
243 * struct auxtrace_index_entry - indexes a AUX area tracing event within a
244 *                               perf.data file.
245 * @file_offset: offset within the perf.data file
246 * @sz: size of the event
247 */
248struct auxtrace_index_entry {
249	u64			file_offset;
250	u64			sz;
251};
252
253#define PERF_AUXTRACE_INDEX_ENTRY_COUNT 256
254
255/**
256 * struct auxtrace_index - index of AUX area tracing events within a perf.data
257 *                         file.
258 * @list: linking a number of arrays of entries
259 * @nr: number of entries
260 * @entries: array of entries
261 */
262struct auxtrace_index {
263	struct list_head	list;
264	size_t			nr;
265	struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
266};
267
268	HEADER_STAT = 19,
269
270This is merely a flag signifying that the data section contains data
271recorded from perf stat record.
272
273	HEADER_CACHE = 20,
274
275Description of the cache hierarchy. Based on the Linux sysfs format
276in /sys/devices/system/cpu/cpu*/cache/
277
278	u32 version	Currently always 1
279	u32 number_of_cache_levels
280
281struct {
282	u32	level;
283	u32	line_size;
284	u32	sets;
285	u32	ways;
286	struct perf_header_string type;
287	struct perf_header_string size;
288	struct perf_header_string map;
289}[number_of_cache_levels];
290
291	HEADER_SAMPLE_TIME = 21,
292
293Two uint64_t for the time of first sample and the time of last sample.
294
295	HEADER_SAMPLE_TOPOLOGY = 22,
296
297Physical memory map and its node assignments.
298
299The format of data in MEM_TOPOLOGY is as follows:
300
301	u64 version;            // Currently 1
302	u64 block_size_bytes;   // /sys/devices/system/memory/block_size_bytes
303	u64 count;              // number of nodes
304
305struct memory_node {
306        u64 node_id;            // node index
307        u64 size;               // size of bitmap
308        struct bitmap {
309		/* size of bitmap again */
310                u64 bitmapsize;
311		/* bitmap of memory indexes that belongs to node     */
312		/* /sys/devices/system/node/node<NODE>/memory<INDEX> */
313                u64 entries[(bitmapsize/64)+1];
314        }
315}[count];
316
317The MEM_TOPOLOGY can be displayed with following command:
318
319$ perf report --header-only -I
320...
321# memory nodes (nr 1, block size 0x8000000):
322#    0 [7G]: 0-23,32-69
323
324	HEADER_CLOCKID = 23,
325
326One uint64_t for the clockid frequency, specified, for instance, via 'perf
327record -k' (see clock_gettime()), to enable timestamps derived metrics
328conversion into wall clock time on the reporting stage.
329
330	HEADER_DIR_FORMAT = 24,
331
332The data files layout is described by HEADER_DIR_FORMAT feature.  Currently it
333holds only version number (1):
334
335  uint64_t version;
336
337The current version holds only version value (1) means that data files:
338
339- Follow the 'data.*' name format.
340
341- Contain raw events data in standard perf format as read from kernel (and need
342  to be sorted)
343
344Future versions are expected to describe different data files layout according
345to special needs.
346
347        HEADER_BPF_PROG_INFO = 25,
348
349struct perf_bpil, which contains detailed information about
350a BPF program, including type, id, tag, jited/xlated instructions, etc.
351The format of data in HEADER_BPF_PROG_INFO is as follows:
352	u32 count
353
354	struct perf_bpil {
355		u32 info_len;	/* size of struct bpf_prog_info, when the tool is compiled */
356		u32 data_len;	/* total bytes allocated for data, round up to 8 bytes */
357		u64 arrays;	/* which arrays are included in data */
358		struct bpf_prog_info info;
359		u8  data[];
360	}[count];
361
362        HEADER_BPF_BTF = 26,
363
364Contains BPF Type Format (BTF). For more information about BTF, please
365refer to Documentation/bpf/btf.rst.
366
367struct {
368	u32	id;
369	u32	data_size;
370	char	data[];
371};
372
373        HEADER_COMPRESSED = 27,
374
375struct {
376	u32	version;
377	u32	type;
378	u32	level;
379	u32	ratio;
380	u32	mmap_len;
381};
382
383Indicates that trace contains records of PERF_RECORD_COMPRESSED2 type
384that have perf_events records in compressed form.
385
386	HEADER_CPU_PMU_CAPS = 28,
387
388	A list of cpu PMU capabilities. The format of data is as below.
389
390struct {
391	u32 nr_cpu_pmu_caps;
392	{
393		char	name[];
394		char	value[];
395	} [nr_cpu_pmu_caps]
396};
397
398
399Example:
400 cpu pmu capabilities: branches=32, max_precise=3, pmu_name=icelake
401
402	HEADER_CLOCK_DATA = 29,
403
404	Contains clock id and its reference time together with wall clock
405	time taken at the 'same time', both values are in nanoseconds.
406	The format of data is as below.
407
408struct {
409	u32 version;  /* version = 1 */
410	u32 clockid;
411	u64 wall_clock_ns;
412	u64 clockid_time_ns;
413};
414
415	HEADER_HYBRID_TOPOLOGY = 30,
416
417Indicate the hybrid CPUs. The format of data is as below.
418
419struct {
420	u32 nr;
421	struct {
422		char pmu_name[];
423		char cpus[];
424	} [nr]; /* Variable length records */
425};
426
427Example:
428  hybrid cpu system:
429  cpu_core cpu list : 0-15
430  cpu_atom cpu list : 16-23
431
432	HEADER_PMU_CAPS = 31,
433
434	List of pmu capabilities (except cpu pmu which is already
435	covered by HEADER_CPU_PMU_CAPS). Note that hybrid cpu pmu
436	capabilities are also stored here.
437
438struct {
439	u32 nr_pmu;
440	struct {
441		u32 nr_caps;
442		{
443			char	name[];
444			char	value[];
445		} [nr_caps];
446		char pmu_name[];
447	} [nr_pmu];
448};
449
450	other bits are reserved and should ignored for now
451	HEADER_FEAT_BITS	= 256,
452
453Attributes
454
455This is an array of perf_event_attrs, each attr_size bytes long, which defines
456each event collected. See perf_event.h or the man page for a detailed
457description.
458
459Data
460
461This section is the bulk of the file. It consist of a stream of perf_events
462describing events. This matches the format generated by the kernel.
463See perf_event.h or the manpage for a detailed description.
464
465Some notes on parsing:
466
467Ordering
468
469The events are not necessarily in time stamp order, as they can be
470collected in parallel on different CPUs. If the events should be
471processed in time order they need to be sorted first. It is possible
472to only do a partial sort using the FINISHED_ROUND event header (see
473below). perf record guarantees that there is no reordering over a
474FINISHED_ROUND.
475
476ID vs IDENTIFIER
477
478When the event stream contains multiple events each event is identified
479by an ID. This can be either through the PERF_SAMPLE_ID or the
480PERF_SAMPLE_IDENTIFIER header. The PERF_SAMPLE_IDENTIFIER header is
481at a fixed offset from the event header, which allows reliable
482parsing of the header. Relying on ID may be ambiguous.
483IDENTIFIER is only supported by newer Linux kernels.
484
485Perf record specific events:
486
487In addition to the kernel generated event types perf record adds its
488own event types (in addition it also synthesizes some kernel events,
489for example MMAP events)
490
491	PERF_RECORD_USER_TYPE_START		= 64,
492	PERF_RECORD_HEADER_ATTR			= 64,
493
494struct attr_event {
495	struct perf_event_header header;
496	struct perf_event_attr attr;
497	uint64_t id[];
498};
499
500	PERF_RECORD_HEADER_EVENT_TYPE		= 65, /* deprecated */
501
502#define MAX_EVENT_NAME 64
503
504struct perf_trace_event_type {
505	uint64_t	event_id;
506	char	name[MAX_EVENT_NAME];
507};
508
509struct event_type_event {
510	struct perf_event_header header;
511	struct perf_trace_event_type event_type;
512};
513
514
515	PERF_RECORD_HEADER_TRACING_DATA		= 66,
516
517Describe me
518
519struct tracing_data_event {
520	struct perf_event_header header;
521	uint32_t size;
522};
523
524	PERF_RECORD_HEADER_BUILD_ID		= 67,
525
526Define a ELF build ID for a referenced executable.
527
528       struct build_id_event;   /* See above */
529
530	PERF_RECORD_FINISHED_ROUND		= 68,
531
532No event reordering over this header. No payload.
533
534	PERF_RECORD_ID_INDEX			= 69,
535
536Map event ids to CPUs and TIDs.
537
538struct id_index_entry {
539	uint64_t id;
540	uint64_t idx;
541	uint64_t cpu;
542	uint64_t tid;
543};
544
545struct id_index_event {
546	struct perf_event_header header;
547	uint64_t nr;
548	struct id_index_entry entries[nr];
549};
550
551	PERF_RECORD_AUXTRACE_INFO		= 70,
552
553Auxtrace type specific information. Describe me
554
555struct auxtrace_info_event {
556	struct perf_event_header header;
557	uint32_t type;
558	uint32_t reserved__; /* For alignment */
559	uint64_t priv[];
560};
561
562	PERF_RECORD_AUXTRACE			= 71,
563
564Defines auxtrace data. Followed by the actual data. The contents of
565the auxtrace data is dependent on the event and the CPU. For example
566for Intel Processor Trace it contains Processor Trace data generated
567by the CPU.
568
569struct auxtrace_event {
570	struct perf_event_header header;
571	uint64_t size;
572	uint64_t offset;
573	uint64_t reference;
574	uint32_t idx;
575	uint32_t tid;
576	uint32_t cpu;
577	uint32_t reserved__; /* For alignment */
578};
579
580struct aux_event {
581	struct perf_event_header header;
582	uint64_t	aux_offset;
583	uint64_t	aux_size;
584	uint64_t	flags;
585};
586
587	PERF_RECORD_AUXTRACE_ERROR		= 72,
588
589Describes an error in hardware tracing
590
591enum auxtrace_error_type {
592	PERF_AUXTRACE_ERROR_ITRACE  = 1,
593	PERF_AUXTRACE_ERROR_MAX
594};
595
596#define MAX_AUXTRACE_ERROR_MSG 64
597
598struct auxtrace_error_event {
599	struct perf_event_header header;
600	uint32_t type;
601	uint32_t code;
602	uint32_t cpu;
603	uint32_t pid;
604	uint32_t tid;
605	uint32_t reserved__; /* For alignment */
606	uint64_t ip;
607	char msg[MAX_AUXTRACE_ERROR_MSG];
608};
609
610	PERF_RECORD_HEADER_FEATURE		= 80,
611
612Describes a header feature. These are records used in pipe-mode that
613contain information that otherwise would be in perf.data file's header.
614
615	PERF_RECORD_COMPRESSED 			= 81, /* deprecated */
616
617The header is followed by compressed data frame that can be decompressed
618into array of perf trace records. The size of the entire compressed event
619record including the header is limited by the max value of header.size.
620
621It is deprecated and new files should use PERF_RECORD_COMPRESSED2 to gurantee
6228-byte alignment.
623
624struct compressed_event {
625	struct perf_event_header	header;
626	char				data[];
627};
628
629	PERF_RECORD_FINISHED_INIT			= 82,
630
631Marks the end of records for the system, pre-existing threads in system wide
632sessions, etc. Those are the ones prefixed PERF_RECORD_USER_*.
633
634This is used, for instance, to 'perf inject' events after init and before
635regular events, those emitted by the kernel, to support combining guest and
636host records.
637
638	PERF_RECORD_COMPRESSED2			= 83,
639
6408-byte aligned version of `PERF_RECORD_COMPRESSED`. `header.size` indicates the
641total record size, including padding for 8-byte alignment, and `data_size`
642specifies the actual size of the compressed data.
643
644struct perf_record_compressed2 {
645	struct perf_event_header	header;
646	__u64				data_size;
647	char				data[];
648};
649
650Event types
651
652Define the event attributes with their IDs.
653
654An array bound by the perf_file_section size.
655
656	struct {
657		struct perf_event_attr attr;   /* Size defined by header.attr_size */
658		struct perf_file_section ids;
659	}
660
661ids points to a array of uint64_t defining the ids for event attr attr.
662
663Pipe-mode data
664
665Pipe-mode avoid seeks in the file by removing the perf_file_section and flags
666from the struct perf_header. The trimmed header is:
667
668struct perf_pipe_file_header {
669	u64				magic;
670	u64				size;
671};
672
673The information about attrs, data, and event_types is instead in the
674synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA,
675PERF_RECORD_HEADER_EVENT_TYPE, and PERF_RECORD_HEADER_FEATURE
676that are generated by perf record in pipe-mode.
677
678
679References:
680
681include/uapi/linux/perf_event.h
682
683This is the canonical description of the kernel generated perf_events
684and the perf_event_attrs.
685
686perf_events manpage
687
688A manpage describing perf_event and perf_event_attr is here:
689http://web.eece.maine.edu/~vweaver/projects/perf_events/programming.html
690This tends to be slightly behind the kernel include, but has better
691descriptions.  An (typically older) version of the man page may be
692included with the standard Linux man pages, available with "man
693perf_events"
694
695pmu-tools
696
697https://github.com/andikleen/pmu-tools/tree/master/parser
698
699A definition of the perf.data format in python "construct" format is available
700in pmu-tools parser. This allows to read perf.data from python and dump it.
701
702quipper
703
704The quipper C++ parser is available at
705http://github.com/google/perf_data_converter/tree/master/src/quipper
706
707