1 perf.data format 1 perf.data format
2 2
3 Uptodate as of v4.7 3 Uptodate as of v4.7
4 4
5 This document describes the on-disk perf.data 5 This document describes the on-disk perf.data format, generated by perf record
6 or perf inject and consumed by the other perf 6 or perf inject and consumed by the other perf tools.
7 7
8 On a high level perf.data contains the events 8 On a high level perf.data contains the events generated by the PMUs, plus metadata.
9 9
10 All fields are in native-endian of the machine 10 All fields are in native-endian of the machine that generated the perf.data.
11 11
12 When perf is writing to a pipe it uses a speci 12 When perf is writing to a pipe it uses a special version of the file
13 format that does not rely on seeking to adjust 13 format that does not rely on seeking to adjust data offsets. This
14 format is described in "Pipe-mode data" sectio 14 format is described in "Pipe-mode data" section. The pipe data version can be
15 augmented with additional events using perf in 15 augmented with additional events using perf inject.
16 16
17 The file starts with a perf_header: 17 The file starts with a perf_header:
18 18
19 struct perf_header { 19 struct perf_header {
20 char magic[8]; /* PERFILE2 */ 20 char magic[8]; /* PERFILE2 */
21 uint64_t size; /* size of the 21 uint64_t size; /* size of the header */
22 uint64_t attr_size; /* size of an 22 uint64_t attr_size; /* size of an attribute in attrs */
23 struct perf_file_section attrs; 23 struct perf_file_section attrs;
24 struct perf_file_section data; 24 struct perf_file_section data;
25 struct perf_file_section event_types; 25 struct perf_file_section event_types;
26 uint64_t flags; 26 uint64_t flags;
27 uint64_t flags1[3]; 27 uint64_t flags1[3];
28 }; 28 };
29 29
30 The magic number identifies the perf file and 30 The magic number identifies the perf file and the version. Current perf versions
31 use PERFILE2. Old perf versions generated a ve 31 use PERFILE2. Old perf versions generated a version 1 format (PERFFILE). Version 1
32 is not described here. The magic number also i 32 is not described here. The magic number also identifies the endian. When the
33 magic value is 64bit byte swapped compared the 33 magic value is 64bit byte swapped compared the file is in non-native
34 endian. 34 endian.
35 35
36 A perf_file_section contains a pointer to anot 36 A perf_file_section contains a pointer to another section of the perf file.
37 The header contains three such pointers: for a 37 The header contains three such pointers: for attributes, data and event types.
38 38
39 struct perf_file_section { 39 struct perf_file_section {
40 uint64_t offset; /* offset from 40 uint64_t offset; /* offset from start of file */
41 uint64_t size; /* size of the 41 uint64_t size; /* size of the section */
42 }; 42 };
43 43
44 Flags section: 44 Flags section:
45 45
46 For each of the optional features a perf_file_ !! 46 For each of the optional features a perf_file_section it placed after the data
47 section if the feature bit is set in the perf_ 47 section if the feature bit is set in the perf_header flags bitset. The
48 respective perf_file_section points to the dat 48 respective perf_file_section points to the data of the additional header and
49 defines its size. 49 defines its size.
50 50
51 Some headers consist of strings, which are def 51 Some headers consist of strings, which are defined like this:
52 52
53 struct perf_header_string { 53 struct perf_header_string {
54 uint32_t len; 54 uint32_t len;
55 char string[len]; /* zero terminated */ 55 char string[len]; /* zero terminated */
56 }; 56 };
57 57
58 Some headers consist of a sequence of strings, 58 Some headers consist of a sequence of strings, which start with a
59 59
60 struct perf_header_string_list { 60 struct perf_header_string_list {
61 uint32_t nr; 61 uint32_t nr;
62 struct perf_header_string strings[nr]; /* 62 struct perf_header_string strings[nr]; /* variable length records */
63 }; 63 };
64 64
65 The bits are the flags bits in a 256 bit bitma 65 The bits are the flags bits in a 256 bit bitmap starting with
66 flags. These define the valid bits: 66 flags. These define the valid bits:
67 67
68 HEADER_RESERVED = 0, /* alw 68 HEADER_RESERVED = 0, /* always cleared */
69 HEADER_FIRST_FEATURE = 1, 69 HEADER_FIRST_FEATURE = 1,
70 HEADER_TRACING_DATA = 1, 70 HEADER_TRACING_DATA = 1,
71 71
72 Describe me. 72 Describe me.
73 73
74 HEADER_BUILD_ID = 2, 74 HEADER_BUILD_ID = 2,
75 75
76 The header consists of an sequence of build_id 76 The header consists of an sequence of build_id_event. The size of each record
77 is defined by header.size (see perf_event.h). 77 is defined by header.size (see perf_event.h). Each event defines a ELF build id
78 for a executable file name for a pid. An ELF b 78 for a executable file name for a pid. An ELF build id is a unique identifier
79 assigned by the linker to an executable. 79 assigned by the linker to an executable.
80 80
81 struct build_id_event { 81 struct build_id_event {
82 struct perf_event_header header; 82 struct perf_event_header header;
83 pid_t pid; 83 pid_t pid;
84 uint8_t build_id[24]; 84 uint8_t build_id[24];
85 char filename[head 85 char filename[header.size - offsetof(struct build_id_event, filename)];
86 }; 86 };
87 87
88 HEADER_HOSTNAME = 3, 88 HEADER_HOSTNAME = 3,
89 89
90 A perf_header_string with the hostname where t 90 A perf_header_string with the hostname where the data was collected
91 (uname -n) 91 (uname -n)
92 92
93 HEADER_OSRELEASE = 4, 93 HEADER_OSRELEASE = 4,
94 94
95 A perf_header_string with the os release where 95 A perf_header_string with the os release where the data was collected
96 (uname -r) 96 (uname -r)
97 97
98 HEADER_VERSION = 5, 98 HEADER_VERSION = 5,
99 99
100 A perf_header_string with the perf user tool v 100 A perf_header_string with the perf user tool version where the
101 data was collected. This is the same as the ve 101 data was collected. This is the same as the version of the source tree
102 the perf tool was built from. 102 the perf tool was built from.
103 103
104 HEADER_ARCH = 6, 104 HEADER_ARCH = 6,
105 105
106 A perf_header_string with the CPU architecture 106 A perf_header_string with the CPU architecture (uname -m)
107 107
108 HEADER_NRCPUS = 7, 108 HEADER_NRCPUS = 7,
109 109
110 A structure defining the number of CPUs. 110 A structure defining the number of CPUs.
111 111
112 struct nr_cpus { 112 struct nr_cpus {
113 uint32_t nr_cpus_available; /* CPUs not 113 uint32_t nr_cpus_available; /* CPUs not yet onlined */
114 uint32_t nr_cpus_online; 114 uint32_t nr_cpus_online;
115 }; 115 };
116 116
117 HEADER_CPUDESC = 8, 117 HEADER_CPUDESC = 8,
118 118
119 A perf_header_string with description of the C 119 A perf_header_string with description of the CPU. On x86 this is the model name
120 in /proc/cpuinfo 120 in /proc/cpuinfo
121 121
122 HEADER_CPUID = 9, 122 HEADER_CPUID = 9,
123 123
124 A perf_header_string with the exact CPU type. 124 A perf_header_string with the exact CPU type. On x86 this is
125 vendor,family,model,stepping. For example: Gen 125 vendor,family,model,stepping. For example: GenuineIntel,6,69,1
126 126
127 HEADER_TOTAL_MEM = 10, 127 HEADER_TOTAL_MEM = 10,
128 128
129 An uint64_t with the total memory in kilobytes !! 129 An uint64_t with the total memory in bytes.
130 130
131 HEADER_CMDLINE = 11, 131 HEADER_CMDLINE = 11,
132 132
133 A perf_header_string_list with the perf arg-ve 133 A perf_header_string_list with the perf arg-vector used to collect the data.
134 134
135 HEADER_EVENT_DESC = 12, 135 HEADER_EVENT_DESC = 12,
136 136
137 Another description of the perf_event_attrs, m 137 Another description of the perf_event_attrs, more detailed than header.attrs
138 including IDs and names. See perf_event.h or t 138 including IDs and names. See perf_event.h or the man page for a description
139 of a struct perf_event_attr. 139 of a struct perf_event_attr.
140 140
141 struct { 141 struct {
142 uint32_t nr; /* number of events */ 142 uint32_t nr; /* number of events */
143 uint32_t attr_size; /* size of each per 143 uint32_t attr_size; /* size of each perf_event_attr */
144 struct { 144 struct {
145 struct perf_event_attr attr; /* 145 struct perf_event_attr attr; /* size of attr_size */
146 uint32_t nr_ids; 146 uint32_t nr_ids;
147 struct perf_header_string event_ 147 struct perf_header_string event_string;
148 uint64_t ids[nr_ids]; 148 uint64_t ids[nr_ids];
149 } events[nr]; /* Variable length record 149 } events[nr]; /* Variable length records */
150 }; 150 };
151 151
152 HEADER_CPU_TOPOLOGY = 13, 152 HEADER_CPU_TOPOLOGY = 13,
153 153
154 struct { !! 154 String lists defining the core and CPU threads topology.
155 /* !! 155 The string lists are followed by a variable length array
156 * First revision of HEADER_CPU_TOPOLO !! 156 which contains core_id and socket_id of each cpu.
157 * !! 157 The number of entries can be determined by the size of the
158 * See 'struct perf_header_string_list !! 158 section minus the sizes of both string lists.
159 * in this file. <<
160 */ <<
161 159
>> 160 struct {
162 struct perf_header_string_list cores; / 161 struct perf_header_string_list cores; /* Variable length */
163 struct perf_header_string_list threads; 162 struct perf_header_string_list threads; /* Variable length */
164 <<
165 /* <<
166 * Second revision of HEADER_CPU_TOPOLO <<
167 * will not consider what comes next <<
168 */ <<
169 <<
170 struct { 163 struct {
171 uint32_t core_id; 164 uint32_t core_id;
172 uint32_t socket_id; 165 uint32_t socket_id;
173 } cpus[nr]; /* Variable length records 166 } cpus[nr]; /* Variable length records */
174 /* 'nr' comes from previously processed <<
175 <<
176 /* <<
177 * Third revision of HEADER_CPU_TOPOLO <<
178 * will not consider what comes next <<
179 */ <<
180 <<
181 struct perf_header_string_list dies; / <<
182 uint32_t die_id[nr_cpus_avail]; /* fro <<
183 }; 167 };
184 168
185 Example: 169 Example:
186 sibling sockets : 0-8 !! 170 sibling cores : 0-3
187 sibling dies : 0-3 <<
188 sibling dies : 4-7 <<
189 sibling threads : 0-1 171 sibling threads : 0-1
190 sibling threads : 2-3 172 sibling threads : 2-3
191 sibling threads : 4-5 <<
192 sibling threads : 6-7 <<
193 173
194 HEADER_NUMA_TOPOLOGY = 14, 174 HEADER_NUMA_TOPOLOGY = 14,
195 175
196 A list of NUMA node descriptions 176 A list of NUMA node descriptions
197 177
198 struct { 178 struct {
199 uint32_t nr; 179 uint32_t nr;
200 struct { 180 struct {
201 uint32_t nodenr; 181 uint32_t nodenr;
202 uint64_t mem_total; 182 uint64_t mem_total;
203 uint64_t mem_free; 183 uint64_t mem_free;
204 struct perf_header_string cpus; 184 struct perf_header_string cpus;
205 } nodes[nr]; /* Variable length records 185 } nodes[nr]; /* Variable length records */
206 }; 186 };
207 187
208 HEADER_BRANCH_STACK = 15, 188 HEADER_BRANCH_STACK = 15,
209 189
210 Not implemented in perf. 190 Not implemented in perf.
211 191
212 HEADER_PMU_MAPPINGS = 16, 192 HEADER_PMU_MAPPINGS = 16,
213 193
214 A list of PMU structures, defining the 194 A list of PMU structures, defining the different PMUs supported by perf.
215 195
216 struct { 196 struct {
217 uint32_t nr; 197 uint32_t nr;
218 struct pmu { 198 struct pmu {
219 uint32_t pmu_type; 199 uint32_t pmu_type;
220 struct perf_header_string pmu_na 200 struct perf_header_string pmu_name;
221 } [nr]; /* Variable length records */ 201 } [nr]; /* Variable length records */
222 }; 202 };
223 203
224 HEADER_GROUP_DESC = 17, 204 HEADER_GROUP_DESC = 17,
225 205
226 Description of counter groups ({...} i 206 Description of counter groups ({...} in perf syntax)
227 207
228 struct { 208 struct {
229 uint32_t nr; 209 uint32_t nr;
230 struct { 210 struct {
231 struct perf_header_string stri 211 struct perf_header_string string;
232 uint32_t leader_idx; 212 uint32_t leader_idx;
233 uint32_t nr_members; 213 uint32_t nr_members;
234 } [nr]; /* Variable length records */ 214 } [nr]; /* Variable length records */
235 }; 215 };
236 216
237 HEADER_AUXTRACE = 18, 217 HEADER_AUXTRACE = 18,
238 218
239 Define additional auxtrace areas in the perf.d 219 Define additional auxtrace areas in the perf.data. auxtrace is used to store
240 undecoded hardware tracing information, such a 220 undecoded hardware tracing information, such as Intel Processor Trace data.
241 221
242 /** 222 /**
243 * struct auxtrace_index_entry - indexes a AUX 223 * struct auxtrace_index_entry - indexes a AUX area tracing event within a
244 * perf.data fil 224 * perf.data file.
245 * @file_offset: offset within the perf.data f 225 * @file_offset: offset within the perf.data file
246 * @sz: size of the event 226 * @sz: size of the event
247 */ 227 */
248 struct auxtrace_index_entry { 228 struct auxtrace_index_entry {
249 u64 file_offset; 229 u64 file_offset;
250 u64 sz; 230 u64 sz;
251 }; 231 };
252 232
253 #define PERF_AUXTRACE_INDEX_ENTRY_COUNT 256 233 #define PERF_AUXTRACE_INDEX_ENTRY_COUNT 256
254 234
255 /** 235 /**
256 * struct auxtrace_index - index of AUX area t 236 * struct auxtrace_index - index of AUX area tracing events within a perf.data
257 * file. 237 * file.
258 * @list: linking a number of arrays of entrie 238 * @list: linking a number of arrays of entries
259 * @nr: number of entries 239 * @nr: number of entries
260 * @entries: array of entries 240 * @entries: array of entries
261 */ 241 */
262 struct auxtrace_index { 242 struct auxtrace_index {
263 struct list_head list; 243 struct list_head list;
264 size_t nr; 244 size_t nr;
265 struct auxtrace_index_entry entries[PE 245 struct auxtrace_index_entry entries[PERF_AUXTRACE_INDEX_ENTRY_COUNT];
266 }; 246 };
267 247
268 HEADER_STAT = 19, 248 HEADER_STAT = 19,
269 249
270 This is merely a flag signifying that the data 250 This is merely a flag signifying that the data section contains data
271 recorded from perf stat record. 251 recorded from perf stat record.
272 252
273 HEADER_CACHE = 20, 253 HEADER_CACHE = 20,
274 254
275 Description of the cache hierarchy. Based on t 255 Description of the cache hierarchy. Based on the Linux sysfs format
276 in /sys/devices/system/cpu/cpu*/cache/ 256 in /sys/devices/system/cpu/cpu*/cache/
277 257
278 u32 version Currently always 1 258 u32 version Currently always 1
279 u32 number_of_cache_levels 259 u32 number_of_cache_levels
280 260
281 struct { 261 struct {
282 u32 level; 262 u32 level;
283 u32 line_size; 263 u32 line_size;
284 u32 sets; 264 u32 sets;
285 u32 ways; 265 u32 ways;
286 struct perf_header_string type; 266 struct perf_header_string type;
287 struct perf_header_string size; 267 struct perf_header_string size;
288 struct perf_header_string map; 268 struct perf_header_string map;
289 }[number_of_cache_levels]; 269 }[number_of_cache_levels];
290 270
291 HEADER_SAMPLE_TIME = 21, 271 HEADER_SAMPLE_TIME = 21,
292 272
293 Two uint64_t for the time of first sample and 273 Two uint64_t for the time of first sample and the time of last sample.
294 274
295 HEADER_SAMPLE_TOPOLOGY = 22, <<
296 <<
297 Physical memory map and its node assignments. <<
298 <<
299 The format of data in MEM_TOPOLOGY is as follo <<
300 <<
301 u64 version; // Currently 1 <<
302 u64 block_size_bytes; // /sys/device <<
303 u64 count; // number of n <<
304 <<
305 struct memory_node { <<
306 u64 node_id; // node index <<
307 u64 size; // size of bit <<
308 struct bitmap { <<
309 /* size of bitmap again */ <<
310 u64 bitmapsize; <<
311 /* bitmap of memory indexes th <<
312 /* /sys/devices/system/node/no <<
313 u64 entries[(bitmapsize/64)+1] <<
314 } <<
315 }[count]; <<
316 <<
317 The MEM_TOPOLOGY can be displayed with followi <<
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 <<
326 One uint64_t for the clockid frequency, specif <<
327 record -k' (see clock_gettime()), to enable ti <<
328 conversion into wall clock time on the reporti <<
329 <<
330 HEADER_DIR_FORMAT = 24, <<
331 <<
332 The data files layout is described by HEADER_D <<
333 holds only version number (1): <<
334 <<
335 uint64_t version; <<
336 <<
337 The current version holds only version value ( <<
338 <<
339 - Follow the 'data.*' name format. <<
340 <<
341 - Contain raw events data in standard perf for <<
342 to be sorted) <<
343 <<
344 Future versions are expected to describe diffe <<
345 to special needs. <<
346 <<
347 HEADER_BPF_PROG_INFO = 25, <<
348 <<
349 struct perf_bpil, which contains detailed info <<
350 a BPF program, including type, id, tag, jited/ <<
351 <<
352 HEADER_BPF_BTF = 26, <<
353 <<
354 Contains BPF Type Format (BTF). For more infor <<
355 refer to Documentation/bpf/btf.rst. <<
356 <<
357 struct { <<
358 u32 id; <<
359 u32 data_size; <<
360 char data[]; <<
361 }; <<
362 <<
363 HEADER_COMPRESSED = 27, 275 HEADER_COMPRESSED = 27,
364 276
365 struct { 277 struct {
366 u32 version; 278 u32 version;
367 u32 type; 279 u32 type;
368 u32 level; 280 u32 level;
369 u32 ratio; 281 u32 ratio;
370 u32 mmap_len; 282 u32 mmap_len;
371 }; 283 };
372 284
373 Indicates that trace contains records of PERF_ 285 Indicates that trace contains records of PERF_RECORD_COMPRESSED type
374 that have perf_events records in compressed fo 286 that have perf_events records in compressed form.
375 287
376 HEADER_CPU_PMU_CAPS = 28, <<
377 <<
378 A list of cpu PMU capabilities. The fo <<
379 <<
380 struct { <<
381 u32 nr_cpu_pmu_caps; <<
382 { <<
383 char name[]; <<
384 char value[]; <<
385 } [nr_cpu_pmu_caps] <<
386 }; <<
387 <<
388 <<
389 Example: <<
390 cpu pmu capabilities: branches=32, max_precis <<
391 <<
392 HEADER_CLOCK_DATA = 29, <<
393 <<
394 Contains clock id and its reference ti <<
395 time taken at the 'same time', both va <<
396 The format of data is as below. <<
397 <<
398 struct { <<
399 u32 version; /* version = 1 */ <<
400 u32 clockid; <<
401 u64 wall_clock_ns; <<
402 u64 clockid_time_ns; <<
403 }; <<
404 <<
405 HEADER_HYBRID_TOPOLOGY = 30, <<
406 <<
407 Indicate the hybrid CPUs. The format of data i <<
408 <<
409 struct { <<
410 u32 nr; <<
411 struct { <<
412 char pmu_name[]; <<
413 char cpus[]; <<
414 } [nr]; /* Variable length records */ <<
415 }; <<
416 <<
417 Example: <<
418 hybrid cpu system: <<
419 cpu_core cpu list : 0-15 <<
420 cpu_atom cpu list : 16-23 <<
421 <<
422 HEADER_PMU_CAPS = 31, <<
423 <<
424 List of pmu capabilities (except cpu p <<
425 covered by HEADER_CPU_PMU_CAPS). Note <<
426 capabilities are also stored here. <<
427 <<
428 struct { <<
429 u32 nr_pmu; <<
430 struct { <<
431 u32 nr_caps; <<
432 { <<
433 char name[]; <<
434 char value[]; <<
435 } [nr_caps]; <<
436 char pmu_name[]; <<
437 } [nr_pmu]; <<
438 }; <<
439 <<
440 other bits are reserved and should ign 288 other bits are reserved and should ignored for now
441 HEADER_FEAT_BITS = 256, 289 HEADER_FEAT_BITS = 256,
442 290
443 Attributes 291 Attributes
444 292
445 This is an array of perf_event_attrs, each att 293 This is an array of perf_event_attrs, each attr_size bytes long, which defines
446 each event collected. See perf_event.h or the 294 each event collected. See perf_event.h or the man page for a detailed
447 description. 295 description.
448 296
449 Data 297 Data
450 298
451 This section is the bulk of the file. It consi 299 This section is the bulk of the file. It consist of a stream of perf_events
452 describing events. This matches the format gen 300 describing events. This matches the format generated by the kernel.
453 See perf_event.h or the manpage for a detailed 301 See perf_event.h or the manpage for a detailed description.
454 302
455 Some notes on parsing: 303 Some notes on parsing:
456 304
457 Ordering 305 Ordering
458 306
459 The events are not necessarily in time stamp o 307 The events are not necessarily in time stamp order, as they can be
460 collected in parallel on different CPUs. If th 308 collected in parallel on different CPUs. If the events should be
461 processed in time order they need to be sorted 309 processed in time order they need to be sorted first. It is possible
462 to only do a partial sort using the FINISHED_R 310 to only do a partial sort using the FINISHED_ROUND event header (see
463 below). perf record guarantees that there is n 311 below). perf record guarantees that there is no reordering over a
464 FINISHED_ROUND. 312 FINISHED_ROUND.
465 313
466 ID vs IDENTIFIER 314 ID vs IDENTIFIER
467 315
468 When the event stream contains multiple events 316 When the event stream contains multiple events each event is identified
469 by an ID. This can be either through the PERF_ 317 by an ID. This can be either through the PERF_SAMPLE_ID or the
470 PERF_SAMPLE_IDENTIFIER header. The PERF_SAMPLE 318 PERF_SAMPLE_IDENTIFIER header. The PERF_SAMPLE_IDENTIFIER header is
471 at a fixed offset from the event header, which 319 at a fixed offset from the event header, which allows reliable
472 parsing of the header. Relying on ID may be am 320 parsing of the header. Relying on ID may be ambiguous.
473 IDENTIFIER is only supported by newer Linux ke 321 IDENTIFIER is only supported by newer Linux kernels.
474 322
475 Perf record specific events: 323 Perf record specific events:
476 324
477 In addition to the kernel generated event type 325 In addition to the kernel generated event types perf record adds its
478 own event types (in addition it also synthesiz 326 own event types (in addition it also synthesizes some kernel events,
479 for example MMAP events) 327 for example MMAP events)
480 328
481 PERF_RECORD_USER_TYPE_START 329 PERF_RECORD_USER_TYPE_START = 64,
482 PERF_RECORD_HEADER_ATTR 330 PERF_RECORD_HEADER_ATTR = 64,
483 331
484 struct attr_event { 332 struct attr_event {
485 struct perf_event_header header; 333 struct perf_event_header header;
486 struct perf_event_attr attr; 334 struct perf_event_attr attr;
487 uint64_t id[]; 335 uint64_t id[];
488 }; 336 };
489 337
490 PERF_RECORD_HEADER_EVENT_TYPE 338 PERF_RECORD_HEADER_EVENT_TYPE = 65, /* deprecated */
491 339
492 #define MAX_EVENT_NAME 64 340 #define MAX_EVENT_NAME 64
493 341
494 struct perf_trace_event_type { 342 struct perf_trace_event_type {
495 uint64_t event_id; 343 uint64_t event_id;
496 char name[MAX_EVENT_NAME]; 344 char name[MAX_EVENT_NAME];
497 }; 345 };
498 346
499 struct event_type_event { 347 struct event_type_event {
500 struct perf_event_header header; 348 struct perf_event_header header;
501 struct perf_trace_event_type event_typ 349 struct perf_trace_event_type event_type;
502 }; 350 };
503 351
504 352
505 PERF_RECORD_HEADER_TRACING_DATA 353 PERF_RECORD_HEADER_TRACING_DATA = 66,
506 354
507 Describe me 355 Describe me
508 356
509 struct tracing_data_event { 357 struct tracing_data_event {
510 struct perf_event_header header; 358 struct perf_event_header header;
511 uint32_t size; 359 uint32_t size;
512 }; 360 };
513 361
514 PERF_RECORD_HEADER_BUILD_ID 362 PERF_RECORD_HEADER_BUILD_ID = 67,
515 363
516 Define a ELF build ID for a referenced executa 364 Define a ELF build ID for a referenced executable.
517 365
518 struct build_id_event; /* See above * 366 struct build_id_event; /* See above */
519 367
520 PERF_RECORD_FINISHED_ROUND 368 PERF_RECORD_FINISHED_ROUND = 68,
521 369
522 No event reordering over this header. No paylo 370 No event reordering over this header. No payload.
523 371
524 PERF_RECORD_ID_INDEX 372 PERF_RECORD_ID_INDEX = 69,
525 373
526 Map event ids to CPUs and TIDs. 374 Map event ids to CPUs and TIDs.
527 375
528 struct id_index_entry { 376 struct id_index_entry {
529 uint64_t id; 377 uint64_t id;
530 uint64_t idx; 378 uint64_t idx;
531 uint64_t cpu; 379 uint64_t cpu;
532 uint64_t tid; 380 uint64_t tid;
533 }; 381 };
534 382
535 struct id_index_event { 383 struct id_index_event {
536 struct perf_event_header header; 384 struct perf_event_header header;
537 uint64_t nr; 385 uint64_t nr;
538 struct id_index_entry entries[nr]; 386 struct id_index_entry entries[nr];
539 }; 387 };
540 388
541 PERF_RECORD_AUXTRACE_INFO 389 PERF_RECORD_AUXTRACE_INFO = 70,
542 390
543 Auxtrace type specific information. Describe m 391 Auxtrace type specific information. Describe me
544 392
545 struct auxtrace_info_event { 393 struct auxtrace_info_event {
546 struct perf_event_header header; 394 struct perf_event_header header;
547 uint32_t type; 395 uint32_t type;
548 uint32_t reserved__; /* For alignment 396 uint32_t reserved__; /* For alignment */
549 uint64_t priv[]; 397 uint64_t priv[];
550 }; 398 };
551 399
552 PERF_RECORD_AUXTRACE 400 PERF_RECORD_AUXTRACE = 71,
553 401
554 Defines auxtrace data. Followed by the actual 402 Defines auxtrace data. Followed by the actual data. The contents of
555 the auxtrace data is dependent on the event an 403 the auxtrace data is dependent on the event and the CPU. For example
556 for Intel Processor Trace it contains Processo 404 for Intel Processor Trace it contains Processor Trace data generated
557 by the CPU. 405 by the CPU.
558 406
559 struct auxtrace_event { 407 struct auxtrace_event {
560 struct perf_event_header header; 408 struct perf_event_header header;
561 uint64_t size; 409 uint64_t size;
562 uint64_t offset; 410 uint64_t offset;
563 uint64_t reference; 411 uint64_t reference;
564 uint32_t idx; 412 uint32_t idx;
565 uint32_t tid; 413 uint32_t tid;
566 uint32_t cpu; 414 uint32_t cpu;
567 uint32_t reserved__; /* For alignment 415 uint32_t reserved__; /* For alignment */
568 }; 416 };
569 417
570 struct aux_event { 418 struct aux_event {
571 struct perf_event_header header; 419 struct perf_event_header header;
572 uint64_t aux_offset; 420 uint64_t aux_offset;
573 uint64_t aux_size; 421 uint64_t aux_size;
574 uint64_t flags; 422 uint64_t flags;
575 }; 423 };
576 424
577 PERF_RECORD_AUXTRACE_ERROR 425 PERF_RECORD_AUXTRACE_ERROR = 72,
578 426
579 Describes an error in hardware tracing 427 Describes an error in hardware tracing
580 428
581 enum auxtrace_error_type { 429 enum auxtrace_error_type {
582 PERF_AUXTRACE_ERROR_ITRACE = 1, 430 PERF_AUXTRACE_ERROR_ITRACE = 1,
583 PERF_AUXTRACE_ERROR_MAX 431 PERF_AUXTRACE_ERROR_MAX
584 }; 432 };
585 433
586 #define MAX_AUXTRACE_ERROR_MSG 64 434 #define MAX_AUXTRACE_ERROR_MSG 64
587 435
588 struct auxtrace_error_event { 436 struct auxtrace_error_event {
589 struct perf_event_header header; 437 struct perf_event_header header;
590 uint32_t type; 438 uint32_t type;
591 uint32_t code; 439 uint32_t code;
592 uint32_t cpu; 440 uint32_t cpu;
593 uint32_t pid; 441 uint32_t pid;
594 uint32_t tid; 442 uint32_t tid;
595 uint32_t reserved__; /* For alignment 443 uint32_t reserved__; /* For alignment */
596 uint64_t ip; 444 uint64_t ip;
597 char msg[MAX_AUXTRACE_ERROR_MSG]; 445 char msg[MAX_AUXTRACE_ERROR_MSG];
598 }; 446 };
599 447
600 PERF_RECORD_HEADER_FEATURE 448 PERF_RECORD_HEADER_FEATURE = 80,
601 449
602 Describes a header feature. These are records 450 Describes a header feature. These are records used in pipe-mode that
603 contain information that otherwise would be in 451 contain information that otherwise would be in perf.data file's header.
604 452
605 PERF_RECORD_COMPRESSED 453 PERF_RECORD_COMPRESSED = 81,
606 454
607 struct compressed_event { 455 struct compressed_event {
608 struct perf_event_header header 456 struct perf_event_header header;
609 char data[] 457 char data[];
610 }; 458 };
611 <<
612 PERF_RECORD_FINISHED_INIT <<
613 <<
614 Marks the end of records for the system, pre-e <<
615 sessions, etc. Those are the ones prefixed PER <<
616 <<
617 This is used, for instance, to 'perf inject' e <<
618 regular events, those emitted by the kernel, t <<
619 host records. <<
620 <<
621 459
622 The header is followed by compressed data fram 460 The header is followed by compressed data frame that can be decompressed
623 into array of perf trace records. The size of 461 into array of perf trace records. The size of the entire compressed event
624 record including the header is limited by the 462 record including the header is limited by the max value of header.size.
625 463
626 Event types 464 Event types
627 465
628 Define the event attributes with their IDs. 466 Define the event attributes with their IDs.
629 467
630 An array bound by the perf_file_section size. 468 An array bound by the perf_file_section size.
631 469
632 struct { 470 struct {
633 struct perf_event_attr attr; 471 struct perf_event_attr attr; /* Size defined by header.attr_size */
634 struct perf_file_section ids; 472 struct perf_file_section ids;
635 } 473 }
636 474
637 ids points to a array of uint64_t defining the 475 ids points to a array of uint64_t defining the ids for event attr attr.
638 476
639 Pipe-mode data 477 Pipe-mode data
640 478
641 Pipe-mode avoid seeks in the file by removing 479 Pipe-mode avoid seeks in the file by removing the perf_file_section and flags
642 from the struct perf_header. The trimmed heade 480 from the struct perf_header. The trimmed header is:
643 481
644 struct perf_pipe_file_header { 482 struct perf_pipe_file_header {
645 u64 magic; 483 u64 magic;
646 u64 size; 484 u64 size;
647 }; 485 };
648 486
649 The information about attrs, data, and event_t 487 The information about attrs, data, and event_types is instead in the
650 synthesized events PERF_RECORD_ATTR, PERF_RECO 488 synthesized events PERF_RECORD_ATTR, PERF_RECORD_HEADER_TRACING_DATA,
651 PERF_RECORD_HEADER_EVENT_TYPE, and PERF_RECORD 489 PERF_RECORD_HEADER_EVENT_TYPE, and PERF_RECORD_HEADER_FEATURE
652 that are generated by perf record in pipe-mode 490 that are generated by perf record in pipe-mode.
653 491
654 492
655 References: 493 References:
656 494
657 include/uapi/linux/perf_event.h 495 include/uapi/linux/perf_event.h
658 496
659 This is the canonical description of the kerne 497 This is the canonical description of the kernel generated perf_events
660 and the perf_event_attrs. 498 and the perf_event_attrs.
661 499
662 perf_events manpage 500 perf_events manpage
663 501
664 A manpage describing perf_event and perf_event 502 A manpage describing perf_event and perf_event_attr is here:
665 http://web.eece.maine.edu/~vweaver/projects/pe 503 http://web.eece.maine.edu/~vweaver/projects/perf_events/programming.html
666 This tends to be slightly behind the kernel in 504 This tends to be slightly behind the kernel include, but has better
667 descriptions. An (typically older) version of 505 descriptions. An (typically older) version of the man page may be
668 included with the standard Linux man pages, av 506 included with the standard Linux man pages, available with "man
669 perf_events" 507 perf_events"
670 508
671 pmu-tools 509 pmu-tools
672 510
673 https://github.com/andikleen/pmu-tools/tree/ma 511 https://github.com/andikleen/pmu-tools/tree/master/parser
674 512
675 A definition of the perf.data format in python 513 A definition of the perf.data format in python "construct" format is available
676 in pmu-tools parser. This allows to read perf. 514 in pmu-tools parser. This allows to read perf.data from python and dump it.
677 515
678 quipper 516 quipper
679 517
680 The quipper C++ parser is available at 518 The quipper C++ parser is available at
681 http://github.com/google/perf_data_converter/t 519 http://github.com/google/perf_data_converter/tree/master/src/quipper
682 520
Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.