forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathbuiltin-stat.c
1935 lines (1624 loc) · 49.7 KB
/
builtin-stat.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* builtin-stat.c
*
* Builtin stat command: Give a precise performance counters summary
* overview about any workload, CPU or specific PID.
*
* Sample output:
$ perf stat ./hackbench 10
Time: 0.118
Performance counter stats for './hackbench 10':
1708.761321 task-clock # 11.037 CPUs utilized
41,190 context-switches # 0.024 M/sec
6,735 CPU-migrations # 0.004 M/sec
17,318 page-faults # 0.010 M/sec
5,205,202,243 cycles # 3.046 GHz
3,856,436,920 stalled-cycles-frontend # 74.09% frontend cycles idle
1,600,790,871 stalled-cycles-backend # 30.75% backend cycles idle
2,603,501,247 instructions # 0.50 insns per cycle
# 1.48 stalled cycles per insn
484,357,498 branches # 283.455 M/sec
6,388,934 branch-misses # 1.32% of all branches
0.154822978 seconds time elapsed
*
* Copyright (C) 2008-2011, Red Hat Inc, Ingo Molnar <[email protected]>
*
* Improvements and fixes by:
*
* Arjan van de Ven <[email protected]>
* Yanmin Zhang <[email protected]>
* Wu Fengguang <[email protected]>
* Mike Galbraith <[email protected]>
* Paul Mackerras <[email protected]>
* Jaswinder Singh Rajput <[email protected]>
*
* Released under the GPL v2. (and only v2, not any later version)
*/
#include "perf.h"
#include "builtin.h"
#include "util/cgroup.h"
#include "util/util.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
#include "util/pmu.h"
#include "util/event.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/debug.h"
#include "util/color.h"
#include "util/stat.h"
#include "util/header.h"
#include "util/cpumap.h"
#include "util/thread.h"
#include "util/thread_map.h"
#include <stdlib.h>
#include <sys/prctl.h>
#include <locale.h>
#define DEFAULT_SEPARATOR " "
#define CNTR_NOT_SUPPORTED "<not supported>"
#define CNTR_NOT_COUNTED "<not counted>"
static void print_stat(int argc, const char **argv);
static void print_counter_aggr(struct perf_evsel *counter, char *prefix);
static void print_counter(struct perf_evsel *counter, char *prefix);
static void print_aggr(char *prefix);
/* Default events used for perf stat -T */
static const char * const transaction_attrs[] = {
"task-clock",
"{"
"instructions,"
"cycles,"
"cpu/cycles-t/,"
"cpu/tx-start/,"
"cpu/el-start/,"
"cpu/cycles-ct/"
"}"
};
/* More limited version when the CPU does not have all events. */
static const char * const transaction_limited_attrs[] = {
"task-clock",
"{"
"instructions,"
"cycles,"
"cpu/cycles-t/,"
"cpu/tx-start/"
"}"
};
/* must match transaction_attrs and the beginning limited_attrs */
enum {
T_TASK_CLOCK,
T_INSTRUCTIONS,
T_CYCLES,
T_CYCLES_IN_TX,
T_TRANSACTION_START,
T_ELISION_START,
T_CYCLES_IN_TX_CP,
};
static struct perf_evlist *evsel_list;
static struct target target = {
.uid = UINT_MAX,
};
enum aggr_mode {
AGGR_NONE,
AGGR_GLOBAL,
AGGR_SOCKET,
AGGR_CORE,
};
static int run_count = 1;
static bool no_inherit = false;
static bool scale = true;
static enum aggr_mode aggr_mode = AGGR_GLOBAL;
static volatile pid_t child_pid = -1;
static bool null_run = false;
static int detailed_run = 0;
static bool transaction_run;
static bool big_num = true;
static int big_num_opt = -1;
static const char *csv_sep = NULL;
static bool csv_output = false;
static bool group = false;
static FILE *output = NULL;
static const char *pre_cmd = NULL;
static const char *post_cmd = NULL;
static bool sync_run = false;
static unsigned int interval = 0;
static unsigned int initial_delay = 0;
static unsigned int unit_width = 4; /* strlen("unit") */
static bool forever = false;
static struct timespec ref_time;
static struct cpu_map *aggr_map;
static int (*aggr_get_id)(struct cpu_map *m, int cpu);
static volatile int done = 0;
struct perf_stat {
struct stats res_stats[3];
};
static inline void diff_timespec(struct timespec *r, struct timespec *a,
struct timespec *b)
{
r->tv_sec = a->tv_sec - b->tv_sec;
if (a->tv_nsec < b->tv_nsec) {
r->tv_nsec = a->tv_nsec + 1000000000L - b->tv_nsec;
r->tv_sec--;
} else {
r->tv_nsec = a->tv_nsec - b->tv_nsec ;
}
}
static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel)
{
return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus;
}
static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel)
{
return perf_evsel__cpus(evsel)->nr;
}
static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel)
{
int i;
struct perf_stat *ps = evsel->priv;
for (i = 0; i < 3; i++)
init_stats(&ps->res_stats[i]);
}
static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
{
evsel->priv = zalloc(sizeof(struct perf_stat));
if (evsel->priv == NULL)
return -ENOMEM;
perf_evsel__reset_stat_priv(evsel);
return 0;
}
static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
{
zfree(&evsel->priv);
}
static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel)
{
void *addr;
size_t sz;
sz = sizeof(*evsel->counts) +
(perf_evsel__nr_cpus(evsel) * sizeof(struct perf_counts_values));
addr = zalloc(sz);
if (!addr)
return -ENOMEM;
evsel->prev_raw_counts = addr;
return 0;
}
static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel)
{
zfree(&evsel->prev_raw_counts);
}
static void perf_evlist__free_stats(struct perf_evlist *evlist)
{
struct perf_evsel *evsel;
evlist__for_each(evlist, evsel) {
perf_evsel__free_stat_priv(evsel);
perf_evsel__free_counts(evsel);
perf_evsel__free_prev_raw_counts(evsel);
}
}
static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw)
{
struct perf_evsel *evsel;
evlist__for_each(evlist, evsel) {
if (perf_evsel__alloc_stat_priv(evsel) < 0 ||
perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 ||
(alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0))
goto out_free;
}
return 0;
out_free:
perf_evlist__free_stats(evlist);
return -1;
}
static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
static struct stats runtime_cycles_stats[MAX_NR_CPUS];
static struct stats runtime_stalled_cycles_front_stats[MAX_NR_CPUS];
static struct stats runtime_stalled_cycles_back_stats[MAX_NR_CPUS];
static struct stats runtime_branches_stats[MAX_NR_CPUS];
static struct stats runtime_cacherefs_stats[MAX_NR_CPUS];
static struct stats runtime_l1_dcache_stats[MAX_NR_CPUS];
static struct stats runtime_l1_icache_stats[MAX_NR_CPUS];
static struct stats runtime_ll_cache_stats[MAX_NR_CPUS];
static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS];
static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS];
static struct stats runtime_cycles_in_tx_stats[MAX_NR_CPUS];
static struct stats walltime_nsecs_stats;
static struct stats runtime_transaction_stats[MAX_NR_CPUS];
static struct stats runtime_elision_stats[MAX_NR_CPUS];
static void perf_stat__reset_stats(struct perf_evlist *evlist)
{
struct perf_evsel *evsel;
evlist__for_each(evlist, evsel) {
perf_evsel__reset_stat_priv(evsel);
perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
}
memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
memset(runtime_cycles_in_tx_stats, 0,
sizeof(runtime_cycles_in_tx_stats));
memset(runtime_transaction_stats, 0,
sizeof(runtime_transaction_stats));
memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
}
static int create_perf_stat_counter(struct perf_evsel *evsel)
{
struct perf_event_attr *attr = &evsel->attr;
if (scale)
attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
PERF_FORMAT_TOTAL_TIME_RUNNING;
attr->inherit = !no_inherit;
if (target__has_cpu(&target))
return perf_evsel__open_per_cpu(evsel, perf_evsel__cpus(evsel));
if (!target__has_task(&target) && perf_evsel__is_group_leader(evsel)) {
attr->disabled = 1;
if (!initial_delay)
attr->enable_on_exec = 1;
}
return perf_evsel__open_per_thread(evsel, evsel_list->threads);
}
/*
* Does the counter have nsecs as a unit?
*/
static inline int nsec_counter(struct perf_evsel *evsel)
{
if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
return 1;
return 0;
}
static struct perf_evsel *nth_evsel(int n)
{
static struct perf_evsel **array;
static int array_len;
struct perf_evsel *ev;
int j;
/* Assumes this only called when evsel_list does not change anymore. */
if (!array) {
evlist__for_each(evsel_list, ev)
array_len++;
array = malloc(array_len * sizeof(void *));
if (!array)
exit(ENOMEM);
j = 0;
evlist__for_each(evsel_list, ev)
array[j++] = ev;
}
if (n < array_len)
return array[n];
return NULL;
}
/*
* Update various tracking values we maintain to print
* more semantic information such as miss/hit ratios,
* instruction rates, etc:
*/
static void update_shadow_stats(struct perf_evsel *counter, u64 *count,
int cpu)
{
if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
update_stats(&runtime_nsecs_stats[cpu], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
update_stats(&runtime_cycles_stats[cpu], count[0]);
else if (transaction_run &&
perf_evsel__cmp(counter, nth_evsel(T_CYCLES_IN_TX)))
update_stats(&runtime_cycles_in_tx_stats[cpu], count[0]);
else if (transaction_run &&
perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START)))
update_stats(&runtime_transaction_stats[cpu], count[0]);
else if (transaction_run &&
perf_evsel__cmp(counter, nth_evsel(T_ELISION_START)))
update_stats(&runtime_elision_stats[cpu], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_stats(&runtime_stalled_cycles_front_stats[cpu], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
update_stats(&runtime_stalled_cycles_back_stats[cpu], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
update_stats(&runtime_branches_stats[cpu], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
update_stats(&runtime_cacherefs_stats[cpu], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
update_stats(&runtime_l1_dcache_stats[cpu], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
update_stats(&runtime_l1_icache_stats[cpu], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
update_stats(&runtime_ll_cache_stats[cpu], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
update_stats(&runtime_dtlb_cache_stats[cpu], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
update_stats(&runtime_itlb_cache_stats[cpu], count[0]);
}
static void zero_per_pkg(struct perf_evsel *counter)
{
if (counter->per_pkg_mask)
memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
}
static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
{
unsigned long *mask = counter->per_pkg_mask;
struct cpu_map *cpus = perf_evsel__cpus(counter);
int s;
*skip = false;
if (!counter->per_pkg)
return 0;
if (cpu_map__empty(cpus))
return 0;
if (!mask) {
mask = zalloc(MAX_NR_CPUS);
if (!mask)
return -ENOMEM;
counter->per_pkg_mask = mask;
}
s = cpu_map__get_socket(cpus, cpu);
if (s < 0)
return -1;
*skip = test_and_set_bit(s, mask) == 1;
return 0;
}
static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
struct perf_counts_values *count)
{
struct perf_counts_values *aggr = &evsel->counts->aggr;
static struct perf_counts_values zero;
bool skip = false;
if (check_per_pkg(evsel, cpu, &skip)) {
pr_err("failed to read per-pkg counter\n");
return -1;
}
if (skip)
count = &zero;
switch (aggr_mode) {
case AGGR_CORE:
case AGGR_SOCKET:
case AGGR_NONE:
if (!evsel->snapshot)
perf_evsel__compute_deltas(evsel, cpu, count);
perf_counts_values__scale(count, scale, NULL);
evsel->counts->cpu[cpu] = *count;
if (aggr_mode == AGGR_NONE)
update_shadow_stats(evsel, count->values, cpu);
break;
case AGGR_GLOBAL:
aggr->val += count->val;
if (scale) {
aggr->ena += count->ena;
aggr->run += count->run;
}
default:
break;
}
return 0;
}
static int read_counter(struct perf_evsel *counter);
/*
* Read out the results of a single counter:
* aggregate counts across CPUs in system-wide mode
*/
static int read_counter_aggr(struct perf_evsel *counter)
{
struct perf_counts_values *aggr = &counter->counts->aggr;
struct perf_stat *ps = counter->priv;
u64 *count = counter->counts->aggr.values;
int i;
aggr->val = aggr->ena = aggr->run = 0;
if (read_counter(counter))
return -1;
if (!counter->snapshot)
perf_evsel__compute_deltas(counter, -1, aggr);
perf_counts_values__scale(aggr, scale, &counter->counts->scaled);
for (i = 0; i < 3; i++)
update_stats(&ps->res_stats[i], count[i]);
if (verbose) {
fprintf(output, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
perf_evsel__name(counter), count[0], count[1], count[2]);
}
/*
* Save the full runtime - to allow normalization during printout:
*/
update_shadow_stats(counter, count, 0);
return 0;
}
/*
* Read out the results of a single counter:
* do not aggregate counts across CPUs in system-wide mode
*/
static int read_counter(struct perf_evsel *counter)
{
int nthreads = thread_map__nr(evsel_list->threads);
int ncpus = perf_evsel__nr_cpus(counter);
int cpu, thread;
if (!counter->supported)
return -ENOENT;
if (counter->system_wide)
nthreads = 1;
if (counter->per_pkg)
zero_per_pkg(counter);
for (thread = 0; thread < nthreads; thread++) {
for (cpu = 0; cpu < ncpus; cpu++) {
if (perf_evsel__read_cb(counter, cpu, thread, read_cb))
return -1;
}
}
return 0;
}
static void print_interval(void)
{
static int num_print_interval;
struct perf_evsel *counter;
struct perf_stat *ps;
struct timespec ts, rs;
char prefix[64];
if (aggr_mode == AGGR_GLOBAL) {
evlist__for_each(evsel_list, counter) {
ps = counter->priv;
memset(ps->res_stats, 0, sizeof(ps->res_stats));
read_counter_aggr(counter);
}
} else {
evlist__for_each(evsel_list, counter) {
ps = counter->priv;
memset(ps->res_stats, 0, sizeof(ps->res_stats));
read_counter(counter);
}
}
clock_gettime(CLOCK_MONOTONIC, &ts);
diff_timespec(&rs, &ts, &ref_time);
sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep);
if (num_print_interval == 0 && !csv_output) {
switch (aggr_mode) {
case AGGR_SOCKET:
fprintf(output, "# time socket cpus counts %*s events\n", unit_width, "unit");
break;
case AGGR_CORE:
fprintf(output, "# time core cpus counts %*s events\n", unit_width, "unit");
break;
case AGGR_NONE:
fprintf(output, "# time CPU counts %*s events\n", unit_width, "unit");
break;
case AGGR_GLOBAL:
default:
fprintf(output, "# time counts %*s events\n", unit_width, "unit");
}
}
if (++num_print_interval == 25)
num_print_interval = 0;
switch (aggr_mode) {
case AGGR_CORE:
case AGGR_SOCKET:
print_aggr(prefix);
break;
case AGGR_NONE:
evlist__for_each(evsel_list, counter)
print_counter(counter, prefix);
break;
case AGGR_GLOBAL:
default:
evlist__for_each(evsel_list, counter)
print_counter_aggr(counter, prefix);
}
fflush(output);
}
static void handle_initial_delay(void)
{
struct perf_evsel *counter;
if (initial_delay) {
const int ncpus = cpu_map__nr(evsel_list->cpus),
nthreads = thread_map__nr(evsel_list->threads);
usleep(initial_delay * 1000);
evlist__for_each(evsel_list, counter)
perf_evsel__enable(counter, ncpus, nthreads);
}
}
static volatile int workload_exec_errno;
/*
* perf_evlist__prepare_workload will send a SIGUSR1
* if the fork fails, since we asked by setting its
* want_signal to true.
*/
static void workload_exec_failed_signal(int signo __maybe_unused, siginfo_t *info,
void *ucontext __maybe_unused)
{
workload_exec_errno = info->si_value.sival_int;
}
static int __run_perf_stat(int argc, const char **argv)
{
char msg[512];
unsigned long long t0, t1;
struct perf_evsel *counter;
struct timespec ts;
size_t l;
int status = 0;
const bool forks = (argc > 0);
if (interval) {
ts.tv_sec = interval / 1000;
ts.tv_nsec = (interval % 1000) * 1000000;
} else {
ts.tv_sec = 1;
ts.tv_nsec = 0;
}
if (forks) {
if (perf_evlist__prepare_workload(evsel_list, &target, argv, false,
workload_exec_failed_signal) < 0) {
perror("failed to prepare workload");
return -1;
}
child_pid = evsel_list->workload.pid;
}
if (group)
perf_evlist__set_leader(evsel_list);
evlist__for_each(evsel_list, counter) {
if (create_perf_stat_counter(counter) < 0) {
/*
* PPC returns ENXIO for HW counters until 2.6.37
* (behavior changed with commit b0a873e).
*/
if (errno == EINVAL || errno == ENOSYS ||
errno == ENOENT || errno == EOPNOTSUPP ||
errno == ENXIO) {
if (verbose)
ui__warning("%s event is not supported by the kernel.\n",
perf_evsel__name(counter));
counter->supported = false;
continue;
}
perf_evsel__open_strerror(counter, &target,
errno, msg, sizeof(msg));
ui__error("%s\n", msg);
if (child_pid != -1)
kill(child_pid, SIGTERM);
return -1;
}
counter->supported = true;
l = strlen(counter->unit);
if (l > unit_width)
unit_width = l;
}
if (perf_evlist__apply_filters(evsel_list, &counter)) {
error("failed to set filter \"%s\" on event %s with %d (%s)\n",
counter->filter, perf_evsel__name(counter), errno,
strerror_r(errno, msg, sizeof(msg)));
return -1;
}
/*
* Enable counters and exec the command:
*/
t0 = rdclock();
clock_gettime(CLOCK_MONOTONIC, &ref_time);
if (forks) {
perf_evlist__start_workload(evsel_list);
handle_initial_delay();
if (interval) {
while (!waitpid(child_pid, &status, WNOHANG)) {
nanosleep(&ts, NULL);
print_interval();
}
}
wait(&status);
if (workload_exec_errno) {
const char *emsg = strerror_r(workload_exec_errno, msg, sizeof(msg));
pr_err("Workload failed: %s\n", emsg);
return -1;
}
if (WIFSIGNALED(status))
psignal(WTERMSIG(status), argv[0]);
} else {
handle_initial_delay();
while (!done) {
nanosleep(&ts, NULL);
if (interval)
print_interval();
}
}
t1 = rdclock();
update_stats(&walltime_nsecs_stats, t1 - t0);
if (aggr_mode == AGGR_GLOBAL) {
evlist__for_each(evsel_list, counter) {
read_counter_aggr(counter);
perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
thread_map__nr(evsel_list->threads));
}
} else {
evlist__for_each(evsel_list, counter) {
read_counter(counter);
perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1);
}
}
return WEXITSTATUS(status);
}
static int run_perf_stat(int argc, const char **argv)
{
int ret;
if (pre_cmd) {
ret = system(pre_cmd);
if (ret)
return ret;
}
if (sync_run)
sync();
ret = __run_perf_stat(argc, argv);
if (ret)
return ret;
if (post_cmd) {
ret = system(post_cmd);
if (ret)
return ret;
}
return ret;
}
static void print_running(u64 run, u64 ena)
{
if (csv_output) {
fprintf(output, "%s%" PRIu64 "%s%.2f",
csv_sep,
run,
csv_sep,
ena ? 100.0 * run / ena : 100.0);
} else if (run != ena) {
fprintf(output, " (%.2f%%)", 100.0 * run / ena);
}
}
static void print_noise_pct(double total, double avg)
{
double pct = rel_stddev_stats(total, avg);
if (csv_output)
fprintf(output, "%s%.2f%%", csv_sep, pct);
else if (pct)
fprintf(output, " ( +-%6.2f%% )", pct);
}
static void print_noise(struct perf_evsel *evsel, double avg)
{
struct perf_stat *ps;
if (run_count == 1)
return;
ps = evsel->priv;
print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
}
static void aggr_printout(struct perf_evsel *evsel, int id, int nr)
{
switch (aggr_mode) {
case AGGR_CORE:
fprintf(output, "S%d-C%*d%s%*d%s",
cpu_map__id_to_socket(id),
csv_output ? 0 : -8,
cpu_map__id_to_cpu(id),
csv_sep,
csv_output ? 0 : 4,
nr,
csv_sep);
break;
case AGGR_SOCKET:
fprintf(output, "S%*d%s%*d%s",
csv_output ? 0 : -5,
id,
csv_sep,
csv_output ? 0 : 4,
nr,
csv_sep);
break;
case AGGR_NONE:
fprintf(output, "CPU%*d%s",
csv_output ? 0 : -4,
perf_evsel__cpus(evsel)->map[id], csv_sep);
break;
case AGGR_GLOBAL:
default:
break;
}
}
static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
{
double msecs = avg / 1e6;
const char *fmt_v, *fmt_n;
char name[25];
fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
fmt_n = csv_output ? "%s" : "%-25s";
aggr_printout(evsel, id, nr);
scnprintf(name, sizeof(name), "%s%s",
perf_evsel__name(evsel), csv_output ? "" : " (msec)");
fprintf(output, fmt_v, msecs, csv_sep);
if (csv_output)
fprintf(output, "%s%s", evsel->unit, csv_sep);
else
fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep);
fprintf(output, fmt_n, name);
if (evsel->cgrp)
fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
if (csv_output || interval)
return;
if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
fprintf(output, " # %8.3f CPUs utilized ",
avg / avg_stats(&walltime_nsecs_stats));
else
fprintf(output, " ");
}
/* used for get_ratio_color() */
enum grc_type {
GRC_STALLED_CYCLES_FE,
GRC_STALLED_CYCLES_BE,
GRC_CACHE_MISSES,
GRC_MAX_NR
};
static const char *get_ratio_color(enum grc_type type, double ratio)
{
static const double grc_table[GRC_MAX_NR][3] = {
[GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },
[GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },
[GRC_CACHE_MISSES] = { 20.0, 10.0, 5.0 },
};
const char *color = PERF_COLOR_NORMAL;
if (ratio > grc_table[type][0])
color = PERF_COLOR_RED;
else if (ratio > grc_table[type][1])
color = PERF_COLOR_MAGENTA;
else if (ratio > grc_table[type][2])
color = PERF_COLOR_YELLOW;
return color;
}
static void print_stalled_cycles_frontend(int cpu,
struct perf_evsel *evsel
__maybe_unused, double avg)
{
double total, ratio = 0.0;
const char *color;
total = avg_stats(&runtime_cycles_stats[cpu]);
if (total)
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
fprintf(output, " # ");
color_fprintf(output, color, "%6.2f%%", ratio);
fprintf(output, " frontend cycles idle ");
}
static void print_stalled_cycles_backend(int cpu,
struct perf_evsel *evsel
__maybe_unused, double avg)
{
double total, ratio = 0.0;
const char *color;
total = avg_stats(&runtime_cycles_stats[cpu]);
if (total)
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
fprintf(output, " # ");
color_fprintf(output, color, "%6.2f%%", ratio);
fprintf(output, " backend cycles idle ");
}
static void print_branch_misses(int cpu,
struct perf_evsel *evsel __maybe_unused,
double avg)
{
double total, ratio = 0.0;
const char *color;
total = avg_stats(&runtime_branches_stats[cpu]);
if (total)
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
fprintf(output, " # ");
color_fprintf(output, color, "%6.2f%%", ratio);
fprintf(output, " of all branches ");
}
static void print_l1_dcache_misses(int cpu,
struct perf_evsel *evsel __maybe_unused,
double avg)
{
double total, ratio = 0.0;
const char *color;
total = avg_stats(&runtime_l1_dcache_stats[cpu]);
if (total)
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
fprintf(output, " # ");
color_fprintf(output, color, "%6.2f%%", ratio);
fprintf(output, " of all L1-dcache hits ");
}
static void print_l1_icache_misses(int cpu,
struct perf_evsel *evsel __maybe_unused,
double avg)
{
double total, ratio = 0.0;
const char *color;
total = avg_stats(&runtime_l1_icache_stats[cpu]);
if (total)
ratio = avg / total * 100.0;
color = get_ratio_color(GRC_CACHE_MISSES, ratio);
fprintf(output, " # ");
color_fprintf(output, color, "%6.2f%%", ratio);
fprintf(output, " of all L1-icache hits ");
}
static void print_dtlb_cache_misses(int cpu,