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
|
// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// Malloc profiling.
// Patterned after tcmalloc's algorithms; shorter code.
package runtime
import (
"runtime/internal/atomic"
"unsafe"
)
// Export temporarily for gccgo's C code to call:
//go:linkname mProf_Malloc runtime.mProf_Malloc
//go:linkname mProf_Free runtime.mProf_Free
//go:linkname mProf_GC runtime.mProf_GC
//go:linkname tracealloc runtime.tracealloc
//go:linkname tracefree runtime.tracefree
//go:linkname tracegc runtime.tracegc
//go:linkname iterate_memprof runtime.iterate_memprof
// NOTE(rsc): Everything here could use cas if contention became an issue.
var proflock mutex
// All memory allocations are local and do not escape outside of the profiler.
// The profiler is forbidden from referring to garbage-collected memory.
const (
// profile types
memProfile bucketType = 1 + iota
blockProfile
// size of bucket hash table
buckHashSize = 179999
// max depth of stack to record in bucket
maxStack = 32
)
type bucketType int
// A bucket holds per-call-stack profiling information.
// The representation is a bit sleazy, inherited from C.
// This struct defines the bucket header. It is followed in
// memory by the stack words and then the actual record
// data, either a memRecord or a blockRecord.
//
// Per-call-stack profiling information.
// Lookup by hashing call stack into a linked-list hash table.
type bucket struct {
next *bucket
allnext *bucket
typ bucketType // memBucket or blockBucket
hash uintptr
size uintptr
nstk uintptr
}
// A memRecord is the bucket data for a bucket of type memProfile,
// part of the memory profile.
type memRecord struct {
// The following complex 3-stage scheme of stats accumulation
// is required to obtain a consistent picture of mallocs and frees
// for some point in time.
// The problem is that mallocs come in real time, while frees
// come only after a GC during concurrent sweeping. So if we would
// naively count them, we would get a skew toward mallocs.
//
// Mallocs are accounted in recent stats.
// Explicit frees are accounted in recent stats.
// GC frees are accounted in prev stats.
// After GC prev stats are added to final stats and
// recent stats are moved into prev stats.
allocs uintptr
frees uintptr
alloc_bytes uintptr
free_bytes uintptr
// changes between next-to-last GC and last GC
prev_allocs uintptr
prev_frees uintptr
prev_alloc_bytes uintptr
prev_free_bytes uintptr
// changes since last GC
recent_allocs uintptr
recent_frees uintptr
recent_alloc_bytes uintptr
recent_free_bytes uintptr
}
// A blockRecord is the bucket data for a bucket of type blockProfile,
// part of the blocking profile.
type blockRecord struct {
count int64
cycles int64
}
var (
mbuckets *bucket // memory profile buckets
bbuckets *bucket // blocking profile buckets
buckhash *[179999]*bucket
bucketmem uintptr
)
// newBucket allocates a bucket with the given type and number of stack entries.
func newBucket(typ bucketType, nstk int) *bucket {
size := unsafe.Sizeof(bucket{}) + uintptr(nstk)*unsafe.Sizeof(location{})
switch typ {
default:
throw("invalid profile bucket type")
case memProfile:
size += unsafe.Sizeof(memRecord{})
case blockProfile:
size += unsafe.Sizeof(blockRecord{})
}
b := (*bucket)(persistentalloc(size, 0, &memstats.buckhash_sys))
bucketmem += size
b.typ = typ
b.nstk = uintptr(nstk)
return b
}
// stk returns the slice in b holding the stack.
func (b *bucket) stk() []location {
stk := (*[maxStack]location)(add(unsafe.Pointer(b), unsafe.Sizeof(*b)))
return stk[:b.nstk:b.nstk]
}
// mp returns the memRecord associated with the memProfile bucket b.
func (b *bucket) mp() *memRecord {
if b.typ != memProfile {
throw("bad use of bucket.mp")
}
data := add(unsafe.Pointer(b), unsafe.Sizeof(*b)+b.nstk*unsafe.Sizeof(location{}))
return (*memRecord)(data)
}
// bp returns the blockRecord associated with the blockProfile bucket b.
func (b *bucket) bp() *blockRecord {
if b.typ != blockProfile {
throw("bad use of bucket.bp")
}
data := add(unsafe.Pointer(b), unsafe.Sizeof(*b)+b.nstk*unsafe.Sizeof(location{}))
return (*blockRecord)(data)
}
// Return the bucket for stk[0:nstk], allocating new bucket if needed.
func stkbucket(typ bucketType, size uintptr, stk []location, alloc bool) *bucket {
if buckhash == nil {
buckhash = (*[buckHashSize]*bucket)(sysAlloc(unsafe.Sizeof(*buckhash), &memstats.buckhash_sys))
if buckhash == nil {
throw("runtime: cannot allocate memory")
}
}
// Hash stack.
var h uintptr
for _, loc := range stk {
h += loc.pc
h += h << 10
h ^= h >> 6
}
// hash in size
h += size
h += h << 10
h ^= h >> 6
// finalize
h += h << 3
h ^= h >> 11
i := int(h % buckHashSize)
for b := buckhash[i]; b != nil; b = b.next {
if b.typ == typ && b.hash == h && b.size == size && eqslice(b.stk(), stk) {
return b
}
}
if !alloc {
return nil
}
// Create new bucket.
b := newBucket(typ, len(stk))
copy(b.stk(), stk)
b.hash = h
b.size = size
b.next = buckhash[i]
buckhash[i] = b
if typ == memProfile {
b.allnext = mbuckets
mbuckets = b
} else {
b.allnext = bbuckets
bbuckets = b
}
return b
}
func eqslice(x, y []location) bool {
if len(x) != len(y) {
return false
}
for i, xi := range x {
if xi != y[i] {
return false
}
}
return true
}
func mprof_GC() {
for b := mbuckets; b != nil; b = b.allnext {
mp := b.mp()
mp.allocs += mp.prev_allocs
mp.frees += mp.prev_frees
mp.alloc_bytes += mp.prev_alloc_bytes
mp.free_bytes += mp.prev_free_bytes
mp.prev_allocs = mp.recent_allocs
mp.prev_frees = mp.recent_frees
mp.prev_alloc_bytes = mp.recent_alloc_bytes
mp.prev_free_bytes = mp.recent_free_bytes
mp.recent_allocs = 0
mp.recent_frees = 0
mp.recent_alloc_bytes = 0
mp.recent_free_bytes = 0
}
}
// Record that a gc just happened: all the 'recent' statistics are now real.
func mProf_GC() {
lock(&proflock)
mprof_GC()
unlock(&proflock)
}
// Called by malloc to record a profiled block.
func mProf_Malloc(p unsafe.Pointer, size uintptr) {
var stk [maxStack]location
nstk := callers(4, stk[:])
lock(&proflock)
b := stkbucket(memProfile, size, stk[:nstk], true)
mp := b.mp()
mp.recent_allocs++
mp.recent_alloc_bytes += size
unlock(&proflock)
// Setprofilebucket locks a bunch of other mutexes, so we call it outside of proflock.
// This reduces potential contention and chances of deadlocks.
// Since the object must be alive during call to mProf_Malloc,
// it's fine to do this non-atomically.
systemstack(func() {
setprofilebucket(p, b)
})
}
// Called when freeing a profiled block.
func mProf_Free(b *bucket, size uintptr) {
lock(&proflock)
mp := b.mp()
mp.prev_frees++
mp.prev_free_bytes += size
unlock(&proflock)
}
var blockprofilerate uint64 // in CPU ticks
// SetBlockProfileRate controls the fraction of goroutine blocking events
// that are reported in the blocking profile. The profiler aims to sample
// an average of one blocking event per rate nanoseconds spent blocked.
//
// To include every blocking event in the profile, pass rate = 1.
// To turn off profiling entirely, pass rate <= 0.
func SetBlockProfileRate(rate int) {
var r int64
if rate <= 0 {
r = 0 // disable profiling
} else if rate == 1 {
r = 1 // profile everything
} else {
// convert ns to cycles, use float64 to prevent overflow during multiplication
r = int64(float64(rate) * float64(tickspersecond()) / (1000 * 1000 * 1000))
if r == 0 {
r = 1
}
}
atomic.Store64(&blockprofilerate, uint64(r))
}
func blockevent(cycles int64, skip int) {
if cycles <= 0 {
cycles = 1
}
rate := int64(atomic.Load64(&blockprofilerate))
if rate <= 0 || (rate > cycles && int64(fastrand1())%rate > cycles) {
return
}
gp := getg()
var nstk int
var stk [maxStack]location
if gp.m.curg == nil || gp.m.curg == gp {
nstk = callers(skip, stk[:])
} else {
// FIXME: This should get a traceback of gp.m.curg.
// nstk = gcallers(gp.m.curg, skip, stk[:])
nstk = callers(skip, stk[:])
}
lock(&proflock)
b := stkbucket(blockProfile, 0, stk[:nstk], true)
b.bp().count++
b.bp().cycles += cycles
unlock(&proflock)
}
// Go interface to profile data.
// A StackRecord describes a single execution stack.
type StackRecord struct {
Stack0 [32]uintptr // stack trace for this record; ends at first 0 entry
}
// Stack returns the stack trace associated with the record,
// a prefix of r.Stack0.
func (r *StackRecord) Stack() []uintptr {
for i, v := range r.Stack0 {
if v == 0 {
return r.Stack0[0:i]
}
}
return r.Stack0[0:]
}
// MemProfileRate controls the fraction of memory allocations
// that are recorded and reported in the memory profile.
// The profiler aims to sample an average of
// one allocation per MemProfileRate bytes allocated.
//
// To include every allocated block in the profile, set MemProfileRate to 1.
// To turn off profiling entirely, set MemProfileRate to 0.
//
// The tools that process the memory profiles assume that the
// profile rate is constant across the lifetime of the program
// and equal to the current value. Programs that change the
// memory profiling rate should do so just once, as early as
// possible in the execution of the program (for example,
// at the beginning of main).
var MemProfileRate int = 512 * 1024
// A MemProfileRecord describes the live objects allocated
// by a particular call sequence (stack trace).
type MemProfileRecord struct {
AllocBytes, FreeBytes int64 // number of bytes allocated, freed
AllocObjects, FreeObjects int64 // number of objects allocated, freed
Stack0 [32]uintptr // stack trace for this record; ends at first 0 entry
}
// InUseBytes returns the number of bytes in use (AllocBytes - FreeBytes).
func (r *MemProfileRecord) InUseBytes() int64 { return r.AllocBytes - r.FreeBytes }
// InUseObjects returns the number of objects in use (AllocObjects - FreeObjects).
func (r *MemProfileRecord) InUseObjects() int64 {
return r.AllocObjects - r.FreeObjects
}
// Stack returns the stack trace associated with the record,
// a prefix of r.Stack0.
func (r *MemProfileRecord) Stack() []uintptr {
for i, v := range r.Stack0 {
if v == 0 {
return r.Stack0[0:i]
}
}
return r.Stack0[0:]
}
// MemProfile returns a profile of memory allocated and freed per allocation
// site.
//
// MemProfile returns n, the number of records in the current memory profile.
// If len(p) >= n, MemProfile copies the profile into p and returns n, true.
// If len(p) < n, MemProfile does not change p and returns n, false.
//
// If inuseZero is true, the profile includes allocation records
// where r.AllocBytes > 0 but r.AllocBytes == r.FreeBytes.
// These are sites where memory was allocated, but it has all
// been released back to the runtime.
//
// The returned profile may be up to two garbage collection cycles old.
// This is to avoid skewing the profile toward allocations; because
// allocations happen in real time but frees are delayed until the garbage
// collector performs sweeping, the profile only accounts for allocations
// that have had a chance to be freed by the garbage collector.
//
// Most clients should use the runtime/pprof package or
// the testing package's -test.memprofile flag instead
// of calling MemProfile directly.
func MemProfile(p []MemProfileRecord, inuseZero bool) (n int, ok bool) {
lock(&proflock)
clear := true
for b := mbuckets; b != nil; b = b.allnext {
mp := b.mp()
if inuseZero || mp.alloc_bytes != mp.free_bytes {
n++
}
if mp.allocs != 0 || mp.frees != 0 {
clear = false
}
}
if clear {
// Absolutely no data, suggesting that a garbage collection
// has not yet happened. In order to allow profiling when
// garbage collection is disabled from the beginning of execution,
// accumulate stats as if a GC just happened, and recount buckets.
mprof_GC()
mprof_GC()
n = 0
for b := mbuckets; b != nil; b = b.allnext {
mp := b.mp()
if inuseZero || mp.alloc_bytes != mp.free_bytes {
n++
}
}
}
if n <= len(p) {
ok = true
idx := 0
for b := mbuckets; b != nil; b = b.allnext {
mp := b.mp()
if inuseZero || mp.alloc_bytes != mp.free_bytes {
record(&p[idx], b)
idx++
}
}
}
unlock(&proflock)
return
}
// Write b's data to r.
func record(r *MemProfileRecord, b *bucket) {
mp := b.mp()
r.AllocBytes = int64(mp.alloc_bytes)
r.FreeBytes = int64(mp.free_bytes)
r.AllocObjects = int64(mp.allocs)
r.FreeObjects = int64(mp.frees)
for i, loc := range b.stk() {
if i >= len(r.Stack0) {
break
}
r.Stack0[i] = loc.pc
}
for i := int(b.nstk); i < len(r.Stack0); i++ {
r.Stack0[i] = 0
}
}
func iterate_memprof(fn func(*bucket, uintptr, *location, uintptr, uintptr, uintptr)) {
lock(&proflock)
for b := mbuckets; b != nil; b = b.allnext {
mp := b.mp()
fn(b, b.nstk, &b.stk()[0], b.size, mp.allocs, mp.frees)
}
unlock(&proflock)
}
// BlockProfileRecord describes blocking events originated
// at a particular call sequence (stack trace).
type BlockProfileRecord struct {
Count int64
Cycles int64
StackRecord
}
// BlockProfile returns n, the number of records in the current blocking profile.
// If len(p) >= n, BlockProfile copies the profile into p and returns n, true.
// If len(p) < n, BlockProfile does not change p and returns n, false.
//
// Most clients should use the runtime/pprof package or
// the testing package's -test.blockprofile flag instead
// of calling BlockProfile directly.
func BlockProfile(p []BlockProfileRecord) (n int, ok bool) {
lock(&proflock)
for b := bbuckets; b != nil; b = b.allnext {
n++
}
if n <= len(p) {
ok = true
for b := bbuckets; b != nil; b = b.allnext {
bp := b.bp()
r := &p[0]
r.Count = bp.count
r.Cycles = bp.cycles
i := 0
var loc location
for i, loc = range b.stk() {
if i >= len(r.Stack0) {
break
}
r.Stack0[i] = loc.pc
}
for ; i < len(r.Stack0); i++ {
r.Stack0[i] = 0
}
p = p[1:]
}
}
unlock(&proflock)
return
}
// ThreadCreateProfile returns n, the number of records in the thread creation profile.
// If len(p) >= n, ThreadCreateProfile copies the profile into p and returns n, true.
// If len(p) < n, ThreadCreateProfile does not change p and returns n, false.
//
// Most clients should use the runtime/pprof package instead
// of calling ThreadCreateProfile directly.
func ThreadCreateProfile(p []StackRecord) (n int, ok bool) {
first := (*m)(atomic.Loadp(unsafe.Pointer(allm())))
for mp := first; mp != nil; mp = mp.alllink {
n++
}
if n <= len(p) {
ok = true
i := 0
for mp := first; mp != nil; mp = mp.alllink {
for j := range mp.createstack {
p[i].Stack0[j] = mp.createstack[j].pc
}
i++
}
}
return
}
// GoroutineProfile returns n, the number of records in the active goroutine stack profile.
// If len(p) >= n, GoroutineProfile copies the profile into p and returns n, true.
// If len(p) < n, GoroutineProfile does not change p and returns n, false.
//
// Most clients should use the runtime/pprof package instead
// of calling GoroutineProfile directly.
func GoroutineProfile(p []StackRecord) (n int, ok bool) {
gp := getg()
isOK := func(gp1 *g) bool {
// Checking isSystemGoroutine here makes GoroutineProfile
// consistent with both NumGoroutine and Stack.
return gp1 != gp && readgstatus(gp1) != _Gdead && !isSystemGoroutine(gp1)
}
stopTheWorld("profile")
n = 1
for _, gp1 := range allgs {
if isOK(gp1) {
n++
}
}
if n <= len(p) {
ok = true
r := p
// Save current goroutine.
saveg(gp, &r[0])
r = r[1:]
// Save other goroutines.
for _, gp1 := range allgs {
if isOK(gp1) {
if len(r) == 0 {
// Should be impossible, but better to return a
// truncated profile than to crash the entire process.
break
}
saveg(gp1, &r[0])
r = r[1:]
}
}
}
startTheWorld()
return n, ok
}
func saveg(gp *g, r *StackRecord) {
if gp == getg() {
var locbuf [32]location
n := callers(1, locbuf[:])
for i := 0; i < n; i++ {
r.Stack0[i] = locbuf[i].pc
}
if n < len(r.Stack0) {
r.Stack0[n] = 0
}
} else {
// FIXME: Not implemented.
r.Stack0[0] = 0
}
}
// Stack formats a stack trace of the calling goroutine into buf
// and returns the number of bytes written to buf.
// If all is true, Stack formats stack traces of all other goroutines
// into buf after the trace for the current goroutine.
func Stack(buf []byte, all bool) int {
if all {
stopTheWorld("stack trace")
}
n := 0
if len(buf) > 0 {
gp := getg()
// Force traceback=1 to override GOTRACEBACK setting,
// so that Stack's results are consistent.
// GOTRACEBACK is only about crash dumps.
gp.m.traceback = 1
gp.writebuf = buf[0:0:len(buf)]
goroutineheader(gp)
traceback(1)
if all {
tracebackothers(gp)
}
gp.m.traceback = 0
n = len(gp.writebuf)
gp.writebuf = nil
}
if all {
startTheWorld()
}
return n
}
// Tracing of alloc/free/gc.
var tracelock mutex
func tracealloc(p unsafe.Pointer, size uintptr, typ *_type) {
lock(&tracelock)
gp := getg()
gp.m.traceback = 2
if typ == nil {
print("tracealloc(", p, ", ", hex(size), ")\n")
} else {
print("tracealloc(", p, ", ", hex(size), ", ", *typ.string, ")\n")
}
if gp.m.curg == nil || gp == gp.m.curg {
goroutineheader(gp)
traceback(1)
} else {
goroutineheader(gp.m.curg)
// FIXME: Can't do traceback of other g.
}
print("\n")
gp.m.traceback = 0
unlock(&tracelock)
}
func tracefree(p unsafe.Pointer, size uintptr) {
lock(&tracelock)
gp := getg()
gp.m.traceback = 2
print("tracefree(", p, ", ", hex(size), ")\n")
goroutineheader(gp)
traceback(1)
print("\n")
gp.m.traceback = 0
unlock(&tracelock)
}
func tracegc() {
lock(&tracelock)
gp := getg()
gp.m.traceback = 2
print("tracegc()\n")
// running on m->g0 stack; show all non-g0 goroutines
tracebackothers(gp)
print("end tracegc\n")
print("\n")
gp.m.traceback = 0
unlock(&tracelock)
}
|