-
Notifications
You must be signed in to change notification settings - Fork 4.5k
/
lwlock.c
1969 lines (1671 loc) · 53.8 KB
/
lwlock.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
/*-------------------------------------------------------------------------
*
* lwlock.c
* Lightweight lock manager
*
* Lightweight locks are intended primarily to provide mutual exclusion of
* access to shared-memory data structures. Therefore, they offer both
* exclusive and shared lock modes (to support read/write and read-only
* access to a shared object). There are few other frammishes. User-level
* locking should be done with the full lock manager --- which depends on
* LWLocks to protect its shared state.
*
* In addition to exclusive and shared modes, lightweight locks can be used to
* wait until a variable changes value. The variable is initially not set
* when the lock is acquired with LWLockAcquire, i.e. it remains set to the
* value it was set to when the lock was released last, and can be updated
* without releasing the lock by calling LWLockUpdateVar. LWLockWaitForVar
* waits for the variable to be updated, or until the lock is free. When
* releasing the lock with LWLockReleaseClearVar() the value can be set to an
* appropriate value for a free lock. The meaning of the variable is up to
* the caller, the lightweight lock code just assigns and compares it.
*
* Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* src/backend/storage/lmgr/lwlock.c
*
* NOTES:
*
* This used to be a pretty straight forward reader-writer lock
* implementation, in which the internal state was protected by a
* spinlock. Unfortunately the overhead of taking the spinlock proved to be
* too high for workloads/locks that were taken in shared mode very
* frequently. Often we were spinning in the (obviously exclusive) spinlock,
* while trying to acquire a shared lock that was actually free.
*
* Thus a new implementation was devised that provides wait-free shared lock
* acquisition for locks that aren't exclusively locked.
*
* The basic idea is to have a single atomic variable 'lockcount' instead of
* the formerly separate shared and exclusive counters and to use atomic
* operations to acquire the lock. That's fairly easy to do for plain
* rw-spinlocks, but a lot harder for something like LWLocks that want to wait
* in the OS.
*
* For lock acquisition we use an atomic compare-and-exchange on the lockcount
* variable. For exclusive lock we swap in a sentinel value
* (LW_VAL_EXCLUSIVE), for shared locks we count the number of holders.
*
* To release the lock we use an atomic decrement to release the lock. If the
* new value is zero (we get that atomically), we know we can/have to release
* waiters.
*
* Obviously it is important that the sentinel value for exclusive locks
* doesn't conflict with the maximum number of possible share lockers -
* luckily MAX_BACKENDS makes that easily possible.
*
*
* The attentive reader might have noticed that naively doing the above has a
* glaring race condition: We try to lock using the atomic operations and
* notice that we have to wait. Unfortunately by the time we have finished
* queuing, the former locker very well might have already finished it's
* work. That's problematic because we're now stuck waiting inside the OS.
* To mitigate those races we use a two phased attempt at locking:
* Phase 1: Try to do it atomically, if we succeed, nice
* Phase 2: Add ourselves to the waitqueue of the lock
* Phase 3: Try to grab the lock again, if we succeed, remove ourselves from
* the queue
* Phase 4: Sleep till wake-up, goto Phase 1
*
* This protects us against the problem from above as nobody can release too
* quick, before we're queued, since after Phase 2 we're already queued.
* -------------------------------------------------------------------------
*/
#include "postgres.h"
#include "miscadmin.h"
#include "pg_trace.h"
#include "pgstat.h"
#include "port/pg_bitutils.h"
#include "postmaster/postmaster.h"
#include "replication/slot.h"
#include "storage/ipc.h"
#include "storage/predicate.h"
#include "storage/proc.h"
#include "storage/proclist.h"
#include "storage/spin.h"
#include "utils/memutils.h"
#ifdef LWLOCK_STATS
#include "utils/hsearch.h"
#endif
/* We use the ShmemLock spinlock to protect LWLockCounter */
extern slock_t *ShmemLock;
#define LW_FLAG_HAS_WAITERS ((uint32) 1 << 30)
#define LW_FLAG_RELEASE_OK ((uint32) 1 << 29)
#define LW_FLAG_LOCKED ((uint32) 1 << 28)
#define LW_VAL_EXCLUSIVE ((uint32) 1 << 24)
#define LW_VAL_SHARED 1
#define LW_LOCK_MASK ((uint32) ((1 << 25)-1))
/* Must be greater than MAX_BACKENDS - which is 2^23-1, so we're fine. */
#define LW_SHARED_MASK ((uint32) ((1 << 24)-1))
StaticAssertDecl(LW_VAL_EXCLUSIVE > (uint32) MAX_BACKENDS,
"MAX_BACKENDS too big for lwlock.c");
/*
* There are three sorts of LWLock "tranches":
*
* 1. The individually-named locks defined in lwlocknames.h each have their
* own tranche. The names of these tranches appear in IndividualLWLockNames[]
* in lwlocknames.c.
*
* 2. There are some predefined tranches for built-in groups of locks.
* These are listed in enum BuiltinTrancheIds in lwlock.h, and their names
* appear in BuiltinTrancheNames[] below.
*
* 3. Extensions can create new tranches, via either RequestNamedLWLockTranche
* or LWLockRegisterTranche. The names of these that are known in the current
* process appear in LWLockTrancheNames[].
*
* All these names are user-visible as wait event names, so choose with care
* ... and do not forget to update the documentation's list of wait events.
*/
extern const char *const IndividualLWLockNames[]; /* in lwlocknames.c */
static const char *const BuiltinTrancheNames[] = {
/* LWTRANCHE_XACT_BUFFER: */
"XactBuffer",
/* LWTRANCHE_COMMITTS_BUFFER: */
"CommitTSBuffer",
/* LWTRANCHE_SUBTRANS_BUFFER: */
"SubtransBuffer",
/* LWTRANCHE_MULTIXACTOFFSET_BUFFER: */
"MultiXactOffsetBuffer",
/* LWTRANCHE_MULTIXACTMEMBER_BUFFER: */
"MultiXactMemberBuffer",
/* LWTRANCHE_NOTIFY_BUFFER: */
"NotifyBuffer",
/* LWTRANCHE_SERIAL_BUFFER: */
"SerialBuffer",
/* LWTRANCHE_WAL_INSERT: */
"WALInsert",
/* LWTRANCHE_BUFFER_CONTENT: */
"BufferContent",
/* LWTRANCHE_REPLICATION_ORIGIN_STATE: */
"ReplicationOriginState",
/* LWTRANCHE_REPLICATION_SLOT_IO: */
"ReplicationSlotIO",
/* LWTRANCHE_LOCK_FASTPATH: */
"LockFastPath",
/* LWTRANCHE_BUFFER_MAPPING: */
"BufferMapping",
/* LWTRANCHE_LOCK_MANAGER: */
"LockManager",
/* LWTRANCHE_PREDICATE_LOCK_MANAGER: */
"PredicateLockManager",
/* LWTRANCHE_PARALLEL_HASH_JOIN: */
"ParallelHashJoin",
/* LWTRANCHE_PARALLEL_QUERY_DSA: */
"ParallelQueryDSA",
/* LWTRANCHE_PER_SESSION_DSA: */
"PerSessionDSA",
/* LWTRANCHE_PER_SESSION_RECORD_TYPE: */
"PerSessionRecordType",
/* LWTRANCHE_PER_SESSION_RECORD_TYPMOD: */
"PerSessionRecordTypmod",
/* LWTRANCHE_SHARED_TUPLESTORE: */
"SharedTupleStore",
/* LWTRANCHE_SHARED_TIDBITMAP: */
"SharedTidBitmap",
/* LWTRANCHE_PARALLEL_APPEND: */
"ParallelAppend",
/* LWTRANCHE_PER_XACT_PREDICATE_LIST: */
"PerXactPredicateList",
/* LWTRANCHE_PGSTATS_DSA: */
"PgStatsDSA",
/* LWTRANCHE_PGSTATS_HASH: */
"PgStatsHash",
/* LWTRANCHE_PGSTATS_DATA: */
"PgStatsData",
};
StaticAssertDecl(lengthof(BuiltinTrancheNames) ==
LWTRANCHE_FIRST_USER_DEFINED - NUM_INDIVIDUAL_LWLOCKS,
"missing entries in BuiltinTrancheNames[]");
/*
* This is indexed by tranche ID minus LWTRANCHE_FIRST_USER_DEFINED, and
* stores the names of all dynamically-created tranches known to the current
* process. Any unused entries in the array will contain NULL.
*/
static const char **LWLockTrancheNames = NULL;
static int LWLockTrancheNamesAllocated = 0;
/*
* This points to the main array of LWLocks in shared memory. Backends inherit
* the pointer by fork from the postmaster (except in the EXEC_BACKEND case,
* where we have special measures to pass it down).
*/
LWLockPadded *MainLWLockArray = NULL;
/*
* We use this structure to keep track of locked LWLocks for release
* during error recovery. Normally, only a few will be held at once, but
* occasionally the number can be much higher; for example, the pg_buffercache
* extension locks all buffer partitions simultaneously.
*/
#define MAX_SIMUL_LWLOCKS 200
/* struct representing the LWLocks we're holding */
typedef struct LWLockHandle
{
LWLock *lock;
LWLockMode mode;
} LWLockHandle;
static int num_held_lwlocks = 0;
static LWLockHandle held_lwlocks[MAX_SIMUL_LWLOCKS];
/* struct representing the LWLock tranche request for named tranche */
typedef struct NamedLWLockTrancheRequest
{
char tranche_name[NAMEDATALEN];
int num_lwlocks;
} NamedLWLockTrancheRequest;
static NamedLWLockTrancheRequest *NamedLWLockTrancheRequestArray = NULL;
static int NamedLWLockTrancheRequestsAllocated = 0;
/*
* NamedLWLockTrancheRequests is both the valid length of the request array,
* and the length of the shared-memory NamedLWLockTrancheArray later on.
* This variable and NamedLWLockTrancheArray are non-static so that
* postmaster.c can copy them to child processes in EXEC_BACKEND builds.
*/
int NamedLWLockTrancheRequests = 0;
/* points to data in shared memory: */
NamedLWLockTranche *NamedLWLockTrancheArray = NULL;
static void InitializeLWLocks(void);
static inline void LWLockReportWaitStart(LWLock *lock);
static inline void LWLockReportWaitEnd(void);
static const char *GetLWTrancheName(uint16 trancheId);
#define T_NAME(lock) \
GetLWTrancheName((lock)->tranche)
#ifdef LWLOCK_STATS
typedef struct lwlock_stats_key
{
int tranche;
void *instance;
} lwlock_stats_key;
typedef struct lwlock_stats
{
lwlock_stats_key key;
int sh_acquire_count;
int ex_acquire_count;
int block_count;
int dequeue_self_count;
int spin_delay_count;
} lwlock_stats;
static HTAB *lwlock_stats_htab;
static lwlock_stats lwlock_stats_dummy;
#endif
#ifdef LOCK_DEBUG
bool Trace_lwlocks = false;
inline static void
PRINT_LWDEBUG(const char *where, LWLock *lock, LWLockMode mode)
{
/* hide statement & context here, otherwise the log is just too verbose */
if (Trace_lwlocks)
{
uint32 state = pg_atomic_read_u32(&lock->state);
ereport(LOG,
(errhidestmt(true),
errhidecontext(true),
errmsg_internal("%d: %s(%s %p): excl %u shared %u haswaiters %u waiters %u rOK %d",
MyProcPid,
where, T_NAME(lock), lock,
(state & LW_VAL_EXCLUSIVE) != 0,
state & LW_SHARED_MASK,
(state & LW_FLAG_HAS_WAITERS) != 0,
pg_atomic_read_u32(&lock->nwaiters),
(state & LW_FLAG_RELEASE_OK) != 0)));
}
}
inline static void
LOG_LWDEBUG(const char *where, LWLock *lock, const char *msg)
{
/* hide statement & context here, otherwise the log is just too verbose */
if (Trace_lwlocks)
{
ereport(LOG,
(errhidestmt(true),
errhidecontext(true),
errmsg_internal("%s(%s %p): %s", where,
T_NAME(lock), lock, msg)));
}
}
#else /* not LOCK_DEBUG */
#define PRINT_LWDEBUG(a,b,c) ((void)0)
#define LOG_LWDEBUG(a,b,c) ((void)0)
#endif /* LOCK_DEBUG */
#ifdef LWLOCK_STATS
static void init_lwlock_stats(void);
static void print_lwlock_stats(int code, Datum arg);
static lwlock_stats * get_lwlock_stats_entry(LWLock *lock);
static void
init_lwlock_stats(void)
{
HASHCTL ctl;
static MemoryContext lwlock_stats_cxt = NULL;
static bool exit_registered = false;
if (lwlock_stats_cxt != NULL)
MemoryContextDelete(lwlock_stats_cxt);
/*
* The LWLock stats will be updated within a critical section, which
* requires allocating new hash entries. Allocations within a critical
* section are normally not allowed because running out of memory would
* lead to a PANIC, but LWLOCK_STATS is debugging code that's not normally
* turned on in production, so that's an acceptable risk. The hash entries
* are small, so the risk of running out of memory is minimal in practice.
*/
lwlock_stats_cxt = AllocSetContextCreate(TopMemoryContext,
"LWLock stats",
ALLOCSET_DEFAULT_SIZES);
MemoryContextAllowInCriticalSection(lwlock_stats_cxt, true);
ctl.keysize = sizeof(lwlock_stats_key);
ctl.entrysize = sizeof(lwlock_stats);
ctl.hcxt = lwlock_stats_cxt;
lwlock_stats_htab = hash_create("lwlock stats", 16384, &ctl,
HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);
if (!exit_registered)
{
on_shmem_exit(print_lwlock_stats, 0);
exit_registered = true;
}
}
static void
print_lwlock_stats(int code, Datum arg)
{
HASH_SEQ_STATUS scan;
lwlock_stats *lwstats;
hash_seq_init(&scan, lwlock_stats_htab);
/* Grab an LWLock to keep different backends from mixing reports */
LWLockAcquire(&MainLWLockArray[0].lock, LW_EXCLUSIVE);
while ((lwstats = (lwlock_stats *) hash_seq_search(&scan)) != NULL)
{
fprintf(stderr,
"PID %d lwlock %s %p: shacq %u exacq %u blk %u spindelay %u dequeue self %u\n",
MyProcPid, GetLWTrancheName(lwstats->key.tranche),
lwstats->key.instance, lwstats->sh_acquire_count,
lwstats->ex_acquire_count, lwstats->block_count,
lwstats->spin_delay_count, lwstats->dequeue_self_count);
}
LWLockRelease(&MainLWLockArray[0].lock);
}
static lwlock_stats *
get_lwlock_stats_entry(LWLock *lock)
{
lwlock_stats_key key;
lwlock_stats *lwstats;
bool found;
/*
* During shared memory initialization, the hash table doesn't exist yet.
* Stats of that phase aren't very interesting, so just collect operations
* on all locks in a single dummy entry.
*/
if (lwlock_stats_htab == NULL)
return &lwlock_stats_dummy;
/* Fetch or create the entry. */
MemSet(&key, 0, sizeof(key));
key.tranche = lock->tranche;
key.instance = lock;
lwstats = hash_search(lwlock_stats_htab, &key, HASH_ENTER, &found);
if (!found)
{
lwstats->sh_acquire_count = 0;
lwstats->ex_acquire_count = 0;
lwstats->block_count = 0;
lwstats->dequeue_self_count = 0;
lwstats->spin_delay_count = 0;
}
return lwstats;
}
#endif /* LWLOCK_STATS */
/*
* Compute number of LWLocks required by named tranches. These will be
* allocated in the main array.
*/
static int
NumLWLocksForNamedTranches(void)
{
int numLocks = 0;
int i;
for (i = 0; i < NamedLWLockTrancheRequests; i++)
numLocks += NamedLWLockTrancheRequestArray[i].num_lwlocks;
return numLocks;
}
/*
* Compute shmem space needed for LWLocks and named tranches.
*/
Size
LWLockShmemSize(void)
{
Size size;
int i;
int numLocks = NUM_FIXED_LWLOCKS;
/* Calculate total number of locks needed in the main array. */
numLocks += NumLWLocksForNamedTranches();
/* Space for the LWLock array. */
size = mul_size(numLocks, sizeof(LWLockPadded));
/* Space for dynamic allocation counter, plus room for alignment. */
size = add_size(size, sizeof(int) + LWLOCK_PADDED_SIZE);
/* space for named tranches. */
size = add_size(size, mul_size(NamedLWLockTrancheRequests, sizeof(NamedLWLockTranche)));
/* space for name of each tranche. */
for (i = 0; i < NamedLWLockTrancheRequests; i++)
size = add_size(size, strlen(NamedLWLockTrancheRequestArray[i].tranche_name) + 1);
return size;
}
/*
* Allocate shmem space for the main LWLock array and all tranches and
* initialize it. We also register extension LWLock tranches here.
*/
void
CreateLWLocks(void)
{
if (!IsUnderPostmaster)
{
Size spaceLocks = LWLockShmemSize();
int *LWLockCounter;
char *ptr;
/* Allocate space */
ptr = (char *) ShmemAlloc(spaceLocks);
/* Leave room for dynamic allocation of tranches */
ptr += sizeof(int);
/* Ensure desired alignment of LWLock array */
ptr += LWLOCK_PADDED_SIZE - ((uintptr_t) ptr) % LWLOCK_PADDED_SIZE;
MainLWLockArray = (LWLockPadded *) ptr;
/*
* Initialize the dynamic-allocation counter for tranches, which is
* stored just before the first LWLock.
*/
LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
*LWLockCounter = LWTRANCHE_FIRST_USER_DEFINED;
/* Initialize all LWLocks */
InitializeLWLocks();
}
/* Register named extension LWLock tranches in the current process. */
for (int i = 0; i < NamedLWLockTrancheRequests; i++)
LWLockRegisterTranche(NamedLWLockTrancheArray[i].trancheId,
NamedLWLockTrancheArray[i].trancheName);
}
/*
* Initialize LWLocks that are fixed and those belonging to named tranches.
*/
static void
InitializeLWLocks(void)
{
int numNamedLocks = NumLWLocksForNamedTranches();
int id;
int i;
int j;
LWLockPadded *lock;
/* Initialize all individual LWLocks in main array */
for (id = 0, lock = MainLWLockArray; id < NUM_INDIVIDUAL_LWLOCKS; id++, lock++)
LWLockInitialize(&lock->lock, id);
/* Initialize buffer mapping LWLocks in main array */
lock = MainLWLockArray + BUFFER_MAPPING_LWLOCK_OFFSET;
for (id = 0; id < NUM_BUFFER_PARTITIONS; id++, lock++)
LWLockInitialize(&lock->lock, LWTRANCHE_BUFFER_MAPPING);
/* Initialize lmgrs' LWLocks in main array */
lock = MainLWLockArray + LOCK_MANAGER_LWLOCK_OFFSET;
for (id = 0; id < NUM_LOCK_PARTITIONS; id++, lock++)
LWLockInitialize(&lock->lock, LWTRANCHE_LOCK_MANAGER);
/* Initialize predicate lmgrs' LWLocks in main array */
lock = MainLWLockArray + PREDICATELOCK_MANAGER_LWLOCK_OFFSET;
for (id = 0; id < NUM_PREDICATELOCK_PARTITIONS; id++, lock++)
LWLockInitialize(&lock->lock, LWTRANCHE_PREDICATE_LOCK_MANAGER);
/*
* Copy the info about any named tranches into shared memory (so that
* other processes can see it), and initialize the requested LWLocks.
*/
if (NamedLWLockTrancheRequests > 0)
{
char *trancheNames;
NamedLWLockTrancheArray = (NamedLWLockTranche *)
&MainLWLockArray[NUM_FIXED_LWLOCKS + numNamedLocks];
trancheNames = (char *) NamedLWLockTrancheArray +
(NamedLWLockTrancheRequests * sizeof(NamedLWLockTranche));
lock = &MainLWLockArray[NUM_FIXED_LWLOCKS];
for (i = 0; i < NamedLWLockTrancheRequests; i++)
{
NamedLWLockTrancheRequest *request;
NamedLWLockTranche *tranche;
char *name;
request = &NamedLWLockTrancheRequestArray[i];
tranche = &NamedLWLockTrancheArray[i];
name = trancheNames;
trancheNames += strlen(request->tranche_name) + 1;
strcpy(name, request->tranche_name);
tranche->trancheId = LWLockNewTrancheId();
tranche->trancheName = name;
for (j = 0; j < request->num_lwlocks; j++, lock++)
LWLockInitialize(&lock->lock, tranche->trancheId);
}
}
}
/*
* InitLWLockAccess - initialize backend-local state needed to hold LWLocks
*/
void
InitLWLockAccess(void)
{
#ifdef LWLOCK_STATS
init_lwlock_stats();
#endif
}
/*
* GetNamedLWLockTranche - returns the base address of LWLock from the
* specified tranche.
*
* Caller needs to retrieve the requested number of LWLocks starting from
* the base lock address returned by this API. This can be used for
* tranches that are requested by using RequestNamedLWLockTranche() API.
*/
LWLockPadded *
GetNamedLWLockTranche(const char *tranche_name)
{
int lock_pos;
int i;
/*
* Obtain the position of base address of LWLock belonging to requested
* tranche_name in MainLWLockArray. LWLocks for named tranches are placed
* in MainLWLockArray after fixed locks.
*/
lock_pos = NUM_FIXED_LWLOCKS;
for (i = 0; i < NamedLWLockTrancheRequests; i++)
{
if (strcmp(NamedLWLockTrancheRequestArray[i].tranche_name,
tranche_name) == 0)
return &MainLWLockArray[lock_pos];
lock_pos += NamedLWLockTrancheRequestArray[i].num_lwlocks;
}
elog(ERROR, "requested tranche is not registered");
/* just to keep compiler quiet */
return NULL;
}
/*
* Allocate a new tranche ID.
*/
int
LWLockNewTrancheId(void)
{
int result;
int *LWLockCounter;
LWLockCounter = (int *) ((char *) MainLWLockArray - sizeof(int));
SpinLockAcquire(ShmemLock);
result = (*LWLockCounter)++;
SpinLockRelease(ShmemLock);
return result;
}
/*
* Register a dynamic tranche name in the lookup table of the current process.
*
* This routine will save a pointer to the tranche name passed as an argument,
* so the name should be allocated in a backend-lifetime context
* (shared memory, TopMemoryContext, static constant, or similar).
*
* The tranche name will be user-visible as a wait event name, so try to
* use a name that fits the style for those.
*/
void
LWLockRegisterTranche(int tranche_id, const char *tranche_name)
{
/* This should only be called for user-defined tranches. */
if (tranche_id < LWTRANCHE_FIRST_USER_DEFINED)
return;
/* Convert to array index. */
tranche_id -= LWTRANCHE_FIRST_USER_DEFINED;
/* If necessary, create or enlarge array. */
if (tranche_id >= LWLockTrancheNamesAllocated)
{
int newalloc;
newalloc = pg_nextpower2_32(Max(8, tranche_id + 1));
if (LWLockTrancheNames == NULL)
LWLockTrancheNames = (const char **)
MemoryContextAllocZero(TopMemoryContext,
newalloc * sizeof(char *));
else
LWLockTrancheNames =
repalloc0_array(LWLockTrancheNames, const char *, LWLockTrancheNamesAllocated, newalloc);
LWLockTrancheNamesAllocated = newalloc;
}
LWLockTrancheNames[tranche_id] = tranche_name;
}
/*
* RequestNamedLWLockTranche
* Request that extra LWLocks be allocated during postmaster
* startup.
*
* This may only be called via the shmem_request_hook of a library that is
* loaded into the postmaster via shared_preload_libraries. Calls from
* elsewhere will fail.
*
* The tranche name will be user-visible as a wait event name, so try to
* use a name that fits the style for those.
*/
void
RequestNamedLWLockTranche(const char *tranche_name, int num_lwlocks)
{
NamedLWLockTrancheRequest *request;
if (!process_shmem_requests_in_progress)
elog(FATAL, "cannot request additional LWLocks outside shmem_request_hook");
if (NamedLWLockTrancheRequestArray == NULL)
{
NamedLWLockTrancheRequestsAllocated = 16;
NamedLWLockTrancheRequestArray = (NamedLWLockTrancheRequest *)
MemoryContextAlloc(TopMemoryContext,
NamedLWLockTrancheRequestsAllocated
* sizeof(NamedLWLockTrancheRequest));
}
if (NamedLWLockTrancheRequests >= NamedLWLockTrancheRequestsAllocated)
{
int i = pg_nextpower2_32(NamedLWLockTrancheRequests + 1);
NamedLWLockTrancheRequestArray = (NamedLWLockTrancheRequest *)
repalloc(NamedLWLockTrancheRequestArray,
i * sizeof(NamedLWLockTrancheRequest));
NamedLWLockTrancheRequestsAllocated = i;
}
request = &NamedLWLockTrancheRequestArray[NamedLWLockTrancheRequests];
Assert(strlen(tranche_name) + 1 <= NAMEDATALEN);
strlcpy(request->tranche_name, tranche_name, NAMEDATALEN);
request->num_lwlocks = num_lwlocks;
NamedLWLockTrancheRequests++;
}
/*
* LWLockInitialize - initialize a new lwlock; it's initially unlocked
*/
void
LWLockInitialize(LWLock *lock, int tranche_id)
{
pg_atomic_init_u32(&lock->state, LW_FLAG_RELEASE_OK);
#ifdef LOCK_DEBUG
pg_atomic_init_u32(&lock->nwaiters, 0);
#endif
lock->tranche = tranche_id;
proclist_init(&lock->waiters);
}
/*
* Report start of wait event for light-weight locks.
*
* This function will be used by all the light-weight lock calls which
* needs to wait to acquire the lock. This function distinguishes wait
* event based on tranche and lock id.
*/
static inline void
LWLockReportWaitStart(LWLock *lock)
{
pgstat_report_wait_start(PG_WAIT_LWLOCK | lock->tranche);
}
/*
* Report end of wait event for light-weight locks.
*/
static inline void
LWLockReportWaitEnd(void)
{
pgstat_report_wait_end();
}
/*
* Return the name of an LWLock tranche.
*/
static const char *
GetLWTrancheName(uint16 trancheId)
{
/* Individual LWLock? */
if (trancheId < NUM_INDIVIDUAL_LWLOCKS)
return IndividualLWLockNames[trancheId];
/* Built-in tranche? */
if (trancheId < LWTRANCHE_FIRST_USER_DEFINED)
return BuiltinTrancheNames[trancheId - NUM_INDIVIDUAL_LWLOCKS];
/*
* It's an extension tranche, so look in LWLockTrancheNames[]. However,
* it's possible that the tranche has never been registered in the current
* process, in which case give up and return "extension".
*/
trancheId -= LWTRANCHE_FIRST_USER_DEFINED;
if (trancheId >= LWLockTrancheNamesAllocated ||
LWLockTrancheNames[trancheId] == NULL)
return "extension";
return LWLockTrancheNames[trancheId];
}
/*
* Return an identifier for an LWLock based on the wait class and event.
*/
const char *
GetLWLockIdentifier(uint32 classId, uint16 eventId)
{
Assert(classId == PG_WAIT_LWLOCK);
/* The event IDs are just tranche numbers. */
return GetLWTrancheName(eventId);
}
/*
* Internal function that tries to atomically acquire the lwlock in the passed
* in mode.
*
* This function will not block waiting for a lock to become free - that's the
* callers job.
*
* Returns true if the lock isn't free and we need to wait.
*/
static bool
LWLockAttemptLock(LWLock *lock, LWLockMode mode)
{
uint32 old_state;
Assert(mode == LW_EXCLUSIVE || mode == LW_SHARED);
/*
* Read once outside the loop, later iterations will get the newer value
* via compare & exchange.
*/
old_state = pg_atomic_read_u32(&lock->state);
/* loop until we've determined whether we could acquire the lock or not */
while (true)
{
uint32 desired_state;
bool lock_free;
desired_state = old_state;
if (mode == LW_EXCLUSIVE)
{
lock_free = (old_state & LW_LOCK_MASK) == 0;
if (lock_free)
desired_state += LW_VAL_EXCLUSIVE;
}
else
{
lock_free = (old_state & LW_VAL_EXCLUSIVE) == 0;
if (lock_free)
desired_state += LW_VAL_SHARED;
}
/*
* Attempt to swap in the state we are expecting. If we didn't see
* lock to be free, that's just the old value. If we saw it as free,
* we'll attempt to mark it acquired. The reason that we always swap
* in the value is that this doubles as a memory barrier. We could try
* to be smarter and only swap in values if we saw the lock as free,
* but benchmark haven't shown it as beneficial so far.
*
* Retry if the value changed since we last looked at it.
*/
if (pg_atomic_compare_exchange_u32(&lock->state,
&old_state, desired_state))
{
if (lock_free)
{
/* Great! Got the lock. */
#ifdef LOCK_DEBUG
if (mode == LW_EXCLUSIVE)
lock->owner = MyProc;
#endif
return false;
}
else
return true; /* somebody else has the lock */
}
}
pg_unreachable();
}
/*
* Lock the LWLock's wait list against concurrent activity.
*
* NB: even though the wait list is locked, non-conflicting lock operations
* may still happen concurrently.
*
* Time spent holding mutex should be short!
*/
static void
LWLockWaitListLock(LWLock *lock)
{
uint32 old_state;
#ifdef LWLOCK_STATS
lwlock_stats *lwstats;
uint32 delays = 0;
lwstats = get_lwlock_stats_entry(lock);
#endif
while (true)
{
/* always try once to acquire lock directly */
old_state = pg_atomic_fetch_or_u32(&lock->state, LW_FLAG_LOCKED);
if (!(old_state & LW_FLAG_LOCKED))
break; /* got lock */
/* and then spin without atomic operations until lock is released */
{
SpinDelayStatus delayStatus;
init_local_spin_delay(&delayStatus);
while (old_state & LW_FLAG_LOCKED)
{
perform_spin_delay(&delayStatus);
old_state = pg_atomic_read_u32(&lock->state);
}
#ifdef LWLOCK_STATS
delays += delayStatus.delays;
#endif
finish_spin_delay(&delayStatus);
}
/*
* Retry. The lock might obviously already be re-acquired by the time
* we're attempting to get it again.
*/
}
#ifdef LWLOCK_STATS
lwstats->spin_delay_count += delays;
#endif
}
/*
* Unlock the LWLock's wait list.
*
* Note that it can be more efficient to manipulate flags and release the
* locks in a single atomic operation.
*/
static void
LWLockWaitListUnlock(LWLock *lock)
{
uint32 old_state PG_USED_FOR_ASSERTS_ONLY;
old_state = pg_atomic_fetch_and_u32(&lock->state, ~LW_FLAG_LOCKED);
Assert(old_state & LW_FLAG_LOCKED);
}
/*
* Wakeup all the lockers that currently have a chance to acquire the lock.
*/
static void
LWLockWakeup(LWLock *lock)
{
bool new_release_ok;
bool wokeup_somebody = false;
proclist_head wakeup;
proclist_mutable_iter iter;
proclist_init(&wakeup);
new_release_ok = true;
/* lock wait list while collecting backends to wake up */
LWLockWaitListLock(lock);
proclist_foreach_modify(iter, &lock->waiters, lwWaitLink)
{
PGPROC *waiter = GetPGProcByNumber(iter.cur);
if (wokeup_somebody && waiter->lwWaitMode == LW_EXCLUSIVE)
continue;
proclist_delete(&lock->waiters, iter.cur, lwWaitLink);
proclist_push_tail(&wakeup, iter.cur, lwWaitLink);
if (waiter->lwWaitMode != LW_WAIT_UNTIL_FREE)
{
/*
* Prevent additional wakeups until retryer gets to run. Backends
* that are just waiting for the lock to become free don't retry
* automatically.
*/
new_release_ok = false;
/*
* Don't wakeup (further) exclusive locks.
*/
wokeup_somebody = true;
}
/*
* Signal that the process isn't on the wait list anymore. This allows
* LWLockDequeueSelf() to remove itself of the waitlist with a
* proclist_delete(), rather than having to check if it has been
* removed from the list.
*/
Assert(waiter->lwWaiting == LW_WS_WAITING);
waiter->lwWaiting = LW_WS_PENDING_WAKEUP;
/*
* Once we've woken up an exclusive lock, there's no point in waking
* up anybody else.
*/
if (waiter->lwWaitMode == LW_EXCLUSIVE)
break;
}
Assert(proclist_is_empty(&wakeup) || pg_atomic_read_u32(&lock->state) & LW_FLAG_HAS_WAITERS);