Line data Source code
1 : /*-------------------------------------------------------------------------
2 : *
3 : * predicate.c
4 : * POSTGRES predicate locking
5 : * to support full serializable transaction isolation
6 : *
7 : *
8 : * The approach taken is to implement Serializable Snapshot Isolation (SSI)
9 : * as initially described in this paper:
10 : *
11 : * Michael J. Cahill, Uwe Röhm, and Alan D. Fekete. 2008.
12 : * Serializable isolation for snapshot databases.
13 : * In SIGMOD '08: Proceedings of the 2008 ACM SIGMOD
14 : * international conference on Management of data,
15 : * pages 729-738, New York, NY, USA. ACM.
16 : * http://doi.acm.org/10.1145/1376616.1376690
17 : *
18 : * and further elaborated in Cahill's doctoral thesis:
19 : *
20 : * Michael James Cahill. 2009.
21 : * Serializable Isolation for Snapshot Databases.
22 : * Sydney Digital Theses.
23 : * University of Sydney, School of Information Technologies.
24 : * http://hdl.handle.net/2123/5353
25 : *
26 : *
27 : * Predicate locks for Serializable Snapshot Isolation (SSI) are SIREAD
28 : * locks, which are so different from normal locks that a distinct set of
29 : * structures is required to handle them. They are needed to detect
30 : * rw-conflicts when the read happens before the write. (When the write
31 : * occurs first, the reading transaction can check for a conflict by
32 : * examining the MVCC data.)
33 : *
34 : * (1) Besides tuples actually read, they must cover ranges of tuples
35 : * which would have been read based on the predicate. This will
36 : * require modelling the predicates through locks against database
37 : * objects such as pages, index ranges, or entire tables.
38 : *
39 : * (2) They must be kept in RAM for quick access. Because of this, it
40 : * isn't possible to always maintain tuple-level granularity -- when
41 : * the space allocated to store these approaches exhaustion, a
42 : * request for a lock may need to scan for situations where a single
43 : * transaction holds many fine-grained locks which can be coalesced
44 : * into a single coarser-grained lock.
45 : *
46 : * (3) They never block anything; they are more like flags than locks
47 : * in that regard; although they refer to database objects and are
48 : * used to identify rw-conflicts with normal write locks.
49 : *
50 : * (4) While they are associated with a transaction, they must survive
51 : * a successful COMMIT of that transaction, and remain until all
52 : * overlapping transactions complete. This even means that they
53 : * must survive termination of the transaction's process. If a
54 : * top level transaction is rolled back, however, it is immediately
55 : * flagged so that it can be ignored, and its SIREAD locks can be
56 : * released any time after that.
57 : *
58 : * (5) The only transactions which create SIREAD locks or check for
59 : * conflicts with them are serializable transactions.
60 : *
61 : * (6) When a write lock for a top level transaction is found to cover
62 : * an existing SIREAD lock for the same transaction, the SIREAD lock
63 : * can be deleted.
64 : *
65 : * (7) A write from a serializable transaction must ensure that an xact
66 : * record exists for the transaction, with the same lifespan (until
67 : * all concurrent transaction complete or the transaction is rolled
68 : * back) so that rw-dependencies to that transaction can be
69 : * detected.
70 : *
71 : * We use an optimization for read-only transactions. Under certain
72 : * circumstances, a read-only transaction's snapshot can be shown to
73 : * never have conflicts with other transactions. This is referred to
74 : * as a "safe" snapshot (and one known not to be is "unsafe").
75 : * However, it can't be determined whether a snapshot is safe until
76 : * all concurrent read/write transactions complete.
77 : *
78 : * Once a read-only transaction is known to have a safe snapshot, it
79 : * can release its predicate locks and exempt itself from further
80 : * predicate lock tracking. READ ONLY DEFERRABLE transactions run only
81 : * on safe snapshots, waiting as necessary for one to be available.
82 : *
83 : *
84 : * Lightweight locks to manage access to the predicate locking shared
85 : * memory objects must be taken in this order, and should be released in
86 : * reverse order:
87 : *
88 : * SerializableFinishedListLock
89 : * - Protects the list of transactions which have completed but which
90 : * may yet matter because they overlap still-active transactions.
91 : *
92 : * SerializablePredicateListLock
93 : * - Protects the linked list of locks held by a transaction. Note
94 : * that the locks themselves are also covered by the partition
95 : * locks of their respective lock targets; this lock only affects
96 : * the linked list connecting the locks related to a transaction.
97 : * - All transactions share this single lock (with no partitioning).
98 : * - There is never a need for a process other than the one running
99 : * an active transaction to walk the list of locks held by that
100 : * transaction, except parallel query workers sharing the leader's
101 : * transaction. In the parallel case, an extra per-sxact lock is
102 : * taken; see below.
103 : * - It is relatively infrequent that another process needs to
104 : * modify the list for a transaction, but it does happen for such
105 : * things as index page splits for pages with predicate locks and
106 : * freeing of predicate locked pages by a vacuum process. When
107 : * removing a lock in such cases, the lock itself contains the
108 : * pointers needed to remove it from the list. When adding a
109 : * lock in such cases, the lock can be added using the anchor in
110 : * the transaction structure. Neither requires walking the list.
111 : * - Cleaning up the list for a terminated transaction is sometimes
112 : * not done on a retail basis, in which case no lock is required.
113 : * - Due to the above, a process accessing its active transaction's
114 : * list always uses a shared lock, regardless of whether it is
115 : * walking or maintaining the list. This improves concurrency
116 : * for the common access patterns.
117 : * - A process which needs to alter the list of a transaction other
118 : * than its own active transaction must acquire an exclusive
119 : * lock.
120 : *
121 : * SERIALIZABLEXACT's member 'perXactPredicateListLock'
122 : * - Protects the linked list of predicate locks held by a transaction.
123 : * Only needed for parallel mode, where multiple backends share the
124 : * same SERIALIZABLEXACT object. Not needed if
125 : * SerializablePredicateListLock is held exclusively.
126 : *
127 : * PredicateLockHashPartitionLock(hashcode)
128 : * - The same lock protects a target, all locks on that target, and
129 : * the linked list of locks on the target.
130 : * - When more than one is needed, acquire in ascending address order.
131 : * - When all are needed (rare), acquire in ascending index order with
132 : * PredicateLockHashPartitionLockByIndex(index).
133 : *
134 : * SerializableXactHashLock
135 : * - Protects both PredXact and SerializableXidHash.
136 : *
137 : * SerialControlLock
138 : * - Protects SerialControlData members
139 : *
140 : * SLRU per-bank locks
141 : * - Protects SerialSlruCtl
142 : *
143 : * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
144 : * Portions Copyright (c) 1994, Regents of the University of California
145 : *
146 : *
147 : * IDENTIFICATION
148 : * src/backend/storage/lmgr/predicate.c
149 : *
150 : *-------------------------------------------------------------------------
151 : */
152 : /*
153 : * INTERFACE ROUTINES
154 : *
155 : * housekeeping for setting up shared memory predicate lock structures
156 : * PredicateLockShmemInit(void)
157 : * PredicateLockShmemSize(void)
158 : *
159 : * predicate lock reporting
160 : * GetPredicateLockStatusData(void)
161 : * PageIsPredicateLocked(Relation relation, BlockNumber blkno)
162 : *
163 : * predicate lock maintenance
164 : * GetSerializableTransactionSnapshot(Snapshot snapshot)
165 : * SetSerializableTransactionSnapshot(Snapshot snapshot,
166 : * VirtualTransactionId *sourcevxid)
167 : * RegisterPredicateLockingXid(void)
168 : * PredicateLockRelation(Relation relation, Snapshot snapshot)
169 : * PredicateLockPage(Relation relation, BlockNumber blkno,
170 : * Snapshot snapshot)
171 : * PredicateLockTID(Relation relation, ItemPointer tid, Snapshot snapshot,
172 : * TransactionId tuple_xid)
173 : * PredicateLockPageSplit(Relation relation, BlockNumber oldblkno,
174 : * BlockNumber newblkno)
175 : * PredicateLockPageCombine(Relation relation, BlockNumber oldblkno,
176 : * BlockNumber newblkno)
177 : * TransferPredicateLocksToHeapRelation(Relation relation)
178 : * ReleasePredicateLocks(bool isCommit, bool isReadOnlySafe)
179 : *
180 : * conflict detection (may also trigger rollback)
181 : * CheckForSerializableConflictOut(Relation relation, TransactionId xid,
182 : * Snapshot snapshot)
183 : * CheckForSerializableConflictIn(Relation relation, ItemPointer tid,
184 : * BlockNumber blkno)
185 : * CheckTableForSerializableConflictIn(Relation relation)
186 : *
187 : * final rollback checking
188 : * PreCommit_CheckForSerializationFailure(void)
189 : *
190 : * two-phase commit support
191 : * AtPrepare_PredicateLocks(void);
192 : * PostPrepare_PredicateLocks(TransactionId xid);
193 : * PredicateLockTwoPhaseFinish(TransactionId xid, bool isCommit);
194 : * predicatelock_twophase_recover(TransactionId xid, uint16 info,
195 : * void *recdata, uint32 len);
196 : */
197 :
198 : #include "postgres.h"
199 :
200 : #include "access/parallel.h"
201 : #include "access/slru.h"
202 : #include "access/transam.h"
203 : #include "access/twophase.h"
204 : #include "access/twophase_rmgr.h"
205 : #include "access/xact.h"
206 : #include "access/xlog.h"
207 : #include "miscadmin.h"
208 : #include "pgstat.h"
209 : #include "port/pg_lfind.h"
210 : #include "storage/predicate.h"
211 : #include "storage/predicate_internals.h"
212 : #include "storage/proc.h"
213 : #include "storage/procarray.h"
214 : #include "utils/guc_hooks.h"
215 : #include "utils/rel.h"
216 : #include "utils/snapmgr.h"
217 :
218 : /* Uncomment the next line to test the graceful degradation code. */
219 : /* #define TEST_SUMMARIZE_SERIAL */
220 :
221 : /*
222 : * Test the most selective fields first, for performance.
223 : *
224 : * a is covered by b if all of the following hold:
225 : * 1) a.database = b.database
226 : * 2) a.relation = b.relation
227 : * 3) b.offset is invalid (b is page-granularity or higher)
228 : * 4) either of the following:
229 : * 4a) a.offset is valid (a is tuple-granularity) and a.page = b.page
230 : * or 4b) a.offset is invalid and b.page is invalid (a is
231 : * page-granularity and b is relation-granularity
232 : */
233 : #define TargetTagIsCoveredBy(covered_target, covering_target) \
234 : ((GET_PREDICATELOCKTARGETTAG_RELATION(covered_target) == /* (2) */ \
235 : GET_PREDICATELOCKTARGETTAG_RELATION(covering_target)) \
236 : && (GET_PREDICATELOCKTARGETTAG_OFFSET(covering_target) == \
237 : InvalidOffsetNumber) /* (3) */ \
238 : && (((GET_PREDICATELOCKTARGETTAG_OFFSET(covered_target) != \
239 : InvalidOffsetNumber) /* (4a) */ \
240 : && (GET_PREDICATELOCKTARGETTAG_PAGE(covering_target) == \
241 : GET_PREDICATELOCKTARGETTAG_PAGE(covered_target))) \
242 : || ((GET_PREDICATELOCKTARGETTAG_PAGE(covering_target) == \
243 : InvalidBlockNumber) /* (4b) */ \
244 : && (GET_PREDICATELOCKTARGETTAG_PAGE(covered_target) \
245 : != InvalidBlockNumber))) \
246 : && (GET_PREDICATELOCKTARGETTAG_DB(covered_target) == /* (1) */ \
247 : GET_PREDICATELOCKTARGETTAG_DB(covering_target)))
248 :
249 : /*
250 : * The predicate locking target and lock shared hash tables are partitioned to
251 : * reduce contention. To determine which partition a given target belongs to,
252 : * compute the tag's hash code with PredicateLockTargetTagHashCode(), then
253 : * apply one of these macros.
254 : * NB: NUM_PREDICATELOCK_PARTITIONS must be a power of 2!
255 : */
256 : #define PredicateLockHashPartition(hashcode) \
257 : ((hashcode) % NUM_PREDICATELOCK_PARTITIONS)
258 : #define PredicateLockHashPartitionLock(hashcode) \
259 : (&MainLWLockArray[PREDICATELOCK_MANAGER_LWLOCK_OFFSET + \
260 : PredicateLockHashPartition(hashcode)].lock)
261 : #define PredicateLockHashPartitionLockByIndex(i) \
262 : (&MainLWLockArray[PREDICATELOCK_MANAGER_LWLOCK_OFFSET + (i)].lock)
263 :
264 : #define NPREDICATELOCKTARGETENTS() \
265 : mul_size(max_predicate_locks_per_xact, add_size(MaxBackends, max_prepared_xacts))
266 :
267 : #define SxactIsOnFinishedList(sxact) (!dlist_node_is_detached(&(sxact)->finishedLink))
268 :
269 : /*
270 : * Note that a sxact is marked "prepared" once it has passed
271 : * PreCommit_CheckForSerializationFailure, even if it isn't using
272 : * 2PC. This is the point at which it can no longer be aborted.
273 : *
274 : * The PREPARED flag remains set after commit, so SxactIsCommitted
275 : * implies SxactIsPrepared.
276 : */
277 : #define SxactIsCommitted(sxact) (((sxact)->flags & SXACT_FLAG_COMMITTED) != 0)
278 : #define SxactIsPrepared(sxact) (((sxact)->flags & SXACT_FLAG_PREPARED) != 0)
279 : #define SxactIsRolledBack(sxact) (((sxact)->flags & SXACT_FLAG_ROLLED_BACK) != 0)
280 : #define SxactIsDoomed(sxact) (((sxact)->flags & SXACT_FLAG_DOOMED) != 0)
281 : #define SxactIsReadOnly(sxact) (((sxact)->flags & SXACT_FLAG_READ_ONLY) != 0)
282 : #define SxactHasSummaryConflictIn(sxact) (((sxact)->flags & SXACT_FLAG_SUMMARY_CONFLICT_IN) != 0)
283 : #define SxactHasSummaryConflictOut(sxact) (((sxact)->flags & SXACT_FLAG_SUMMARY_CONFLICT_OUT) != 0)
284 : /*
285 : * The following macro actually means that the specified transaction has a
286 : * conflict out *to a transaction which committed ahead of it*. It's hard
287 : * to get that into a name of a reasonable length.
288 : */
289 : #define SxactHasConflictOut(sxact) (((sxact)->flags & SXACT_FLAG_CONFLICT_OUT) != 0)
290 : #define SxactIsDeferrableWaiting(sxact) (((sxact)->flags & SXACT_FLAG_DEFERRABLE_WAITING) != 0)
291 : #define SxactIsROSafe(sxact) (((sxact)->flags & SXACT_FLAG_RO_SAFE) != 0)
292 : #define SxactIsROUnsafe(sxact) (((sxact)->flags & SXACT_FLAG_RO_UNSAFE) != 0)
293 : #define SxactIsPartiallyReleased(sxact) (((sxact)->flags & SXACT_FLAG_PARTIALLY_RELEASED) != 0)
294 :
295 : /*
296 : * Compute the hash code associated with a PREDICATELOCKTARGETTAG.
297 : *
298 : * To avoid unnecessary recomputations of the hash code, we try to do this
299 : * just once per function, and then pass it around as needed. Aside from
300 : * passing the hashcode to hash_search_with_hash_value(), we can extract
301 : * the lock partition number from the hashcode.
302 : */
303 : #define PredicateLockTargetTagHashCode(predicatelocktargettag) \
304 : get_hash_value(PredicateLockTargetHash, predicatelocktargettag)
305 :
306 : /*
307 : * Given a predicate lock tag, and the hash for its target,
308 : * compute the lock hash.
309 : *
310 : * To make the hash code also depend on the transaction, we xor the sxid
311 : * struct's address into the hash code, left-shifted so that the
312 : * partition-number bits don't change. Since this is only a hash, we
313 : * don't care if we lose high-order bits of the address; use an
314 : * intermediate variable to suppress cast-pointer-to-int warnings.
315 : */
316 : #define PredicateLockHashCodeFromTargetHashCode(predicatelocktag, targethash) \
317 : ((targethash) ^ ((uint32) PointerGetDatum((predicatelocktag)->myXact)) \
318 : << LOG2_NUM_PREDICATELOCK_PARTITIONS)
319 :
320 :
321 : /*
322 : * The SLRU buffer area through which we access the old xids.
323 : */
324 : static SlruCtlData SerialSlruCtlData;
325 :
326 : #define SerialSlruCtl (&SerialSlruCtlData)
327 :
328 : #define SERIAL_PAGESIZE BLCKSZ
329 : #define SERIAL_ENTRYSIZE sizeof(SerCommitSeqNo)
330 : #define SERIAL_ENTRIESPERPAGE (SERIAL_PAGESIZE / SERIAL_ENTRYSIZE)
331 :
332 : /*
333 : * Set maximum pages based on the number needed to track all transactions.
334 : */
335 : #define SERIAL_MAX_PAGE (MaxTransactionId / SERIAL_ENTRIESPERPAGE)
336 :
337 : #define SerialNextPage(page) (((page) >= SERIAL_MAX_PAGE) ? 0 : (page) + 1)
338 :
339 : #define SerialValue(slotno, xid) (*((SerCommitSeqNo *) \
340 : (SerialSlruCtl->shared->page_buffer[slotno] + \
341 : ((((uint32) (xid)) % SERIAL_ENTRIESPERPAGE) * SERIAL_ENTRYSIZE))))
342 :
343 : #define SerialPage(xid) (((uint32) (xid)) / SERIAL_ENTRIESPERPAGE)
344 :
345 : typedef struct SerialControlData
346 : {
347 : int64 headPage; /* newest initialized page */
348 : TransactionId headXid; /* newest valid Xid in the SLRU */
349 : TransactionId tailXid; /* oldest xmin we might be interested in */
350 : } SerialControlData;
351 :
352 : typedef struct SerialControlData *SerialControl;
353 :
354 : static SerialControl serialControl;
355 :
356 : /*
357 : * When the oldest committed transaction on the "finished" list is moved to
358 : * SLRU, its predicate locks will be moved to this "dummy" transaction,
359 : * collapsing duplicate targets. When a duplicate is found, the later
360 : * commitSeqNo is used.
361 : */
362 : static SERIALIZABLEXACT *OldCommittedSxact;
363 :
364 :
365 : /*
366 : * These configuration variables are used to set the predicate lock table size
367 : * and to control promotion of predicate locks to coarser granularity in an
368 : * attempt to degrade performance (mostly as false positive serialization
369 : * failure) gracefully in the face of memory pressure.
370 : */
371 : int max_predicate_locks_per_xact; /* in guc_tables.c */
372 : int max_predicate_locks_per_relation; /* in guc_tables.c */
373 : int max_predicate_locks_per_page; /* in guc_tables.c */
374 :
375 : /*
376 : * This provides a list of objects in order to track transactions
377 : * participating in predicate locking. Entries in the list are fixed size,
378 : * and reside in shared memory. The memory address of an entry must remain
379 : * fixed during its lifetime. The list will be protected from concurrent
380 : * update externally; no provision is made in this code to manage that. The
381 : * number of entries in the list, and the size allowed for each entry is
382 : * fixed upon creation.
383 : */
384 : static PredXactList PredXact;
385 :
386 : /*
387 : * This provides a pool of RWConflict data elements to use in conflict lists
388 : * between transactions.
389 : */
390 : static RWConflictPoolHeader RWConflictPool;
391 :
392 : /*
393 : * The predicate locking hash tables are in shared memory.
394 : * Each backend keeps pointers to them.
395 : */
396 : static HTAB *SerializableXidHash;
397 : static HTAB *PredicateLockTargetHash;
398 : static HTAB *PredicateLockHash;
399 : static dlist_head *FinishedSerializableTransactions;
400 :
401 : /*
402 : * Tag for a dummy entry in PredicateLockTargetHash. By temporarily removing
403 : * this entry, you can ensure that there's enough scratch space available for
404 : * inserting one entry in the hash table. This is an otherwise-invalid tag.
405 : */
406 : static const PREDICATELOCKTARGETTAG ScratchTargetTag = {0, 0, 0, 0};
407 : static uint32 ScratchTargetTagHash;
408 : static LWLock *ScratchPartitionLock;
409 :
410 : /*
411 : * The local hash table used to determine when to combine multiple fine-
412 : * grained locks into a single courser-grained lock.
413 : */
414 : static HTAB *LocalPredicateLockHash = NULL;
415 :
416 : /*
417 : * Keep a pointer to the currently-running serializable transaction (if any)
418 : * for quick reference. Also, remember if we have written anything that could
419 : * cause a rw-conflict.
420 : */
421 : static SERIALIZABLEXACT *MySerializableXact = InvalidSerializableXact;
422 : static bool MyXactDidWrite = false;
423 :
424 : /*
425 : * The SXACT_FLAG_RO_UNSAFE optimization might lead us to release
426 : * MySerializableXact early. If that happens in a parallel query, the leader
427 : * needs to defer the destruction of the SERIALIZABLEXACT until end of
428 : * transaction, because the workers still have a reference to it. In that
429 : * case, the leader stores it here.
430 : */
431 : static SERIALIZABLEXACT *SavedSerializableXact = InvalidSerializableXact;
432 :
433 : /* local functions */
434 :
435 : static SERIALIZABLEXACT *CreatePredXact(void);
436 : static void ReleasePredXact(SERIALIZABLEXACT *sxact);
437 :
438 : static bool RWConflictExists(const SERIALIZABLEXACT *reader, const SERIALIZABLEXACT *writer);
439 : static void SetRWConflict(SERIALIZABLEXACT *reader, SERIALIZABLEXACT *writer);
440 : static void SetPossibleUnsafeConflict(SERIALIZABLEXACT *roXact, SERIALIZABLEXACT *activeXact);
441 : static void ReleaseRWConflict(RWConflict conflict);
442 : static void FlagSxactUnsafe(SERIALIZABLEXACT *sxact);
443 :
444 : static bool SerialPagePrecedesLogically(int64 page1, int64 page2);
445 : static void SerialInit(void);
446 : static void SerialAdd(TransactionId xid, SerCommitSeqNo minConflictCommitSeqNo);
447 : static SerCommitSeqNo SerialGetMinConflictCommitSeqNo(TransactionId xid);
448 : static void SerialSetActiveSerXmin(TransactionId xid);
449 :
450 : static uint32 predicatelock_hash(const void *key, Size keysize);
451 : static void SummarizeOldestCommittedSxact(void);
452 : static Snapshot GetSafeSnapshot(Snapshot origSnapshot);
453 : static Snapshot GetSerializableTransactionSnapshotInt(Snapshot snapshot,
454 : VirtualTransactionId *sourcevxid,
455 : int sourcepid);
456 : static bool PredicateLockExists(const PREDICATELOCKTARGETTAG *targettag);
457 : static bool GetParentPredicateLockTag(const PREDICATELOCKTARGETTAG *tag,
458 : PREDICATELOCKTARGETTAG *parent);
459 : static bool CoarserLockCovers(const PREDICATELOCKTARGETTAG *newtargettag);
460 : static void RemoveScratchTarget(bool lockheld);
461 : static void RestoreScratchTarget(bool lockheld);
462 : static void RemoveTargetIfNoLongerUsed(PREDICATELOCKTARGET *target,
463 : uint32 targettaghash);
464 : static void DeleteChildTargetLocks(const PREDICATELOCKTARGETTAG *newtargettag);
465 : static int MaxPredicateChildLocks(const PREDICATELOCKTARGETTAG *tag);
466 : static bool CheckAndPromotePredicateLockRequest(const PREDICATELOCKTARGETTAG *reqtag);
467 : static void DecrementParentLocks(const PREDICATELOCKTARGETTAG *targettag);
468 : static void CreatePredicateLock(const PREDICATELOCKTARGETTAG *targettag,
469 : uint32 targettaghash,
470 : SERIALIZABLEXACT *sxact);
471 : static void DeleteLockTarget(PREDICATELOCKTARGET *target, uint32 targettaghash);
472 : static bool TransferPredicateLocksToNewTarget(PREDICATELOCKTARGETTAG oldtargettag,
473 : PREDICATELOCKTARGETTAG newtargettag,
474 : bool removeOld);
475 : static void PredicateLockAcquire(const PREDICATELOCKTARGETTAG *targettag);
476 : static void DropAllPredicateLocksFromTable(Relation relation,
477 : bool transfer);
478 : static void SetNewSxactGlobalXmin(void);
479 : static void ClearOldPredicateLocks(void);
480 : static void ReleaseOneSerializableXact(SERIALIZABLEXACT *sxact, bool partial,
481 : bool summarize);
482 : static bool XidIsConcurrent(TransactionId xid);
483 : static void CheckTargetForConflictsIn(PREDICATELOCKTARGETTAG *targettag);
484 : static void FlagRWConflict(SERIALIZABLEXACT *reader, SERIALIZABLEXACT *writer);
485 : static void OnConflict_CheckForSerializationFailure(const SERIALIZABLEXACT *reader,
486 : SERIALIZABLEXACT *writer);
487 : static void CreateLocalPredicateLockHash(void);
488 : static void ReleasePredicateLocksLocal(void);
489 :
490 :
491 : /*------------------------------------------------------------------------*/
492 :
493 : /*
494 : * Does this relation participate in predicate locking? Temporary and system
495 : * relations are exempt.
496 : */
497 : static inline bool
498 309108 : PredicateLockingNeededForRelation(Relation relation)
499 : {
500 423478 : return !(relation->rd_id < FirstUnpinnedObjectId ||
501 114370 : RelationUsesLocalBuffers(relation));
502 : }
503 :
504 : /*
505 : * When a public interface method is called for a read, this is the test to
506 : * see if we should do a quick return.
507 : *
508 : * Note: this function has side-effects! If this transaction has been flagged
509 : * as RO-safe since the last call, we release all predicate locks and reset
510 : * MySerializableXact. That makes subsequent calls to return quickly.
511 : *
512 : * This is marked as 'inline' to eliminate the function call overhead in the
513 : * common case that serialization is not needed.
514 : */
515 : static inline bool
516 120991234 : SerializationNeededForRead(Relation relation, Snapshot snapshot)
517 : {
518 : /* Nothing to do if this is not a serializable transaction */
519 120991234 : if (MySerializableXact == InvalidSerializableXact)
520 120693464 : return false;
521 :
522 : /*
523 : * Don't acquire locks or conflict when scanning with a special snapshot.
524 : * This excludes things like CLUSTER and REINDEX. They use the wholesale
525 : * functions TransferPredicateLocksToHeapRelation() and
526 : * CheckTableForSerializableConflictIn() to participate in serialization,
527 : * but the scans involved don't need serialization.
528 : */
529 297770 : if (!IsMVCCSnapshot(snapshot))
530 3214 : return false;
531 :
532 : /*
533 : * Check if we have just become "RO-safe". If we have, immediately release
534 : * all locks as they're not needed anymore. This also resets
535 : * MySerializableXact, so that subsequent calls to this function can exit
536 : * quickly.
537 : *
538 : * A transaction is flagged as RO_SAFE if all concurrent R/W transactions
539 : * commit without having conflicts out to an earlier snapshot, thus
540 : * ensuring that no conflicts are possible for this transaction.
541 : */
542 294556 : if (SxactIsROSafe(MySerializableXact))
543 : {
544 66 : ReleasePredicateLocks(false, true);
545 66 : return false;
546 : }
547 :
548 : /* Check if the relation doesn't participate in predicate locking */
549 294490 : if (!PredicateLockingNeededForRelation(relation))
550 189658 : return false;
551 :
552 104832 : return true; /* no excuse to skip predicate locking */
553 : }
554 :
555 : /*
556 : * Like SerializationNeededForRead(), but called on writes.
557 : * The logic is the same, but there is no snapshot and we can't be RO-safe.
558 : */
559 : static inline bool
560 32900434 : SerializationNeededForWrite(Relation relation)
561 : {
562 : /* Nothing to do if this is not a serializable transaction */
563 32900434 : if (MySerializableXact == InvalidSerializableXact)
564 32886260 : return false;
565 :
566 : /* Check if the relation doesn't participate in predicate locking */
567 14174 : if (!PredicateLockingNeededForRelation(relation))
568 5318 : return false;
569 :
570 8856 : return true; /* no excuse to skip predicate locking */
571 : }
572 :
573 :
574 : /*------------------------------------------------------------------------*/
575 :
576 : /*
577 : * These functions are a simple implementation of a list for this specific
578 : * type of struct. If there is ever a generalized shared memory list, we
579 : * should probably switch to that.
580 : */
581 : static SERIALIZABLEXACT *
582 5378 : CreatePredXact(void)
583 : {
584 : SERIALIZABLEXACT *sxact;
585 :
586 5378 : if (dlist_is_empty(&PredXact->availableList))
587 0 : return NULL;
588 :
589 5378 : sxact = dlist_container(SERIALIZABLEXACT, xactLink,
590 : dlist_pop_head_node(&PredXact->availableList));
591 5378 : dlist_push_tail(&PredXact->activeList, &sxact->xactLink);
592 5378 : return sxact;
593 : }
594 :
595 : static void
596 3282 : ReleasePredXact(SERIALIZABLEXACT *sxact)
597 : {
598 : Assert(ShmemAddrIsValid(sxact));
599 :
600 3282 : dlist_delete(&sxact->xactLink);
601 3282 : dlist_push_tail(&PredXact->availableList, &sxact->xactLink);
602 3282 : }
603 :
604 : /*------------------------------------------------------------------------*/
605 :
606 : /*
607 : * These functions manage primitive access to the RWConflict pool and lists.
608 : */
609 : static bool
610 3736 : RWConflictExists(const SERIALIZABLEXACT *reader, const SERIALIZABLEXACT *writer)
611 : {
612 : dlist_iter iter;
613 :
614 : Assert(reader != writer);
615 :
616 : /* Check the ends of the purported conflict first. */
617 3736 : if (SxactIsDoomed(reader)
618 3736 : || SxactIsDoomed(writer)
619 3736 : || dlist_is_empty(&reader->outConflicts)
620 1134 : || dlist_is_empty(&writer->inConflicts))
621 2682 : return false;
622 :
623 : /*
624 : * A conflict is possible; walk the list to find out.
625 : *
626 : * The unconstify is needed as we have no const version of
627 : * dlist_foreach().
628 : */
629 1086 : dlist_foreach(iter, &unconstify(SERIALIZABLEXACT *, reader)->outConflicts)
630 : {
631 1054 : RWConflict conflict =
632 1054 : dlist_container(RWConflictData, outLink, iter.cur);
633 :
634 1054 : if (conflict->sxactIn == writer)
635 1022 : return true;
636 : }
637 :
638 : /* No conflict found. */
639 32 : return false;
640 : }
641 :
642 : static void
643 1560 : SetRWConflict(SERIALIZABLEXACT *reader, SERIALIZABLEXACT *writer)
644 : {
645 : RWConflict conflict;
646 :
647 : Assert(reader != writer);
648 : Assert(!RWConflictExists(reader, writer));
649 :
650 1560 : if (dlist_is_empty(&RWConflictPool->availableList))
651 0 : ereport(ERROR,
652 : (errcode(ERRCODE_OUT_OF_MEMORY),
653 : errmsg("not enough elements in RWConflictPool to record a read/write conflict"),
654 : errhint("You might need to run fewer transactions at a time or increase \"max_connections\".")));
655 :
656 1560 : conflict = dlist_head_element(RWConflictData, outLink, &RWConflictPool->availableList);
657 1560 : dlist_delete(&conflict->outLink);
658 :
659 1560 : conflict->sxactOut = reader;
660 1560 : conflict->sxactIn = writer;
661 1560 : dlist_push_tail(&reader->outConflicts, &conflict->outLink);
662 1560 : dlist_push_tail(&writer->inConflicts, &conflict->inLink);
663 1560 : }
664 :
665 : static void
666 268 : SetPossibleUnsafeConflict(SERIALIZABLEXACT *roXact,
667 : SERIALIZABLEXACT *activeXact)
668 : {
669 : RWConflict conflict;
670 :
671 : Assert(roXact != activeXact);
672 : Assert(SxactIsReadOnly(roXact));
673 : Assert(!SxactIsReadOnly(activeXact));
674 :
675 268 : if (dlist_is_empty(&RWConflictPool->availableList))
676 0 : ereport(ERROR,
677 : (errcode(ERRCODE_OUT_OF_MEMORY),
678 : errmsg("not enough elements in RWConflictPool to record a potential read/write conflict"),
679 : errhint("You might need to run fewer transactions at a time or increase \"max_connections\".")));
680 :
681 268 : conflict = dlist_head_element(RWConflictData, outLink, &RWConflictPool->availableList);
682 268 : dlist_delete(&conflict->outLink);
683 :
684 268 : conflict->sxactOut = activeXact;
685 268 : conflict->sxactIn = roXact;
686 268 : dlist_push_tail(&activeXact->possibleUnsafeConflicts, &conflict->outLink);
687 268 : dlist_push_tail(&roXact->possibleUnsafeConflicts, &conflict->inLink);
688 268 : }
689 :
690 : static void
691 1828 : ReleaseRWConflict(RWConflict conflict)
692 : {
693 1828 : dlist_delete(&conflict->inLink);
694 1828 : dlist_delete(&conflict->outLink);
695 1828 : dlist_push_tail(&RWConflictPool->availableList, &conflict->outLink);
696 1828 : }
697 :
698 : static void
699 6 : FlagSxactUnsafe(SERIALIZABLEXACT *sxact)
700 : {
701 : dlist_mutable_iter iter;
702 :
703 : Assert(SxactIsReadOnly(sxact));
704 : Assert(!SxactIsROSafe(sxact));
705 :
706 6 : sxact->flags |= SXACT_FLAG_RO_UNSAFE;
707 :
708 : /*
709 : * We know this isn't a safe snapshot, so we can stop looking for other
710 : * potential conflicts.
711 : */
712 12 : dlist_foreach_modify(iter, &sxact->possibleUnsafeConflicts)
713 : {
714 6 : RWConflict conflict =
715 6 : dlist_container(RWConflictData, inLink, iter.cur);
716 :
717 : Assert(!SxactIsReadOnly(conflict->sxactOut));
718 : Assert(sxact == conflict->sxactIn);
719 :
720 6 : ReleaseRWConflict(conflict);
721 : }
722 6 : }
723 :
724 : /*------------------------------------------------------------------------*/
725 :
726 : /*
727 : * Decide whether a Serial page number is "older" for truncation purposes.
728 : * Analogous to CLOGPagePrecedes().
729 : */
730 : static bool
731 0 : SerialPagePrecedesLogically(int64 page1, int64 page2)
732 : {
733 : TransactionId xid1;
734 : TransactionId xid2;
735 :
736 0 : xid1 = ((TransactionId) page1) * SERIAL_ENTRIESPERPAGE;
737 0 : xid1 += FirstNormalTransactionId + 1;
738 0 : xid2 = ((TransactionId) page2) * SERIAL_ENTRIESPERPAGE;
739 0 : xid2 += FirstNormalTransactionId + 1;
740 :
741 0 : return (TransactionIdPrecedes(xid1, xid2) &&
742 0 : TransactionIdPrecedes(xid1, xid2 + SERIAL_ENTRIESPERPAGE - 1));
743 : }
744 :
745 : #ifdef USE_ASSERT_CHECKING
746 : static void
747 : SerialPagePrecedesLogicallyUnitTests(void)
748 : {
749 : int per_page = SERIAL_ENTRIESPERPAGE,
750 : offset = per_page / 2;
751 : int64 newestPage,
752 : oldestPage,
753 : headPage,
754 : targetPage;
755 : TransactionId newestXact,
756 : oldestXact;
757 :
758 : /* GetNewTransactionId() has assigned the last XID it can safely use. */
759 : newestPage = 2 * SLRU_PAGES_PER_SEGMENT - 1; /* nothing special */
760 : newestXact = newestPage * per_page + offset;
761 : Assert(newestXact / per_page == newestPage);
762 : oldestXact = newestXact + 1;
763 : oldestXact -= 1U << 31;
764 : oldestPage = oldestXact / per_page;
765 :
766 : /*
767 : * In this scenario, the SLRU headPage pertains to the last ~1000 XIDs
768 : * assigned. oldestXact finishes, ~2B XIDs having elapsed since it
769 : * started. Further transactions cause us to summarize oldestXact to
770 : * tailPage. Function must return false so SerialAdd() doesn't zero
771 : * tailPage (which may contain entries for other old, recently-finished
772 : * XIDs) and half the SLRU. Reaching this requires burning ~2B XIDs in
773 : * single-user mode, a negligible possibility.
774 : */
775 : headPage = newestPage;
776 : targetPage = oldestPage;
777 : Assert(!SerialPagePrecedesLogically(headPage, targetPage));
778 :
779 : /*
780 : * In this scenario, the SLRU headPage pertains to oldestXact. We're
781 : * summarizing an XID near newestXact. (Assume few other XIDs used
782 : * SERIALIZABLE, hence the minimal headPage advancement. Assume
783 : * oldestXact was long-running and only recently reached the SLRU.)
784 : * Function must return true to make SerialAdd() create targetPage.
785 : *
786 : * Today's implementation mishandles this case, but it doesn't matter
787 : * enough to fix. Verify that the defect affects just one page by
788 : * asserting correct treatment of its prior page. Reaching this case
789 : * requires burning ~2B XIDs in single-user mode, a negligible
790 : * possibility. Moreover, if it does happen, the consequence would be
791 : * mild, namely a new transaction failing in SimpleLruReadPage().
792 : */
793 : headPage = oldestPage;
794 : targetPage = newestPage;
795 : Assert(SerialPagePrecedesLogically(headPage, targetPage - 1));
796 : #if 0
797 : Assert(SerialPagePrecedesLogically(headPage, targetPage));
798 : #endif
799 : }
800 : #endif
801 :
802 : /*
803 : * Initialize for the tracking of old serializable committed xids.
804 : */
805 : static void
806 2096 : SerialInit(void)
807 : {
808 : bool found;
809 :
810 : /*
811 : * Set up SLRU management of the pg_serial data.
812 : */
813 2096 : SerialSlruCtl->PagePrecedes = SerialPagePrecedesLogically;
814 2096 : SimpleLruInit(SerialSlruCtl, "serializable",
815 : serializable_buffers, 0, "pg_serial",
816 : LWTRANCHE_SERIAL_BUFFER, LWTRANCHE_SERIAL_SLRU,
817 : SYNC_HANDLER_NONE, false);
818 : #ifdef USE_ASSERT_CHECKING
819 : SerialPagePrecedesLogicallyUnitTests();
820 : #endif
821 : SlruPagePrecedesUnitTests(SerialSlruCtl, SERIAL_ENTRIESPERPAGE);
822 :
823 : /*
824 : * Create or attach to the SerialControl structure.
825 : */
826 2096 : serialControl = (SerialControl)
827 2096 : ShmemInitStruct("SerialControlData", sizeof(SerialControlData), &found);
828 :
829 : Assert(found == IsUnderPostmaster);
830 2096 : if (!found)
831 : {
832 : /*
833 : * Set control information to reflect empty SLRU.
834 : */
835 2096 : LWLockAcquire(SerialControlLock, LW_EXCLUSIVE);
836 2096 : serialControl->headPage = -1;
837 2096 : serialControl->headXid = InvalidTransactionId;
838 2096 : serialControl->tailXid = InvalidTransactionId;
839 2096 : LWLockRelease(SerialControlLock);
840 : }
841 2096 : }
842 :
843 : /*
844 : * GUC check_hook for serializable_buffers
845 : */
846 : bool
847 2164 : check_serial_buffers(int *newval, void **extra, GucSource source)
848 : {
849 2164 : return check_slru_buffers("serializable_buffers", newval);
850 : }
851 :
852 : /*
853 : * Record a committed read write serializable xid and the minimum
854 : * commitSeqNo of any transactions to which this xid had a rw-conflict out.
855 : * An invalid commitSeqNo means that there were no conflicts out from xid.
856 : */
857 : static void
858 0 : SerialAdd(TransactionId xid, SerCommitSeqNo minConflictCommitSeqNo)
859 : {
860 : TransactionId tailXid;
861 : int64 targetPage;
862 : int slotno;
863 : int64 firstZeroPage;
864 : bool isNewPage;
865 : LWLock *lock;
866 :
867 : Assert(TransactionIdIsValid(xid));
868 :
869 0 : targetPage = SerialPage(xid);
870 0 : lock = SimpleLruGetBankLock(SerialSlruCtl, targetPage);
871 :
872 : /*
873 : * In this routine, we must hold both SerialControlLock and the SLRU bank
874 : * lock simultaneously while making the SLRU data catch up with the new
875 : * state that we determine.
876 : */
877 0 : LWLockAcquire(SerialControlLock, LW_EXCLUSIVE);
878 :
879 : /*
880 : * If 'xid' is older than the global xmin (== tailXid), there's no need to
881 : * store it, after all. This can happen if the oldest transaction holding
882 : * back the global xmin just finished, making 'xid' uninteresting, but
883 : * ClearOldPredicateLocks() has not yet run.
884 : */
885 0 : tailXid = serialControl->tailXid;
886 0 : if (!TransactionIdIsValid(tailXid) || TransactionIdPrecedes(xid, tailXid))
887 : {
888 0 : LWLockRelease(SerialControlLock);
889 0 : return;
890 : }
891 :
892 : /*
893 : * If the SLRU is currently unused, zero out the whole active region from
894 : * tailXid to headXid before taking it into use. Otherwise zero out only
895 : * any new pages that enter the tailXid-headXid range as we advance
896 : * headXid.
897 : */
898 0 : if (serialControl->headPage < 0)
899 : {
900 0 : firstZeroPage = SerialPage(tailXid);
901 0 : isNewPage = true;
902 : }
903 : else
904 : {
905 0 : firstZeroPage = SerialNextPage(serialControl->headPage);
906 0 : isNewPage = SerialPagePrecedesLogically(serialControl->headPage,
907 : targetPage);
908 : }
909 :
910 0 : if (!TransactionIdIsValid(serialControl->headXid)
911 0 : || TransactionIdFollows(xid, serialControl->headXid))
912 0 : serialControl->headXid = xid;
913 0 : if (isNewPage)
914 0 : serialControl->headPage = targetPage;
915 :
916 0 : if (isNewPage)
917 : {
918 : /* Initialize intervening pages; might involve trading locks */
919 : for (;;)
920 : {
921 0 : lock = SimpleLruGetBankLock(SerialSlruCtl, firstZeroPage);
922 0 : LWLockAcquire(lock, LW_EXCLUSIVE);
923 0 : slotno = SimpleLruZeroPage(SerialSlruCtl, firstZeroPage);
924 0 : if (firstZeroPage == targetPage)
925 0 : break;
926 0 : firstZeroPage = SerialNextPage(firstZeroPage);
927 0 : LWLockRelease(lock);
928 : }
929 : }
930 : else
931 : {
932 0 : LWLockAcquire(lock, LW_EXCLUSIVE);
933 0 : slotno = SimpleLruReadPage(SerialSlruCtl, targetPage, true, xid);
934 : }
935 :
936 0 : SerialValue(slotno, xid) = minConflictCommitSeqNo;
937 0 : SerialSlruCtl->shared->page_dirty[slotno] = true;
938 :
939 0 : LWLockRelease(lock);
940 0 : LWLockRelease(SerialControlLock);
941 : }
942 :
943 : /*
944 : * Get the minimum commitSeqNo for any conflict out for the given xid. For
945 : * a transaction which exists but has no conflict out, InvalidSerCommitSeqNo
946 : * will be returned.
947 : */
948 : static SerCommitSeqNo
949 44 : SerialGetMinConflictCommitSeqNo(TransactionId xid)
950 : {
951 : TransactionId headXid;
952 : TransactionId tailXid;
953 : SerCommitSeqNo val;
954 : int slotno;
955 :
956 : Assert(TransactionIdIsValid(xid));
957 :
958 44 : LWLockAcquire(SerialControlLock, LW_SHARED);
959 44 : headXid = serialControl->headXid;
960 44 : tailXid = serialControl->tailXid;
961 44 : LWLockRelease(SerialControlLock);
962 :
963 44 : if (!TransactionIdIsValid(headXid))
964 44 : return 0;
965 :
966 : Assert(TransactionIdIsValid(tailXid));
967 :
968 0 : if (TransactionIdPrecedes(xid, tailXid)
969 0 : || TransactionIdFollows(xid, headXid))
970 0 : return 0;
971 :
972 : /*
973 : * The following function must be called without holding SLRU bank lock,
974 : * but will return with that lock held, which must then be released.
975 : */
976 0 : slotno = SimpleLruReadPage_ReadOnly(SerialSlruCtl,
977 : SerialPage(xid), xid);
978 0 : val = SerialValue(slotno, xid);
979 0 : LWLockRelease(SimpleLruGetBankLock(SerialSlruCtl, SerialPage(xid)));
980 0 : return val;
981 : }
982 :
983 : /*
984 : * Call this whenever there is a new xmin for active serializable
985 : * transactions. We don't need to keep information on transactions which
986 : * precede that. InvalidTransactionId means none active, so everything in
987 : * the SLRU can be discarded.
988 : */
989 : static void
990 3306 : SerialSetActiveSerXmin(TransactionId xid)
991 : {
992 3306 : LWLockAcquire(SerialControlLock, LW_EXCLUSIVE);
993 :
994 : /*
995 : * When no sxacts are active, nothing overlaps, set the xid values to
996 : * invalid to show that there are no valid entries. Don't clear headPage,
997 : * though. A new xmin might still land on that page, and we don't want to
998 : * repeatedly zero out the same page.
999 : */
1000 3306 : if (!TransactionIdIsValid(xid))
1001 : {
1002 1634 : serialControl->tailXid = InvalidTransactionId;
1003 1634 : serialControl->headXid = InvalidTransactionId;
1004 1634 : LWLockRelease(SerialControlLock);
1005 1634 : return;
1006 : }
1007 :
1008 : /*
1009 : * When we're recovering prepared transactions, the global xmin might move
1010 : * backwards depending on the order they're recovered. Normally that's not
1011 : * OK, but during recovery no serializable transactions will commit, so
1012 : * the SLRU is empty and we can get away with it.
1013 : */
1014 1672 : if (RecoveryInProgress())
1015 : {
1016 : Assert(serialControl->headPage < 0);
1017 0 : if (!TransactionIdIsValid(serialControl->tailXid)
1018 0 : || TransactionIdPrecedes(xid, serialControl->tailXid))
1019 : {
1020 0 : serialControl->tailXid = xid;
1021 : }
1022 0 : LWLockRelease(SerialControlLock);
1023 0 : return;
1024 : }
1025 :
1026 : Assert(!TransactionIdIsValid(serialControl->tailXid)
1027 : || TransactionIdFollows(xid, serialControl->tailXid));
1028 :
1029 1672 : serialControl->tailXid = xid;
1030 :
1031 1672 : LWLockRelease(SerialControlLock);
1032 : }
1033 :
1034 : /*
1035 : * Perform a checkpoint --- either during shutdown, or on-the-fly
1036 : *
1037 : * We don't have any data that needs to survive a restart, but this is a
1038 : * convenient place to truncate the SLRU.
1039 : */
1040 : void
1041 3312 : CheckPointPredicate(void)
1042 : {
1043 : int64 truncateCutoffPage;
1044 :
1045 3312 : LWLockAcquire(SerialControlLock, LW_EXCLUSIVE);
1046 :
1047 : /* Exit quickly if the SLRU is currently not in use. */
1048 3312 : if (serialControl->headPage < 0)
1049 : {
1050 3312 : LWLockRelease(SerialControlLock);
1051 3312 : return;
1052 : }
1053 :
1054 0 : if (TransactionIdIsValid(serialControl->tailXid))
1055 : {
1056 : int64 tailPage;
1057 :
1058 0 : tailPage = SerialPage(serialControl->tailXid);
1059 :
1060 : /*
1061 : * It is possible for the tailXid to be ahead of the headXid. This
1062 : * occurs if we checkpoint while there are in-progress serializable
1063 : * transaction(s) advancing the tail but we are yet to summarize the
1064 : * transactions. In this case, we cutoff up to the headPage and the
1065 : * next summary will advance the headXid.
1066 : */
1067 0 : if (SerialPagePrecedesLogically(tailPage, serialControl->headPage))
1068 : {
1069 : /* We can truncate the SLRU up to the page containing tailXid */
1070 0 : truncateCutoffPage = tailPage;
1071 : }
1072 : else
1073 0 : truncateCutoffPage = serialControl->headPage;
1074 : }
1075 : else
1076 : {
1077 : /*----------
1078 : * The SLRU is no longer needed. Truncate to head before we set head
1079 : * invalid.
1080 : *
1081 : * XXX: It's possible that the SLRU is not needed again until XID
1082 : * wrap-around has happened, so that the segment containing headPage
1083 : * that we leave behind will appear to be new again. In that case it
1084 : * won't be removed until XID horizon advances enough to make it
1085 : * current again.
1086 : *
1087 : * XXX: This should happen in vac_truncate_clog(), not in checkpoints.
1088 : * Consider this scenario, starting from a system with no in-progress
1089 : * transactions and VACUUM FREEZE having maximized oldestXact:
1090 : * - Start a SERIALIZABLE transaction.
1091 : * - Start, finish, and summarize a SERIALIZABLE transaction, creating
1092 : * one SLRU page.
1093 : * - Consume XIDs to reach xidStopLimit.
1094 : * - Finish all transactions. Due to the long-running SERIALIZABLE
1095 : * transaction, earlier checkpoints did not touch headPage. The
1096 : * next checkpoint will change it, but that checkpoint happens after
1097 : * the end of the scenario.
1098 : * - VACUUM to advance XID limits.
1099 : * - Consume ~2M XIDs, crossing the former xidWrapLimit.
1100 : * - Start, finish, and summarize a SERIALIZABLE transaction.
1101 : * SerialAdd() declines to create the targetPage, because headPage
1102 : * is not regarded as in the past relative to that targetPage. The
1103 : * transaction instigating the summarize fails in
1104 : * SimpleLruReadPage().
1105 : */
1106 0 : truncateCutoffPage = serialControl->headPage;
1107 0 : serialControl->headPage = -1;
1108 : }
1109 :
1110 0 : LWLockRelease(SerialControlLock);
1111 :
1112 : /*
1113 : * Truncate away pages that are no longer required. Note that no
1114 : * additional locking is required, because this is only called as part of
1115 : * a checkpoint, and the validity limits have already been determined.
1116 : */
1117 0 : SimpleLruTruncate(SerialSlruCtl, truncateCutoffPage);
1118 :
1119 : /*
1120 : * Write dirty SLRU pages to disk
1121 : *
1122 : * This is not actually necessary from a correctness point of view. We do
1123 : * it merely as a debugging aid.
1124 : *
1125 : * We're doing this after the truncation to avoid writing pages right
1126 : * before deleting the file in which they sit, which would be completely
1127 : * pointless.
1128 : */
1129 0 : SimpleLruWriteAll(SerialSlruCtl, true);
1130 : }
1131 :
1132 : /*------------------------------------------------------------------------*/
1133 :
1134 : /*
1135 : * PredicateLockShmemInit -- Initialize the predicate locking data structures.
1136 : *
1137 : * This is called from CreateSharedMemoryAndSemaphores(), which see for
1138 : * more comments. In the normal postmaster case, the shared hash tables
1139 : * are created here. Backends inherit the pointers
1140 : * to the shared tables via fork(). In the EXEC_BACKEND case, each
1141 : * backend re-executes this code to obtain pointers to the already existing
1142 : * shared hash tables.
1143 : */
1144 : void
1145 2096 : PredicateLockShmemInit(void)
1146 : {
1147 : HASHCTL info;
1148 : long max_table_size;
1149 : Size requestSize;
1150 : bool found;
1151 :
1152 : #ifndef EXEC_BACKEND
1153 : Assert(!IsUnderPostmaster);
1154 : #endif
1155 :
1156 : /*
1157 : * Compute size of predicate lock target hashtable. Note these
1158 : * calculations must agree with PredicateLockShmemSize!
1159 : */
1160 2096 : max_table_size = NPREDICATELOCKTARGETENTS();
1161 :
1162 : /*
1163 : * Allocate hash table for PREDICATELOCKTARGET structs. This stores
1164 : * per-predicate-lock-target information.
1165 : */
1166 2096 : info.keysize = sizeof(PREDICATELOCKTARGETTAG);
1167 2096 : info.entrysize = sizeof(PREDICATELOCKTARGET);
1168 2096 : info.num_partitions = NUM_PREDICATELOCK_PARTITIONS;
1169 :
1170 2096 : PredicateLockTargetHash = ShmemInitHash("PREDICATELOCKTARGET hash",
1171 : max_table_size,
1172 : max_table_size,
1173 : &info,
1174 : HASH_ELEM | HASH_BLOBS |
1175 : HASH_PARTITION | HASH_FIXED_SIZE);
1176 :
1177 : /*
1178 : * Reserve a dummy entry in the hash table; we use it to make sure there's
1179 : * always one entry available when we need to split or combine a page,
1180 : * because running out of space there could mean aborting a
1181 : * non-serializable transaction.
1182 : */
1183 2096 : if (!IsUnderPostmaster)
1184 : {
1185 2096 : (void) hash_search(PredicateLockTargetHash, &ScratchTargetTag,
1186 : HASH_ENTER, &found);
1187 : Assert(!found);
1188 : }
1189 :
1190 : /* Pre-calculate the hash and partition lock of the scratch entry */
1191 2096 : ScratchTargetTagHash = PredicateLockTargetTagHashCode(&ScratchTargetTag);
1192 2096 : ScratchPartitionLock = PredicateLockHashPartitionLock(ScratchTargetTagHash);
1193 :
1194 : /*
1195 : * Allocate hash table for PREDICATELOCK structs. This stores per
1196 : * xact-lock-of-a-target information.
1197 : */
1198 2096 : info.keysize = sizeof(PREDICATELOCKTAG);
1199 2096 : info.entrysize = sizeof(PREDICATELOCK);
1200 2096 : info.hash = predicatelock_hash;
1201 2096 : info.num_partitions = NUM_PREDICATELOCK_PARTITIONS;
1202 :
1203 : /* Assume an average of 2 xacts per target */
1204 2096 : max_table_size *= 2;
1205 :
1206 2096 : PredicateLockHash = ShmemInitHash("PREDICATELOCK hash",
1207 : max_table_size,
1208 : max_table_size,
1209 : &info,
1210 : HASH_ELEM | HASH_FUNCTION |
1211 : HASH_PARTITION | HASH_FIXED_SIZE);
1212 :
1213 : /*
1214 : * Compute size for serializable transaction hashtable. Note these
1215 : * calculations must agree with PredicateLockShmemSize!
1216 : */
1217 2096 : max_table_size = (MaxBackends + max_prepared_xacts);
1218 :
1219 : /*
1220 : * Allocate a list to hold information on transactions participating in
1221 : * predicate locking.
1222 : *
1223 : * Assume an average of 10 predicate locking transactions per backend.
1224 : * This allows aggressive cleanup while detail is present before data must
1225 : * be summarized for storage in SLRU and the "dummy" transaction.
1226 : */
1227 2096 : max_table_size *= 10;
1228 :
1229 2096 : requestSize = add_size(PredXactListDataSize,
1230 : (mul_size((Size) max_table_size,
1231 : sizeof(SERIALIZABLEXACT))));
1232 :
1233 2096 : PredXact = ShmemInitStruct("PredXactList",
1234 : requestSize,
1235 : &found);
1236 : Assert(found == IsUnderPostmaster);
1237 2096 : if (!found)
1238 : {
1239 : int i;
1240 :
1241 : /* clean everything, both the header and the element */
1242 2096 : memset(PredXact, 0, requestSize);
1243 :
1244 2096 : dlist_init(&PredXact->availableList);
1245 2096 : dlist_init(&PredXact->activeList);
1246 2096 : PredXact->SxactGlobalXmin = InvalidTransactionId;
1247 2096 : PredXact->SxactGlobalXminCount = 0;
1248 2096 : PredXact->WritableSxactCount = 0;
1249 2096 : PredXact->LastSxactCommitSeqNo = FirstNormalSerCommitSeqNo - 1;
1250 2096 : PredXact->CanPartialClearThrough = 0;
1251 2096 : PredXact->HavePartialClearedThrough = 0;
1252 2096 : PredXact->element
1253 2096 : = (SERIALIZABLEXACT *) ((char *) PredXact + PredXactListDataSize);
1254 : /* Add all elements to available list, clean. */
1255 1991556 : for (i = 0; i < max_table_size; i++)
1256 : {
1257 1989460 : LWLockInitialize(&PredXact->element[i].perXactPredicateListLock,
1258 : LWTRANCHE_PER_XACT_PREDICATE_LIST);
1259 1989460 : dlist_push_tail(&PredXact->availableList, &PredXact->element[i].xactLink);
1260 : }
1261 2096 : PredXact->OldCommittedSxact = CreatePredXact();
1262 2096 : SetInvalidVirtualTransactionId(PredXact->OldCommittedSxact->vxid);
1263 2096 : PredXact->OldCommittedSxact->prepareSeqNo = 0;
1264 2096 : PredXact->OldCommittedSxact->commitSeqNo = 0;
1265 2096 : PredXact->OldCommittedSxact->SeqNo.lastCommitBeforeSnapshot = 0;
1266 2096 : dlist_init(&PredXact->OldCommittedSxact->outConflicts);
1267 2096 : dlist_init(&PredXact->OldCommittedSxact->inConflicts);
1268 2096 : dlist_init(&PredXact->OldCommittedSxact->predicateLocks);
1269 2096 : dlist_node_init(&PredXact->OldCommittedSxact->finishedLink);
1270 2096 : dlist_init(&PredXact->OldCommittedSxact->possibleUnsafeConflicts);
1271 2096 : PredXact->OldCommittedSxact->topXid = InvalidTransactionId;
1272 2096 : PredXact->OldCommittedSxact->finishedBefore = InvalidTransactionId;
1273 2096 : PredXact->OldCommittedSxact->xmin = InvalidTransactionId;
1274 2096 : PredXact->OldCommittedSxact->flags = SXACT_FLAG_COMMITTED;
1275 2096 : PredXact->OldCommittedSxact->pid = 0;
1276 2096 : PredXact->OldCommittedSxact->pgprocno = INVALID_PROC_NUMBER;
1277 : }
1278 : /* This never changes, so let's keep a local copy. */
1279 2096 : OldCommittedSxact = PredXact->OldCommittedSxact;
1280 :
1281 : /*
1282 : * Allocate hash table for SERIALIZABLEXID structs. This stores per-xid
1283 : * information for serializable transactions which have accessed data.
1284 : */
1285 2096 : info.keysize = sizeof(SERIALIZABLEXIDTAG);
1286 2096 : info.entrysize = sizeof(SERIALIZABLEXID);
1287 :
1288 2096 : SerializableXidHash = ShmemInitHash("SERIALIZABLEXID hash",
1289 : max_table_size,
1290 : max_table_size,
1291 : &info,
1292 : HASH_ELEM | HASH_BLOBS |
1293 : HASH_FIXED_SIZE);
1294 :
1295 : /*
1296 : * Allocate space for tracking rw-conflicts in lists attached to the
1297 : * transactions.
1298 : *
1299 : * Assume an average of 5 conflicts per transaction. Calculations suggest
1300 : * that this will prevent resource exhaustion in even the most pessimal
1301 : * loads up to max_connections = 200 with all 200 connections pounding the
1302 : * database with serializable transactions. Beyond that, there may be
1303 : * occasional transactions canceled when trying to flag conflicts. That's
1304 : * probably OK.
1305 : */
1306 2096 : max_table_size *= 5;
1307 :
1308 2096 : requestSize = RWConflictPoolHeaderDataSize +
1309 2096 : mul_size((Size) max_table_size,
1310 : RWConflictDataSize);
1311 :
1312 2096 : RWConflictPool = ShmemInitStruct("RWConflictPool",
1313 : requestSize,
1314 : &found);
1315 : Assert(found == IsUnderPostmaster);
1316 2096 : if (!found)
1317 : {
1318 : int i;
1319 :
1320 : /* clean everything, including the elements */
1321 2096 : memset(RWConflictPool, 0, requestSize);
1322 :
1323 2096 : dlist_init(&RWConflictPool->availableList);
1324 2096 : RWConflictPool->element = (RWConflict) ((char *) RWConflictPool +
1325 : RWConflictPoolHeaderDataSize);
1326 : /* Add all elements to available list, clean. */
1327 9949396 : for (i = 0; i < max_table_size; i++)
1328 : {
1329 9947300 : dlist_push_tail(&RWConflictPool->availableList,
1330 9947300 : &RWConflictPool->element[i].outLink);
1331 : }
1332 : }
1333 :
1334 : /*
1335 : * Create or attach to the header for the list of finished serializable
1336 : * transactions.
1337 : */
1338 2096 : FinishedSerializableTransactions = (dlist_head *)
1339 2096 : ShmemInitStruct("FinishedSerializableTransactions",
1340 : sizeof(dlist_head),
1341 : &found);
1342 : Assert(found == IsUnderPostmaster);
1343 2096 : if (!found)
1344 2096 : dlist_init(FinishedSerializableTransactions);
1345 :
1346 : /*
1347 : * Initialize the SLRU storage for old committed serializable
1348 : * transactions.
1349 : */
1350 2096 : SerialInit();
1351 2096 : }
1352 :
1353 : /*
1354 : * Estimate shared-memory space used for predicate lock table
1355 : */
1356 : Size
1357 3898 : PredicateLockShmemSize(void)
1358 : {
1359 3898 : Size size = 0;
1360 : long max_table_size;
1361 :
1362 : /* predicate lock target hash table */
1363 3898 : max_table_size = NPREDICATELOCKTARGETENTS();
1364 3898 : size = add_size(size, hash_estimate_size(max_table_size,
1365 : sizeof(PREDICATELOCKTARGET)));
1366 :
1367 : /* predicate lock hash table */
1368 3898 : max_table_size *= 2;
1369 3898 : size = add_size(size, hash_estimate_size(max_table_size,
1370 : sizeof(PREDICATELOCK)));
1371 :
1372 : /*
1373 : * Since NPREDICATELOCKTARGETENTS is only an estimate, add 10% safety
1374 : * margin.
1375 : */
1376 3898 : size = add_size(size, size / 10);
1377 :
1378 : /* transaction list */
1379 3898 : max_table_size = MaxBackends + max_prepared_xacts;
1380 3898 : max_table_size *= 10;
1381 3898 : size = add_size(size, PredXactListDataSize);
1382 3898 : size = add_size(size, mul_size((Size) max_table_size,
1383 : sizeof(SERIALIZABLEXACT)));
1384 :
1385 : /* transaction xid table */
1386 3898 : size = add_size(size, hash_estimate_size(max_table_size,
1387 : sizeof(SERIALIZABLEXID)));
1388 :
1389 : /* rw-conflict pool */
1390 3898 : max_table_size *= 5;
1391 3898 : size = add_size(size, RWConflictPoolHeaderDataSize);
1392 3898 : size = add_size(size, mul_size((Size) max_table_size,
1393 : RWConflictDataSize));
1394 :
1395 : /* Head for list of finished serializable transactions. */
1396 3898 : size = add_size(size, sizeof(dlist_head));
1397 :
1398 : /* Shared memory structures for SLRU tracking of old committed xids. */
1399 3898 : size = add_size(size, sizeof(SerialControlData));
1400 3898 : size = add_size(size, SimpleLruShmemSize(serializable_buffers, 0));
1401 :
1402 3898 : return size;
1403 : }
1404 :
1405 :
1406 : /*
1407 : * Compute the hash code associated with a PREDICATELOCKTAG.
1408 : *
1409 : * Because we want to use just one set of partition locks for both the
1410 : * PREDICATELOCKTARGET and PREDICATELOCK hash tables, we have to make sure
1411 : * that PREDICATELOCKs fall into the same partition number as their
1412 : * associated PREDICATELOCKTARGETs. dynahash.c expects the partition number
1413 : * to be the low-order bits of the hash code, and therefore a
1414 : * PREDICATELOCKTAG's hash code must have the same low-order bits as the
1415 : * associated PREDICATELOCKTARGETTAG's hash code. We achieve this with this
1416 : * specialized hash function.
1417 : */
1418 : static uint32
1419 0 : predicatelock_hash(const void *key, Size keysize)
1420 : {
1421 0 : const PREDICATELOCKTAG *predicatelocktag = (const PREDICATELOCKTAG *) key;
1422 : uint32 targethash;
1423 :
1424 : Assert(keysize == sizeof(PREDICATELOCKTAG));
1425 :
1426 : /* Look into the associated target object, and compute its hash code */
1427 0 : targethash = PredicateLockTargetTagHashCode(&predicatelocktag->myTarget->tag);
1428 :
1429 0 : return PredicateLockHashCodeFromTargetHashCode(predicatelocktag, targethash);
1430 : }
1431 :
1432 :
1433 : /*
1434 : * GetPredicateLockStatusData
1435 : * Return a table containing the internal state of the predicate
1436 : * lock manager for use in pg_lock_status.
1437 : *
1438 : * Like GetLockStatusData, this function tries to hold the partition LWLocks
1439 : * for as short a time as possible by returning two arrays that simply
1440 : * contain the PREDICATELOCKTARGETTAG and SERIALIZABLEXACT for each lock
1441 : * table entry. Multiple copies of the same PREDICATELOCKTARGETTAG and
1442 : * SERIALIZABLEXACT will likely appear.
1443 : */
1444 : PredicateLockData *
1445 550 : GetPredicateLockStatusData(void)
1446 : {
1447 : PredicateLockData *data;
1448 : int i;
1449 : int els,
1450 : el;
1451 : HASH_SEQ_STATUS seqstat;
1452 : PREDICATELOCK *predlock;
1453 :
1454 550 : data = (PredicateLockData *) palloc(sizeof(PredicateLockData));
1455 :
1456 : /*
1457 : * To ensure consistency, take simultaneous locks on all partition locks
1458 : * in ascending order, then SerializableXactHashLock.
1459 : */
1460 9350 : for (i = 0; i < NUM_PREDICATELOCK_PARTITIONS; i++)
1461 8800 : LWLockAcquire(PredicateLockHashPartitionLockByIndex(i), LW_SHARED);
1462 550 : LWLockAcquire(SerializableXactHashLock, LW_SHARED);
1463 :
1464 : /* Get number of locks and allocate appropriately-sized arrays. */
1465 550 : els = hash_get_num_entries(PredicateLockHash);
1466 550 : data->nelements = els;
1467 550 : data->locktags = (PREDICATELOCKTARGETTAG *)
1468 550 : palloc(sizeof(PREDICATELOCKTARGETTAG) * els);
1469 550 : data->xacts = (SERIALIZABLEXACT *)
1470 550 : palloc(sizeof(SERIALIZABLEXACT) * els);
1471 :
1472 :
1473 : /* Scan through PredicateLockHash and copy contents */
1474 550 : hash_seq_init(&seqstat, PredicateLockHash);
1475 :
1476 550 : el = 0;
1477 :
1478 556 : while ((predlock = (PREDICATELOCK *) hash_seq_search(&seqstat)))
1479 : {
1480 6 : data->locktags[el] = predlock->tag.myTarget->tag;
1481 6 : data->xacts[el] = *predlock->tag.myXact;
1482 6 : el++;
1483 : }
1484 :
1485 : Assert(el == els);
1486 :
1487 : /* Release locks in reverse order */
1488 550 : LWLockRelease(SerializableXactHashLock);
1489 9350 : for (i = NUM_PREDICATELOCK_PARTITIONS - 1; i >= 0; i--)
1490 8800 : LWLockRelease(PredicateLockHashPartitionLockByIndex(i));
1491 :
1492 550 : return data;
1493 : }
1494 :
1495 : /*
1496 : * Free up shared memory structures by pushing the oldest sxact (the one at
1497 : * the front of the SummarizeOldestCommittedSxact queue) into summary form.
1498 : * Each call will free exactly one SERIALIZABLEXACT structure and may also
1499 : * free one or more of these structures: SERIALIZABLEXID, PREDICATELOCK,
1500 : * PREDICATELOCKTARGET, RWConflictData.
1501 : */
1502 : static void
1503 0 : SummarizeOldestCommittedSxact(void)
1504 : {
1505 : SERIALIZABLEXACT *sxact;
1506 :
1507 0 : LWLockAcquire(SerializableFinishedListLock, LW_EXCLUSIVE);
1508 :
1509 : /*
1510 : * This function is only called if there are no sxact slots available.
1511 : * Some of them must belong to old, already-finished transactions, so
1512 : * there should be something in FinishedSerializableTransactions list that
1513 : * we can summarize. However, there's a race condition: while we were not
1514 : * holding any locks, a transaction might have ended and cleaned up all
1515 : * the finished sxact entries already, freeing up their sxact slots. In
1516 : * that case, we have nothing to do here. The caller will find one of the
1517 : * slots released by the other backend when it retries.
1518 : */
1519 0 : if (dlist_is_empty(FinishedSerializableTransactions))
1520 : {
1521 0 : LWLockRelease(SerializableFinishedListLock);
1522 0 : return;
1523 : }
1524 :
1525 : /*
1526 : * Grab the first sxact off the finished list -- this will be the earliest
1527 : * commit. Remove it from the list.
1528 : */
1529 0 : sxact = dlist_head_element(SERIALIZABLEXACT, finishedLink,
1530 : FinishedSerializableTransactions);
1531 0 : dlist_delete_thoroughly(&sxact->finishedLink);
1532 :
1533 : /* Add to SLRU summary information. */
1534 0 : if (TransactionIdIsValid(sxact->topXid) && !SxactIsReadOnly(sxact))
1535 0 : SerialAdd(sxact->topXid, SxactHasConflictOut(sxact)
1536 : ? sxact->SeqNo.earliestOutConflictCommit : InvalidSerCommitSeqNo);
1537 :
1538 : /* Summarize and release the detail. */
1539 0 : ReleaseOneSerializableXact(sxact, false, true);
1540 :
1541 0 : LWLockRelease(SerializableFinishedListLock);
1542 : }
1543 :
1544 : /*
1545 : * GetSafeSnapshot
1546 : * Obtain and register a snapshot for a READ ONLY DEFERRABLE
1547 : * transaction. Ensures that the snapshot is "safe", i.e. a
1548 : * read-only transaction running on it can execute serializably
1549 : * without further checks. This requires waiting for concurrent
1550 : * transactions to complete, and retrying with a new snapshot if
1551 : * one of them could possibly create a conflict.
1552 : *
1553 : * As with GetSerializableTransactionSnapshot (which this is a subroutine
1554 : * for), the passed-in Snapshot pointer should reference a static data
1555 : * area that can safely be passed to GetSnapshotData.
1556 : */
1557 : static Snapshot
1558 10 : GetSafeSnapshot(Snapshot origSnapshot)
1559 : {
1560 : Snapshot snapshot;
1561 :
1562 : Assert(XactReadOnly && XactDeferrable);
1563 :
1564 : while (true)
1565 : {
1566 : /*
1567 : * GetSerializableTransactionSnapshotInt is going to call
1568 : * GetSnapshotData, so we need to provide it the static snapshot area
1569 : * our caller passed to us. The pointer returned is actually the same
1570 : * one passed to it, but we avoid assuming that here.
1571 : */
1572 10 : snapshot = GetSerializableTransactionSnapshotInt(origSnapshot,
1573 : NULL, InvalidPid);
1574 :
1575 10 : if (MySerializableXact == InvalidSerializableXact)
1576 6 : return snapshot; /* no concurrent r/w xacts; it's safe */
1577 :
1578 4 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
1579 :
1580 : /*
1581 : * Wait for concurrent transactions to finish. Stop early if one of
1582 : * them marked us as conflicted.
1583 : */
1584 4 : MySerializableXact->flags |= SXACT_FLAG_DEFERRABLE_WAITING;
1585 10 : while (!(dlist_is_empty(&MySerializableXact->possibleUnsafeConflicts) ||
1586 6 : SxactIsROUnsafe(MySerializableXact)))
1587 : {
1588 6 : LWLockRelease(SerializableXactHashLock);
1589 6 : ProcWaitForSignal(WAIT_EVENT_SAFE_SNAPSHOT);
1590 6 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
1591 : }
1592 4 : MySerializableXact->flags &= ~SXACT_FLAG_DEFERRABLE_WAITING;
1593 :
1594 4 : if (!SxactIsROUnsafe(MySerializableXact))
1595 : {
1596 2 : LWLockRelease(SerializableXactHashLock);
1597 2 : break; /* success */
1598 : }
1599 :
1600 2 : LWLockRelease(SerializableXactHashLock);
1601 :
1602 : /* else, need to retry... */
1603 2 : ereport(DEBUG2,
1604 : (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
1605 : errmsg_internal("deferrable snapshot was unsafe; trying a new one")));
1606 2 : ReleasePredicateLocks(false, false);
1607 : }
1608 :
1609 : /*
1610 : * Now we have a safe snapshot, so we don't need to do any further checks.
1611 : */
1612 : Assert(SxactIsROSafe(MySerializableXact));
1613 2 : ReleasePredicateLocks(false, true);
1614 :
1615 2 : return snapshot;
1616 : }
1617 :
1618 : /*
1619 : * GetSafeSnapshotBlockingPids
1620 : * If the specified process is currently blocked in GetSafeSnapshot,
1621 : * write the process IDs of all processes that it is blocked by
1622 : * into the caller-supplied buffer output[]. The list is truncated at
1623 : * output_size, and the number of PIDs written into the buffer is
1624 : * returned. Returns zero if the given PID is not currently blocked
1625 : * in GetSafeSnapshot.
1626 : */
1627 : int
1628 982 : GetSafeSnapshotBlockingPids(int blocked_pid, int *output, int output_size)
1629 : {
1630 982 : int num_written = 0;
1631 : dlist_iter iter;
1632 982 : SERIALIZABLEXACT *blocking_sxact = NULL;
1633 :
1634 982 : LWLockAcquire(SerializableXactHashLock, LW_SHARED);
1635 :
1636 : /* Find blocked_pid's SERIALIZABLEXACT by linear search. */
1637 2388 : dlist_foreach(iter, &PredXact->activeList)
1638 : {
1639 1654 : SERIALIZABLEXACT *sxact =
1640 1654 : dlist_container(SERIALIZABLEXACT, xactLink, iter.cur);
1641 :
1642 1654 : if (sxact->pid == blocked_pid)
1643 : {
1644 248 : blocking_sxact = sxact;
1645 248 : break;
1646 : }
1647 : }
1648 :
1649 : /* Did we find it, and is it currently waiting in GetSafeSnapshot? */
1650 982 : if (blocking_sxact != NULL && SxactIsDeferrableWaiting(blocking_sxact))
1651 : {
1652 : /* Traverse the list of possible unsafe conflicts collecting PIDs. */
1653 4 : dlist_foreach(iter, &blocking_sxact->possibleUnsafeConflicts)
1654 : {
1655 4 : RWConflict possibleUnsafeConflict =
1656 4 : dlist_container(RWConflictData, inLink, iter.cur);
1657 :
1658 4 : output[num_written++] = possibleUnsafeConflict->sxactOut->pid;
1659 :
1660 4 : if (num_written >= output_size)
1661 4 : break;
1662 : }
1663 : }
1664 :
1665 982 : LWLockRelease(SerializableXactHashLock);
1666 :
1667 982 : return num_written;
1668 : }
1669 :
1670 : /*
1671 : * Acquire a snapshot that can be used for the current transaction.
1672 : *
1673 : * Make sure we have a SERIALIZABLEXACT reference in MySerializableXact.
1674 : * It should be current for this process and be contained in PredXact.
1675 : *
1676 : * The passed-in Snapshot pointer should reference a static data area that
1677 : * can safely be passed to GetSnapshotData. The return value is actually
1678 : * always this same pointer; no new snapshot data structure is allocated
1679 : * within this function.
1680 : */
1681 : Snapshot
1682 3280 : GetSerializableTransactionSnapshot(Snapshot snapshot)
1683 : {
1684 : Assert(IsolationIsSerializable());
1685 :
1686 : /*
1687 : * Can't use serializable mode while recovery is still active, as it is,
1688 : * for example, on a hot standby. We could get here despite the check in
1689 : * check_transaction_isolation() if default_transaction_isolation is set
1690 : * to serializable, so phrase the hint accordingly.
1691 : */
1692 3280 : if (RecoveryInProgress())
1693 0 : ereport(ERROR,
1694 : (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
1695 : errmsg("cannot use serializable mode in a hot standby"),
1696 : errdetail("\"default_transaction_isolation\" is set to \"serializable\"."),
1697 : errhint("You can use \"SET default_transaction_isolation = 'repeatable read'\" to change the default.")));
1698 :
1699 : /*
1700 : * A special optimization is available for SERIALIZABLE READ ONLY
1701 : * DEFERRABLE transactions -- we can wait for a suitable snapshot and
1702 : * thereby avoid all SSI overhead once it's running.
1703 : */
1704 3280 : if (XactReadOnly && XactDeferrable)
1705 8 : return GetSafeSnapshot(snapshot);
1706 :
1707 3272 : return GetSerializableTransactionSnapshotInt(snapshot,
1708 : NULL, InvalidPid);
1709 : }
1710 :
1711 : /*
1712 : * Import a snapshot to be used for the current transaction.
1713 : *
1714 : * This is nearly the same as GetSerializableTransactionSnapshot, except that
1715 : * we don't take a new snapshot, but rather use the data we're handed.
1716 : *
1717 : * The caller must have verified that the snapshot came from a serializable
1718 : * transaction; and if we're read-write, the source transaction must not be
1719 : * read-only.
1720 : */
1721 : void
1722 26 : SetSerializableTransactionSnapshot(Snapshot snapshot,
1723 : VirtualTransactionId *sourcevxid,
1724 : int sourcepid)
1725 : {
1726 : Assert(IsolationIsSerializable());
1727 :
1728 : /*
1729 : * If this is called by parallel.c in a parallel worker, we don't want to
1730 : * create a SERIALIZABLEXACT just yet because the leader's
1731 : * SERIALIZABLEXACT will be installed with AttachSerializableXact(). We
1732 : * also don't want to reject SERIALIZABLE READ ONLY DEFERRABLE in this
1733 : * case, because the leader has already determined that the snapshot it
1734 : * has passed us is safe. So there is nothing for us to do.
1735 : */
1736 26 : if (IsParallelWorker())
1737 26 : return;
1738 :
1739 : /*
1740 : * We do not allow SERIALIZABLE READ ONLY DEFERRABLE transactions to
1741 : * import snapshots, since there's no way to wait for a safe snapshot when
1742 : * we're using the snap we're told to. (XXX instead of throwing an error,
1743 : * we could just ignore the XactDeferrable flag?)
1744 : */
1745 0 : if (XactReadOnly && XactDeferrable)
1746 0 : ereport(ERROR,
1747 : (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
1748 : errmsg("a snapshot-importing transaction must not be READ ONLY DEFERRABLE")));
1749 :
1750 0 : (void) GetSerializableTransactionSnapshotInt(snapshot, sourcevxid,
1751 : sourcepid);
1752 : }
1753 :
1754 : /*
1755 : * Guts of GetSerializableTransactionSnapshot
1756 : *
1757 : * If sourcevxid is valid, this is actually an import operation and we should
1758 : * skip calling GetSnapshotData, because the snapshot contents are already
1759 : * loaded up. HOWEVER: to avoid race conditions, we must check that the
1760 : * source xact is still running after we acquire SerializableXactHashLock.
1761 : * We do that by calling ProcArrayInstallImportedXmin.
1762 : */
1763 : static Snapshot
1764 3282 : GetSerializableTransactionSnapshotInt(Snapshot snapshot,
1765 : VirtualTransactionId *sourcevxid,
1766 : int sourcepid)
1767 : {
1768 : PGPROC *proc;
1769 : VirtualTransactionId vxid;
1770 : SERIALIZABLEXACT *sxact,
1771 : *othersxact;
1772 :
1773 : /* We only do this for serializable transactions. Once. */
1774 : Assert(MySerializableXact == InvalidSerializableXact);
1775 :
1776 : Assert(!RecoveryInProgress());
1777 :
1778 : /*
1779 : * Since all parts of a serializable transaction must use the same
1780 : * snapshot, it is too late to establish one after a parallel operation
1781 : * has begun.
1782 : */
1783 3282 : if (IsInParallelMode())
1784 0 : elog(ERROR, "cannot establish serializable snapshot during a parallel operation");
1785 :
1786 3282 : proc = MyProc;
1787 : Assert(proc != NULL);
1788 3282 : GET_VXID_FROM_PGPROC(vxid, *proc);
1789 :
1790 : /*
1791 : * First we get the sxact structure, which may involve looping and access
1792 : * to the "finished" list to free a structure for use.
1793 : *
1794 : * We must hold SerializableXactHashLock when taking/checking the snapshot
1795 : * to avoid race conditions, for much the same reasons that
1796 : * GetSnapshotData takes the ProcArrayLock. Since we might have to
1797 : * release SerializableXactHashLock to call SummarizeOldestCommittedSxact,
1798 : * this means we have to create the sxact first, which is a bit annoying
1799 : * (in particular, an elog(ERROR) in procarray.c would cause us to leak
1800 : * the sxact). Consider refactoring to avoid this.
1801 : */
1802 : #ifdef TEST_SUMMARIZE_SERIAL
1803 : SummarizeOldestCommittedSxact();
1804 : #endif
1805 3282 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
1806 : do
1807 : {
1808 3282 : sxact = CreatePredXact();
1809 : /* If null, push out committed sxact to SLRU summary & retry. */
1810 3282 : if (!sxact)
1811 : {
1812 0 : LWLockRelease(SerializableXactHashLock);
1813 0 : SummarizeOldestCommittedSxact();
1814 0 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
1815 : }
1816 3282 : } while (!sxact);
1817 :
1818 : /* Get the snapshot, or check that it's safe to use */
1819 3282 : if (!sourcevxid)
1820 3282 : snapshot = GetSnapshotData(snapshot);
1821 0 : else if (!ProcArrayInstallImportedXmin(snapshot->xmin, sourcevxid))
1822 : {
1823 0 : ReleasePredXact(sxact);
1824 0 : LWLockRelease(SerializableXactHashLock);
1825 0 : ereport(ERROR,
1826 : (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
1827 : errmsg("could not import the requested snapshot"),
1828 : errdetail("The source process with PID %d is not running anymore.",
1829 : sourcepid)));
1830 : }
1831 :
1832 : /*
1833 : * If there are no serializable transactions which are not read-only, we
1834 : * can "opt out" of predicate locking and conflict checking for a
1835 : * read-only transaction.
1836 : *
1837 : * The reason this is safe is that a read-only transaction can only become
1838 : * part of a dangerous structure if it overlaps a writable transaction
1839 : * which in turn overlaps a writable transaction which committed before
1840 : * the read-only transaction started. A new writable transaction can
1841 : * overlap this one, but it can't meet the other condition of overlapping
1842 : * a transaction which committed before this one started.
1843 : */
1844 3282 : if (XactReadOnly && PredXact->WritableSxactCount == 0)
1845 : {
1846 222 : ReleasePredXact(sxact);
1847 222 : LWLockRelease(SerializableXactHashLock);
1848 222 : return snapshot;
1849 : }
1850 :
1851 : /* Initialize the structure. */
1852 3060 : sxact->vxid = vxid;
1853 3060 : sxact->SeqNo.lastCommitBeforeSnapshot = PredXact->LastSxactCommitSeqNo;
1854 3060 : sxact->prepareSeqNo = InvalidSerCommitSeqNo;
1855 3060 : sxact->commitSeqNo = InvalidSerCommitSeqNo;
1856 3060 : dlist_init(&(sxact->outConflicts));
1857 3060 : dlist_init(&(sxact->inConflicts));
1858 3060 : dlist_init(&(sxact->possibleUnsafeConflicts));
1859 3060 : sxact->topXid = GetTopTransactionIdIfAny();
1860 3060 : sxact->finishedBefore = InvalidTransactionId;
1861 3060 : sxact->xmin = snapshot->xmin;
1862 3060 : sxact->pid = MyProcPid;
1863 3060 : sxact->pgprocno = MyProcNumber;
1864 3060 : dlist_init(&sxact->predicateLocks);
1865 3060 : dlist_node_init(&sxact->finishedLink);
1866 3060 : sxact->flags = 0;
1867 3060 : if (XactReadOnly)
1868 : {
1869 : dlist_iter iter;
1870 :
1871 214 : sxact->flags |= SXACT_FLAG_READ_ONLY;
1872 :
1873 : /*
1874 : * Register all concurrent r/w transactions as possible conflicts; if
1875 : * all of them commit without any outgoing conflicts to earlier
1876 : * transactions then this snapshot can be deemed safe (and we can run
1877 : * without tracking predicate locks).
1878 : */
1879 938 : dlist_foreach(iter, &PredXact->activeList)
1880 : {
1881 724 : othersxact = dlist_container(SERIALIZABLEXACT, xactLink, iter.cur);
1882 :
1883 724 : if (!SxactIsCommitted(othersxact)
1884 484 : && !SxactIsDoomed(othersxact)
1885 484 : && !SxactIsReadOnly(othersxact))
1886 : {
1887 268 : SetPossibleUnsafeConflict(sxact, othersxact);
1888 : }
1889 : }
1890 :
1891 : /*
1892 : * If we didn't find any possibly unsafe conflicts because every
1893 : * uncommitted writable transaction turned out to be doomed, then we
1894 : * can "opt out" immediately. See comments above the earlier check
1895 : * for PredXact->WritableSxactCount == 0.
1896 : */
1897 214 : if (dlist_is_empty(&sxact->possibleUnsafeConflicts))
1898 : {
1899 0 : ReleasePredXact(sxact);
1900 0 : LWLockRelease(SerializableXactHashLock);
1901 0 : return snapshot;
1902 : }
1903 : }
1904 : else
1905 : {
1906 2846 : ++(PredXact->WritableSxactCount);
1907 : Assert(PredXact->WritableSxactCount <=
1908 : (MaxBackends + max_prepared_xacts));
1909 : }
1910 :
1911 : /* Maintain serializable global xmin info. */
1912 3060 : if (!TransactionIdIsValid(PredXact->SxactGlobalXmin))
1913 : {
1914 : Assert(PredXact->SxactGlobalXminCount == 0);
1915 1634 : PredXact->SxactGlobalXmin = snapshot->xmin;
1916 1634 : PredXact->SxactGlobalXminCount = 1;
1917 1634 : SerialSetActiveSerXmin(snapshot->xmin);
1918 : }
1919 1426 : else if (TransactionIdEquals(snapshot->xmin, PredXact->SxactGlobalXmin))
1920 : {
1921 : Assert(PredXact->SxactGlobalXminCount > 0);
1922 1344 : PredXact->SxactGlobalXminCount++;
1923 : }
1924 : else
1925 : {
1926 : Assert(TransactionIdFollows(snapshot->xmin, PredXact->SxactGlobalXmin));
1927 : }
1928 :
1929 3060 : MySerializableXact = sxact;
1930 3060 : MyXactDidWrite = false; /* haven't written anything yet */
1931 :
1932 3060 : LWLockRelease(SerializableXactHashLock);
1933 :
1934 3060 : CreateLocalPredicateLockHash();
1935 :
1936 3060 : return snapshot;
1937 : }
1938 :
1939 : static void
1940 3086 : CreateLocalPredicateLockHash(void)
1941 : {
1942 : HASHCTL hash_ctl;
1943 :
1944 : /* Initialize the backend-local hash table of parent locks */
1945 : Assert(LocalPredicateLockHash == NULL);
1946 3086 : hash_ctl.keysize = sizeof(PREDICATELOCKTARGETTAG);
1947 3086 : hash_ctl.entrysize = sizeof(LOCALPREDICATELOCK);
1948 3086 : LocalPredicateLockHash = hash_create("Local predicate lock",
1949 : max_predicate_locks_per_xact,
1950 : &hash_ctl,
1951 : HASH_ELEM | HASH_BLOBS);
1952 3086 : }
1953 :
1954 : /*
1955 : * Register the top level XID in SerializableXidHash.
1956 : * Also store it for easy reference in MySerializableXact.
1957 : */
1958 : void
1959 263434 : RegisterPredicateLockingXid(TransactionId xid)
1960 : {
1961 : SERIALIZABLEXIDTAG sxidtag;
1962 : SERIALIZABLEXID *sxid;
1963 : bool found;
1964 :
1965 : /*
1966 : * If we're not tracking predicate lock data for this transaction, we
1967 : * should ignore the request and return quickly.
1968 : */
1969 263434 : if (MySerializableXact == InvalidSerializableXact)
1970 260908 : return;
1971 :
1972 : /* We should have a valid XID and be at the top level. */
1973 : Assert(TransactionIdIsValid(xid));
1974 :
1975 2526 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
1976 :
1977 : /* This should only be done once per transaction. */
1978 : Assert(MySerializableXact->topXid == InvalidTransactionId);
1979 :
1980 2526 : MySerializableXact->topXid = xid;
1981 :
1982 2526 : sxidtag.xid = xid;
1983 2526 : sxid = (SERIALIZABLEXID *) hash_search(SerializableXidHash,
1984 : &sxidtag,
1985 : HASH_ENTER, &found);
1986 : Assert(!found);
1987 :
1988 : /* Initialize the structure. */
1989 2526 : sxid->myXact = MySerializableXact;
1990 2526 : LWLockRelease(SerializableXactHashLock);
1991 : }
1992 :
1993 :
1994 : /*
1995 : * Check whether there are any predicate locks held by any transaction
1996 : * for the page at the given block number.
1997 : *
1998 : * Note that the transaction may be completed but not yet subject to
1999 : * cleanup due to overlapping serializable transactions. This must
2000 : * return valid information regardless of transaction isolation level.
2001 : *
2002 : * Also note that this doesn't check for a conflicting relation lock,
2003 : * just a lock specifically on the given page.
2004 : *
2005 : * One use is to support proper behavior during GiST index vacuum.
2006 : */
2007 : bool
2008 0 : PageIsPredicateLocked(Relation relation, BlockNumber blkno)
2009 : {
2010 : PREDICATELOCKTARGETTAG targettag;
2011 : uint32 targettaghash;
2012 : LWLock *partitionLock;
2013 : PREDICATELOCKTARGET *target;
2014 :
2015 0 : SET_PREDICATELOCKTARGETTAG_PAGE(targettag,
2016 : relation->rd_locator.dbOid,
2017 : relation->rd_id,
2018 : blkno);
2019 :
2020 0 : targettaghash = PredicateLockTargetTagHashCode(&targettag);
2021 0 : partitionLock = PredicateLockHashPartitionLock(targettaghash);
2022 0 : LWLockAcquire(partitionLock, LW_SHARED);
2023 : target = (PREDICATELOCKTARGET *)
2024 0 : hash_search_with_hash_value(PredicateLockTargetHash,
2025 : &targettag, targettaghash,
2026 : HASH_FIND, NULL);
2027 0 : LWLockRelease(partitionLock);
2028 :
2029 0 : return (target != NULL);
2030 : }
2031 :
2032 :
2033 : /*
2034 : * Check whether a particular lock is held by this transaction.
2035 : *
2036 : * Important note: this function may return false even if the lock is
2037 : * being held, because it uses the local lock table which is not
2038 : * updated if another transaction modifies our lock list (e.g. to
2039 : * split an index page). It can also return true when a coarser
2040 : * granularity lock that covers this target is being held. Be careful
2041 : * to only use this function in circumstances where such errors are
2042 : * acceptable!
2043 : */
2044 : static bool
2045 154380 : PredicateLockExists(const PREDICATELOCKTARGETTAG *targettag)
2046 : {
2047 : LOCALPREDICATELOCK *lock;
2048 :
2049 : /* check local hash table */
2050 154380 : lock = (LOCALPREDICATELOCK *) hash_search(LocalPredicateLockHash,
2051 : targettag,
2052 : HASH_FIND, NULL);
2053 :
2054 154380 : if (!lock)
2055 60178 : return false;
2056 :
2057 : /*
2058 : * Found entry in the table, but still need to check whether it's actually
2059 : * held -- it could just be a parent of some held lock.
2060 : */
2061 94202 : return lock->held;
2062 : }
2063 :
2064 : /*
2065 : * Return the parent lock tag in the lock hierarchy: the next coarser
2066 : * lock that covers the provided tag.
2067 : *
2068 : * Returns true and sets *parent to the parent tag if one exists,
2069 : * returns false if none exists.
2070 : */
2071 : static bool
2072 90298 : GetParentPredicateLockTag(const PREDICATELOCKTARGETTAG *tag,
2073 : PREDICATELOCKTARGETTAG *parent)
2074 : {
2075 90298 : switch (GET_PREDICATELOCKTARGETTAG_TYPE(*tag))
2076 : {
2077 19600 : case PREDLOCKTAG_RELATION:
2078 : /* relation locks have no parent lock */
2079 19600 : return false;
2080 :
2081 16832 : case PREDLOCKTAG_PAGE:
2082 : /* parent lock is relation lock */
2083 16832 : SET_PREDICATELOCKTARGETTAG_RELATION(*parent,
2084 : GET_PREDICATELOCKTARGETTAG_DB(*tag),
2085 : GET_PREDICATELOCKTARGETTAG_RELATION(*tag));
2086 :
2087 16832 : return true;
2088 :
2089 53866 : case PREDLOCKTAG_TUPLE:
2090 : /* parent lock is page lock */
2091 53866 : SET_PREDICATELOCKTARGETTAG_PAGE(*parent,
2092 : GET_PREDICATELOCKTARGETTAG_DB(*tag),
2093 : GET_PREDICATELOCKTARGETTAG_RELATION(*tag),
2094 : GET_PREDICATELOCKTARGETTAG_PAGE(*tag));
2095 53866 : return true;
2096 : }
2097 :
2098 : /* not reachable */
2099 : Assert(false);
2100 0 : return false;
2101 : }
2102 :
2103 : /*
2104 : * Check whether the lock we are considering is already covered by a
2105 : * coarser lock for our transaction.
2106 : *
2107 : * Like PredicateLockExists, this function might return a false
2108 : * negative, but it will never return a false positive.
2109 : */
2110 : static bool
2111 52062 : CoarserLockCovers(const PREDICATELOCKTARGETTAG *newtargettag)
2112 : {
2113 : PREDICATELOCKTARGETTAG targettag,
2114 : parenttag;
2115 :
2116 52062 : targettag = *newtargettag;
2117 :
2118 : /* check parents iteratively until no more */
2119 62830 : while (GetParentPredicateLockTag(&targettag, &parenttag))
2120 : {
2121 54410 : targettag = parenttag;
2122 54410 : if (PredicateLockExists(&targettag))
2123 43642 : return true;
2124 : }
2125 :
2126 : /* no more parents to check; lock is not covered */
2127 8420 : return false;
2128 : }
2129 :
2130 : /*
2131 : * Remove the dummy entry from the predicate lock target hash, to free up some
2132 : * scratch space. The caller must be holding SerializablePredicateListLock,
2133 : * and must restore the entry with RestoreScratchTarget() before releasing the
2134 : * lock.
2135 : *
2136 : * If lockheld is true, the caller is already holding the partition lock
2137 : * of the partition containing the scratch entry.
2138 : */
2139 : static void
2140 294 : RemoveScratchTarget(bool lockheld)
2141 : {
2142 : bool found;
2143 :
2144 : Assert(LWLockHeldByMe(SerializablePredicateListLock));
2145 :
2146 294 : if (!lockheld)
2147 0 : LWLockAcquire(ScratchPartitionLock, LW_EXCLUSIVE);
2148 294 : hash_search_with_hash_value(PredicateLockTargetHash,
2149 : &ScratchTargetTag,
2150 : ScratchTargetTagHash,
2151 : HASH_REMOVE, &found);
2152 : Assert(found);
2153 294 : if (!lockheld)
2154 0 : LWLockRelease(ScratchPartitionLock);
2155 294 : }
2156 :
2157 : /*
2158 : * Re-insert the dummy entry in predicate lock target hash.
2159 : */
2160 : static void
2161 294 : RestoreScratchTarget(bool lockheld)
2162 : {
2163 : bool found;
2164 :
2165 : Assert(LWLockHeldByMe(SerializablePredicateListLock));
2166 :
2167 294 : if (!lockheld)
2168 0 : LWLockAcquire(ScratchPartitionLock, LW_EXCLUSIVE);
2169 294 : hash_search_with_hash_value(PredicateLockTargetHash,
2170 : &ScratchTargetTag,
2171 : ScratchTargetTagHash,
2172 : HASH_ENTER, &found);
2173 : Assert(!found);
2174 294 : if (!lockheld)
2175 0 : LWLockRelease(ScratchPartitionLock);
2176 294 : }
2177 :
2178 : /*
2179 : * Check whether the list of related predicate locks is empty for a
2180 : * predicate lock target, and remove the target if it is.
2181 : */
2182 : static void
2183 8408 : RemoveTargetIfNoLongerUsed(PREDICATELOCKTARGET *target, uint32 targettaghash)
2184 : {
2185 : PREDICATELOCKTARGET *rmtarget PG_USED_FOR_ASSERTS_ONLY;
2186 :
2187 : Assert(LWLockHeldByMe(SerializablePredicateListLock));
2188 :
2189 : /* Can't remove it until no locks at this target. */
2190 8408 : if (!dlist_is_empty(&target->predicateLocks))
2191 1922 : return;
2192 :
2193 : /* Actually remove the target. */
2194 6486 : rmtarget = hash_search_with_hash_value(PredicateLockTargetHash,
2195 6486 : &target->tag,
2196 : targettaghash,
2197 : HASH_REMOVE, NULL);
2198 : Assert(rmtarget == target);
2199 : }
2200 :
2201 : /*
2202 : * Delete child target locks owned by this process.
2203 : * This implementation is assuming that the usage of each target tag field
2204 : * is uniform. No need to make this hard if we don't have to.
2205 : *
2206 : * We acquire an LWLock in the case of parallel mode, because worker
2207 : * backends have access to the leader's SERIALIZABLEXACT. Otherwise,
2208 : * we aren't acquiring LWLocks for the predicate lock or lock
2209 : * target structures associated with this transaction unless we're going
2210 : * to modify them, because no other process is permitted to modify our
2211 : * locks.
2212 : */
2213 : static void
2214 4688 : DeleteChildTargetLocks(const PREDICATELOCKTARGETTAG *newtargettag)
2215 : {
2216 : SERIALIZABLEXACT *sxact;
2217 : PREDICATELOCK *predlock;
2218 : dlist_mutable_iter iter;
2219 :
2220 4688 : LWLockAcquire(SerializablePredicateListLock, LW_SHARED);
2221 4688 : sxact = MySerializableXact;
2222 4688 : if (IsInParallelMode())
2223 22 : LWLockAcquire(&sxact->perXactPredicateListLock, LW_EXCLUSIVE);
2224 :
2225 15532 : dlist_foreach_modify(iter, &sxact->predicateLocks)
2226 : {
2227 : PREDICATELOCKTAG oldlocktag;
2228 : PREDICATELOCKTARGET *oldtarget;
2229 : PREDICATELOCKTARGETTAG oldtargettag;
2230 :
2231 10844 : predlock = dlist_container(PREDICATELOCK, xactLink, iter.cur);
2232 :
2233 10844 : oldlocktag = predlock->tag;
2234 : Assert(oldlocktag.myXact == sxact);
2235 10844 : oldtarget = oldlocktag.myTarget;
2236 10844 : oldtargettag = oldtarget->tag;
2237 :
2238 10844 : if (TargetTagIsCoveredBy(oldtargettag, *newtargettag))
2239 : {
2240 : uint32 oldtargettaghash;
2241 : LWLock *partitionLock;
2242 : PREDICATELOCK *rmpredlock PG_USED_FOR_ASSERTS_ONLY;
2243 :
2244 1998 : oldtargettaghash = PredicateLockTargetTagHashCode(&oldtargettag);
2245 1998 : partitionLock = PredicateLockHashPartitionLock(oldtargettaghash);
2246 :
2247 1998 : LWLockAcquire(partitionLock, LW_EXCLUSIVE);
2248 :
2249 1998 : dlist_delete(&predlock->xactLink);
2250 1998 : dlist_delete(&predlock->targetLink);
2251 1998 : rmpredlock = hash_search_with_hash_value
2252 : (PredicateLockHash,
2253 : &oldlocktag,
2254 1998 : PredicateLockHashCodeFromTargetHashCode(&oldlocktag,
2255 : oldtargettaghash),
2256 : HASH_REMOVE, NULL);
2257 : Assert(rmpredlock == predlock);
2258 :
2259 1998 : RemoveTargetIfNoLongerUsed(oldtarget, oldtargettaghash);
2260 :
2261 1998 : LWLockRelease(partitionLock);
2262 :
2263 1998 : DecrementParentLocks(&oldtargettag);
2264 : }
2265 : }
2266 4688 : if (IsInParallelMode())
2267 22 : LWLockRelease(&sxact->perXactPredicateListLock);
2268 4688 : LWLockRelease(SerializablePredicateListLock);
2269 4688 : }
2270 :
2271 : /*
2272 : * Returns the promotion limit for a given predicate lock target. This is the
2273 : * max number of descendant locks allowed before promoting to the specified
2274 : * tag. Note that the limit includes non-direct descendants (e.g., both tuples
2275 : * and pages for a relation lock).
2276 : *
2277 : * Currently the default limit is 2 for a page lock, and half of the value of
2278 : * max_pred_locks_per_transaction - 1 for a relation lock, to match behavior
2279 : * of earlier releases when upgrading.
2280 : *
2281 : * TODO SSI: We should probably add additional GUCs to allow a maximum ratio
2282 : * of page and tuple locks based on the pages in a relation, and the maximum
2283 : * ratio of tuple locks to tuples in a page. This would provide more
2284 : * generally "balanced" allocation of locks to where they are most useful,
2285 : * while still allowing the absolute numbers to prevent one relation from
2286 : * tying up all predicate lock resources.
2287 : */
2288 : static int
2289 10768 : MaxPredicateChildLocks(const PREDICATELOCKTARGETTAG *tag)
2290 : {
2291 10768 : switch (GET_PREDICATELOCKTARGETTAG_TYPE(*tag))
2292 : {
2293 7036 : case PREDLOCKTAG_RELATION:
2294 7036 : return max_predicate_locks_per_relation < 0
2295 : ? (max_predicate_locks_per_xact
2296 7036 : / (-max_predicate_locks_per_relation)) - 1
2297 7036 : : max_predicate_locks_per_relation;
2298 :
2299 3732 : case PREDLOCKTAG_PAGE:
2300 3732 : return max_predicate_locks_per_page;
2301 :
2302 0 : case PREDLOCKTAG_TUPLE:
2303 :
2304 : /*
2305 : * not reachable: nothing is finer-granularity than a tuple, so we
2306 : * should never try to promote to it.
2307 : */
2308 : Assert(false);
2309 0 : return 0;
2310 : }
2311 :
2312 : /* not reachable */
2313 : Assert(false);
2314 0 : return 0;
2315 : }
2316 :
2317 : /*
2318 : * For all ancestors of a newly-acquired predicate lock, increment
2319 : * their child count in the parent hash table. If any of them have
2320 : * more descendants than their promotion threshold, acquire the
2321 : * coarsest such lock.
2322 : *
2323 : * Returns true if a parent lock was acquired and false otherwise.
2324 : */
2325 : static bool
2326 8420 : CheckAndPromotePredicateLockRequest(const PREDICATELOCKTARGETTAG *reqtag)
2327 : {
2328 : PREDICATELOCKTARGETTAG targettag,
2329 : nexttag,
2330 : promotiontag;
2331 : LOCALPREDICATELOCK *parentlock;
2332 : bool found,
2333 : promote;
2334 :
2335 8420 : promote = false;
2336 :
2337 8420 : targettag = *reqtag;
2338 :
2339 : /* check parents iteratively */
2340 19188 : while (GetParentPredicateLockTag(&targettag, &nexttag))
2341 : {
2342 10768 : targettag = nexttag;
2343 10768 : parentlock = (LOCALPREDICATELOCK *) hash_search(LocalPredicateLockHash,
2344 : &targettag,
2345 : HASH_ENTER,
2346 : &found);
2347 10768 : if (!found)
2348 : {
2349 6646 : parentlock->held = false;
2350 6646 : parentlock->childLocks = 1;
2351 : }
2352 : else
2353 4122 : parentlock->childLocks++;
2354 :
2355 10768 : if (parentlock->childLocks >
2356 10768 : MaxPredicateChildLocks(&targettag))
2357 : {
2358 : /*
2359 : * We should promote to this parent lock. Continue to check its
2360 : * ancestors, however, both to get their child counts right and to
2361 : * check whether we should just go ahead and promote to one of
2362 : * them.
2363 : */
2364 666 : promotiontag = targettag;
2365 666 : promote = true;
2366 : }
2367 : }
2368 :
2369 8420 : if (promote)
2370 : {
2371 : /* acquire coarsest ancestor eligible for promotion */
2372 666 : PredicateLockAcquire(&promotiontag);
2373 666 : return true;
2374 : }
2375 : else
2376 7754 : return false;
2377 : }
2378 :
2379 : /*
2380 : * When releasing a lock, decrement the child count on all ancestor
2381 : * locks.
2382 : *
2383 : * This is called only when releasing a lock via
2384 : * DeleteChildTargetLocks (i.e. when a lock becomes redundant because
2385 : * we've acquired its parent, possibly due to promotion) or when a new
2386 : * MVCC write lock makes the predicate lock unnecessary. There's no
2387 : * point in calling it when locks are released at transaction end, as
2388 : * this information is no longer needed.
2389 : */
2390 : static void
2391 2760 : DecrementParentLocks(const PREDICATELOCKTARGETTAG *targettag)
2392 : {
2393 : PREDICATELOCKTARGETTAG parenttag,
2394 : nexttag;
2395 :
2396 2760 : parenttag = *targettag;
2397 :
2398 8280 : while (GetParentPredicateLockTag(&parenttag, &nexttag))
2399 : {
2400 : uint32 targettaghash;
2401 : LOCALPREDICATELOCK *parentlock,
2402 : *rmlock PG_USED_FOR_ASSERTS_ONLY;
2403 :
2404 5520 : parenttag = nexttag;
2405 5520 : targettaghash = PredicateLockTargetTagHashCode(&parenttag);
2406 : parentlock = (LOCALPREDICATELOCK *)
2407 5520 : hash_search_with_hash_value(LocalPredicateLockHash,
2408 : &parenttag, targettaghash,
2409 : HASH_FIND, NULL);
2410 :
2411 : /*
2412 : * There's a small chance the parent lock doesn't exist in the lock
2413 : * table. This can happen if we prematurely removed it because an
2414 : * index split caused the child refcount to be off.
2415 : */
2416 5520 : if (parentlock == NULL)
2417 0 : continue;
2418 :
2419 5520 : parentlock->childLocks--;
2420 :
2421 : /*
2422 : * Under similar circumstances the parent lock's refcount might be
2423 : * zero. This only happens if we're holding that lock (otherwise we
2424 : * would have removed the entry).
2425 : */
2426 5520 : if (parentlock->childLocks < 0)
2427 : {
2428 : Assert(parentlock->held);
2429 0 : parentlock->childLocks = 0;
2430 : }
2431 :
2432 5520 : if ((parentlock->childLocks == 0) && (!parentlock->held))
2433 : {
2434 : rmlock = (LOCALPREDICATELOCK *)
2435 1500 : hash_search_with_hash_value(LocalPredicateLockHash,
2436 : &parenttag, targettaghash,
2437 : HASH_REMOVE, NULL);
2438 : Assert(rmlock == parentlock);
2439 : }
2440 : }
2441 2760 : }
2442 :
2443 : /*
2444 : * Indicate that a predicate lock on the given target is held by the
2445 : * specified transaction. Has no effect if the lock is already held.
2446 : *
2447 : * This updates the lock table and the sxact's lock list, and creates
2448 : * the lock target if necessary, but does *not* do anything related to
2449 : * granularity promotion or the local lock table. See
2450 : * PredicateLockAcquire for that.
2451 : */
2452 : static void
2453 8420 : CreatePredicateLock(const PREDICATELOCKTARGETTAG *targettag,
2454 : uint32 targettaghash,
2455 : SERIALIZABLEXACT *sxact)
2456 : {
2457 : PREDICATELOCKTARGET *target;
2458 : PREDICATELOCKTAG locktag;
2459 : PREDICATELOCK *lock;
2460 : LWLock *partitionLock;
2461 : bool found;
2462 :
2463 8420 : partitionLock = PredicateLockHashPartitionLock(targettaghash);
2464 :
2465 8420 : LWLockAcquire(SerializablePredicateListLock, LW_SHARED);
2466 8420 : if (IsInParallelMode())
2467 32 : LWLockAcquire(&sxact->perXactPredicateListLock, LW_EXCLUSIVE);
2468 8420 : LWLockAcquire(partitionLock, LW_EXCLUSIVE);
2469 :
2470 : /* Make sure that the target is represented. */
2471 : target = (PREDICATELOCKTARGET *)
2472 8420 : hash_search_with_hash_value(PredicateLockTargetHash,
2473 : targettag, targettaghash,
2474 : HASH_ENTER_NULL, &found);
2475 8420 : if (!target)
2476 0 : ereport(ERROR,
2477 : (errcode(ERRCODE_OUT_OF_MEMORY),
2478 : errmsg("out of shared memory"),
2479 : errhint("You might need to increase \"%s\".", "max_pred_locks_per_transaction")));
2480 8420 : if (!found)
2481 6486 : dlist_init(&target->predicateLocks);
2482 :
2483 : /* We've got the sxact and target, make sure they're joined. */
2484 8420 : locktag.myTarget = target;
2485 8420 : locktag.myXact = sxact;
2486 : lock = (PREDICATELOCK *)
2487 8420 : hash_search_with_hash_value(PredicateLockHash, &locktag,
2488 8420 : PredicateLockHashCodeFromTargetHashCode(&locktag, targettaghash),
2489 : HASH_ENTER_NULL, &found);
2490 8420 : if (!lock)
2491 0 : ereport(ERROR,
2492 : (errcode(ERRCODE_OUT_OF_MEMORY),
2493 : errmsg("out of shared memory"),
2494 : errhint("You might need to increase \"%s\".", "max_pred_locks_per_transaction")));
2495 :
2496 8420 : if (!found)
2497 : {
2498 8408 : dlist_push_tail(&target->predicateLocks, &lock->targetLink);
2499 8408 : dlist_push_tail(&sxact->predicateLocks, &lock->xactLink);
2500 8408 : lock->commitSeqNo = InvalidSerCommitSeqNo;
2501 : }
2502 :
2503 8420 : LWLockRelease(partitionLock);
2504 8420 : if (IsInParallelMode())
2505 32 : LWLockRelease(&sxact->perXactPredicateListLock);
2506 8420 : LWLockRelease(SerializablePredicateListLock);
2507 8420 : }
2508 :
2509 : /*
2510 : * Acquire a predicate lock on the specified target for the current
2511 : * connection if not already held. This updates the local lock table
2512 : * and uses it to implement granularity promotion. It will consolidate
2513 : * multiple locks into a coarser lock if warranted, and will release
2514 : * any finer-grained locks covered by the new one.
2515 : */
2516 : static void
2517 52462 : PredicateLockAcquire(const PREDICATELOCKTARGETTAG *targettag)
2518 : {
2519 : uint32 targettaghash;
2520 : bool found;
2521 : LOCALPREDICATELOCK *locallock;
2522 :
2523 : /* Do we have the lock already, or a covering lock? */
2524 52462 : if (PredicateLockExists(targettag))
2525 44042 : return;
2526 :
2527 52062 : if (CoarserLockCovers(targettag))
2528 43642 : return;
2529 :
2530 : /* the same hash and LW lock apply to the lock target and the local lock. */
2531 8420 : targettaghash = PredicateLockTargetTagHashCode(targettag);
2532 :
2533 : /* Acquire lock in local table */
2534 : locallock = (LOCALPREDICATELOCK *)
2535 8420 : hash_search_with_hash_value(LocalPredicateLockHash,
2536 : targettag, targettaghash,
2537 : HASH_ENTER, &found);
2538 8420 : locallock->held = true;
2539 8420 : if (!found)
2540 7754 : locallock->childLocks = 0;
2541 :
2542 : /* Actually create the lock */
2543 8420 : CreatePredicateLock(targettag, targettaghash, MySerializableXact);
2544 :
2545 : /*
2546 : * Lock has been acquired. Check whether it should be promoted to a
2547 : * coarser granularity, or whether there are finer-granularity locks to
2548 : * clean up.
2549 : */
2550 8420 : if (CheckAndPromotePredicateLockRequest(targettag))
2551 : {
2552 : /*
2553 : * Lock request was promoted to a coarser-granularity lock, and that
2554 : * lock was acquired. It will delete this lock and any of its
2555 : * children, so we're done.
2556 : */
2557 : }
2558 : else
2559 : {
2560 : /* Clean up any finer-granularity locks */
2561 7754 : if (GET_PREDICATELOCKTARGETTAG_TYPE(*targettag) != PREDLOCKTAG_TUPLE)
2562 4688 : DeleteChildTargetLocks(targettag);
2563 : }
2564 : }
2565 :
2566 :
2567 : /*
2568 : * PredicateLockRelation
2569 : *
2570 : * Gets a predicate lock at the relation level.
2571 : * Skip if not in full serializable transaction isolation level.
2572 : * Skip if this is a temporary table.
2573 : * Clear any finer-grained predicate locks this session has on the relation.
2574 : */
2575 : void
2576 734488 : PredicateLockRelation(Relation relation, Snapshot snapshot)
2577 : {
2578 : PREDICATELOCKTARGETTAG tag;
2579 :
2580 734488 : if (!SerializationNeededForRead(relation, snapshot))
2581 733062 : return;
2582 :
2583 1426 : SET_PREDICATELOCKTARGETTAG_RELATION(tag,
2584 : relation->rd_locator.dbOid,
2585 : relation->rd_id);
2586 1426 : PredicateLockAcquire(&tag);
2587 : }
2588 :
2589 : /*
2590 : * PredicateLockPage
2591 : *
2592 : * Gets a predicate lock at the page level.
2593 : * Skip if not in full serializable transaction isolation level.
2594 : * Skip if this is a temporary table.
2595 : * Skip if a coarser predicate lock already covers this page.
2596 : * Clear any finer-grained predicate locks this session has on the relation.
2597 : */
2598 : void
2599 18522248 : PredicateLockPage(Relation relation, BlockNumber blkno, Snapshot snapshot)
2600 : {
2601 : PREDICATELOCKTARGETTAG tag;
2602 :
2603 18522248 : if (!SerializationNeededForRead(relation, snapshot))
2604 18519386 : return;
2605 :
2606 2862 : SET_PREDICATELOCKTARGETTAG_PAGE(tag,
2607 : relation->rd_locator.dbOid,
2608 : relation->rd_id,
2609 : blkno);
2610 2862 : PredicateLockAcquire(&tag);
2611 : }
2612 :
2613 : /*
2614 : * PredicateLockTID
2615 : *
2616 : * Gets a predicate lock at the tuple level.
2617 : * Skip if not in full serializable transaction isolation level.
2618 : * Skip if this is a temporary table.
2619 : */
2620 : void
2621 33003540 : PredicateLockTID(Relation relation, ItemPointer tid, Snapshot snapshot,
2622 : TransactionId tuple_xid)
2623 : {
2624 : PREDICATELOCKTARGETTAG tag;
2625 :
2626 33003540 : if (!SerializationNeededForRead(relation, snapshot))
2627 32956032 : return;
2628 :
2629 : /*
2630 : * Return if this xact wrote it.
2631 : */
2632 47508 : if (relation->rd_index == NULL)
2633 : {
2634 : /* If we wrote it; we already have a write lock. */
2635 47508 : if (TransactionIdIsCurrentTransactionId(tuple_xid))
2636 0 : return;
2637 : }
2638 :
2639 : /*
2640 : * Do quick-but-not-definitive test for a relation lock first. This will
2641 : * never cause a return when the relation is *not* locked, but will
2642 : * occasionally let the check continue when there really *is* a relation
2643 : * level lock.
2644 : */
2645 47508 : SET_PREDICATELOCKTARGETTAG_RELATION(tag,
2646 : relation->rd_locator.dbOid,
2647 : relation->rd_id);
2648 47508 : if (PredicateLockExists(&tag))
2649 0 : return;
2650 :
2651 47508 : SET_PREDICATELOCKTARGETTAG_TUPLE(tag,
2652 : relation->rd_locator.dbOid,
2653 : relation->rd_id,
2654 : ItemPointerGetBlockNumber(tid),
2655 : ItemPointerGetOffsetNumber(tid));
2656 47508 : PredicateLockAcquire(&tag);
2657 : }
2658 :
2659 :
2660 : /*
2661 : * DeleteLockTarget
2662 : *
2663 : * Remove a predicate lock target along with any locks held for it.
2664 : *
2665 : * Caller must hold SerializablePredicateListLock and the
2666 : * appropriate hash partition lock for the target.
2667 : */
2668 : static void
2669 0 : DeleteLockTarget(PREDICATELOCKTARGET *target, uint32 targettaghash)
2670 : {
2671 : dlist_mutable_iter iter;
2672 :
2673 : Assert(LWLockHeldByMeInMode(SerializablePredicateListLock,
2674 : LW_EXCLUSIVE));
2675 : Assert(LWLockHeldByMe(PredicateLockHashPartitionLock(targettaghash)));
2676 :
2677 0 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
2678 :
2679 0 : dlist_foreach_modify(iter, &target->predicateLocks)
2680 : {
2681 0 : PREDICATELOCK *predlock =
2682 0 : dlist_container(PREDICATELOCK, targetLink, iter.cur);
2683 : bool found;
2684 :
2685 0 : dlist_delete(&(predlock->xactLink));
2686 0 : dlist_delete(&(predlock->targetLink));
2687 :
2688 0 : hash_search_with_hash_value
2689 : (PredicateLockHash,
2690 0 : &predlock->tag,
2691 0 : PredicateLockHashCodeFromTargetHashCode(&predlock->tag,
2692 : targettaghash),
2693 : HASH_REMOVE, &found);
2694 : Assert(found);
2695 : }
2696 0 : LWLockRelease(SerializableXactHashLock);
2697 :
2698 : /* Remove the target itself, if possible. */
2699 0 : RemoveTargetIfNoLongerUsed(target, targettaghash);
2700 0 : }
2701 :
2702 :
2703 : /*
2704 : * TransferPredicateLocksToNewTarget
2705 : *
2706 : * Move or copy all the predicate locks for a lock target, for use by
2707 : * index page splits/combines and other things that create or replace
2708 : * lock targets. If 'removeOld' is true, the old locks and the target
2709 : * will be removed.
2710 : *
2711 : * Returns true on success, or false if we ran out of shared memory to
2712 : * allocate the new target or locks. Guaranteed to always succeed if
2713 : * removeOld is set (by using the scratch entry in PredicateLockTargetHash
2714 : * for scratch space).
2715 : *
2716 : * Warning: the "removeOld" option should be used only with care,
2717 : * because this function does not (indeed, can not) update other
2718 : * backends' LocalPredicateLockHash. If we are only adding new
2719 : * entries, this is not a problem: the local lock table is used only
2720 : * as a hint, so missing entries for locks that are held are
2721 : * OK. Having entries for locks that are no longer held, as can happen
2722 : * when using "removeOld", is not in general OK. We can only use it
2723 : * safely when replacing a lock with a coarser-granularity lock that
2724 : * covers it, or if we are absolutely certain that no one will need to
2725 : * refer to that lock in the future.
2726 : *
2727 : * Caller must hold SerializablePredicateListLock exclusively.
2728 : */
2729 : static bool
2730 26 : TransferPredicateLocksToNewTarget(PREDICATELOCKTARGETTAG oldtargettag,
2731 : PREDICATELOCKTARGETTAG newtargettag,
2732 : bool removeOld)
2733 : {
2734 : uint32 oldtargettaghash;
2735 : LWLock *oldpartitionLock;
2736 : PREDICATELOCKTARGET *oldtarget;
2737 : uint32 newtargettaghash;
2738 : LWLock *newpartitionLock;
2739 : bool found;
2740 26 : bool outOfShmem = false;
2741 :
2742 : Assert(LWLockHeldByMeInMode(SerializablePredicateListLock,
2743 : LW_EXCLUSIVE));
2744 :
2745 26 : oldtargettaghash = PredicateLockTargetTagHashCode(&oldtargettag);
2746 26 : newtargettaghash = PredicateLockTargetTagHashCode(&newtargettag);
2747 26 : oldpartitionLock = PredicateLockHashPartitionLock(oldtargettaghash);
2748 26 : newpartitionLock = PredicateLockHashPartitionLock(newtargettaghash);
2749 :
2750 26 : if (removeOld)
2751 : {
2752 : /*
2753 : * Remove the dummy entry to give us scratch space, so we know we'll
2754 : * be able to create the new lock target.
2755 : */
2756 0 : RemoveScratchTarget(false);
2757 : }
2758 :
2759 : /*
2760 : * We must get the partition locks in ascending sequence to avoid
2761 : * deadlocks. If old and new partitions are the same, we must request the
2762 : * lock only once.
2763 : */
2764 26 : if (oldpartitionLock < newpartitionLock)
2765 : {
2766 14 : LWLockAcquire(oldpartitionLock,
2767 14 : (removeOld ? LW_EXCLUSIVE : LW_SHARED));
2768 14 : LWLockAcquire(newpartitionLock, LW_EXCLUSIVE);
2769 : }
2770 12 : else if (oldpartitionLock > newpartitionLock)
2771 : {
2772 10 : LWLockAcquire(newpartitionLock, LW_EXCLUSIVE);
2773 10 : LWLockAcquire(oldpartitionLock,
2774 10 : (removeOld ? LW_EXCLUSIVE : LW_SHARED));
2775 : }
2776 : else
2777 2 : LWLockAcquire(newpartitionLock, LW_EXCLUSIVE);
2778 :
2779 : /*
2780 : * Look for the old target. If not found, that's OK; no predicate locks
2781 : * are affected, so we can just clean up and return. If it does exist,
2782 : * walk its list of predicate locks and move or copy them to the new
2783 : * target.
2784 : */
2785 26 : oldtarget = hash_search_with_hash_value(PredicateLockTargetHash,
2786 : &oldtargettag,
2787 : oldtargettaghash,
2788 : HASH_FIND, NULL);
2789 :
2790 26 : if (oldtarget)
2791 : {
2792 : PREDICATELOCKTARGET *newtarget;
2793 : PREDICATELOCKTAG newpredlocktag;
2794 : dlist_mutable_iter iter;
2795 :
2796 0 : newtarget = hash_search_with_hash_value(PredicateLockTargetHash,
2797 : &newtargettag,
2798 : newtargettaghash,
2799 : HASH_ENTER_NULL, &found);
2800 :
2801 0 : if (!newtarget)
2802 : {
2803 : /* Failed to allocate due to insufficient shmem */
2804 0 : outOfShmem = true;
2805 0 : goto exit;
2806 : }
2807 :
2808 : /* If we created a new entry, initialize it */
2809 0 : if (!found)
2810 0 : dlist_init(&newtarget->predicateLocks);
2811 :
2812 0 : newpredlocktag.myTarget = newtarget;
2813 :
2814 : /*
2815 : * Loop through all the locks on the old target, replacing them with
2816 : * locks on the new target.
2817 : */
2818 0 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
2819 :
2820 0 : dlist_foreach_modify(iter, &oldtarget->predicateLocks)
2821 : {
2822 0 : PREDICATELOCK *oldpredlock =
2823 0 : dlist_container(PREDICATELOCK, targetLink, iter.cur);
2824 : PREDICATELOCK *newpredlock;
2825 0 : SerCommitSeqNo oldCommitSeqNo = oldpredlock->commitSeqNo;
2826 :
2827 0 : newpredlocktag.myXact = oldpredlock->tag.myXact;
2828 :
2829 0 : if (removeOld)
2830 : {
2831 0 : dlist_delete(&(oldpredlock->xactLink));
2832 0 : dlist_delete(&(oldpredlock->targetLink));
2833 :
2834 0 : hash_search_with_hash_value
2835 : (PredicateLockHash,
2836 0 : &oldpredlock->tag,
2837 0 : PredicateLockHashCodeFromTargetHashCode(&oldpredlock->tag,
2838 : oldtargettaghash),
2839 : HASH_REMOVE, &found);
2840 : Assert(found);
2841 : }
2842 :
2843 : newpredlock = (PREDICATELOCK *)
2844 0 : hash_search_with_hash_value(PredicateLockHash,
2845 : &newpredlocktag,
2846 0 : PredicateLockHashCodeFromTargetHashCode(&newpredlocktag,
2847 : newtargettaghash),
2848 : HASH_ENTER_NULL,
2849 : &found);
2850 0 : if (!newpredlock)
2851 : {
2852 : /* Out of shared memory. Undo what we've done so far. */
2853 0 : LWLockRelease(SerializableXactHashLock);
2854 0 : DeleteLockTarget(newtarget, newtargettaghash);
2855 0 : outOfShmem = true;
2856 0 : goto exit;
2857 : }
2858 0 : if (!found)
2859 : {
2860 0 : dlist_push_tail(&(newtarget->predicateLocks),
2861 : &(newpredlock->targetLink));
2862 0 : dlist_push_tail(&(newpredlocktag.myXact->predicateLocks),
2863 : &(newpredlock->xactLink));
2864 0 : newpredlock->commitSeqNo = oldCommitSeqNo;
2865 : }
2866 : else
2867 : {
2868 0 : if (newpredlock->commitSeqNo < oldCommitSeqNo)
2869 0 : newpredlock->commitSeqNo = oldCommitSeqNo;
2870 : }
2871 :
2872 : Assert(newpredlock->commitSeqNo != 0);
2873 : Assert((newpredlock->commitSeqNo == InvalidSerCommitSeqNo)
2874 : || (newpredlock->tag.myXact == OldCommittedSxact));
2875 : }
2876 0 : LWLockRelease(SerializableXactHashLock);
2877 :
2878 0 : if (removeOld)
2879 : {
2880 : Assert(dlist_is_empty(&oldtarget->predicateLocks));
2881 0 : RemoveTargetIfNoLongerUsed(oldtarget, oldtargettaghash);
2882 : }
2883 : }
2884 :
2885 :
2886 26 : exit:
2887 : /* Release partition locks in reverse order of acquisition. */
2888 26 : if (oldpartitionLock < newpartitionLock)
2889 : {
2890 14 : LWLockRelease(newpartitionLock);
2891 14 : LWLockRelease(oldpartitionLock);
2892 : }
2893 12 : else if (oldpartitionLock > newpartitionLock)
2894 : {
2895 10 : LWLockRelease(oldpartitionLock);
2896 10 : LWLockRelease(newpartitionLock);
2897 : }
2898 : else
2899 2 : LWLockRelease(newpartitionLock);
2900 :
2901 26 : if (removeOld)
2902 : {
2903 : /* We shouldn't run out of memory if we're moving locks */
2904 : Assert(!outOfShmem);
2905 :
2906 : /* Put the scratch entry back */
2907 0 : RestoreScratchTarget(false);
2908 : }
2909 :
2910 26 : return !outOfShmem;
2911 : }
2912 :
2913 : /*
2914 : * Drop all predicate locks of any granularity from the specified relation,
2915 : * which can be a heap relation or an index relation. If 'transfer' is true,
2916 : * acquire a relation lock on the heap for any transactions with any lock(s)
2917 : * on the specified relation.
2918 : *
2919 : * This requires grabbing a lot of LW locks and scanning the entire lock
2920 : * target table for matches. That makes this more expensive than most
2921 : * predicate lock management functions, but it will only be called for DDL
2922 : * type commands that are expensive anyway, and there are fast returns when
2923 : * no serializable transactions are active or the relation is temporary.
2924 : *
2925 : * We don't use the TransferPredicateLocksToNewTarget function because it
2926 : * acquires its own locks on the partitions of the two targets involved,
2927 : * and we'll already be holding all partition locks.
2928 : *
2929 : * We can't throw an error from here, because the call could be from a
2930 : * transaction which is not serializable.
2931 : *
2932 : * NOTE: This is currently only called with transfer set to true, but that may
2933 : * change. If we decide to clean up the locks from a table on commit of a
2934 : * transaction which executed DROP TABLE, the false condition will be useful.
2935 : */
2936 : static void
2937 33902 : DropAllPredicateLocksFromTable(Relation relation, bool transfer)
2938 : {
2939 : HASH_SEQ_STATUS seqstat;
2940 : PREDICATELOCKTARGET *oldtarget;
2941 : PREDICATELOCKTARGET *heaptarget;
2942 : Oid dbId;
2943 : Oid relId;
2944 : Oid heapId;
2945 : int i;
2946 : bool isIndex;
2947 : bool found;
2948 : uint32 heaptargettaghash;
2949 :
2950 : /*
2951 : * Bail out quickly if there are no serializable transactions running.
2952 : * It's safe to check this without taking locks because the caller is
2953 : * holding an ACCESS EXCLUSIVE lock on the relation. No new locks which
2954 : * would matter here can be acquired while that is held.
2955 : */
2956 33902 : if (!TransactionIdIsValid(PredXact->SxactGlobalXmin))
2957 33608 : return;
2958 :
2959 368 : if (!PredicateLockingNeededForRelation(relation))
2960 74 : return;
2961 :
2962 294 : dbId = relation->rd_locator.dbOid;
2963 294 : relId = relation->rd_id;
2964 294 : if (relation->rd_index == NULL)
2965 : {
2966 8 : isIndex = false;
2967 8 : heapId = relId;
2968 : }
2969 : else
2970 : {
2971 286 : isIndex = true;
2972 286 : heapId = relation->rd_index->indrelid;
2973 : }
2974 : Assert(heapId != InvalidOid);
2975 : Assert(transfer || !isIndex); /* index OID only makes sense with
2976 : * transfer */
2977 :
2978 : /* Retrieve first time needed, then keep. */
2979 294 : heaptargettaghash = 0;
2980 294 : heaptarget = NULL;
2981 :
2982 : /* Acquire locks on all lock partitions */
2983 294 : LWLockAcquire(SerializablePredicateListLock, LW_EXCLUSIVE);
2984 4998 : for (i = 0; i < NUM_PREDICATELOCK_PARTITIONS; i++)
2985 4704 : LWLockAcquire(PredicateLockHashPartitionLockByIndex(i), LW_EXCLUSIVE);
2986 294 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
2987 :
2988 : /*
2989 : * Remove the dummy entry to give us scratch space, so we know we'll be
2990 : * able to create the new lock target.
2991 : */
2992 294 : if (transfer)
2993 294 : RemoveScratchTarget(true);
2994 :
2995 : /* Scan through target map */
2996 294 : hash_seq_init(&seqstat, PredicateLockTargetHash);
2997 :
2998 624 : while ((oldtarget = (PREDICATELOCKTARGET *) hash_seq_search(&seqstat)))
2999 : {
3000 : dlist_mutable_iter iter;
3001 :
3002 : /*
3003 : * Check whether this is a target which needs attention.
3004 : */
3005 330 : if (GET_PREDICATELOCKTARGETTAG_RELATION(oldtarget->tag) != relId)
3006 330 : continue; /* wrong relation id */
3007 0 : if (GET_PREDICATELOCKTARGETTAG_DB(oldtarget->tag) != dbId)
3008 0 : continue; /* wrong database id */
3009 0 : if (transfer && !isIndex
3010 0 : && GET_PREDICATELOCKTARGETTAG_TYPE(oldtarget->tag) == PREDLOCKTAG_RELATION)
3011 0 : continue; /* already the right lock */
3012 :
3013 : /*
3014 : * If we made it here, we have work to do. We make sure the heap
3015 : * relation lock exists, then we walk the list of predicate locks for
3016 : * the old target we found, moving all locks to the heap relation lock
3017 : * -- unless they already hold that.
3018 : */
3019 :
3020 : /*
3021 : * First make sure we have the heap relation target. We only need to
3022 : * do this once.
3023 : */
3024 0 : if (transfer && heaptarget == NULL)
3025 : {
3026 : PREDICATELOCKTARGETTAG heaptargettag;
3027 :
3028 0 : SET_PREDICATELOCKTARGETTAG_RELATION(heaptargettag, dbId, heapId);
3029 0 : heaptargettaghash = PredicateLockTargetTagHashCode(&heaptargettag);
3030 0 : heaptarget = hash_search_with_hash_value(PredicateLockTargetHash,
3031 : &heaptargettag,
3032 : heaptargettaghash,
3033 : HASH_ENTER, &found);
3034 0 : if (!found)
3035 0 : dlist_init(&heaptarget->predicateLocks);
3036 : }
3037 :
3038 : /*
3039 : * Loop through all the locks on the old target, replacing them with
3040 : * locks on the new target.
3041 : */
3042 0 : dlist_foreach_modify(iter, &oldtarget->predicateLocks)
3043 : {
3044 0 : PREDICATELOCK *oldpredlock =
3045 0 : dlist_container(PREDICATELOCK, targetLink, iter.cur);
3046 : PREDICATELOCK *newpredlock;
3047 : SerCommitSeqNo oldCommitSeqNo;
3048 : SERIALIZABLEXACT *oldXact;
3049 :
3050 : /*
3051 : * Remove the old lock first. This avoids the chance of running
3052 : * out of lock structure entries for the hash table.
3053 : */
3054 0 : oldCommitSeqNo = oldpredlock->commitSeqNo;
3055 0 : oldXact = oldpredlock->tag.myXact;
3056 :
3057 0 : dlist_delete(&(oldpredlock->xactLink));
3058 :
3059 : /*
3060 : * No need for retail delete from oldtarget list, we're removing
3061 : * the whole target anyway.
3062 : */
3063 0 : hash_search(PredicateLockHash,
3064 0 : &oldpredlock->tag,
3065 : HASH_REMOVE, &found);
3066 : Assert(found);
3067 :
3068 0 : if (transfer)
3069 : {
3070 : PREDICATELOCKTAG newpredlocktag;
3071 :
3072 0 : newpredlocktag.myTarget = heaptarget;
3073 0 : newpredlocktag.myXact = oldXact;
3074 : newpredlock = (PREDICATELOCK *)
3075 0 : hash_search_with_hash_value(PredicateLockHash,
3076 : &newpredlocktag,
3077 0 : PredicateLockHashCodeFromTargetHashCode(&newpredlocktag,
3078 : heaptargettaghash),
3079 : HASH_ENTER,
3080 : &found);
3081 0 : if (!found)
3082 : {
3083 0 : dlist_push_tail(&(heaptarget->predicateLocks),
3084 : &(newpredlock->targetLink));
3085 0 : dlist_push_tail(&(newpredlocktag.myXact->predicateLocks),
3086 : &(newpredlock->xactLink));
3087 0 : newpredlock->commitSeqNo = oldCommitSeqNo;
3088 : }
3089 : else
3090 : {
3091 0 : if (newpredlock->commitSeqNo < oldCommitSeqNo)
3092 0 : newpredlock->commitSeqNo = oldCommitSeqNo;
3093 : }
3094 :
3095 : Assert(newpredlock->commitSeqNo != 0);
3096 : Assert((newpredlock->commitSeqNo == InvalidSerCommitSeqNo)
3097 : || (newpredlock->tag.myXact == OldCommittedSxact));
3098 : }
3099 : }
3100 :
3101 0 : hash_search(PredicateLockTargetHash, &oldtarget->tag, HASH_REMOVE,
3102 : &found);
3103 : Assert(found);
3104 : }
3105 :
3106 : /* Put the scratch entry back */
3107 294 : if (transfer)
3108 294 : RestoreScratchTarget(true);
3109 :
3110 : /* Release locks in reverse order */
3111 294 : LWLockRelease(SerializableXactHashLock);
3112 4998 : for (i = NUM_PREDICATELOCK_PARTITIONS - 1; i >= 0; i--)
3113 4704 : LWLockRelease(PredicateLockHashPartitionLockByIndex(i));
3114 294 : LWLockRelease(SerializablePredicateListLock);
3115 : }
3116 :
3117 : /*
3118 : * TransferPredicateLocksToHeapRelation
3119 : * For all transactions, transfer all predicate locks for the given
3120 : * relation to a single relation lock on the heap.
3121 : */
3122 : void
3123 33902 : TransferPredicateLocksToHeapRelation(Relation relation)
3124 : {
3125 33902 : DropAllPredicateLocksFromTable(relation, true);
3126 33902 : }
3127 :
3128 :
3129 : /*
3130 : * PredicateLockPageSplit
3131 : *
3132 : * Copies any predicate locks for the old page to the new page.
3133 : * Skip if this is a temporary table or toast table.
3134 : *
3135 : * NOTE: A page split (or overflow) affects all serializable transactions,
3136 : * even if it occurs in the context of another transaction isolation level.
3137 : *
3138 : * NOTE: This currently leaves the local copy of the locks without
3139 : * information on the new lock which is in shared memory. This could cause
3140 : * problems if enough page splits occur on locked pages without the processes
3141 : * which hold the locks getting in and noticing.
3142 : */
3143 : void
3144 60062 : PredicateLockPageSplit(Relation relation, BlockNumber oldblkno,
3145 : BlockNumber newblkno)
3146 : {
3147 : PREDICATELOCKTARGETTAG oldtargettag;
3148 : PREDICATELOCKTARGETTAG newtargettag;
3149 : bool success;
3150 :
3151 : /*
3152 : * Bail out quickly if there are no serializable transactions running.
3153 : *
3154 : * It's safe to do this check without taking any additional locks. Even if
3155 : * a serializable transaction starts concurrently, we know it can't take
3156 : * any SIREAD locks on the page being split because the caller is holding
3157 : * the associated buffer page lock. Memory reordering isn't an issue; the
3158 : * memory barrier in the LWLock acquisition guarantees that this read
3159 : * occurs while the buffer page lock is held.
3160 : */
3161 60062 : if (!TransactionIdIsValid(PredXact->SxactGlobalXmin))
3162 60036 : return;
3163 :
3164 76 : if (!PredicateLockingNeededForRelation(relation))
3165 50 : return;
3166 :
3167 : Assert(oldblkno != newblkno);
3168 : Assert(BlockNumberIsValid(oldblkno));
3169 : Assert(BlockNumberIsValid(newblkno));
3170 :
3171 26 : SET_PREDICATELOCKTARGETTAG_PAGE(oldtargettag,
3172 : relation->rd_locator.dbOid,
3173 : relation->rd_id,
3174 : oldblkno);
3175 26 : SET_PREDICATELOCKTARGETTAG_PAGE(newtargettag,
3176 : relation->rd_locator.dbOid,
3177 : relation->rd_id,
3178 : newblkno);
3179 :
3180 26 : LWLockAcquire(SerializablePredicateListLock, LW_EXCLUSIVE);
3181 :
3182 : /*
3183 : * Try copying the locks over to the new page's tag, creating it if
3184 : * necessary.
3185 : */
3186 26 : success = TransferPredicateLocksToNewTarget(oldtargettag,
3187 : newtargettag,
3188 : false);
3189 :
3190 26 : if (!success)
3191 : {
3192 : /*
3193 : * No more predicate lock entries are available. Failure isn't an
3194 : * option here, so promote the page lock to a relation lock.
3195 : */
3196 :
3197 : /* Get the parent relation lock's lock tag */
3198 0 : success = GetParentPredicateLockTag(&oldtargettag,
3199 : &newtargettag);
3200 : Assert(success);
3201 :
3202 : /*
3203 : * Move the locks to the parent. This shouldn't fail.
3204 : *
3205 : * Note that here we are removing locks held by other backends,
3206 : * leading to a possible inconsistency in their local lock hash table.
3207 : * This is OK because we're replacing it with a lock that covers the
3208 : * old one.
3209 : */
3210 0 : success = TransferPredicateLocksToNewTarget(oldtargettag,
3211 : newtargettag,
3212 : true);
3213 : Assert(success);
3214 : }
3215 :
3216 26 : LWLockRelease(SerializablePredicateListLock);
3217 : }
3218 :
3219 : /*
3220 : * PredicateLockPageCombine
3221 : *
3222 : * Combines predicate locks for two existing pages.
3223 : * Skip if this is a temporary table or toast table.
3224 : *
3225 : * NOTE: A page combine affects all serializable transactions, even if it
3226 : * occurs in the context of another transaction isolation level.
3227 : */
3228 : void
3229 5458 : PredicateLockPageCombine(Relation relation, BlockNumber oldblkno,
3230 : BlockNumber newblkno)
3231 : {
3232 : /*
3233 : * Page combines differ from page splits in that we ought to be able to
3234 : * remove the locks on the old page after transferring them to the new
3235 : * page, instead of duplicating them. However, because we can't edit other
3236 : * backends' local lock tables, removing the old lock would leave them
3237 : * with an entry in their LocalPredicateLockHash for a lock they're not
3238 : * holding, which isn't acceptable. So we wind up having to do the same
3239 : * work as a page split, acquiring a lock on the new page and keeping the
3240 : * old page locked too. That can lead to some false positives, but should
3241 : * be rare in practice.
3242 : */
3243 5458 : PredicateLockPageSplit(relation, oldblkno, newblkno);
3244 5458 : }
3245 :
3246 : /*
3247 : * Walk the list of in-progress serializable transactions and find the new
3248 : * xmin.
3249 : */
3250 : static void
3251 1672 : SetNewSxactGlobalXmin(void)
3252 : {
3253 : dlist_iter iter;
3254 :
3255 : Assert(LWLockHeldByMe(SerializableXactHashLock));
3256 :
3257 1672 : PredXact->SxactGlobalXmin = InvalidTransactionId;
3258 1672 : PredXact->SxactGlobalXminCount = 0;
3259 :
3260 6440 : dlist_foreach(iter, &PredXact->activeList)
3261 : {
3262 4768 : SERIALIZABLEXACT *sxact =
3263 4768 : dlist_container(SERIALIZABLEXACT, xactLink, iter.cur);
3264 :
3265 4768 : if (!SxactIsRolledBack(sxact)
3266 4172 : && !SxactIsCommitted(sxact)
3267 40 : && sxact != OldCommittedSxact)
3268 : {
3269 : Assert(sxact->xmin != InvalidTransactionId);
3270 40 : if (!TransactionIdIsValid(PredXact->SxactGlobalXmin)
3271 2 : || TransactionIdPrecedes(sxact->xmin,
3272 2 : PredXact->SxactGlobalXmin))
3273 : {
3274 38 : PredXact->SxactGlobalXmin = sxact->xmin;
3275 38 : PredXact->SxactGlobalXminCount = 1;
3276 : }
3277 2 : else if (TransactionIdEquals(sxact->xmin,
3278 : PredXact->SxactGlobalXmin))
3279 2 : PredXact->SxactGlobalXminCount++;
3280 : }
3281 : }
3282 :
3283 1672 : SerialSetActiveSerXmin(PredXact->SxactGlobalXmin);
3284 1672 : }
3285 :
3286 : /*
3287 : * ReleasePredicateLocks
3288 : *
3289 : * Releases predicate locks based on completion of the current transaction,
3290 : * whether committed or rolled back. It can also be called for a read only
3291 : * transaction when it becomes impossible for the transaction to become
3292 : * part of a dangerous structure.
3293 : *
3294 : * We do nothing unless this is a serializable transaction.
3295 : *
3296 : * This method must ensure that shared memory hash tables are cleaned
3297 : * up in some relatively timely fashion.
3298 : *
3299 : * If this transaction is committing and is holding any predicate locks,
3300 : * it must be added to a list of completed serializable transactions still
3301 : * holding locks.
3302 : *
3303 : * If isReadOnlySafe is true, then predicate locks are being released before
3304 : * the end of the transaction because MySerializableXact has been determined
3305 : * to be RO_SAFE. In non-parallel mode we can release it completely, but it
3306 : * in parallel mode we partially release the SERIALIZABLEXACT and keep it
3307 : * around until the end of the transaction, allowing each backend to clear its
3308 : * MySerializableXact variable and benefit from the optimization in its own
3309 : * time.
3310 : */
3311 : void
3312 857624 : ReleasePredicateLocks(bool isCommit, bool isReadOnlySafe)
3313 : {
3314 857624 : bool partiallyReleasing = false;
3315 : bool needToClear;
3316 : SERIALIZABLEXACT *roXact;
3317 : dlist_mutable_iter iter;
3318 :
3319 : /*
3320 : * We can't trust XactReadOnly here, because a transaction which started
3321 : * as READ WRITE can show as READ ONLY later, e.g., within
3322 : * subtransactions. We want to flag a transaction as READ ONLY if it
3323 : * commits without writing so that de facto READ ONLY transactions get the
3324 : * benefit of some RO optimizations, so we will use this local variable to
3325 : * get some cleanup logic right which is based on whether the transaction
3326 : * was declared READ ONLY at the top level.
3327 : */
3328 : bool topLevelIsDeclaredReadOnly;
3329 :
3330 : /* We can't be both committing and releasing early due to RO_SAFE. */
3331 : Assert(!(isCommit && isReadOnlySafe));
3332 :
3333 : /* Are we at the end of a transaction, that is, a commit or abort? */
3334 857624 : if (!isReadOnlySafe)
3335 : {
3336 : /*
3337 : * Parallel workers mustn't release predicate locks at the end of
3338 : * their transaction. The leader will do that at the end of its
3339 : * transaction.
3340 : */
3341 857556 : if (IsParallelWorker())
3342 : {
3343 8214 : ReleasePredicateLocksLocal();
3344 854560 : return;
3345 : }
3346 :
3347 : /*
3348 : * By the time the leader in a parallel query reaches end of
3349 : * transaction, it has waited for all workers to exit.
3350 : */
3351 : Assert(!ParallelContextActive());
3352 :
3353 : /*
3354 : * If the leader in a parallel query earlier stashed a partially
3355 : * released SERIALIZABLEXACT for final clean-up at end of transaction
3356 : * (because workers might still have been accessing it), then it's
3357 : * time to restore it.
3358 : */
3359 849342 : if (SavedSerializableXact != InvalidSerializableXact)
3360 : {
3361 : Assert(MySerializableXact == InvalidSerializableXact);
3362 2 : MySerializableXact = SavedSerializableXact;
3363 2 : SavedSerializableXact = InvalidSerializableXact;
3364 : Assert(SxactIsPartiallyReleased(MySerializableXact));
3365 : }
3366 : }
3367 :
3368 849410 : if (MySerializableXact == InvalidSerializableXact)
3369 : {
3370 : Assert(LocalPredicateLockHash == NULL);
3371 846340 : return;
3372 : }
3373 :
3374 3070 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
3375 :
3376 : /*
3377 : * If the transaction is committing, but it has been partially released
3378 : * already, then treat this as a roll back. It was marked as rolled back.
3379 : */
3380 3070 : if (isCommit && SxactIsPartiallyReleased(MySerializableXact))
3381 4 : isCommit = false;
3382 :
3383 : /*
3384 : * If we're called in the middle of a transaction because we discovered
3385 : * that the SXACT_FLAG_RO_SAFE flag was set, then we'll partially release
3386 : * it (that is, release the predicate locks and conflicts, but not the
3387 : * SERIALIZABLEXACT itself) if we're the first backend to have noticed.
3388 : */
3389 3070 : if (isReadOnlySafe && IsInParallelMode())
3390 : {
3391 : /*
3392 : * The leader needs to stash a pointer to it, so that it can
3393 : * completely release it at end-of-transaction.
3394 : */
3395 10 : if (!IsParallelWorker())
3396 2 : SavedSerializableXact = MySerializableXact;
3397 :
3398 : /*
3399 : * The first backend to reach this condition will partially release
3400 : * the SERIALIZABLEXACT. All others will just clear their
3401 : * backend-local state so that they stop doing SSI checks for the rest
3402 : * of the transaction.
3403 : */
3404 10 : if (SxactIsPartiallyReleased(MySerializableXact))
3405 : {
3406 6 : LWLockRelease(SerializableXactHashLock);
3407 6 : ReleasePredicateLocksLocal();
3408 6 : return;
3409 : }
3410 : else
3411 : {
3412 4 : MySerializableXact->flags |= SXACT_FLAG_PARTIALLY_RELEASED;
3413 4 : partiallyReleasing = true;
3414 : /* ... and proceed to perform the partial release below. */
3415 : }
3416 : }
3417 : Assert(!isCommit || SxactIsPrepared(MySerializableXact));
3418 : Assert(!isCommit || !SxactIsDoomed(MySerializableXact));
3419 : Assert(!SxactIsCommitted(MySerializableXact));
3420 : Assert(SxactIsPartiallyReleased(MySerializableXact)
3421 : || !SxactIsRolledBack(MySerializableXact));
3422 :
3423 : /* may not be serializable during COMMIT/ROLLBACK PREPARED */
3424 : Assert(MySerializableXact->pid == 0 || IsolationIsSerializable());
3425 :
3426 : /* We'd better not already be on the cleanup list. */
3427 : Assert(!SxactIsOnFinishedList(MySerializableXact));
3428 :
3429 3064 : topLevelIsDeclaredReadOnly = SxactIsReadOnly(MySerializableXact);
3430 :
3431 : /*
3432 : * We don't hold XidGenLock lock here, assuming that TransactionId is
3433 : * atomic!
3434 : *
3435 : * If this value is changing, we don't care that much whether we get the
3436 : * old or new value -- it is just used to determine how far
3437 : * SxactGlobalXmin must advance before this transaction can be fully
3438 : * cleaned up. The worst that could happen is we wait for one more
3439 : * transaction to complete before freeing some RAM; correctness of visible
3440 : * behavior is not affected.
3441 : */
3442 3064 : MySerializableXact->finishedBefore = XidFromFullTransactionId(TransamVariables->nextXid);
3443 :
3444 : /*
3445 : * If it's not a commit it's either a rollback or a read-only transaction
3446 : * flagged SXACT_FLAG_RO_SAFE, and we can clear our locks immediately.
3447 : */
3448 3064 : if (isCommit)
3449 : {
3450 2420 : MySerializableXact->flags |= SXACT_FLAG_COMMITTED;
3451 2420 : MySerializableXact->commitSeqNo = ++(PredXact->LastSxactCommitSeqNo);
3452 : /* Recognize implicit read-only transaction (commit without write). */
3453 2420 : if (!MyXactDidWrite)
3454 466 : MySerializableXact->flags |= SXACT_FLAG_READ_ONLY;
3455 : }
3456 : else
3457 : {
3458 : /*
3459 : * The DOOMED flag indicates that we intend to roll back this
3460 : * transaction and so it should not cause serialization failures for
3461 : * other transactions that conflict with it. Note that this flag might
3462 : * already be set, if another backend marked this transaction for
3463 : * abort.
3464 : *
3465 : * The ROLLED_BACK flag further indicates that ReleasePredicateLocks
3466 : * has been called, and so the SerializableXact is eligible for
3467 : * cleanup. This means it should not be considered when calculating
3468 : * SxactGlobalXmin.
3469 : */
3470 644 : MySerializableXact->flags |= SXACT_FLAG_DOOMED;
3471 644 : MySerializableXact->flags |= SXACT_FLAG_ROLLED_BACK;
3472 :
3473 : /*
3474 : * If the transaction was previously prepared, but is now failing due
3475 : * to a ROLLBACK PREPARED or (hopefully very rare) error after the
3476 : * prepare, clear the prepared flag. This simplifies conflict
3477 : * checking.
3478 : */
3479 644 : MySerializableXact->flags &= ~SXACT_FLAG_PREPARED;
3480 : }
3481 :
3482 3064 : if (!topLevelIsDeclaredReadOnly)
3483 : {
3484 : Assert(PredXact->WritableSxactCount > 0);
3485 2846 : if (--(PredXact->WritableSxactCount) == 0)
3486 : {
3487 : /*
3488 : * Release predicate locks and rw-conflicts in for all committed
3489 : * transactions. There are no longer any transactions which might
3490 : * conflict with the locks and no chance for new transactions to
3491 : * overlap. Similarly, existing conflicts in can't cause pivots,
3492 : * and any conflicts in which could have completed a dangerous
3493 : * structure would already have caused a rollback, so any
3494 : * remaining ones must be benign.
3495 : */
3496 1654 : PredXact->CanPartialClearThrough = PredXact->LastSxactCommitSeqNo;
3497 : }
3498 : }
3499 : else
3500 : {
3501 : /*
3502 : * Read-only transactions: clear the list of transactions that might
3503 : * make us unsafe. Note that we use 'inLink' for the iteration as
3504 : * opposed to 'outLink' for the r/w xacts.
3505 : */
3506 302 : dlist_foreach_modify(iter, &MySerializableXact->possibleUnsafeConflicts)
3507 : {
3508 84 : RWConflict possibleUnsafeConflict =
3509 84 : dlist_container(RWConflictData, inLink, iter.cur);
3510 :
3511 : Assert(!SxactIsReadOnly(possibleUnsafeConflict->sxactOut));
3512 : Assert(MySerializableXact == possibleUnsafeConflict->sxactIn);
3513 :
3514 84 : ReleaseRWConflict(possibleUnsafeConflict);
3515 : }
3516 : }
3517 :
3518 : /* Check for conflict out to old committed transactions. */
3519 3064 : if (isCommit
3520 2420 : && !SxactIsReadOnly(MySerializableXact)
3521 1954 : && SxactHasSummaryConflictOut(MySerializableXact))
3522 : {
3523 : /*
3524 : * we don't know which old committed transaction we conflicted with,
3525 : * so be conservative and use FirstNormalSerCommitSeqNo here
3526 : */
3527 0 : MySerializableXact->SeqNo.earliestOutConflictCommit =
3528 : FirstNormalSerCommitSeqNo;
3529 0 : MySerializableXact->flags |= SXACT_FLAG_CONFLICT_OUT;
3530 : }
3531 :
3532 : /*
3533 : * Release all outConflicts to committed transactions. If we're rolling
3534 : * back clear them all. Set SXACT_FLAG_CONFLICT_OUT if any point to
3535 : * previously committed transactions.
3536 : */
3537 4422 : dlist_foreach_modify(iter, &MySerializableXact->outConflicts)
3538 : {
3539 1358 : RWConflict conflict =
3540 1358 : dlist_container(RWConflictData, outLink, iter.cur);
3541 :
3542 1358 : if (isCommit
3543 902 : && !SxactIsReadOnly(MySerializableXact)
3544 686 : && SxactIsCommitted(conflict->sxactIn))
3545 : {
3546 192 : if ((MySerializableXact->flags & SXACT_FLAG_CONFLICT_OUT) == 0
3547 0 : || conflict->sxactIn->prepareSeqNo < MySerializableXact->SeqNo.earliestOutConflictCommit)
3548 192 : MySerializableXact->SeqNo.earliestOutConflictCommit = conflict->sxactIn->prepareSeqNo;
3549 192 : MySerializableXact->flags |= SXACT_FLAG_CONFLICT_OUT;
3550 : }
3551 :
3552 1358 : if (!isCommit
3553 902 : || SxactIsCommitted(conflict->sxactIn)
3554 666 : || (conflict->sxactIn->SeqNo.lastCommitBeforeSnapshot >= PredXact->LastSxactCommitSeqNo))
3555 692 : ReleaseRWConflict(conflict);
3556 : }
3557 :
3558 : /*
3559 : * Release all inConflicts from committed and read-only transactions. If
3560 : * we're rolling back, clear them all.
3561 : */
3562 4602 : dlist_foreach_modify(iter, &MySerializableXact->inConflicts)
3563 : {
3564 1538 : RWConflict conflict =
3565 1538 : dlist_container(RWConflictData, inLink, iter.cur);
3566 :
3567 1538 : if (!isCommit
3568 1198 : || SxactIsCommitted(conflict->sxactOut)
3569 830 : || SxactIsReadOnly(conflict->sxactOut))
3570 868 : ReleaseRWConflict(conflict);
3571 : }
3572 :
3573 3064 : if (!topLevelIsDeclaredReadOnly)
3574 : {
3575 : /*
3576 : * Remove ourselves from the list of possible conflicts for concurrent
3577 : * READ ONLY transactions, flagging them as unsafe if we have a
3578 : * conflict out. If any are waiting DEFERRABLE transactions, wake them
3579 : * up if they are known safe or known unsafe.
3580 : */
3581 3030 : dlist_foreach_modify(iter, &MySerializableXact->possibleUnsafeConflicts)
3582 : {
3583 184 : RWConflict possibleUnsafeConflict =
3584 184 : dlist_container(RWConflictData, outLink, iter.cur);
3585 :
3586 184 : roXact = possibleUnsafeConflict->sxactIn;
3587 : Assert(MySerializableXact == possibleUnsafeConflict->sxactOut);
3588 : Assert(SxactIsReadOnly(roXact));
3589 :
3590 : /* Mark conflicted if necessary. */
3591 184 : if (isCommit
3592 180 : && MyXactDidWrite
3593 170 : && SxactHasConflictOut(MySerializableXact)
3594 26 : && (MySerializableXact->SeqNo.earliestOutConflictCommit
3595 26 : <= roXact->SeqNo.lastCommitBeforeSnapshot))
3596 : {
3597 : /*
3598 : * This releases possibleUnsafeConflict (as well as all other
3599 : * possible conflicts for roXact)
3600 : */
3601 6 : FlagSxactUnsafe(roXact);
3602 : }
3603 : else
3604 : {
3605 178 : ReleaseRWConflict(possibleUnsafeConflict);
3606 :
3607 : /*
3608 : * If we were the last possible conflict, flag it safe. The
3609 : * transaction can now safely release its predicate locks (but
3610 : * that transaction's backend has to do that itself).
3611 : */
3612 178 : if (dlist_is_empty(&roXact->possibleUnsafeConflicts))
3613 132 : roXact->flags |= SXACT_FLAG_RO_SAFE;
3614 : }
3615 :
3616 : /*
3617 : * Wake up the process for a waiting DEFERRABLE transaction if we
3618 : * now know it's either safe or conflicted.
3619 : */
3620 184 : if (SxactIsDeferrableWaiting(roXact) &&
3621 6 : (SxactIsROUnsafe(roXact) || SxactIsROSafe(roXact)))
3622 4 : ProcSendSignal(roXact->pgprocno);
3623 : }
3624 : }
3625 :
3626 : /*
3627 : * Check whether it's time to clean up old transactions. This can only be
3628 : * done when the last serializable transaction with the oldest xmin among
3629 : * serializable transactions completes. We then find the "new oldest"
3630 : * xmin and purge any transactions which finished before this transaction
3631 : * was launched.
3632 : *
3633 : * For parallel queries in read-only transactions, it might run twice. We
3634 : * only release the reference on the first call.
3635 : */
3636 3064 : needToClear = false;
3637 3064 : if ((partiallyReleasing ||
3638 3060 : !SxactIsPartiallyReleased(MySerializableXact)) &&
3639 3060 : TransactionIdEquals(MySerializableXact->xmin,
3640 : PredXact->SxactGlobalXmin))
3641 : {
3642 : Assert(PredXact->SxactGlobalXminCount > 0);
3643 3018 : if (--(PredXact->SxactGlobalXminCount) == 0)
3644 : {
3645 1672 : SetNewSxactGlobalXmin();
3646 1672 : needToClear = true;
3647 : }
3648 : }
3649 :
3650 3064 : LWLockRelease(SerializableXactHashLock);
3651 :
3652 3064 : LWLockAcquire(SerializableFinishedListLock, LW_EXCLUSIVE);
3653 :
3654 : /* Add this to the list of transactions to check for later cleanup. */
3655 3064 : if (isCommit)
3656 2420 : dlist_push_tail(FinishedSerializableTransactions,
3657 2420 : &MySerializableXact->finishedLink);
3658 :
3659 : /*
3660 : * If we're releasing a RO_SAFE transaction in parallel mode, we'll only
3661 : * partially release it. That's necessary because other backends may have
3662 : * a reference to it. The leader will release the SERIALIZABLEXACT itself
3663 : * at the end of the transaction after workers have stopped running.
3664 : */
3665 3064 : if (!isCommit)
3666 644 : ReleaseOneSerializableXact(MySerializableXact,
3667 644 : isReadOnlySafe && IsInParallelMode(),
3668 : false);
3669 :
3670 3064 : LWLockRelease(SerializableFinishedListLock);
3671 :
3672 3064 : if (needToClear)
3673 1672 : ClearOldPredicateLocks();
3674 :
3675 3064 : ReleasePredicateLocksLocal();
3676 : }
3677 :
3678 : static void
3679 11284 : ReleasePredicateLocksLocal(void)
3680 : {
3681 11284 : MySerializableXact = InvalidSerializableXact;
3682 11284 : MyXactDidWrite = false;
3683 :
3684 : /* Delete per-transaction lock table */
3685 11284 : if (LocalPredicateLockHash != NULL)
3686 : {
3687 3062 : hash_destroy(LocalPredicateLockHash);
3688 3062 : LocalPredicateLockHash = NULL;
3689 : }
3690 11284 : }
3691 :
3692 : /*
3693 : * Clear old predicate locks, belonging to committed transactions that are no
3694 : * longer interesting to any in-progress transaction.
3695 : */
3696 : static void
3697 1672 : ClearOldPredicateLocks(void)
3698 : {
3699 : dlist_mutable_iter iter;
3700 :
3701 : /*
3702 : * Loop through finished transactions. They are in commit order, so we can
3703 : * stop as soon as we find one that's still interesting.
3704 : */
3705 1672 : LWLockAcquire(SerializableFinishedListLock, LW_EXCLUSIVE);
3706 1672 : LWLockAcquire(SerializableXactHashLock, LW_SHARED);
3707 4108 : dlist_foreach_modify(iter, FinishedSerializableTransactions)
3708 : {
3709 2456 : SERIALIZABLEXACT *finishedSxact =
3710 2456 : dlist_container(SERIALIZABLEXACT, finishedLink, iter.cur);
3711 :
3712 2456 : if (!TransactionIdIsValid(PredXact->SxactGlobalXmin)
3713 62 : || TransactionIdPrecedesOrEquals(finishedSxact->finishedBefore,
3714 62 : PredXact->SxactGlobalXmin))
3715 : {
3716 : /*
3717 : * This transaction committed before any in-progress transaction
3718 : * took its snapshot. It's no longer interesting.
3719 : */
3720 2420 : LWLockRelease(SerializableXactHashLock);
3721 2420 : dlist_delete_thoroughly(&finishedSxact->finishedLink);
3722 2420 : ReleaseOneSerializableXact(finishedSxact, false, false);
3723 2420 : LWLockAcquire(SerializableXactHashLock, LW_SHARED);
3724 : }
3725 36 : else if (finishedSxact->commitSeqNo > PredXact->HavePartialClearedThrough
3726 36 : && finishedSxact->commitSeqNo <= PredXact->CanPartialClearThrough)
3727 : {
3728 : /*
3729 : * Any active transactions that took their snapshot before this
3730 : * transaction committed are read-only, so we can clear part of
3731 : * its state.
3732 : */
3733 16 : LWLockRelease(SerializableXactHashLock);
3734 :
3735 16 : if (SxactIsReadOnly(finishedSxact))
3736 : {
3737 : /* A read-only transaction can be removed entirely */
3738 0 : dlist_delete_thoroughly(&(finishedSxact->finishedLink));
3739 0 : ReleaseOneSerializableXact(finishedSxact, false, false);
3740 : }
3741 : else
3742 : {
3743 : /*
3744 : * A read-write transaction can only be partially cleared. We
3745 : * need to keep the SERIALIZABLEXACT but can release the
3746 : * SIREAD locks and conflicts in.
3747 : */
3748 16 : ReleaseOneSerializableXact(finishedSxact, true, false);
3749 : }
3750 :
3751 16 : PredXact->HavePartialClearedThrough = finishedSxact->commitSeqNo;
3752 16 : LWLockAcquire(SerializableXactHashLock, LW_SHARED);
3753 : }
3754 : else
3755 : {
3756 : /* Still interesting. */
3757 : break;
3758 : }
3759 : }
3760 1672 : LWLockRelease(SerializableXactHashLock);
3761 :
3762 : /*
3763 : * Loop through predicate locks on dummy transaction for summarized data.
3764 : */
3765 1672 : LWLockAcquire(SerializablePredicateListLock, LW_SHARED);
3766 1672 : dlist_foreach_modify(iter, &OldCommittedSxact->predicateLocks)
3767 : {
3768 0 : PREDICATELOCK *predlock =
3769 0 : dlist_container(PREDICATELOCK, xactLink, iter.cur);
3770 : bool canDoPartialCleanup;
3771 :
3772 0 : LWLockAcquire(SerializableXactHashLock, LW_SHARED);
3773 : Assert(predlock->commitSeqNo != 0);
3774 : Assert(predlock->commitSeqNo != InvalidSerCommitSeqNo);
3775 0 : canDoPartialCleanup = (predlock->commitSeqNo <= PredXact->CanPartialClearThrough);
3776 0 : LWLockRelease(SerializableXactHashLock);
3777 :
3778 : /*
3779 : * If this lock originally belonged to an old enough transaction, we
3780 : * can release it.
3781 : */
3782 0 : if (canDoPartialCleanup)
3783 : {
3784 : PREDICATELOCKTAG tag;
3785 : PREDICATELOCKTARGET *target;
3786 : PREDICATELOCKTARGETTAG targettag;
3787 : uint32 targettaghash;
3788 : LWLock *partitionLock;
3789 :
3790 0 : tag = predlock->tag;
3791 0 : target = tag.myTarget;
3792 0 : targettag = target->tag;
3793 0 : targettaghash = PredicateLockTargetTagHashCode(&targettag);
3794 0 : partitionLock = PredicateLockHashPartitionLock(targettaghash);
3795 :
3796 0 : LWLockAcquire(partitionLock, LW_EXCLUSIVE);
3797 :
3798 0 : dlist_delete(&(predlock->targetLink));
3799 0 : dlist_delete(&(predlock->xactLink));
3800 :
3801 0 : hash_search_with_hash_value(PredicateLockHash, &tag,
3802 0 : PredicateLockHashCodeFromTargetHashCode(&tag,
3803 : targettaghash),
3804 : HASH_REMOVE, NULL);
3805 0 : RemoveTargetIfNoLongerUsed(target, targettaghash);
3806 :
3807 0 : LWLockRelease(partitionLock);
3808 : }
3809 : }
3810 :
3811 1672 : LWLockRelease(SerializablePredicateListLock);
3812 1672 : LWLockRelease(SerializableFinishedListLock);
3813 1672 : }
3814 :
3815 : /*
3816 : * This is the normal way to delete anything from any of the predicate
3817 : * locking hash tables. Given a transaction which we know can be deleted:
3818 : * delete all predicate locks held by that transaction and any predicate
3819 : * lock targets which are now unreferenced by a lock; delete all conflicts
3820 : * for the transaction; delete all xid values for the transaction; then
3821 : * delete the transaction.
3822 : *
3823 : * When the partial flag is set, we can release all predicate locks and
3824 : * in-conflict information -- we've established that there are no longer
3825 : * any overlapping read write transactions for which this transaction could
3826 : * matter -- but keep the transaction entry itself and any outConflicts.
3827 : *
3828 : * When the summarize flag is set, we've run short of room for sxact data
3829 : * and must summarize to the SLRU. Predicate locks are transferred to a
3830 : * dummy "old" transaction, with duplicate locks on a single target
3831 : * collapsing to a single lock with the "latest" commitSeqNo from among
3832 : * the conflicting locks..
3833 : */
3834 : static void
3835 3080 : ReleaseOneSerializableXact(SERIALIZABLEXACT *sxact, bool partial,
3836 : bool summarize)
3837 : {
3838 : SERIALIZABLEXIDTAG sxidtag;
3839 : dlist_mutable_iter iter;
3840 :
3841 : Assert(sxact != NULL);
3842 : Assert(SxactIsRolledBack(sxact) || SxactIsCommitted(sxact));
3843 : Assert(partial || !SxactIsOnFinishedList(sxact));
3844 : Assert(LWLockHeldByMe(SerializableFinishedListLock));
3845 :
3846 : /*
3847 : * First release all the predicate locks held by this xact (or transfer
3848 : * them to OldCommittedSxact if summarize is true)
3849 : */
3850 3080 : LWLockAcquire(SerializablePredicateListLock, LW_SHARED);
3851 3080 : if (IsInParallelMode())
3852 6 : LWLockAcquire(&sxact->perXactPredicateListLock, LW_EXCLUSIVE);
3853 8728 : dlist_foreach_modify(iter, &sxact->predicateLocks)
3854 : {
3855 5648 : PREDICATELOCK *predlock =
3856 5648 : dlist_container(PREDICATELOCK, xactLink, iter.cur);
3857 : PREDICATELOCKTAG tag;
3858 : PREDICATELOCKTARGET *target;
3859 : PREDICATELOCKTARGETTAG targettag;
3860 : uint32 targettaghash;
3861 : LWLock *partitionLock;
3862 :
3863 5648 : tag = predlock->tag;
3864 5648 : target = tag.myTarget;
3865 5648 : targettag = target->tag;
3866 5648 : targettaghash = PredicateLockTargetTagHashCode(&targettag);
3867 5648 : partitionLock = PredicateLockHashPartitionLock(targettaghash);
3868 :
3869 5648 : LWLockAcquire(partitionLock, LW_EXCLUSIVE);
3870 :
3871 5648 : dlist_delete(&predlock->targetLink);
3872 :
3873 5648 : hash_search_with_hash_value(PredicateLockHash, &tag,
3874 5648 : PredicateLockHashCodeFromTargetHashCode(&tag,
3875 : targettaghash),
3876 : HASH_REMOVE, NULL);
3877 5648 : if (summarize)
3878 : {
3879 : bool found;
3880 :
3881 : /* Fold into dummy transaction list. */
3882 0 : tag.myXact = OldCommittedSxact;
3883 0 : predlock = hash_search_with_hash_value(PredicateLockHash, &tag,
3884 0 : PredicateLockHashCodeFromTargetHashCode(&tag,
3885 : targettaghash),
3886 : HASH_ENTER_NULL, &found);
3887 0 : if (!predlock)
3888 0 : ereport(ERROR,
3889 : (errcode(ERRCODE_OUT_OF_MEMORY),
3890 : errmsg("out of shared memory"),
3891 : errhint("You might need to increase \"%s\".", "max_pred_locks_per_transaction")));
3892 0 : if (found)
3893 : {
3894 : Assert(predlock->commitSeqNo != 0);
3895 : Assert(predlock->commitSeqNo != InvalidSerCommitSeqNo);
3896 0 : if (predlock->commitSeqNo < sxact->commitSeqNo)
3897 0 : predlock->commitSeqNo = sxact->commitSeqNo;
3898 : }
3899 : else
3900 : {
3901 0 : dlist_push_tail(&target->predicateLocks,
3902 : &predlock->targetLink);
3903 0 : dlist_push_tail(&OldCommittedSxact->predicateLocks,
3904 : &predlock->xactLink);
3905 0 : predlock->commitSeqNo = sxact->commitSeqNo;
3906 : }
3907 : }
3908 : else
3909 5648 : RemoveTargetIfNoLongerUsed(target, targettaghash);
3910 :
3911 5648 : LWLockRelease(partitionLock);
3912 : }
3913 :
3914 : /*
3915 : * Rather than retail removal, just re-init the head after we've run
3916 : * through the list.
3917 : */
3918 3080 : dlist_init(&sxact->predicateLocks);
3919 :
3920 3080 : if (IsInParallelMode())
3921 6 : LWLockRelease(&sxact->perXactPredicateListLock);
3922 3080 : LWLockRelease(SerializablePredicateListLock);
3923 :
3924 3080 : sxidtag.xid = sxact->topXid;
3925 3080 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
3926 :
3927 : /* Release all outConflicts (unless 'partial' is true) */
3928 3080 : if (!partial)
3929 : {
3930 3060 : dlist_foreach_modify(iter, &sxact->outConflicts)
3931 : {
3932 0 : RWConflict conflict =
3933 0 : dlist_container(RWConflictData, outLink, iter.cur);
3934 :
3935 0 : if (summarize)
3936 0 : conflict->sxactIn->flags |= SXACT_FLAG_SUMMARY_CONFLICT_IN;
3937 0 : ReleaseRWConflict(conflict);
3938 : }
3939 : }
3940 :
3941 : /* Release all inConflicts. */
3942 3080 : dlist_foreach_modify(iter, &sxact->inConflicts)
3943 : {
3944 0 : RWConflict conflict =
3945 0 : dlist_container(RWConflictData, inLink, iter.cur);
3946 :
3947 0 : if (summarize)
3948 0 : conflict->sxactOut->flags |= SXACT_FLAG_SUMMARY_CONFLICT_OUT;
3949 0 : ReleaseRWConflict(conflict);
3950 : }
3951 :
3952 : /* Finally, get rid of the xid and the record of the transaction itself. */
3953 3080 : if (!partial)
3954 : {
3955 3060 : if (sxidtag.xid != InvalidTransactionId)
3956 2526 : hash_search(SerializableXidHash, &sxidtag, HASH_REMOVE, NULL);
3957 3060 : ReleasePredXact(sxact);
3958 : }
3959 :
3960 3080 : LWLockRelease(SerializableXactHashLock);
3961 3080 : }
3962 :
3963 : /*
3964 : * Tests whether the given top level transaction is concurrent with
3965 : * (overlaps) our current transaction.
3966 : *
3967 : * We need to identify the top level transaction for SSI, anyway, so pass
3968 : * that to this function to save the overhead of checking the snapshot's
3969 : * subxip array.
3970 : */
3971 : static bool
3972 1064 : XidIsConcurrent(TransactionId xid)
3973 : {
3974 : Snapshot snap;
3975 :
3976 : Assert(TransactionIdIsValid(xid));
3977 : Assert(!TransactionIdEquals(xid, GetTopTransactionIdIfAny()));
3978 :
3979 1064 : snap = GetTransactionSnapshot();
3980 :
3981 1064 : if (TransactionIdPrecedes(xid, snap->xmin))
3982 0 : return false;
3983 :
3984 1064 : if (TransactionIdFollowsOrEquals(xid, snap->xmax))
3985 1044 : return true;
3986 :
3987 20 : return pg_lfind32(xid, snap->xip, snap->xcnt);
3988 : }
3989 :
3990 : bool
3991 68729830 : CheckForSerializableConflictOutNeeded(Relation relation, Snapshot snapshot)
3992 : {
3993 68729830 : if (!SerializationNeededForRead(relation, snapshot))
3994 68677922 : return false;
3995 :
3996 : /* Check if someone else has already decided that we need to die */
3997 51908 : if (SxactIsDoomed(MySerializableXact))
3998 : {
3999 0 : ereport(ERROR,
4000 : (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
4001 : errmsg("could not serialize access due to read/write dependencies among transactions"),
4002 : errdetail_internal("Reason code: Canceled on identification as a pivot, during conflict out checking."),
4003 : errhint("The transaction might succeed if retried.")));
4004 : }
4005 :
4006 51908 : return true;
4007 : }
4008 :
4009 : /*
4010 : * CheckForSerializableConflictOut
4011 : * A table AM is reading a tuple that has been modified. If it determines
4012 : * that the tuple version it is reading is not visible to us, it should
4013 : * pass in the top level xid of the transaction that created it.
4014 : * Otherwise, if it determines that it is visible to us but it has been
4015 : * deleted or there is a newer version available due to an update, it
4016 : * should pass in the top level xid of the modifying transaction.
4017 : *
4018 : * This function will check for overlap with our own transaction. If the given
4019 : * xid is also serializable and the transactions overlap (i.e., they cannot see
4020 : * each other's writes), then we have a conflict out.
4021 : */
4022 : void
4023 1128 : CheckForSerializableConflictOut(Relation relation, TransactionId xid, Snapshot snapshot)
4024 : {
4025 : SERIALIZABLEXIDTAG sxidtag;
4026 : SERIALIZABLEXID *sxid;
4027 : SERIALIZABLEXACT *sxact;
4028 :
4029 1128 : if (!SerializationNeededForRead(relation, snapshot))
4030 402 : return;
4031 :
4032 : /* Check if someone else has already decided that we need to die */
4033 1128 : if (SxactIsDoomed(MySerializableXact))
4034 : {
4035 0 : ereport(ERROR,
4036 : (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
4037 : errmsg("could not serialize access due to read/write dependencies among transactions"),
4038 : errdetail_internal("Reason code: Canceled on identification as a pivot, during conflict out checking."),
4039 : errhint("The transaction might succeed if retried.")));
4040 : }
4041 : Assert(TransactionIdIsValid(xid));
4042 :
4043 1128 : if (TransactionIdEquals(xid, GetTopTransactionIdIfAny()))
4044 0 : return;
4045 :
4046 : /*
4047 : * Find sxact or summarized info for the top level xid.
4048 : */
4049 1128 : sxidtag.xid = xid;
4050 1128 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
4051 : sxid = (SERIALIZABLEXID *)
4052 1128 : hash_search(SerializableXidHash, &sxidtag, HASH_FIND, NULL);
4053 1128 : if (!sxid)
4054 : {
4055 : /*
4056 : * Transaction not found in "normal" SSI structures. Check whether it
4057 : * got pushed out to SLRU storage for "old committed" transactions.
4058 : */
4059 : SerCommitSeqNo conflictCommitSeqNo;
4060 :
4061 44 : conflictCommitSeqNo = SerialGetMinConflictCommitSeqNo(xid);
4062 44 : if (conflictCommitSeqNo != 0)
4063 : {
4064 0 : if (conflictCommitSeqNo != InvalidSerCommitSeqNo
4065 0 : && (!SxactIsReadOnly(MySerializableXact)
4066 0 : || conflictCommitSeqNo
4067 0 : <= MySerializableXact->SeqNo.lastCommitBeforeSnapshot))
4068 0 : ereport(ERROR,
4069 : (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
4070 : errmsg("could not serialize access due to read/write dependencies among transactions"),
4071 : errdetail_internal("Reason code: Canceled on conflict out to old pivot %u.", xid),
4072 : errhint("The transaction might succeed if retried.")));
4073 :
4074 0 : if (SxactHasSummaryConflictIn(MySerializableXact)
4075 0 : || !dlist_is_empty(&MySerializableXact->inConflicts))
4076 0 : ereport(ERROR,
4077 : (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
4078 : errmsg("could not serialize access due to read/write dependencies among transactions"),
4079 : errdetail_internal("Reason code: Canceled on identification as a pivot, with conflict out to old committed transaction %u.", xid),
4080 : errhint("The transaction might succeed if retried.")));
4081 :
4082 0 : MySerializableXact->flags |= SXACT_FLAG_SUMMARY_CONFLICT_OUT;
4083 : }
4084 :
4085 : /* It's not serializable or otherwise not important. */
4086 44 : LWLockRelease(SerializableXactHashLock);
4087 44 : return;
4088 : }
4089 1084 : sxact = sxid->myXact;
4090 : Assert(TransactionIdEquals(sxact->topXid, xid));
4091 1084 : if (sxact == MySerializableXact || SxactIsDoomed(sxact))
4092 : {
4093 : /* Can't conflict with ourself or a transaction that will roll back. */
4094 8 : LWLockRelease(SerializableXactHashLock);
4095 8 : return;
4096 : }
4097 :
4098 : /*
4099 : * We have a conflict out to a transaction which has a conflict out to a
4100 : * summarized transaction. That summarized transaction must have
4101 : * committed first, and we can't tell when it committed in relation to our
4102 : * snapshot acquisition, so something needs to be canceled.
4103 : */
4104 1076 : if (SxactHasSummaryConflictOut(sxact))
4105 : {
4106 0 : if (!SxactIsPrepared(sxact))
4107 : {
4108 0 : sxact->flags |= SXACT_FLAG_DOOMED;
4109 0 : LWLockRelease(SerializableXactHashLock);
4110 0 : return;
4111 : }
4112 : else
4113 : {
4114 0 : LWLockRelease(SerializableXactHashLock);
4115 0 : ereport(ERROR,
4116 : (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
4117 : errmsg("could not serialize access due to read/write dependencies among transactions"),
4118 : errdetail_internal("Reason code: Canceled on conflict out to old pivot."),
4119 : errhint("The transaction might succeed if retried.")));
4120 : }
4121 : }
4122 :
4123 : /*
4124 : * If this is a read-only transaction and the writing transaction has
4125 : * committed, and it doesn't have a rw-conflict to a transaction which
4126 : * committed before it, no conflict.
4127 : */
4128 1076 : if (SxactIsReadOnly(MySerializableXact)
4129 238 : && SxactIsCommitted(sxact)
4130 16 : && !SxactHasSummaryConflictOut(sxact)
4131 16 : && (!SxactHasConflictOut(sxact)
4132 4 : || MySerializableXact->SeqNo.lastCommitBeforeSnapshot < sxact->SeqNo.earliestOutConflictCommit))
4133 : {
4134 : /* Read-only transaction will appear to run first. No conflict. */
4135 12 : LWLockRelease(SerializableXactHashLock);
4136 12 : return;
4137 : }
4138 :
4139 1064 : if (!XidIsConcurrent(xid))
4140 : {
4141 : /* This write was already in our snapshot; no conflict. */
4142 0 : LWLockRelease(SerializableXactHashLock);
4143 0 : return;
4144 : }
4145 :
4146 1064 : if (RWConflictExists(MySerializableXact, sxact))
4147 : {
4148 : /* We don't want duplicate conflict records in the list. */
4149 338 : LWLockRelease(SerializableXactHashLock);
4150 338 : return;
4151 : }
4152 :
4153 : /*
4154 : * Flag the conflict. But first, if this conflict creates a dangerous
4155 : * structure, ereport an error.
4156 : */
4157 726 : FlagRWConflict(MySerializableXact, sxact);
4158 700 : LWLockRelease(SerializableXactHashLock);
4159 : }
4160 :
4161 : /*
4162 : * Check a particular target for rw-dependency conflict in. A subroutine of
4163 : * CheckForSerializableConflictIn().
4164 : */
4165 : static void
4166 14956 : CheckTargetForConflictsIn(PREDICATELOCKTARGETTAG *targettag)
4167 : {
4168 : uint32 targettaghash;
4169 : LWLock *partitionLock;
4170 : PREDICATELOCKTARGET *target;
4171 14956 : PREDICATELOCK *mypredlock = NULL;
4172 : PREDICATELOCKTAG mypredlocktag;
4173 : dlist_mutable_iter iter;
4174 :
4175 : Assert(MySerializableXact != InvalidSerializableXact);
4176 :
4177 : /*
4178 : * The same hash and LW lock apply to the lock target and the lock itself.
4179 : */
4180 14956 : targettaghash = PredicateLockTargetTagHashCode(targettag);
4181 14956 : partitionLock = PredicateLockHashPartitionLock(targettaghash);
4182 14956 : LWLockAcquire(partitionLock, LW_SHARED);
4183 : target = (PREDICATELOCKTARGET *)
4184 14956 : hash_search_with_hash_value(PredicateLockTargetHash,
4185 : targettag, targettaghash,
4186 : HASH_FIND, NULL);
4187 14956 : if (!target)
4188 : {
4189 : /* Nothing has this target locked; we're done here. */
4190 11214 : LWLockRelease(partitionLock);
4191 11214 : return;
4192 : }
4193 :
4194 : /*
4195 : * Each lock for an overlapping transaction represents a conflict: a
4196 : * rw-dependency in to this transaction.
4197 : */
4198 3742 : LWLockAcquire(SerializableXactHashLock, LW_SHARED);
4199 :
4200 8432 : dlist_foreach_modify(iter, &target->predicateLocks)
4201 : {
4202 4824 : PREDICATELOCK *predlock =
4203 4824 : dlist_container(PREDICATELOCK, targetLink, iter.cur);
4204 4824 : SERIALIZABLEXACT *sxact = predlock->tag.myXact;
4205 :
4206 4824 : if (sxact == MySerializableXact)
4207 : {
4208 : /*
4209 : * If we're getting a write lock on a tuple, we don't need a
4210 : * predicate (SIREAD) lock on the same tuple. We can safely remove
4211 : * our SIREAD lock, but we'll defer doing so until after the loop
4212 : * because that requires upgrading to an exclusive partition lock.
4213 : *
4214 : * We can't use this optimization within a subtransaction because
4215 : * the subtransaction could roll back, and we would be left
4216 : * without any lock at the top level.
4217 : */
4218 3128 : if (!IsSubTransaction()
4219 3128 : && GET_PREDICATELOCKTARGETTAG_OFFSET(*targettag))
4220 : {
4221 776 : mypredlock = predlock;
4222 776 : mypredlocktag = predlock->tag;
4223 : }
4224 : }
4225 1696 : else if (!SxactIsDoomed(sxact)
4226 1696 : && (!SxactIsCommitted(sxact)
4227 166 : || TransactionIdPrecedes(GetTransactionSnapshot()->xmin,
4228 : sxact->finishedBefore))
4229 1678 : && !RWConflictExists(sxact, MySerializableXact))
4230 : {
4231 994 : LWLockRelease(SerializableXactHashLock);
4232 994 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
4233 :
4234 : /*
4235 : * Re-check after getting exclusive lock because the other
4236 : * transaction may have flagged a conflict.
4237 : */
4238 994 : if (!SxactIsDoomed(sxact)
4239 994 : && (!SxactIsCommitted(sxact)
4240 148 : || TransactionIdPrecedes(GetTransactionSnapshot()->xmin,
4241 : sxact->finishedBefore))
4242 994 : && !RWConflictExists(sxact, MySerializableXact))
4243 : {
4244 994 : FlagRWConflict(sxact, MySerializableXact);
4245 : }
4246 :
4247 860 : LWLockRelease(SerializableXactHashLock);
4248 860 : LWLockAcquire(SerializableXactHashLock, LW_SHARED);
4249 : }
4250 : }
4251 3608 : LWLockRelease(SerializableXactHashLock);
4252 3608 : LWLockRelease(partitionLock);
4253 :
4254 : /*
4255 : * If we found one of our own SIREAD locks to remove, remove it now.
4256 : *
4257 : * At this point our transaction already has a RowExclusiveLock on the
4258 : * relation, so we are OK to drop the predicate lock on the tuple, if
4259 : * found, without fearing that another write against the tuple will occur
4260 : * before the MVCC information makes it to the buffer.
4261 : */
4262 3608 : if (mypredlock != NULL)
4263 : {
4264 : uint32 predlockhashcode;
4265 : PREDICATELOCK *rmpredlock;
4266 :
4267 762 : LWLockAcquire(SerializablePredicateListLock, LW_SHARED);
4268 762 : if (IsInParallelMode())
4269 0 : LWLockAcquire(&MySerializableXact->perXactPredicateListLock, LW_EXCLUSIVE);
4270 762 : LWLockAcquire(partitionLock, LW_EXCLUSIVE);
4271 762 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
4272 :
4273 : /*
4274 : * Remove the predicate lock from shared memory, if it wasn't removed
4275 : * while the locks were released. One way that could happen is from
4276 : * autovacuum cleaning up an index.
4277 : */
4278 762 : predlockhashcode = PredicateLockHashCodeFromTargetHashCode
4279 : (&mypredlocktag, targettaghash);
4280 : rmpredlock = (PREDICATELOCK *)
4281 762 : hash_search_with_hash_value(PredicateLockHash,
4282 : &mypredlocktag,
4283 : predlockhashcode,
4284 : HASH_FIND, NULL);
4285 762 : if (rmpredlock != NULL)
4286 : {
4287 : Assert(rmpredlock == mypredlock);
4288 :
4289 762 : dlist_delete(&(mypredlock->targetLink));
4290 762 : dlist_delete(&(mypredlock->xactLink));
4291 :
4292 : rmpredlock = (PREDICATELOCK *)
4293 762 : hash_search_with_hash_value(PredicateLockHash,
4294 : &mypredlocktag,
4295 : predlockhashcode,
4296 : HASH_REMOVE, NULL);
4297 : Assert(rmpredlock == mypredlock);
4298 :
4299 762 : RemoveTargetIfNoLongerUsed(target, targettaghash);
4300 : }
4301 :
4302 762 : LWLockRelease(SerializableXactHashLock);
4303 762 : LWLockRelease(partitionLock);
4304 762 : if (IsInParallelMode())
4305 0 : LWLockRelease(&MySerializableXact->perXactPredicateListLock);
4306 762 : LWLockRelease(SerializablePredicateListLock);
4307 :
4308 762 : if (rmpredlock != NULL)
4309 : {
4310 : /*
4311 : * Remove entry in local lock table if it exists. It's OK if it
4312 : * doesn't exist; that means the lock was transferred to a new
4313 : * target by a different backend.
4314 : */
4315 762 : hash_search_with_hash_value(LocalPredicateLockHash,
4316 : targettag, targettaghash,
4317 : HASH_REMOVE, NULL);
4318 :
4319 762 : DecrementParentLocks(targettag);
4320 : }
4321 : }
4322 : }
4323 :
4324 : /*
4325 : * CheckForSerializableConflictIn
4326 : * We are writing the given tuple. If that indicates a rw-conflict
4327 : * in from another serializable transaction, take appropriate action.
4328 : *
4329 : * Skip checking for any granularity for which a parameter is missing.
4330 : *
4331 : * A tuple update or delete is in conflict if we have a predicate lock
4332 : * against the relation or page in which the tuple exists, or against the
4333 : * tuple itself.
4334 : */
4335 : void
4336 32899964 : CheckForSerializableConflictIn(Relation relation, ItemPointer tid, BlockNumber blkno)
4337 : {
4338 : PREDICATELOCKTARGETTAG targettag;
4339 :
4340 32899964 : if (!SerializationNeededForWrite(relation))
4341 32891114 : return;
4342 :
4343 : /* Check if someone else has already decided that we need to die */
4344 8850 : if (SxactIsDoomed(MySerializableXact))
4345 2 : ereport(ERROR,
4346 : (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
4347 : errmsg("could not serialize access due to read/write dependencies among transactions"),
4348 : errdetail_internal("Reason code: Canceled on identification as a pivot, during conflict in checking."),
4349 : errhint("The transaction might succeed if retried.")));
4350 :
4351 : /*
4352 : * We're doing a write which might cause rw-conflicts now or later.
4353 : * Memorize that fact.
4354 : */
4355 8848 : MyXactDidWrite = true;
4356 :
4357 : /*
4358 : * It is important that we check for locks from the finest granularity to
4359 : * the coarsest granularity, so that granularity promotion doesn't cause
4360 : * us to miss a lock. The new (coarser) lock will be acquired before the
4361 : * old (finer) locks are released.
4362 : *
4363 : * It is not possible to take and hold a lock across the checks for all
4364 : * granularities because each target could be in a separate partition.
4365 : */
4366 8848 : if (tid != NULL)
4367 : {
4368 1286 : SET_PREDICATELOCKTARGETTAG_TUPLE(targettag,
4369 : relation->rd_locator.dbOid,
4370 : relation->rd_id,
4371 : ItemPointerGetBlockNumber(tid),
4372 : ItemPointerGetOffsetNumber(tid));
4373 1286 : CheckTargetForConflictsIn(&targettag);
4374 : }
4375 :
4376 8802 : if (blkno != InvalidBlockNumber)
4377 : {
4378 4928 : SET_PREDICATELOCKTARGETTAG_PAGE(targettag,
4379 : relation->rd_locator.dbOid,
4380 : relation->rd_id,
4381 : blkno);
4382 4928 : CheckTargetForConflictsIn(&targettag);
4383 : }
4384 :
4385 8742 : SET_PREDICATELOCKTARGETTAG_RELATION(targettag,
4386 : relation->rd_locator.dbOid,
4387 : relation->rd_id);
4388 8742 : CheckTargetForConflictsIn(&targettag);
4389 : }
4390 :
4391 : /*
4392 : * CheckTableForSerializableConflictIn
4393 : * The entire table is going through a DDL-style logical mass delete
4394 : * like TRUNCATE or DROP TABLE. If that causes a rw-conflict in from
4395 : * another serializable transaction, take appropriate action.
4396 : *
4397 : * While these operations do not operate entirely within the bounds of
4398 : * snapshot isolation, they can occur inside a serializable transaction, and
4399 : * will logically occur after any reads which saw rows which were destroyed
4400 : * by these operations, so we do what we can to serialize properly under
4401 : * SSI.
4402 : *
4403 : * The relation passed in must be a heap relation. Any predicate lock of any
4404 : * granularity on the heap will cause a rw-conflict in to this transaction.
4405 : * Predicate locks on indexes do not matter because they only exist to guard
4406 : * against conflicting inserts into the index, and this is a mass *delete*.
4407 : * When a table is truncated or dropped, the index will also be truncated
4408 : * or dropped, and we'll deal with locks on the index when that happens.
4409 : *
4410 : * Dropping or truncating a table also needs to drop any existing predicate
4411 : * locks on heap tuples or pages, because they're about to go away. This
4412 : * should be done before altering the predicate locks because the transaction
4413 : * could be rolled back because of a conflict, in which case the lock changes
4414 : * are not needed. (At the moment, we don't actually bother to drop the
4415 : * existing locks on a dropped or truncated table at the moment. That might
4416 : * lead to some false positives, but it doesn't seem worth the trouble.)
4417 : */
4418 : void
4419 51912 : CheckTableForSerializableConflictIn(Relation relation)
4420 : {
4421 : HASH_SEQ_STATUS seqstat;
4422 : PREDICATELOCKTARGET *target;
4423 : Oid dbId;
4424 : Oid heapId;
4425 : int i;
4426 :
4427 : /*
4428 : * Bail out quickly if there are no serializable transactions running.
4429 : * It's safe to check this without taking locks because the caller is
4430 : * holding an ACCESS EXCLUSIVE lock on the relation. No new locks which
4431 : * would matter here can be acquired while that is held.
4432 : */
4433 51912 : if (!TransactionIdIsValid(PredXact->SxactGlobalXmin))
4434 51906 : return;
4435 :
4436 470 : if (!SerializationNeededForWrite(relation))
4437 464 : return;
4438 :
4439 : /*
4440 : * We're doing a write which might cause rw-conflicts now or later.
4441 : * Memorize that fact.
4442 : */
4443 6 : MyXactDidWrite = true;
4444 :
4445 : Assert(relation->rd_index == NULL); /* not an index relation */
4446 :
4447 6 : dbId = relation->rd_locator.dbOid;
4448 6 : heapId = relation->rd_id;
4449 :
4450 6 : LWLockAcquire(SerializablePredicateListLock, LW_EXCLUSIVE);
4451 102 : for (i = 0; i < NUM_PREDICATELOCK_PARTITIONS; i++)
4452 96 : LWLockAcquire(PredicateLockHashPartitionLockByIndex(i), LW_SHARED);
4453 6 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
4454 :
4455 : /* Scan through target list */
4456 6 : hash_seq_init(&seqstat, PredicateLockTargetHash);
4457 :
4458 12 : while ((target = (PREDICATELOCKTARGET *) hash_seq_search(&seqstat)))
4459 : {
4460 : dlist_mutable_iter iter;
4461 :
4462 : /*
4463 : * Check whether this is a target which needs attention.
4464 : */
4465 6 : if (GET_PREDICATELOCKTARGETTAG_RELATION(target->tag) != heapId)
4466 6 : continue; /* wrong relation id */
4467 0 : if (GET_PREDICATELOCKTARGETTAG_DB(target->tag) != dbId)
4468 0 : continue; /* wrong database id */
4469 :
4470 : /*
4471 : * Loop through locks for this target and flag conflicts.
4472 : */
4473 0 : dlist_foreach_modify(iter, &target->predicateLocks)
4474 : {
4475 0 : PREDICATELOCK *predlock =
4476 0 : dlist_container(PREDICATELOCK, targetLink, iter.cur);
4477 :
4478 0 : if (predlock->tag.myXact != MySerializableXact
4479 0 : && !RWConflictExists(predlock->tag.myXact, MySerializableXact))
4480 : {
4481 0 : FlagRWConflict(predlock->tag.myXact, MySerializableXact);
4482 : }
4483 : }
4484 : }
4485 :
4486 : /* Release locks in reverse order */
4487 6 : LWLockRelease(SerializableXactHashLock);
4488 102 : for (i = NUM_PREDICATELOCK_PARTITIONS - 1; i >= 0; i--)
4489 96 : LWLockRelease(PredicateLockHashPartitionLockByIndex(i));
4490 6 : LWLockRelease(SerializablePredicateListLock);
4491 : }
4492 :
4493 :
4494 : /*
4495 : * Flag a rw-dependency between two serializable transactions.
4496 : *
4497 : * The caller is responsible for ensuring that we have a LW lock on
4498 : * the transaction hash table.
4499 : */
4500 : static void
4501 1720 : FlagRWConflict(SERIALIZABLEXACT *reader, SERIALIZABLEXACT *writer)
4502 : {
4503 : Assert(reader != writer);
4504 :
4505 : /* First, see if this conflict causes failure. */
4506 1720 : OnConflict_CheckForSerializationFailure(reader, writer);
4507 :
4508 : /* Actually do the conflict flagging. */
4509 1560 : if (reader == OldCommittedSxact)
4510 0 : writer->flags |= SXACT_FLAG_SUMMARY_CONFLICT_IN;
4511 1560 : else if (writer == OldCommittedSxact)
4512 0 : reader->flags |= SXACT_FLAG_SUMMARY_CONFLICT_OUT;
4513 : else
4514 1560 : SetRWConflict(reader, writer);
4515 1560 : }
4516 :
4517 : /*----------------------------------------------------------------------------
4518 : * We are about to add a RW-edge to the dependency graph - check that we don't
4519 : * introduce a dangerous structure by doing so, and abort one of the
4520 : * transactions if so.
4521 : *
4522 : * A serialization failure can only occur if there is a dangerous structure
4523 : * in the dependency graph:
4524 : *
4525 : * Tin ------> Tpivot ------> Tout
4526 : * rw rw
4527 : *
4528 : * Furthermore, Tout must commit first.
4529 : *
4530 : * One more optimization is that if Tin is declared READ ONLY (or commits
4531 : * without writing), we can only have a problem if Tout committed before Tin
4532 : * acquired its snapshot.
4533 : *----------------------------------------------------------------------------
4534 : */
4535 : static void
4536 1720 : OnConflict_CheckForSerializationFailure(const SERIALIZABLEXACT *reader,
4537 : SERIALIZABLEXACT *writer)
4538 : {
4539 : bool failure;
4540 :
4541 : Assert(LWLockHeldByMe(SerializableXactHashLock));
4542 :
4543 1720 : failure = false;
4544 :
4545 : /*------------------------------------------------------------------------
4546 : * Check for already-committed writer with rw-conflict out flagged
4547 : * (conflict-flag on W means that T2 committed before W):
4548 : *
4549 : * R ------> W ------> T2
4550 : * rw rw
4551 : *
4552 : * That is a dangerous structure, so we must abort. (Since the writer
4553 : * has already committed, we must be the reader)
4554 : *------------------------------------------------------------------------
4555 : */
4556 1720 : if (SxactIsCommitted(writer)
4557 36 : && (SxactHasConflictOut(writer) || SxactHasSummaryConflictOut(writer)))
4558 4 : failure = true;
4559 :
4560 : /*------------------------------------------------------------------------
4561 : * Check whether the writer has become a pivot with an out-conflict
4562 : * committed transaction (T2), and T2 committed first:
4563 : *
4564 : * R ------> W ------> T2
4565 : * rw rw
4566 : *
4567 : * Because T2 must've committed first, there is no anomaly if:
4568 : * - the reader committed before T2
4569 : * - the writer committed before T2
4570 : * - the reader is a READ ONLY transaction and the reader was concurrent
4571 : * with T2 (= reader acquired its snapshot before T2 committed)
4572 : *
4573 : * We also handle the case that T2 is prepared but not yet committed
4574 : * here. In that case T2 has already checked for conflicts, so if it
4575 : * commits first, making the above conflict real, it's too late for it
4576 : * to abort.
4577 : *------------------------------------------------------------------------
4578 : */
4579 1720 : if (!failure && SxactHasSummaryConflictOut(writer))
4580 0 : failure = true;
4581 1720 : else if (!failure)
4582 : {
4583 : dlist_iter iter;
4584 :
4585 2142 : dlist_foreach(iter, &writer->outConflicts)
4586 : {
4587 576 : RWConflict conflict =
4588 576 : dlist_container(RWConflictData, outLink, iter.cur);
4589 576 : SERIALIZABLEXACT *t2 = conflict->sxactIn;
4590 :
4591 576 : if (SxactIsPrepared(t2)
4592 162 : && (!SxactIsCommitted(reader)
4593 130 : || t2->prepareSeqNo <= reader->commitSeqNo)
4594 162 : && (!SxactIsCommitted(writer)
4595 0 : || t2->prepareSeqNo <= writer->commitSeqNo)
4596 162 : && (!SxactIsReadOnly(reader)
4597 24 : || t2->prepareSeqNo <= reader->SeqNo.lastCommitBeforeSnapshot))
4598 : {
4599 150 : failure = true;
4600 150 : break;
4601 : }
4602 : }
4603 : }
4604 :
4605 : /*------------------------------------------------------------------------
4606 : * Check whether the reader has become a pivot with a writer
4607 : * that's committed (or prepared):
4608 : *
4609 : * T0 ------> R ------> W
4610 : * rw rw
4611 : *
4612 : * Because W must've committed first for an anomaly to occur, there is no
4613 : * anomaly if:
4614 : * - T0 committed before the writer
4615 : * - T0 is READ ONLY, and overlaps the writer
4616 : *------------------------------------------------------------------------
4617 : */
4618 1720 : if (!failure && SxactIsPrepared(writer) && !SxactIsReadOnly(reader))
4619 : {
4620 36 : if (SxactHasSummaryConflictIn(reader))
4621 : {
4622 0 : failure = true;
4623 : }
4624 : else
4625 : {
4626 : dlist_iter iter;
4627 :
4628 : /*
4629 : * The unconstify is needed as we have no const version of
4630 : * dlist_foreach().
4631 : */
4632 36 : dlist_foreach(iter, &unconstify(SERIALIZABLEXACT *, reader)->inConflicts)
4633 : {
4634 22 : const RWConflict conflict =
4635 22 : dlist_container(RWConflictData, inLink, iter.cur);
4636 22 : const SERIALIZABLEXACT *t0 = conflict->sxactOut;
4637 :
4638 22 : if (!SxactIsDoomed(t0)
4639 22 : && (!SxactIsCommitted(t0)
4640 22 : || t0->commitSeqNo >= writer->prepareSeqNo)
4641 22 : && (!SxactIsReadOnly(t0)
4642 0 : || t0->SeqNo.lastCommitBeforeSnapshot >= writer->prepareSeqNo))
4643 : {
4644 22 : failure = true;
4645 22 : break;
4646 : }
4647 : }
4648 : }
4649 : }
4650 :
4651 1720 : if (failure)
4652 : {
4653 : /*
4654 : * We have to kill a transaction to avoid a possible anomaly from
4655 : * occurring. If the writer is us, we can just ereport() to cause a
4656 : * transaction abort. Otherwise we flag the writer for termination,
4657 : * causing it to abort when it tries to commit. However, if the writer
4658 : * is a prepared transaction, already prepared, we can't abort it
4659 : * anymore, so we have to kill the reader instead.
4660 : */
4661 176 : if (MySerializableXact == writer)
4662 : {
4663 134 : LWLockRelease(SerializableXactHashLock);
4664 134 : ereport(ERROR,
4665 : (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
4666 : errmsg("could not serialize access due to read/write dependencies among transactions"),
4667 : errdetail_internal("Reason code: Canceled on identification as a pivot, during write."),
4668 : errhint("The transaction might succeed if retried.")));
4669 : }
4670 42 : else if (SxactIsPrepared(writer))
4671 : {
4672 26 : LWLockRelease(SerializableXactHashLock);
4673 :
4674 : /* if we're not the writer, we have to be the reader */
4675 : Assert(MySerializableXact == reader);
4676 26 : ereport(ERROR,
4677 : (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
4678 : errmsg("could not serialize access due to read/write dependencies among transactions"),
4679 : errdetail_internal("Reason code: Canceled on conflict out to pivot %u, during read.", writer->topXid),
4680 : errhint("The transaction might succeed if retried.")));
4681 : }
4682 16 : writer->flags |= SXACT_FLAG_DOOMED;
4683 : }
4684 1560 : }
4685 :
4686 : /*
4687 : * PreCommit_CheckForSerializationFailure
4688 : * Check for dangerous structures in a serializable transaction
4689 : * at commit.
4690 : *
4691 : * We're checking for a dangerous structure as each conflict is recorded.
4692 : * The only way we could have a problem at commit is if this is the "out"
4693 : * side of a pivot, and neither the "in" side nor the pivot has yet
4694 : * committed.
4695 : *
4696 : * If a dangerous structure is found, the pivot (the near conflict) is
4697 : * marked for death, because rolling back another transaction might mean
4698 : * that we fail without ever making progress. This transaction is
4699 : * committing writes, so letting it commit ensures progress. If we
4700 : * canceled the far conflict, it might immediately fail again on retry.
4701 : */
4702 : void
4703 806318 : PreCommit_CheckForSerializationFailure(void)
4704 : {
4705 : dlist_iter near_iter;
4706 :
4707 806318 : if (MySerializableXact == InvalidSerializableXact)
4708 803554 : return;
4709 :
4710 : Assert(IsolationIsSerializable());
4711 :
4712 2764 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
4713 :
4714 : /*
4715 : * Check if someone else has already decided that we need to die. Since
4716 : * we set our own DOOMED flag when partially releasing, ignore in that
4717 : * case.
4718 : */
4719 2764 : if (SxactIsDoomed(MySerializableXact) &&
4720 312 : !SxactIsPartiallyReleased(MySerializableXact))
4721 : {
4722 310 : LWLockRelease(SerializableXactHashLock);
4723 310 : ereport(ERROR,
4724 : (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
4725 : errmsg("could not serialize access due to read/write dependencies among transactions"),
4726 : errdetail_internal("Reason code: Canceled on identification as a pivot, during commit attempt."),
4727 : errhint("The transaction might succeed if retried.")));
4728 : }
4729 :
4730 3656 : dlist_foreach(near_iter, &MySerializableXact->inConflicts)
4731 : {
4732 1202 : RWConflict nearConflict =
4733 1202 : dlist_container(RWConflictData, inLink, near_iter.cur);
4734 :
4735 1202 : if (!SxactIsCommitted(nearConflict->sxactOut)
4736 834 : && !SxactIsDoomed(nearConflict->sxactOut))
4737 : {
4738 : dlist_iter far_iter;
4739 :
4740 894 : dlist_foreach(far_iter, &nearConflict->sxactOut->inConflicts)
4741 : {
4742 356 : RWConflict farConflict =
4743 356 : dlist_container(RWConflictData, inLink, far_iter.cur);
4744 :
4745 356 : if (farConflict->sxactOut == MySerializableXact
4746 84 : || (!SxactIsCommitted(farConflict->sxactOut)
4747 48 : && !SxactIsReadOnly(farConflict->sxactOut)
4748 24 : && !SxactIsDoomed(farConflict->sxactOut)))
4749 : {
4750 : /*
4751 : * Normally, we kill the pivot transaction to make sure we
4752 : * make progress if the failing transaction is retried.
4753 : * However, we can't kill it if it's already prepared, so
4754 : * in that case we commit suicide instead.
4755 : */
4756 296 : if (SxactIsPrepared(nearConflict->sxactOut))
4757 : {
4758 0 : LWLockRelease(SerializableXactHashLock);
4759 0 : ereport(ERROR,
4760 : (errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
4761 : errmsg("could not serialize access due to read/write dependencies among transactions"),
4762 : errdetail_internal("Reason code: Canceled on commit attempt with conflict in from prepared pivot."),
4763 : errhint("The transaction might succeed if retried.")));
4764 : }
4765 296 : nearConflict->sxactOut->flags |= SXACT_FLAG_DOOMED;
4766 296 : break;
4767 : }
4768 : }
4769 : }
4770 : }
4771 :
4772 2454 : MySerializableXact->prepareSeqNo = ++(PredXact->LastSxactCommitSeqNo);
4773 2454 : MySerializableXact->flags |= SXACT_FLAG_PREPARED;
4774 :
4775 2454 : LWLockRelease(SerializableXactHashLock);
4776 : }
4777 :
4778 : /*------------------------------------------------------------------------*/
4779 :
4780 : /*
4781 : * Two-phase commit support
4782 : */
4783 :
4784 : /*
4785 : * AtPrepare_Locks
4786 : * Do the preparatory work for a PREPARE: make 2PC state file
4787 : * records for all predicate locks currently held.
4788 : */
4789 : void
4790 592 : AtPrepare_PredicateLocks(void)
4791 : {
4792 : SERIALIZABLEXACT *sxact;
4793 : TwoPhasePredicateRecord record;
4794 : TwoPhasePredicateXactRecord *xactRecord;
4795 : TwoPhasePredicateLockRecord *lockRecord;
4796 : dlist_iter iter;
4797 :
4798 592 : sxact = MySerializableXact;
4799 592 : xactRecord = &(record.data.xactRecord);
4800 592 : lockRecord = &(record.data.lockRecord);
4801 :
4802 592 : if (MySerializableXact == InvalidSerializableXact)
4803 568 : return;
4804 :
4805 : /* Generate an xact record for our SERIALIZABLEXACT */
4806 24 : record.type = TWOPHASEPREDICATERECORD_XACT;
4807 24 : xactRecord->xmin = MySerializableXact->xmin;
4808 24 : xactRecord->flags = MySerializableXact->flags;
4809 :
4810 : /*
4811 : * Note that we don't include the list of conflicts in our out in the
4812 : * statefile, because new conflicts can be added even after the
4813 : * transaction prepares. We'll just make a conservative assumption during
4814 : * recovery instead.
4815 : */
4816 :
4817 24 : RegisterTwoPhaseRecord(TWOPHASE_RM_PREDICATELOCK_ID, 0,
4818 : &record, sizeof(record));
4819 :
4820 : /*
4821 : * Generate a lock record for each lock.
4822 : *
4823 : * To do this, we need to walk the predicate lock list in our sxact rather
4824 : * than using the local predicate lock table because the latter is not
4825 : * guaranteed to be accurate.
4826 : */
4827 24 : LWLockAcquire(SerializablePredicateListLock, LW_SHARED);
4828 :
4829 : /*
4830 : * No need to take sxact->perXactPredicateListLock in parallel mode
4831 : * because there cannot be any parallel workers running while we are
4832 : * preparing a transaction.
4833 : */
4834 : Assert(!IsParallelWorker() && !ParallelContextActive());
4835 :
4836 44 : dlist_foreach(iter, &sxact->predicateLocks)
4837 : {
4838 20 : PREDICATELOCK *predlock =
4839 20 : dlist_container(PREDICATELOCK, xactLink, iter.cur);
4840 :
4841 20 : record.type = TWOPHASEPREDICATERECORD_LOCK;
4842 20 : lockRecord->target = predlock->tag.myTarget->tag;
4843 :
4844 20 : RegisterTwoPhaseRecord(TWOPHASE_RM_PREDICATELOCK_ID, 0,
4845 : &record, sizeof(record));
4846 : }
4847 :
4848 24 : LWLockRelease(SerializablePredicateListLock);
4849 : }
4850 :
4851 : /*
4852 : * PostPrepare_Locks
4853 : * Clean up after successful PREPARE. Unlike the non-predicate
4854 : * lock manager, we do not need to transfer locks to a dummy
4855 : * PGPROC because our SERIALIZABLEXACT will stay around
4856 : * anyway. We only need to clean up our local state.
4857 : */
4858 : void
4859 592 : PostPrepare_PredicateLocks(TransactionId xid)
4860 : {
4861 592 : if (MySerializableXact == InvalidSerializableXact)
4862 568 : return;
4863 :
4864 : Assert(SxactIsPrepared(MySerializableXact));
4865 :
4866 24 : MySerializableXact->pid = 0;
4867 24 : MySerializableXact->pgprocno = INVALID_PROC_NUMBER;
4868 :
4869 24 : hash_destroy(LocalPredicateLockHash);
4870 24 : LocalPredicateLockHash = NULL;
4871 :
4872 24 : MySerializableXact = InvalidSerializableXact;
4873 24 : MyXactDidWrite = false;
4874 : }
4875 :
4876 : /*
4877 : * PredicateLockTwoPhaseFinish
4878 : * Release a prepared transaction's predicate locks once it
4879 : * commits or aborts.
4880 : */
4881 : void
4882 598 : PredicateLockTwoPhaseFinish(TransactionId xid, bool isCommit)
4883 : {
4884 : SERIALIZABLEXID *sxid;
4885 : SERIALIZABLEXIDTAG sxidtag;
4886 :
4887 598 : sxidtag.xid = xid;
4888 :
4889 598 : LWLockAcquire(SerializableXactHashLock, LW_SHARED);
4890 : sxid = (SERIALIZABLEXID *)
4891 598 : hash_search(SerializableXidHash, &sxidtag, HASH_FIND, NULL);
4892 598 : LWLockRelease(SerializableXactHashLock);
4893 :
4894 : /* xid will not be found if it wasn't a serializable transaction */
4895 598 : if (sxid == NULL)
4896 574 : return;
4897 :
4898 : /* Release its locks */
4899 24 : MySerializableXact = sxid->myXact;
4900 24 : MyXactDidWrite = true; /* conservatively assume that we wrote
4901 : * something */
4902 24 : ReleasePredicateLocks(isCommit, false);
4903 : }
4904 :
4905 : /*
4906 : * Re-acquire a predicate lock belonging to a transaction that was prepared.
4907 : */
4908 : void
4909 0 : predicatelock_twophase_recover(TransactionId xid, uint16 info,
4910 : void *recdata, uint32 len)
4911 : {
4912 : TwoPhasePredicateRecord *record;
4913 :
4914 : Assert(len == sizeof(TwoPhasePredicateRecord));
4915 :
4916 0 : record = (TwoPhasePredicateRecord *) recdata;
4917 :
4918 : Assert((record->type == TWOPHASEPREDICATERECORD_XACT) ||
4919 : (record->type == TWOPHASEPREDICATERECORD_LOCK));
4920 :
4921 0 : if (record->type == TWOPHASEPREDICATERECORD_XACT)
4922 : {
4923 : /* Per-transaction record. Set up a SERIALIZABLEXACT. */
4924 : TwoPhasePredicateXactRecord *xactRecord;
4925 : SERIALIZABLEXACT *sxact;
4926 : SERIALIZABLEXID *sxid;
4927 : SERIALIZABLEXIDTAG sxidtag;
4928 : bool found;
4929 :
4930 0 : xactRecord = (TwoPhasePredicateXactRecord *) &record->data.xactRecord;
4931 :
4932 0 : LWLockAcquire(SerializableXactHashLock, LW_EXCLUSIVE);
4933 0 : sxact = CreatePredXact();
4934 0 : if (!sxact)
4935 0 : ereport(ERROR,
4936 : (errcode(ERRCODE_OUT_OF_MEMORY),
4937 : errmsg("out of shared memory")));
4938 :
4939 : /* vxid for a prepared xact is INVALID_PROC_NUMBER/xid; no pid */
4940 0 : sxact->vxid.procNumber = INVALID_PROC_NUMBER;
4941 0 : sxact->vxid.localTransactionId = (LocalTransactionId) xid;
4942 0 : sxact->pid = 0;
4943 0 : sxact->pgprocno = INVALID_PROC_NUMBER;
4944 :
4945 : /* a prepared xact hasn't committed yet */
4946 0 : sxact->prepareSeqNo = RecoverySerCommitSeqNo;
4947 0 : sxact->commitSeqNo = InvalidSerCommitSeqNo;
4948 0 : sxact->finishedBefore = InvalidTransactionId;
4949 :
4950 0 : sxact->SeqNo.lastCommitBeforeSnapshot = RecoverySerCommitSeqNo;
4951 :
4952 : /*
4953 : * Don't need to track this; no transactions running at the time the
4954 : * recovered xact started are still active, except possibly other
4955 : * prepared xacts and we don't care whether those are RO_SAFE or not.
4956 : */
4957 0 : dlist_init(&(sxact->possibleUnsafeConflicts));
4958 :
4959 0 : dlist_init(&(sxact->predicateLocks));
4960 0 : dlist_node_init(&sxact->finishedLink);
4961 :
4962 0 : sxact->topXid = xid;
4963 0 : sxact->xmin = xactRecord->xmin;
4964 0 : sxact->flags = xactRecord->flags;
4965 : Assert(SxactIsPrepared(sxact));
4966 0 : if (!SxactIsReadOnly(sxact))
4967 : {
4968 0 : ++(PredXact->WritableSxactCount);
4969 : Assert(PredXact->WritableSxactCount <=
4970 : (MaxBackends + max_prepared_xacts));
4971 : }
4972 :
4973 : /*
4974 : * We don't know whether the transaction had any conflicts or not, so
4975 : * we'll conservatively assume that it had both a conflict in and a
4976 : * conflict out, and represent that with the summary conflict flags.
4977 : */
4978 0 : dlist_init(&(sxact->outConflicts));
4979 0 : dlist_init(&(sxact->inConflicts));
4980 0 : sxact->flags |= SXACT_FLAG_SUMMARY_CONFLICT_IN;
4981 0 : sxact->flags |= SXACT_FLAG_SUMMARY_CONFLICT_OUT;
4982 :
4983 : /* Register the transaction's xid */
4984 0 : sxidtag.xid = xid;
4985 0 : sxid = (SERIALIZABLEXID *) hash_search(SerializableXidHash,
4986 : &sxidtag,
4987 : HASH_ENTER, &found);
4988 : Assert(sxid != NULL);
4989 : Assert(!found);
4990 0 : sxid->myXact = (SERIALIZABLEXACT *) sxact;
4991 :
4992 : /*
4993 : * Update global xmin. Note that this is a special case compared to
4994 : * registering a normal transaction, because the global xmin might go
4995 : * backwards. That's OK, because until recovery is over we're not
4996 : * going to complete any transactions or create any non-prepared
4997 : * transactions, so there's no danger of throwing away.
4998 : */
4999 0 : if ((!TransactionIdIsValid(PredXact->SxactGlobalXmin)) ||
5000 0 : (TransactionIdFollows(PredXact->SxactGlobalXmin, sxact->xmin)))
5001 : {
5002 0 : PredXact->SxactGlobalXmin = sxact->xmin;
5003 0 : PredXact->SxactGlobalXminCount = 1;
5004 0 : SerialSetActiveSerXmin(sxact->xmin);
5005 : }
5006 0 : else if (TransactionIdEquals(sxact->xmin, PredXact->SxactGlobalXmin))
5007 : {
5008 : Assert(PredXact->SxactGlobalXminCount > 0);
5009 0 : PredXact->SxactGlobalXminCount++;
5010 : }
5011 :
5012 0 : LWLockRelease(SerializableXactHashLock);
5013 : }
5014 0 : else if (record->type == TWOPHASEPREDICATERECORD_LOCK)
5015 : {
5016 : /* Lock record. Recreate the PREDICATELOCK */
5017 : TwoPhasePredicateLockRecord *lockRecord;
5018 : SERIALIZABLEXID *sxid;
5019 : SERIALIZABLEXACT *sxact;
5020 : SERIALIZABLEXIDTAG sxidtag;
5021 : uint32 targettaghash;
5022 :
5023 0 : lockRecord = (TwoPhasePredicateLockRecord *) &record->data.lockRecord;
5024 0 : targettaghash = PredicateLockTargetTagHashCode(&lockRecord->target);
5025 :
5026 0 : LWLockAcquire(SerializableXactHashLock, LW_SHARED);
5027 0 : sxidtag.xid = xid;
5028 : sxid = (SERIALIZABLEXID *)
5029 0 : hash_search(SerializableXidHash, &sxidtag, HASH_FIND, NULL);
5030 0 : LWLockRelease(SerializableXactHashLock);
5031 :
5032 : Assert(sxid != NULL);
5033 0 : sxact = sxid->myXact;
5034 : Assert(sxact != InvalidSerializableXact);
5035 :
5036 0 : CreatePredicateLock(&lockRecord->target, targettaghash, sxact);
5037 : }
5038 0 : }
5039 :
5040 : /*
5041 : * Prepare to share the current SERIALIZABLEXACT with parallel workers.
5042 : * Return a handle object that can be used by AttachSerializableXact() in a
5043 : * parallel worker.
5044 : */
5045 : SerializableXactHandle
5046 910 : ShareSerializableXact(void)
5047 : {
5048 910 : return MySerializableXact;
5049 : }
5050 :
5051 : /*
5052 : * Allow parallel workers to import the leader's SERIALIZABLEXACT.
5053 : */
5054 : void
5055 2738 : AttachSerializableXact(SerializableXactHandle handle)
5056 : {
5057 :
5058 : Assert(MySerializableXact == InvalidSerializableXact);
5059 :
5060 2738 : MySerializableXact = (SERIALIZABLEXACT *) handle;
5061 2738 : if (MySerializableXact != InvalidSerializableXact)
5062 26 : CreateLocalPredicateLockHash();
5063 2738 : }
|
