-
Notifications
You must be signed in to change notification settings - Fork 2
/
pg_dump_sort.c
1474 lines (1363 loc) · 42.5 KB
/
pg_dump_sort.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*-------------------------------------------------------------------------
*
* pg_dump_sort.c
* Sort the items of a dump into a safe order for dumping
*
*
* Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
* src/bin/pg_dump/pg_dump_sort.c
*
*-------------------------------------------------------------------------
*/
#include "pg_backup_archiver.h"
#include "pg_backup_utils.h"
#include "parallel.h"
/* translator: this is a module name */
static const char *modulename = gettext_noop("sorter");
/*
* Sort priority for object types when dumping a pre-7.3 database.
* Objects are sorted by priority levels, and within an equal priority level
* by OID. (This is a relatively crude hack to provide semi-reasonable
* behavior for old databases without full dependency info.) Note: collations,
* extensions, text search, foreign-data, materialized view, event trigger,
* and default ACL objects can't really happen here, so the rather bogus
* priorities for them don't matter.
*
* NOTE: object-type priorities must match the section assignments made in
* pg_dump.c; that is, PRE_DATA objects must sort before DO_PRE_DATA_BOUNDARY,
* POST_DATA objects must sort after DO_POST_DATA_BOUNDARY, and DATA objects
* must sort between them.
*/
static const int oldObjectTypePriority[] =
{
1, /* DO_NAMESPACE */
1, /* DO_EXTENSION */
2, /* DO_TYPE */
2, /* DO_SHELL_TYPE */
2, /* DO_FUNC */
3, /* DO_AGG */
3, /* DO_OPERATOR */
4, /* DO_OPCLASS */
4, /* DO_OPFAMILY */
4, /* DO_COLLATION */
5, /* DO_CONVERSION */
6, /* DO_TABLE */
8, /* DO_ATTRDEF */
15, /* DO_INDEX */
16, /* DO_RULE */
17, /* DO_TRIGGER */
14, /* DO_CONSTRAINT */
18, /* DO_FK_CONSTRAINT */
2, /* DO_PROCLANG */
2, /* DO_CAST */
11, /* DO_TABLE_DATA */
7, /* DO_DUMMY_TYPE */
4, /* DO_TSPARSER */
4, /* DO_TSDICT */
4, /* DO_TSTEMPLATE */
4, /* DO_TSCONFIG */
4, /* DO_FDW */
4, /* DO_FOREIGN_SERVER */
19, /* DO_DEFAULT_ACL */
9, /* DO_BLOB */
12, /* DO_BLOB_DATA */
10, /* DO_PRE_DATA_BOUNDARY */
13, /* DO_POST_DATA_BOUNDARY */
20, /* DO_EVENT_TRIGGER */
15 /* DO_REFRESH_MATVIEW */
};
/*
* Sort priority for object types when dumping newer databases.
* Objects are sorted by type, and within a type by name.
*
* NOTE: object-type priorities must match the section assignments made in
* pg_dump.c; that is, PRE_DATA objects must sort before DO_PRE_DATA_BOUNDARY,
* POST_DATA objects must sort after DO_POST_DATA_BOUNDARY, and DATA objects
* must sort between them.
*/
static const int newObjectTypePriority[] =
{
1, /* DO_NAMESPACE */
4, /* DO_EXTENSION */
5, /* DO_TYPE */
5, /* DO_SHELL_TYPE */
6, /* DO_FUNC */
7, /* DO_AGG */
8, /* DO_OPERATOR */
9, /* DO_OPCLASS */
9, /* DO_OPFAMILY */
3, /* DO_COLLATION */
11, /* DO_CONVERSION */
18, /* DO_TABLE */
20, /* DO_ATTRDEF */
27, /* DO_INDEX */
28, /* DO_RULE */
29, /* DO_TRIGGER */
26, /* DO_CONSTRAINT */
30, /* DO_FK_CONSTRAINT */
2, /* DO_PROCLANG */
10, /* DO_CAST */
23, /* DO_TABLE_DATA */
19, /* DO_DUMMY_TYPE */
12, /* DO_TSPARSER */
14, /* DO_TSDICT */
13, /* DO_TSTEMPLATE */
15, /* DO_TSCONFIG */
16, /* DO_FDW */
17, /* DO_FOREIGN_SERVER */
31, /* DO_DEFAULT_ACL */
21, /* DO_BLOB */
24, /* DO_BLOB_DATA */
22, /* DO_PRE_DATA_BOUNDARY */
25, /* DO_POST_DATA_BOUNDARY */
32, /* DO_EVENT_TRIGGER */
33 /* DO_REFRESH_MATVIEW */
};
static DumpId preDataBoundId;
static DumpId postDataBoundId;
static int DOTypeNameCompare(const void *p1, const void *p2);
static int DOTypeOidCompare(const void *p1, const void *p2);
static bool TopoSort(DumpableObject **objs,
int numObjs,
DumpableObject **ordering,
int *nOrdering);
static void addHeapElement(int val, int *heap, int heapLength);
static int removeHeapElement(int *heap, int heapLength);
static void findDependencyLoops(DumpableObject **objs, int nObjs, int totObjs);
static int findLoop(DumpableObject *obj,
DumpId startPoint,
bool *processed,
DumpId *searchFailed,
DumpableObject **workspace,
int depth);
static void repairDependencyLoop(DumpableObject **loop,
int nLoop);
static void describeDumpableObject(DumpableObject *obj,
char *buf, int bufsize);
static int DOSizeCompare(const void *p1, const void *p2);
static int
findFirstEqualType(DumpableObjectType type, DumpableObject **objs, int numObjs)
{
int i;
for (i = 0; i < numObjs; i++)
if (objs[i]->objType == type)
return i;
return -1;
}
static int
findFirstDifferentType(DumpableObjectType type, DumpableObject **objs, int numObjs, int start)
{
int i;
for (i = start; i < numObjs; i++)
if (objs[i]->objType != type)
return i;
return numObjs - 1;
}
/*
* When we do a parallel dump, we want to start with the largest items first.
*
* Say we have the objects in this order:
* ....DDDDD....III....
*
* with D = Table data, I = Index, . = other object
*
* This sorting function now takes each of the D or I blocks and sorts them
* according to their size.
*/
void
sortDataAndIndexObjectsBySize(DumpableObject **objs, int numObjs)
{
int startIdx,
endIdx;
void *startPtr;
if (numObjs <= 1)
return;
startIdx = findFirstEqualType(DO_TABLE_DATA, objs, numObjs);
if (startIdx >= 0)
{
endIdx = findFirstDifferentType(DO_TABLE_DATA, objs, numObjs, startIdx);
startPtr = objs + startIdx;
qsort(startPtr, endIdx - startIdx, sizeof(DumpableObject *),
DOSizeCompare);
}
startIdx = findFirstEqualType(DO_INDEX, objs, numObjs);
if (startIdx >= 0)
{
endIdx = findFirstDifferentType(DO_INDEX, objs, numObjs, startIdx);
startPtr = objs + startIdx;
qsort(startPtr, endIdx - startIdx, sizeof(DumpableObject *),
DOSizeCompare);
}
}
static int
DOSizeCompare(const void *p1, const void *p2)
{
DumpableObject *obj1 = *(DumpableObject **) p1;
DumpableObject *obj2 = *(DumpableObject **) p2;
int obj1_size = 0;
int obj2_size = 0;
if (obj1->objType == DO_TABLE_DATA)
obj1_size = ((TableDataInfo *) obj1)->tdtable->relpages;
if (obj1->objType == DO_INDEX)
obj1_size = ((IndxInfo *) obj1)->relpages;
if (obj2->objType == DO_TABLE_DATA)
obj2_size = ((TableDataInfo *) obj2)->tdtable->relpages;
if (obj2->objType == DO_INDEX)
obj2_size = ((IndxInfo *) obj2)->relpages;
/* we want to see the biggest item go first */
if (obj1_size > obj2_size)
return -1;
if (obj2_size > obj1_size)
return 1;
return 0;
}
/*
* Sort the given objects into a type/name-based ordering
*
* Normally this is just the starting point for the dependency-based
* ordering.
*/
void
sortDumpableObjectsByTypeName(DumpableObject **objs, int numObjs)
{
if (numObjs > 1)
qsort((void *) objs, numObjs, sizeof(DumpableObject *),
DOTypeNameCompare);
}
static int
DOTypeNameCompare(const void *p1, const void *p2)
{
DumpableObject *obj1 = *(DumpableObject *const *) p1;
DumpableObject *obj2 = *(DumpableObject *const *) p2;
int cmpval;
/* Sort by type */
cmpval = newObjectTypePriority[obj1->objType] -
newObjectTypePriority[obj2->objType];
if (cmpval != 0)
return cmpval;
/*
* Sort by namespace. Note that all objects of the same type should
* either have or not have a namespace link, so we needn't be fancy about
* cases where one link is null and the other not.
*/
if (obj1->namespace && obj2->namespace)
{
cmpval = strcmp(obj1->namespace->dobj.name,
obj2->namespace->dobj.name);
if (cmpval != 0)
return cmpval;
}
/* Sort by name */
cmpval = strcmp(obj1->name, obj2->name);
if (cmpval != 0)
return cmpval;
/* To have a stable sort order, break ties for some object types */
if (obj1->objType == DO_FUNC || obj1->objType == DO_AGG)
{
FuncInfo *fobj1 = *(FuncInfo *const *) p1;
FuncInfo *fobj2 = *(FuncInfo *const *) p2;
int i;
cmpval = fobj1->nargs - fobj2->nargs;
if (cmpval != 0)
return cmpval;
for (i = 0; i < fobj1->nargs; i++)
{
TypeInfo *argtype1 = findTypeByOid(fobj1->argtypes[i]);
TypeInfo *argtype2 = findTypeByOid(fobj2->argtypes[i]);
if (argtype1 && argtype2)
{
if (argtype1->dobj.namespace && argtype2->dobj.namespace)
{
cmpval = strcmp(argtype1->dobj.namespace->dobj.name,
argtype2->dobj.namespace->dobj.name);
if (cmpval != 0)
return cmpval;
}
cmpval = strcmp(argtype1->dobj.name, argtype2->dobj.name);
if (cmpval != 0)
return cmpval;
}
}
}
else if (obj1->objType == DO_OPERATOR)
{
OprInfo *oobj1 = *(OprInfo *const *) p1;
OprInfo *oobj2 = *(OprInfo *const *) p2;
/* oprkind is 'l', 'r', or 'b'; this sorts prefix, postfix, infix */
cmpval = (oobj2->oprkind - oobj1->oprkind);
if (cmpval != 0)
return cmpval;
}
else if (obj1->objType == DO_ATTRDEF)
{
AttrDefInfo *adobj1 = *(AttrDefInfo *const *) p1;
AttrDefInfo *adobj2 = *(AttrDefInfo *const *) p2;
cmpval = (adobj1->adnum - adobj2->adnum);
if (cmpval != 0)
return cmpval;
}
/* Usually shouldn't get here, but if we do, sort by OID */
return oidcmp(obj1->catId.oid, obj2->catId.oid);
}
/*
* Sort the given objects into a type/OID-based ordering
*
* This is used with pre-7.3 source databases as a crude substitute for the
* lack of dependency information.
*/
void
sortDumpableObjectsByTypeOid(DumpableObject **objs, int numObjs)
{
if (numObjs > 1)
qsort((void *) objs, numObjs, sizeof(DumpableObject *),
DOTypeOidCompare);
}
static int
DOTypeOidCompare(const void *p1, const void *p2)
{
DumpableObject *obj1 = *(DumpableObject *const *) p1;
DumpableObject *obj2 = *(DumpableObject *const *) p2;
int cmpval;
cmpval = oldObjectTypePriority[obj1->objType] -
oldObjectTypePriority[obj2->objType];
if (cmpval != 0)
return cmpval;
return oidcmp(obj1->catId.oid, obj2->catId.oid);
}
/*
* Sort the given objects into a safe dump order using dependency
* information (to the extent we have it available).
*
* The DumpIds of the PRE_DATA_BOUNDARY and POST_DATA_BOUNDARY objects are
* passed in separately, in case we need them during dependency loop repair.
*/
void
sortDumpableObjects(DumpableObject **objs, int numObjs,
DumpId preBoundaryId, DumpId postBoundaryId)
{
DumpableObject **ordering;
int nOrdering;
if (numObjs <= 0) /* can't happen anymore ... */
return;
/*
* Saving the boundary IDs in static variables is a bit grotty, but seems
* better than adding them to parameter lists of subsidiary functions.
*/
preDataBoundId = preBoundaryId;
postDataBoundId = postBoundaryId;
ordering = (DumpableObject **) pg_malloc(numObjs * sizeof(DumpableObject *));
while (!TopoSort(objs, numObjs, ordering, &nOrdering))
findDependencyLoops(ordering, nOrdering, numObjs);
memcpy(objs, ordering, numObjs * sizeof(DumpableObject *));
free(ordering);
}
/*
* TopoSort -- topological sort of a dump list
*
* Generate a re-ordering of the dump list that satisfies all the dependency
* constraints shown in the dump list. (Each such constraint is a fact of a
* partial ordering.) Minimize rearrangement of the list not needed to
* achieve the partial ordering.
*
* The input is the list of numObjs objects in objs[]. This list is not
* modified.
*
* Returns TRUE if able to build an ordering that satisfies all the
* constraints, FALSE if not (there are contradictory constraints).
*
* On success (TRUE result), ordering[] is filled with a sorted array of
* DumpableObject pointers, of length equal to the input list length.
*
* On failure (FALSE result), ordering[] is filled with an unsorted array of
* DumpableObject pointers of length *nOrdering, listing the objects that
* prevented the sort from being completed. In general, these objects either
* participate directly in a dependency cycle, or are depended on by objects
* that are in a cycle. (The latter objects are not actually problematic,
* but it takes further analysis to identify which are which.)
*
* The caller is responsible for allocating sufficient space at *ordering.
*/
static bool
TopoSort(DumpableObject **objs,
int numObjs,
DumpableObject **ordering, /* output argument */
int *nOrdering) /* output argument */
{
DumpId maxDumpId = getMaxDumpId();
int *pendingHeap;
int *beforeConstraints;
int *idMap;
DumpableObject *obj;
int heapLength;
int i,
j,
k;
/*
* This is basically the same algorithm shown for topological sorting in
* Knuth's Volume 1. However, we would like to minimize unnecessary
* rearrangement of the input ordering; that is, when we have a choice of
* which item to output next, we always want to take the one highest in
* the original list. Therefore, instead of maintaining an unordered
* linked list of items-ready-to-output as Knuth does, we maintain a heap
* of their item numbers, which we can use as a priority queue. This
* turns the algorithm from O(N) to O(N log N) because each insertion or
* removal of a heap item takes O(log N) time. However, that's still
* plenty fast enough for this application.
*/
*nOrdering = numObjs; /* for success return */
/* Eliminate the null case */
if (numObjs <= 0)
return true;
/* Create workspace for the above-described heap */
pendingHeap = (int *) pg_malloc(numObjs * sizeof(int));
/*
* Scan the constraints, and for each item in the input, generate a count
* of the number of constraints that say it must be before something else.
* The count for the item with dumpId j is stored in beforeConstraints[j].
* We also make a map showing the input-order index of the item with
* dumpId j.
*/
beforeConstraints = (int *) pg_malloc((maxDumpId + 1) * sizeof(int));
memset(beforeConstraints, 0, (maxDumpId + 1) * sizeof(int));
idMap = (int *) pg_malloc((maxDumpId + 1) * sizeof(int));
for (i = 0; i < numObjs; i++)
{
obj = objs[i];
j = obj->dumpId;
if (j <= 0 || j > maxDumpId)
exit_horribly(modulename, "invalid dumpId %d\n", j);
idMap[j] = i;
for (j = 0; j < obj->nDeps; j++)
{
k = obj->dependencies[j];
if (k <= 0 || k > maxDumpId)
exit_horribly(modulename, "invalid dependency %d\n", k);
beforeConstraints[k]++;
}
}
/*
* Now initialize the heap of items-ready-to-output by filling it with the
* indexes of items that already have beforeConstraints[id] == 0.
*
* The essential property of a heap is heap[(j-1)/2] >= heap[j] for each j
* in the range 1..heapLength-1 (note we are using 0-based subscripts
* here, while the discussion in Knuth assumes 1-based subscripts). So, if
* we simply enter the indexes into pendingHeap[] in decreasing order, we
* a-fortiori have the heap invariant satisfied at completion of this
* loop, and don't need to do any sift-up comparisons.
*/
heapLength = 0;
for (i = numObjs; --i >= 0;)
{
if (beforeConstraints[objs[i]->dumpId] == 0)
pendingHeap[heapLength++] = i;
}
/*--------------------
* Now emit objects, working backwards in the output list. At each step,
* we use the priority heap to select the last item that has no remaining
* before-constraints. We remove that item from the heap, output it to
* ordering[], and decrease the beforeConstraints count of each of the
* items it was constrained against. Whenever an item's beforeConstraints
* count is thereby decreased to zero, we insert it into the priority heap
* to show that it is a candidate to output. We are done when the heap
* becomes empty; if we have output every element then we succeeded,
* otherwise we failed.
* i = number of ordering[] entries left to output
* j = objs[] index of item we are outputting
* k = temp for scanning constraint list for item j
*--------------------
*/
i = numObjs;
while (heapLength > 0)
{
/* Select object to output by removing largest heap member */
j = removeHeapElement(pendingHeap, heapLength--);
obj = objs[j];
/* Output candidate to ordering[] */
ordering[--i] = obj;
/* Update beforeConstraints counts of its predecessors */
for (k = 0; k < obj->nDeps; k++)
{
int id = obj->dependencies[k];
if ((--beforeConstraints[id]) == 0)
addHeapElement(idMap[id], pendingHeap, heapLength++);
}
}
/*
* If we failed, report the objects that couldn't be output; these are the
* ones with beforeConstraints[] still nonzero.
*/
if (i != 0)
{
k = 0;
for (j = 1; j <= maxDumpId; j++)
{
if (beforeConstraints[j] != 0)
ordering[k++] = objs[idMap[j]];
}
*nOrdering = k;
}
/* Done */
free(pendingHeap);
free(beforeConstraints);
free(idMap);
return (i == 0);
}
/*
* Add an item to a heap (priority queue)
*
* heapLength is the current heap size; caller is responsible for increasing
* its value after the call. There must be sufficient storage at *heap.
*/
static void
addHeapElement(int val, int *heap, int heapLength)
{
int j;
/*
* Sift-up the new entry, per Knuth 5.2.3 exercise 16. Note that Knuth is
* using 1-based array indexes, not 0-based.
*/
j = heapLength;
while (j > 0)
{
int i = (j - 1) >> 1;
if (val <= heap[i])
break;
heap[j] = heap[i];
j = i;
}
heap[j] = val;
}
/*
* Remove the largest item present in a heap (priority queue)
*
* heapLength is the current heap size; caller is responsible for decreasing
* its value after the call.
*
* We remove and return heap[0], which is always the largest element of
* the heap, and then "sift up" to maintain the heap invariant.
*/
static int
removeHeapElement(int *heap, int heapLength)
{
int result = heap[0];
int val;
int i;
if (--heapLength <= 0)
return result;
val = heap[heapLength]; /* value that must be reinserted */
i = 0; /* i is where the "hole" is */
for (;;)
{
int j = 2 * i + 1;
if (j >= heapLength)
break;
if (j + 1 < heapLength &&
heap[j] < heap[j + 1])
j++;
if (val >= heap[j])
break;
heap[i] = heap[j];
i = j;
}
heap[i] = val;
return result;
}
/*
* findDependencyLoops - identify loops in TopoSort's failure output,
* and pass each such loop to repairDependencyLoop() for action
*
* In general there may be many loops in the set of objects returned by
* TopoSort; for speed we should try to repair as many loops as we can
* before trying TopoSort again. We can safely repair loops that are
* disjoint (have no members in common); if we find overlapping loops
* then we repair only the first one found, because the action taken to
* repair the first might have repaired the other as well. (If not,
* we'll fix it on the next go-round.)
*
* objs[] lists the objects TopoSort couldn't sort
* nObjs is the number of such objects
* totObjs is the total number of objects in the universe
*/
static void
findDependencyLoops(DumpableObject **objs, int nObjs, int totObjs)
{
/*
* We use three data structures here:
*
* processed[] is a bool array indexed by dump ID, marking the objects
* already processed during this invocation of findDependencyLoops().
*
* searchFailed[] is another array indexed by dump ID. searchFailed[j] is
* set to dump ID k if we have proven that there is no dependency path
* leading from object j back to start point k. This allows us to skip
* useless searching when there are multiple dependency paths from k to j,
* which is a common situation. We could use a simple bool array for
* this, but then we'd need to re-zero it for each start point, resulting
* in O(N^2) zeroing work. Using the start point's dump ID as the "true"
* value lets us skip clearing the array before we consider the next start
* point.
*
* workspace[] is an array of DumpableObject pointers, in which we try to
* build lists of objects constituting loops. We make workspace[] large
* enough to hold all the objects in TopoSort's output, which is huge
* overkill in most cases but could theoretically be necessary if there is
* a single dependency chain linking all the objects.
*/
bool *processed;
DumpId *searchFailed;
DumpableObject **workspace;
bool fixedloop;
int i;
processed = (bool *) pg_malloc0((getMaxDumpId() + 1) * sizeof(bool));
searchFailed = (DumpId *) pg_malloc0((getMaxDumpId() + 1) * sizeof(DumpId));
workspace = (DumpableObject **) pg_malloc(totObjs * sizeof(DumpableObject *));
fixedloop = false;
for (i = 0; i < nObjs; i++)
{
DumpableObject *obj = objs[i];
int looplen;
int j;
looplen = findLoop(obj,
obj->dumpId,
processed,
searchFailed,
workspace,
0);
if (looplen > 0)
{
/* Found a loop, repair it */
repairDependencyLoop(workspace, looplen);
fixedloop = true;
/* Mark loop members as processed */
for (j = 0; j < looplen; j++)
processed[workspace[j]->dumpId] = true;
}
else
{
/*
* There's no loop starting at this object, but mark it processed
* anyway. This is not necessary for correctness, but saves later
* invocations of findLoop() from uselessly chasing references to
* such an object.
*/
processed[obj->dumpId] = true;
}
}
/* We'd better have fixed at least one loop */
if (!fixedloop)
exit_horribly(modulename, "could not identify dependency loop\n");
free(workspace);
free(searchFailed);
free(processed);
}
/*
* Recursively search for a circular dependency loop that doesn't include
* any already-processed objects.
*
* obj: object we are examining now
* startPoint: dumpId of starting object for the hoped-for circular loop
* processed[]: flag array marking already-processed objects
* searchFailed[]: flag array marking already-unsuccessfully-visited objects
* workspace[]: work array in which we are building list of loop members
* depth: number of valid entries in workspace[] at call
*
* On success, the length of the loop is returned, and workspace[] is filled
* with pointers to the members of the loop. On failure, we return 0.
*
* Note: it is possible that the given starting object is a member of more
* than one cycle; if so, we will find an arbitrary one of the cycles.
*/
static int
findLoop(DumpableObject *obj,
DumpId startPoint,
bool *processed,
DumpId *searchFailed,
DumpableObject **workspace,
int depth)
{
int i;
/*
* Reject if obj is already processed. This test prevents us from finding
* loops that overlap previously-processed loops.
*/
if (processed[obj->dumpId])
return 0;
/*
* If we've already proven there is no path from this object back to the
* startPoint, forget it.
*/
if (searchFailed[obj->dumpId] == startPoint)
return 0;
/*
* Reject if obj is already present in workspace. This test prevents us
* from going into infinite recursion if we are given a startPoint object
* that links to a cycle it's not a member of, and it guarantees that we
* can't overflow the allocated size of workspace[].
*/
for (i = 0; i < depth; i++)
{
if (workspace[i] == obj)
return 0;
}
/*
* Okay, tentatively add obj to workspace
*/
workspace[depth++] = obj;
/*
* See if we've found a loop back to the desired startPoint; if so, done
*/
for (i = 0; i < obj->nDeps; i++)
{
if (obj->dependencies[i] == startPoint)
return depth;
}
/*
* Recurse down each outgoing branch
*/
for (i = 0; i < obj->nDeps; i++)
{
DumpableObject *nextobj = findObjectByDumpId(obj->dependencies[i]);
int newDepth;
if (!nextobj)
continue; /* ignore dependencies on undumped objects */
newDepth = findLoop(nextobj,
startPoint,
processed,
searchFailed,
workspace,
depth);
if (newDepth > 0)
return newDepth;
}
/*
* Remember there is no path from here back to startPoint
*/
searchFailed[obj->dumpId] = startPoint;
return 0;
}
/*
* A user-defined datatype will have a dependency loop with each of its
* I/O functions (since those have the datatype as input or output).
* Similarly, a range type will have a loop with its canonicalize function,
* if any. Break the loop by making the function depend on the associated
* shell type, instead.
*/
static void
repairTypeFuncLoop(DumpableObject *typeobj, DumpableObject *funcobj)
{
TypeInfo *typeInfo = (TypeInfo *) typeobj;
/* remove function's dependency on type */
removeObjectDependency(funcobj, typeobj->dumpId);
/* add function's dependency on shell type, instead */
if (typeInfo->shellType)
{
addObjectDependency(funcobj, typeInfo->shellType->dobj.dumpId);
/* Mark shell type as to be dumped if any such function is */
if (funcobj->dump)
typeInfo->shellType->dobj.dump = true;
}
}
/*
* Because we force a view to depend on its ON SELECT rule, while there
* will be an implicit dependency in the other direction, we need to break
* the loop. If there are no other objects in the loop then we can remove
* the implicit dependency and leave the ON SELECT rule non-separate.
* This applies to matviews, as well.
*/
static void
repairViewRuleLoop(DumpableObject *viewobj,
DumpableObject *ruleobj)
{
/* remove rule's dependency on view */
removeObjectDependency(ruleobj, viewobj->dumpId);
}
/*
* However, if there are other objects in the loop, we must break the loop
* by making the ON SELECT rule a separately-dumped object.
*
* Because findLoop() finds shorter cycles before longer ones, it's likely
* that we will have previously fired repairViewRuleLoop() and removed the
* rule's dependency on the view. Put it back to ensure the rule won't be
* emitted before the view.
*
* Note: this approach does *not* work for matviews, at the moment.
*/
static void
repairViewRuleMultiLoop(DumpableObject *viewobj,
DumpableObject *ruleobj)
{
TableInfo *viewinfo = (TableInfo *) viewobj;
RuleInfo *ruleinfo = (RuleInfo *) ruleobj;
int i;
/* remove view's dependency on rule */
removeObjectDependency(viewobj, ruleobj->dumpId);
/* pretend view is a plain table and dump it that way */
viewinfo->relkind = 'r'; /* RELKIND_RELATION */
/* mark rule as needing its own dump */
ruleinfo->separate = true;
/* move any reloptions from view to rule */
if (viewinfo->reloptions)
{
ruleinfo->reloptions = viewinfo->reloptions;
viewinfo->reloptions = NULL;
}
/* put back rule's dependency on view */
addObjectDependency(ruleobj, viewobj->dumpId);
/* now that rule is separate, it must be post-data */
addObjectDependency(ruleobj, postDataBoundId);
/* also, any triggers on the view must be dumped after the rule */
for (i = 0; i < viewinfo->numTriggers; i++)
addObjectDependency(&(viewinfo->triggers[i].dobj), ruleobj->dumpId);
}
/*
* If a matview is involved in a multi-object loop, we can't currently fix
* that by splitting off the rule. As a stopgap, we try to fix it by
* dropping the constraint that the matview be dumped in the pre-data section.
* This is sufficient to handle cases where a matview depends on some unique
* index, as can happen if it has a GROUP BY for example.
*
* Note that the "next object" is not necessarily the matview itself;
* it could be the matview's rowtype, for example. We may come through here
* several times while removing all the pre-data linkages.
*/
static void
repairMatViewBoundaryMultiLoop(DumpableObject *matviewobj,
DumpableObject *boundaryobj,
DumpableObject *nextobj)
{
TableInfo *matviewinfo = (TableInfo *) matviewobj;
/* remove boundary's dependency on object after it in loop */
removeObjectDependency(boundaryobj, nextobj->dumpId);
/* mark matview as postponed into post-data section */
matviewinfo->postponed_def = true;
}
/*
* Because we make tables depend on their CHECK constraints, while there
* will be an automatic dependency in the other direction, we need to break
* the loop. If there are no other objects in the loop then we can remove
* the automatic dependency and leave the CHECK constraint non-separate.
*/
static void
repairTableConstraintLoop(DumpableObject *tableobj,
DumpableObject *constraintobj)
{
/* remove constraint's dependency on table */
removeObjectDependency(constraintobj, tableobj->dumpId);
}
/*
* However, if there are other objects in the loop, we must break the loop
* by making the CHECK constraint a separately-dumped object.
*
* Because findLoop() finds shorter cycles before longer ones, it's likely
* that we will have previously fired repairTableConstraintLoop() and
* removed the constraint's dependency on the table. Put it back to ensure
* the constraint won't be emitted before the table...
*/
static void
repairTableConstraintMultiLoop(DumpableObject *tableobj,
DumpableObject *constraintobj)
{
/* remove table's dependency on constraint */
removeObjectDependency(tableobj, constraintobj->dumpId);
/* mark constraint as needing its own dump */
((ConstraintInfo *) constraintobj)->separate = true;
/* put back constraint's dependency on table */
addObjectDependency(constraintobj, tableobj->dumpId);
/* now that constraint is separate, it must be post-data */
addObjectDependency(constraintobj, postDataBoundId);
}
/*
* Attribute defaults behave exactly the same as CHECK constraints...
*/
static void
repairTableAttrDefLoop(DumpableObject *tableobj,
DumpableObject *attrdefobj)
{
/* remove attrdef's dependency on table */
removeObjectDependency(attrdefobj, tableobj->dumpId);
}
static void
repairTableAttrDefMultiLoop(DumpableObject *tableobj,
DumpableObject *attrdefobj)
{
/* remove table's dependency on attrdef */
removeObjectDependency(tableobj, attrdefobj->dumpId);
/* mark attrdef as needing its own dump */
((AttrDefInfo *) attrdefobj)->separate = true;
/* put back attrdef's dependency on table */
addObjectDependency(attrdefobj, tableobj->dumpId);
}
/*
* CHECK constraints on domains work just like those on tables ...
*/
static void
repairDomainConstraintLoop(DumpableObject *domainobj,
DumpableObject *constraintobj)
{
/* remove constraint's dependency on domain */
removeObjectDependency(constraintobj, domainobj->dumpId);
}
static void
repairDomainConstraintMultiLoop(DumpableObject *domainobj,