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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
|
/*-------------------------------------------------------------------------
*
* indexcmds.c
* POSTGRES define and remove index code.
*
* Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
* src/backend/commands/indexcmds.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "access/amapi.h"
#include "access/heapam.h"
#include "access/htup_details.h"
#include "access/reloptions.h"
#include "access/sysattr.h"
#include "access/tableam.h"
#include "access/xact.h"
#include "catalog/catalog.h"
#include "catalog/index.h"
#include "catalog/indexing.h"
#include "catalog/pg_am.h"
#include "catalog/pg_constraint.h"
#include "catalog/pg_database.h"
#include "catalog/pg_inherits.h"
#include "catalog/pg_namespace.h"
#include "catalog/pg_opclass.h"
#include "catalog/pg_opfamily.h"
#include "catalog/pg_tablespace.h"
#include "catalog/pg_type.h"
#include "commands/comment.h"
#include "commands/dbcommands.h"
#include "commands/defrem.h"
#include "commands/event_trigger.h"
#include "commands/progress.h"
#include "commands/tablecmds.h"
#include "commands/tablespace.h"
#include "mb/pg_wchar.h"
#include "miscadmin.h"
#include "nodes/makefuncs.h"
#include "nodes/nodeFuncs.h"
#include "optimizer/optimizer.h"
#include "parser/parse_coerce.h"
#include "parser/parse_func.h"
#include "parser/parse_oper.h"
#include "partitioning/partdesc.h"
#include "pgstat.h"
#include "rewrite/rewriteManip.h"
#include "storage/lmgr.h"
#include "storage/proc.h"
#include "storage/procarray.h"
#include "storage/sinvaladt.h"
#include "utils/acl.h"
#include "utils/builtins.h"
#include "utils/fmgroids.h"
#include "utils/guc.h"
#include "utils/inval.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
#include "utils/partcache.h"
#include "utils/pg_rusage.h"
#include "utils/regproc.h"
#include "utils/snapmgr.h"
#include "utils/syscache.h"
/* non-export function prototypes */
static bool CompareOpclassOptions(Datum *opts1, Datum *opts2, int natts);
static void CheckPredicate(Expr *predicate);
static void ComputeIndexAttrs(IndexInfo *indexInfo,
Oid *typeOidP,
Oid *collationOidP,
Oid *classOidP,
int16 *colOptionP,
List *attList,
List *exclusionOpNames,
Oid relId,
const char *accessMethodName, Oid accessMethodId,
bool amcanorder,
bool isconstraint,
Oid ddl_userid,
int ddl_sec_context,
int *ddl_save_nestlevel);
static char *ChooseIndexName(const char *tabname, Oid namespaceId,
List *colnames, List *exclusionOpNames,
bool primary, bool isconstraint);
static char *ChooseIndexNameAddition(List *colnames);
static List *ChooseIndexColumnNames(List *indexElems);
static void ReindexIndex(RangeVar *indexRelation, ReindexParams *params,
bool isTopLevel);
static void RangeVarCallbackForReindexIndex(const RangeVar *relation,
Oid relId, Oid oldRelId, void *arg);
static Oid ReindexTable(RangeVar *relation, ReindexParams *params,
bool isTopLevel);
static void ReindexMultipleTables(const char *objectName,
ReindexObjectType objectKind, ReindexParams *params);
static void reindex_error_callback(void *arg);
static void ReindexPartitions(Oid relid, ReindexParams *params,
bool isTopLevel);
static void ReindexMultipleInternal(List *relids,
ReindexParams *params);
static bool ReindexRelationConcurrently(Oid relationOid,
ReindexParams *params);
static void update_relispartition(Oid relationId, bool newval);
static inline void set_indexsafe_procflags(void);
/*
* callback argument type for RangeVarCallbackForReindexIndex()
*/
struct ReindexIndexCallbackState
{
ReindexParams params; /* options from statement */
Oid locked_table_oid; /* tracks previously locked table */
};
/*
* callback arguments for reindex_error_callback()
*/
typedef struct ReindexErrorInfo
{
char *relname;
char *relnamespace;
char relkind;
} ReindexErrorInfo;
/*
* CheckIndexCompatible
* Determine whether an existing index definition is compatible with a
* prospective index definition, such that the existing index storage
* could become the storage of the new index, avoiding a rebuild.
*
* 'oldId': the OID of the existing index
* 'accessMethodName': name of the AM to use.
* 'attributeList': a list of IndexElem specifying columns and expressions
* to index on.
* 'exclusionOpNames': list of names of exclusion-constraint operators,
* or NIL if not an exclusion constraint.
*
* This is tailored to the needs of ALTER TABLE ALTER TYPE, which recreates
* any indexes that depended on a changing column from their pg_get_indexdef
* or pg_get_constraintdef definitions. We omit some of the sanity checks of
* DefineIndex. We assume that the old and new indexes have the same number
* of columns and that if one has an expression column or predicate, both do.
* Errors arising from the attribute list still apply.
*
* Most column type changes that can skip a table rewrite do not invalidate
* indexes. We acknowledge this when all operator classes, collations and
* exclusion operators match. Though we could further permit intra-opfamily
* changes for btree and hash indexes, that adds subtle complexity with no
* concrete benefit for core types. Note, that INCLUDE columns aren't
* checked by this function, for them it's enough that table rewrite is
* skipped.
*
* When a comparison or exclusion operator has a polymorphic input type, the
* actual input types must also match. This defends against the possibility
* that operators could vary behavior in response to get_fn_expr_argtype().
* At present, this hazard is theoretical: check_exclusion_constraint() and
* all core index access methods decline to set fn_expr for such calls.
*
* We do not yet implement a test to verify compatibility of expression
* columns or predicates, so assume any such index is incompatible.
*/
bool
CheckIndexCompatible(Oid oldId,
const char *accessMethodName,
List *attributeList,
List *exclusionOpNames)
{
bool isconstraint;
Oid *typeObjectId;
Oid *collationObjectId;
Oid *classObjectId;
Oid accessMethodId;
Oid relationId;
HeapTuple tuple;
Form_pg_index indexForm;
Form_pg_am accessMethodForm;
IndexAmRoutine *amRoutine;
bool amcanorder;
bool amsummarizing;
int16 *coloptions;
IndexInfo *indexInfo;
int numberOfAttributes;
int old_natts;
bool ret = true;
oidvector *old_indclass;
oidvector *old_indcollation;
Relation irel;
int i;
Datum d;
/* Caller should already have the relation locked in some way. */
relationId = IndexGetRelation(oldId, false);
/*
* We can pretend isconstraint = false unconditionally. It only serves to
* decide the text of an error message that should never happen for us.
*/
isconstraint = false;
numberOfAttributes = list_length(attributeList);
Assert(numberOfAttributes > 0);
Assert(numberOfAttributes <= INDEX_MAX_KEYS);
/* look up the access method */
tuple = SearchSysCache1(AMNAME, PointerGetDatum(accessMethodName));
if (!HeapTupleIsValid(tuple))
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_OBJECT),
errmsg("access method \"%s\" does not exist",
accessMethodName)));
accessMethodForm = (Form_pg_am) GETSTRUCT(tuple);
accessMethodId = accessMethodForm->oid;
amRoutine = GetIndexAmRoutine(accessMethodForm->amhandler);
ReleaseSysCache(tuple);
amcanorder = amRoutine->amcanorder;
amsummarizing = amRoutine->amsummarizing;
/*
* Compute the operator classes, collations, and exclusion operators for
* the new index, so we can test whether it's compatible with the existing
* one. Note that ComputeIndexAttrs might fail here, but that's OK:
* DefineIndex would have failed later. Our attributeList contains only
* key attributes, thus we're filling ii_NumIndexAttrs and
* ii_NumIndexKeyAttrs with same value.
*/
indexInfo = makeIndexInfo(numberOfAttributes, numberOfAttributes,
accessMethodId, NIL, NIL, false, false,
false, false, amsummarizing);
typeObjectId = palloc_array(Oid, numberOfAttributes);
collationObjectId = palloc_array(Oid, numberOfAttributes);
classObjectId = palloc_array(Oid, numberOfAttributes);
coloptions = palloc_array(int16, numberOfAttributes);
ComputeIndexAttrs(indexInfo,
typeObjectId, collationObjectId, classObjectId,
coloptions, attributeList,
exclusionOpNames, relationId,
accessMethodName, accessMethodId,
amcanorder, isconstraint, InvalidOid, 0, NULL);
/* Get the soon-obsolete pg_index tuple. */
tuple = SearchSysCache1(INDEXRELID, ObjectIdGetDatum(oldId));
if (!HeapTupleIsValid(tuple))
elog(ERROR, "cache lookup failed for index %u", oldId);
indexForm = (Form_pg_index) GETSTRUCT(tuple);
/*
* We don't assess expressions or predicates; assume incompatibility.
* Also, if the index is invalid for any reason, treat it as incompatible.
*/
if (!(heap_attisnull(tuple, Anum_pg_index_indpred, NULL) &&
heap_attisnull(tuple, Anum_pg_index_indexprs, NULL) &&
indexForm->indisvalid))
{
ReleaseSysCache(tuple);
return false;
}
/* Any change in operator class or collation breaks compatibility. */
old_natts = indexForm->indnkeyatts;
Assert(old_natts == numberOfAttributes);
d = SysCacheGetAttrNotNull(INDEXRELID, tuple, Anum_pg_index_indcollation);
old_indcollation = (oidvector *) DatumGetPointer(d);
d = SysCacheGetAttrNotNull(INDEXRELID, tuple, Anum_pg_index_indclass);
old_indclass = (oidvector *) DatumGetPointer(d);
ret = (memcmp(old_indclass->values, classObjectId,
old_natts * sizeof(Oid)) == 0 &&
memcmp(old_indcollation->values, collationObjectId,
old_natts * sizeof(Oid)) == 0);
ReleaseSysCache(tuple);
if (!ret)
return false;
/* For polymorphic opcintype, column type changes break compatibility. */
irel = index_open(oldId, AccessShareLock); /* caller probably has a lock */
for (i = 0; i < old_natts; i++)
{
if (IsPolymorphicType(get_opclass_input_type(classObjectId[i])) &&
TupleDescAttr(irel->rd_att, i)->atttypid != typeObjectId[i])
{
ret = false;
break;
}
}
/* Any change in opclass options break compatibility. */
if (ret)
{
Datum *opclassOptions = RelationGetIndexRawAttOptions(irel);
ret = CompareOpclassOptions(opclassOptions,
indexInfo->ii_OpclassOptions, old_natts);
if (opclassOptions)
pfree(opclassOptions);
}
/* Any change in exclusion operator selections breaks compatibility. */
if (ret && indexInfo->ii_ExclusionOps != NULL)
{
Oid *old_operators,
*old_procs;
uint16 *old_strats;
RelationGetExclusionInfo(irel, &old_operators, &old_procs, &old_strats);
ret = memcmp(old_operators, indexInfo->ii_ExclusionOps,
old_natts * sizeof(Oid)) == 0;
/* Require an exact input type match for polymorphic operators. */
if (ret)
{
for (i = 0; i < old_natts && ret; i++)
{
Oid left,
right;
op_input_types(indexInfo->ii_ExclusionOps[i], &left, &right);
if ((IsPolymorphicType(left) || IsPolymorphicType(right)) &&
TupleDescAttr(irel->rd_att, i)->atttypid != typeObjectId[i])
{
ret = false;
break;
}
}
}
}
index_close(irel, NoLock);
return ret;
}
/*
* CompareOpclassOptions
*
* Compare per-column opclass options which are represented by arrays of text[]
* datums. Both elements of arrays and array themselves can be NULL.
*/
static bool
CompareOpclassOptions(Datum *opts1, Datum *opts2, int natts)
{
int i;
if (!opts1 && !opts2)
return true;
for (i = 0; i < natts; i++)
{
Datum opt1 = opts1 ? opts1[i] : (Datum) 0;
Datum opt2 = opts2 ? opts2[i] : (Datum) 0;
if (opt1 == (Datum) 0)
{
if (opt2 == (Datum) 0)
continue;
else
return false;
}
else if (opt2 == (Datum) 0)
return false;
/* Compare non-NULL text[] datums. */
if (!DatumGetBool(DirectFunctionCall2(array_eq, opt1, opt2)))
return false;
}
return true;
}
/*
* WaitForOlderSnapshots
*
* Wait for transactions that might have an older snapshot than the given xmin
* limit, because it might not contain tuples deleted just before it has
* been taken. Obtain a list of VXIDs of such transactions, and wait for them
* individually. This is used when building an index concurrently.
*
* We can exclude any running transactions that have xmin > the xmin given;
* their oldest snapshot must be newer than our xmin limit.
* We can also exclude any transactions that have xmin = zero, since they
* evidently have no live snapshot at all (and any one they might be in
* process of taking is certainly newer than ours). Transactions in other
* DBs can be ignored too, since they'll never even be able to see the
* index being worked on.
*
* We can also exclude autovacuum processes and processes running manual
* lazy VACUUMs, because they won't be fazed by missing index entries
* either. (Manual ANALYZEs, however, can't be excluded because they
* might be within transactions that are going to do arbitrary operations
* later.) Processes running CREATE INDEX CONCURRENTLY or REINDEX CONCURRENTLY
* on indexes that are neither expressional nor partial are also safe to
* ignore, since we know that those processes won't examine any data
* outside the table they're indexing.
*
* Also, GetCurrentVirtualXIDs never reports our own vxid, so we need not
* check for that.
*
* If a process goes idle-in-transaction with xmin zero, we do not need to
* wait for it anymore, per the above argument. We do not have the
* infrastructure right now to stop waiting if that happens, but we can at
* least avoid the folly of waiting when it is idle at the time we would
* begin to wait. We do this by repeatedly rechecking the output of
* GetCurrentVirtualXIDs. If, during any iteration, a particular vxid
* doesn't show up in the output, we know we can forget about it.
*/
void
WaitForOlderSnapshots(TransactionId limitXmin, bool progress)
{
int n_old_snapshots;
int i;
VirtualTransactionId *old_snapshots;
old_snapshots = GetCurrentVirtualXIDs(limitXmin, true, false,
PROC_IS_AUTOVACUUM | PROC_IN_VACUUM
| PROC_IN_SAFE_IC,
&n_old_snapshots);
if (progress)
pgstat_progress_update_param(PROGRESS_WAITFOR_TOTAL, n_old_snapshots);
for (i = 0; i < n_old_snapshots; i++)
{
if (!VirtualTransactionIdIsValid(old_snapshots[i]))
continue; /* found uninteresting in previous cycle */
if (i > 0)
{
/* see if anything's changed ... */
VirtualTransactionId *newer_snapshots;
int n_newer_snapshots;
int j;
int k;
newer_snapshots = GetCurrentVirtualXIDs(limitXmin,
true, false,
PROC_IS_AUTOVACUUM | PROC_IN_VACUUM
| PROC_IN_SAFE_IC,
&n_newer_snapshots);
for (j = i; j < n_old_snapshots; j++)
{
if (!VirtualTransactionIdIsValid(old_snapshots[j]))
continue; /* found uninteresting in previous cycle */
for (k = 0; k < n_newer_snapshots; k++)
{
if (VirtualTransactionIdEquals(old_snapshots[j],
newer_snapshots[k]))
break;
}
if (k >= n_newer_snapshots) /* not there anymore */
SetInvalidVirtualTransactionId(old_snapshots[j]);
}
pfree(newer_snapshots);
}
if (VirtualTransactionIdIsValid(old_snapshots[i]))
{
/* If requested, publish who we're going to wait for. */
if (progress)
{
PGPROC *holder = BackendIdGetProc(old_snapshots[i].backendId);
if (holder)
pgstat_progress_update_param(PROGRESS_WAITFOR_CURRENT_PID,
holder->pid);
}
VirtualXactLock(old_snapshots[i], true);
}
if (progress)
pgstat_progress_update_param(PROGRESS_WAITFOR_DONE, i + 1);
}
}
/*
* DefineIndex
* Creates a new index.
*
* This function manages the current userid according to the needs of pg_dump.
* Recreating old-database catalog entries in new-database is fine, regardless
* of which users would have permission to recreate those entries now. That's
* just preservation of state. Running opaque expressions, like calling a
* function named in a catalog entry or evaluating a pg_node_tree in a catalog
* entry, as anyone other than the object owner, is not fine. To adhere to
* those principles and to remain fail-safe, use the table owner userid for
* most ACL checks. Use the original userid for ACL checks reached without
* traversing opaque expressions. (pg_dump can predict such ACL checks from
* catalogs.) Overall, this is a mess. Future DDL development should
* consider offering one DDL command for catalog setup and a separate DDL
* command for steps that run opaque expressions.
*
* 'relationId': the OID of the heap relation on which the index is to be
* created
* 'stmt': IndexStmt describing the properties of the new index.
* 'indexRelationId': normally InvalidOid, but during bootstrap can be
* nonzero to specify a preselected OID for the index.
* 'parentIndexId': the OID of the parent index; InvalidOid if not the child
* of a partitioned index.
* 'parentConstraintId': the OID of the parent constraint; InvalidOid if not
* the child of a constraint (only used when recursing)
* 'total_parts': total number of direct and indirect partitions of relation;
* pass -1 if not known or rel is not partitioned.
* 'is_alter_table': this is due to an ALTER rather than a CREATE operation.
* 'check_rights': check for CREATE rights in namespace and tablespace. (This
* should be true except when ALTER is deleting/recreating an index.)
* 'check_not_in_use': check for table not already in use in current session.
* This should be true unless caller is holding the table open, in which
* case the caller had better have checked it earlier.
* 'skip_build': make the catalog entries but don't create the index files
* 'quiet': suppress the NOTICE chatter ordinarily provided for constraints.
*
* Returns the object address of the created index.
*/
ObjectAddress
DefineIndex(Oid relationId,
IndexStmt *stmt,
Oid indexRelationId,
Oid parentIndexId,
Oid parentConstraintId,
int total_parts,
bool is_alter_table,
bool check_rights,
bool check_not_in_use,
bool skip_build,
bool quiet)
{
bool concurrent;
char *indexRelationName;
char *accessMethodName;
Oid *typeObjectId;
Oid *collationObjectId;
Oid *classObjectId;
Oid accessMethodId;
Oid namespaceId;
Oid tablespaceId;
Oid createdConstraintId = InvalidOid;
List *indexColNames;
List *allIndexParams;
Relation rel;
HeapTuple tuple;
Form_pg_am accessMethodForm;
IndexAmRoutine *amRoutine;
bool amcanorder;
bool amissummarizing;
amoptions_function amoptions;
bool partitioned;
bool safe_index;
Datum reloptions;
int16 *coloptions;
IndexInfo *indexInfo;
bits16 flags;
bits16 constr_flags;
int numberOfAttributes;
int numberOfKeyAttributes;
TransactionId limitXmin;
ObjectAddress address;
LockRelId heaprelid;
LOCKTAG heaplocktag;
LOCKMODE lockmode;
Snapshot snapshot;
Oid root_save_userid;
int root_save_sec_context;
int root_save_nestlevel;
root_save_nestlevel = NewGUCNestLevel();
/*
* Some callers need us to run with an empty default_tablespace; this is a
* necessary hack to be able to reproduce catalog state accurately when
* recreating indexes after table-rewriting ALTER TABLE.
*/
if (stmt->reset_default_tblspc)
(void) set_config_option("default_tablespace", "",
PGC_USERSET, PGC_S_SESSION,
GUC_ACTION_SAVE, true, 0, false);
/*
* Force non-concurrent build on temporary relations, even if CONCURRENTLY
* was requested. Other backends can't access a temporary relation, so
* there's no harm in grabbing a stronger lock, and a non-concurrent DROP
* is more efficient. Do this before any use of the concurrent option is
* done.
*/
if (stmt->concurrent && get_rel_persistence(relationId) != RELPERSISTENCE_TEMP)
concurrent = true;
else
concurrent = false;
/*
* Start progress report. If we're building a partition, this was already
* done.
*/
if (!OidIsValid(parentIndexId))
{
pgstat_progress_start_command(PROGRESS_COMMAND_CREATE_INDEX,
relationId);
pgstat_progress_update_param(PROGRESS_CREATEIDX_COMMAND,
concurrent ?
PROGRESS_CREATEIDX_COMMAND_CREATE_CONCURRENTLY :
PROGRESS_CREATEIDX_COMMAND_CREATE);
}
/*
* No index OID to report yet
*/
pgstat_progress_update_param(PROGRESS_CREATEIDX_INDEX_OID,
InvalidOid);
/*
* count key attributes in index
*/
numberOfKeyAttributes = list_length(stmt->indexParams);
/*
* Calculate the new list of index columns including both key columns and
* INCLUDE columns. Later we can determine which of these are key
* columns, and which are just part of the INCLUDE list by checking the
* list position. A list item in a position less than ii_NumIndexKeyAttrs
* is part of the key columns, and anything equal to and over is part of
* the INCLUDE columns.
*/
allIndexParams = list_concat_copy(stmt->indexParams,
stmt->indexIncludingParams);
numberOfAttributes = list_length(allIndexParams);
if (numberOfKeyAttributes <= 0)
ereport(ERROR,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("must specify at least one column")));
if (numberOfAttributes > INDEX_MAX_KEYS)
ereport(ERROR,
(errcode(ERRCODE_TOO_MANY_COLUMNS),
errmsg("cannot use more than %d columns in an index",
INDEX_MAX_KEYS)));
/*
* Only SELECT ... FOR UPDATE/SHARE are allowed while doing a standard
* index build; but for concurrent builds we allow INSERT/UPDATE/DELETE
* (but not VACUUM).
*
* NB: Caller is responsible for making sure that relationId refers to the
* relation on which the index should be built; except in bootstrap mode,
* this will typically require the caller to have already locked the
* relation. To avoid lock upgrade hazards, that lock should be at least
* as strong as the one we take here.
*
* NB: If the lock strength here ever changes, code that is run by
* parallel workers under the control of certain particular ambuild
* functions will need to be updated, too.
*/
lockmode = concurrent ? ShareUpdateExclusiveLock : ShareLock;
rel = table_open(relationId, lockmode);
/*
* Switch to the table owner's userid, so that any index functions are run
* as that user. Also lock down security-restricted operations. We
* already arranged to make GUC variable changes local to this command.
*/
GetUserIdAndSecContext(&root_save_userid, &root_save_sec_context);
SetUserIdAndSecContext(rel->rd_rel->relowner,
root_save_sec_context | SECURITY_RESTRICTED_OPERATION);
namespaceId = RelationGetNamespace(rel);
/* Ensure that it makes sense to index this kind of relation */
switch (rel->rd_rel->relkind)
{
case RELKIND_RELATION:
case RELKIND_MATVIEW:
case RELKIND_PARTITIONED_TABLE:
/* OK */
break;
default:
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("cannot create index on relation \"%s\"",
RelationGetRelationName(rel)),
errdetail_relkind_not_supported(rel->rd_rel->relkind)));
break;
}
/*
* Establish behavior for partitioned tables, and verify sanity of
* parameters.
*
* We do not build an actual index in this case; we only create a few
* catalog entries. The actual indexes are built by recursing for each
* partition.
*/
partitioned = rel->rd_rel->relkind == RELKIND_PARTITIONED_TABLE;
if (partitioned)
{
/*
* Note: we check 'stmt->concurrent' rather than 'concurrent', so that
* the error is thrown also for temporary tables. Seems better to be
* consistent, even though we could do it on temporary table because
* we're not actually doing it concurrently.
*/
if (stmt->concurrent)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot create index on partitioned table \"%s\" concurrently",
RelationGetRelationName(rel))));
if (stmt->excludeOpNames)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot create exclusion constraints on partitioned table \"%s\"",
RelationGetRelationName(rel))));
}
/*
* Don't try to CREATE INDEX on temp tables of other backends.
*/
if (RELATION_IS_OTHER_TEMP(rel))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot create indexes on temporary tables of other sessions")));
/*
* Unless our caller vouches for having checked this already, insist that
* the table not be in use by our own session, either. Otherwise we might
* fail to make entries in the new index (for instance, if an INSERT or
* UPDATE is in progress and has already made its list of target indexes).
*/
if (check_not_in_use)
CheckTableNotInUse(rel, "CREATE INDEX");
/*
* Verify we (still) have CREATE rights in the rel's namespace.
* (Presumably we did when the rel was created, but maybe not anymore.)
* Skip check if caller doesn't want it. Also skip check if
* bootstrapping, since permissions machinery may not be working yet.
*/
if (check_rights && !IsBootstrapProcessingMode())
{
AclResult aclresult;
aclresult = object_aclcheck(NamespaceRelationId, namespaceId, root_save_userid,
ACL_CREATE);
if (aclresult != ACLCHECK_OK)
aclcheck_error(aclresult, OBJECT_SCHEMA,
get_namespace_name(namespaceId));
}
/*
* Select tablespace to use. If not specified, use default tablespace
* (which may in turn default to database's default).
*/
if (stmt->tableSpace)
{
tablespaceId = get_tablespace_oid(stmt->tableSpace, false);
if (partitioned && tablespaceId == MyDatabaseTableSpace)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot specify default tablespace for partitioned relations")));
}
else
{
tablespaceId = GetDefaultTablespace(rel->rd_rel->relpersistence,
partitioned);
/* note InvalidOid is OK in this case */
}
/* Check tablespace permissions */
if (check_rights &&
OidIsValid(tablespaceId) && tablespaceId != MyDatabaseTableSpace)
{
AclResult aclresult;
aclresult = object_aclcheck(TableSpaceRelationId, tablespaceId, root_save_userid,
ACL_CREATE);
if (aclresult != ACLCHECK_OK)
aclcheck_error(aclresult, OBJECT_TABLESPACE,
get_tablespace_name(tablespaceId));
}
/*
* Force shared indexes into the pg_global tablespace. This is a bit of a
* hack but seems simpler than marking them in the BKI commands. On the
* other hand, if it's not shared, don't allow it to be placed there.
*/
if (rel->rd_rel->relisshared)
tablespaceId = GLOBALTABLESPACE_OID;
else if (tablespaceId == GLOBALTABLESPACE_OID)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("only shared relations can be placed in pg_global tablespace")));
/*
* Choose the index column names.
*/
indexColNames = ChooseIndexColumnNames(allIndexParams);
/*
* Select name for index if caller didn't specify
*/
indexRelationName = stmt->idxname;
if (indexRelationName == NULL)
indexRelationName = ChooseIndexName(RelationGetRelationName(rel),
namespaceId,
indexColNames,
stmt->excludeOpNames,
stmt->primary,
stmt->isconstraint);
/*
* look up the access method, verify it can handle the requested features
*/
accessMethodName = stmt->accessMethod;
tuple = SearchSysCache1(AMNAME, PointerGetDatum(accessMethodName));
if (!HeapTupleIsValid(tuple))
{
/*
* Hack to provide more-or-less-transparent updating of old RTREE
* indexes to GiST: if RTREE is requested and not found, use GIST.
*/
if (strcmp(accessMethodName, "rtree") == 0)
{
ereport(NOTICE,
(errmsg("substituting access method \"gist\" for obsolete method \"rtree\"")));
accessMethodName = "gist";
tuple = SearchSysCache1(AMNAME, PointerGetDatum(accessMethodName));
}
if (!HeapTupleIsValid(tuple))
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_OBJECT),
errmsg("access method \"%s\" does not exist",
accessMethodName)));
}
accessMethodForm = (Form_pg_am) GETSTRUCT(tuple);
accessMethodId = accessMethodForm->oid;
amRoutine = GetIndexAmRoutine(accessMethodForm->amhandler);
pgstat_progress_update_param(PROGRESS_CREATEIDX_ACCESS_METHOD_OID,
accessMethodId);
if (stmt->unique && !amRoutine->amcanunique)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("access method \"%s\" does not support unique indexes",
accessMethodName)));
if (stmt->indexIncludingParams != NIL && !amRoutine->amcaninclude)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("access method \"%s\" does not support included columns",
accessMethodName)));
if (numberOfKeyAttributes > 1 && !amRoutine->amcanmulticol)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("access method \"%s\" does not support multicolumn indexes",
accessMethodName)));
if (stmt->excludeOpNames && amRoutine->amgettuple == NULL)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("access method \"%s\" does not support exclusion constraints",
accessMethodName)));
amcanorder = amRoutine->amcanorder;
amoptions = amRoutine->amoptions;
amissummarizing = amRoutine->amsummarizing;
pfree(amRoutine);
ReleaseSysCache(tuple);
/*
* Validate predicate, if given
*/
if (stmt->whereClause)
CheckPredicate((Expr *) stmt->whereClause);
/*
* Parse AM-specific options, convert to text array form, validate.
*/
reloptions = transformRelOptions((Datum) 0, stmt->options,
NULL, NULL, false, false);
(void) index_reloptions(amoptions, reloptions, true);
/*
* Prepare arguments for index_create, primarily an IndexInfo structure.
* Note that predicates must be in implicit-AND format. In a concurrent
* build, mark it not-ready-for-inserts.
*/
indexInfo = makeIndexInfo(numberOfAttributes,
numberOfKeyAttributes,
accessMethodId,
NIL, /* expressions, NIL for now */
make_ands_implicit((Expr *) stmt->whereClause),
stmt->unique,
stmt->nulls_not_distinct,
!concurrent,
concurrent,
amissummarizing);
typeObjectId = palloc_array(Oid, numberOfAttributes);
collationObjectId = palloc_array(Oid, numberOfAttributes);
classObjectId = palloc_array(Oid, numberOfAttributes);
coloptions = palloc_array(int16, numberOfAttributes);
ComputeIndexAttrs(indexInfo,
typeObjectId, collationObjectId, classObjectId,
coloptions, allIndexParams,
stmt->excludeOpNames, relationId,
accessMethodName, accessMethodId,
amcanorder, stmt->isconstraint, root_save_userid,
root_save_sec_context, &root_save_nestlevel);
/*
* Extra checks when creating a PRIMARY KEY index.
*/
if (stmt->primary)
index_check_primary_key(rel, indexInfo, is_alter_table, stmt);
/*
* If this table is partitioned and we're creating a unique index or a
* primary key, make sure that the partition key is a subset of the
* index's columns. Otherwise it would be possible to violate uniqueness
* by putting values that ought to be unique in different partitions.
*
* We could lift this limitation if we had global indexes, but those have
* their own problems, so this is a useful feature combination.
*/
if (partitioned && (stmt->unique || stmt->primary))
{
PartitionKey key = RelationGetPartitionKey(rel);
const char *constraint_type;
int i;
if (stmt->primary)
constraint_type = "PRIMARY KEY";
else if (stmt->unique)
constraint_type = "UNIQUE";
else if (stmt->excludeOpNames != NIL)
constraint_type = "EXCLUDE";
else
{
elog(ERROR, "unknown constraint type");
constraint_type = NULL; /* keep compiler quiet */
}
/*
* Verify that all the columns in the partition key appear in the
* unique key definition, with the same notion of equality.
*/
for (i = 0; i < key->partnatts; i++)
{
bool found = false;
int eq_strategy;
Oid ptkey_eqop;
int j;
/*
* Identify the equality operator associated with this partkey
* column. For list and range partitioning, partkeys use btree
* operator classes; hash partitioning uses hash operator classes.
* (Keep this in sync with ComputePartitionAttrs!)
*/
if (key->strategy == PARTITION_STRATEGY_HASH)
eq_strategy = HTEqualStrategyNumber;
else
eq_strategy = BTEqualStrategyNumber;
ptkey_eqop = get_opfamily_member(key->partopfamily[i],
key->partopcintype[i],
key->partopcintype[i],
eq_strategy);
if (!OidIsValid(ptkey_eqop))
elog(ERROR, "missing operator %d(%u,%u) in partition opfamily %u",
eq_strategy, key->partopcintype[i], key->partopcintype[i],
key->partopfamily[i]);
/*
* We'll need to be able to identify the equality operators
* associated with index columns, too. We know what to do with
* btree opclasses; if there are ever any other index types that
* support unique indexes, this logic will need extension.
*/
if (accessMethodId == BTREE_AM_OID)
eq_strategy = BTEqualStrategyNumber;
else
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot match partition key to an index using access method \"%s\"",
accessMethodName)));
/*
* It may be possible to support UNIQUE constraints when partition
* keys are expressions, but is it worth it? Give up for now.
*/
if (key->partattrs[i] == 0)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("unsupported %s constraint with partition key definition",
constraint_type),
errdetail("%s constraints cannot be used when partition keys include expressions.",
constraint_type)));
/* Search the index column(s) for a match */
for (j = 0; j < indexInfo->ii_NumIndexKeyAttrs; j++)
{
if (key->partattrs[i] == indexInfo->ii_IndexAttrNumbers[j])
{
/* Matched the column, now what about the collation and equality op? */
Oid idx_opfamily;
Oid idx_opcintype;
if (key->partcollation[i] != collationObjectId[j])
continue;
if (get_opclass_opfamily_and_input_type(classObjectId[j],
&idx_opfamily,
&idx_opcintype))
{
Oid idx_eqop;
idx_eqop = get_opfamily_member(idx_opfamily,
idx_opcintype,
idx_opcintype,
eq_strategy);
if (ptkey_eqop == idx_eqop)
{
found = true;
break;
}
}
}
}
if (!found)
{
Form_pg_attribute att;
att = TupleDescAttr(RelationGetDescr(rel),
key->partattrs[i] - 1);
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("unique constraint on partitioned table must include all partitioning columns"),
errdetail("%s constraint on table \"%s\" lacks column \"%s\" which is part of the partition key.",
constraint_type, RelationGetRelationName(rel),
NameStr(att->attname))));
}
}
}
/*
* We disallow indexes on system columns. They would not necessarily get
* updated correctly, and they don't seem useful anyway.
*/
for (int i = 0; i < indexInfo->ii_NumIndexAttrs; i++)
{
AttrNumber attno = indexInfo->ii_IndexAttrNumbers[i];
if (attno < 0)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("index creation on system columns is not supported")));
}
/*
* Also check for system columns used in expressions or predicates.
*/
if (indexInfo->ii_Expressions || indexInfo->ii_Predicate)
{
Bitmapset *indexattrs = NULL;
pull_varattnos((Node *) indexInfo->ii_Expressions, 1, &indexattrs);
pull_varattnos((Node *) indexInfo->ii_Predicate, 1, &indexattrs);
for (int i = FirstLowInvalidHeapAttributeNumber + 1; i < 0; i++)
{
if (bms_is_member(i - FirstLowInvalidHeapAttributeNumber,
indexattrs))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("index creation on system columns is not supported")));
}
}
/* Is index safe for others to ignore? See set_indexsafe_procflags() */
safe_index = indexInfo->ii_Expressions == NIL &&
indexInfo->ii_Predicate == NIL;
/*
* Report index creation if appropriate (delay this till after most of the
* error checks)
*/
if (stmt->isconstraint && !quiet)
{
const char *constraint_type;
if (stmt->primary)
constraint_type = "PRIMARY KEY";
else if (stmt->unique)
constraint_type = "UNIQUE";
else if (stmt->excludeOpNames != NIL)
constraint_type = "EXCLUDE";
else
{
elog(ERROR, "unknown constraint type");
constraint_type = NULL; /* keep compiler quiet */
}
ereport(DEBUG1,
(errmsg_internal("%s %s will create implicit index \"%s\" for table \"%s\"",
is_alter_table ? "ALTER TABLE / ADD" : "CREATE TABLE /",
constraint_type,
indexRelationName, RelationGetRelationName(rel))));
}
/*
* A valid stmt->oldNumber implies that we already have a built form of
* the index. The caller should also decline any index build.
*/
Assert(!RelFileNumberIsValid(stmt->oldNumber) || (skip_build && !concurrent));
/*
* Make the catalog entries for the index, including constraints. This
* step also actually builds the index, except if caller requested not to
* or in concurrent mode, in which case it'll be done later, or doing a
* partitioned index (because those don't have storage).
*/
flags = constr_flags = 0;
if (stmt->isconstraint)
flags |= INDEX_CREATE_ADD_CONSTRAINT;
if (skip_build || concurrent || partitioned)
flags |= INDEX_CREATE_SKIP_BUILD;
if (stmt->if_not_exists)
flags |= INDEX_CREATE_IF_NOT_EXISTS;
if (concurrent)
flags |= INDEX_CREATE_CONCURRENT;
if (partitioned)
flags |= INDEX_CREATE_PARTITIONED;
if (stmt->primary)
flags |= INDEX_CREATE_IS_PRIMARY;
/*
* If the table is partitioned, and recursion was declined but partitions
* exist, mark the index as invalid.
*/
if (partitioned && stmt->relation && !stmt->relation->inh)
{
PartitionDesc pd = RelationGetPartitionDesc(rel, true);
if (pd->nparts != 0)
flags |= INDEX_CREATE_INVALID;
}
if (stmt->deferrable)
constr_flags |= INDEX_CONSTR_CREATE_DEFERRABLE;
if (stmt->initdeferred)
constr_flags |= INDEX_CONSTR_CREATE_INIT_DEFERRED;
indexRelationId =
index_create(rel, indexRelationName, indexRelationId, parentIndexId,
parentConstraintId,
stmt->oldNumber, indexInfo, indexColNames,
accessMethodId, tablespaceId,
collationObjectId, classObjectId,
coloptions, reloptions,
flags, constr_flags,
allowSystemTableMods, !check_rights,
&createdConstraintId);
ObjectAddressSet(address, RelationRelationId, indexRelationId);
if (!OidIsValid(indexRelationId))
{
/*
* Roll back any GUC changes executed by index functions. Also revert
* to original default_tablespace if we changed it above.
*/
AtEOXact_GUC(false, root_save_nestlevel);
/* Restore userid and security context */
SetUserIdAndSecContext(root_save_userid, root_save_sec_context);
table_close(rel, NoLock);
/* If this is the top-level index, we're done */
if (!OidIsValid(parentIndexId))
pgstat_progress_end_command();
return address;
}
/*
* Roll back any GUC changes executed by index functions, and keep
* subsequent changes local to this command. This is essential if some
* index function changed a behavior-affecting GUC, e.g. search_path.
*/
AtEOXact_GUC(false, root_save_nestlevel);
root_save_nestlevel = NewGUCNestLevel();
/* Add any requested comment */
if (stmt->idxcomment != NULL)
CreateComments(indexRelationId, RelationRelationId, 0,
stmt->idxcomment);
if (partitioned)
{
PartitionDesc partdesc;
/*
* Unless caller specified to skip this step (via ONLY), process each
* partition to make sure they all contain a corresponding index.
*
* If we're called internally (no stmt->relation), recurse always.
*/
partdesc = RelationGetPartitionDesc(rel, true);
if ((!stmt->relation || stmt->relation->inh) && partdesc->nparts > 0)
{
int nparts = partdesc->nparts;
Oid *part_oids = palloc_array(Oid, nparts);
bool invalidate_parent = false;
Relation parentIndex;
TupleDesc parentDesc;
/*
* Report the total number of partitions at the start of the
* command; don't update it when being called recursively.
*/
if (!OidIsValid(parentIndexId))
{
/*
* When called by ProcessUtilitySlow, the number of partitions
* is passed in as an optimization; but other callers pass -1
* since they don't have the value handy. This should count
* partitions the same way, ie one less than the number of
* relations find_all_inheritors reports.
*
* We assume we needn't ask find_all_inheritors to take locks,
* because that should have happened already for all callers.
* Even if it did not, this is safe as long as we don't try to
* touch the partitions here; the worst consequence would be a
* bogus progress-reporting total.
*/
if (total_parts < 0)
{
List *children = find_all_inheritors(relationId,
NoLock, NULL);
total_parts = list_length(children) - 1;
list_free(children);
}
pgstat_progress_update_param(PROGRESS_CREATEIDX_PARTITIONS_TOTAL,
total_parts);
}
/* Make a local copy of partdesc->oids[], just for safety */
memcpy(part_oids, partdesc->oids, sizeof(Oid) * nparts);
/*
* We'll need an IndexInfo describing the parent index. The one
* built above is almost good enough, but not quite, because (for
* example) its predicate expression if any hasn't been through
* expression preprocessing. The most reliable way to get an
* IndexInfo that will match those for child indexes is to build
* it the same way, using BuildIndexInfo().
*/
parentIndex = index_open(indexRelationId, lockmode);
indexInfo = BuildIndexInfo(parentIndex);
parentDesc = RelationGetDescr(rel);
/*
* For each partition, scan all existing indexes; if one matches
* our index definition and is not already attached to some other
* parent index, attach it to the one we just created.
*
* If none matches, build a new index by calling ourselves
* recursively with the same options (except for the index name).
*/
for (int i = 0; i < nparts; i++)
{
Oid childRelid = part_oids[i];
Relation childrel;
Oid child_save_userid;
int child_save_sec_context;
int child_save_nestlevel;
List *childidxs;
ListCell *cell;
AttrMap *attmap;
bool found = false;
childrel = table_open(childRelid, lockmode);
GetUserIdAndSecContext(&child_save_userid,
&child_save_sec_context);
SetUserIdAndSecContext(childrel->rd_rel->relowner,
child_save_sec_context | SECURITY_RESTRICTED_OPERATION);
child_save_nestlevel = NewGUCNestLevel();
/*
* Don't try to create indexes on foreign tables, though. Skip
* those if a regular index, or fail if trying to create a
* constraint index.
*/
if (childrel->rd_rel->relkind == RELKIND_FOREIGN_TABLE)
{
if (stmt->unique || stmt->primary)
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("cannot create unique index on partitioned table \"%s\"",
RelationGetRelationName(rel)),
errdetail("Table \"%s\" contains partitions that are foreign tables.",
RelationGetRelationName(rel))));
AtEOXact_GUC(false, child_save_nestlevel);
SetUserIdAndSecContext(child_save_userid,
child_save_sec_context);
table_close(childrel, lockmode);
continue;
}
childidxs = RelationGetIndexList(childrel);
attmap =
build_attrmap_by_name(RelationGetDescr(childrel),
parentDesc,
false);
foreach(cell, childidxs)
{
Oid cldidxid = lfirst_oid(cell);
Relation cldidx;
IndexInfo *cldIdxInfo;
/* this index is already partition of another one */
if (has_superclass(cldidxid))
continue;
cldidx = index_open(cldidxid, lockmode);
cldIdxInfo = BuildIndexInfo(cldidx);
if (CompareIndexInfo(cldIdxInfo, indexInfo,
cldidx->rd_indcollation,
parentIndex->rd_indcollation,
cldidx->rd_opfamily,
parentIndex->rd_opfamily,
attmap))
{
Oid cldConstrOid = InvalidOid;
/*
* Found a match.
*
* If this index is being created in the parent
* because of a constraint, then the child needs to
* have a constraint also, so look for one. If there
* is no such constraint, this index is no good, so
* keep looking.
*/
if (createdConstraintId != InvalidOid)
{
cldConstrOid =
get_relation_idx_constraint_oid(childRelid,
cldidxid);
if (cldConstrOid == InvalidOid)
{
index_close(cldidx, lockmode);
continue;
}
}
/* Attach index to parent and we're done. */
IndexSetParentIndex(cldidx, indexRelationId);
if (createdConstraintId != InvalidOid)
ConstraintSetParentConstraint(cldConstrOid,
createdConstraintId,
childRelid);
if (!cldidx->rd_index->indisvalid)
invalidate_parent = true;
found = true;
/*
* Report this partition as processed. Note that if
* the partition has children itself, we'd ideally
* count the children and update the progress report
* for all of them; but that seems unduly expensive.
* Instead, the progress report will act like all such
* indirect children were processed in zero time at
* the end of the command.
*/
pgstat_progress_incr_param(PROGRESS_CREATEIDX_PARTITIONS_DONE, 1);
/* keep lock till commit */
index_close(cldidx, NoLock);
break;
}
index_close(cldidx, lockmode);
}
list_free(childidxs);
AtEOXact_GUC(false, child_save_nestlevel);
SetUserIdAndSecContext(child_save_userid,
child_save_sec_context);
table_close(childrel, NoLock);
/*
* If no matching index was found, create our own.
*/
if (!found)
{
IndexStmt *childStmt = copyObject(stmt);
bool found_whole_row;
ListCell *lc;
ObjectAddress childAddr;
/*
* We can't use the same index name for the child index,
* so clear idxname to let the recursive invocation choose
* a new name. Likewise, the existing target relation
* field is wrong, and if indexOid or oldNumber are set,
* they mustn't be applied to the child either.
*/
childStmt->idxname = NULL;
childStmt->relation = NULL;
childStmt->indexOid = InvalidOid;
childStmt->oldNumber = InvalidRelFileNumber;
childStmt->oldCreateSubid = InvalidSubTransactionId;
childStmt->oldFirstRelfilelocatorSubid = InvalidSubTransactionId;
/*
* Adjust any Vars (both in expressions and in the index's
* WHERE clause) to match the partition's column numbering
* in case it's different from the parent's.
*/
foreach(lc, childStmt->indexParams)
{
IndexElem *ielem = lfirst(lc);
/*
* If the index parameter is an expression, we must
* translate it to contain child Vars.
*/
if (ielem->expr)
{
ielem->expr =
map_variable_attnos((Node *) ielem->expr,
1, 0, attmap,
InvalidOid,
&found_whole_row);
if (found_whole_row)
elog(ERROR, "cannot convert whole-row table reference");
}
}
childStmt->whereClause =
map_variable_attnos(stmt->whereClause, 1, 0,
attmap,
InvalidOid, &found_whole_row);
if (found_whole_row)
elog(ERROR, "cannot convert whole-row table reference");
/*
* Recurse as the starting user ID. Callee will use that
* for permission checks, then switch again.
*/
Assert(GetUserId() == child_save_userid);
SetUserIdAndSecContext(root_save_userid,
root_save_sec_context);
childAddr =
DefineIndex(childRelid, childStmt,
InvalidOid, /* no predefined OID */
indexRelationId, /* this is our child */
createdConstraintId,
-1,
is_alter_table, check_rights,
check_not_in_use,
skip_build, quiet);
SetUserIdAndSecContext(child_save_userid,
child_save_sec_context);
/*
* Check if the index just created is valid or not, as it
* could be possible that it has been switched as invalid
* when recursing across multiple partition levels.
*/
if (!get_index_isvalid(childAddr.objectId))
invalidate_parent = true;
}
free_attrmap(attmap);
}
index_close(parentIndex, lockmode);
/*
* The pg_index row we inserted for this index was marked
* indisvalid=true. But if we attached an existing index that is
* invalid, this is incorrect, so update our row to invalid too.
*/
if (invalidate_parent)
{
Relation pg_index = table_open(IndexRelationId, RowExclusiveLock);
HeapTuple tup,
newtup;
tup = SearchSysCache1(INDEXRELID,
ObjectIdGetDatum(indexRelationId));
if (!HeapTupleIsValid(tup))
elog(ERROR, "cache lookup failed for index %u",
indexRelationId);
newtup = heap_copytuple(tup);
((Form_pg_index) GETSTRUCT(newtup))->indisvalid = false;
CatalogTupleUpdate(pg_index, &tup->t_self, newtup);
ReleaseSysCache(tup);
table_close(pg_index, RowExclusiveLock);
heap_freetuple(newtup);
/*
* CCI here to make this update visible, in case this recurses
* across multiple partition levels.
*/
CommandCounterIncrement();
}
}
/*
* Indexes on partitioned tables are not themselves built, so we're
* done here.
*/
AtEOXact_GUC(false, root_save_nestlevel);
SetUserIdAndSecContext(root_save_userid, root_save_sec_context);
table_close(rel, NoLock);
if (!OidIsValid(parentIndexId))
pgstat_progress_end_command();
else
{
/* Update progress for an intermediate partitioned index itself */
pgstat_progress_incr_param(PROGRESS_CREATEIDX_PARTITIONS_DONE, 1);
}
return address;
}
AtEOXact_GUC(false, root_save_nestlevel);
SetUserIdAndSecContext(root_save_userid, root_save_sec_context);
if (!concurrent)
{
/* Close the heap and we're done, in the non-concurrent case */
table_close(rel, NoLock);
/*
* If this is the top-level index, the command is done overall;
* otherwise, increment progress to report one child index is done.
*/
if (!OidIsValid(parentIndexId))
pgstat_progress_end_command();
else
pgstat_progress_incr_param(PROGRESS_CREATEIDX_PARTITIONS_DONE, 1);
return address;
}
/* save lockrelid and locktag for below, then close rel */
heaprelid = rel->rd_lockInfo.lockRelId;
SET_LOCKTAG_RELATION(heaplocktag, heaprelid.dbId, heaprelid.relId);
table_close(rel, NoLock);
/*
* For a concurrent build, it's important to make the catalog entries
* visible to other transactions before we start to build the index. That
* will prevent them from making incompatible HOT updates. The new index
* will be marked not indisready and not indisvalid, so that no one else
* tries to either insert into it or use it for queries.
*
* We must commit our current transaction so that the index becomes
* visible; then start another. Note that all the data structures we just
* built are lost in the commit. The only data we keep past here are the
* relation IDs.
*
* Before committing, get a session-level lock on the table, to ensure
* that neither it nor the index can be dropped before we finish. This
* cannot block, even if someone else is waiting for access, because we
* already have the same lock within our transaction.
*
* Note: we don't currently bother with a session lock on the index,
* because there are no operations that could change its state while we
* hold lock on the parent table. This might need to change later.
*/
LockRelationIdForSession(&heaprelid, ShareUpdateExclusiveLock);
PopActiveSnapshot();
CommitTransactionCommand();
StartTransactionCommand();
/* Tell concurrent index builds to ignore us, if index qualifies */
if (safe_index)
set_indexsafe_procflags();
/*
* The index is now visible, so we can report the OID. While on it,
* include the report for the beginning of phase 2.
*/
{
const int progress_cols[] = {
PROGRESS_CREATEIDX_INDEX_OID,
PROGRESS_CREATEIDX_PHASE
};
const int64 progress_vals[] = {
indexRelationId,
PROGRESS_CREATEIDX_PHASE_WAIT_1
};
pgstat_progress_update_multi_param(2, progress_cols, progress_vals);
}
/*
* Phase 2 of concurrent index build (see comments for validate_index()
* for an overview of how this works)
*
* Now we must wait until no running transaction could have the table open
* with the old list of indexes. Use ShareLock to consider running
* transactions that hold locks that permit writing to the table. Note we
* do not need to worry about xacts that open the table for writing after
* this point; they will see the new index when they open it.
*
* Note: the reason we use actual lock acquisition here, rather than just
* checking the ProcArray and sleeping, is that deadlock is possible if
* one of the transactions in question is blocked trying to acquire an
* exclusive lock on our table. The lock code will detect deadlock and
* error out properly.
*/
WaitForLockers(heaplocktag, ShareLock, true);
/*
* At this moment we are sure that there are no transactions with the
* table open for write that don't have this new index in their list of
* indexes. We have waited out all the existing transactions and any new
* transaction will have the new index in its list, but the index is still
* marked as "not-ready-for-inserts". The index is consulted while
* deciding HOT-safety though. This arrangement ensures that no new HOT
* chains can be created where the new tuple and the old tuple in the
* chain have different index keys.
*
* We now take a new snapshot, and build the index using all tuples that
* are visible in this snapshot. We can be sure that any HOT updates to
* these tuples will be compatible with the index, since any updates made
* by transactions that didn't know about the index are now committed or
* rolled back. Thus, each visible tuple is either the end of its
* HOT-chain or the extension of the chain is HOT-safe for this index.
*/
/* Set ActiveSnapshot since functions in the indexes may need it */
PushActiveSnapshot(GetTransactionSnapshot());
/* Perform concurrent build of index */
index_concurrently_build(relationId, indexRelationId);
/* we can do away with our snapshot */
PopActiveSnapshot();
/*
* Commit this transaction to make the indisready update visible.
*/
CommitTransactionCommand();
StartTransactionCommand();
/* Tell concurrent index builds to ignore us, if index qualifies */
if (safe_index)
set_indexsafe_procflags();
/*
* Phase 3 of concurrent index build
*
* We once again wait until no transaction can have the table open with
* the index marked as read-only for updates.
*/
pgstat_progress_update_param(PROGRESS_CREATEIDX_PHASE,
PROGRESS_CREATEIDX_PHASE_WAIT_2);
WaitForLockers(heaplocktag, ShareLock, true);
/*
* Now take the "reference snapshot" that will be used by validate_index()
* to filter candidate tuples. Beware! There might still be snapshots in
* use that treat some transaction as in-progress that our reference
* snapshot treats as committed. If such a recently-committed transaction
* deleted tuples in the table, we will not include them in the index; yet
* those transactions which see the deleting one as still-in-progress will
* expect such tuples to be there once we mark the index as valid.
*
* We solve this by waiting for all endangered transactions to exit before
* we mark the index as valid.
*
* We also set ActiveSnapshot to this snap, since functions in indexes may
* need a snapshot.
*/
snapshot = RegisterSnapshot(GetTransactionSnapshot());
PushActiveSnapshot(snapshot);
/*
* Scan the index and the heap, insert any missing index entries.
*/
validate_index(relationId, indexRelationId, snapshot);
/*
* Drop the reference snapshot. We must do this before waiting out other
* snapshot holders, else we will deadlock against other processes also
* doing CREATE INDEX CONCURRENTLY, which would see our snapshot as one
* they must wait for. But first, save the snapshot's xmin to use as
* limitXmin for GetCurrentVirtualXIDs().
*/
limitXmin = snapshot->xmin;
PopActiveSnapshot();
UnregisterSnapshot(snapshot);
/*
* The snapshot subsystem could still contain registered snapshots that
* are holding back our process's advertised xmin; in particular, if
* default_transaction_isolation = serializable, there is a transaction
* snapshot that is still active. The CatalogSnapshot is likewise a
* hazard. To ensure no deadlocks, we must commit and start yet another
* transaction, and do our wait before any snapshot has been taken in it.
*/
CommitTransactionCommand();
StartTransactionCommand();
/* Tell concurrent index builds to ignore us, if index qualifies */
if (safe_index)
set_indexsafe_procflags();
/* We should now definitely not be advertising any xmin. */
Assert(MyProc->xmin == InvalidTransactionId);
/*
* The index is now valid in the sense that it contains all currently
* interesting tuples. But since it might not contain tuples deleted just
* before the reference snap was taken, we have to wait out any
* transactions that might have older snapshots.
*/
pgstat_progress_update_param(PROGRESS_CREATEIDX_PHASE,
PROGRESS_CREATEIDX_PHASE_WAIT_3);
WaitForOlderSnapshots(limitXmin, true);
/*
* Index can now be marked valid -- update its pg_index entry
*/
index_set_state_flags(indexRelationId, INDEX_CREATE_SET_VALID);
/*
* The pg_index update will cause backends (including this one) to update
* relcache entries for the index itself, but we should also send a
* relcache inval on the parent table to force replanning of cached plans.
* Otherwise existing sessions might fail to use the new index where it
* would be useful. (Note that our earlier commits did not create reasons
* to replan; so relcache flush on the index itself was sufficient.)
*/
CacheInvalidateRelcacheByRelid(heaprelid.relId);
/*
* Last thing to do is release the session-level lock on the parent table.
*/
UnlockRelationIdForSession(&heaprelid, ShareUpdateExclusiveLock);
pgstat_progress_end_command();
return address;
}
/*
* CheckPredicate
* Checks that the given partial-index predicate is valid.
*
* This used to also constrain the form of the predicate to forms that
* indxpath.c could do something with. However, that seems overly
* restrictive. One useful application of partial indexes is to apply
* a UNIQUE constraint across a subset of a table, and in that scenario
* any evaluable predicate will work. So accept any predicate here
* (except ones requiring a plan), and let indxpath.c fend for itself.
*/
static void
CheckPredicate(Expr *predicate)
{
/*
* transformExpr() should have already rejected subqueries, aggregates,
* and window functions, based on the EXPR_KIND_ for a predicate.
*/
/*
* A predicate using mutable functions is probably wrong, for the same
* reasons that we don't allow an index expression to use one.
*/
if (contain_mutable_functions_after_planning(predicate))
ereport(ERROR,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("functions in index predicate must be marked IMMUTABLE")));
}
/*
* Compute per-index-column information, including indexed column numbers
* or index expressions, opclasses and their options. Note, all output vectors
* should be allocated for all columns, including "including" ones.
*
* If the caller switched to the table owner, ddl_userid is the role for ACL
* checks reached without traversing opaque expressions. Otherwise, it's
* InvalidOid, and other ddl_* arguments are undefined.
*/
static void
ComputeIndexAttrs(IndexInfo *indexInfo,
Oid *typeOidP,
Oid *collationOidP,
Oid *classOidP,
int16 *colOptionP,
List *attList, /* list of IndexElem's */
List *exclusionOpNames,
Oid relId,
const char *accessMethodName,
Oid accessMethodId,
bool amcanorder,
bool isconstraint,
Oid ddl_userid,
int ddl_sec_context,
int *ddl_save_nestlevel)
{
ListCell *nextExclOp;
ListCell *lc;
int attn;
int nkeycols = indexInfo->ii_NumIndexKeyAttrs;
Oid save_userid;
int save_sec_context;
/* Allocate space for exclusion operator info, if needed */
if (exclusionOpNames)
{
Assert(list_length(exclusionOpNames) == nkeycols);
indexInfo->ii_ExclusionOps = palloc_array(Oid, nkeycols);
indexInfo->ii_ExclusionProcs = palloc_array(Oid, nkeycols);
indexInfo->ii_ExclusionStrats = palloc_array(uint16, nkeycols);
nextExclOp = list_head(exclusionOpNames);
}
else
nextExclOp = NULL;
if (OidIsValid(ddl_userid))
GetUserIdAndSecContext(&save_userid, &save_sec_context);
/*
* process attributeList
*/
attn = 0;
foreach(lc, attList)
{
IndexElem *attribute = (IndexElem *) lfirst(lc);
Oid atttype;
Oid attcollation;
/*
* Process the column-or-expression to be indexed.
*/
if (attribute->name != NULL)
{
/* Simple index attribute */
HeapTuple atttuple;
Form_pg_attribute attform;
Assert(attribute->expr == NULL);
atttuple = SearchSysCacheAttName(relId, attribute->name);
if (!HeapTupleIsValid(atttuple))
{
/* difference in error message spellings is historical */
if (isconstraint)
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_COLUMN),
errmsg("column \"%s\" named in key does not exist",
attribute->name)));
else
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_COLUMN),
errmsg("column \"%s\" does not exist",
attribute->name)));
}
attform = (Form_pg_attribute) GETSTRUCT(atttuple);
indexInfo->ii_IndexAttrNumbers[attn] = attform->attnum;
atttype = attform->atttypid;
attcollation = attform->attcollation;
ReleaseSysCache(atttuple);
}
else
{
/* Index expression */
Node *expr = attribute->expr;
Assert(expr != NULL);
if (attn >= nkeycols)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("expressions are not supported in included columns")));
atttype = exprType(expr);
attcollation = exprCollation(expr);
/*
* Strip any top-level COLLATE clause. This ensures that we treat
* "x COLLATE y" and "(x COLLATE y)" alike.
*/
while (IsA(expr, CollateExpr))
expr = (Node *) ((CollateExpr *) expr)->arg;
if (IsA(expr, Var) &&
((Var *) expr)->varattno != InvalidAttrNumber)
{
/*
* User wrote "(column)" or "(column COLLATE something)".
* Treat it like simple attribute anyway.
*/
indexInfo->ii_IndexAttrNumbers[attn] = ((Var *) expr)->varattno;
}
else
{
indexInfo->ii_IndexAttrNumbers[attn] = 0; /* marks expression */
indexInfo->ii_Expressions = lappend(indexInfo->ii_Expressions,
expr);
/*
* transformExpr() should have already rejected subqueries,
* aggregates, and window functions, based on the EXPR_KIND_
* for an index expression.
*/
/*
* An expression using mutable functions is probably wrong,
* since if you aren't going to get the same result for the
* same data every time, it's not clear what the index entries
* mean at all.
*/
if (contain_mutable_functions_after_planning((Expr *) expr))
ereport(ERROR,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("functions in index expression must be marked IMMUTABLE")));
}
}
typeOidP[attn] = atttype;
/*
* Included columns have no collation, no opclass and no ordering
* options.
*/
if (attn >= nkeycols)
{
if (attribute->collation)
ereport(ERROR,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("including column does not support a collation")));
if (attribute->opclass)
ereport(ERROR,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("including column does not support an operator class")));
if (attribute->ordering != SORTBY_DEFAULT)
ereport(ERROR,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("including column does not support ASC/DESC options")));
if (attribute->nulls_ordering != SORTBY_NULLS_DEFAULT)
ereport(ERROR,
(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
errmsg("including column does not support NULLS FIRST/LAST options")));
classOidP[attn] = InvalidOid;
colOptionP[attn] = 0;
collationOidP[attn] = InvalidOid;
attn++;
continue;
}
/*
* Apply collation override if any. Use of ddl_userid is necessary
* due to ACL checks therein, and it's safe because collations don't
* contain opaque expressions (or non-opaque expressions).
*/
if (attribute->collation)
{
if (OidIsValid(ddl_userid))
{
AtEOXact_GUC(false, *ddl_save_nestlevel);
SetUserIdAndSecContext(ddl_userid, ddl_sec_context);
}
attcollation = get_collation_oid(attribute->collation, false);
if (OidIsValid(ddl_userid))
{
SetUserIdAndSecContext(save_userid, save_sec_context);
*ddl_save_nestlevel = NewGUCNestLevel();
}
}
/*
* Check we have a collation iff it's a collatable type. The only
* expected failures here are (1) COLLATE applied to a noncollatable
* type, or (2) index expression had an unresolved collation. But we
* might as well code this to be a complete consistency check.
*/
if (type_is_collatable(atttype))
{
if (!OidIsValid(attcollation))
ereport(ERROR,
(errcode(ERRCODE_INDETERMINATE_COLLATION),
errmsg("could not determine which collation to use for index expression"),
errhint("Use the COLLATE clause to set the collation explicitly.")));
}
else
{
if (OidIsValid(attcollation))
ereport(ERROR,
(errcode(ERRCODE_DATATYPE_MISMATCH),
errmsg("collations are not supported by type %s",
format_type_be(atttype))));
}
collationOidP[attn] = attcollation;
/*
* Identify the opclass to use. Use of ddl_userid is necessary due to
* ACL checks therein. This is safe despite opclasses containing
* opaque expressions (specifically, functions), because only
* superusers can define opclasses.
*/
if (OidIsValid(ddl_userid))
{
AtEOXact_GUC(false, *ddl_save_nestlevel);
SetUserIdAndSecContext(ddl_userid, ddl_sec_context);
}
classOidP[attn] = ResolveOpClass(attribute->opclass,
atttype,
accessMethodName,
accessMethodId);
if (OidIsValid(ddl_userid))
{
SetUserIdAndSecContext(save_userid, save_sec_context);
*ddl_save_nestlevel = NewGUCNestLevel();
}
/*
* Identify the exclusion operator, if any.
*/
if (nextExclOp)
{
List *opname = (List *) lfirst(nextExclOp);
Oid opid;
Oid opfamily;
int strat;
/*
* Find the operator --- it must accept the column datatype
* without runtime coercion (but binary compatibility is OK).
* Operators contain opaque expressions (specifically, functions).
* compatible_oper_opid() boils down to oper() and
* IsBinaryCoercible(). PostgreSQL would have security problems
* elsewhere if oper() started calling opaque expressions.
*/
if (OidIsValid(ddl_userid))
{
AtEOXact_GUC(false, *ddl_save_nestlevel);
SetUserIdAndSecContext(ddl_userid, ddl_sec_context);
}
opid = compatible_oper_opid(opname, atttype, atttype, false);
if (OidIsValid(ddl_userid))
{
SetUserIdAndSecContext(save_userid, save_sec_context);
*ddl_save_nestlevel = NewGUCNestLevel();
}
/*
* Only allow commutative operators to be used in exclusion
* constraints. If X conflicts with Y, but Y does not conflict
* with X, bad things will happen.
*/
if (get_commutator(opid) != opid)
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("operator %s is not commutative",
format_operator(opid)),
errdetail("Only commutative operators can be used in exclusion constraints.")));
/*
* Operator must be a member of the right opfamily, too
*/
opfamily = get_opclass_family(classOidP[attn]);
strat = get_op_opfamily_strategy(opid, opfamily);
if (strat == 0)
{
HeapTuple opftuple;
Form_pg_opfamily opfform;
/*
* attribute->opclass might not explicitly name the opfamily,
* so fetch the name of the selected opfamily for use in the
* error message.
*/
opftuple = SearchSysCache1(OPFAMILYOID,
ObjectIdGetDatum(opfamily));
if (!HeapTupleIsValid(opftuple))
elog(ERROR, "cache lookup failed for opfamily %u",
opfamily);
opfform = (Form_pg_opfamily) GETSTRUCT(opftuple);
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("operator %s is not a member of operator family \"%s\"",
format_operator(opid),
NameStr(opfform->opfname)),
errdetail("The exclusion operator must be related to the index operator class for the constraint.")));
}
indexInfo->ii_ExclusionOps[attn] = opid;
indexInfo->ii_ExclusionProcs[attn] = get_opcode(opid);
indexInfo->ii_ExclusionStrats[attn] = strat;
nextExclOp = lnext(exclusionOpNames, nextExclOp);
}
/*
* Set up the per-column options (indoption field). For now, this is
* zero for any un-ordered index, while ordered indexes have DESC and
* NULLS FIRST/LAST options.
*/
colOptionP[attn] = 0;
if (amcanorder)
{
/* default ordering is ASC */
if (attribute->ordering == SORTBY_DESC)
colOptionP[attn] |= INDOPTION_DESC;
/* default null ordering is LAST for ASC, FIRST for DESC */
if (attribute->nulls_ordering == SORTBY_NULLS_DEFAULT)
{
if (attribute->ordering == SORTBY_DESC)
colOptionP[attn] |= INDOPTION_NULLS_FIRST;
}
else if (attribute->nulls_ordering == SORTBY_NULLS_FIRST)
colOptionP[attn] |= INDOPTION_NULLS_FIRST;
}
else
{
/* index AM does not support ordering */
if (attribute->ordering != SORTBY_DEFAULT)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("access method \"%s\" does not support ASC/DESC options",
accessMethodName)));
if (attribute->nulls_ordering != SORTBY_NULLS_DEFAULT)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("access method \"%s\" does not support NULLS FIRST/LAST options",
accessMethodName)));
}
/* Set up the per-column opclass options (attoptions field). */
if (attribute->opclassopts)
{
Assert(attn < nkeycols);
if (!indexInfo->ii_OpclassOptions)
indexInfo->ii_OpclassOptions =
palloc0_array(Datum, indexInfo->ii_NumIndexAttrs);
indexInfo->ii_OpclassOptions[attn] =
transformRelOptions((Datum) 0, attribute->opclassopts,
NULL, NULL, false, false);
}
attn++;
}
}
/*
* Resolve possibly-defaulted operator class specification
*
* Note: This is used to resolve operator class specifications in index and
* partition key definitions.
*/
Oid
ResolveOpClass(List *opclass, Oid attrType,
const char *accessMethodName, Oid accessMethodId)
{
char *schemaname;
char *opcname;
HeapTuple tuple;
Form_pg_opclass opform;
Oid opClassId,
opInputType;
if (opclass == NIL)
{
/* no operator class specified, so find the default */
opClassId = GetDefaultOpClass(attrType, accessMethodId);
if (!OidIsValid(opClassId))
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_OBJECT),
errmsg("data type %s has no default operator class for access method \"%s\"",
format_type_be(attrType), accessMethodName),
errhint("You must specify an operator class for the index or define a default operator class for the data type.")));
return opClassId;
}
/*
* Specific opclass name given, so look up the opclass.
*/
/* deconstruct the name list */
DeconstructQualifiedName(opclass, &schemaname, &opcname);
if (schemaname)
{
/* Look in specific schema only */
Oid namespaceId;
namespaceId = LookupExplicitNamespace(schemaname, false);
tuple = SearchSysCache3(CLAAMNAMENSP,
ObjectIdGetDatum(accessMethodId),
PointerGetDatum(opcname),
ObjectIdGetDatum(namespaceId));
}
else
{
/* Unqualified opclass name, so search the search path */
opClassId = OpclassnameGetOpcid(accessMethodId, opcname);
if (!OidIsValid(opClassId))
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_OBJECT),
errmsg("operator class \"%s\" does not exist for access method \"%s\"",
opcname, accessMethodName)));
tuple = SearchSysCache1(CLAOID, ObjectIdGetDatum(opClassId));
}
if (!HeapTupleIsValid(tuple))
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_OBJECT),
errmsg("operator class \"%s\" does not exist for access method \"%s\"",
NameListToString(opclass), accessMethodName)));
/*
* Verify that the index operator class accepts this datatype. Note we
* will accept binary compatibility.
*/
opform = (Form_pg_opclass) GETSTRUCT(tuple);
opClassId = opform->oid;
opInputType = opform->opcintype;
if (!IsBinaryCoercible(attrType, opInputType))
ereport(ERROR,
(errcode(ERRCODE_DATATYPE_MISMATCH),
errmsg("operator class \"%s\" does not accept data type %s",
NameListToString(opclass), format_type_be(attrType))));
ReleaseSysCache(tuple);
return opClassId;
}
/*
* GetDefaultOpClass
*
* Given the OIDs of a datatype and an access method, find the default
* operator class, if any. Returns InvalidOid if there is none.
*/
Oid
GetDefaultOpClass(Oid type_id, Oid am_id)
{
Oid result = InvalidOid;
int nexact = 0;
int ncompatible = 0;
int ncompatiblepreferred = 0;
Relation rel;
ScanKeyData skey[1];
SysScanDesc scan;
HeapTuple tup;
TYPCATEGORY tcategory;
/* If it's a domain, look at the base type instead */
type_id = getBaseType(type_id);
tcategory = TypeCategory(type_id);
/*
* We scan through all the opclasses available for the access method,
* looking for one that is marked default and matches the target type
* (either exactly or binary-compatibly, but prefer an exact match).
*
* We could find more than one binary-compatible match. If just one is
* for a preferred type, use that one; otherwise we fail, forcing the user
* to specify which one he wants. (The preferred-type special case is a
* kluge for varchar: it's binary-compatible to both text and bpchar, so
* we need a tiebreaker.) If we find more than one exact match, then
* someone put bogus entries in pg_opclass.
*/
rel = table_open(OperatorClassRelationId, AccessShareLock);
ScanKeyInit(&skey[0],
Anum_pg_opclass_opcmethod,
BTEqualStrategyNumber, F_OIDEQ,
ObjectIdGetDatum(am_id));
scan = systable_beginscan(rel, OpclassAmNameNspIndexId, true,
NULL, 1, skey);
while (HeapTupleIsValid(tup = systable_getnext(scan)))
{
Form_pg_opclass opclass = (Form_pg_opclass) GETSTRUCT(tup);
/* ignore altogether if not a default opclass */
if (!opclass->opcdefault)
continue;
if (opclass->opcintype == type_id)
{
nexact++;
result = opclass->oid;
}
else if (nexact == 0 &&
IsBinaryCoercible(type_id, opclass->opcintype))
{
if (IsPreferredType(tcategory, opclass->opcintype))
{
ncompatiblepreferred++;
result = opclass->oid;
}
else if (ncompatiblepreferred == 0)
{
ncompatible++;
result = opclass->oid;
}
}
}
systable_endscan(scan);
table_close(rel, AccessShareLock);
/* raise error if pg_opclass contains inconsistent data */
if (nexact > 1)
ereport(ERROR,
(errcode(ERRCODE_DUPLICATE_OBJECT),
errmsg("there are multiple default operator classes for data type %s",
format_type_be(type_id))));
if (nexact == 1 ||
ncompatiblepreferred == 1 ||
(ncompatiblepreferred == 0 && ncompatible == 1))
return result;
return InvalidOid;
}
/*
* makeObjectName()
*
* Create a name for an implicitly created index, sequence, constraint,
* extended statistics, etc.
*
* The parameters are typically: the original table name, the original field
* name, and a "type" string (such as "seq" or "pkey"). The field name
* and/or type can be NULL if not relevant.
*
* The result is a palloc'd string.
*
* The basic result we want is "name1_name2_label", omitting "_name2" or
* "_label" when those parameters are NULL. However, we must generate
* a name with less than NAMEDATALEN characters! So, we truncate one or
* both names if necessary to make a short-enough string. The label part
* is never truncated (so it had better be reasonably short).
*
* The caller is responsible for checking uniqueness of the generated
* name and retrying as needed; retrying will be done by altering the
* "label" string (which is why we never truncate that part).
*/
char *
makeObjectName(const char *name1, const char *name2, const char *label)
{
char *name;
int overhead = 0; /* chars needed for label and underscores */
int availchars; /* chars available for name(s) */
int name1chars; /* chars allocated to name1 */
int name2chars; /* chars allocated to name2 */
int ndx;
name1chars = strlen(name1);
if (name2)
{
name2chars = strlen(name2);
overhead++; /* allow for separating underscore */
}
else
name2chars = 0;
if (label)
overhead += strlen(label) + 1;
availchars = NAMEDATALEN - 1 - overhead;
Assert(availchars > 0); /* else caller chose a bad label */
/*
* If we must truncate, preferentially truncate the longer name. This
* logic could be expressed without a loop, but it's simple and obvious as
* a loop.
*/
while (name1chars + name2chars > availchars)
{
if (name1chars > name2chars)
name1chars--;
else
name2chars--;
}
name1chars = pg_mbcliplen(name1, name1chars, name1chars);
if (name2)
name2chars = pg_mbcliplen(name2, name2chars, name2chars);
/* Now construct the string using the chosen lengths */
name = palloc(name1chars + name2chars + overhead + 1);
memcpy(name, name1, name1chars);
ndx = name1chars;
if (name2)
{
name[ndx++] = '_';
memcpy(name + ndx, name2, name2chars);
ndx += name2chars;
}
if (label)
{
name[ndx++] = '_';
strcpy(name + ndx, label);
}
else
name[ndx] = '\0';
return name;
}
/*
* Select a nonconflicting name for a new relation. This is ordinarily
* used to choose index names (which is why it's here) but it can also
* be used for sequences, or any autogenerated relation kind.
*
* name1, name2, and label are used the same way as for makeObjectName(),
* except that the label can't be NULL; digits will be appended to the label
* if needed to create a name that is unique within the specified namespace.
*
* If isconstraint is true, we also avoid choosing a name matching any
* existing constraint in the same namespace. (This is stricter than what
* Postgres itself requires, but the SQL standard says that constraint names
* should be unique within schemas, so we follow that for autogenerated
* constraint names.)
*
* Note: it is theoretically possible to get a collision anyway, if someone
* else chooses the same name concurrently. This is fairly unlikely to be
* a problem in practice, especially if one is holding an exclusive lock on
* the relation identified by name1. However, if choosing multiple names
* within a single command, you'd better create the new object and do
* CommandCounterIncrement before choosing the next one!
*
* Returns a palloc'd string.
*/
char *
ChooseRelationName(const char *name1, const char *name2,
const char *label, Oid namespaceid,
bool isconstraint)
{
int pass = 0;
char *relname = NULL;
char modlabel[NAMEDATALEN];
/* try the unmodified label first */
strlcpy(modlabel, label, sizeof(modlabel));
for (;;)
{
relname = makeObjectName(name1, name2, modlabel);
if (!OidIsValid(get_relname_relid(relname, namespaceid)))
{
if (!isconstraint ||
!ConstraintNameExists(relname, namespaceid))
break;
}
/* found a conflict, so try a new name component */
pfree(relname);
snprintf(modlabel, sizeof(modlabel), "%s%d", label, ++pass);
}
return relname;
}
/*
* Select the name to be used for an index.
*
* The argument list is pretty ad-hoc :-(
*/
static char *
ChooseIndexName(const char *tabname, Oid namespaceId,
List *colnames, List *exclusionOpNames,
bool primary, bool isconstraint)
{
char *indexname;
if (primary)
{
/* the primary key's name does not depend on the specific column(s) */
indexname = ChooseRelationName(tabname,
NULL,
"pkey",
namespaceId,
true);
}
else if (exclusionOpNames != NIL)
{
indexname = ChooseRelationName(tabname,
ChooseIndexNameAddition(colnames),
"excl",
namespaceId,
true);
}
else if (isconstraint)
{
indexname = ChooseRelationName(tabname,
ChooseIndexNameAddition(colnames),
"key",
namespaceId,
true);
}
else
{
indexname = ChooseRelationName(tabname,
ChooseIndexNameAddition(colnames),
"idx",
namespaceId,
false);
}
return indexname;
}
/*
* Generate "name2" for a new index given the list of column names for it
* (as produced by ChooseIndexColumnNames). This will be passed to
* ChooseRelationName along with the parent table name and a suitable label.
*
* We know that less than NAMEDATALEN characters will actually be used,
* so we can truncate the result once we've generated that many.
*
* XXX See also ChooseForeignKeyConstraintNameAddition and
* ChooseExtendedStatisticNameAddition.
*/
static char *
ChooseIndexNameAddition(List *colnames)
{
char buf[NAMEDATALEN * 2];
int buflen = 0;
ListCell *lc;
buf[0] = '\0';
foreach(lc, colnames)
{
const char *name = (const char *) lfirst(lc);
if (buflen > 0)
buf[buflen++] = '_'; /* insert _ between names */
/*
* At this point we have buflen <= NAMEDATALEN. name should be less
* than NAMEDATALEN already, but use strlcpy for paranoia.
*/
strlcpy(buf + buflen, name, NAMEDATALEN);
buflen += strlen(buf + buflen);
if (buflen >= NAMEDATALEN)
break;
}
return pstrdup(buf);
}
/*
* Select the actual names to be used for the columns of an index, given the
* list of IndexElems for the columns. This is mostly about ensuring the
* names are unique so we don't get a conflicting-attribute-names error.
*
* Returns a List of plain strings (char *, not String nodes).
*/
static List *
ChooseIndexColumnNames(List *indexElems)
{
List *result = NIL;
ListCell *lc;
foreach(lc, indexElems)
{
IndexElem *ielem = (IndexElem *) lfirst(lc);
const char *origname;
const char *curname;
int i;
char buf[NAMEDATALEN];
/* Get the preliminary name from the IndexElem */
if (ielem->indexcolname)
origname = ielem->indexcolname; /* caller-specified name */
else if (ielem->name)
origname = ielem->name; /* simple column reference */
else
origname = "expr"; /* default name for expression */
/* If it conflicts with any previous column, tweak it */
curname = origname;
for (i = 1;; i++)
{
ListCell *lc2;
char nbuf[32];
int nlen;
foreach(lc2, result)
{
if (strcmp(curname, (char *) lfirst(lc2)) == 0)
break;
}
if (lc2 == NULL)
break; /* found nonconflicting name */
sprintf(nbuf, "%d", i);
/* Ensure generated names are shorter than NAMEDATALEN */
nlen = pg_mbcliplen(origname, strlen(origname),
NAMEDATALEN - 1 - strlen(nbuf));
memcpy(buf, origname, nlen);
strcpy(buf + nlen, nbuf);
curname = buf;
}
/* And attach to the result list */
result = lappend(result, pstrdup(curname));
}
return result;
}
/*
* ExecReindex
*
* Primary entry point for manual REINDEX commands. This is mainly a
* preparation wrapper for the real operations that will happen in
* each subroutine of REINDEX.
*/
void
ExecReindex(ParseState *pstate, ReindexStmt *stmt, bool isTopLevel)
{
ReindexParams params = {0};
ListCell *lc;
bool concurrently = false;
bool verbose = false;
char *tablespacename = NULL;
/* Parse option list */
foreach(lc, stmt->params)
{
DefElem *opt = (DefElem *) lfirst(lc);
if (strcmp(opt->defname, "verbose") == 0)
verbose = defGetBoolean(opt);
else if (strcmp(opt->defname, "concurrently") == 0)
concurrently = defGetBoolean(opt);
else if (strcmp(opt->defname, "tablespace") == 0)
tablespacename = defGetString(opt);
else
ereport(ERROR,
(errcode(ERRCODE_SYNTAX_ERROR),
errmsg("unrecognized REINDEX option \"%s\"",
opt->defname),
parser_errposition(pstate, opt->location)));
}
if (concurrently)
PreventInTransactionBlock(isTopLevel,
"REINDEX CONCURRENTLY");
params.options =
(verbose ? REINDEXOPT_VERBOSE : 0) |
(concurrently ? REINDEXOPT_CONCURRENTLY : 0);
/*
* Assign the tablespace OID to move indexes to, with InvalidOid to do
* nothing.
*/
if (tablespacename != NULL)
{
params.tablespaceOid = get_tablespace_oid(tablespacename, false);
/* Check permissions except when moving to database's default */
if (OidIsValid(params.tablespaceOid) &&
params.tablespaceOid != MyDatabaseTableSpace)
{
AclResult aclresult;
aclresult = object_aclcheck(TableSpaceRelationId, params.tablespaceOid,
GetUserId(), ACL_CREATE);
if (aclresult != ACLCHECK_OK)
aclcheck_error(aclresult, OBJECT_TABLESPACE,
get_tablespace_name(params.tablespaceOid));
}
}
else
params.tablespaceOid = InvalidOid;
switch (stmt->kind)
{
case REINDEX_OBJECT_INDEX:
ReindexIndex(stmt->relation, ¶ms, isTopLevel);
break;
case REINDEX_OBJECT_TABLE:
ReindexTable(stmt->relation, ¶ms, isTopLevel);
break;
case REINDEX_OBJECT_SCHEMA:
case REINDEX_OBJECT_SYSTEM:
case REINDEX_OBJECT_DATABASE:
/*
* This cannot run inside a user transaction block; if we were
* inside a transaction, then its commit- and
* start-transaction-command calls would not have the intended
* effect!
*/
PreventInTransactionBlock(isTopLevel,
(stmt->kind == REINDEX_OBJECT_SCHEMA) ? "REINDEX SCHEMA" :
(stmt->kind == REINDEX_OBJECT_SYSTEM) ? "REINDEX SYSTEM" :
"REINDEX DATABASE");
ReindexMultipleTables(stmt->name, stmt->kind, ¶ms);
break;
default:
elog(ERROR, "unrecognized object type: %d",
(int) stmt->kind);
break;
}
}
/*
* ReindexIndex
* Recreate a specific index.
*/
static void
ReindexIndex(RangeVar *indexRelation, ReindexParams *params, bool isTopLevel)
{
struct ReindexIndexCallbackState state;
Oid indOid;
char persistence;
char relkind;
/*
* Find and lock index, and check permissions on table; use callback to
* obtain lock on table first, to avoid deadlock hazard. The lock level
* used here must match the index lock obtained in reindex_index().
*
* If it's a temporary index, we will perform a non-concurrent reindex,
* even if CONCURRENTLY was requested. In that case, reindex_index() will
* upgrade the lock, but that's OK, because other sessions can't hold
* locks on our temporary table.
*/
state.params = *params;
state.locked_table_oid = InvalidOid;
indOid = RangeVarGetRelidExtended(indexRelation,
(params->options & REINDEXOPT_CONCURRENTLY) != 0 ?
ShareUpdateExclusiveLock : AccessExclusiveLock,
0,
RangeVarCallbackForReindexIndex,
&state);
/*
* Obtain the current persistence and kind of the existing index. We
* already hold a lock on the index.
*/
persistence = get_rel_persistence(indOid);
relkind = get_rel_relkind(indOid);
if (relkind == RELKIND_PARTITIONED_INDEX)
ReindexPartitions(indOid, params, isTopLevel);
else if ((params->options & REINDEXOPT_CONCURRENTLY) != 0 &&
persistence != RELPERSISTENCE_TEMP)
ReindexRelationConcurrently(indOid, params);
else
{
ReindexParams newparams = *params;
newparams.options |= REINDEXOPT_REPORT_PROGRESS;
reindex_index(indOid, false, persistence, &newparams);
}
}
/*
* Check permissions on table before acquiring relation lock; also lock
* the heap before the RangeVarGetRelidExtended takes the index lock, to avoid
* deadlocks.
*/
static void
RangeVarCallbackForReindexIndex(const RangeVar *relation,
Oid relId, Oid oldRelId, void *arg)
{
char relkind;
struct ReindexIndexCallbackState *state = arg;
LOCKMODE table_lockmode;
/*
* Lock level here should match table lock in reindex_index() for
* non-concurrent case and table locks used by index_concurrently_*() for
* concurrent case.
*/
table_lockmode = (state->params.options & REINDEXOPT_CONCURRENTLY) != 0 ?
ShareUpdateExclusiveLock : ShareLock;
/*
* If we previously locked some other index's heap, and the name we're
* looking up no longer refers to that relation, release the now-useless
* lock.
*/
if (relId != oldRelId && OidIsValid(oldRelId))
{
UnlockRelationOid(state->locked_table_oid, table_lockmode);
state->locked_table_oid = InvalidOid;
}
/* If the relation does not exist, there's nothing more to do. */
if (!OidIsValid(relId))
return;
/*
* If the relation does exist, check whether it's an index. But note that
* the relation might have been dropped between the time we did the name
* lookup and now. In that case, there's nothing to do.
*/
relkind = get_rel_relkind(relId);
if (!relkind)
return;
if (relkind != RELKIND_INDEX &&
relkind != RELKIND_PARTITIONED_INDEX)
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("\"%s\" is not an index", relation->relname)));
/* Check permissions */
if (!object_ownercheck(RelationRelationId, relId, GetUserId()))
aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_INDEX, relation->relname);
/* Lock heap before index to avoid deadlock. */
if (relId != oldRelId)
{
Oid table_oid = IndexGetRelation(relId, true);
/*
* If the OID isn't valid, it means the index was concurrently
* dropped, which is not a problem for us; just return normally.
*/
if (OidIsValid(table_oid))
{
LockRelationOid(table_oid, table_lockmode);
state->locked_table_oid = table_oid;
}
}
}
/*
* ReindexTable
* Recreate all indexes of a table (and of its toast table, if any)
*/
static Oid
ReindexTable(RangeVar *relation, ReindexParams *params, bool isTopLevel)
{
Oid heapOid;
bool result;
/*
* The lock level used here should match reindex_relation().
*
* If it's a temporary table, we will perform a non-concurrent reindex,
* even if CONCURRENTLY was requested. In that case, reindex_relation()
* will upgrade the lock, but that's OK, because other sessions can't hold
* locks on our temporary table.
*/
heapOid = RangeVarGetRelidExtended(relation,
(params->options & REINDEXOPT_CONCURRENTLY) != 0 ?
ShareUpdateExclusiveLock : ShareLock,
0,
RangeVarCallbackOwnsTable, NULL);
if (get_rel_relkind(heapOid) == RELKIND_PARTITIONED_TABLE)
ReindexPartitions(heapOid, params, isTopLevel);
else if ((params->options & REINDEXOPT_CONCURRENTLY) != 0 &&
get_rel_persistence(heapOid) != RELPERSISTENCE_TEMP)
{
result = ReindexRelationConcurrently(heapOid, params);
if (!result)
ereport(NOTICE,
(errmsg("table \"%s\" has no indexes that can be reindexed concurrently",
relation->relname)));
}
else
{
ReindexParams newparams = *params;
newparams.options |= REINDEXOPT_REPORT_PROGRESS;
result = reindex_relation(heapOid,
REINDEX_REL_PROCESS_TOAST |
REINDEX_REL_CHECK_CONSTRAINTS,
&newparams);
if (!result)
ereport(NOTICE,
(errmsg("table \"%s\" has no indexes to reindex",
relation->relname)));
}
return heapOid;
}
/*
* ReindexMultipleTables
* Recreate indexes of tables selected by objectName/objectKind.
*
* To reduce the probability of deadlocks, each table is reindexed in a
* separate transaction, so we can release the lock on it right away.
* That means this must not be called within a user transaction block!
*/
static void
ReindexMultipleTables(const char *objectName, ReindexObjectType objectKind,
ReindexParams *params)
{
Oid objectOid;
Relation relationRelation;
TableScanDesc scan;
ScanKeyData scan_keys[1];
HeapTuple tuple;
MemoryContext private_context;
MemoryContext old;
List *relids = NIL;
int num_keys;
bool concurrent_warning = false;
bool tablespace_warning = false;
Assert(objectKind == REINDEX_OBJECT_SCHEMA ||
objectKind == REINDEX_OBJECT_SYSTEM ||
objectKind == REINDEX_OBJECT_DATABASE);
/*
* This matches the options enforced by the grammar, where the object name
* is optional for DATABASE and SYSTEM.
*/
Assert(objectName || objectKind != REINDEX_OBJECT_SCHEMA);
if (objectKind == REINDEX_OBJECT_SYSTEM &&
(params->options & REINDEXOPT_CONCURRENTLY) != 0)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot reindex system catalogs concurrently")));
/*
* Get OID of object to reindex, being the database currently being used
* by session for a database or for system catalogs, or the schema defined
* by caller. At the same time do permission checks that need different
* processing depending on the object type.
*/
if (objectKind == REINDEX_OBJECT_SCHEMA)
{
objectOid = get_namespace_oid(objectName, false);
if (!object_ownercheck(NamespaceRelationId, objectOid, GetUserId()))
aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_SCHEMA,
objectName);
}
else
{
objectOid = MyDatabaseId;
if (objectName && strcmp(objectName, get_database_name(objectOid)) != 0)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("can only reindex the currently open database")));
if (!object_ownercheck(DatabaseRelationId, objectOid, GetUserId()))
aclcheck_error(ACLCHECK_NOT_OWNER, OBJECT_DATABASE,
get_database_name(objectOid));
}
/*
* Create a memory context that will survive forced transaction commits we
* do below. Since it is a child of PortalContext, it will go away
* eventually even if we suffer an error; there's no need for special
* abort cleanup logic.
*/
private_context = AllocSetContextCreate(PortalContext,
"ReindexMultipleTables",
ALLOCSET_SMALL_SIZES);
/*
* Define the search keys to find the objects to reindex. For a schema, we
* select target relations using relnamespace, something not necessary for
* a database-wide operation.
*/
if (objectKind == REINDEX_OBJECT_SCHEMA)
{
num_keys = 1;
ScanKeyInit(&scan_keys[0],
Anum_pg_class_relnamespace,
BTEqualStrategyNumber, F_OIDEQ,
ObjectIdGetDatum(objectOid));
}
else
num_keys = 0;
/*
* Scan pg_class to build a list of the relations we need to reindex.
*
* We only consider plain relations and materialized views here (toast
* rels will be processed indirectly by reindex_relation).
*/
relationRelation = table_open(RelationRelationId, AccessShareLock);
scan = table_beginscan_catalog(relationRelation, num_keys, scan_keys);
while ((tuple = heap_getnext(scan, ForwardScanDirection)) != NULL)
{
Form_pg_class classtuple = (Form_pg_class) GETSTRUCT(tuple);
Oid relid = classtuple->oid;
/*
* Only regular tables and matviews can have indexes, so ignore any
* other kind of relation.
*
* Partitioned tables/indexes are skipped but matching leaf partitions
* are processed.
*/
if (classtuple->relkind != RELKIND_RELATION &&
classtuple->relkind != RELKIND_MATVIEW)
continue;
/* Skip temp tables of other backends; we can't reindex them at all */
if (classtuple->relpersistence == RELPERSISTENCE_TEMP &&
!isTempNamespace(classtuple->relnamespace))
continue;
/*
* Check user/system classification. SYSTEM processes all the
* catalogs, and DATABASE processes everything that's not a catalog.
*/
if (objectKind == REINDEX_OBJECT_SYSTEM &&
!IsCatalogRelationOid(relid))
continue;
else if (objectKind == REINDEX_OBJECT_DATABASE &&
IsCatalogRelationOid(relid))
continue;
/*
* The table can be reindexed if the user is superuser, the table
* owner, or the database/schema owner (but in the latter case, only
* if it's not a shared relation). object_ownercheck includes the
* superuser case, and depending on objectKind we already know that
* the user has permission to run REINDEX on this database or schema
* per the permission checks at the beginning of this routine.
*/
if (classtuple->relisshared &&
!object_ownercheck(RelationRelationId, relid, GetUserId()))
continue;
/*
* Skip system tables, since index_create() would reject indexing them
* concurrently (and it would likely fail if we tried).
*/
if ((params->options & REINDEXOPT_CONCURRENTLY) != 0 &&
IsCatalogRelationOid(relid))
{
if (!concurrent_warning)
ereport(WARNING,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot reindex system catalogs concurrently, skipping all")));
concurrent_warning = true;
continue;
}
/*
* If a new tablespace is set, check if this relation has to be
* skipped.
*/
if (OidIsValid(params->tablespaceOid))
{
bool skip_rel = false;
/*
* Mapped relations cannot be moved to different tablespaces (in
* particular this eliminates all shared catalogs.).
*/
if (RELKIND_HAS_STORAGE(classtuple->relkind) &&
!RelFileNumberIsValid(classtuple->relfilenode))
skip_rel = true;
/*
* A system relation is always skipped, even with
* allow_system_table_mods enabled.
*/
if (IsSystemClass(relid, classtuple))
skip_rel = true;
if (skip_rel)
{
if (!tablespace_warning)
ereport(WARNING,
(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
errmsg("cannot move system relations, skipping all")));
tablespace_warning = true;
continue;
}
}
/* Save the list of relation OIDs in private context */
old = MemoryContextSwitchTo(private_context);
/*
* We always want to reindex pg_class first if it's selected to be
* reindexed. This ensures that if there is any corruption in
* pg_class' indexes, they will be fixed before we process any other
* tables. This is critical because reindexing itself will try to
* update pg_class.
*/
if (relid == RelationRelationId)
relids = lcons_oid(relid, relids);
else
relids = lappend_oid(relids, relid);
MemoryContextSwitchTo(old);
}
table_endscan(scan);
table_close(relationRelation, AccessShareLock);
/*
* Process each relation listed in a separate transaction. Note that this
* commits and then starts a new transaction immediately.
*/
ReindexMultipleInternal(relids, params);
MemoryContextDelete(private_context);
}
/*
* Error callback specific to ReindexPartitions().
*/
static void
reindex_error_callback(void *arg)
{
ReindexErrorInfo *errinfo = (ReindexErrorInfo *) arg;
Assert(RELKIND_HAS_PARTITIONS(errinfo->relkind));
if (errinfo->relkind == RELKIND_PARTITIONED_TABLE)
errcontext("while reindexing partitioned table \"%s.%s\"",
errinfo->relnamespace, errinfo->relname);
else if (errinfo->relkind == RELKIND_PARTITIONED_INDEX)
errcontext("while reindexing partitioned index \"%s.%s\"",
errinfo->relnamespace, errinfo->relname);
}
/*
* ReindexPartitions
*
* Reindex a set of partitions, per the partitioned index or table given
* by the caller.
*/
static void
ReindexPartitions(Oid relid, ReindexParams *params, bool isTopLevel)
{
List *partitions = NIL;
char relkind = get_rel_relkind(relid);
char *relname = get_rel_name(relid);
char *relnamespace = get_namespace_name(get_rel_namespace(relid));
MemoryContext reindex_context;
List *inhoids;
ListCell *lc;
ErrorContextCallback errcallback;
ReindexErrorInfo errinfo;
Assert(RELKIND_HAS_PARTITIONS(relkind));
/*
* Check if this runs in a transaction block, with an error callback to
* provide more context under which a problem happens.
*/
errinfo.relname = pstrdup(relname);
errinfo.relnamespace = pstrdup(relnamespace);
errinfo.relkind = relkind;
errcallback.callback = reindex_error_callback;
errcallback.arg = (void *) &errinfo;
errcallback.previous = error_context_stack;
error_context_stack = &errcallback;
PreventInTransactionBlock(isTopLevel,
relkind == RELKIND_PARTITIONED_TABLE ?
"REINDEX TABLE" : "REINDEX INDEX");
/* Pop the error context stack */
error_context_stack = errcallback.previous;
/*
* Create special memory context for cross-transaction storage.
*
* Since it is a child of PortalContext, it will go away eventually even
* if we suffer an error so there is no need for special abort cleanup
* logic.
*/
reindex_context = AllocSetContextCreate(PortalContext, "Reindex",
ALLOCSET_DEFAULT_SIZES);
/* ShareLock is enough to prevent schema modifications */
inhoids = find_all_inheritors(relid, ShareLock, NULL);
/*
* The list of relations to reindex are the physical partitions of the
* tree so discard any partitioned table or index.
*/
foreach(lc, inhoids)
{
Oid partoid = lfirst_oid(lc);
char partkind = get_rel_relkind(partoid);
MemoryContext old_context;
/*
* This discards partitioned tables, partitioned indexes and foreign
* tables.
*/
if (!RELKIND_HAS_STORAGE(partkind))
continue;
Assert(partkind == RELKIND_INDEX ||
partkind == RELKIND_RELATION);
/* Save partition OID */
old_context = MemoryContextSwitchTo(reindex_context);
partitions = lappend_oid(partitions, partoid);
MemoryContextSwitchTo(old_context);
}
/*
* Process each partition listed in a separate transaction. Note that
* this commits and then starts a new transaction immediately.
*/
ReindexMultipleInternal(partitions, params);
/*
* Clean up working storage --- note we must do this after
* StartTransactionCommand, else we might be trying to delete the active
* context!
*/
MemoryContextDelete(reindex_context);
}
/*
* ReindexMultipleInternal
*
* Reindex a list of relations, each one being processed in its own
* transaction. This commits the existing transaction immediately,
* and starts a new transaction when finished.
*/
static void
ReindexMultipleInternal(List *relids, ReindexParams *params)
{
ListCell *l;
PopActiveSnapshot();
CommitTransactionCommand();
foreach(l, relids)
{
Oid relid = lfirst_oid(l);
char relkind;
char relpersistence;
StartTransactionCommand();
/* functions in indexes may want a snapshot set */
PushActiveSnapshot(GetTransactionSnapshot());
/* check if the relation still exists */
if (!SearchSysCacheExists1(RELOID, ObjectIdGetDatum(relid)))
{
PopActiveSnapshot();
CommitTransactionCommand();
continue;
}
/*
* Check permissions except when moving to database's default if a new
* tablespace is chosen. Note that this check also happens in
* ExecReindex(), but we do an extra check here as this runs across
* multiple transactions.
*/
if (OidIsValid(params->tablespaceOid) &&
params->tablespaceOid != MyDatabaseTableSpace)
{
AclResult aclresult;
aclresult = object_aclcheck(TableSpaceRelationId, params->tablespaceOid,
GetUserId(), ACL_CREATE);
if (aclresult != ACLCHECK_OK)
aclcheck_error(aclresult, OBJECT_TABLESPACE,
get_tablespace_name(params->tablespaceOid));
}
relkind = get_rel_relkind(relid);
relpersistence = get_rel_persistence(relid);
/*
* Partitioned tables and indexes can never be processed directly, and
* a list of their leaves should be built first.
*/
Assert(!RELKIND_HAS_PARTITIONS(relkind));
if ((params->options & REINDEXOPT_CONCURRENTLY) != 0 &&
relpersistence != RELPERSISTENCE_TEMP)
{
ReindexParams newparams = *params;
newparams.options |= REINDEXOPT_MISSING_OK;
(void) ReindexRelationConcurrently(relid, &newparams);
/* ReindexRelationConcurrently() does the verbose output */
}
else if (relkind == RELKIND_INDEX)
{
ReindexParams newparams = *params;
newparams.options |=
REINDEXOPT_REPORT_PROGRESS | REINDEXOPT_MISSING_OK;
reindex_index(relid, false, relpersistence, &newparams);
PopActiveSnapshot();
/* reindex_index() does the verbose output */
}
else
{
bool result;
ReindexParams newparams = *params;
newparams.options |=
REINDEXOPT_REPORT_PROGRESS | REINDEXOPT_MISSING_OK;
result = reindex_relation(relid,
REINDEX_REL_PROCESS_TOAST |
REINDEX_REL_CHECK_CONSTRAINTS,
&newparams);
if (result && (params->options & REINDEXOPT_VERBOSE) != 0)
ereport(INFO,
(errmsg("table \"%s.%s\" was reindexed",
get_namespace_name(get_rel_namespace(relid)),
get_rel_name(relid))));
PopActiveSnapshot();
}
CommitTransactionCommand();
}
StartTransactionCommand();
}
/*
* ReindexRelationConcurrently - process REINDEX CONCURRENTLY for given
* relation OID
*
* 'relationOid' can either belong to an index, a table or a materialized
* view. For tables and materialized views, all its indexes will be rebuilt,
* excluding invalid indexes and any indexes used in exclusion constraints,
* but including its associated toast table indexes. For indexes, the index
* itself will be rebuilt.
*
* The locks taken on parent tables and involved indexes are kept until the
* transaction is committed, at which point a session lock is taken on each
* relation. Both of these protect against concurrent schema changes.
*
* Returns true if any indexes have been rebuilt (including toast table's
* indexes, when relevant), otherwise returns false.
*
* NOTE: This cannot be used on temporary relations. A concurrent build would
* cause issues with ON COMMIT actions triggered by the transactions of the
* concurrent build. Temporary relations are not subject to concurrent
* concerns, so there's no need for the more complicated concurrent build,
* anyway, and a non-concurrent reindex is more efficient.
*/
static bool
ReindexRelationConcurrently(Oid relationOid, ReindexParams *params)
{
typedef struct ReindexIndexInfo
{
Oid indexId;
Oid tableId;
Oid amId;
bool safe; /* for set_indexsafe_procflags */
} ReindexIndexInfo;
List *heapRelationIds = NIL;
List *indexIds = NIL;
List *newIndexIds = NIL;
List *relationLocks = NIL;
List *lockTags = NIL;
ListCell *lc,
*lc2;
MemoryContext private_context;
MemoryContext oldcontext;
char relkind;
char *relationName = NULL;
char *relationNamespace = NULL;
PGRUsage ru0;
const int progress_index[] = {
PROGRESS_CREATEIDX_COMMAND,
PROGRESS_CREATEIDX_PHASE,
PROGRESS_CREATEIDX_INDEX_OID,
PROGRESS_CREATEIDX_ACCESS_METHOD_OID
};
int64 progress_vals[4];
/*
* Create a memory context that will survive forced transaction commits we
* do below. Since it is a child of PortalContext, it will go away
* eventually even if we suffer an error; there's no need for special
* abort cleanup logic.
*/
private_context = AllocSetContextCreate(PortalContext,
"ReindexConcurrent",
ALLOCSET_SMALL_SIZES);
if ((params->options & REINDEXOPT_VERBOSE) != 0)
{
/* Save data needed by REINDEX VERBOSE in private context */
oldcontext = MemoryContextSwitchTo(private_context);
relationName = get_rel_name(relationOid);
relationNamespace = get_namespace_name(get_rel_namespace(relationOid));
pg_rusage_init(&ru0);
MemoryContextSwitchTo(oldcontext);
}
relkind = get_rel_relkind(relationOid);
/*
* Extract the list of indexes that are going to be rebuilt based on the
* relation Oid given by caller.
*/
switch (relkind)
{
case RELKIND_RELATION:
case RELKIND_MATVIEW:
case RELKIND_TOASTVALUE:
{
/*
* In the case of a relation, find all its indexes including
* toast indexes.
*/
Relation heapRelation;
/* Save the list of relation OIDs in private context */
oldcontext = MemoryContextSwitchTo(private_context);
/* Track this relation for session locks */
heapRelationIds = lappend_oid(heapRelationIds, relationOid);
MemoryContextSwitchTo(oldcontext);
if (IsCatalogRelationOid(relationOid))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot reindex system catalogs concurrently")));
/* Open relation to get its indexes */
if ((params->options & REINDEXOPT_MISSING_OK) != 0)
{
heapRelation = try_table_open(relationOid,
ShareUpdateExclusiveLock);
/* leave if relation does not exist */
if (!heapRelation)
break;
}
else
heapRelation = table_open(relationOid,
ShareUpdateExclusiveLock);
if (OidIsValid(params->tablespaceOid) &&
IsSystemRelation(heapRelation))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot move system relation \"%s\"",
RelationGetRelationName(heapRelation))));
/* Add all the valid indexes of relation to list */
foreach(lc, RelationGetIndexList(heapRelation))
{
Oid cellOid = lfirst_oid(lc);
Relation indexRelation = index_open(cellOid,
ShareUpdateExclusiveLock);
if (!indexRelation->rd_index->indisvalid)
ereport(WARNING,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot reindex invalid index \"%s.%s\" concurrently, skipping",
get_namespace_name(get_rel_namespace(cellOid)),
get_rel_name(cellOid))));
else if (indexRelation->rd_index->indisexclusion)
ereport(WARNING,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot reindex exclusion constraint index \"%s.%s\" concurrently, skipping",
get_namespace_name(get_rel_namespace(cellOid)),
get_rel_name(cellOid))));
else
{
ReindexIndexInfo *idx;
/* Save the list of relation OIDs in private context */
oldcontext = MemoryContextSwitchTo(private_context);
idx = palloc_object(ReindexIndexInfo);
idx->indexId = cellOid;
/* other fields set later */
indexIds = lappend(indexIds, idx);
MemoryContextSwitchTo(oldcontext);
}
index_close(indexRelation, NoLock);
}
/* Also add the toast indexes */
if (OidIsValid(heapRelation->rd_rel->reltoastrelid))
{
Oid toastOid = heapRelation->rd_rel->reltoastrelid;
Relation toastRelation = table_open(toastOid,
ShareUpdateExclusiveLock);
/* Save the list of relation OIDs in private context */
oldcontext = MemoryContextSwitchTo(private_context);
/* Track this relation for session locks */
heapRelationIds = lappend_oid(heapRelationIds, toastOid);
MemoryContextSwitchTo(oldcontext);
foreach(lc2, RelationGetIndexList(toastRelation))
{
Oid cellOid = lfirst_oid(lc2);
Relation indexRelation = index_open(cellOid,
ShareUpdateExclusiveLock);
if (!indexRelation->rd_index->indisvalid)
ereport(WARNING,
(errcode(ERRCODE_INDEX_CORRUPTED),
errmsg("cannot reindex invalid index \"%s.%s\" concurrently, skipping",
get_namespace_name(get_rel_namespace(cellOid)),
get_rel_name(cellOid))));
else
{
ReindexIndexInfo *idx;
/*
* Save the list of relation OIDs in private
* context
*/
oldcontext = MemoryContextSwitchTo(private_context);
idx = palloc_object(ReindexIndexInfo);
idx->indexId = cellOid;
indexIds = lappend(indexIds, idx);
/* other fields set later */
MemoryContextSwitchTo(oldcontext);
}
index_close(indexRelation, NoLock);
}
table_close(toastRelation, NoLock);
}
table_close(heapRelation, NoLock);
break;
}
case RELKIND_INDEX:
{
Oid heapId = IndexGetRelation(relationOid,
(params->options & REINDEXOPT_MISSING_OK) != 0);
Relation heapRelation;
ReindexIndexInfo *idx;
/* if relation is missing, leave */
if (!OidIsValid(heapId))
break;
if (IsCatalogRelationOid(heapId))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot reindex system catalogs concurrently")));
/*
* Don't allow reindex for an invalid index on TOAST table, as
* if rebuilt it would not be possible to drop it. Match
* error message in reindex_index().
*/
if (IsToastNamespace(get_rel_namespace(relationOid)) &&
!get_index_isvalid(relationOid))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot reindex invalid index on TOAST table")));
/*
* Check if parent relation can be locked and if it exists,
* this needs to be done at this stage as the list of indexes
* to rebuild is not complete yet, and REINDEXOPT_MISSING_OK
* should not be used once all the session locks are taken.
*/
if ((params->options & REINDEXOPT_MISSING_OK) != 0)
{
heapRelation = try_table_open(heapId,
ShareUpdateExclusiveLock);
/* leave if relation does not exist */
if (!heapRelation)
break;
}
else
heapRelation = table_open(heapId,
ShareUpdateExclusiveLock);
if (OidIsValid(params->tablespaceOid) &&
IsSystemRelation(heapRelation))
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot move system relation \"%s\"",
get_rel_name(relationOid))));
table_close(heapRelation, NoLock);
/* Save the list of relation OIDs in private context */
oldcontext = MemoryContextSwitchTo(private_context);
/* Track the heap relation of this index for session locks */
heapRelationIds = list_make1_oid(heapId);
/*
* Save the list of relation OIDs in private context. Note
* that invalid indexes are allowed here.
*/
idx = palloc_object(ReindexIndexInfo);
idx->indexId = relationOid;
indexIds = lappend(indexIds, idx);
/* other fields set later */
MemoryContextSwitchTo(oldcontext);
break;
}
case RELKIND_PARTITIONED_TABLE:
case RELKIND_PARTITIONED_INDEX:
default:
/* Return error if type of relation is not supported */
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("cannot reindex this type of relation concurrently")));
break;
}
/*
* Definitely no indexes, so leave. Any checks based on
* REINDEXOPT_MISSING_OK should be done only while the list of indexes to
* work on is built as the session locks taken before this transaction
* commits will make sure that they cannot be dropped by a concurrent
* session until this operation completes.
*/
if (indexIds == NIL)
{
PopActiveSnapshot();
return false;
}
/* It's not a shared catalog, so refuse to move it to shared tablespace */
if (params->tablespaceOid == GLOBALTABLESPACE_OID)
ereport(ERROR,
(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
errmsg("cannot move non-shared relation to tablespace \"%s\"",
get_tablespace_name(params->tablespaceOid))));
Assert(heapRelationIds != NIL);
/*-----
* Now we have all the indexes we want to process in indexIds.
*
* The phases now are:
*
* 1. create new indexes in the catalog
* 2. build new indexes
* 3. let new indexes catch up with tuples inserted in the meantime
* 4. swap index names
* 5. mark old indexes as dead
* 6. drop old indexes
*
* We process each phase for all indexes before moving to the next phase,
* for efficiency.
*/
/*
* Phase 1 of REINDEX CONCURRENTLY
*
* Create a new index with the same properties as the old one, but it is
* only registered in catalogs and will be built later. Then get session
* locks on all involved tables. See analogous code in DefineIndex() for
* more detailed comments.
*/
foreach(lc, indexIds)
{
char *concurrentName;
ReindexIndexInfo *idx = lfirst(lc);
ReindexIndexInfo *newidx;
Oid newIndexId;
Relation indexRel;
Relation heapRel;
Oid save_userid;
int save_sec_context;
int save_nestlevel;
Relation newIndexRel;
LockRelId *lockrelid;
Oid tablespaceid;
indexRel = index_open(idx->indexId, ShareUpdateExclusiveLock);
heapRel = table_open(indexRel->rd_index->indrelid,
ShareUpdateExclusiveLock);
/*
* Switch to the table owner's userid, so that any index functions are
* run as that user. Also lock down security-restricted operations
* and arrange to make GUC variable changes local to this command.
*/
GetUserIdAndSecContext(&save_userid, &save_sec_context);
SetUserIdAndSecContext(heapRel->rd_rel->relowner,
save_sec_context | SECURITY_RESTRICTED_OPERATION);
save_nestlevel = NewGUCNestLevel();
/* determine safety of this index for set_indexsafe_procflags */
idx->safe = (indexRel->rd_indexprs == NIL &&
indexRel->rd_indpred == NIL);
idx->tableId = RelationGetRelid(heapRel);
idx->amId = indexRel->rd_rel->relam;
/* This function shouldn't be called for temporary relations. */
if (indexRel->rd_rel->relpersistence == RELPERSISTENCE_TEMP)
elog(ERROR, "cannot reindex a temporary table concurrently");
pgstat_progress_start_command(PROGRESS_COMMAND_CREATE_INDEX,
idx->tableId);
progress_vals[0] = PROGRESS_CREATEIDX_COMMAND_REINDEX_CONCURRENTLY;
progress_vals[1] = 0; /* initializing */
progress_vals[2] = idx->indexId;
progress_vals[3] = idx->amId;
pgstat_progress_update_multi_param(4, progress_index, progress_vals);
/* Choose a temporary relation name for the new index */
concurrentName = ChooseRelationName(get_rel_name(idx->indexId),
NULL,
"ccnew",
get_rel_namespace(indexRel->rd_index->indrelid),
false);
/* Choose the new tablespace, indexes of toast tables are not moved */
if (OidIsValid(params->tablespaceOid) &&
heapRel->rd_rel->relkind != RELKIND_TOASTVALUE)
tablespaceid = params->tablespaceOid;
else
tablespaceid = indexRel->rd_rel->reltablespace;
/* Create new index definition based on given index */
newIndexId = index_concurrently_create_copy(heapRel,
idx->indexId,
tablespaceid,
concurrentName);
/*
* Now open the relation of the new index, a session-level lock is
* also needed on it.
*/
newIndexRel = index_open(newIndexId, ShareUpdateExclusiveLock);
/*
* Save the list of OIDs and locks in private context
*/
oldcontext = MemoryContextSwitchTo(private_context);
newidx = palloc_object(ReindexIndexInfo);
newidx->indexId = newIndexId;
newidx->safe = idx->safe;
newidx->tableId = idx->tableId;
newidx->amId = idx->amId;
newIndexIds = lappend(newIndexIds, newidx);
/*
* Save lockrelid to protect each relation from drop then close
* relations. The lockrelid on parent relation is not taken here to
* avoid multiple locks taken on the same relation, instead we rely on
* parentRelationIds built earlier.
*/
lockrelid = palloc_object(LockRelId);
*lockrelid = indexRel->rd_lockInfo.lockRelId;
relationLocks = lappend(relationLocks, lockrelid);
lockrelid = palloc_object(LockRelId);
*lockrelid = newIndexRel->rd_lockInfo.lockRelId;
relationLocks = lappend(relationLocks, lockrelid);
MemoryContextSwitchTo(oldcontext);
index_close(indexRel, NoLock);
index_close(newIndexRel, NoLock);
/* Roll back any GUC changes executed by index functions */
AtEOXact_GUC(false, save_nestlevel);
/* Restore userid and security context */
SetUserIdAndSecContext(save_userid, save_sec_context);
table_close(heapRel, NoLock);
}
/*
* Save the heap lock for following visibility checks with other backends
* might conflict with this session.
*/
foreach(lc, heapRelationIds)
{
Relation heapRelation = table_open(lfirst_oid(lc), ShareUpdateExclusiveLock);
LockRelId *lockrelid;
LOCKTAG *heaplocktag;
/* Save the list of locks in private context */
oldcontext = MemoryContextSwitchTo(private_context);
/* Add lockrelid of heap relation to the list of locked relations */
lockrelid = palloc_object(LockRelId);
*lockrelid = heapRelation->rd_lockInfo.lockRelId;
relationLocks = lappend(relationLocks, lockrelid);
heaplocktag = palloc_object(LOCKTAG);
/* Save the LOCKTAG for this parent relation for the wait phase */
SET_LOCKTAG_RELATION(*heaplocktag, lockrelid->dbId, lockrelid->relId);
lockTags = lappend(lockTags, heaplocktag);
MemoryContextSwitchTo(oldcontext);
/* Close heap relation */
table_close(heapRelation, NoLock);
}
/* Get a session-level lock on each table. */
foreach(lc, relationLocks)
{
LockRelId *lockrelid = (LockRelId *) lfirst(lc);
LockRelationIdForSession(lockrelid, ShareUpdateExclusiveLock);
}
PopActiveSnapshot();
CommitTransactionCommand();
StartTransactionCommand();
/*
* Because we don't take a snapshot in this transaction, there's no need
* to set the PROC_IN_SAFE_IC flag here.
*/
/*
* Phase 2 of REINDEX CONCURRENTLY
*
* Build the new indexes in a separate transaction for each index to avoid
* having open transactions for an unnecessary long time. But before
* doing that, wait until no running transactions could have the table of
* the index open with the old list of indexes. See "phase 2" in
* DefineIndex() for more details.
*/
pgstat_progress_update_param(PROGRESS_CREATEIDX_PHASE,
PROGRESS_CREATEIDX_PHASE_WAIT_1);
WaitForLockersMultiple(lockTags, ShareLock, true);
CommitTransactionCommand();
foreach(lc, newIndexIds)
{
ReindexIndexInfo *newidx = lfirst(lc);
/* Start new transaction for this index's concurrent build */
StartTransactionCommand();
/*
* Check for user-requested abort. This is inside a transaction so as
* xact.c does not issue a useless WARNING, and ensures that
* session-level locks are cleaned up on abort.
*/
CHECK_FOR_INTERRUPTS();
/* Tell concurrent indexing to ignore us, if index qualifies */
if (newidx->safe)
set_indexsafe_procflags();
/* Set ActiveSnapshot since functions in the indexes may need it */
PushActiveSnapshot(GetTransactionSnapshot());
/*
* Update progress for the index to build, with the correct parent
* table involved.
*/
pgstat_progress_start_command(PROGRESS_COMMAND_CREATE_INDEX, newidx->tableId);
progress_vals[0] = PROGRESS_CREATEIDX_COMMAND_REINDEX_CONCURRENTLY;
progress_vals[1] = PROGRESS_CREATEIDX_PHASE_BUILD;
progress_vals[2] = newidx->indexId;
progress_vals[3] = newidx->amId;
pgstat_progress_update_multi_param(4, progress_index, progress_vals);
/* Perform concurrent build of new index */
index_concurrently_build(newidx->tableId, newidx->indexId);
PopActiveSnapshot();
CommitTransactionCommand();
}
StartTransactionCommand();
/*
* Because we don't take a snapshot or Xid in this transaction, there's no
* need to set the PROC_IN_SAFE_IC flag here.
*/
/*
* Phase 3 of REINDEX CONCURRENTLY
*
* During this phase the old indexes catch up with any new tuples that
* were created during the previous phase. See "phase 3" in DefineIndex()
* for more details.
*/
pgstat_progress_update_param(PROGRESS_CREATEIDX_PHASE,
PROGRESS_CREATEIDX_PHASE_WAIT_2);
WaitForLockersMultiple(lockTags, ShareLock, true);
CommitTransactionCommand();
foreach(lc, newIndexIds)
{
ReindexIndexInfo *newidx = lfirst(lc);
TransactionId limitXmin;
Snapshot snapshot;
StartTransactionCommand();
/*
* Check for user-requested abort. This is inside a transaction so as
* xact.c does not issue a useless WARNING, and ensures that
* session-level locks are cleaned up on abort.
*/
CHECK_FOR_INTERRUPTS();
/* Tell concurrent indexing to ignore us, if index qualifies */
if (newidx->safe)
set_indexsafe_procflags();
/*
* Take the "reference snapshot" that will be used by validate_index()
* to filter candidate tuples.
*/
snapshot = RegisterSnapshot(GetTransactionSnapshot());
PushActiveSnapshot(snapshot);
/*
* Update progress for the index to build, with the correct parent
* table involved.
*/
pgstat_progress_start_command(PROGRESS_COMMAND_CREATE_INDEX,
newidx->tableId);
progress_vals[0] = PROGRESS_CREATEIDX_COMMAND_REINDEX_CONCURRENTLY;
progress_vals[1] = PROGRESS_CREATEIDX_PHASE_VALIDATE_IDXSCAN;
progress_vals[2] = newidx->indexId;
progress_vals[3] = newidx->amId;
pgstat_progress_update_multi_param(4, progress_index, progress_vals);
validate_index(newidx->tableId, newidx->indexId, snapshot);
/*
* We can now do away with our active snapshot, we still need to save
* the xmin limit to wait for older snapshots.
*/
limitXmin = snapshot->xmin;
PopActiveSnapshot();
UnregisterSnapshot(snapshot);
/*
* To ensure no deadlocks, we must commit and start yet another
* transaction, and do our wait before any snapshot has been taken in
* it.
*/
CommitTransactionCommand();
StartTransactionCommand();
/*
* The index is now valid in the sense that it contains all currently
* interesting tuples. But since it might not contain tuples deleted
* just before the reference snap was taken, we have to wait out any
* transactions that might have older snapshots.
*
* Because we don't take a snapshot or Xid in this transaction,
* there's no need to set the PROC_IN_SAFE_IC flag here.
*/
pgstat_progress_update_param(PROGRESS_CREATEIDX_PHASE,
PROGRESS_CREATEIDX_PHASE_WAIT_3);
WaitForOlderSnapshots(limitXmin, true);
CommitTransactionCommand();
}
/*
* Phase 4 of REINDEX CONCURRENTLY
*
* Now that the new indexes have been validated, swap each new index with
* its corresponding old index.
*
* We mark the new indexes as valid and the old indexes as not valid at
* the same time to make sure we only get constraint violations from the
* indexes with the correct names.
*/
StartTransactionCommand();
/*
* Because this transaction only does catalog manipulations and doesn't do
* any index operations, we can set the PROC_IN_SAFE_IC flag here
* unconditionally.
*/
set_indexsafe_procflags();
forboth(lc, indexIds, lc2, newIndexIds)
{
ReindexIndexInfo *oldidx = lfirst(lc);
ReindexIndexInfo *newidx = lfirst(lc2);
char *oldName;
/*
* Check for user-requested abort. This is inside a transaction so as
* xact.c does not issue a useless WARNING, and ensures that
* session-level locks are cleaned up on abort.
*/
CHECK_FOR_INTERRUPTS();
/* Choose a relation name for old index */
oldName = ChooseRelationName(get_rel_name(oldidx->indexId),
NULL,
"ccold",
get_rel_namespace(oldidx->tableId),
false);
/*
* Swap old index with the new one. This also marks the new one as
* valid and the old one as not valid.
*/
index_concurrently_swap(newidx->indexId, oldidx->indexId, oldName);
/*
* Invalidate the relcache for the table, so that after this commit
* all sessions will refresh any cached plans that might reference the
* index.
*/
CacheInvalidateRelcacheByRelid(oldidx->tableId);
/*
* CCI here so that subsequent iterations see the oldName in the
* catalog and can choose a nonconflicting name for their oldName.
* Otherwise, this could lead to conflicts if a table has two indexes
* whose names are equal for the first NAMEDATALEN-minus-a-few
* characters.
*/
CommandCounterIncrement();
}
/* Commit this transaction and make index swaps visible */
CommitTransactionCommand();
StartTransactionCommand();
/*
* While we could set PROC_IN_SAFE_IC if all indexes qualified, there's no
* real need for that, because we only acquire an Xid after the wait is
* done, and that lasts for a very short period.
*/
/*
* Phase 5 of REINDEX CONCURRENTLY
*
* Mark the old indexes as dead. First we must wait until no running
* transaction could be using the index for a query. See also
* index_drop() for more details.
*/
pgstat_progress_update_param(PROGRESS_CREATEIDX_PHASE,
PROGRESS_CREATEIDX_PHASE_WAIT_4);
WaitForLockersMultiple(lockTags, AccessExclusiveLock, true);
foreach(lc, indexIds)
{
ReindexIndexInfo *oldidx = lfirst(lc);
/*
* Check for user-requested abort. This is inside a transaction so as
* xact.c does not issue a useless WARNING, and ensures that
* session-level locks are cleaned up on abort.
*/
CHECK_FOR_INTERRUPTS();
index_concurrently_set_dead(oldidx->tableId, oldidx->indexId);
}
/* Commit this transaction to make the updates visible. */
CommitTransactionCommand();
StartTransactionCommand();
/*
* While we could set PROC_IN_SAFE_IC if all indexes qualified, there's no
* real need for that, because we only acquire an Xid after the wait is
* done, and that lasts for a very short period.
*/
/*
* Phase 6 of REINDEX CONCURRENTLY
*
* Drop the old indexes.
*/
pgstat_progress_update_param(PROGRESS_CREATEIDX_PHASE,
PROGRESS_CREATEIDX_PHASE_WAIT_5);
WaitForLockersMultiple(lockTags, AccessExclusiveLock, true);
PushActiveSnapshot(GetTransactionSnapshot());
{
ObjectAddresses *objects = new_object_addresses();
foreach(lc, indexIds)
{
ReindexIndexInfo *idx = lfirst(lc);
ObjectAddress object;
object.classId = RelationRelationId;
object.objectId = idx->indexId;
object.objectSubId = 0;
add_exact_object_address(&object, objects);
}
/*
* Use PERFORM_DELETION_CONCURRENT_LOCK so that index_drop() uses the
* right lock level.
*/
performMultipleDeletions(objects, DROP_RESTRICT,
PERFORM_DELETION_CONCURRENT_LOCK | PERFORM_DELETION_INTERNAL);
}
PopActiveSnapshot();
CommitTransactionCommand();
/*
* Finally, release the session-level lock on the table.
*/
foreach(lc, relationLocks)
{
LockRelId *lockrelid = (LockRelId *) lfirst(lc);
UnlockRelationIdForSession(lockrelid, ShareUpdateExclusiveLock);
}
/* Start a new transaction to finish process properly */
StartTransactionCommand();
/* Log what we did */
if ((params->options & REINDEXOPT_VERBOSE) != 0)
{
if (relkind == RELKIND_INDEX)
ereport(INFO,
(errmsg("index \"%s.%s\" was reindexed",
relationNamespace, relationName),
errdetail("%s.",
pg_rusage_show(&ru0))));
else
{
foreach(lc, newIndexIds)
{
ReindexIndexInfo *idx = lfirst(lc);
Oid indOid = idx->indexId;
ereport(INFO,
(errmsg("index \"%s.%s\" was reindexed",
get_namespace_name(get_rel_namespace(indOid)),
get_rel_name(indOid))));
/* Don't show rusage here, since it's not per index. */
}
ereport(INFO,
(errmsg("table \"%s.%s\" was reindexed",
relationNamespace, relationName),
errdetail("%s.",
pg_rusage_show(&ru0))));
}
}
MemoryContextDelete(private_context);
pgstat_progress_end_command();
return true;
}
/*
* Insert or delete an appropriate pg_inherits tuple to make the given index
* be a partition of the indicated parent index.
*
* This also corrects the pg_depend information for the affected index.
*/
void
IndexSetParentIndex(Relation partitionIdx, Oid parentOid)
{
Relation pg_inherits;
ScanKeyData key[2];
SysScanDesc scan;
Oid partRelid = RelationGetRelid(partitionIdx);
HeapTuple tuple;
bool fix_dependencies;
/* Make sure this is an index */
Assert(partitionIdx->rd_rel->relkind == RELKIND_INDEX ||
partitionIdx->rd_rel->relkind == RELKIND_PARTITIONED_INDEX);
/*
* Scan pg_inherits for rows linking our index to some parent.
*/
pg_inherits = relation_open(InheritsRelationId, RowExclusiveLock);
ScanKeyInit(&key[0],
Anum_pg_inherits_inhrelid,
BTEqualStrategyNumber, F_OIDEQ,
ObjectIdGetDatum(partRelid));
ScanKeyInit(&key[1],
Anum_pg_inherits_inhseqno,
BTEqualStrategyNumber, F_INT4EQ,
Int32GetDatum(1));
scan = systable_beginscan(pg_inherits, InheritsRelidSeqnoIndexId, true,
NULL, 2, key);
tuple = systable_getnext(scan);
if (!HeapTupleIsValid(tuple))
{
if (parentOid == InvalidOid)
{
/*
* No pg_inherits row, and no parent wanted: nothing to do in this
* case.
*/
fix_dependencies = false;
}
else
{
StoreSingleInheritance(partRelid, parentOid, 1);
fix_dependencies = true;
}
}
else
{
Form_pg_inherits inhForm = (Form_pg_inherits) GETSTRUCT(tuple);
if (parentOid == InvalidOid)
{
/*
* There exists a pg_inherits row, which we want to clear; do so.
*/
CatalogTupleDelete(pg_inherits, &tuple->t_self);
fix_dependencies = true;
}
else
{
/*
* A pg_inherits row exists. If it's the same we want, then we're
* good; if it differs, that amounts to a corrupt catalog and
* should not happen.
*/
if (inhForm->inhparent != parentOid)
{
/* unexpected: we should not get called in this case */
elog(ERROR, "bogus pg_inherit row: inhrelid %u inhparent %u",
inhForm->inhrelid, inhForm->inhparent);
}
/* already in the right state */
fix_dependencies = false;
}
}
/* done with pg_inherits */
systable_endscan(scan);
relation_close(pg_inherits, RowExclusiveLock);
/* set relhassubclass if an index partition has been added to the parent */
if (OidIsValid(parentOid))
SetRelationHasSubclass(parentOid, true);
/* set relispartition correctly on the partition */
update_relispartition(partRelid, OidIsValid(parentOid));
if (fix_dependencies)
{
/*
* Insert/delete pg_depend rows. If setting a parent, add PARTITION
* dependencies on the parent index and the table; if removing a
* parent, delete PARTITION dependencies.
*/
if (OidIsValid(parentOid))
{
ObjectAddress partIdx;
ObjectAddress parentIdx;
ObjectAddress partitionTbl;
ObjectAddressSet(partIdx, RelationRelationId, partRelid);
ObjectAddressSet(parentIdx, RelationRelationId, parentOid);
ObjectAddressSet(partitionTbl, RelationRelationId,
partitionIdx->rd_index->indrelid);
recordDependencyOn(&partIdx, &parentIdx,
DEPENDENCY_PARTITION_PRI);
recordDependencyOn(&partIdx, &partitionTbl,
DEPENDENCY_PARTITION_SEC);
}
else
{
deleteDependencyRecordsForClass(RelationRelationId, partRelid,
RelationRelationId,
DEPENDENCY_PARTITION_PRI);
deleteDependencyRecordsForClass(RelationRelationId, partRelid,
RelationRelationId,
DEPENDENCY_PARTITION_SEC);
}
/* make our updates visible */
CommandCounterIncrement();
}
}
/*
* Subroutine of IndexSetParentIndex to update the relispartition flag of the
* given index to the given value.
*/
static void
update_relispartition(Oid relationId, bool newval)
{
HeapTuple tup;
Relation classRel;
classRel = table_open(RelationRelationId, RowExclusiveLock);
tup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relationId));
if (!HeapTupleIsValid(tup))
elog(ERROR, "cache lookup failed for relation %u", relationId);
Assert(((Form_pg_class) GETSTRUCT(tup))->relispartition != newval);
((Form_pg_class) GETSTRUCT(tup))->relispartition = newval;
CatalogTupleUpdate(classRel, &tup->t_self, tup);
heap_freetuple(tup);
table_close(classRel, RowExclusiveLock);
}
/*
* Set the PROC_IN_SAFE_IC flag in MyProc->statusFlags.
*
* When doing concurrent index builds, we can set this flag
* to tell other processes concurrently running CREATE
* INDEX CONCURRENTLY or REINDEX CONCURRENTLY to ignore us when
* doing their waits for concurrent snapshots. On one hand it
* avoids pointlessly waiting for a process that's not interesting
* anyway; but more importantly it avoids deadlocks in some cases.
*
* This can be done safely only for indexes that don't execute any
* expressions that could access other tables, so index must not be
* expressional nor partial. Caller is responsible for only calling
* this routine when that assumption holds true.
*
* (The flag is reset automatically at transaction end, so it must be
* set for each transaction.)
*/
static inline void
set_indexsafe_procflags(void)
{
/*
* This should only be called before installing xid or xmin in MyProc;
* otherwise, concurrent processes could see an Xmin that moves backwards.
*/
Assert(MyProc->xid == InvalidTransactionId &&
MyProc->xmin == InvalidTransactionId);
LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
MyProc->statusFlags |= PROC_IN_SAFE_IC;
ProcGlobal->statusFlags[MyProc->pgxactoff] = MyProc->statusFlags;
LWLockRelease(ProcArrayLock);
}
|