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
|
/*-------------------------------------------------------------------------
*
* allpaths.c
* Routines to find possible search paths for processing a query
*
* Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
* src/backend/optimizer/path/allpaths.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include <limits.h>
#include <math.h>
#include "access/sysattr.h"
#include "access/tsmapi.h"
#include "catalog/pg_class.h"
#include "catalog/pg_operator.h"
#include "catalog/pg_proc.h"
#include "foreign/fdwapi.h"
#include "miscadmin.h"
#include "nodes/makefuncs.h"
#include "nodes/nodeFuncs.h"
#ifdef OPTIMIZER_DEBUG
#include "nodes/print.h"
#endif
#include "optimizer/appendinfo.h"
#include "optimizer/clauses.h"
#include "optimizer/cost.h"
#include "optimizer/geqo.h"
#include "optimizer/inherit.h"
#include "optimizer/optimizer.h"
#include "optimizer/pathnode.h"
#include "optimizer/paths.h"
#include "optimizer/plancat.h"
#include "optimizer/planner.h"
#include "optimizer/restrictinfo.h"
#include "optimizer/tlist.h"
#include "parser/parse_clause.h"
#include "parser/parsetree.h"
#include "partitioning/partbounds.h"
#include "partitioning/partprune.h"
#include "rewrite/rewriteManip.h"
#include "utils/lsyscache.h"
/* results of subquery_is_pushdown_safe */
typedef struct pushdown_safety_info
{
bool *unsafeColumns; /* which output columns are unsafe to use */
bool unsafeVolatile; /* don't push down volatile quals */
bool unsafeLeaky; /* don't push down leaky quals */
} pushdown_safety_info;
/* These parameters are set by GUC */
bool enable_geqo = false; /* just in case GUC doesn't set it */
int geqo_threshold;
int min_parallel_table_scan_size;
int min_parallel_index_scan_size;
/* Hook for plugins to get control in set_rel_pathlist() */
set_rel_pathlist_hook_type set_rel_pathlist_hook = NULL;
/* Hook for plugins to replace standard_join_search() */
join_search_hook_type join_search_hook = NULL;
static void set_base_rel_consider_startup(PlannerInfo *root);
static void set_base_rel_sizes(PlannerInfo *root);
static void set_base_rel_pathlists(PlannerInfo *root);
static void set_rel_size(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte);
static void set_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte);
static void set_plain_rel_size(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void create_plain_partial_paths(PlannerInfo *root, RelOptInfo *rel);
static void set_rel_consider_parallel(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_plain_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_tablesample_rel_size(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_tablesample_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_foreign_size(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_foreign_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_append_rel_size(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte);
static void set_append_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte);
static void generate_orderedappend_paths(PlannerInfo *root, RelOptInfo *rel,
List *live_childrels,
List *all_child_pathkeys,
List *partitioned_rels);
static Path *get_cheapest_parameterized_child_path(PlannerInfo *root,
RelOptInfo *rel,
Relids required_outer);
static void accumulate_append_subpath(Path *path,
List **subpaths, List **special_subpaths);
static Path *get_singleton_append_subpath(Path *path);
static void set_dummy_rel_pathlist(RelOptInfo *rel);
static void set_subquery_pathlist(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte);
static void set_function_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_values_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_tablefunc_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_cte_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_namedtuplestore_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_result_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static void set_worktable_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte);
static RelOptInfo *make_rel_from_joinlist(PlannerInfo *root, List *joinlist);
static bool subquery_is_pushdown_safe(Query *subquery, Query *topquery,
pushdown_safety_info *safetyInfo);
static bool recurse_pushdown_safe(Node *setOp, Query *topquery,
pushdown_safety_info *safetyInfo);
static void check_output_expressions(Query *subquery,
pushdown_safety_info *safetyInfo);
static void compare_tlist_datatypes(List *tlist, List *colTypes,
pushdown_safety_info *safetyInfo);
static bool targetIsInAllPartitionLists(TargetEntry *tle, Query *query);
static bool qual_is_pushdown_safe(Query *subquery, Index rti, Node *qual,
pushdown_safety_info *safetyInfo);
static void subquery_push_qual(Query *subquery,
RangeTblEntry *rte, Index rti, Node *qual);
static void recurse_push_qual(Node *setOp, Query *topquery,
RangeTblEntry *rte, Index rti, Node *qual);
static void remove_unused_subquery_outputs(Query *subquery, RelOptInfo *rel);
/*
* make_one_rel
* Finds all possible access paths for executing a query, returning a
* single rel that represents the join of all base rels in the query.
*/
RelOptInfo *
make_one_rel(PlannerInfo *root, List *joinlist)
{
RelOptInfo *rel;
Index rti;
double total_pages;
/*
* Construct the all_baserels Relids set.
*/
root->all_baserels = NULL;
for (rti = 1; rti < root->simple_rel_array_size; rti++)
{
RelOptInfo *brel = root->simple_rel_array[rti];
/* there may be empty slots corresponding to non-baserel RTEs */
if (brel == NULL)
continue;
Assert(brel->relid == rti); /* sanity check on array */
/* ignore RTEs that are "other rels" */
if (brel->reloptkind != RELOPT_BASEREL)
continue;
root->all_baserels = bms_add_member(root->all_baserels, brel->relid);
}
/* Mark base rels as to whether we care about fast-start plans */
set_base_rel_consider_startup(root);
/*
* Compute size estimates and consider_parallel flags for each base rel.
*/
set_base_rel_sizes(root);
/*
* We should now have size estimates for every actual table involved in
* the query, and we also know which if any have been deleted from the
* query by join removal, pruned by partition pruning, or eliminated by
* constraint exclusion. So we can now compute total_table_pages.
*
* Note that appendrels are not double-counted here, even though we don't
* bother to distinguish RelOptInfos for appendrel parents, because the
* parents will have pages = 0.
*
* XXX if a table is self-joined, we will count it once per appearance,
* which perhaps is the wrong thing ... but that's not completely clear,
* and detecting self-joins here is difficult, so ignore it for now.
*/
total_pages = 0;
for (rti = 1; rti < root->simple_rel_array_size; rti++)
{
RelOptInfo *brel = root->simple_rel_array[rti];
if (brel == NULL)
continue;
Assert(brel->relid == rti); /* sanity check on array */
if (IS_DUMMY_REL(brel))
continue;
if (IS_SIMPLE_REL(brel))
total_pages += (double) brel->pages;
}
root->total_table_pages = total_pages;
/*
* Generate access paths for each base rel.
*/
set_base_rel_pathlists(root);
/*
* Generate access paths for the entire join tree.
*/
rel = make_rel_from_joinlist(root, joinlist);
/*
* The result should join all and only the query's base rels.
*/
Assert(bms_equal(rel->relids, root->all_baserels));
return rel;
}
/*
* set_base_rel_consider_startup
* Set the consider_[param_]startup flags for each base-relation entry.
*
* For the moment, we only deal with consider_param_startup here; because the
* logic for consider_startup is pretty trivial and is the same for every base
* relation, we just let build_simple_rel() initialize that flag correctly to
* start with. If that logic ever gets more complicated it would probably
* be better to move it here.
*/
static void
set_base_rel_consider_startup(PlannerInfo *root)
{
/*
* Since parameterized paths can only be used on the inside of a nestloop
* join plan, there is usually little value in considering fast-start
* plans for them. However, for relations that are on the RHS of a SEMI
* or ANTI join, a fast-start plan can be useful because we're only going
* to care about fetching one tuple anyway.
*
* To minimize growth of planning time, we currently restrict this to
* cases where the RHS is a single base relation, not a join; there is no
* provision for consider_param_startup to get set at all on joinrels.
* Also we don't worry about appendrels. costsize.c's costing rules for
* nestloop semi/antijoins don't consider such cases either.
*/
ListCell *lc;
foreach(lc, root->join_info_list)
{
SpecialJoinInfo *sjinfo = (SpecialJoinInfo *) lfirst(lc);
int varno;
if ((sjinfo->jointype == JOIN_SEMI || sjinfo->jointype == JOIN_ANTI) &&
bms_get_singleton_member(sjinfo->syn_righthand, &varno))
{
RelOptInfo *rel = find_base_rel(root, varno);
rel->consider_param_startup = true;
}
}
}
/*
* set_base_rel_sizes
* Set the size estimates (rows and widths) for each base-relation entry.
* Also determine whether to consider parallel paths for base relations.
*
* We do this in a separate pass over the base rels so that rowcount
* estimates are available for parameterized path generation, and also so
* that each rel's consider_parallel flag is set correctly before we begin to
* generate paths.
*/
static void
set_base_rel_sizes(PlannerInfo *root)
{
Index rti;
for (rti = 1; rti < root->simple_rel_array_size; rti++)
{
RelOptInfo *rel = root->simple_rel_array[rti];
RangeTblEntry *rte;
/* there may be empty slots corresponding to non-baserel RTEs */
if (rel == NULL)
continue;
Assert(rel->relid == rti); /* sanity check on array */
/* ignore RTEs that are "other rels" */
if (rel->reloptkind != RELOPT_BASEREL)
continue;
rte = root->simple_rte_array[rti];
/*
* If parallelism is allowable for this query in general, see whether
* it's allowable for this rel in particular. We have to do this
* before set_rel_size(), because (a) if this rel is an inheritance
* parent, set_append_rel_size() will use and perhaps change the rel's
* consider_parallel flag, and (b) for some RTE types, set_rel_size()
* goes ahead and makes paths immediately.
*/
if (root->glob->parallelModeOK)
set_rel_consider_parallel(root, rel, rte);
set_rel_size(root, rel, rti, rte);
}
}
/*
* set_base_rel_pathlists
* Finds all paths available for scanning each base-relation entry.
* Sequential scan and any available indices are considered.
* Each useful path is attached to its relation's 'pathlist' field.
*/
static void
set_base_rel_pathlists(PlannerInfo *root)
{
Index rti;
for (rti = 1; rti < root->simple_rel_array_size; rti++)
{
RelOptInfo *rel = root->simple_rel_array[rti];
/* there may be empty slots corresponding to non-baserel RTEs */
if (rel == NULL)
continue;
Assert(rel->relid == rti); /* sanity check on array */
/* ignore RTEs that are "other rels" */
if (rel->reloptkind != RELOPT_BASEREL)
continue;
set_rel_pathlist(root, rel, rti, root->simple_rte_array[rti]);
}
}
/*
* set_rel_size
* Set size estimates for a base relation
*/
static void
set_rel_size(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte)
{
if (rel->reloptkind == RELOPT_BASEREL &&
relation_excluded_by_constraints(root, rel, rte))
{
/*
* We proved we don't need to scan the rel via constraint exclusion,
* so set up a single dummy path for it. Here we only check this for
* regular baserels; if it's an otherrel, CE was already checked in
* set_append_rel_size().
*
* In this case, we go ahead and set up the relation's path right away
* instead of leaving it for set_rel_pathlist to do. This is because
* we don't have a convention for marking a rel as dummy except by
* assigning a dummy path to it.
*/
set_dummy_rel_pathlist(rel);
}
else if (rte->inh)
{
/* It's an "append relation", process accordingly */
set_append_rel_size(root, rel, rti, rte);
}
else
{
switch (rel->rtekind)
{
case RTE_RELATION:
if (rte->relkind == RELKIND_FOREIGN_TABLE)
{
/* Foreign table */
set_foreign_size(root, rel, rte);
}
else if (rte->relkind == RELKIND_PARTITIONED_TABLE)
{
/*
* We could get here if asked to scan a partitioned table
* with ONLY. In that case we shouldn't scan any of the
* partitions, so mark it as a dummy rel.
*/
set_dummy_rel_pathlist(rel);
}
else if (rte->tablesample != NULL)
{
/* Sampled relation */
set_tablesample_rel_size(root, rel, rte);
}
else
{
/* Plain relation */
set_plain_rel_size(root, rel, rte);
}
break;
case RTE_SUBQUERY:
/*
* Subqueries don't support making a choice between
* parameterized and unparameterized paths, so just go ahead
* and build their paths immediately.
*/
set_subquery_pathlist(root, rel, rti, rte);
break;
case RTE_FUNCTION:
set_function_size_estimates(root, rel);
break;
case RTE_TABLEFUNC:
set_tablefunc_size_estimates(root, rel);
break;
case RTE_VALUES:
set_values_size_estimates(root, rel);
break;
case RTE_CTE:
/*
* CTEs don't support making a choice between parameterized
* and unparameterized paths, so just go ahead and build their
* paths immediately.
*/
if (rte->self_reference)
set_worktable_pathlist(root, rel, rte);
else
set_cte_pathlist(root, rel, rte);
break;
case RTE_NAMEDTUPLESTORE:
/* Might as well just build the path immediately */
set_namedtuplestore_pathlist(root, rel, rte);
break;
case RTE_RESULT:
/* Might as well just build the path immediately */
set_result_pathlist(root, rel, rte);
break;
default:
elog(ERROR, "unexpected rtekind: %d", (int) rel->rtekind);
break;
}
}
/*
* We insist that all non-dummy rels have a nonzero rowcount estimate.
*/
Assert(rel->rows > 0 || IS_DUMMY_REL(rel));
}
/*
* set_rel_pathlist
* Build access paths for a base relation
*/
static void
set_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte)
{
if (IS_DUMMY_REL(rel))
{
/* We already proved the relation empty, so nothing more to do */
}
else if (rte->inh)
{
/* It's an "append relation", process accordingly */
set_append_rel_pathlist(root, rel, rti, rte);
}
else
{
switch (rel->rtekind)
{
case RTE_RELATION:
if (rte->relkind == RELKIND_FOREIGN_TABLE)
{
/* Foreign table */
set_foreign_pathlist(root, rel, rte);
}
else if (rte->tablesample != NULL)
{
/* Sampled relation */
set_tablesample_rel_pathlist(root, rel, rte);
}
else
{
/* Plain relation */
set_plain_rel_pathlist(root, rel, rte);
}
break;
case RTE_SUBQUERY:
/* Subquery --- fully handled during set_rel_size */
break;
case RTE_FUNCTION:
/* RangeFunction */
set_function_pathlist(root, rel, rte);
break;
case RTE_TABLEFUNC:
/* Table Function */
set_tablefunc_pathlist(root, rel, rte);
break;
case RTE_VALUES:
/* Values list */
set_values_pathlist(root, rel, rte);
break;
case RTE_CTE:
/* CTE reference --- fully handled during set_rel_size */
break;
case RTE_NAMEDTUPLESTORE:
/* tuplestore reference --- fully handled during set_rel_size */
break;
case RTE_RESULT:
/* simple Result --- fully handled during set_rel_size */
break;
default:
elog(ERROR, "unexpected rtekind: %d", (int) rel->rtekind);
break;
}
}
/*
* Allow a plugin to editorialize on the set of Paths for this base
* relation. It could add new paths (such as CustomPaths) by calling
* add_path(), or add_partial_path() if parallel aware. It could also
* delete or modify paths added by the core code.
*/
if (set_rel_pathlist_hook)
(*set_rel_pathlist_hook) (root, rel, rti, rte);
/*
* If this is a baserel, we should normally consider gathering any partial
* paths we may have created for it. We have to do this after calling the
* set_rel_pathlist_hook, else it cannot add partial paths to be included
* here.
*
* However, if this is an inheritance child, skip it. Otherwise, we could
* end up with a very large number of gather nodes, each trying to grab
* its own pool of workers. Instead, we'll consider gathering partial
* paths for the parent appendrel.
*
* Also, if this is the topmost scan/join rel (that is, the only baserel),
* we postpone gathering until the final scan/join targetlist is available
* (see grouping_planner).
*/
if (rel->reloptkind == RELOPT_BASEREL &&
bms_membership(root->all_baserels) != BMS_SINGLETON)
generate_gather_paths(root, rel, false);
/* Now find the cheapest of the paths for this rel */
set_cheapest(rel);
#ifdef OPTIMIZER_DEBUG
debug_print_rel(root, rel);
#endif
}
/*
* set_plain_rel_size
* Set size estimates for a plain relation (no subquery, no inheritance)
*/
static void
set_plain_rel_size(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
/*
* Test any partial indexes of rel for applicability. We must do this
* first since partial unique indexes can affect size estimates.
*/
check_index_predicates(root, rel);
/* Mark rel with estimated output rows, width, etc */
set_baserel_size_estimates(root, rel);
}
/*
* If this relation could possibly be scanned from within a worker, then set
* its consider_parallel flag.
*/
static void
set_rel_consider_parallel(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte)
{
/*
* The flag has previously been initialized to false, so we can just
* return if it becomes clear that we can't safely set it.
*/
Assert(!rel->consider_parallel);
/* Don't call this if parallelism is disallowed for the entire query. */
Assert(root->glob->parallelModeOK);
/* This should only be called for baserels and appendrel children. */
Assert(IS_SIMPLE_REL(rel));
/* Assorted checks based on rtekind. */
switch (rte->rtekind)
{
case RTE_RELATION:
/*
* Currently, parallel workers can't access the leader's temporary
* tables. We could possibly relax this if the wrote all of its
* local buffers at the start of the query and made no changes
* thereafter (maybe we could allow hint bit changes), and if we
* taught the workers to read them. Writing a large number of
* temporary buffers could be expensive, though, and we don't have
* the rest of the necessary infrastructure right now anyway. So
* for now, bail out if we see a temporary table.
*/
if (get_rel_persistence(rte->relid) == RELPERSISTENCE_TEMP)
return;
/*
* Table sampling can be pushed down to workers if the sample
* function and its arguments are safe.
*/
if (rte->tablesample != NULL)
{
char proparallel = func_parallel(rte->tablesample->tsmhandler);
if (proparallel != PROPARALLEL_SAFE)
return;
if (!is_parallel_safe(root, (Node *) rte->tablesample->args))
return;
}
/*
* Ask FDWs whether they can support performing a ForeignScan
* within a worker. Most often, the answer will be no. For
* example, if the nature of the FDW is such that it opens a TCP
* connection with a remote server, each parallel worker would end
* up with a separate connection, and these connections might not
* be appropriately coordinated between workers and the leader.
*/
if (rte->relkind == RELKIND_FOREIGN_TABLE)
{
Assert(rel->fdwroutine);
if (!rel->fdwroutine->IsForeignScanParallelSafe)
return;
if (!rel->fdwroutine->IsForeignScanParallelSafe(root, rel, rte))
return;
}
/*
* There are additional considerations for appendrels, which we'll
* deal with in set_append_rel_size and set_append_rel_pathlist.
* For now, just set consider_parallel based on the rel's own
* quals and targetlist.
*/
break;
case RTE_SUBQUERY:
/*
* There's no intrinsic problem with scanning a subquery-in-FROM
* (as distinct from a SubPlan or InitPlan) in a parallel worker.
* If the subquery doesn't happen to have any parallel-safe paths,
* then flagging it as consider_parallel won't change anything,
* but that's true for plain tables, too. We must set
* consider_parallel based on the rel's own quals and targetlist,
* so that if a subquery path is parallel-safe but the quals and
* projection we're sticking onto it are not, we correctly mark
* the SubqueryScanPath as not parallel-safe. (Note that
* set_subquery_pathlist() might push some of these quals down
* into the subquery itself, but that doesn't change anything.)
*
* We can't push sub-select containing LIMIT/OFFSET to workers as
* there is no guarantee that the row order will be fully
* deterministic, and applying LIMIT/OFFSET will lead to
* inconsistent results at the top-level. (In some cases, where
* the result is ordered, we could relax this restriction. But it
* doesn't currently seem worth expending extra effort to do so.)
*/
{
Query *subquery = castNode(Query, rte->subquery);
if (limit_needed(subquery))
return;
}
break;
case RTE_JOIN:
/* Shouldn't happen; we're only considering baserels here. */
Assert(false);
return;
case RTE_FUNCTION:
/* Check for parallel-restricted functions. */
if (!is_parallel_safe(root, (Node *) rte->functions))
return;
break;
case RTE_TABLEFUNC:
/* not parallel safe */
return;
case RTE_VALUES:
/* Check for parallel-restricted functions. */
if (!is_parallel_safe(root, (Node *) rte->values_lists))
return;
break;
case RTE_CTE:
/*
* CTE tuplestores aren't shared among parallel workers, so we
* force all CTE scans to happen in the leader. Also, populating
* the CTE would require executing a subplan that's not available
* in the worker, might be parallel-restricted, and must get
* executed only once.
*/
return;
case RTE_NAMEDTUPLESTORE:
/*
* tuplestore cannot be shared, at least without more
* infrastructure to support that.
*/
return;
case RTE_RESULT:
/* RESULT RTEs, in themselves, are no problem. */
break;
}
/*
* If there's anything in baserestrictinfo that's parallel-restricted, we
* give up on parallelizing access to this relation. We could consider
* instead postponing application of the restricted quals until we're
* above all the parallelism in the plan tree, but it's not clear that
* that would be a win in very many cases, and it might be tricky to make
* outer join clauses work correctly. It would likely break equivalence
* classes, too.
*/
if (!is_parallel_safe(root, (Node *) rel->baserestrictinfo))
return;
/*
* Likewise, if the relation's outputs are not parallel-safe, give up.
* (Usually, they're just Vars, but sometimes they're not.)
*/
if (!is_parallel_safe(root, (Node *) rel->reltarget->exprs))
return;
/* We have a winner. */
rel->consider_parallel = true;
}
/*
* set_plain_rel_pathlist
* Build access paths for a plain relation (no subquery, no inheritance)
*/
static void
set_plain_rel_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
Relids required_outer;
/*
* We don't support pushing join clauses into the quals of a seqscan, but
* it could still have required parameterization due to LATERAL refs in
* its tlist.
*/
required_outer = rel->lateral_relids;
/* Consider sequential scan */
add_path(rel, create_seqscan_path(root, rel, required_outer, 0));
/* If appropriate, consider parallel sequential scan */
if (rel->consider_parallel && required_outer == NULL)
create_plain_partial_paths(root, rel);
/* Consider index scans */
create_index_paths(root, rel);
/* Consider TID scans */
create_tidscan_paths(root, rel);
}
/*
* create_plain_partial_paths
* Build partial access paths for parallel scan of a plain relation
*/
static void
create_plain_partial_paths(PlannerInfo *root, RelOptInfo *rel)
{
int parallel_workers;
parallel_workers = compute_parallel_worker(rel, rel->pages, -1,
max_parallel_workers_per_gather);
/* If any limit was set to zero, the user doesn't want a parallel scan. */
if (parallel_workers <= 0)
return;
/* Add an unordered partial path based on a parallel sequential scan. */
add_partial_path(rel, create_seqscan_path(root, rel, NULL, parallel_workers));
}
/*
* set_tablesample_rel_size
* Set size estimates for a sampled relation
*/
static void
set_tablesample_rel_size(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
TableSampleClause *tsc = rte->tablesample;
TsmRoutine *tsm;
BlockNumber pages;
double tuples;
/*
* Test any partial indexes of rel for applicability. We must do this
* first since partial unique indexes can affect size estimates.
*/
check_index_predicates(root, rel);
/*
* Call the sampling method's estimation function to estimate the number
* of pages it will read and the number of tuples it will return. (Note:
* we assume the function returns sane values.)
*/
tsm = GetTsmRoutine(tsc->tsmhandler);
tsm->SampleScanGetSampleSize(root, rel, tsc->args,
&pages, &tuples);
/*
* For the moment, because we will only consider a SampleScan path for the
* rel, it's okay to just overwrite the pages and tuples estimates for the
* whole relation. If we ever consider multiple path types for sampled
* rels, we'll need more complication.
*/
rel->pages = pages;
rel->tuples = tuples;
/* Mark rel with estimated output rows, width, etc */
set_baserel_size_estimates(root, rel);
}
/*
* set_tablesample_rel_pathlist
* Build access paths for a sampled relation
*/
static void
set_tablesample_rel_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
Relids required_outer;
Path *path;
/*
* We don't support pushing join clauses into the quals of a samplescan,
* but it could still have required parameterization due to LATERAL refs
* in its tlist or TABLESAMPLE arguments.
*/
required_outer = rel->lateral_relids;
/* Consider sampled scan */
path = create_samplescan_path(root, rel, required_outer);
/*
* If the sampling method does not support repeatable scans, we must avoid
* plans that would scan the rel multiple times. Ideally, we'd simply
* avoid putting the rel on the inside of a nestloop join; but adding such
* a consideration to the planner seems like a great deal of complication
* to support an uncommon usage of second-rate sampling methods. Instead,
* if there is a risk that the query might perform an unsafe join, just
* wrap the SampleScan in a Materialize node. We can check for joins by
* counting the membership of all_baserels (note that this correctly
* counts inheritance trees as single rels). If we're inside a subquery,
* we can't easily check whether a join might occur in the outer query, so
* just assume one is possible.
*
* GetTsmRoutine is relatively expensive compared to the other tests here,
* so check repeatable_across_scans last, even though that's a bit odd.
*/
if ((root->query_level > 1 ||
bms_membership(root->all_baserels) != BMS_SINGLETON) &&
!(GetTsmRoutine(rte->tablesample->tsmhandler)->repeatable_across_scans))
{
path = (Path *) create_material_path(rel, path);
}
add_path(rel, path);
/* For the moment, at least, there are no other paths to consider */
}
/*
* set_foreign_size
* Set size estimates for a foreign table RTE
*/
static void
set_foreign_size(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
/* Mark rel with estimated output rows, width, etc */
set_foreign_size_estimates(root, rel);
/* Let FDW adjust the size estimates, if it can */
rel->fdwroutine->GetForeignRelSize(root, rel, rte->relid);
/* ... but do not let it set the rows estimate to zero */
rel->rows = clamp_row_est(rel->rows);
}
/*
* set_foreign_pathlist
* Build access paths for a foreign table RTE
*/
static void
set_foreign_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
/* Call the FDW's GetForeignPaths function to generate path(s) */
rel->fdwroutine->GetForeignPaths(root, rel, rte->relid);
}
/*
* set_append_rel_size
* Set size estimates for a simple "append relation"
*
* The passed-in rel and RTE represent the entire append relation. The
* relation's contents are computed by appending together the output of the
* individual member relations. Note that in the non-partitioned inheritance
* case, the first member relation is actually the same table as is mentioned
* in the parent RTE ... but it has a different RTE and RelOptInfo. This is
* a good thing because their outputs are not the same size.
*/
static void
set_append_rel_size(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte)
{
int parentRTindex = rti;
bool has_live_children;
double parent_rows;
double parent_size;
double *parent_attrsizes;
int nattrs;
ListCell *l;
/* Guard against stack overflow due to overly deep inheritance tree. */
check_stack_depth();
Assert(IS_SIMPLE_REL(rel));
/*
* Initialize partitioned_child_rels to contain this RT index.
*
* Note that during the set_append_rel_pathlist() phase, we will bubble up
* the indexes of partitioned relations that appear down in the tree, so
* that when we've created Paths for all the children, the root
* partitioned table's list will contain all such indexes.
*/
if (rte->relkind == RELKIND_PARTITIONED_TABLE)
rel->partitioned_child_rels = list_make1_int(rti);
/*
* If this is a partitioned baserel, set the consider_partitionwise_join
* flag; currently, we only consider partitionwise joins with the baserel
* if its targetlist doesn't contain a whole-row Var.
*/
if (enable_partitionwise_join &&
rel->reloptkind == RELOPT_BASEREL &&
rte->relkind == RELKIND_PARTITIONED_TABLE &&
rel->attr_needed[InvalidAttrNumber - rel->min_attr] == NULL)
rel->consider_partitionwise_join = true;
/*
* Initialize to compute size estimates for whole append relation.
*
* We handle width estimates by weighting the widths of different child
* rels proportionally to their number of rows. This is sensible because
* the use of width estimates is mainly to compute the total relation
* "footprint" if we have to sort or hash it. To do this, we sum the
* total equivalent size (in "double" arithmetic) and then divide by the
* total rowcount estimate. This is done separately for the total rel
* width and each attribute.
*
* Note: if you consider changing this logic, beware that child rels could
* have zero rows and/or width, if they were excluded by constraints.
*/
has_live_children = false;
parent_rows = 0;
parent_size = 0;
nattrs = rel->max_attr - rel->min_attr + 1;
parent_attrsizes = (double *) palloc0(nattrs * sizeof(double));
foreach(l, root->append_rel_list)
{
AppendRelInfo *appinfo = (AppendRelInfo *) lfirst(l);
int childRTindex;
RangeTblEntry *childRTE;
RelOptInfo *childrel;
ListCell *parentvars;
ListCell *childvars;
/* append_rel_list contains all append rels; ignore others */
if (appinfo->parent_relid != parentRTindex)
continue;
childRTindex = appinfo->child_relid;
childRTE = root->simple_rte_array[childRTindex];
/*
* The child rel's RelOptInfo was already created during
* add_other_rels_to_query.
*/
childrel = find_base_rel(root, childRTindex);
Assert(childrel->reloptkind == RELOPT_OTHER_MEMBER_REL);
/* We may have already proven the child to be dummy. */
if (IS_DUMMY_REL(childrel))
continue;
/*
* We have to copy the parent's targetlist and quals to the child,
* with appropriate substitution of variables. However, the
* baserestrictinfo quals were already copied/substituted when the
* child RelOptInfo was built. So we don't need any additional setup
* before applying constraint exclusion.
*/
if (relation_excluded_by_constraints(root, childrel, childRTE))
{
/*
* This child need not be scanned, so we can omit it from the
* appendrel.
*/
set_dummy_rel_pathlist(childrel);
continue;
}
/*
* Constraint exclusion failed, so copy the parent's join quals and
* targetlist to the child, with appropriate variable substitutions.
*
* NB: the resulting childrel->reltarget->exprs may contain arbitrary
* expressions, which otherwise would not occur in a rel's targetlist.
* Code that might be looking at an appendrel child must cope with
* such. (Normally, a rel's targetlist would only include Vars and
* PlaceHolderVars.) XXX we do not bother to update the cost or width
* fields of childrel->reltarget; not clear if that would be useful.
*/
childrel->joininfo = (List *)
adjust_appendrel_attrs(root,
(Node *) rel->joininfo,
1, &appinfo);
childrel->reltarget->exprs = (List *)
adjust_appendrel_attrs(root,
(Node *) rel->reltarget->exprs,
1, &appinfo);
/*
* We have to make child entries in the EquivalenceClass data
* structures as well. This is needed either if the parent
* participates in some eclass joins (because we will want to consider
* inner-indexscan joins on the individual children) or if the parent
* has useful pathkeys (because we should try to build MergeAppend
* paths that produce those sort orderings).
*/
if (rel->has_eclass_joins || has_useful_pathkeys(root, rel))
add_child_rel_equivalences(root, appinfo, rel, childrel);
childrel->has_eclass_joins = rel->has_eclass_joins;
/*
* Note: we could compute appropriate attr_needed data for the child's
* variables, by transforming the parent's attr_needed through the
* translated_vars mapping. However, currently there's no need
* because attr_needed is only examined for base relations not
* otherrels. So we just leave the child's attr_needed empty.
*/
/*
* If we consider partitionwise joins with the parent rel, do the same
* for partitioned child rels.
*
* Note: here we abuse the consider_partitionwise_join flag by setting
* it for child rels that are not themselves partitioned. We do so to
* tell try_partitionwise_join() that the child rel is sufficiently
* valid to be used as a per-partition input, even if it later gets
* proven to be dummy. (It's not usable until we've set up the
* reltarget and EC entries, which we just did.)
*/
if (rel->consider_partitionwise_join)
childrel->consider_partitionwise_join = true;
/*
* If parallelism is allowable for this query in general, see whether
* it's allowable for this childrel in particular. But if we've
* already decided the appendrel is not parallel-safe as a whole,
* there's no point in considering parallelism for this child. For
* consistency, do this before calling set_rel_size() for the child.
*/
if (root->glob->parallelModeOK && rel->consider_parallel)
set_rel_consider_parallel(root, childrel, childRTE);
/*
* Compute the child's size.
*/
set_rel_size(root, childrel, childRTindex, childRTE);
/*
* It is possible that constraint exclusion detected a contradiction
* within a child subquery, even though we didn't prove one above. If
* so, we can skip this child.
*/
if (IS_DUMMY_REL(childrel))
continue;
/* We have at least one live child. */
has_live_children = true;
/*
* If any live child is not parallel-safe, treat the whole appendrel
* as not parallel-safe. In future we might be able to generate plans
* in which some children are farmed out to workers while others are
* not; but we don't have that today, so it's a waste to consider
* partial paths anywhere in the appendrel unless it's all safe.
* (Child rels visited before this one will be unmarked in
* set_append_rel_pathlist().)
*/
if (!childrel->consider_parallel)
rel->consider_parallel = false;
/*
* Accumulate size information from each live child.
*/
Assert(childrel->rows > 0);
parent_rows += childrel->rows;
parent_size += childrel->reltarget->width * childrel->rows;
/*
* Accumulate per-column estimates too. We need not do anything for
* PlaceHolderVars in the parent list. If child expression isn't a
* Var, or we didn't record a width estimate for it, we have to fall
* back on a datatype-based estimate.
*
* By construction, child's targetlist is 1-to-1 with parent's.
*/
forboth(parentvars, rel->reltarget->exprs,
childvars, childrel->reltarget->exprs)
{
Var *parentvar = (Var *) lfirst(parentvars);
Node *childvar = (Node *) lfirst(childvars);
if (IsA(parentvar, Var))
{
int pndx = parentvar->varattno - rel->min_attr;
int32 child_width = 0;
if (IsA(childvar, Var) &&
((Var *) childvar)->varno == childrel->relid)
{
int cndx = ((Var *) childvar)->varattno - childrel->min_attr;
child_width = childrel->attr_widths[cndx];
}
if (child_width <= 0)
child_width = get_typavgwidth(exprType(childvar),
exprTypmod(childvar));
Assert(child_width > 0);
parent_attrsizes[pndx] += child_width * childrel->rows;
}
}
}
if (has_live_children)
{
/*
* Save the finished size estimates.
*/
int i;
Assert(parent_rows > 0);
rel->rows = parent_rows;
rel->reltarget->width = rint(parent_size / parent_rows);
for (i = 0; i < nattrs; i++)
rel->attr_widths[i] = rint(parent_attrsizes[i] / parent_rows);
/*
* Set "raw tuples" count equal to "rows" for the appendrel; needed
* because some places assume rel->tuples is valid for any baserel.
*/
rel->tuples = parent_rows;
/*
* Note that we leave rel->pages as zero; this is important to avoid
* double-counting the appendrel tree in total_table_pages.
*/
}
else
{
/*
* All children were excluded by constraints, so mark the whole
* appendrel dummy. We must do this in this phase so that the rel's
* dummy-ness is visible when we generate paths for other rels.
*/
set_dummy_rel_pathlist(rel);
}
pfree(parent_attrsizes);
}
/*
* set_append_rel_pathlist
* Build access paths for an "append relation"
*/
static void
set_append_rel_pathlist(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte)
{
int parentRTindex = rti;
List *live_childrels = NIL;
ListCell *l;
/*
* Generate access paths for each member relation, and remember the
* non-dummy children.
*/
foreach(l, root->append_rel_list)
{
AppendRelInfo *appinfo = (AppendRelInfo *) lfirst(l);
int childRTindex;
RangeTblEntry *childRTE;
RelOptInfo *childrel;
/* append_rel_list contains all append rels; ignore others */
if (appinfo->parent_relid != parentRTindex)
continue;
/* Re-locate the child RTE and RelOptInfo */
childRTindex = appinfo->child_relid;
childRTE = root->simple_rte_array[childRTindex];
childrel = root->simple_rel_array[childRTindex];
/*
* If set_append_rel_size() decided the parent appendrel was
* parallel-unsafe at some point after visiting this child rel, we
* need to propagate the unsafety marking down to the child, so that
* we don't generate useless partial paths for it.
*/
if (!rel->consider_parallel)
childrel->consider_parallel = false;
/*
* Compute the child's access paths.
*/
set_rel_pathlist(root, childrel, childRTindex, childRTE);
/*
* If child is dummy, ignore it.
*/
if (IS_DUMMY_REL(childrel))
continue;
/* Bubble up childrel's partitioned children. */
if (rel->part_scheme)
rel->partitioned_child_rels =
list_concat(rel->partitioned_child_rels,
childrel->partitioned_child_rels);
/*
* Child is live, so add it to the live_childrels list for use below.
*/
live_childrels = lappend(live_childrels, childrel);
}
/* Add paths to the append relation. */
add_paths_to_append_rel(root, rel, live_childrels);
}
/*
* add_paths_to_append_rel
* Generate paths for the given append relation given the set of non-dummy
* child rels.
*
* The function collects all parameterizations and orderings supported by the
* non-dummy children. For every such parameterization or ordering, it creates
* an append path collecting one path from each non-dummy child with given
* parameterization or ordering. Similarly it collects partial paths from
* non-dummy children to create partial append paths.
*/
void
add_paths_to_append_rel(PlannerInfo *root, RelOptInfo *rel,
List *live_childrels)
{
List *subpaths = NIL;
bool subpaths_valid = true;
List *partial_subpaths = NIL;
List *pa_partial_subpaths = NIL;
List *pa_nonpartial_subpaths = NIL;
bool partial_subpaths_valid = true;
bool pa_subpaths_valid;
List *all_child_pathkeys = NIL;
List *all_child_outers = NIL;
ListCell *l;
List *partitioned_rels = NIL;
double partial_rows = -1;
/* If appropriate, consider parallel append */
pa_subpaths_valid = enable_parallel_append && rel->consider_parallel;
/*
* AppendPath generated for partitioned tables must record the RT indexes
* of partitioned tables that are direct or indirect children of this
* Append rel.
*
* AppendPath may be for a sub-query RTE (UNION ALL), in which case, 'rel'
* itself does not represent a partitioned relation, but the child sub-
* queries may contain references to partitioned relations. The loop
* below will look for such children and collect them in a list to be
* passed to the path creation function. (This assumes that we don't need
* to look through multiple levels of subquery RTEs; if we ever do, we
* could consider stuffing the list we generate here into sub-query RTE's
* RelOptInfo, just like we do for partitioned rels, which would be used
* when populating our parent rel with paths. For the present, that
* appears to be unnecessary.)
*/
if (rel->part_scheme != NULL)
{
if (IS_SIMPLE_REL(rel))
partitioned_rels = list_make1(rel->partitioned_child_rels);
else if (IS_JOIN_REL(rel))
{
int relid = -1;
List *partrels = NIL;
/*
* For a partitioned joinrel, concatenate the component rels'
* partitioned_child_rels lists.
*/
while ((relid = bms_next_member(rel->relids, relid)) >= 0)
{
RelOptInfo *component;
Assert(relid >= 1 && relid < root->simple_rel_array_size);
component = root->simple_rel_array[relid];
Assert(component->part_scheme != NULL);
Assert(list_length(component->partitioned_child_rels) >= 1);
partrels = list_concat(partrels,
component->partitioned_child_rels);
}
partitioned_rels = list_make1(partrels);
}
Assert(list_length(partitioned_rels) >= 1);
}
/*
* For every non-dummy child, remember the cheapest path. Also, identify
* all pathkeys (orderings) and parameterizations (required_outer sets)
* available for the non-dummy member relations.
*/
foreach(l, live_childrels)
{
RelOptInfo *childrel = lfirst(l);
ListCell *lcp;
Path *cheapest_partial_path = NULL;
/*
* For UNION ALLs with non-empty partitioned_child_rels, accumulate
* the Lists of child relations.
*/
if (rel->rtekind == RTE_SUBQUERY && childrel->partitioned_child_rels != NIL)
partitioned_rels = lappend(partitioned_rels,
childrel->partitioned_child_rels);
/*
* If child has an unparameterized cheapest-total path, add that to
* the unparameterized Append path we are constructing for the parent.
* If not, there's no workable unparameterized path.
*
* With partitionwise aggregates, the child rel's pathlist may be
* empty, so don't assume that a path exists here.
*/
if (childrel->pathlist != NIL &&
childrel->cheapest_total_path->param_info == NULL)
accumulate_append_subpath(childrel->cheapest_total_path,
&subpaths, NULL);
else
subpaths_valid = false;
/* Same idea, but for a partial plan. */
if (childrel->partial_pathlist != NIL)
{
cheapest_partial_path = linitial(childrel->partial_pathlist);
accumulate_append_subpath(cheapest_partial_path,
&partial_subpaths, NULL);
}
else
partial_subpaths_valid = false;
/*
* Same idea, but for a parallel append mixing partial and non-partial
* paths.
*/
if (pa_subpaths_valid)
{
Path *nppath = NULL;
nppath =
get_cheapest_parallel_safe_total_inner(childrel->pathlist);
if (cheapest_partial_path == NULL && nppath == NULL)
{
/* Neither a partial nor a parallel-safe path? Forget it. */
pa_subpaths_valid = false;
}
else if (nppath == NULL ||
(cheapest_partial_path != NULL &&
cheapest_partial_path->total_cost < nppath->total_cost))
{
/* Partial path is cheaper or the only option. */
Assert(cheapest_partial_path != NULL);
accumulate_append_subpath(cheapest_partial_path,
&pa_partial_subpaths,
&pa_nonpartial_subpaths);
}
else
{
/*
* Either we've got only a non-partial path, or we think that
* a single backend can execute the best non-partial path
* faster than all the parallel backends working together can
* execute the best partial path.
*
* It might make sense to be more aggressive here. Even if
* the best non-partial path is more expensive than the best
* partial path, it could still be better to choose the
* non-partial path if there are several such paths that can
* be given to different workers. For now, we don't try to
* figure that out.
*/
accumulate_append_subpath(nppath,
&pa_nonpartial_subpaths,
NULL);
}
}
/*
* Collect lists of all the available path orderings and
* parameterizations for all the children. We use these as a
* heuristic to indicate which sort orderings and parameterizations we
* should build Append and MergeAppend paths for.
*/
foreach(lcp, childrel->pathlist)
{
Path *childpath = (Path *) lfirst(lcp);
List *childkeys = childpath->pathkeys;
Relids childouter = PATH_REQ_OUTER(childpath);
/* Unsorted paths don't contribute to pathkey list */
if (childkeys != NIL)
{
ListCell *lpk;
bool found = false;
/* Have we already seen this ordering? */
foreach(lpk, all_child_pathkeys)
{
List *existing_pathkeys = (List *) lfirst(lpk);
if (compare_pathkeys(existing_pathkeys,
childkeys) == PATHKEYS_EQUAL)
{
found = true;
break;
}
}
if (!found)
{
/* No, so add it to all_child_pathkeys */
all_child_pathkeys = lappend(all_child_pathkeys,
childkeys);
}
}
/* Unparameterized paths don't contribute to param-set list */
if (childouter)
{
ListCell *lco;
bool found = false;
/* Have we already seen this param set? */
foreach(lco, all_child_outers)
{
Relids existing_outers = (Relids) lfirst(lco);
if (bms_equal(existing_outers, childouter))
{
found = true;
break;
}
}
if (!found)
{
/* No, so add it to all_child_outers */
all_child_outers = lappend(all_child_outers,
childouter);
}
}
}
}
/*
* If we found unparameterized paths for all children, build an unordered,
* unparameterized Append path for the rel. (Note: this is correct even
* if we have zero or one live subpath due to constraint exclusion.)
*/
if (subpaths_valid)
add_path(rel, (Path *) create_append_path(root, rel, subpaths, NIL,
NIL, NULL, 0, false,
partitioned_rels, -1));
/*
* Consider an append of unordered, unparameterized partial paths. Make
* it parallel-aware if possible.
*/
if (partial_subpaths_valid && partial_subpaths != NIL)
{
AppendPath *appendpath;
ListCell *lc;
int parallel_workers = 0;
/* Find the highest number of workers requested for any subpath. */
foreach(lc, partial_subpaths)
{
Path *path = lfirst(lc);
parallel_workers = Max(parallel_workers, path->parallel_workers);
}
Assert(parallel_workers > 0);
/*
* If the use of parallel append is permitted, always request at least
* log2(# of children) workers. We assume it can be useful to have
* extra workers in this case because they will be spread out across
* the children. The precise formula is just a guess, but we don't
* want to end up with a radically different answer for a table with N
* partitions vs. an unpartitioned table with the same data, so the
* use of some kind of log-scaling here seems to make some sense.
*/
if (enable_parallel_append)
{
parallel_workers = Max(parallel_workers,
fls(list_length(live_childrels)));
parallel_workers = Min(parallel_workers,
max_parallel_workers_per_gather);
}
Assert(parallel_workers > 0);
/* Generate a partial append path. */
appendpath = create_append_path(root, rel, NIL, partial_subpaths,
NIL, NULL, parallel_workers,
enable_parallel_append,
partitioned_rels, -1);
/*
* Make sure any subsequent partial paths use the same row count
* estimate.
*/
partial_rows = appendpath->path.rows;
/* Add the path. */
add_partial_path(rel, (Path *) appendpath);
}
/*
* Consider a parallel-aware append using a mix of partial and non-partial
* paths. (This only makes sense if there's at least one child which has
* a non-partial path that is substantially cheaper than any partial path;
* otherwise, we should use the append path added in the previous step.)
*/
if (pa_subpaths_valid && pa_nonpartial_subpaths != NIL)
{
AppendPath *appendpath;
ListCell *lc;
int parallel_workers = 0;
/*
* Find the highest number of workers requested for any partial
* subpath.
*/
foreach(lc, pa_partial_subpaths)
{
Path *path = lfirst(lc);
parallel_workers = Max(parallel_workers, path->parallel_workers);
}
/*
* Same formula here as above. It's even more important in this
* instance because the non-partial paths won't contribute anything to
* the planned number of parallel workers.
*/
parallel_workers = Max(parallel_workers,
fls(list_length(live_childrels)));
parallel_workers = Min(parallel_workers,
max_parallel_workers_per_gather);
Assert(parallel_workers > 0);
appendpath = create_append_path(root, rel, pa_nonpartial_subpaths,
pa_partial_subpaths,
NIL, NULL, parallel_workers, true,
partitioned_rels, partial_rows);
add_partial_path(rel, (Path *) appendpath);
}
/*
* Also build unparameterized ordered append paths based on the collected
* list of child pathkeys.
*/
if (subpaths_valid)
generate_orderedappend_paths(root, rel, live_childrels,
all_child_pathkeys,
partitioned_rels);
/*
* Build Append paths for each parameterization seen among the child rels.
* (This may look pretty expensive, but in most cases of practical
* interest, the child rels will expose mostly the same parameterizations,
* so that not that many cases actually get considered here.)
*
* The Append node itself cannot enforce quals, so all qual checking must
* be done in the child paths. This means that to have a parameterized
* Append path, we must have the exact same parameterization for each
* child path; otherwise some children might be failing to check the
* moved-down quals. To make them match up, we can try to increase the
* parameterization of lesser-parameterized paths.
*/
foreach(l, all_child_outers)
{
Relids required_outer = (Relids) lfirst(l);
ListCell *lcr;
/* Select the child paths for an Append with this parameterization */
subpaths = NIL;
subpaths_valid = true;
foreach(lcr, live_childrels)
{
RelOptInfo *childrel = (RelOptInfo *) lfirst(lcr);
Path *subpath;
if (childrel->pathlist == NIL)
{
/* failed to make a suitable path for this child */
subpaths_valid = false;
break;
}
subpath = get_cheapest_parameterized_child_path(root,
childrel,
required_outer);
if (subpath == NULL)
{
/* failed to make a suitable path for this child */
subpaths_valid = false;
break;
}
accumulate_append_subpath(subpath, &subpaths, NULL);
}
if (subpaths_valid)
add_path(rel, (Path *)
create_append_path(root, rel, subpaths, NIL,
NIL, required_outer, 0, false,
partitioned_rels, -1));
}
/*
* When there is only a single child relation, the Append path can inherit
* any ordering available for the child rel's path, so that it's useful to
* consider ordered partial paths. Above we only considered the cheapest
* partial path for each child, but let's also make paths using any
* partial paths that have pathkeys.
*/
if (list_length(live_childrels) == 1)
{
RelOptInfo *childrel = (RelOptInfo *) linitial(live_childrels);
foreach(l, childrel->partial_pathlist)
{
Path *path = (Path *) lfirst(l);
AppendPath *appendpath;
/*
* Skip paths with no pathkeys. Also skip the cheapest partial
* path, since we already used that above.
*/
if (path->pathkeys == NIL ||
path == linitial(childrel->partial_pathlist))
continue;
appendpath = create_append_path(root, rel, NIL, list_make1(path),
NIL, NULL,
path->parallel_workers, true,
partitioned_rels, partial_rows);
add_partial_path(rel, (Path *) appendpath);
}
}
}
/*
* generate_orderedappend_paths
* Generate ordered append paths for an append relation
*
* Usually we generate MergeAppend paths here, but there are some special
* cases where we can generate simple Append paths, because the subpaths
* can provide tuples in the required order already.
*
* We generate a path for each ordering (pathkey list) appearing in
* all_child_pathkeys.
*
* We consider both cheapest-startup and cheapest-total cases, ie, for each
* interesting ordering, collect all the cheapest startup subpaths and all the
* cheapest total paths, and build a suitable path for each case.
*
* We don't currently generate any parameterized ordered paths here. While
* it would not take much more code here to do so, it's very unclear that it
* is worth the planning cycles to investigate such paths: there's little
* use for an ordered path on the inside of a nestloop. In fact, it's likely
* that the current coding of add_path would reject such paths out of hand,
* because add_path gives no credit for sort ordering of parameterized paths,
* and a parameterized MergeAppend is going to be more expensive than the
* corresponding parameterized Append path. If we ever try harder to support
* parameterized mergejoin plans, it might be worth adding support for
* parameterized paths here to feed such joins. (See notes in
* optimizer/README for why that might not ever happen, though.)
*/
static void
generate_orderedappend_paths(PlannerInfo *root, RelOptInfo *rel,
List *live_childrels,
List *all_child_pathkeys,
List *partitioned_rels)
{
ListCell *lcp;
List *partition_pathkeys = NIL;
List *partition_pathkeys_desc = NIL;
bool partition_pathkeys_partial = true;
bool partition_pathkeys_desc_partial = true;
/*
* Some partitioned table setups may allow us to use an Append node
* instead of a MergeAppend. This is possible in cases such as RANGE
* partitioned tables where it's guaranteed that an earlier partition must
* contain rows which come earlier in the sort order. To detect whether
* this is relevant, build pathkey descriptions of the partition ordering,
* for both forward and reverse scans.
*/
if (rel->part_scheme != NULL && IS_SIMPLE_REL(rel) &&
partitions_are_ordered(rel->boundinfo, rel->nparts))
{
partition_pathkeys = build_partition_pathkeys(root, rel,
ForwardScanDirection,
&partition_pathkeys_partial);
partition_pathkeys_desc = build_partition_pathkeys(root, rel,
BackwardScanDirection,
&partition_pathkeys_desc_partial);
/*
* You might think we should truncate_useless_pathkeys here, but
* allowing partition keys which are a subset of the query's pathkeys
* can often be useful. For example, consider a table partitioned by
* RANGE (a, b), and a query with ORDER BY a, b, c. If we have child
* paths that can produce the a, b, c ordering (perhaps via indexes on
* (a, b, c)) then it works to consider the appendrel output as
* ordered by a, b, c.
*/
}
/* Now consider each interesting sort ordering */
foreach(lcp, all_child_pathkeys)
{
List *pathkeys = (List *) lfirst(lcp);
List *startup_subpaths = NIL;
List *total_subpaths = NIL;
bool startup_neq_total = false;
ListCell *lcr;
bool match_partition_order;
bool match_partition_order_desc;
/*
* Determine if this sort ordering matches any partition pathkeys we
* have, for both ascending and descending partition order. If the
* partition pathkeys happen to be contained in pathkeys then it still
* works, as described above, providing that the partition pathkeys
* are complete and not just a prefix of the partition keys. (In such
* cases we'll be relying on the child paths to have sorted the
* lower-order columns of the required pathkeys.)
*/
match_partition_order =
pathkeys_contained_in(pathkeys, partition_pathkeys) ||
(!partition_pathkeys_partial &&
pathkeys_contained_in(partition_pathkeys, pathkeys));
match_partition_order_desc = !match_partition_order &&
(pathkeys_contained_in(pathkeys, partition_pathkeys_desc) ||
(!partition_pathkeys_desc_partial &&
pathkeys_contained_in(partition_pathkeys_desc, pathkeys)));
/* Select the child paths for this ordering... */
foreach(lcr, live_childrels)
{
RelOptInfo *childrel = (RelOptInfo *) lfirst(lcr);
Path *cheapest_startup,
*cheapest_total;
/* Locate the right paths, if they are available. */
cheapest_startup =
get_cheapest_path_for_pathkeys(childrel->pathlist,
pathkeys,
NULL,
STARTUP_COST,
false);
cheapest_total =
get_cheapest_path_for_pathkeys(childrel->pathlist,
pathkeys,
NULL,
TOTAL_COST,
false);
/*
* If we can't find any paths with the right order just use the
* cheapest-total path; we'll have to sort it later.
*/
if (cheapest_startup == NULL || cheapest_total == NULL)
{
cheapest_startup = cheapest_total =
childrel->cheapest_total_path;
/* Assert we do have an unparameterized path for this child */
Assert(cheapest_total->param_info == NULL);
}
/*
* Notice whether we actually have different paths for the
* "cheapest" and "total" cases; frequently there will be no point
* in two create_merge_append_path() calls.
*/
if (cheapest_startup != cheapest_total)
startup_neq_total = true;
/*
* Collect the appropriate child paths. The required logic varies
* for the Append and MergeAppend cases.
*/
if (match_partition_order)
{
/*
* We're going to make a plain Append path. We don't need
* most of what accumulate_append_subpath would do, but we do
* want to cut out child Appends or MergeAppends if they have
* just a single subpath (and hence aren't doing anything
* useful).
*/
cheapest_startup = get_singleton_append_subpath(cheapest_startup);
cheapest_total = get_singleton_append_subpath(cheapest_total);
startup_subpaths = lappend(startup_subpaths, cheapest_startup);
total_subpaths = lappend(total_subpaths, cheapest_total);
}
else if (match_partition_order_desc)
{
/*
* As above, but we need to reverse the order of the children,
* because nodeAppend.c doesn't know anything about reverse
* ordering and will scan the children in the order presented.
*/
cheapest_startup = get_singleton_append_subpath(cheapest_startup);
cheapest_total = get_singleton_append_subpath(cheapest_total);
startup_subpaths = lcons(cheapest_startup, startup_subpaths);
total_subpaths = lcons(cheapest_total, total_subpaths);
}
else
{
/*
* Otherwise, rely on accumulate_append_subpath to collect the
* child paths for the MergeAppend.
*/
accumulate_append_subpath(cheapest_startup,
&startup_subpaths, NULL);
accumulate_append_subpath(cheapest_total,
&total_subpaths, NULL);
}
}
/* ... and build the Append or MergeAppend paths */
if (match_partition_order || match_partition_order_desc)
{
/* We only need Append */
add_path(rel, (Path *) create_append_path(root,
rel,
startup_subpaths,
NIL,
pathkeys,
NULL,
0,
false,
partitioned_rels,
-1));
if (startup_neq_total)
add_path(rel, (Path *) create_append_path(root,
rel,
total_subpaths,
NIL,
pathkeys,
NULL,
0,
false,
partitioned_rels,
-1));
}
else
{
/* We need MergeAppend */
add_path(rel, (Path *) create_merge_append_path(root,
rel,
startup_subpaths,
pathkeys,
NULL,
partitioned_rels));
if (startup_neq_total)
add_path(rel, (Path *) create_merge_append_path(root,
rel,
total_subpaths,
pathkeys,
NULL,
partitioned_rels));
}
}
}
/*
* get_cheapest_parameterized_child_path
* Get cheapest path for this relation that has exactly the requested
* parameterization.
*
* Returns NULL if unable to create such a path.
*/
static Path *
get_cheapest_parameterized_child_path(PlannerInfo *root, RelOptInfo *rel,
Relids required_outer)
{
Path *cheapest;
ListCell *lc;
/*
* Look up the cheapest existing path with no more than the needed
* parameterization. If it has exactly the needed parameterization, we're
* done.
*/
cheapest = get_cheapest_path_for_pathkeys(rel->pathlist,
NIL,
required_outer,
TOTAL_COST,
false);
Assert(cheapest != NULL);
if (bms_equal(PATH_REQ_OUTER(cheapest), required_outer))
return cheapest;
/*
* Otherwise, we can "reparameterize" an existing path to match the given
* parameterization, which effectively means pushing down additional
* joinquals to be checked within the path's scan. However, some existing
* paths might check the available joinquals already while others don't;
* therefore, it's not clear which existing path will be cheapest after
* reparameterization. We have to go through them all and find out.
*/
cheapest = NULL;
foreach(lc, rel->pathlist)
{
Path *path = (Path *) lfirst(lc);
/* Can't use it if it needs more than requested parameterization */
if (!bms_is_subset(PATH_REQ_OUTER(path), required_outer))
continue;
/*
* Reparameterization can only increase the path's cost, so if it's
* already more expensive than the current cheapest, forget it.
*/
if (cheapest != NULL &&
compare_path_costs(cheapest, path, TOTAL_COST) <= 0)
continue;
/* Reparameterize if needed, then recheck cost */
if (!bms_equal(PATH_REQ_OUTER(path), required_outer))
{
path = reparameterize_path(root, path, required_outer, 1.0);
if (path == NULL)
continue; /* failed to reparameterize this one */
Assert(bms_equal(PATH_REQ_OUTER(path), required_outer));
if (cheapest != NULL &&
compare_path_costs(cheapest, path, TOTAL_COST) <= 0)
continue;
}
/* We have a new best path */
cheapest = path;
}
/* Return the best path, or NULL if we found no suitable candidate */
return cheapest;
}
/*
* accumulate_append_subpath
* Add a subpath to the list being built for an Append or MergeAppend.
*
* It's possible that the child is itself an Append or MergeAppend path, in
* which case we can "cut out the middleman" and just add its child paths to
* our own list. (We don't try to do this earlier because we need to apply
* both levels of transformation to the quals.)
*
* Note that if we omit a child MergeAppend in this way, we are effectively
* omitting a sort step, which seems fine: if the parent is to be an Append,
* its result would be unsorted anyway, while if the parent is to be a
* MergeAppend, there's no point in a separate sort on a child.
*
* Normally, either path is a partial path and subpaths is a list of partial
* paths, or else path is a non-partial plan and subpaths is a list of those.
* However, if path is a parallel-aware Append, then we add its partial path
* children to subpaths and the rest to special_subpaths. If the latter is
* NULL, we don't flatten the path at all (unless it contains only partial
* paths).
*/
static void
accumulate_append_subpath(Path *path, List **subpaths, List **special_subpaths)
{
if (IsA(path, AppendPath))
{
AppendPath *apath = (AppendPath *) path;
if (!apath->path.parallel_aware || apath->first_partial_path == 0)
{
*subpaths = list_concat(*subpaths, apath->subpaths);
return;
}
else if (special_subpaths != NULL)
{
List *new_special_subpaths;
/* Split Parallel Append into partial and non-partial subpaths */
*subpaths = list_concat(*subpaths,
list_copy_tail(apath->subpaths,
apath->first_partial_path));
new_special_subpaths =
list_truncate(list_copy(apath->subpaths),
apath->first_partial_path);
*special_subpaths = list_concat(*special_subpaths,
new_special_subpaths);
return;
}
}
else if (IsA(path, MergeAppendPath))
{
MergeAppendPath *mpath = (MergeAppendPath *) path;
*subpaths = list_concat(*subpaths, mpath->subpaths);
return;
}
*subpaths = lappend(*subpaths, path);
}
/*
* get_singleton_append_subpath
* Returns the single subpath of an Append/MergeAppend, or just
* return 'path' if it's not a single sub-path Append/MergeAppend.
*
* Note: 'path' must not be a parallel-aware path.
*/
static Path *
get_singleton_append_subpath(Path *path)
{
Assert(!path->parallel_aware);
if (IsA(path, AppendPath))
{
AppendPath *apath = (AppendPath *) path;
if (list_length(apath->subpaths) == 1)
return (Path *) linitial(apath->subpaths);
}
else if (IsA(path, MergeAppendPath))
{
MergeAppendPath *mpath = (MergeAppendPath *) path;
if (list_length(mpath->subpaths) == 1)
return (Path *) linitial(mpath->subpaths);
}
return path;
}
/*
* set_dummy_rel_pathlist
* Build a dummy path for a relation that's been excluded by constraints
*
* Rather than inventing a special "dummy" path type, we represent this as an
* AppendPath with no members (see also IS_DUMMY_APPEND/IS_DUMMY_REL macros).
*
* (See also mark_dummy_rel, which does basically the same thing, but is
* typically used to change a rel into dummy state after we already made
* paths for it.)
*/
static void
set_dummy_rel_pathlist(RelOptInfo *rel)
{
/* Set dummy size estimates --- we leave attr_widths[] as zeroes */
rel->rows = 0;
rel->reltarget->width = 0;
/* Discard any pre-existing paths; no further need for them */
rel->pathlist = NIL;
rel->partial_pathlist = NIL;
/* Set up the dummy path */
add_path(rel, (Path *) create_append_path(NULL, rel, NIL, NIL,
NIL, rel->lateral_relids,
0, false, NIL, -1));
/*
* We set the cheapest-path fields immediately, just in case they were
* pointing at some discarded path. This is redundant when we're called
* from set_rel_size(), but not when called from elsewhere, and doing it
* twice is harmless anyway.
*/
set_cheapest(rel);
}
/* quick-and-dirty test to see if any joining is needed */
static bool
has_multiple_baserels(PlannerInfo *root)
{
int num_base_rels = 0;
Index rti;
for (rti = 1; rti < root->simple_rel_array_size; rti++)
{
RelOptInfo *brel = root->simple_rel_array[rti];
if (brel == NULL)
continue;
/* ignore RTEs that are "other rels" */
if (brel->reloptkind == RELOPT_BASEREL)
if (++num_base_rels > 1)
return true;
}
return false;
}
/*
* set_subquery_pathlist
* Generate SubqueryScan access paths for a subquery RTE
*
* We don't currently support generating parameterized paths for subqueries
* by pushing join clauses down into them; it seems too expensive to re-plan
* the subquery multiple times to consider different alternatives.
* (XXX that could stand to be reconsidered, now that we use Paths.)
* So the paths made here will be parameterized if the subquery contains
* LATERAL references, otherwise not. As long as that's true, there's no need
* for a separate set_subquery_size phase: just make the paths right away.
*/
static void
set_subquery_pathlist(PlannerInfo *root, RelOptInfo *rel,
Index rti, RangeTblEntry *rte)
{
Query *parse = root->parse;
Query *subquery = rte->subquery;
Relids required_outer;
pushdown_safety_info safetyInfo;
double tuple_fraction;
RelOptInfo *sub_final_rel;
ListCell *lc;
/*
* Must copy the Query so that planning doesn't mess up the RTE contents
* (really really need to fix the planner to not scribble on its input,
* someday ... but see remove_unused_subquery_outputs to start with).
*/
subquery = copyObject(subquery);
/*
* If it's a LATERAL subquery, it might contain some Vars of the current
* query level, requiring it to be treated as parameterized, even though
* we don't support pushing down join quals into subqueries.
*/
required_outer = rel->lateral_relids;
/*
* Zero out result area for subquery_is_pushdown_safe, so that it can set
* flags as needed while recursing. In particular, we need a workspace
* for keeping track of unsafe-to-reference columns. unsafeColumns[i]
* will be set true if we find that output column i of the subquery is
* unsafe to use in a pushed-down qual.
*/
memset(&safetyInfo, 0, sizeof(safetyInfo));
safetyInfo.unsafeColumns = (bool *)
palloc0((list_length(subquery->targetList) + 1) * sizeof(bool));
/*
* If the subquery has the "security_barrier" flag, it means the subquery
* originated from a view that must enforce row level security. Then we
* must not push down quals that contain leaky functions. (Ideally this
* would be checked inside subquery_is_pushdown_safe, but since we don't
* currently pass the RTE to that function, we must do it here.)
*/
safetyInfo.unsafeLeaky = rte->security_barrier;
/*
* If there are any restriction clauses that have been attached to the
* subquery relation, consider pushing them down to become WHERE or HAVING
* quals of the subquery itself. This transformation is useful because it
* may allow us to generate a better plan for the subquery than evaluating
* all the subquery output rows and then filtering them.
*
* There are several cases where we cannot push down clauses. Restrictions
* involving the subquery are checked by subquery_is_pushdown_safe().
* Restrictions on individual clauses are checked by
* qual_is_pushdown_safe(). Also, we don't want to push down
* pseudoconstant clauses; better to have the gating node above the
* subquery.
*
* Non-pushed-down clauses will get evaluated as qpquals of the
* SubqueryScan node.
*
* XXX Are there any cases where we want to make a policy decision not to
* push down a pushable qual, because it'd result in a worse plan?
*/
if (rel->baserestrictinfo != NIL &&
subquery_is_pushdown_safe(subquery, subquery, &safetyInfo))
{
/* OK to consider pushing down individual quals */
List *upperrestrictlist = NIL;
ListCell *l;
foreach(l, rel->baserestrictinfo)
{
RestrictInfo *rinfo = (RestrictInfo *) lfirst(l);
Node *clause = (Node *) rinfo->clause;
if (!rinfo->pseudoconstant &&
qual_is_pushdown_safe(subquery, rti, clause, &safetyInfo))
{
/* Push it down */
subquery_push_qual(subquery, rte, rti, clause);
}
else
{
/* Keep it in the upper query */
upperrestrictlist = lappend(upperrestrictlist, rinfo);
}
}
rel->baserestrictinfo = upperrestrictlist;
/* We don't bother recomputing baserestrict_min_security */
}
pfree(safetyInfo.unsafeColumns);
/*
* The upper query might not use all the subquery's output columns; if
* not, we can simplify.
*/
remove_unused_subquery_outputs(subquery, rel);
/*
* We can safely pass the outer tuple_fraction down to the subquery if the
* outer level has no joining, aggregation, or sorting to do. Otherwise
* we'd better tell the subquery to plan for full retrieval. (XXX This
* could probably be made more intelligent ...)
*/
if (parse->hasAggs ||
parse->groupClause ||
parse->groupingSets ||
parse->havingQual ||
parse->distinctClause ||
parse->sortClause ||
has_multiple_baserels(root))
tuple_fraction = 0.0; /* default case */
else
tuple_fraction = root->tuple_fraction;
/* plan_params should not be in use in current query level */
Assert(root->plan_params == NIL);
/* Generate a subroot and Paths for the subquery */
rel->subroot = subquery_planner(root->glob, subquery,
root,
false, tuple_fraction);
/* Isolate the params needed by this specific subplan */
rel->subplan_params = root->plan_params;
root->plan_params = NIL;
/*
* It's possible that constraint exclusion proved the subquery empty. If
* so, it's desirable to produce an unadorned dummy path so that we will
* recognize appropriate optimizations at this query level.
*/
sub_final_rel = fetch_upper_rel(rel->subroot, UPPERREL_FINAL, NULL);
if (IS_DUMMY_REL(sub_final_rel))
{
set_dummy_rel_pathlist(rel);
return;
}
/*
* Mark rel with estimated output rows, width, etc. Note that we have to
* do this before generating outer-query paths, else cost_subqueryscan is
* not happy.
*/
set_subquery_size_estimates(root, rel);
/*
* For each Path that subquery_planner produced, make a SubqueryScanPath
* in the outer query.
*/
foreach(lc, sub_final_rel->pathlist)
{
Path *subpath = (Path *) lfirst(lc);
List *pathkeys;
/* Convert subpath's pathkeys to outer representation */
pathkeys = convert_subquery_pathkeys(root,
rel,
subpath->pathkeys,
make_tlist_from_pathtarget(subpath->pathtarget));
/* Generate outer path using this subpath */
add_path(rel, (Path *)
create_subqueryscan_path(root, rel, subpath,
pathkeys, required_outer));
}
/* If outer rel allows parallelism, do same for partial paths. */
if (rel->consider_parallel && bms_is_empty(required_outer))
{
/* If consider_parallel is false, there should be no partial paths. */
Assert(sub_final_rel->consider_parallel ||
sub_final_rel->partial_pathlist == NIL);
/* Same for partial paths. */
foreach(lc, sub_final_rel->partial_pathlist)
{
Path *subpath = (Path *) lfirst(lc);
List *pathkeys;
/* Convert subpath's pathkeys to outer representation */
pathkeys = convert_subquery_pathkeys(root,
rel,
subpath->pathkeys,
make_tlist_from_pathtarget(subpath->pathtarget));
/* Generate outer path using this subpath */
add_partial_path(rel, (Path *)
create_subqueryscan_path(root, rel, subpath,
pathkeys,
required_outer));
}
}
}
/*
* set_function_pathlist
* Build the (single) access path for a function RTE
*/
static void
set_function_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
Relids required_outer;
List *pathkeys = NIL;
/*
* We don't support pushing join clauses into the quals of a function
* scan, but it could still have required parameterization due to LATERAL
* refs in the function expression.
*/
required_outer = rel->lateral_relids;
/*
* The result is considered unordered unless ORDINALITY was used, in which
* case it is ordered by the ordinal column (the last one). See if we
* care, by checking for uses of that Var in equivalence classes.
*/
if (rte->funcordinality)
{
AttrNumber ordattno = rel->max_attr;
Var *var = NULL;
ListCell *lc;
/*
* Is there a Var for it in rel's targetlist? If not, the query did
* not reference the ordinality column, or at least not in any way
* that would be interesting for sorting.
*/
foreach(lc, rel->reltarget->exprs)
{
Var *node = (Var *) lfirst(lc);
/* checking varno/varlevelsup is just paranoia */
if (IsA(node, Var) &&
node->varattno == ordattno &&
node->varno == rel->relid &&
node->varlevelsup == 0)
{
var = node;
break;
}
}
/*
* Try to build pathkeys for this Var with int8 sorting. We tell
* build_expression_pathkey not to build any new equivalence class; if
* the Var isn't already mentioned in some EC, it means that nothing
* cares about the ordering.
*/
if (var)
pathkeys = build_expression_pathkey(root,
(Expr *) var,
NULL, /* below outer joins */
Int8LessOperator,
rel->relids,
false);
}
/* Generate appropriate path */
add_path(rel, create_functionscan_path(root, rel,
pathkeys, required_outer));
}
/*
* set_values_pathlist
* Build the (single) access path for a VALUES RTE
*/
static void
set_values_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
Relids required_outer;
/*
* We don't support pushing join clauses into the quals of a values scan,
* but it could still have required parameterization due to LATERAL refs
* in the values expressions.
*/
required_outer = rel->lateral_relids;
/* Generate appropriate path */
add_path(rel, create_valuesscan_path(root, rel, required_outer));
}
/*
* set_tablefunc_pathlist
* Build the (single) access path for a table func RTE
*/
static void
set_tablefunc_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
Relids required_outer;
/*
* We don't support pushing join clauses into the quals of a tablefunc
* scan, but it could still have required parameterization due to LATERAL
* refs in the function expression.
*/
required_outer = rel->lateral_relids;
/* Generate appropriate path */
add_path(rel, create_tablefuncscan_path(root, rel,
required_outer));
}
/*
* set_cte_pathlist
* Build the (single) access path for a non-self-reference CTE RTE
*
* There's no need for a separate set_cte_size phase, since we don't
* support join-qual-parameterized paths for CTEs.
*/
static void
set_cte_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
Plan *cteplan;
PlannerInfo *cteroot;
Index levelsup;
int ndx;
ListCell *lc;
int plan_id;
Relids required_outer;
/*
* Find the referenced CTE, and locate the plan previously made for it.
*/
levelsup = rte->ctelevelsup;
cteroot = root;
while (levelsup-- > 0)
{
cteroot = cteroot->parent_root;
if (!cteroot) /* shouldn't happen */
elog(ERROR, "bad levelsup for CTE \"%s\"", rte->ctename);
}
/*
* Note: cte_plan_ids can be shorter than cteList, if we are still working
* on planning the CTEs (ie, this is a side-reference from another CTE).
* So we mustn't use forboth here.
*/
ndx = 0;
foreach(lc, cteroot->parse->cteList)
{
CommonTableExpr *cte = (CommonTableExpr *) lfirst(lc);
if (strcmp(cte->ctename, rte->ctename) == 0)
break;
ndx++;
}
if (lc == NULL) /* shouldn't happen */
elog(ERROR, "could not find CTE \"%s\"", rte->ctename);
if (ndx >= list_length(cteroot->cte_plan_ids))
elog(ERROR, "could not find plan for CTE \"%s\"", rte->ctename);
plan_id = list_nth_int(cteroot->cte_plan_ids, ndx);
Assert(plan_id > 0);
cteplan = (Plan *) list_nth(root->glob->subplans, plan_id - 1);
/* Mark rel with estimated output rows, width, etc */
set_cte_size_estimates(root, rel, cteplan->plan_rows);
/*
* We don't support pushing join clauses into the quals of a CTE scan, but
* it could still have required parameterization due to LATERAL refs in
* its tlist.
*/
required_outer = rel->lateral_relids;
/* Generate appropriate path */
add_path(rel, create_ctescan_path(root, rel, required_outer));
}
/*
* set_namedtuplestore_pathlist
* Build the (single) access path for a named tuplestore RTE
*
* There's no need for a separate set_namedtuplestore_size phase, since we
* don't support join-qual-parameterized paths for tuplestores.
*/
static void
set_namedtuplestore_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte)
{
Relids required_outer;
/* Mark rel with estimated output rows, width, etc */
set_namedtuplestore_size_estimates(root, rel);
/*
* We don't support pushing join clauses into the quals of a tuplestore
* scan, but it could still have required parameterization due to LATERAL
* refs in its tlist.
*/
required_outer = rel->lateral_relids;
/* Generate appropriate path */
add_path(rel, create_namedtuplestorescan_path(root, rel, required_outer));
/* Select cheapest path (pretty easy in this case...) */
set_cheapest(rel);
}
/*
* set_result_pathlist
* Build the (single) access path for an RTE_RESULT RTE
*
* There's no need for a separate set_result_size phase, since we
* don't support join-qual-parameterized paths for these RTEs.
*/
static void
set_result_pathlist(PlannerInfo *root, RelOptInfo *rel,
RangeTblEntry *rte)
{
Relids required_outer;
/* Mark rel with estimated output rows, width, etc */
set_result_size_estimates(root, rel);
/*
* We don't support pushing join clauses into the quals of a Result scan,
* but it could still have required parameterization due to LATERAL refs
* in its tlist.
*/
required_outer = rel->lateral_relids;
/* Generate appropriate path */
add_path(rel, create_resultscan_path(root, rel, required_outer));
/* Select cheapest path (pretty easy in this case...) */
set_cheapest(rel);
}
/*
* set_worktable_pathlist
* Build the (single) access path for a self-reference CTE RTE
*
* There's no need for a separate set_worktable_size phase, since we don't
* support join-qual-parameterized paths for CTEs.
*/
static void
set_worktable_pathlist(PlannerInfo *root, RelOptInfo *rel, RangeTblEntry *rte)
{
Path *ctepath;
PlannerInfo *cteroot;
Index levelsup;
Relids required_outer;
/*
* We need to find the non-recursive term's path, which is in the plan
* level that's processing the recursive UNION, which is one level *below*
* where the CTE comes from.
*/
levelsup = rte->ctelevelsup;
if (levelsup == 0) /* shouldn't happen */
elog(ERROR, "bad levelsup for CTE \"%s\"", rte->ctename);
levelsup--;
cteroot = root;
while (levelsup-- > 0)
{
cteroot = cteroot->parent_root;
if (!cteroot) /* shouldn't happen */
elog(ERROR, "bad levelsup for CTE \"%s\"", rte->ctename);
}
ctepath = cteroot->non_recursive_path;
if (!ctepath) /* shouldn't happen */
elog(ERROR, "could not find path for CTE \"%s\"", rte->ctename);
/* Mark rel with estimated output rows, width, etc */
set_cte_size_estimates(root, rel, ctepath->rows);
/*
* We don't support pushing join clauses into the quals of a worktable
* scan, but it could still have required parameterization due to LATERAL
* refs in its tlist. (I'm not sure this is actually possible given the
* restrictions on recursive references, but it's easy enough to support.)
*/
required_outer = rel->lateral_relids;
/* Generate appropriate path */
add_path(rel, create_worktablescan_path(root, rel, required_outer));
}
/*
* generate_gather_paths
* Generate parallel access paths for a relation by pushing a Gather or
* Gather Merge on top of a partial path.
*
* This must not be called until after we're done creating all partial paths
* for the specified relation. (Otherwise, add_partial_path might delete a
* path that some GatherPath or GatherMergePath has a reference to.)
*
* If we're generating paths for a scan or join relation, override_rows will
* be false, and we'll just use the relation's size estimate. When we're
* being called for a partially-grouped path, though, we need to override
* the rowcount estimate. (It's not clear that the particular value we're
* using here is actually best, but the underlying rel has no estimate so
* we must do something.)
*/
void
generate_gather_paths(PlannerInfo *root, RelOptInfo *rel, bool override_rows)
{
Path *cheapest_partial_path;
Path *simple_gather_path;
ListCell *lc;
double rows;
double *rowsp = NULL;
/* If there are no partial paths, there's nothing to do here. */
if (rel->partial_pathlist == NIL)
return;
/* Should we override the rel's rowcount estimate? */
if (override_rows)
rowsp = &rows;
/*
* The output of Gather is always unsorted, so there's only one partial
* path of interest: the cheapest one. That will be the one at the front
* of partial_pathlist because of the way add_partial_path works.
*/
cheapest_partial_path = linitial(rel->partial_pathlist);
rows =
cheapest_partial_path->rows * cheapest_partial_path->parallel_workers;
simple_gather_path = (Path *)
create_gather_path(root, rel, cheapest_partial_path, rel->reltarget,
NULL, rowsp);
add_path(rel, simple_gather_path);
/*
* For each useful ordering, we can consider an order-preserving Gather
* Merge.
*/
foreach(lc, rel->partial_pathlist)
{
Path *subpath = (Path *) lfirst(lc);
GatherMergePath *path;
if (subpath->pathkeys == NIL)
continue;
rows = subpath->rows * subpath->parallel_workers;
path = create_gather_merge_path(root, rel, subpath, rel->reltarget,
subpath->pathkeys, NULL, rowsp);
add_path(rel, &path->path);
}
}
/*
* make_rel_from_joinlist
* Build access paths using a "joinlist" to guide the join path search.
*
* See comments for deconstruct_jointree() for definition of the joinlist
* data structure.
*/
static RelOptInfo *
make_rel_from_joinlist(PlannerInfo *root, List *joinlist)
{
int levels_needed;
List *initial_rels;
ListCell *jl;
/*
* Count the number of child joinlist nodes. This is the depth of the
* dynamic-programming algorithm we must employ to consider all ways of
* joining the child nodes.
*/
levels_needed = list_length(joinlist);
if (levels_needed <= 0)
return NULL; /* nothing to do? */
/*
* Construct a list of rels corresponding to the child joinlist nodes.
* This may contain both base rels and rels constructed according to
* sub-joinlists.
*/
initial_rels = NIL;
foreach(jl, joinlist)
{
Node *jlnode = (Node *) lfirst(jl);
RelOptInfo *thisrel;
if (IsA(jlnode, RangeTblRef))
{
int varno = ((RangeTblRef *) jlnode)->rtindex;
thisrel = find_base_rel(root, varno);
}
else if (IsA(jlnode, List))
{
/* Recurse to handle subproblem */
thisrel = make_rel_from_joinlist(root, (List *) jlnode);
}
else
{
elog(ERROR, "unrecognized joinlist node type: %d",
(int) nodeTag(jlnode));
thisrel = NULL; /* keep compiler quiet */
}
initial_rels = lappend(initial_rels, thisrel);
}
if (levels_needed == 1)
{
/*
* Single joinlist node, so we're done.
*/
return (RelOptInfo *) linitial(initial_rels);
}
else
{
/*
* Consider the different orders in which we could join the rels,
* using a plugin, GEQO, or the regular join search code.
*
* We put the initial_rels list into a PlannerInfo field because
* has_legal_joinclause() needs to look at it (ugly :-().
*/
root->initial_rels = initial_rels;
if (join_search_hook)
return (*join_search_hook) (root, levels_needed, initial_rels);
else if (enable_geqo && levels_needed >= geqo_threshold)
return geqo(root, levels_needed, initial_rels);
else
return standard_join_search(root, levels_needed, initial_rels);
}
}
/*
* standard_join_search
* Find possible joinpaths for a query by successively finding ways
* to join component relations into join relations.
*
* 'levels_needed' is the number of iterations needed, ie, the number of
* independent jointree items in the query. This is > 1.
*
* 'initial_rels' is a list of RelOptInfo nodes for each independent
* jointree item. These are the components to be joined together.
* Note that levels_needed == list_length(initial_rels).
*
* Returns the final level of join relations, i.e., the relation that is
* the result of joining all the original relations together.
* At least one implementation path must be provided for this relation and
* all required sub-relations.
*
* To support loadable plugins that modify planner behavior by changing the
* join searching algorithm, we provide a hook variable that lets a plugin
* replace or supplement this function. Any such hook must return the same
* final join relation as the standard code would, but it might have a
* different set of implementation paths attached, and only the sub-joinrels
* needed for these paths need have been instantiated.
*
* Note to plugin authors: the functions invoked during standard_join_search()
* modify root->join_rel_list and root->join_rel_hash. If you want to do more
* than one join-order search, you'll probably need to save and restore the
* original states of those data structures. See geqo_eval() for an example.
*/
RelOptInfo *
standard_join_search(PlannerInfo *root, int levels_needed, List *initial_rels)
{
int lev;
RelOptInfo *rel;
/*
* This function cannot be invoked recursively within any one planning
* problem, so join_rel_level[] can't be in use already.
*/
Assert(root->join_rel_level == NULL);
/*
* We employ a simple "dynamic programming" algorithm: we first find all
* ways to build joins of two jointree items, then all ways to build joins
* of three items (from two-item joins and single items), then four-item
* joins, and so on until we have considered all ways to join all the
* items into one rel.
*
* root->join_rel_level[j] is a list of all the j-item rels. Initially we
* set root->join_rel_level[1] to represent all the single-jointree-item
* relations.
*/
root->join_rel_level = (List **) palloc0((levels_needed + 1) * sizeof(List *));
root->join_rel_level[1] = initial_rels;
for (lev = 2; lev <= levels_needed; lev++)
{
ListCell *lc;
/*
* Determine all possible pairs of relations to be joined at this
* level, and build paths for making each one from every available
* pair of lower-level relations.
*/
join_search_one_level(root, lev);
/*
* Run generate_partitionwise_join_paths() and generate_gather_paths()
* for each just-processed joinrel. We could not do this earlier
* because both regular and partial paths can get added to a
* particular joinrel at multiple times within join_search_one_level.
*
* After that, we're done creating paths for the joinrel, so run
* set_cheapest().
*/
foreach(lc, root->join_rel_level[lev])
{
rel = (RelOptInfo *) lfirst(lc);
/* Create paths for partitionwise joins. */
generate_partitionwise_join_paths(root, rel);
/*
* Except for the topmost scan/join rel, consider gathering
* partial paths. We'll do the same for the topmost scan/join rel
* once we know the final targetlist (see grouping_planner).
*/
if (lev < levels_needed)
generate_gather_paths(root, rel, false);
/* Find and save the cheapest paths for this rel */
set_cheapest(rel);
#ifdef OPTIMIZER_DEBUG
debug_print_rel(root, rel);
#endif
}
}
/*
* We should have a single rel at the final level.
*/
if (root->join_rel_level[levels_needed] == NIL)
elog(ERROR, "failed to build any %d-way joins", levels_needed);
Assert(list_length(root->join_rel_level[levels_needed]) == 1);
rel = (RelOptInfo *) linitial(root->join_rel_level[levels_needed]);
root->join_rel_level = NULL;
return rel;
}
/*****************************************************************************
* PUSHING QUALS DOWN INTO SUBQUERIES
*****************************************************************************/
/*
* subquery_is_pushdown_safe - is a subquery safe for pushing down quals?
*
* subquery is the particular component query being checked. topquery
* is the top component of a set-operations tree (the same Query if no
* set-op is involved).
*
* Conditions checked here:
*
* 1. If the subquery has a LIMIT clause, we must not push down any quals,
* since that could change the set of rows returned.
*
* 2. If the subquery contains EXCEPT or EXCEPT ALL set ops we cannot push
* quals into it, because that could change the results.
*
* 3. If the subquery uses DISTINCT, we cannot push volatile quals into it.
* This is because upper-level quals should semantically be evaluated only
* once per distinct row, not once per original row, and if the qual is
* volatile then extra evaluations could change the results. (This issue
* does not apply to other forms of aggregation such as GROUP BY, because
* when those are present we push into HAVING not WHERE, so that the quals
* are still applied after aggregation.)
*
* 4. If the subquery contains window functions, we cannot push volatile quals
* into it. The issue here is a bit different from DISTINCT: a volatile qual
* might succeed for some rows of a window partition and fail for others,
* thereby changing the partition contents and thus the window functions'
* results for rows that remain.
*
* 5. If the subquery contains any set-returning functions in its targetlist,
* we cannot push volatile quals into it. That would push them below the SRFs
* and thereby change the number of times they are evaluated. Also, a
* volatile qual could succeed for some SRF output rows and fail for others,
* a behavior that cannot occur if it's evaluated before SRF expansion.
*
* In addition, we make several checks on the subquery's output columns to see
* if it is safe to reference them in pushed-down quals. If output column k
* is found to be unsafe to reference, we set safetyInfo->unsafeColumns[k]
* to true, but we don't reject the subquery overall since column k might not
* be referenced by some/all quals. The unsafeColumns[] array will be
* consulted later by qual_is_pushdown_safe(). It's better to do it this way
* than to make the checks directly in qual_is_pushdown_safe(), because when
* the subquery involves set operations we have to check the output
* expressions in each arm of the set op.
*
* Note: pushing quals into a DISTINCT subquery is theoretically dubious:
* we're effectively assuming that the quals cannot distinguish values that
* the DISTINCT's equality operator sees as equal, yet there are many
* counterexamples to that assumption. However use of such a qual with a
* DISTINCT subquery would be unsafe anyway, since there's no guarantee which
* "equal" value will be chosen as the output value by the DISTINCT operation.
* So we don't worry too much about that. Another objection is that if the
* qual is expensive to evaluate, running it for each original row might cost
* more than we save by eliminating rows before the DISTINCT step. But it
* would be very hard to estimate that at this stage, and in practice pushdown
* seldom seems to make things worse, so we ignore that problem too.
*
* Note: likewise, pushing quals into a subquery with window functions is a
* bit dubious: the quals might remove some rows of a window partition while
* leaving others, causing changes in the window functions' results for the
* surviving rows. We insist that such a qual reference only partitioning
* columns, but again that only protects us if the qual does not distinguish
* values that the partitioning equality operator sees as equal. The risks
* here are perhaps larger than for DISTINCT, since no de-duplication of rows
* occurs and thus there is no theoretical problem with such a qual. But
* we'll do this anyway because the potential performance benefits are very
* large, and we've seen no field complaints about the longstanding comparable
* behavior with DISTINCT.
*/
static bool
subquery_is_pushdown_safe(Query *subquery, Query *topquery,
pushdown_safety_info *safetyInfo)
{
SetOperationStmt *topop;
/* Check point 1 */
if (subquery->limitOffset != NULL || subquery->limitCount != NULL)
return false;
/* Check points 3, 4, and 5 */
if (subquery->distinctClause ||
subquery->hasWindowFuncs ||
subquery->hasTargetSRFs)
safetyInfo->unsafeVolatile = true;
/*
* If we're at a leaf query, check for unsafe expressions in its target
* list, and mark any unsafe ones in unsafeColumns[]. (Non-leaf nodes in
* setop trees have only simple Vars in their tlists, so no need to check
* them.)
*/
if (subquery->setOperations == NULL)
check_output_expressions(subquery, safetyInfo);
/* Are we at top level, or looking at a setop component? */
if (subquery == topquery)
{
/* Top level, so check any component queries */
if (subquery->setOperations != NULL)
if (!recurse_pushdown_safe(subquery->setOperations, topquery,
safetyInfo))
return false;
}
else
{
/* Setop component must not have more components (too weird) */
if (subquery->setOperations != NULL)
return false;
/* Check whether setop component output types match top level */
topop = castNode(SetOperationStmt, topquery->setOperations);
Assert(topop);
compare_tlist_datatypes(subquery->targetList,
topop->colTypes,
safetyInfo);
}
return true;
}
/*
* Helper routine to recurse through setOperations tree
*/
static bool
recurse_pushdown_safe(Node *setOp, Query *topquery,
pushdown_safety_info *safetyInfo)
{
if (IsA(setOp, RangeTblRef))
{
RangeTblRef *rtr = (RangeTblRef *) setOp;
RangeTblEntry *rte = rt_fetch(rtr->rtindex, topquery->rtable);
Query *subquery = rte->subquery;
Assert(subquery != NULL);
return subquery_is_pushdown_safe(subquery, topquery, safetyInfo);
}
else if (IsA(setOp, SetOperationStmt))
{
SetOperationStmt *op = (SetOperationStmt *) setOp;
/* EXCEPT is no good (point 2 for subquery_is_pushdown_safe) */
if (op->op == SETOP_EXCEPT)
return false;
/* Else recurse */
if (!recurse_pushdown_safe(op->larg, topquery, safetyInfo))
return false;
if (!recurse_pushdown_safe(op->rarg, topquery, safetyInfo))
return false;
}
else
{
elog(ERROR, "unrecognized node type: %d",
(int) nodeTag(setOp));
}
return true;
}
/*
* check_output_expressions - check subquery's output expressions for safety
*
* There are several cases in which it's unsafe to push down an upper-level
* qual if it references a particular output column of a subquery. We check
* each output column of the subquery and set unsafeColumns[k] to true if
* that column is unsafe for a pushed-down qual to reference. The conditions
* checked here are:
*
* 1. We must not push down any quals that refer to subselect outputs that
* return sets, else we'd introduce functions-returning-sets into the
* subquery's WHERE/HAVING quals.
*
* 2. We must not push down any quals that refer to subselect outputs that
* contain volatile functions, for fear of introducing strange results due
* to multiple evaluation of a volatile function.
*
* 3. If the subquery uses DISTINCT ON, we must not push down any quals that
* refer to non-DISTINCT output columns, because that could change the set
* of rows returned. (This condition is vacuous for DISTINCT, because then
* there are no non-DISTINCT output columns, so we needn't check. Note that
* subquery_is_pushdown_safe already reported that we can't use volatile
* quals if there's DISTINCT or DISTINCT ON.)
*
* 4. If the subquery has any window functions, we must not push down quals
* that reference any output columns that are not listed in all the subquery's
* window PARTITION BY clauses. We can push down quals that use only
* partitioning columns because they should succeed or fail identically for
* every row of any one window partition, and totally excluding some
* partitions will not change a window function's results for remaining
* partitions. (Again, this also requires nonvolatile quals, but
* subquery_is_pushdown_safe handles that.)
*/
static void
check_output_expressions(Query *subquery, pushdown_safety_info *safetyInfo)
{
ListCell *lc;
foreach(lc, subquery->targetList)
{
TargetEntry *tle = (TargetEntry *) lfirst(lc);
if (tle->resjunk)
continue; /* ignore resjunk columns */
/* We need not check further if output col is already known unsafe */
if (safetyInfo->unsafeColumns[tle->resno])
continue;
/* Functions returning sets are unsafe (point 1) */
if (subquery->hasTargetSRFs &&
expression_returns_set((Node *) tle->expr))
{
safetyInfo->unsafeColumns[tle->resno] = true;
continue;
}
/* Volatile functions are unsafe (point 2) */
if (contain_volatile_functions((Node *) tle->expr))
{
safetyInfo->unsafeColumns[tle->resno] = true;
continue;
}
/* If subquery uses DISTINCT ON, check point 3 */
if (subquery->hasDistinctOn &&
!targetIsInSortList(tle, InvalidOid, subquery->distinctClause))
{
/* non-DISTINCT column, so mark it unsafe */
safetyInfo->unsafeColumns[tle->resno] = true;
continue;
}
/* If subquery uses window functions, check point 4 */
if (subquery->hasWindowFuncs &&
!targetIsInAllPartitionLists(tle, subquery))
{
/* not present in all PARTITION BY clauses, so mark it unsafe */
safetyInfo->unsafeColumns[tle->resno] = true;
continue;
}
}
}
/*
* For subqueries using UNION/UNION ALL/INTERSECT/INTERSECT ALL, we can
* push quals into each component query, but the quals can only reference
* subquery columns that suffer no type coercions in the set operation.
* Otherwise there are possible semantic gotchas. So, we check the
* component queries to see if any of them have output types different from
* the top-level setop outputs. unsafeColumns[k] is set true if column k
* has different type in any component.
*
* We don't have to care about typmods here: the only allowed difference
* between set-op input and output typmods is input is a specific typmod
* and output is -1, and that does not require a coercion.
*
* tlist is a subquery tlist.
* colTypes is an OID list of the top-level setop's output column types.
* safetyInfo->unsafeColumns[] is the result array.
*/
static void
compare_tlist_datatypes(List *tlist, List *colTypes,
pushdown_safety_info *safetyInfo)
{
ListCell *l;
ListCell *colType = list_head(colTypes);
foreach(l, tlist)
{
TargetEntry *tle = (TargetEntry *) lfirst(l);
if (tle->resjunk)
continue; /* ignore resjunk columns */
if (colType == NULL)
elog(ERROR, "wrong number of tlist entries");
if (exprType((Node *) tle->expr) != lfirst_oid(colType))
safetyInfo->unsafeColumns[tle->resno] = true;
colType = lnext(colTypes, colType);
}
if (colType != NULL)
elog(ERROR, "wrong number of tlist entries");
}
/*
* targetIsInAllPartitionLists
* True if the TargetEntry is listed in the PARTITION BY clause
* of every window defined in the query.
*
* It would be safe to ignore windows not actually used by any window
* function, but it's not easy to get that info at this stage; and it's
* unlikely to be useful to spend any extra cycles getting it, since
* unreferenced window definitions are probably infrequent in practice.
*/
static bool
targetIsInAllPartitionLists(TargetEntry *tle, Query *query)
{
ListCell *lc;
foreach(lc, query->windowClause)
{
WindowClause *wc = (WindowClause *) lfirst(lc);
if (!targetIsInSortList(tle, InvalidOid, wc->partitionClause))
return false;
}
return true;
}
/*
* qual_is_pushdown_safe - is a particular qual safe to push down?
*
* qual is a restriction clause applying to the given subquery (whose RTE
* has index rti in the parent query).
*
* Conditions checked here:
*
* 1. The qual must not contain any SubPlans (mainly because I'm not sure
* it will work correctly: SubLinks will already have been transformed into
* SubPlans in the qual, but not in the subquery). Note that SubLinks that
* transform to initplans are safe, and will be accepted here because what
* we'll see in the qual is just a Param referencing the initplan output.
*
* 2. If unsafeVolatile is set, the qual must not contain any volatile
* functions.
*
* 3. If unsafeLeaky is set, the qual must not contain any leaky functions
* that are passed Var nodes, and therefore might reveal values from the
* subquery as side effects.
*
* 4. The qual must not refer to the whole-row output of the subquery
* (since there is no easy way to name that within the subquery itself).
*
* 5. The qual must not refer to any subquery output columns that were
* found to be unsafe to reference by subquery_is_pushdown_safe().
*/
static bool
qual_is_pushdown_safe(Query *subquery, Index rti, Node *qual,
pushdown_safety_info *safetyInfo)
{
bool safe = true;
List *vars;
ListCell *vl;
/* Refuse subselects (point 1) */
if (contain_subplans(qual))
return false;
/* Refuse volatile quals if we found they'd be unsafe (point 2) */
if (safetyInfo->unsafeVolatile &&
contain_volatile_functions(qual))
return false;
/* Refuse leaky quals if told to (point 3) */
if (safetyInfo->unsafeLeaky &&
contain_leaked_vars(qual))
return false;
/*
* It would be unsafe to push down window function calls, but at least for
* the moment we could never see any in a qual anyhow. (The same applies
* to aggregates, which we check for in pull_var_clause below.)
*/
Assert(!contain_window_function(qual));
/*
* Examine all Vars used in clause; since it's a restriction clause, all
* such Vars must refer to subselect output columns.
*/
vars = pull_var_clause(qual, PVC_INCLUDE_PLACEHOLDERS);
foreach(vl, vars)
{
Var *var = (Var *) lfirst(vl);
/*
* XXX Punt if we find any PlaceHolderVars in the restriction clause.
* It's not clear whether a PHV could safely be pushed down, and even
* less clear whether such a situation could arise in any cases of
* practical interest anyway. So for the moment, just refuse to push
* down.
*/
if (!IsA(var, Var))
{
safe = false;
break;
}
Assert(var->varno == rti);
Assert(var->varattno >= 0);
/* Check point 4 */
if (var->varattno == 0)
{
safe = false;
break;
}
/* Check point 5 */
if (safetyInfo->unsafeColumns[var->varattno])
{
safe = false;
break;
}
}
list_free(vars);
return safe;
}
/*
* subquery_push_qual - push down a qual that we have determined is safe
*/
static void
subquery_push_qual(Query *subquery, RangeTblEntry *rte, Index rti, Node *qual)
{
if (subquery->setOperations != NULL)
{
/* Recurse to push it separately to each component query */
recurse_push_qual(subquery->setOperations, subquery,
rte, rti, qual);
}
else
{
/*
* We need to replace Vars in the qual (which must refer to outputs of
* the subquery) with copies of the subquery's targetlist expressions.
* Note that at this point, any uplevel Vars in the qual should have
* been replaced with Params, so they need no work.
*
* This step also ensures that when we are pushing into a setop tree,
* each component query gets its own copy of the qual.
*/
qual = ReplaceVarsFromTargetList(qual, rti, 0, rte,
subquery->targetList,
REPLACEVARS_REPORT_ERROR, 0,
&subquery->hasSubLinks);
/*
* Now attach the qual to the proper place: normally WHERE, but if the
* subquery uses grouping or aggregation, put it in HAVING (since the
* qual really refers to the group-result rows).
*/
if (subquery->hasAggs || subquery->groupClause || subquery->groupingSets || subquery->havingQual)
subquery->havingQual = make_and_qual(subquery->havingQual, qual);
else
subquery->jointree->quals =
make_and_qual(subquery->jointree->quals, qual);
/*
* We need not change the subquery's hasAggs or hasSubLinks flags,
* since we can't be pushing down any aggregates that weren't there
* before, and we don't push down subselects at all.
*/
}
}
/*
* Helper routine to recurse through setOperations tree
*/
static void
recurse_push_qual(Node *setOp, Query *topquery,
RangeTblEntry *rte, Index rti, Node *qual)
{
if (IsA(setOp, RangeTblRef))
{
RangeTblRef *rtr = (RangeTblRef *) setOp;
RangeTblEntry *subrte = rt_fetch(rtr->rtindex, topquery->rtable);
Query *subquery = subrte->subquery;
Assert(subquery != NULL);
subquery_push_qual(subquery, rte, rti, qual);
}
else if (IsA(setOp, SetOperationStmt))
{
SetOperationStmt *op = (SetOperationStmt *) setOp;
recurse_push_qual(op->larg, topquery, rte, rti, qual);
recurse_push_qual(op->rarg, topquery, rte, rti, qual);
}
else
{
elog(ERROR, "unrecognized node type: %d",
(int) nodeTag(setOp));
}
}
/*****************************************************************************
* SIMPLIFYING SUBQUERY TARGETLISTS
*****************************************************************************/
/*
* remove_unused_subquery_outputs
* Remove subquery targetlist items we don't need
*
* It's possible, even likely, that the upper query does not read all the
* output columns of the subquery. We can remove any such outputs that are
* not needed by the subquery itself (e.g., as sort/group columns) and do not
* affect semantics otherwise (e.g., volatile functions can't be removed).
* This is useful not only because we might be able to remove expensive-to-
* compute expressions, but because deletion of output columns might allow
* optimizations such as join removal to occur within the subquery.
*
* To avoid affecting column numbering in the targetlist, we don't physically
* remove unused tlist entries, but rather replace their expressions with NULL
* constants. This is implemented by modifying subquery->targetList.
*/
static void
remove_unused_subquery_outputs(Query *subquery, RelOptInfo *rel)
{
Bitmapset *attrs_used = NULL;
ListCell *lc;
/*
* Do nothing if subquery has UNION/INTERSECT/EXCEPT: in principle we
* could update all the child SELECTs' tlists, but it seems not worth the
* trouble presently.
*/
if (subquery->setOperations)
return;
/*
* If subquery has regular DISTINCT (not DISTINCT ON), we're wasting our
* time: all its output columns must be used in the distinctClause.
*/
if (subquery->distinctClause && !subquery->hasDistinctOn)
return;
/*
* Collect a bitmap of all the output column numbers used by the upper
* query.
*
* Add all the attributes needed for joins or final output. Note: we must
* look at rel's targetlist, not the attr_needed data, because attr_needed
* isn't computed for inheritance child rels, cf set_append_rel_size().
* (XXX might be worth changing that sometime.)
*/
pull_varattnos((Node *) rel->reltarget->exprs, rel->relid, &attrs_used);
/* Add all the attributes used by un-pushed-down restriction clauses. */
foreach(lc, rel->baserestrictinfo)
{
RestrictInfo *rinfo = (RestrictInfo *) lfirst(lc);
pull_varattnos((Node *) rinfo->clause, rel->relid, &attrs_used);
}
/*
* If there's a whole-row reference to the subquery, we can't remove
* anything.
*/
if (bms_is_member(0 - FirstLowInvalidHeapAttributeNumber, attrs_used))
return;
/*
* Run through the tlist and zap entries we don't need. It's okay to
* modify the tlist items in-place because set_subquery_pathlist made a
* copy of the subquery.
*/
foreach(lc, subquery->targetList)
{
TargetEntry *tle = (TargetEntry *) lfirst(lc);
Node *texpr = (Node *) tle->expr;
/*
* If it has a sortgroupref number, it's used in some sort/group
* clause so we'd better not remove it. Also, don't remove any
* resjunk columns, since their reason for being has nothing to do
* with anybody reading the subquery's output. (It's likely that
* resjunk columns in a sub-SELECT would always have ressortgroupref
* set, but even if they don't, it seems imprudent to remove them.)
*/
if (tle->ressortgroupref || tle->resjunk)
continue;
/*
* If it's used by the upper query, we can't remove it.
*/
if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber,
attrs_used))
continue;
/*
* If it contains a set-returning function, we can't remove it since
* that could change the number of rows returned by the subquery.
*/
if (subquery->hasTargetSRFs &&
expression_returns_set(texpr))
continue;
/*
* If it contains volatile functions, we daren't remove it for fear
* that the user is expecting their side-effects to happen.
*/
if (contain_volatile_functions(texpr))
continue;
/*
* OK, we don't need it. Replace the expression with a NULL constant.
* Preserve the exposed type of the expression, in case something
* looks at the rowtype of the subquery's result.
*/
tle->expr = (Expr *) makeNullConst(exprType(texpr),
exprTypmod(texpr),
exprCollation(texpr));
}
}
/*
* create_partial_bitmap_paths
* Build partial bitmap heap path for the relation
*/
void
create_partial_bitmap_paths(PlannerInfo *root, RelOptInfo *rel,
Path *bitmapqual)
{
int parallel_workers;
double pages_fetched;
/* Compute heap pages for bitmap heap scan */
pages_fetched = compute_bitmap_pages(root, rel, bitmapqual, 1.0,
NULL, NULL);
parallel_workers = compute_parallel_worker(rel, pages_fetched, -1,
max_parallel_workers_per_gather);
if (parallel_workers <= 0)
return;
add_partial_path(rel, (Path *) create_bitmap_heap_path(root, rel,
bitmapqual, rel->lateral_relids, 1.0, parallel_workers));
}
/*
* Compute the number of parallel workers that should be used to scan a
* relation. We compute the parallel workers based on the size of the heap to
* be scanned and the size of the index to be scanned, then choose a minimum
* of those.
*
* "heap_pages" is the number of pages from the table that we expect to scan, or
* -1 if we don't expect to scan any.
*
* "index_pages" is the number of pages from the index that we expect to scan, or
* -1 if we don't expect to scan any.
*
* "max_workers" is caller's limit on the number of workers. This typically
* comes from a GUC.
*/
int
compute_parallel_worker(RelOptInfo *rel, double heap_pages, double index_pages,
int max_workers)
{
int parallel_workers = 0;
/*
* If the user has set the parallel_workers reloption, use that; otherwise
* select a default number of workers.
*/
if (rel->rel_parallel_workers != -1)
parallel_workers = rel->rel_parallel_workers;
else
{
/*
* If the number of pages being scanned is insufficient to justify a
* parallel scan, just return zero ... unless it's an inheritance
* child. In that case, we want to generate a parallel path here
* anyway. It might not be worthwhile just for this relation, but
* when combined with all of its inheritance siblings it may well pay
* off.
*/
if (rel->reloptkind == RELOPT_BASEREL &&
((heap_pages >= 0 && heap_pages < min_parallel_table_scan_size) ||
(index_pages >= 0 && index_pages < min_parallel_index_scan_size)))
return 0;
if (heap_pages >= 0)
{
int heap_parallel_threshold;
int heap_parallel_workers = 1;
/*
* Select the number of workers based on the log of the size of
* the relation. This probably needs to be a good deal more
* sophisticated, but we need something here for now. Note that
* the upper limit of the min_parallel_table_scan_size GUC is
* chosen to prevent overflow here.
*/
heap_parallel_threshold = Max(min_parallel_table_scan_size, 1);
while (heap_pages >= (BlockNumber) (heap_parallel_threshold * 3))
{
heap_parallel_workers++;
heap_parallel_threshold *= 3;
if (heap_parallel_threshold > INT_MAX / 3)
break; /* avoid overflow */
}
parallel_workers = heap_parallel_workers;
}
if (index_pages >= 0)
{
int index_parallel_workers = 1;
int index_parallel_threshold;
/* same calculation as for heap_pages above */
index_parallel_threshold = Max(min_parallel_index_scan_size, 1);
while (index_pages >= (BlockNumber) (index_parallel_threshold * 3))
{
index_parallel_workers++;
index_parallel_threshold *= 3;
if (index_parallel_threshold > INT_MAX / 3)
break; /* avoid overflow */
}
if (parallel_workers > 0)
parallel_workers = Min(parallel_workers, index_parallel_workers);
else
parallel_workers = index_parallel_workers;
}
}
/* In no case use more than caller supplied maximum number of workers */
parallel_workers = Min(parallel_workers, max_workers);
return parallel_workers;
}
/*
* generate_partitionwise_join_paths
* Create paths representing partitionwise join for given partitioned
* join relation.
*
* This must not be called until after we are done adding paths for all
* child-joins. Otherwise, add_path might delete a path to which some path
* generated here has a reference.
*/
void
generate_partitionwise_join_paths(PlannerInfo *root, RelOptInfo *rel)
{
List *live_children = NIL;
int cnt_parts;
int num_parts;
RelOptInfo **part_rels;
/* Handle only join relations here. */
if (!IS_JOIN_REL(rel))
return;
/* We've nothing to do if the relation is not partitioned. */
if (!IS_PARTITIONED_REL(rel))
return;
/* The relation should have consider_partitionwise_join set. */
Assert(rel->consider_partitionwise_join);
/* Guard against stack overflow due to overly deep partition hierarchy. */
check_stack_depth();
num_parts = rel->nparts;
part_rels = rel->part_rels;
/* Collect non-dummy child-joins. */
for (cnt_parts = 0; cnt_parts < num_parts; cnt_parts++)
{
RelOptInfo *child_rel = part_rels[cnt_parts];
/* If it's been pruned entirely, it's certainly dummy. */
if (child_rel == NULL)
continue;
/* Add partitionwise join paths for partitioned child-joins. */
generate_partitionwise_join_paths(root, child_rel);
set_cheapest(child_rel);
/* Dummy children will not be scanned, so ignore those. */
if (IS_DUMMY_REL(child_rel))
continue;
#ifdef OPTIMIZER_DEBUG
debug_print_rel(root, child_rel);
#endif
live_children = lappend(live_children, child_rel);
}
/* If all child-joins are dummy, parent join is also dummy. */
if (!live_children)
{
mark_dummy_rel(rel);
return;
}
/* Build additional paths for this rel from child-join paths. */
add_paths_to_append_rel(root, rel, live_children);
list_free(live_children);
}
/*****************************************************************************
* DEBUG SUPPORT
*****************************************************************************/
#ifdef OPTIMIZER_DEBUG
static void
print_relids(PlannerInfo *root, Relids relids)
{
int x;
bool first = true;
x = -1;
while ((x = bms_next_member(relids, x)) >= 0)
{
if (!first)
printf(" ");
if (x < root->simple_rel_array_size &&
root->simple_rte_array[x])
printf("%s", root->simple_rte_array[x]->eref->aliasname);
else
printf("%d", x);
first = false;
}
}
static void
print_restrictclauses(PlannerInfo *root, List *clauses)
{
ListCell *l;
foreach(l, clauses)
{
RestrictInfo *c = lfirst(l);
print_expr((Node *) c->clause, root->parse->rtable);
if (lnext(clauses, l))
printf(", ");
}
}
static void
print_path(PlannerInfo *root, Path *path, int indent)
{
const char *ptype;
bool join = false;
Path *subpath = NULL;
int i;
switch (nodeTag(path))
{
case T_Path:
switch (path->pathtype)
{
case T_SeqScan:
ptype = "SeqScan";
break;
case T_SampleScan:
ptype = "SampleScan";
break;
case T_FunctionScan:
ptype = "FunctionScan";
break;
case T_TableFuncScan:
ptype = "TableFuncScan";
break;
case T_ValuesScan:
ptype = "ValuesScan";
break;
case T_CteScan:
ptype = "CteScan";
break;
case T_NamedTuplestoreScan:
ptype = "NamedTuplestoreScan";
break;
case T_Result:
ptype = "Result";
break;
case T_WorkTableScan:
ptype = "WorkTableScan";
break;
default:
ptype = "???Path";
break;
}
break;
case T_IndexPath:
ptype = "IdxScan";
break;
case T_BitmapHeapPath:
ptype = "BitmapHeapScan";
break;
case T_BitmapAndPath:
ptype = "BitmapAndPath";
break;
case T_BitmapOrPath:
ptype = "BitmapOrPath";
break;
case T_TidPath:
ptype = "TidScan";
break;
case T_SubqueryScanPath:
ptype = "SubqueryScan";
break;
case T_ForeignPath:
ptype = "ForeignScan";
break;
case T_CustomPath:
ptype = "CustomScan";
break;
case T_NestPath:
ptype = "NestLoop";
join = true;
break;
case T_MergePath:
ptype = "MergeJoin";
join = true;
break;
case T_HashPath:
ptype = "HashJoin";
join = true;
break;
case T_AppendPath:
ptype = "Append";
break;
case T_MergeAppendPath:
ptype = "MergeAppend";
break;
case T_GroupResultPath:
ptype = "GroupResult";
break;
case T_MaterialPath:
ptype = "Material";
subpath = ((MaterialPath *) path)->subpath;
break;
case T_UniquePath:
ptype = "Unique";
subpath = ((UniquePath *) path)->subpath;
break;
case T_GatherPath:
ptype = "Gather";
subpath = ((GatherPath *) path)->subpath;
break;
case T_GatherMergePath:
ptype = "GatherMerge";
subpath = ((GatherMergePath *) path)->subpath;
break;
case T_ProjectionPath:
ptype = "Projection";
subpath = ((ProjectionPath *) path)->subpath;
break;
case T_ProjectSetPath:
ptype = "ProjectSet";
subpath = ((ProjectSetPath *) path)->subpath;
break;
case T_SortPath:
ptype = "Sort";
subpath = ((SortPath *) path)->subpath;
break;
case T_GroupPath:
ptype = "Group";
subpath = ((GroupPath *) path)->subpath;
break;
case T_UpperUniquePath:
ptype = "UpperUnique";
subpath = ((UpperUniquePath *) path)->subpath;
break;
case T_AggPath:
ptype = "Agg";
subpath = ((AggPath *) path)->subpath;
break;
case T_GroupingSetsPath:
ptype = "GroupingSets";
subpath = ((GroupingSetsPath *) path)->subpath;
break;
case T_MinMaxAggPath:
ptype = "MinMaxAgg";
break;
case T_WindowAggPath:
ptype = "WindowAgg";
subpath = ((WindowAggPath *) path)->subpath;
break;
case T_SetOpPath:
ptype = "SetOp";
subpath = ((SetOpPath *) path)->subpath;
break;
case T_RecursiveUnionPath:
ptype = "RecursiveUnion";
break;
case T_LockRowsPath:
ptype = "LockRows";
subpath = ((LockRowsPath *) path)->subpath;
break;
case T_ModifyTablePath:
ptype = "ModifyTable";
break;
case T_LimitPath:
ptype = "Limit";
subpath = ((LimitPath *) path)->subpath;
break;
default:
ptype = "???Path";
break;
}
for (i = 0; i < indent; i++)
printf("\t");
printf("%s", ptype);
if (path->parent)
{
printf("(");
print_relids(root, path->parent->relids);
printf(")");
}
if (path->param_info)
{
printf(" required_outer (");
print_relids(root, path->param_info->ppi_req_outer);
printf(")");
}
printf(" rows=%.0f cost=%.2f..%.2f\n",
path->rows, path->startup_cost, path->total_cost);
if (path->pathkeys)
{
for (i = 0; i < indent; i++)
printf("\t");
printf(" pathkeys: ");
print_pathkeys(path->pathkeys, root->parse->rtable);
}
if (join)
{
JoinPath *jp = (JoinPath *) path;
for (i = 0; i < indent; i++)
printf("\t");
printf(" clauses: ");
print_restrictclauses(root, jp->joinrestrictinfo);
printf("\n");
if (IsA(path, MergePath))
{
MergePath *mp = (MergePath *) path;
for (i = 0; i < indent; i++)
printf("\t");
printf(" sortouter=%d sortinner=%d materializeinner=%d\n",
((mp->outersortkeys) ? 1 : 0),
((mp->innersortkeys) ? 1 : 0),
((mp->materialize_inner) ? 1 : 0));
}
print_path(root, jp->outerjoinpath, indent + 1);
print_path(root, jp->innerjoinpath, indent + 1);
}
if (subpath)
print_path(root, subpath, indent + 1);
}
void
debug_print_rel(PlannerInfo *root, RelOptInfo *rel)
{
ListCell *l;
printf("RELOPTINFO (");
print_relids(root, rel->relids);
printf("): rows=%.0f width=%d\n", rel->rows, rel->reltarget->width);
if (rel->baserestrictinfo)
{
printf("\tbaserestrictinfo: ");
print_restrictclauses(root, rel->baserestrictinfo);
printf("\n");
}
if (rel->joininfo)
{
printf("\tjoininfo: ");
print_restrictclauses(root, rel->joininfo);
printf("\n");
}
printf("\tpath list:\n");
foreach(l, rel->pathlist)
print_path(root, lfirst(l), 1);
if (rel->cheapest_parameterized_paths)
{
printf("\n\tcheapest parameterized paths:\n");
foreach(l, rel->cheapest_parameterized_paths)
print_path(root, lfirst(l), 1);
}
if (rel->cheapest_startup_path)
{
printf("\n\tcheapest startup path:\n");
print_path(root, rel->cheapest_startup_path, 1);
}
if (rel->cheapest_total_path)
{
printf("\n\tcheapest total path:\n");
print_path(root, rel->cheapest_total_path, 1);
}
printf("\n");
fflush(stdout);
}
#endif /* OPTIMIZER_DEBUG */
|