1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
|
/*-------------------------------------------------------------------------
*
* costsize.c
* Routines to compute (and set) relation sizes and path costs
*
* Path costs are measured in arbitrary units established by these basic
* parameters:
*
* seq_page_cost Cost of a sequential page fetch
* random_page_cost Cost of a non-sequential page fetch
* cpu_tuple_cost Cost of typical CPU time to process a tuple
* cpu_index_tuple_cost Cost of typical CPU time to process an index tuple
* cpu_operator_cost Cost of CPU time to execute an operator or function
* parallel_tuple_cost Cost of CPU time to pass a tuple from worker to leader backend
* parallel_setup_cost Cost of setting up shared memory for parallelism
*
* We expect that the kernel will typically do some amount of read-ahead
* optimization; this in conjunction with seek costs means that seq_page_cost
* is normally considerably less than random_page_cost. (However, if the
* database is fully cached in RAM, it is reasonable to set them equal.)
*
* We also use a rough estimate "effective_cache_size" of the number of
* disk pages in Postgres + OS-level disk cache. (We can't simply use
* NBuffers for this purpose because that would ignore the effects of
* the kernel's disk cache.)
*
* Obviously, taking constants for these values is an oversimplification,
* but it's tough enough to get any useful estimates even at this level of
* detail. Note that all of these parameters are user-settable, in case
* the default values are drastically off for a particular platform.
*
* seq_page_cost and random_page_cost can also be overridden for an individual
* tablespace, in case some data is on a fast disk and other data is on a slow
* disk. Per-tablespace overrides never apply to temporary work files such as
* an external sort or a materialize node that overflows work_mem.
*
* We compute two separate costs for each path:
* total_cost: total estimated cost to fetch all tuples
* startup_cost: cost that is expended before first tuple is fetched
* In some scenarios, such as when there is a LIMIT or we are implementing
* an EXISTS(...) sub-select, it is not necessary to fetch all tuples of the
* path's result. A caller can estimate the cost of fetching a partial
* result by interpolating between startup_cost and total_cost. In detail:
* actual_cost = startup_cost +
* (total_cost - startup_cost) * tuples_to_fetch / path->rows;
* Note that a base relation's rows count (and, by extension, plan_rows for
* plan nodes below the LIMIT node) are set without regard to any LIMIT, so
* that this equation works properly. (Note: while path->rows is never zero
* for ordinary relations, it is zero for paths for provably-empty relations,
* so beware of division-by-zero.) The LIMIT is applied as a top-level
* plan node.
*
* For largely historical reasons, most of the routines in this module use
* the passed result Path only to store their results (rows, startup_cost and
* total_cost) into. All the input data they need is passed as separate
* parameters, even though much of it could be extracted from the Path.
* An exception is made for the cost_XXXjoin() routines, which expect all
* the other fields of the passed XXXPath to be filled in, and similarly
* cost_index() assumes the passed IndexPath is valid except for its output
* values.
*
*
* Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* src/backend/optimizer/path/costsize.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include <limits.h>
#include <math.h>
#include "access/amapi.h"
#include "access/htup_details.h"
#include "access/tsmapi.h"
#include "executor/executor.h"
#include "executor/nodeAgg.h"
#include "executor/nodeHash.h"
#include "executor/nodeMemoize.h"
#include "miscadmin.h"
#include "nodes/makefuncs.h"
#include "nodes/nodeFuncs.h"
#include "optimizer/clauses.h"
#include "optimizer/cost.h"
#include "optimizer/optimizer.h"
#include "optimizer/pathnode.h"
#include "optimizer/paths.h"
#include "optimizer/placeholder.h"
#include "optimizer/plancat.h"
#include "optimizer/planmain.h"
#include "optimizer/restrictinfo.h"
#include "parser/parsetree.h"
#include "utils/lsyscache.h"
#include "utils/selfuncs.h"
#include "utils/spccache.h"
#include "utils/tuplesort.h"
#define LOG2(x) (log(x) / 0.693147180559945)
/*
* Append and MergeAppend nodes are less expensive than some other operations
* which use cpu_tuple_cost; instead of adding a separate GUC, estimate the
* per-tuple cost as cpu_tuple_cost multiplied by this value.
*/
#define APPEND_CPU_COST_MULTIPLIER 0.5
/*
* Maximum value for row estimates. We cap row estimates to this to help
* ensure that costs based on these estimates remain within the range of what
* double can represent. add_path() wouldn't act sanely given infinite or NaN
* cost values.
*/
#define MAXIMUM_ROWCOUNT 1e100
double seq_page_cost = DEFAULT_SEQ_PAGE_COST;
double random_page_cost = DEFAULT_RANDOM_PAGE_COST;
double cpu_tuple_cost = DEFAULT_CPU_TUPLE_COST;
double cpu_index_tuple_cost = DEFAULT_CPU_INDEX_TUPLE_COST;
double cpu_operator_cost = DEFAULT_CPU_OPERATOR_COST;
double parallel_tuple_cost = DEFAULT_PARALLEL_TUPLE_COST;
double parallel_setup_cost = DEFAULT_PARALLEL_SETUP_COST;
double recursive_worktable_factor = DEFAULT_RECURSIVE_WORKTABLE_FACTOR;
int effective_cache_size = DEFAULT_EFFECTIVE_CACHE_SIZE;
Cost disable_cost = 1.0e10;
int max_parallel_workers_per_gather = 2;
bool enable_seqscan = true;
bool enable_indexscan = true;
bool enable_indexonlyscan = true;
bool enable_bitmapscan = true;
bool enable_tidscan = true;
bool enable_sort = true;
bool enable_incremental_sort = true;
bool enable_hashagg = true;
bool enable_nestloop = true;
bool enable_material = true;
bool enable_memoize = true;
bool enable_mergejoin = true;
bool enable_hashjoin = true;
bool enable_gathermerge = true;
bool enable_partitionwise_join = false;
bool enable_partitionwise_aggregate = false;
bool enable_parallel_append = true;
bool enable_parallel_hash = true;
bool enable_partition_pruning = true;
bool enable_async_append = true;
typedef struct
{
PlannerInfo *root;
QualCost total;
} cost_qual_eval_context;
static List *extract_nonindex_conditions(List *qual_clauses, List *indexclauses);
static MergeScanSelCache *cached_scansel(PlannerInfo *root,
RestrictInfo *rinfo,
PathKey *pathkey);
static void cost_rescan(PlannerInfo *root, Path *path,
Cost *rescan_startup_cost, Cost *rescan_total_cost);
static bool cost_qual_eval_walker(Node *node, cost_qual_eval_context *context);
static void get_restriction_qual_cost(PlannerInfo *root, RelOptInfo *baserel,
ParamPathInfo *param_info,
QualCost *qpqual_cost);
static bool has_indexed_join_quals(NestPath *path);
static double approx_tuple_count(PlannerInfo *root, JoinPath *path,
List *quals);
static double calc_joinrel_size_estimate(PlannerInfo *root,
RelOptInfo *joinrel,
RelOptInfo *outer_rel,
RelOptInfo *inner_rel,
double outer_rows,
double inner_rows,
SpecialJoinInfo *sjinfo,
List *restrictlist);
static Selectivity get_foreign_key_join_selectivity(PlannerInfo *root,
Relids outer_relids,
Relids inner_relids,
SpecialJoinInfo *sjinfo,
List **restrictlist);
static Cost append_nonpartial_cost(List *subpaths, int numpaths,
int parallel_workers);
static void set_rel_width(PlannerInfo *root, RelOptInfo *rel);
static double relation_byte_size(double tuples, int width);
static double page_size(double tuples, int width);
static double get_parallel_divisor(Path *path);
/*
* clamp_row_est
* Force a row-count estimate to a sane value.
*/
double
clamp_row_est(double nrows)
{
/*
* Avoid infinite and NaN row estimates. Costs derived from such values
* are going to be useless. Also force the estimate to be at least one
* row, to make explain output look better and to avoid possible
* divide-by-zero when interpolating costs. Make it an integer, too.
*/
if (nrows > MAXIMUM_ROWCOUNT || isnan(nrows))
nrows = MAXIMUM_ROWCOUNT;
else if (nrows <= 1.0)
nrows = 1.0;
else
nrows = rint(nrows);
return nrows;
}
/*
* clamp_cardinality_to_long
* Cast a Cardinality value to a sane long value.
*/
long
clamp_cardinality_to_long(Cardinality x)
{
/*
* Just for paranoia's sake, ensure we do something sane with negative or
* NaN values.
*/
if (isnan(x))
return LONG_MAX;
if (x <= 0)
return 0;
/*
* If "long" is 64 bits, then LONG_MAX cannot be represented exactly as a
* double. Casting it to double and back may well result in overflow due
* to rounding, so avoid doing that. We trust that any double value that
* compares strictly less than "(double) LONG_MAX" will cast to a
* representable "long" value.
*/
return (x < (double) LONG_MAX) ? (long) x : LONG_MAX;
}
/*
* cost_seqscan
* Determines and returns the cost of scanning a relation sequentially.
*
* 'baserel' is the relation to be scanned
* 'param_info' is the ParamPathInfo if this is a parameterized path, else NULL
*/
void
cost_seqscan(Path *path, PlannerInfo *root,
RelOptInfo *baserel, ParamPathInfo *param_info)
{
Cost startup_cost = 0;
Cost cpu_run_cost;
Cost disk_run_cost;
double spc_seq_page_cost;
QualCost qpqual_cost;
Cost cpu_per_tuple;
/* Should only be applied to base relations */
Assert(baserel->relid > 0);
Assert(baserel->rtekind == RTE_RELATION);
/* Mark the path with the correct row estimate */
if (param_info)
path->rows = param_info->ppi_rows;
else
path->rows = baserel->rows;
if (!enable_seqscan)
startup_cost += disable_cost;
/* fetch estimated page cost for tablespace containing table */
get_tablespace_page_costs(baserel->reltablespace,
NULL,
&spc_seq_page_cost);
/*
* disk costs
*/
disk_run_cost = spc_seq_page_cost * baserel->pages;
/* CPU costs */
get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
startup_cost += qpqual_cost.startup;
cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
cpu_run_cost = cpu_per_tuple * baserel->tuples;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->pathtarget->cost.startup;
cpu_run_cost += path->pathtarget->cost.per_tuple * path->rows;
/* Adjust costing for parallelism, if used. */
if (path->parallel_workers > 0)
{
double parallel_divisor = get_parallel_divisor(path);
/* The CPU cost is divided among all the workers. */
cpu_run_cost /= parallel_divisor;
/*
* It may be possible to amortize some of the I/O cost, but probably
* not very much, because most operating systems already do aggressive
* prefetching. For now, we assume that the disk run cost can't be
* amortized at all.
*/
/*
* In the case of a parallel plan, the row count needs to represent
* the number of tuples processed per worker.
*/
path->rows = clamp_row_est(path->rows / parallel_divisor);
}
path->startup_cost = startup_cost;
path->total_cost = startup_cost + cpu_run_cost + disk_run_cost;
}
/*
* cost_samplescan
* Determines and returns the cost of scanning a relation using sampling.
*
* 'baserel' is the relation to be scanned
* 'param_info' is the ParamPathInfo if this is a parameterized path, else NULL
*/
void
cost_samplescan(Path *path, PlannerInfo *root,
RelOptInfo *baserel, ParamPathInfo *param_info)
{
Cost startup_cost = 0;
Cost run_cost = 0;
RangeTblEntry *rte;
TableSampleClause *tsc;
TsmRoutine *tsm;
double spc_seq_page_cost,
spc_random_page_cost,
spc_page_cost;
QualCost qpqual_cost;
Cost cpu_per_tuple;
/* Should only be applied to base relations with tablesample clauses */
Assert(baserel->relid > 0);
rte = planner_rt_fetch(baserel->relid, root);
Assert(rte->rtekind == RTE_RELATION);
tsc = rte->tablesample;
Assert(tsc != NULL);
tsm = GetTsmRoutine(tsc->tsmhandler);
/* Mark the path with the correct row estimate */
if (param_info)
path->rows = param_info->ppi_rows;
else
path->rows = baserel->rows;
/* fetch estimated page cost for tablespace containing table */
get_tablespace_page_costs(baserel->reltablespace,
&spc_random_page_cost,
&spc_seq_page_cost);
/* if NextSampleBlock is used, assume random access, else sequential */
spc_page_cost = (tsm->NextSampleBlock != NULL) ?
spc_random_page_cost : spc_seq_page_cost;
/*
* disk costs (recall that baserel->pages has already been set to the
* number of pages the sampling method will visit)
*/
run_cost += spc_page_cost * baserel->pages;
/*
* CPU costs (recall that baserel->tuples has already been set to the
* number of tuples the sampling method will select). Note that we ignore
* execution cost of the TABLESAMPLE parameter expressions; they will be
* evaluated only once per scan, and in most usages they'll likely be
* simple constants anyway. We also don't charge anything for the
* calculations the sampling method might do internally.
*/
get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
startup_cost += qpqual_cost.startup;
cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
run_cost += cpu_per_tuple * baserel->tuples;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->pathtarget->cost.startup;
run_cost += path->pathtarget->cost.per_tuple * path->rows;
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;
}
/*
* cost_gather
* Determines and returns the cost of gather path.
*
* 'rel' is the relation to be operated upon
* 'param_info' is the ParamPathInfo if this is a parameterized path, else NULL
* 'rows' may be used to point to a row estimate; if non-NULL, it overrides
* both 'rel' and 'param_info'. This is useful when the path doesn't exactly
* correspond to any particular RelOptInfo.
*/
void
cost_gather(GatherPath *path, PlannerInfo *root,
RelOptInfo *rel, ParamPathInfo *param_info,
double *rows)
{
Cost startup_cost = 0;
Cost run_cost = 0;
/* Mark the path with the correct row estimate */
if (rows)
path->path.rows = *rows;
else if (param_info)
path->path.rows = param_info->ppi_rows;
else
path->path.rows = rel->rows;
startup_cost = path->subpath->startup_cost;
run_cost = path->subpath->total_cost - path->subpath->startup_cost;
/* Parallel setup and communication cost. */
startup_cost += parallel_setup_cost;
run_cost += parallel_tuple_cost * path->path.rows;
path->path.startup_cost = startup_cost;
path->path.total_cost = (startup_cost + run_cost);
}
/*
* cost_gather_merge
* Determines and returns the cost of gather merge path.
*
* GatherMerge merges several pre-sorted input streams, using a heap that at
* any given instant holds the next tuple from each stream. If there are N
* streams, we need about N*log2(N) tuple comparisons to construct the heap at
* startup, and then for each output tuple, about log2(N) comparisons to
* replace the top heap entry with the next tuple from the same stream.
*/
void
cost_gather_merge(GatherMergePath *path, PlannerInfo *root,
RelOptInfo *rel, ParamPathInfo *param_info,
Cost input_startup_cost, Cost input_total_cost,
double *rows)
{
Cost startup_cost = 0;
Cost run_cost = 0;
Cost comparison_cost;
double N;
double logN;
/* Mark the path with the correct row estimate */
if (rows)
path->path.rows = *rows;
else if (param_info)
path->path.rows = param_info->ppi_rows;
else
path->path.rows = rel->rows;
if (!enable_gathermerge)
startup_cost += disable_cost;
/*
* Add one to the number of workers to account for the leader. This might
* be overgenerous since the leader will do less work than other workers
* in typical cases, but we'll go with it for now.
*/
Assert(path->num_workers > 0);
N = (double) path->num_workers + 1;
logN = LOG2(N);
/* Assumed cost per tuple comparison */
comparison_cost = 2.0 * cpu_operator_cost;
/* Heap creation cost */
startup_cost += comparison_cost * N * logN;
/* Per-tuple heap maintenance cost */
run_cost += path->path.rows * comparison_cost * logN;
/* small cost for heap management, like cost_merge_append */
run_cost += cpu_operator_cost * path->path.rows;
/*
* Parallel setup and communication cost. Since Gather Merge, unlike
* Gather, requires us to block until a tuple is available from every
* worker, we bump the IPC cost up a little bit as compared with Gather.
* For lack of a better idea, charge an extra 5%.
*/
startup_cost += parallel_setup_cost;
run_cost += parallel_tuple_cost * path->path.rows * 1.05;
path->path.startup_cost = startup_cost + input_startup_cost;
path->path.total_cost = (startup_cost + run_cost + input_total_cost);
}
/*
* cost_index
* Determines and returns the cost of scanning a relation using an index.
*
* 'path' describes the indexscan under consideration, and is complete
* except for the fields to be set by this routine
* 'loop_count' is the number of repetitions of the indexscan to factor into
* estimates of caching behavior
*
* In addition to rows, startup_cost and total_cost, cost_index() sets the
* path's indextotalcost and indexselectivity fields. These values will be
* needed if the IndexPath is used in a BitmapIndexScan.
*
* NOTE: path->indexquals must contain only clauses usable as index
* restrictions. Any additional quals evaluated as qpquals may reduce the
* number of returned tuples, but they won't reduce the number of tuples
* we have to fetch from the table, so they don't reduce the scan cost.
*/
void
cost_index(IndexPath *path, PlannerInfo *root, double loop_count,
bool partial_path)
{
IndexOptInfo *index = path->indexinfo;
RelOptInfo *baserel = index->rel;
bool indexonly = (path->path.pathtype == T_IndexOnlyScan);
amcostestimate_function amcostestimate;
List *qpquals;
Cost startup_cost = 0;
Cost run_cost = 0;
Cost cpu_run_cost = 0;
Cost indexStartupCost;
Cost indexTotalCost;
Selectivity indexSelectivity;
double indexCorrelation,
csquared;
double spc_seq_page_cost,
spc_random_page_cost;
Cost min_IO_cost,
max_IO_cost;
QualCost qpqual_cost;
Cost cpu_per_tuple;
double tuples_fetched;
double pages_fetched;
double rand_heap_pages;
double index_pages;
/* Should only be applied to base relations */
Assert(IsA(baserel, RelOptInfo) &&
IsA(index, IndexOptInfo));
Assert(baserel->relid > 0);
Assert(baserel->rtekind == RTE_RELATION);
/*
* Mark the path with the correct row estimate, and identify which quals
* will need to be enforced as qpquals. We need not check any quals that
* are implied by the index's predicate, so we can use indrestrictinfo not
* baserestrictinfo as the list of relevant restriction clauses for the
* rel.
*/
if (path->path.param_info)
{
path->path.rows = path->path.param_info->ppi_rows;
/* qpquals come from the rel's restriction clauses and ppi_clauses */
qpquals = list_concat(extract_nonindex_conditions(path->indexinfo->indrestrictinfo,
path->indexclauses),
extract_nonindex_conditions(path->path.param_info->ppi_clauses,
path->indexclauses));
}
else
{
path->path.rows = baserel->rows;
/* qpquals come from just the rel's restriction clauses */
qpquals = extract_nonindex_conditions(path->indexinfo->indrestrictinfo,
path->indexclauses);
}
if (!enable_indexscan)
startup_cost += disable_cost;
/* we don't need to check enable_indexonlyscan; indxpath.c does that */
/*
* Call index-access-method-specific code to estimate the processing cost
* for scanning the index, as well as the selectivity of the index (ie,
* the fraction of main-table tuples we will have to retrieve) and its
* correlation to the main-table tuple order. We need a cast here because
* pathnodes.h uses a weak function type to avoid including amapi.h.
*/
amcostestimate = (amcostestimate_function) index->amcostestimate;
amcostestimate(root, path, loop_count,
&indexStartupCost, &indexTotalCost,
&indexSelectivity, &indexCorrelation,
&index_pages);
/*
* Save amcostestimate's results for possible use in bitmap scan planning.
* We don't bother to save indexStartupCost or indexCorrelation, because a
* bitmap scan doesn't care about either.
*/
path->indextotalcost = indexTotalCost;
path->indexselectivity = indexSelectivity;
/* all costs for touching index itself included here */
startup_cost += indexStartupCost;
run_cost += indexTotalCost - indexStartupCost;
/* estimate number of main-table tuples fetched */
tuples_fetched = clamp_row_est(indexSelectivity * baserel->tuples);
/* fetch estimated page costs for tablespace containing table */
get_tablespace_page_costs(baserel->reltablespace,
&spc_random_page_cost,
&spc_seq_page_cost);
/*----------
* Estimate number of main-table pages fetched, and compute I/O cost.
*
* When the index ordering is uncorrelated with the table ordering,
* we use an approximation proposed by Mackert and Lohman (see
* index_pages_fetched() for details) to compute the number of pages
* fetched, and then charge spc_random_page_cost per page fetched.
*
* When the index ordering is exactly correlated with the table ordering
* (just after a CLUSTER, for example), the number of pages fetched should
* be exactly selectivity * table_size. What's more, all but the first
* will be sequential fetches, not the random fetches that occur in the
* uncorrelated case. So if the number of pages is more than 1, we
* ought to charge
* spc_random_page_cost + (pages_fetched - 1) * spc_seq_page_cost
* For partially-correlated indexes, we ought to charge somewhere between
* these two estimates. We currently interpolate linearly between the
* estimates based on the correlation squared (XXX is that appropriate?).
*
* If it's an index-only scan, then we will not need to fetch any heap
* pages for which the visibility map shows all tuples are visible.
* Hence, reduce the estimated number of heap fetches accordingly.
* We use the measured fraction of the entire heap that is all-visible,
* which might not be particularly relevant to the subset of the heap
* that this query will fetch; but it's not clear how to do better.
*----------
*/
if (loop_count > 1)
{
/*
* For repeated indexscans, the appropriate estimate for the
* uncorrelated case is to scale up the number of tuples fetched in
* the Mackert and Lohman formula by the number of scans, so that we
* estimate the number of pages fetched by all the scans; then
* pro-rate the costs for one scan. In this case we assume all the
* fetches are random accesses.
*/
pages_fetched = index_pages_fetched(tuples_fetched * loop_count,
baserel->pages,
(double) index->pages,
root);
if (indexonly)
pages_fetched = ceil(pages_fetched * (1.0 - baserel->allvisfrac));
rand_heap_pages = pages_fetched;
max_IO_cost = (pages_fetched * spc_random_page_cost) / loop_count;
/*
* In the perfectly correlated case, the number of pages touched by
* each scan is selectivity * table_size, and we can use the Mackert
* and Lohman formula at the page level to estimate how much work is
* saved by caching across scans. We still assume all the fetches are
* random, though, which is an overestimate that's hard to correct for
* without double-counting the cache effects. (But in most cases
* where such a plan is actually interesting, only one page would get
* fetched per scan anyway, so it shouldn't matter much.)
*/
pages_fetched = ceil(indexSelectivity * (double) baserel->pages);
pages_fetched = index_pages_fetched(pages_fetched * loop_count,
baserel->pages,
(double) index->pages,
root);
if (indexonly)
pages_fetched = ceil(pages_fetched * (1.0 - baserel->allvisfrac));
min_IO_cost = (pages_fetched * spc_random_page_cost) / loop_count;
}
else
{
/*
* Normal case: apply the Mackert and Lohman formula, and then
* interpolate between that and the correlation-derived result.
*/
pages_fetched = index_pages_fetched(tuples_fetched,
baserel->pages,
(double) index->pages,
root);
if (indexonly)
pages_fetched = ceil(pages_fetched * (1.0 - baserel->allvisfrac));
rand_heap_pages = pages_fetched;
/* max_IO_cost is for the perfectly uncorrelated case (csquared=0) */
max_IO_cost = pages_fetched * spc_random_page_cost;
/* min_IO_cost is for the perfectly correlated case (csquared=1) */
pages_fetched = ceil(indexSelectivity * (double) baserel->pages);
if (indexonly)
pages_fetched = ceil(pages_fetched * (1.0 - baserel->allvisfrac));
if (pages_fetched > 0)
{
min_IO_cost = spc_random_page_cost;
if (pages_fetched > 1)
min_IO_cost += (pages_fetched - 1) * spc_seq_page_cost;
}
else
min_IO_cost = 0;
}
if (partial_path)
{
/*
* For index only scans compute workers based on number of index pages
* fetched; the number of heap pages we fetch might be so small as to
* effectively rule out parallelism, which we don't want to do.
*/
if (indexonly)
rand_heap_pages = -1;
/*
* Estimate the number of parallel workers required to scan index. Use
* the number of heap pages computed considering heap fetches won't be
* sequential as for parallel scans the pages are accessed in random
* order.
*/
path->path.parallel_workers = compute_parallel_worker(baserel,
rand_heap_pages,
index_pages,
max_parallel_workers_per_gather);
/*
* Fall out if workers can't be assigned for parallel scan, because in
* such a case this path will be rejected. So there is no benefit in
* doing extra computation.
*/
if (path->path.parallel_workers <= 0)
return;
path->path.parallel_aware = true;
}
/*
* Now interpolate based on estimated index order correlation to get total
* disk I/O cost for main table accesses.
*/
csquared = indexCorrelation * indexCorrelation;
run_cost += max_IO_cost + csquared * (min_IO_cost - max_IO_cost);
/*
* Estimate CPU costs per tuple.
*
* What we want here is cpu_tuple_cost plus the evaluation costs of any
* qual clauses that we have to evaluate as qpquals.
*/
cost_qual_eval(&qpqual_cost, qpquals, root);
startup_cost += qpqual_cost.startup;
cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
cpu_run_cost += cpu_per_tuple * tuples_fetched;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->path.pathtarget->cost.startup;
cpu_run_cost += path->path.pathtarget->cost.per_tuple * path->path.rows;
/* Adjust costing for parallelism, if used. */
if (path->path.parallel_workers > 0)
{
double parallel_divisor = get_parallel_divisor(&path->path);
path->path.rows = clamp_row_est(path->path.rows / parallel_divisor);
/* The CPU cost is divided among all the workers. */
cpu_run_cost /= parallel_divisor;
}
run_cost += cpu_run_cost;
path->path.startup_cost = startup_cost;
path->path.total_cost = startup_cost + run_cost;
}
/*
* extract_nonindex_conditions
*
* Given a list of quals to be enforced in an indexscan, extract the ones that
* will have to be applied as qpquals (ie, the index machinery won't handle
* them). Here we detect only whether a qual clause is directly redundant
* with some indexclause. If the index path is chosen for use, createplan.c
* will try a bit harder to get rid of redundant qual conditions; specifically
* it will see if quals can be proven to be implied by the indexquals. But
* it does not seem worth the cycles to try to factor that in at this stage,
* since we're only trying to estimate qual eval costs. Otherwise this must
* match the logic in create_indexscan_plan().
*
* qual_clauses, and the result, are lists of RestrictInfos.
* indexclauses is a list of IndexClauses.
*/
static List *
extract_nonindex_conditions(List *qual_clauses, List *indexclauses)
{
List *result = NIL;
ListCell *lc;
foreach(lc, qual_clauses)
{
RestrictInfo *rinfo = lfirst_node(RestrictInfo, lc);
if (rinfo->pseudoconstant)
continue; /* we may drop pseudoconstants here */
if (is_redundant_with_indexclauses(rinfo, indexclauses))
continue; /* dup or derived from same EquivalenceClass */
/* ... skip the predicate proof attempt createplan.c will try ... */
result = lappend(result, rinfo);
}
return result;
}
/*
* index_pages_fetched
* Estimate the number of pages actually fetched after accounting for
* cache effects.
*
* We use an approximation proposed by Mackert and Lohman, "Index Scans
* Using a Finite LRU Buffer: A Validated I/O Model", ACM Transactions
* on Database Systems, Vol. 14, No. 3, September 1989, Pages 401-424.
* The Mackert and Lohman approximation is that the number of pages
* fetched is
* PF =
* min(2TNs/(2T+Ns), T) when T <= b
* 2TNs/(2T+Ns) when T > b and Ns <= 2Tb/(2T-b)
* b + (Ns - 2Tb/(2T-b))*(T-b)/T when T > b and Ns > 2Tb/(2T-b)
* where
* T = # pages in table
* N = # tuples in table
* s = selectivity = fraction of table to be scanned
* b = # buffer pages available (we include kernel space here)
*
* We assume that effective_cache_size is the total number of buffer pages
* available for the whole query, and pro-rate that space across all the
* tables in the query and the index currently under consideration. (This
* ignores space needed for other indexes used by the query, but since we
* don't know which indexes will get used, we can't estimate that very well;
* and in any case counting all the tables may well be an overestimate, since
* depending on the join plan not all the tables may be scanned concurrently.)
*
* The product Ns is the number of tuples fetched; we pass in that
* product rather than calculating it here. "pages" is the number of pages
* in the object under consideration (either an index or a table).
* "index_pages" is the amount to add to the total table space, which was
* computed for us by make_one_rel.
*
* Caller is expected to have ensured that tuples_fetched is greater than zero
* and rounded to integer (see clamp_row_est). The result will likewise be
* greater than zero and integral.
*/
double
index_pages_fetched(double tuples_fetched, BlockNumber pages,
double index_pages, PlannerInfo *root)
{
double pages_fetched;
double total_pages;
double T,
b;
/* T is # pages in table, but don't allow it to be zero */
T = (pages > 1) ? (double) pages : 1.0;
/* Compute number of pages assumed to be competing for cache space */
total_pages = root->total_table_pages + index_pages;
total_pages = Max(total_pages, 1.0);
Assert(T <= total_pages);
/* b is pro-rated share of effective_cache_size */
b = (double) effective_cache_size * T / total_pages;
/* force it positive and integral */
if (b <= 1.0)
b = 1.0;
else
b = ceil(b);
/* This part is the Mackert and Lohman formula */
if (T <= b)
{
pages_fetched =
(2.0 * T * tuples_fetched) / (2.0 * T + tuples_fetched);
if (pages_fetched >= T)
pages_fetched = T;
else
pages_fetched = ceil(pages_fetched);
}
else
{
double lim;
lim = (2.0 * T * b) / (2.0 * T - b);
if (tuples_fetched <= lim)
{
pages_fetched =
(2.0 * T * tuples_fetched) / (2.0 * T + tuples_fetched);
}
else
{
pages_fetched =
b + (tuples_fetched - lim) * (T - b) / T;
}
pages_fetched = ceil(pages_fetched);
}
return pages_fetched;
}
/*
* get_indexpath_pages
* Determine the total size of the indexes used in a bitmap index path.
*
* Note: if the same index is used more than once in a bitmap tree, we will
* count it multiple times, which perhaps is the wrong thing ... but it's
* not completely clear, and detecting duplicates is difficult, so ignore it
* for now.
*/
static double
get_indexpath_pages(Path *bitmapqual)
{
double result = 0;
ListCell *l;
if (IsA(bitmapqual, BitmapAndPath))
{
BitmapAndPath *apath = (BitmapAndPath *) bitmapqual;
foreach(l, apath->bitmapquals)
{
result += get_indexpath_pages((Path *) lfirst(l));
}
}
else if (IsA(bitmapqual, BitmapOrPath))
{
BitmapOrPath *opath = (BitmapOrPath *) bitmapqual;
foreach(l, opath->bitmapquals)
{
result += get_indexpath_pages((Path *) lfirst(l));
}
}
else if (IsA(bitmapqual, IndexPath))
{
IndexPath *ipath = (IndexPath *) bitmapqual;
result = (double) ipath->indexinfo->pages;
}
else
elog(ERROR, "unrecognized node type: %d", nodeTag(bitmapqual));
return result;
}
/*
* cost_bitmap_heap_scan
* Determines and returns the cost of scanning a relation using a bitmap
* index-then-heap plan.
*
* 'baserel' is the relation to be scanned
* 'param_info' is the ParamPathInfo if this is a parameterized path, else NULL
* 'bitmapqual' is a tree of IndexPaths, BitmapAndPaths, and BitmapOrPaths
* 'loop_count' is the number of repetitions of the indexscan to factor into
* estimates of caching behavior
*
* Note: the component IndexPaths in bitmapqual should have been costed
* using the same loop_count.
*/
void
cost_bitmap_heap_scan(Path *path, PlannerInfo *root, RelOptInfo *baserel,
ParamPathInfo *param_info,
Path *bitmapqual, double loop_count)
{
Cost startup_cost = 0;
Cost run_cost = 0;
Cost indexTotalCost;
QualCost qpqual_cost;
Cost cpu_per_tuple;
Cost cost_per_page;
Cost cpu_run_cost;
double tuples_fetched;
double pages_fetched;
double spc_seq_page_cost,
spc_random_page_cost;
double T;
/* Should only be applied to base relations */
Assert(IsA(baserel, RelOptInfo));
Assert(baserel->relid > 0);
Assert(baserel->rtekind == RTE_RELATION);
/* Mark the path with the correct row estimate */
if (param_info)
path->rows = param_info->ppi_rows;
else
path->rows = baserel->rows;
if (!enable_bitmapscan)
startup_cost += disable_cost;
pages_fetched = compute_bitmap_pages(root, baserel, bitmapqual,
loop_count, &indexTotalCost,
&tuples_fetched);
startup_cost += indexTotalCost;
T = (baserel->pages > 1) ? (double) baserel->pages : 1.0;
/* Fetch estimated page costs for tablespace containing table. */
get_tablespace_page_costs(baserel->reltablespace,
&spc_random_page_cost,
&spc_seq_page_cost);
/*
* For small numbers of pages we should charge spc_random_page_cost
* apiece, while if nearly all the table's pages are being read, it's more
* appropriate to charge spc_seq_page_cost apiece. The effect is
* nonlinear, too. For lack of a better idea, interpolate like this to
* determine the cost per page.
*/
if (pages_fetched >= 2.0)
cost_per_page = spc_random_page_cost -
(spc_random_page_cost - spc_seq_page_cost)
* sqrt(pages_fetched / T);
else
cost_per_page = spc_random_page_cost;
run_cost += pages_fetched * cost_per_page;
/*
* Estimate CPU costs per tuple.
*
* Often the indexquals don't need to be rechecked at each tuple ... but
* not always, especially not if there are enough tuples involved that the
* bitmaps become lossy. For the moment, just assume they will be
* rechecked always. This means we charge the full freight for all the
* scan clauses.
*/
get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
startup_cost += qpqual_cost.startup;
cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
cpu_run_cost = cpu_per_tuple * tuples_fetched;
/* Adjust costing for parallelism, if used. */
if (path->parallel_workers > 0)
{
double parallel_divisor = get_parallel_divisor(path);
/* The CPU cost is divided among all the workers. */
cpu_run_cost /= parallel_divisor;
path->rows = clamp_row_est(path->rows / parallel_divisor);
}
run_cost += cpu_run_cost;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->pathtarget->cost.startup;
run_cost += path->pathtarget->cost.per_tuple * path->rows;
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;
}
/*
* cost_bitmap_tree_node
* Extract cost and selectivity from a bitmap tree node (index/and/or)
*/
void
cost_bitmap_tree_node(Path *path, Cost *cost, Selectivity *selec)
{
if (IsA(path, IndexPath))
{
*cost = ((IndexPath *) path)->indextotalcost;
*selec = ((IndexPath *) path)->indexselectivity;
/*
* Charge a small amount per retrieved tuple to reflect the costs of
* manipulating the bitmap. This is mostly to make sure that a bitmap
* scan doesn't look to be the same cost as an indexscan to retrieve a
* single tuple.
*/
*cost += 0.1 * cpu_operator_cost * path->rows;
}
else if (IsA(path, BitmapAndPath))
{
*cost = path->total_cost;
*selec = ((BitmapAndPath *) path)->bitmapselectivity;
}
else if (IsA(path, BitmapOrPath))
{
*cost = path->total_cost;
*selec = ((BitmapOrPath *) path)->bitmapselectivity;
}
else
{
elog(ERROR, "unrecognized node type: %d", nodeTag(path));
*cost = *selec = 0; /* keep compiler quiet */
}
}
/*
* cost_bitmap_and_node
* Estimate the cost of a BitmapAnd node
*
* Note that this considers only the costs of index scanning and bitmap
* creation, not the eventual heap access. In that sense the object isn't
* truly a Path, but it has enough path-like properties (costs in particular)
* to warrant treating it as one. We don't bother to set the path rows field,
* however.
*/
void
cost_bitmap_and_node(BitmapAndPath *path, PlannerInfo *root)
{
Cost totalCost;
Selectivity selec;
ListCell *l;
/*
* We estimate AND selectivity on the assumption that the inputs are
* independent. This is probably often wrong, but we don't have the info
* to do better.
*
* The runtime cost of the BitmapAnd itself is estimated at 100x
* cpu_operator_cost for each tbm_intersect needed. Probably too small,
* definitely too simplistic?
*/
totalCost = 0.0;
selec = 1.0;
foreach(l, path->bitmapquals)
{
Path *subpath = (Path *) lfirst(l);
Cost subCost;
Selectivity subselec;
cost_bitmap_tree_node(subpath, &subCost, &subselec);
selec *= subselec;
totalCost += subCost;
if (l != list_head(path->bitmapquals))
totalCost += 100.0 * cpu_operator_cost;
}
path->bitmapselectivity = selec;
path->path.rows = 0; /* per above, not used */
path->path.startup_cost = totalCost;
path->path.total_cost = totalCost;
}
/*
* cost_bitmap_or_node
* Estimate the cost of a BitmapOr node
*
* See comments for cost_bitmap_and_node.
*/
void
cost_bitmap_or_node(BitmapOrPath *path, PlannerInfo *root)
{
Cost totalCost;
Selectivity selec;
ListCell *l;
/*
* We estimate OR selectivity on the assumption that the inputs are
* non-overlapping, since that's often the case in "x IN (list)" type
* situations. Of course, we clamp to 1.0 at the end.
*
* The runtime cost of the BitmapOr itself is estimated at 100x
* cpu_operator_cost for each tbm_union needed. Probably too small,
* definitely too simplistic? We are aware that the tbm_unions are
* optimized out when the inputs are BitmapIndexScans.
*/
totalCost = 0.0;
selec = 0.0;
foreach(l, path->bitmapquals)
{
Path *subpath = (Path *) lfirst(l);
Cost subCost;
Selectivity subselec;
cost_bitmap_tree_node(subpath, &subCost, &subselec);
selec += subselec;
totalCost += subCost;
if (l != list_head(path->bitmapquals) &&
!IsA(subpath, IndexPath))
totalCost += 100.0 * cpu_operator_cost;
}
path->bitmapselectivity = Min(selec, 1.0);
path->path.rows = 0; /* per above, not used */
path->path.startup_cost = totalCost;
path->path.total_cost = totalCost;
}
/*
* cost_tidscan
* Determines and returns the cost of scanning a relation using TIDs.
*
* 'baserel' is the relation to be scanned
* 'tidquals' is the list of TID-checkable quals
* 'param_info' is the ParamPathInfo if this is a parameterized path, else NULL
*/
void
cost_tidscan(Path *path, PlannerInfo *root,
RelOptInfo *baserel, List *tidquals, ParamPathInfo *param_info)
{
Cost startup_cost = 0;
Cost run_cost = 0;
bool isCurrentOf = false;
QualCost qpqual_cost;
Cost cpu_per_tuple;
QualCost tid_qual_cost;
int ntuples;
ListCell *l;
double spc_random_page_cost;
/* Should only be applied to base relations */
Assert(baserel->relid > 0);
Assert(baserel->rtekind == RTE_RELATION);
/* Mark the path with the correct row estimate */
if (param_info)
path->rows = param_info->ppi_rows;
else
path->rows = baserel->rows;
/* Count how many tuples we expect to retrieve */
ntuples = 0;
foreach(l, tidquals)
{
RestrictInfo *rinfo = lfirst_node(RestrictInfo, l);
Expr *qual = rinfo->clause;
if (IsA(qual, ScalarArrayOpExpr))
{
/* Each element of the array yields 1 tuple */
ScalarArrayOpExpr *saop = (ScalarArrayOpExpr *) qual;
Node *arraynode = (Node *) lsecond(saop->args);
ntuples += estimate_array_length(arraynode);
}
else if (IsA(qual, CurrentOfExpr))
{
/* CURRENT OF yields 1 tuple */
isCurrentOf = true;
ntuples++;
}
else
{
/* It's just CTID = something, count 1 tuple */
ntuples++;
}
}
/*
* We must force TID scan for WHERE CURRENT OF, because only nodeTidscan.c
* understands how to do it correctly. Therefore, honor enable_tidscan
* only when CURRENT OF isn't present. Also note that cost_qual_eval
* counts a CurrentOfExpr as having startup cost disable_cost, which we
* subtract off here; that's to prevent other plan types such as seqscan
* from winning.
*/
if (isCurrentOf)
{
Assert(baserel->baserestrictcost.startup >= disable_cost);
startup_cost -= disable_cost;
}
else if (!enable_tidscan)
startup_cost += disable_cost;
/*
* The TID qual expressions will be computed once, any other baserestrict
* quals once per retrieved tuple.
*/
cost_qual_eval(&tid_qual_cost, tidquals, root);
/* fetch estimated page cost for tablespace containing table */
get_tablespace_page_costs(baserel->reltablespace,
&spc_random_page_cost,
NULL);
/* disk costs --- assume each tuple on a different page */
run_cost += spc_random_page_cost * ntuples;
/* Add scanning CPU costs */
get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
/* XXX currently we assume TID quals are a subset of qpquals */
startup_cost += qpqual_cost.startup + tid_qual_cost.per_tuple;
cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple -
tid_qual_cost.per_tuple;
run_cost += cpu_per_tuple * ntuples;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->pathtarget->cost.startup;
run_cost += path->pathtarget->cost.per_tuple * path->rows;
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;
}
/*
* cost_tidrangescan
* Determines and sets the costs of scanning a relation using a range of
* TIDs for 'path'
*
* 'baserel' is the relation to be scanned
* 'tidrangequals' is the list of TID-checkable range quals
* 'param_info' is the ParamPathInfo if this is a parameterized path, else NULL
*/
void
cost_tidrangescan(Path *path, PlannerInfo *root,
RelOptInfo *baserel, List *tidrangequals,
ParamPathInfo *param_info)
{
Selectivity selectivity;
double pages;
Cost startup_cost = 0;
Cost run_cost = 0;
QualCost qpqual_cost;
Cost cpu_per_tuple;
QualCost tid_qual_cost;
double ntuples;
double nseqpages;
double spc_random_page_cost;
double spc_seq_page_cost;
/* Should only be applied to base relations */
Assert(baserel->relid > 0);
Assert(baserel->rtekind == RTE_RELATION);
/* Mark the path with the correct row estimate */
if (param_info)
path->rows = param_info->ppi_rows;
else
path->rows = baserel->rows;
/* Count how many tuples and pages we expect to scan */
selectivity = clauselist_selectivity(root, tidrangequals, baserel->relid,
JOIN_INNER, NULL);
pages = ceil(selectivity * baserel->pages);
if (pages <= 0.0)
pages = 1.0;
/*
* The first page in a range requires a random seek, but each subsequent
* page is just a normal sequential page read. NOTE: it's desirable for
* TID Range Scans to cost more than the equivalent Sequential Scans,
* because Seq Scans have some performance advantages such as scan
* synchronization and parallelizability, and we'd prefer one of them to
* be picked unless a TID Range Scan really is better.
*/
ntuples = selectivity * baserel->tuples;
nseqpages = pages - 1.0;
if (!enable_tidscan)
startup_cost += disable_cost;
/*
* The TID qual expressions will be computed once, any other baserestrict
* quals once per retrieved tuple.
*/
cost_qual_eval(&tid_qual_cost, tidrangequals, root);
/* fetch estimated page cost for tablespace containing table */
get_tablespace_page_costs(baserel->reltablespace,
&spc_random_page_cost,
&spc_seq_page_cost);
/* disk costs; 1 random page and the remainder as seq pages */
run_cost += spc_random_page_cost + spc_seq_page_cost * nseqpages;
/* Add scanning CPU costs */
get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
/*
* XXX currently we assume TID quals are a subset of qpquals at this
* point; they will be removed (if possible) when we create the plan, so
* we subtract their cost from the total qpqual cost. (If the TID quals
* can't be removed, this is a mistake and we're going to underestimate
* the CPU cost a bit.)
*/
startup_cost += qpqual_cost.startup + tid_qual_cost.per_tuple;
cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple -
tid_qual_cost.per_tuple;
run_cost += cpu_per_tuple * ntuples;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->pathtarget->cost.startup;
run_cost += path->pathtarget->cost.per_tuple * path->rows;
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;
}
/*
* cost_subqueryscan
* Determines and returns the cost of scanning a subquery RTE.
*
* 'baserel' is the relation to be scanned
* 'param_info' is the ParamPathInfo if this is a parameterized path, else NULL
* 'trivial_pathtarget' is true if the pathtarget is believed to be trivial.
*/
void
cost_subqueryscan(SubqueryScanPath *path, PlannerInfo *root,
RelOptInfo *baserel, ParamPathInfo *param_info,
bool trivial_pathtarget)
{
Cost startup_cost;
Cost run_cost;
List *qpquals;
QualCost qpqual_cost;
Cost cpu_per_tuple;
/* Should only be applied to base relations that are subqueries */
Assert(baserel->relid > 0);
Assert(baserel->rtekind == RTE_SUBQUERY);
/*
* We compute the rowcount estimate as the subplan's estimate times the
* selectivity of relevant restriction clauses. In simple cases this will
* come out the same as baserel->rows; but when dealing with parallelized
* paths we must do it like this to get the right answer.
*/
if (param_info)
qpquals = list_concat_copy(param_info->ppi_clauses,
baserel->baserestrictinfo);
else
qpquals = baserel->baserestrictinfo;
path->path.rows = clamp_row_est(path->subpath->rows *
clauselist_selectivity(root,
qpquals,
0,
JOIN_INNER,
NULL));
/*
* Cost of path is cost of evaluating the subplan, plus cost of evaluating
* any restriction clauses and tlist that will be attached to the
* SubqueryScan node, plus cpu_tuple_cost to account for selection and
* projection overhead.
*/
path->path.startup_cost = path->subpath->startup_cost;
path->path.total_cost = path->subpath->total_cost;
/*
* However, if there are no relevant restriction clauses and the
* pathtarget is trivial, then we expect that setrefs.c will optimize away
* the SubqueryScan plan node altogether, so we should just make its cost
* and rowcount equal to the input path's.
*
* Note: there are some edge cases where createplan.c will apply a
* different targetlist to the SubqueryScan node, thus falsifying our
* current estimate of whether the target is trivial, and making the cost
* estimate (though not the rowcount) wrong. It does not seem worth the
* extra complication to try to account for that exactly, especially since
* that behavior falsifies other cost estimates as well.
*/
if (qpquals == NIL && trivial_pathtarget)
return;
get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
startup_cost = qpqual_cost.startup;
cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
run_cost = cpu_per_tuple * path->subpath->rows;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->path.pathtarget->cost.startup;
run_cost += path->path.pathtarget->cost.per_tuple * path->path.rows;
path->path.startup_cost += startup_cost;
path->path.total_cost += startup_cost + run_cost;
}
/*
* cost_functionscan
* Determines and returns the cost of scanning a function RTE.
*
* 'baserel' is the relation to be scanned
* 'param_info' is the ParamPathInfo if this is a parameterized path, else NULL
*/
void
cost_functionscan(Path *path, PlannerInfo *root,
RelOptInfo *baserel, ParamPathInfo *param_info)
{
Cost startup_cost = 0;
Cost run_cost = 0;
QualCost qpqual_cost;
Cost cpu_per_tuple;
RangeTblEntry *rte;
QualCost exprcost;
/* Should only be applied to base relations that are functions */
Assert(baserel->relid > 0);
rte = planner_rt_fetch(baserel->relid, root);
Assert(rte->rtekind == RTE_FUNCTION);
/* Mark the path with the correct row estimate */
if (param_info)
path->rows = param_info->ppi_rows;
else
path->rows = baserel->rows;
/*
* Estimate costs of executing the function expression(s).
*
* Currently, nodeFunctionscan.c always executes the functions to
* completion before returning any rows, and caches the results in a
* tuplestore. So the function eval cost is all startup cost, and per-row
* costs are minimal.
*
* XXX in principle we ought to charge tuplestore spill costs if the
* number of rows is large. However, given how phony our rowcount
* estimates for functions tend to be, there's not a lot of point in that
* refinement right now.
*/
cost_qual_eval_node(&exprcost, (Node *) rte->functions, root);
startup_cost += exprcost.startup + exprcost.per_tuple;
/* Add scanning CPU costs */
get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
startup_cost += qpqual_cost.startup;
cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
run_cost += cpu_per_tuple * baserel->tuples;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->pathtarget->cost.startup;
run_cost += path->pathtarget->cost.per_tuple * path->rows;
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;
}
/*
* cost_tablefuncscan
* Determines and returns the cost of scanning a table function.
*
* 'baserel' is the relation to be scanned
* 'param_info' is the ParamPathInfo if this is a parameterized path, else NULL
*/
void
cost_tablefuncscan(Path *path, PlannerInfo *root,
RelOptInfo *baserel, ParamPathInfo *param_info)
{
Cost startup_cost = 0;
Cost run_cost = 0;
QualCost qpqual_cost;
Cost cpu_per_tuple;
RangeTblEntry *rte;
QualCost exprcost;
/* Should only be applied to base relations that are functions */
Assert(baserel->relid > 0);
rte = planner_rt_fetch(baserel->relid, root);
Assert(rte->rtekind == RTE_TABLEFUNC);
/* Mark the path with the correct row estimate */
if (param_info)
path->rows = param_info->ppi_rows;
else
path->rows = baserel->rows;
/*
* Estimate costs of executing the table func expression(s).
*
* XXX in principle we ought to charge tuplestore spill costs if the
* number of rows is large. However, given how phony our rowcount
* estimates for tablefuncs tend to be, there's not a lot of point in that
* refinement right now.
*/
cost_qual_eval_node(&exprcost, (Node *) rte->tablefunc, root);
startup_cost += exprcost.startup + exprcost.per_tuple;
/* Add scanning CPU costs */
get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
startup_cost += qpqual_cost.startup;
cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
run_cost += cpu_per_tuple * baserel->tuples;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->pathtarget->cost.startup;
run_cost += path->pathtarget->cost.per_tuple * path->rows;
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;
}
/*
* cost_valuesscan
* Determines and returns the cost of scanning a VALUES RTE.
*
* 'baserel' is the relation to be scanned
* 'param_info' is the ParamPathInfo if this is a parameterized path, else NULL
*/
void
cost_valuesscan(Path *path, PlannerInfo *root,
RelOptInfo *baserel, ParamPathInfo *param_info)
{
Cost startup_cost = 0;
Cost run_cost = 0;
QualCost qpqual_cost;
Cost cpu_per_tuple;
/* Should only be applied to base relations that are values lists */
Assert(baserel->relid > 0);
Assert(baserel->rtekind == RTE_VALUES);
/* Mark the path with the correct row estimate */
if (param_info)
path->rows = param_info->ppi_rows;
else
path->rows = baserel->rows;
/*
* For now, estimate list evaluation cost at one operator eval per list
* (probably pretty bogus, but is it worth being smarter?)
*/
cpu_per_tuple = cpu_operator_cost;
/* Add scanning CPU costs */
get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
startup_cost += qpqual_cost.startup;
cpu_per_tuple += cpu_tuple_cost + qpqual_cost.per_tuple;
run_cost += cpu_per_tuple * baserel->tuples;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->pathtarget->cost.startup;
run_cost += path->pathtarget->cost.per_tuple * path->rows;
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;
}
/*
* cost_ctescan
* Determines and returns the cost of scanning a CTE RTE.
*
* Note: this is used for both self-reference and regular CTEs; the
* possible cost differences are below the threshold of what we could
* estimate accurately anyway. Note that the costs of evaluating the
* referenced CTE query are added into the final plan as initplan costs,
* and should NOT be counted here.
*/
void
cost_ctescan(Path *path, PlannerInfo *root,
RelOptInfo *baserel, ParamPathInfo *param_info)
{
Cost startup_cost = 0;
Cost run_cost = 0;
QualCost qpqual_cost;
Cost cpu_per_tuple;
/* Should only be applied to base relations that are CTEs */
Assert(baserel->relid > 0);
Assert(baserel->rtekind == RTE_CTE);
/* Mark the path with the correct row estimate */
if (param_info)
path->rows = param_info->ppi_rows;
else
path->rows = baserel->rows;
/* Charge one CPU tuple cost per row for tuplestore manipulation */
cpu_per_tuple = cpu_tuple_cost;
/* Add scanning CPU costs */
get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
startup_cost += qpqual_cost.startup;
cpu_per_tuple += cpu_tuple_cost + qpqual_cost.per_tuple;
run_cost += cpu_per_tuple * baserel->tuples;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->pathtarget->cost.startup;
run_cost += path->pathtarget->cost.per_tuple * path->rows;
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;
}
/*
* cost_namedtuplestorescan
* Determines and returns the cost of scanning a named tuplestore.
*/
void
cost_namedtuplestorescan(Path *path, PlannerInfo *root,
RelOptInfo *baserel, ParamPathInfo *param_info)
{
Cost startup_cost = 0;
Cost run_cost = 0;
QualCost qpqual_cost;
Cost cpu_per_tuple;
/* Should only be applied to base relations that are Tuplestores */
Assert(baserel->relid > 0);
Assert(baserel->rtekind == RTE_NAMEDTUPLESTORE);
/* Mark the path with the correct row estimate */
if (param_info)
path->rows = param_info->ppi_rows;
else
path->rows = baserel->rows;
/* Charge one CPU tuple cost per row for tuplestore manipulation */
cpu_per_tuple = cpu_tuple_cost;
/* Add scanning CPU costs */
get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
startup_cost += qpqual_cost.startup;
cpu_per_tuple += cpu_tuple_cost + qpqual_cost.per_tuple;
run_cost += cpu_per_tuple * baserel->tuples;
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;
}
/*
* cost_resultscan
* Determines and returns the cost of scanning an RTE_RESULT relation.
*/
void
cost_resultscan(Path *path, PlannerInfo *root,
RelOptInfo *baserel, ParamPathInfo *param_info)
{
Cost startup_cost = 0;
Cost run_cost = 0;
QualCost qpqual_cost;
Cost cpu_per_tuple;
/* Should only be applied to RTE_RESULT base relations */
Assert(baserel->relid > 0);
Assert(baserel->rtekind == RTE_RESULT);
/* Mark the path with the correct row estimate */
if (param_info)
path->rows = param_info->ppi_rows;
else
path->rows = baserel->rows;
/* We charge qual cost plus cpu_tuple_cost */
get_restriction_qual_cost(root, baserel, param_info, &qpqual_cost);
startup_cost += qpqual_cost.startup;
cpu_per_tuple = cpu_tuple_cost + qpqual_cost.per_tuple;
run_cost += cpu_per_tuple * baserel->tuples;
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;
}
/*
* cost_recursive_union
* Determines and returns the cost of performing a recursive union,
* and also the estimated output size.
*
* We are given Paths for the nonrecursive and recursive terms.
*/
void
cost_recursive_union(Path *runion, Path *nrterm, Path *rterm)
{
Cost startup_cost;
Cost total_cost;
double total_rows;
/* We probably have decent estimates for the non-recursive term */
startup_cost = nrterm->startup_cost;
total_cost = nrterm->total_cost;
total_rows = nrterm->rows;
/*
* We arbitrarily assume that about 10 recursive iterations will be
* needed, and that we've managed to get a good fix on the cost and output
* size of each one of them. These are mighty shaky assumptions but it's
* hard to see how to do better.
*/
total_cost += 10 * rterm->total_cost;
total_rows += 10 * rterm->rows;
/*
* Also charge cpu_tuple_cost per row to account for the costs of
* manipulating the tuplestores. (We don't worry about possible
* spill-to-disk costs.)
*/
total_cost += cpu_tuple_cost * total_rows;
runion->startup_cost = startup_cost;
runion->total_cost = total_cost;
runion->rows = total_rows;
runion->pathtarget->width = Max(nrterm->pathtarget->width,
rterm->pathtarget->width);
}
/*
* is_fake_var
* Workaround for generate_append_tlist() which generates fake Vars with
* varno == 0, that will cause a fail of estimate_num_group() call
*
* XXX Ummm, why would estimate_num_group fail with this?
*/
static bool
is_fake_var(Expr *expr)
{
if (IsA(expr, RelabelType))
expr = (Expr *) ((RelabelType *) expr)->arg;
return (IsA(expr, Var) && ((Var *) expr)->varno == 0);
}
/*
* get_width_cost_multiplier
* Returns relative complexity of comparing two values based on its width.
* The idea behind is that the comparison becomes more expensive the longer the
* value is. Return value is in cpu_operator_cost units.
*/
static double
get_width_cost_multiplier(PlannerInfo *root, Expr *expr)
{
double width = -1.0; /* fake value */
if (IsA(expr, RelabelType))
expr = (Expr *) ((RelabelType *) expr)->arg;
/* Try to find actual stat in corresponding relation */
if (IsA(expr, Var))
{
Var *var = (Var *) expr;
if (var->varno > 0 && var->varno < root->simple_rel_array_size)
{
RelOptInfo *rel = root->simple_rel_array[var->varno];
if (rel != NULL &&
var->varattno >= rel->min_attr &&
var->varattno <= rel->max_attr)
{
int ndx = var->varattno - rel->min_attr;
if (rel->attr_widths[ndx] > 0)
width = rel->attr_widths[ndx];
}
}
}
/* Didn't find any actual stats, try using type width instead. */
if (width < 0.0)
{
Node *node = (Node *) expr;
width = get_typavgwidth(exprType(node), exprTypmod(node));
}
/*
* Values are passed as Datum type, so comparisons can't be cheaper than
* comparing a Datum value.
*
* FIXME I find this reasoning questionable. We may pass int2, and
* comparing it is probably a bit cheaper than comparing a bigint.
*/
if (width <= sizeof(Datum))
return 1.0;
/*
* We consider the cost of a comparison not to be directly proportional to
* width of the argument, because widths of the arguments could be
* slightly different (we only know the average width for the whole
* column). So we use log16(width) as an estimate.
*/
return 1.0 + 0.125 * LOG2(width / sizeof(Datum));
}
/*
* compute_cpu_sort_cost
* compute CPU cost of sort (i.e. in-memory)
*
* The main thing we need to calculate to estimate sort CPU costs is the number
* of calls to the comparator functions. The difficulty is that for multi-column
* sorts there may be different data types involved (for some of which the calls
* may be much more expensive). Furthermore, columns may have a very different
* number of distinct values - the higher the number, the fewer comparisons will
* be needed for the following columns.
*
* The algorithm is incremental - we add pathkeys one by one, and at each step we
* estimate the number of necessary comparisons (based on the number of distinct
* groups in the current pathkey prefix and the new pathkey), and the comparison
* costs (which is data type specific).
*
* Estimation of the number of comparisons is based on ideas from:
*
* "Quicksort Is Optimal", Robert Sedgewick, Jon Bentley, 2002
* [https://www.cs.princeton.edu/~rs/talks/QuicksortIsOptimal.pdf]
*
* In term of that paper, let N - number of tuples, Xi - number of identical
* tuples with value Ki, then the estimate of number of comparisons is:
*
* log(N! / (X1! * X2! * ..)) ~ sum(Xi * log(N/Xi))
*
* We assume all Xi the same because now we don't have any estimation of
* group sizes, we have only know the estimate of number of groups (distinct
* values). In that case, formula becomes:
*
* N * log(NumberOfGroups)
*
* For multi-column sorts we need to estimate the number of comparisons for
* each individual column - for example with columns (c1, c2, ..., ck) we
* can estimate that number of comparisons on ck is roughly
*
* ncomparisons(c1, c2, ..., ck) / ncomparisons(c1, c2, ..., c(k-1))
*
* Let k be a column number, Gk - number of groups defined by k columns, and Fk
* the cost of the comparison is
*
* N * sum( Fk * log(Gk) )
*
* Note: We also consider column width, not just the comparator cost.
*
* NOTE: some callers currently pass NIL for pathkeys because they
* can't conveniently supply the sort keys. In this case, it will fallback to
* simple comparison cost estimate.
*/
static Cost
compute_cpu_sort_cost(PlannerInfo *root, List *pathkeys, int nPresortedKeys,
Cost comparison_cost, double tuples, double output_tuples,
bool heapSort)
{
Cost per_tuple_cost = 0.0;
ListCell *lc;
List *pathkeyExprs = NIL;
double tuplesPerPrevGroup = tuples;
double totalFuncCost = 1.0;
bool has_fake_var = false;
int i = 0;
Oid prev_datatype = InvalidOid;
List *cache_varinfos = NIL;
/* fallback if pathkeys is unknown */
if (pathkeys == NIL)
{
/*
* If we'll use a bounded heap-sort keeping just K tuples in memory,
* for a total number of tuple comparisons of N log2 K; but the
* constant factor is a bit higher than for quicksort. Tweak it so
* that the cost curve is continuous at the crossover point.
*/
output_tuples = (heapSort) ? 2.0 * output_tuples : tuples;
per_tuple_cost += 2.0 * cpu_operator_cost * LOG2(output_tuples);
/* add cost provided by caller */
per_tuple_cost += comparison_cost;
return per_tuple_cost * tuples;
}
/*
* Computing total cost of sorting takes into account the per-column
* comparison function cost. We try to compute the needed number of
* comparisons per column.
*/
foreach(lc, pathkeys)
{
PathKey *pathkey = (PathKey *) lfirst(lc);
EquivalenceMember *em;
double nGroups,
correctedNGroups;
Cost funcCost = 1.0;
/*
* We believe that equivalence members aren't very different, so, to
* estimate cost we consider just the first member.
*/
em = (EquivalenceMember *) linitial(pathkey->pk_eclass->ec_members);
if (em->em_datatype != InvalidOid)
{
/* do not lookup funcCost if the data type is the same */
if (prev_datatype != em->em_datatype)
{
Oid sortop;
QualCost cost;
sortop = get_opfamily_member(pathkey->pk_opfamily,
em->em_datatype, em->em_datatype,
pathkey->pk_strategy);
cost.startup = 0;
cost.per_tuple = 0;
add_function_cost(root, get_opcode(sortop), NULL, &cost);
/*
* add_function_cost returns the product of cpu_operator_cost
* and procost, but we need just procost, co undo that.
*/
funcCost = cost.per_tuple / cpu_operator_cost;
prev_datatype = em->em_datatype;
}
}
/* factor in the width of the values in this column */
funcCost *= get_width_cost_multiplier(root, em->em_expr);
/* now we have per-key cost, so add to the running total */
totalFuncCost += funcCost;
/* remember if we have found a fake Var in pathkeys */
has_fake_var |= is_fake_var(em->em_expr);
pathkeyExprs = lappend(pathkeyExprs, em->em_expr);
/*
* We need to calculate the number of comparisons for this column,
* which requires knowing the group size. So we estimate the number of
* groups by calling estimate_num_groups_incremental(), which
* estimates the group size for "new" pathkeys.
*
* Note: estimate_num_groups_incremental does not handle fake Vars, so
* use a default estimate otherwise.
*/
if (!has_fake_var)
nGroups = estimate_num_groups_incremental(root, pathkeyExprs,
tuplesPerPrevGroup, NULL, NULL,
&cache_varinfos,
list_length(pathkeyExprs) - 1);
else if (tuples > 4.0)
/*
* Use geometric mean as estimation if there are no stats.
*
* We don't use DEFAULT_NUM_DISTINCT here, because that's used for
* a single column, but here we're dealing with multiple columns.
*/
nGroups = ceil(2.0 + sqrt(tuples) * (i + 1) / list_length(pathkeys));
else
nGroups = tuples;
/*
* Presorted keys are not considered in the cost above, but we still
* do have to compare them in the qsort comparator. So make sure to
* factor in the cost in that case.
*/
if (i >= nPresortedKeys)
{
if (heapSort)
{
/*
* have to keep at least one group, and a multiple of group
* size
*/
correctedNGroups = ceil(output_tuples / tuplesPerPrevGroup);
}
else
/* all groups in the input */
correctedNGroups = nGroups;
correctedNGroups = Max(1.0, ceil(correctedNGroups));
per_tuple_cost += totalFuncCost * LOG2(correctedNGroups);
}
i++;
/*
* Uniform distributions with all groups being of the same size are
* the best case, with nice smooth behavior. Real-world distributions
* tend not to be uniform, though, and we don't have any reliable
* easy-to-use information. As a basic defense against skewed
* distributions, we use a 1.5 factor to make the expected group a bit
* larger, but we need to be careful not to make the group larger than
* in the preceding step.
*/
tuplesPerPrevGroup = Min(tuplesPerPrevGroup,
ceil(1.5 * tuplesPerPrevGroup / nGroups));
/*
* Once we get single-row group, it means tuples in the group are
* unique and we can skip all remaining columns.
*/
if (tuplesPerPrevGroup <= 1.0)
break;
}
list_free(pathkeyExprs);
/* per_tuple_cost is in cpu_operator_cost units */
per_tuple_cost *= cpu_operator_cost;
/*
* Accordingly to "Introduction to algorithms", Thomas H. Cormen, Charles
* E. Leiserson, Ronald L. Rivest, ISBN 0-07-013143-0, quicksort
* estimation formula has additional term proportional to number of tuples
* (see Chapter 8.2 and Theorem 4.1). That affects cases with a low number
* of tuples, approximately less than 1e4. We could implement it as an
* additional multiplier under the logarithm, but we use a bit more
* complex formula which takes into account the number of unique tuples
* and it's not clear how to combine the multiplier with the number of
* groups. Estimate it as 10 cpu_operator_cost units.
*/
per_tuple_cost += 10 * cpu_operator_cost;
per_tuple_cost += comparison_cost;
return tuples * per_tuple_cost;
}
/*
* simple wrapper just to estimate best sort path
*/
Cost
cost_sort_estimate(PlannerInfo *root, List *pathkeys, int nPresortedKeys,
double tuples)
{
return compute_cpu_sort_cost(root, pathkeys, nPresortedKeys,
0, tuples, tuples, false);
}
/*
* cost_tuplesort
* Determines and returns the cost of sorting a relation using tuplesort,
* not including the cost of reading the input data.
*
* If the total volume of data to sort is less than sort_mem, we will do
* an in-memory sort, which requires no I/O and about t*log2(t) tuple
* comparisons for t tuples.
*
* If the total volume exceeds sort_mem, we switch to a tape-style merge
* algorithm. There will still be about t*log2(t) tuple comparisons in
* total, but we will also need to write and read each tuple once per
* merge pass. We expect about ceil(logM(r)) merge passes where r is the
* number of initial runs formed and M is the merge order used by tuplesort.c.
* Since the average initial run should be about sort_mem, we have
* disk traffic = 2 * relsize * ceil(logM(p / sort_mem))
* and cpu cost (computed by compute_cpu_sort_cost()).
*
* If the sort is bounded (i.e., only the first k result tuples are needed)
* and k tuples can fit into sort_mem, we use a heap method that keeps only
* k tuples in the heap; this will require about t*log2(k) tuple comparisons.
*
* The disk traffic is assumed to be 3/4ths sequential and 1/4th random
* accesses (XXX can't we refine that guess?)
*
* By default, we charge two operator evals per tuple comparison, which should
* be in the right ballpark in most cases. The caller can tweak this by
* specifying nonzero comparison_cost; typically that's used for any extra
* work that has to be done to prepare the inputs to the comparison operators.
*
* 'tuples' is the number of tuples in the relation
* 'width' is the average tuple width in bytes
* 'comparison_cost' is the extra cost per comparison, if any
* 'sort_mem' is the number of kilobytes of work memory allowed for the sort
* 'limit_tuples' is the bound on the number of output tuples; -1 if no bound
* 'startup_cost' is expected to be 0 at input. If there is "input cost" it should
* be added by caller later
*/
static void
cost_tuplesort(PlannerInfo *root, List *pathkeys, Cost *startup_cost, Cost *run_cost,
double tuples, int width,
Cost comparison_cost, int sort_mem,
double limit_tuples)
{
double input_bytes = relation_byte_size(tuples, width);
double output_bytes;
double output_tuples;
long sort_mem_bytes = sort_mem * 1024L;
/*
* We want to be sure the cost of a sort is never estimated as zero, even
* if passed-in tuple count is zero. Besides, mustn't do log(0)...
*/
if (tuples < 2.0)
tuples = 2.0;
/* Do we have a useful LIMIT? */
if (limit_tuples > 0 && limit_tuples < tuples)
{
output_tuples = limit_tuples;
output_bytes = relation_byte_size(output_tuples, width);
}
else
{
output_tuples = tuples;
output_bytes = input_bytes;
}
if (output_bytes > sort_mem_bytes)
{
/*
* We'll have to use a disk-based sort of all the tuples
*/
double npages = ceil(input_bytes / BLCKSZ);
double nruns = input_bytes / sort_mem_bytes;
double mergeorder = tuplesort_merge_order(sort_mem_bytes);
double log_runs;
double npageaccesses;
/* CPU costs */
*startup_cost = compute_cpu_sort_cost(root, pathkeys, 0,
comparison_cost, tuples,
tuples, false);
/* Disk costs */
/* Compute logM(r) as log(r) / log(M) */
if (nruns > mergeorder)
log_runs = ceil(log(nruns) / log(mergeorder));
else
log_runs = 1.0;
npageaccesses = 2.0 * npages * log_runs;
/* Assume 3/4ths of accesses are sequential, 1/4th are not */
*startup_cost += npageaccesses *
(seq_page_cost * 0.75 + random_page_cost * 0.25);
}
else if (tuples > 2 * output_tuples || input_bytes > sort_mem_bytes)
{
/* We'll use a bounded heap-sort keeping just K tuples in memory. */
*startup_cost = compute_cpu_sort_cost(root, pathkeys, 0,
comparison_cost, tuples,
output_tuples, true);
}
else
{
/* We'll use plain quicksort on all the input tuples */
*startup_cost = compute_cpu_sort_cost(root, pathkeys, 0,
comparison_cost, tuples,
tuples, false);
}
/*
* Also charge a small amount (arbitrarily set equal to operator cost) per
* extracted tuple. We don't charge cpu_tuple_cost because a Sort node
* doesn't do qual-checking or projection, so it has less overhead than
* most plan nodes. Note it's correct to use tuples not output_tuples
* here --- the upper LIMIT will pro-rate the run cost so we'd be double
* counting the LIMIT otherwise.
*/
*run_cost = cpu_operator_cost * tuples;
}
/*
* cost_incremental_sort
* Determines and returns the cost of sorting a relation incrementally, when
* the input path is presorted by a prefix of the pathkeys.
*
* 'presorted_keys' is the number of leading pathkeys by which the input path
* is sorted.
*
* We estimate the number of groups into which the relation is divided by the
* leading pathkeys, and then calculate the cost of sorting a single group
* with tuplesort using cost_tuplesort().
*/
void
cost_incremental_sort(Path *path,
PlannerInfo *root, List *pathkeys, int presorted_keys,
Cost input_startup_cost, Cost input_total_cost,
double input_tuples, int width, Cost comparison_cost, int sort_mem,
double limit_tuples)
{
Cost startup_cost,
run_cost,
input_run_cost = input_total_cost - input_startup_cost;
double group_tuples,
input_groups;
Cost group_startup_cost,
group_run_cost,
group_input_run_cost;
List *presortedExprs = NIL;
ListCell *l;
int i = 0;
bool unknown_varno = false;
Assert(presorted_keys != 0);
/*
* We want to be sure the cost of a sort is never estimated as zero, even
* if passed-in tuple count is zero. Besides, mustn't do log(0)...
*/
if (input_tuples < 2.0)
input_tuples = 2.0;
/* Default estimate of number of groups, capped to one group per row. */
input_groups = Min(input_tuples, DEFAULT_NUM_DISTINCT);
/*
* Extract presorted keys as list of expressions.
*
* We need to be careful about Vars containing "varno 0" which might have
* been introduced by generate_append_tlist, which would confuse
* estimate_num_groups (in fact it'd fail for such expressions). See
* recurse_set_operations which has to deal with the same issue.
*
* Unlike recurse_set_operations we can't access the original target list
* here, and even if we could it's not very clear how useful would that be
* for a set operation combining multiple tables. So we simply detect if
* there are any expressions with "varno 0" and use the default
* DEFAULT_NUM_DISTINCT in that case.
*
* We might also use either 1.0 (a single group) or input_tuples (each row
* being a separate group), pretty much the worst and best case for
* incremental sort. But those are extreme cases and using something in
* between seems reasonable. Furthermore, generate_append_tlist is used
* for set operations, which are likely to produce mostly unique output
* anyway - from that standpoint the DEFAULT_NUM_DISTINCT is defensive
* while maintaining lower startup cost.
*/
foreach(l, pathkeys)
{
PathKey *key = (PathKey *) lfirst(l);
EquivalenceMember *member = (EquivalenceMember *)
linitial(key->pk_eclass->ec_members);
/*
* Check if the expression contains Var with "varno 0" so that we
* don't call estimate_num_groups in that case.
*/
if (bms_is_member(0, pull_varnos(root, (Node *) member->em_expr)))
{
unknown_varno = true;
break;
}
/* expression not containing any Vars with "varno 0" */
presortedExprs = lappend(presortedExprs, member->em_expr);
i++;
if (i >= presorted_keys)
break;
}
/* Estimate number of groups with equal presorted keys. */
if (!unknown_varno)
input_groups = estimate_num_groups(root, presortedExprs, input_tuples,
NULL, NULL);
group_tuples = input_tuples / input_groups;
group_input_run_cost = input_run_cost / input_groups;
/*
* Estimate average cost of sorting of one group where presorted keys are
* equal. Incremental sort is sensitive to distribution of tuples to the
* groups, where we're relying on quite rough assumptions. Thus, we're
* pessimistic about incremental sort performance and increase its average
* group size by half.
*/
cost_tuplesort(root, pathkeys, &group_startup_cost, &group_run_cost,
1.5 * group_tuples, width, comparison_cost, sort_mem,
limit_tuples);
/*
* Startup cost of incremental sort is the startup cost of its first group
* plus the cost of its input.
*/
startup_cost = group_startup_cost
+ input_startup_cost + group_input_run_cost;
/*
* After we started producing tuples from the first group, the cost of
* producing all the tuples is given by the cost to finish processing this
* group, plus the total cost to process the remaining groups, plus the
* remaining cost of input.
*/
run_cost = group_run_cost
+ (group_run_cost + group_startup_cost) * (input_groups - 1)
+ group_input_run_cost * (input_groups - 1);
/*
* Incremental sort adds some overhead by itself. Firstly, it has to
* detect the sort groups. This is roughly equal to one extra copy and
* comparison per tuple. Secondly, it has to reset the tuplesort context
* for every group.
*/
run_cost += (cpu_tuple_cost + comparison_cost) * input_tuples;
run_cost += 2.0 * cpu_tuple_cost * input_groups;
path->rows = input_tuples;
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;
}
/*
* cost_sort
* Determines and returns the cost of sorting a relation, including
* the cost of reading the input data.
*
* NOTE: some callers currently pass NIL for pathkeys because they
* can't conveniently supply the sort keys. Since this routine doesn't
* currently do anything with pathkeys anyway, that doesn't matter...
* but if it ever does, it should react gracefully to lack of key data.
* (Actually, the thing we'd most likely be interested in is just the number
* of sort keys, which all callers *could* supply.)
*/
void
cost_sort(Path *path, PlannerInfo *root,
List *pathkeys, Cost input_cost, double tuples, int width,
Cost comparison_cost, int sort_mem,
double limit_tuples)
{
Cost startup_cost;
Cost run_cost;
cost_tuplesort(root, pathkeys, &startup_cost, &run_cost,
tuples, width,
comparison_cost, sort_mem,
limit_tuples);
if (!enable_sort)
startup_cost += disable_cost;
startup_cost += input_cost;
path->rows = tuples;
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;
}
/*
* append_nonpartial_cost
* Estimate the cost of the non-partial paths in a Parallel Append.
* The non-partial paths are assumed to be the first "numpaths" paths
* from the subpaths list, and to be in order of decreasing cost.
*/
static Cost
append_nonpartial_cost(List *subpaths, int numpaths, int parallel_workers)
{
Cost *costarr;
int arrlen;
ListCell *l;
ListCell *cell;
int i;
int path_index;
int min_index;
int max_index;
if (numpaths == 0)
return 0;
/*
* Array length is number of workers or number of relevant paths,
* whichever is less.
*/
arrlen = Min(parallel_workers, numpaths);
costarr = (Cost *) palloc(sizeof(Cost) * arrlen);
/* The first few paths will each be claimed by a different worker. */
path_index = 0;
foreach(cell, subpaths)
{
Path *subpath = (Path *) lfirst(cell);
if (path_index == arrlen)
break;
costarr[path_index++] = subpath->total_cost;
}
/*
* Since subpaths are sorted by decreasing cost, the last one will have
* the minimum cost.
*/
min_index = arrlen - 1;
/*
* For each of the remaining subpaths, add its cost to the array element
* with minimum cost.
*/
for_each_cell(l, subpaths, cell)
{
Path *subpath = (Path *) lfirst(l);
int i;
/* Consider only the non-partial paths */
if (path_index++ == numpaths)
break;
costarr[min_index] += subpath->total_cost;
/* Update the new min cost array index */
for (min_index = i = 0; i < arrlen; i++)
{
if (costarr[i] < costarr[min_index])
min_index = i;
}
}
/* Return the highest cost from the array */
for (max_index = i = 0; i < arrlen; i++)
{
if (costarr[i] > costarr[max_index])
max_index = i;
}
return costarr[max_index];
}
/*
* cost_append
* Determines and returns the cost of an Append node.
*/
void
cost_append(AppendPath *apath, PlannerInfo *root)
{
ListCell *l;
apath->path.startup_cost = 0;
apath->path.total_cost = 0;
apath->path.rows = 0;
if (apath->subpaths == NIL)
return;
if (!apath->path.parallel_aware)
{
List *pathkeys = apath->path.pathkeys;
if (pathkeys == NIL)
{
Path *subpath = (Path *) linitial(apath->subpaths);
/*
* For an unordered, non-parallel-aware Append we take the startup
* cost as the startup cost of the first subpath.
*/
apath->path.startup_cost = subpath->startup_cost;
/* Compute rows and costs as sums of subplan rows and costs. */
foreach(l, apath->subpaths)
{
Path *subpath = (Path *) lfirst(l);
apath->path.rows += subpath->rows;
apath->path.total_cost += subpath->total_cost;
}
}
else
{
/*
* For an ordered, non-parallel-aware Append we take the startup
* cost as the sum of the subpath startup costs. This ensures
* that we don't underestimate the startup cost when a query's
* LIMIT is such that several of the children have to be run to
* satisfy it. This might be overkill --- another plausible hack
* would be to take the Append's startup cost as the maximum of
* the child startup costs. But we don't want to risk believing
* that an ORDER BY LIMIT query can be satisfied at small cost
* when the first child has small startup cost but later ones
* don't. (If we had the ability to deal with nonlinear cost
* interpolation for partial retrievals, we would not need to be
* so conservative about this.)
*
* This case is also different from the above in that we have to
* account for possibly injecting sorts into subpaths that aren't
* natively ordered.
*/
foreach(l, apath->subpaths)
{
Path *subpath = (Path *) lfirst(l);
Path sort_path; /* dummy for result of cost_sort */
if (!pathkeys_contained_in(pathkeys, subpath->pathkeys))
{
/*
* We'll need to insert a Sort node, so include costs for
* that. We can use the parent's LIMIT if any, since we
* certainly won't pull more than that many tuples from
* any child.
*/
cost_sort(&sort_path,
root,
pathkeys,
subpath->total_cost,
subpath->rows,
subpath->pathtarget->width,
0.0,
work_mem,
apath->limit_tuples);
subpath = &sort_path;
}
apath->path.rows += subpath->rows;
apath->path.startup_cost += subpath->startup_cost;
apath->path.total_cost += subpath->total_cost;
}
}
}
else /* parallel-aware */
{
int i = 0;
double parallel_divisor = get_parallel_divisor(&apath->path);
/* Parallel-aware Append never produces ordered output. */
Assert(apath->path.pathkeys == NIL);
/* Calculate startup cost. */
foreach(l, apath->subpaths)
{
Path *subpath = (Path *) lfirst(l);
/*
* Append will start returning tuples when the child node having
* lowest startup cost is done setting up. We consider only the
* first few subplans that immediately get a worker assigned.
*/
if (i == 0)
apath->path.startup_cost = subpath->startup_cost;
else if (i < apath->path.parallel_workers)
apath->path.startup_cost = Min(apath->path.startup_cost,
subpath->startup_cost);
/*
* Apply parallel divisor to subpaths. Scale the number of rows
* for each partial subpath based on the ratio of the parallel
* divisor originally used for the subpath to the one we adopted.
* Also add the cost of partial paths to the total cost, but
* ignore non-partial paths for now.
*/
if (i < apath->first_partial_path)
apath->path.rows += subpath->rows / parallel_divisor;
else
{
double subpath_parallel_divisor;
subpath_parallel_divisor = get_parallel_divisor(subpath);
apath->path.rows += subpath->rows * (subpath_parallel_divisor /
parallel_divisor);
apath->path.total_cost += subpath->total_cost;
}
apath->path.rows = clamp_row_est(apath->path.rows);
i++;
}
/* Add cost for non-partial subpaths. */
apath->path.total_cost +=
append_nonpartial_cost(apath->subpaths,
apath->first_partial_path,
apath->path.parallel_workers);
}
/*
* Although Append does not do any selection or projection, it's not free;
* add a small per-tuple overhead.
*/
apath->path.total_cost +=
cpu_tuple_cost * APPEND_CPU_COST_MULTIPLIER * apath->path.rows;
}
/*
* cost_merge_append
* Determines and returns the cost of a MergeAppend node.
*
* MergeAppend merges several pre-sorted input streams, using a heap that
* at any given instant holds the next tuple from each stream. If there
* are N streams, we need about N*log2(N) tuple comparisons to construct
* the heap at startup, and then for each output tuple, about log2(N)
* comparisons to replace the top entry.
*
* (The effective value of N will drop once some of the input streams are
* exhausted, but it seems unlikely to be worth trying to account for that.)
*
* The heap is never spilled to disk, since we assume N is not very large.
* So this is much simpler than cost_sort.
*
* As in cost_sort, we charge two operator evals per tuple comparison.
*
* 'pathkeys' is a list of sort keys
* 'n_streams' is the number of input streams
* 'input_startup_cost' is the sum of the input streams' startup costs
* 'input_total_cost' is the sum of the input streams' total costs
* 'tuples' is the number of tuples in all the streams
*/
void
cost_merge_append(Path *path, PlannerInfo *root,
List *pathkeys, int n_streams,
Cost input_startup_cost, Cost input_total_cost,
double tuples)
{
Cost startup_cost = 0;
Cost run_cost = 0;
Cost comparison_cost;
double N;
double logN;
/*
* Avoid log(0)...
*/
N = (n_streams < 2) ? 2.0 : (double) n_streams;
logN = LOG2(N);
/* Assumed cost per tuple comparison */
comparison_cost = 2.0 * cpu_operator_cost;
/* Heap creation cost */
startup_cost += comparison_cost * N * logN;
/* Per-tuple heap maintenance cost */
run_cost += tuples * comparison_cost * logN;
/*
* Although MergeAppend does not do any selection or projection, it's not
* free; add a small per-tuple overhead.
*/
run_cost += cpu_tuple_cost * APPEND_CPU_COST_MULTIPLIER * tuples;
path->startup_cost = startup_cost + input_startup_cost;
path->total_cost = startup_cost + run_cost + input_total_cost;
}
/*
* cost_material
* Determines and returns the cost of materializing a relation, including
* the cost of reading the input data.
*
* If the total volume of data to materialize exceeds work_mem, we will need
* to write it to disk, so the cost is much higher in that case.
*
* Note that here we are estimating the costs for the first scan of the
* relation, so the materialization is all overhead --- any savings will
* occur only on rescan, which is estimated in cost_rescan.
*/
void
cost_material(Path *path,
Cost input_startup_cost, Cost input_total_cost,
double tuples, int width)
{
Cost startup_cost = input_startup_cost;
Cost run_cost = input_total_cost - input_startup_cost;
double nbytes = relation_byte_size(tuples, width);
long work_mem_bytes = work_mem * 1024L;
path->rows = tuples;
/*
* Whether spilling or not, charge 2x cpu_operator_cost per tuple to
* reflect bookkeeping overhead. (This rate must be more than what
* cost_rescan charges for materialize, ie, cpu_operator_cost per tuple;
* if it is exactly the same then there will be a cost tie between
* nestloop with A outer, materialized B inner and nestloop with B outer,
* materialized A inner. The extra cost ensures we'll prefer
* materializing the smaller rel.) Note that this is normally a good deal
* less than cpu_tuple_cost; which is OK because a Material plan node
* doesn't do qual-checking or projection, so it's got less overhead than
* most plan nodes.
*/
run_cost += 2 * cpu_operator_cost * tuples;
/*
* If we will spill to disk, charge at the rate of seq_page_cost per page.
* This cost is assumed to be evenly spread through the plan run phase,
* which isn't exactly accurate but our cost model doesn't allow for
* nonuniform costs within the run phase.
*/
if (nbytes > work_mem_bytes)
{
double npages = ceil(nbytes / BLCKSZ);
run_cost += seq_page_cost * npages;
}
path->startup_cost = startup_cost;
path->total_cost = startup_cost + run_cost;
}
/*
* cost_memoize_rescan
* Determines the estimated cost of rescanning a Memoize node.
*
* In order to estimate this, we must gain knowledge of how often we expect to
* be called and how many distinct sets of parameters we are likely to be
* called with. If we expect a good cache hit ratio, then we can set our
* costs to account for that hit ratio, plus a little bit of cost for the
* caching itself. Caching will not work out well if we expect to be called
* with too many distinct parameter values. The worst-case here is that we
* never see any parameter value twice, in which case we'd never get a cache
* hit and caching would be a complete waste of effort.
*/
static void
cost_memoize_rescan(PlannerInfo *root, MemoizePath *mpath,
Cost *rescan_startup_cost, Cost *rescan_total_cost)
{
EstimationInfo estinfo;
Cost input_startup_cost = mpath->subpath->startup_cost;
Cost input_total_cost = mpath->subpath->total_cost;
double tuples = mpath->subpath->rows;
double calls = mpath->calls;
int width = mpath->subpath->pathtarget->width;
double hash_mem_bytes;
double est_entry_bytes;
double est_cache_entries;
double ndistinct;
double evict_ratio;
double hit_ratio;
Cost startup_cost;
Cost total_cost;
/* available cache space */
hash_mem_bytes = get_hash_memory_limit();
/*
* Set the number of bytes each cache entry should consume in the cache.
* To provide us with better estimations on how many cache entries we can
* store at once, we make a call to the executor here to ask it what
* memory overheads there are for a single cache entry.
*
* XXX we also store the cache key, but that's not accounted for here.
*/
est_entry_bytes = relation_byte_size(tuples, width) +
ExecEstimateCacheEntryOverheadBytes(tuples);
/* estimate on the upper limit of cache entries we can hold at once */
est_cache_entries = floor(hash_mem_bytes / est_entry_bytes);
/* estimate on the distinct number of parameter values */
ndistinct = estimate_num_groups(root, mpath->param_exprs, calls, NULL,
&estinfo);
/*
* When the estimation fell back on using a default value, it's a bit too
* risky to assume that it's ok to use a Memoize node. The use of a
* default could cause us to use a Memoize node when it's really
* inappropriate to do so. If we see that this has been done, then we'll
* assume that every call will have unique parameters, which will almost
* certainly mean a MemoizePath will never survive add_path().
*/
if ((estinfo.flags & SELFLAG_USED_DEFAULT) != 0)
ndistinct = calls;
/*
* Since we've already estimated the maximum number of entries we can
* store at once and know the estimated number of distinct values we'll be
* called with, we'll take this opportunity to set the path's est_entries.
* This will ultimately determine the hash table size that the executor
* will use. If we leave this at zero, the executor will just choose the
* size itself. Really this is not the right place to do this, but it's
* convenient since everything is already calculated.
*/
mpath->est_entries = Min(Min(ndistinct, est_cache_entries),
PG_UINT32_MAX);
/*
* When the number of distinct parameter values is above the amount we can
* store in the cache, then we'll have to evict some entries from the
* cache. This is not free. Here we estimate how often we'll incur the
* cost of that eviction.
*/
evict_ratio = 1.0 - Min(est_cache_entries, ndistinct) / ndistinct;
/*
* In order to estimate how costly a single scan will be, we need to
* attempt to estimate what the cache hit ratio will be. To do that we
* must look at how many scans are estimated in total for this node and
* how many of those scans we expect to get a cache hit.
*/
hit_ratio = 1.0 / ndistinct * Min(est_cache_entries, ndistinct) -
(ndistinct / calls);
/* Ensure we don't go negative */
hit_ratio = Max(hit_ratio, 0.0);
/*
* Set the total_cost accounting for the expected cache hit ratio. We
* also add on a cpu_operator_cost to account for a cache lookup. This
* will happen regardless of whether it's a cache hit or not.
*/
total_cost = input_total_cost * (1.0 - hit_ratio) + cpu_operator_cost;
/* Now adjust the total cost to account for cache evictions */
/* Charge a cpu_tuple_cost for evicting the actual cache entry */
total_cost += cpu_tuple_cost * evict_ratio;
/*
* Charge a 10th of cpu_operator_cost to evict every tuple in that entry.
* The per-tuple eviction is really just a pfree, so charging a whole
* cpu_operator_cost seems a little excessive.
*/
total_cost += cpu_operator_cost / 10.0 * evict_ratio * tuples;
/*
* Now adjust for storing things in the cache, since that's not free
* either. Everything must go in the cache. We don't proportion this
* over any ratio, just apply it once for the scan. We charge a
* cpu_tuple_cost for the creation of the cache entry and also a
* cpu_operator_cost for each tuple we expect to cache.
*/
total_cost += cpu_tuple_cost + cpu_operator_cost * tuples;
/*
* Getting the first row must be also be proportioned according to the
* expected cache hit ratio.
*/
startup_cost = input_startup_cost * (1.0 - hit_ratio);
/*
* Additionally we charge a cpu_tuple_cost to account for cache lookups,
* which we'll do regardless of whether it was a cache hit or not.
*/
startup_cost += cpu_tuple_cost;
*rescan_startup_cost = startup_cost;
*rescan_total_cost = total_cost;
}
/*
* cost_agg
* Determines and returns the cost of performing an Agg plan node,
* including the cost of its input.
*
* aggcosts can be NULL when there are no actual aggregate functions (i.e.,
* we are using a hashed Agg node just to do grouping).
*
* Note: when aggstrategy == AGG_SORTED, caller must ensure that input costs
* are for appropriately-sorted input.
*/
void
cost_agg(Path *path, PlannerInfo *root,
AggStrategy aggstrategy, const AggClauseCosts *aggcosts,
int numGroupCols, double numGroups,
List *quals,
Cost input_startup_cost, Cost input_total_cost,
double input_tuples, double input_width)
{
double output_tuples;
Cost startup_cost;
Cost total_cost;
AggClauseCosts dummy_aggcosts;
/* Use all-zero per-aggregate costs if NULL is passed */
if (aggcosts == NULL)
{
Assert(aggstrategy == AGG_HASHED);
MemSet(&dummy_aggcosts, 0, sizeof(AggClauseCosts));
aggcosts = &dummy_aggcosts;
}
/*
* The transCost.per_tuple component of aggcosts should be charged once
* per input tuple, corresponding to the costs of evaluating the aggregate
* transfns and their input expressions. The finalCost.per_tuple component
* is charged once per output tuple, corresponding to the costs of
* evaluating the finalfns. Startup costs are of course charged but once.
*
* If we are grouping, we charge an additional cpu_operator_cost per
* grouping column per input tuple for grouping comparisons.
*
* We will produce a single output tuple if not grouping, and a tuple per
* group otherwise. We charge cpu_tuple_cost for each output tuple.
*
* Note: in this cost model, AGG_SORTED and AGG_HASHED have exactly the
* same total CPU cost, but AGG_SORTED has lower startup cost. If the
* input path is already sorted appropriately, AGG_SORTED should be
* preferred (since it has no risk of memory overflow). This will happen
* as long as the computed total costs are indeed exactly equal --- but if
* there's roundoff error we might do the wrong thing. So be sure that
* the computations below form the same intermediate values in the same
* order.
*/
if (aggstrategy == AGG_PLAIN)
{
startup_cost = input_total_cost;
startup_cost += aggcosts->transCost.startup;
startup_cost += aggcosts->transCost.per_tuple * input_tuples;
startup_cost += aggcosts->finalCost.startup;
startup_cost += aggcosts->finalCost.per_tuple;
/* we aren't grouping */
total_cost = startup_cost + cpu_tuple_cost;
output_tuples = 1;
}
else if (aggstrategy == AGG_SORTED || aggstrategy == AGG_MIXED)
{
/* Here we are able to deliver output on-the-fly */
startup_cost = input_startup_cost;
total_cost = input_total_cost;
if (aggstrategy == AGG_MIXED && !enable_hashagg)
{
startup_cost += disable_cost;
total_cost += disable_cost;
}
/* calcs phrased this way to match HASHED case, see note above */
total_cost += aggcosts->transCost.startup;
total_cost += aggcosts->transCost.per_tuple * input_tuples;
total_cost += (cpu_operator_cost * numGroupCols) * input_tuples;
total_cost += aggcosts->finalCost.startup;
total_cost += aggcosts->finalCost.per_tuple * numGroups;
total_cost += cpu_tuple_cost * numGroups;
output_tuples = numGroups;
}
else
{
/* must be AGG_HASHED */
startup_cost = input_total_cost;
if (!enable_hashagg)
startup_cost += disable_cost;
startup_cost += aggcosts->transCost.startup;
startup_cost += aggcosts->transCost.per_tuple * input_tuples;
/* cost of computing hash value */
startup_cost += (cpu_operator_cost * numGroupCols) * input_tuples;
startup_cost += aggcosts->finalCost.startup;
total_cost = startup_cost;
total_cost += aggcosts->finalCost.per_tuple * numGroups;
/* cost of retrieving from hash table */
total_cost += cpu_tuple_cost * numGroups;
output_tuples = numGroups;
}
/*
* Add the disk costs of hash aggregation that spills to disk.
*
* Groups that go into the hash table stay in memory until finalized, so
* spilling and reprocessing tuples doesn't incur additional invocations
* of transCost or finalCost. Furthermore, the computed hash value is
* stored with the spilled tuples, so we don't incur extra invocations of
* the hash function.
*
* Hash Agg begins returning tuples after the first batch is complete.
* Accrue writes (spilled tuples) to startup_cost and to total_cost;
* accrue reads only to total_cost.
*/
if (aggstrategy == AGG_HASHED || aggstrategy == AGG_MIXED)
{
double pages;
double pages_written = 0.0;
double pages_read = 0.0;
double spill_cost;
double hashentrysize;
double nbatches;
Size mem_limit;
uint64 ngroups_limit;
int num_partitions;
int depth;
/*
* Estimate number of batches based on the computed limits. If less
* than or equal to one, all groups are expected to fit in memory;
* otherwise we expect to spill.
*/
hashentrysize = hash_agg_entry_size(list_length(root->aggtransinfos),
input_width,
aggcosts->transitionSpace);
hash_agg_set_limits(hashentrysize, numGroups, 0, &mem_limit,
&ngroups_limit, &num_partitions);
nbatches = Max((numGroups * hashentrysize) / mem_limit,
numGroups / ngroups_limit);
nbatches = Max(ceil(nbatches), 1.0);
num_partitions = Max(num_partitions, 2);
/*
* The number of partitions can change at different levels of
* recursion; but for the purposes of this calculation assume it stays
* constant.
*/
depth = ceil(log(nbatches) / log(num_partitions));
/*
* Estimate number of pages read and written. For each level of
* recursion, a tuple must be written and then later read.
*/
pages = relation_byte_size(input_tuples, input_width) / BLCKSZ;
pages_written = pages_read = pages * depth;
/*
* HashAgg has somewhat worse IO behavior than Sort on typical
* hardware/OS combinations. Account for this with a generic penalty.
*/
pages_read *= 2.0;
pages_written *= 2.0;
startup_cost += pages_written * random_page_cost;
total_cost += pages_written * random_page_cost;
total_cost += pages_read * seq_page_cost;
/* account for CPU cost of spilling a tuple and reading it back */
spill_cost = depth * input_tuples * 2.0 * cpu_tuple_cost;
startup_cost += spill_cost;
total_cost += spill_cost;
}
/*
* If there are quals (HAVING quals), account for their cost and
* selectivity.
*/
if (quals)
{
QualCost qual_cost;
cost_qual_eval(&qual_cost, quals, root);
startup_cost += qual_cost.startup;
total_cost += qual_cost.startup + output_tuples * qual_cost.per_tuple;
output_tuples = clamp_row_est(output_tuples *
clauselist_selectivity(root,
quals,
0,
JOIN_INNER,
NULL));
}
path->rows = output_tuples;
path->startup_cost = startup_cost;
path->total_cost = total_cost;
}
/*
* cost_windowagg
* Determines and returns the cost of performing a WindowAgg plan node,
* including the cost of its input.
*
* Input is assumed already properly sorted.
*/
void
cost_windowagg(Path *path, PlannerInfo *root,
List *windowFuncs, int numPartCols, int numOrderCols,
Cost input_startup_cost, Cost input_total_cost,
double input_tuples)
{
Cost startup_cost;
Cost total_cost;
ListCell *lc;
startup_cost = input_startup_cost;
total_cost = input_total_cost;
/*
* Window functions are assumed to cost their stated execution cost, plus
* the cost of evaluating their input expressions, per tuple. Since they
* may in fact evaluate their inputs at multiple rows during each cycle,
* this could be a drastic underestimate; but without a way to know how
* many rows the window function will fetch, it's hard to do better. In
* any case, it's a good estimate for all the built-in window functions,
* so we'll just do this for now.
*/
foreach(lc, windowFuncs)
{
WindowFunc *wfunc = lfirst_node(WindowFunc, lc);
Cost wfunccost;
QualCost argcosts;
argcosts.startup = argcosts.per_tuple = 0;
add_function_cost(root, wfunc->winfnoid, (Node *) wfunc,
&argcosts);
startup_cost += argcosts.startup;
wfunccost = argcosts.per_tuple;
/* also add the input expressions' cost to per-input-row costs */
cost_qual_eval_node(&argcosts, (Node *) wfunc->args, root);
startup_cost += argcosts.startup;
wfunccost += argcosts.per_tuple;
/*
* Add the filter's cost to per-input-row costs. XXX We should reduce
* input expression costs according to filter selectivity.
*/
cost_qual_eval_node(&argcosts, (Node *) wfunc->aggfilter, root);
startup_cost += argcosts.startup;
wfunccost += argcosts.per_tuple;
total_cost += wfunccost * input_tuples;
}
/*
* We also charge cpu_operator_cost per grouping column per tuple for
* grouping comparisons, plus cpu_tuple_cost per tuple for general
* overhead.
*
* XXX this neglects costs of spooling the data to disk when it overflows
* work_mem. Sooner or later that should get accounted for.
*/
total_cost += cpu_operator_cost * (numPartCols + numOrderCols) * input_tuples;
total_cost += cpu_tuple_cost * input_tuples;
path->rows = input_tuples;
path->startup_cost = startup_cost;
path->total_cost = total_cost;
}
/*
* cost_group
* Determines and returns the cost of performing a Group plan node,
* including the cost of its input.
*
* Note: caller must ensure that input costs are for appropriately-sorted
* input.
*/
void
cost_group(Path *path, PlannerInfo *root,
int numGroupCols, double numGroups,
List *quals,
Cost input_startup_cost, Cost input_total_cost,
double input_tuples)
{
double output_tuples;
Cost startup_cost;
Cost total_cost;
output_tuples = numGroups;
startup_cost = input_startup_cost;
total_cost = input_total_cost;
/*
* Charge one cpu_operator_cost per comparison per input tuple. We assume
* all columns get compared at most of the tuples.
*/
total_cost += cpu_operator_cost * input_tuples * numGroupCols;
/*
* If there are quals (HAVING quals), account for their cost and
* selectivity.
*/
if (quals)
{
QualCost qual_cost;
cost_qual_eval(&qual_cost, quals, root);
startup_cost += qual_cost.startup;
total_cost += qual_cost.startup + output_tuples * qual_cost.per_tuple;
output_tuples = clamp_row_est(output_tuples *
clauselist_selectivity(root,
quals,
0,
JOIN_INNER,
NULL));
}
path->rows = output_tuples;
path->startup_cost = startup_cost;
path->total_cost = total_cost;
}
/*
* initial_cost_nestloop
* Preliminary estimate of the cost of a nestloop join path.
*
* This must quickly produce lower-bound estimates of the path's startup and
* total costs. If we are unable to eliminate the proposed path from
* consideration using the lower bounds, final_cost_nestloop will be called
* to obtain the final estimates.
*
* The exact division of labor between this function and final_cost_nestloop
* is private to them, and represents a tradeoff between speed of the initial
* estimate and getting a tight lower bound. We choose to not examine the
* join quals here, since that's by far the most expensive part of the
* calculations. The end result is that CPU-cost considerations must be
* left for the second phase; and for SEMI/ANTI joins, we must also postpone
* incorporation of the inner path's run cost.
*
* 'workspace' is to be filled with startup_cost, total_cost, and perhaps
* other data to be used by final_cost_nestloop
* 'jointype' is the type of join to be performed
* 'outer_path' is the outer input to the join
* 'inner_path' is the inner input to the join
* 'extra' contains miscellaneous information about the join
*/
void
initial_cost_nestloop(PlannerInfo *root, JoinCostWorkspace *workspace,
JoinType jointype,
Path *outer_path, Path *inner_path,
JoinPathExtraData *extra)
{
Cost startup_cost = 0;
Cost run_cost = 0;
double outer_path_rows = outer_path->rows;
Cost inner_rescan_start_cost;
Cost inner_rescan_total_cost;
Cost inner_run_cost;
Cost inner_rescan_run_cost;
/* estimate costs to rescan the inner relation */
cost_rescan(root, inner_path,
&inner_rescan_start_cost,
&inner_rescan_total_cost);
/* cost of source data */
/*
* NOTE: clearly, we must pay both outer and inner paths' startup_cost
* before we can start returning tuples, so the join's startup cost is
* their sum. We'll also pay the inner path's rescan startup cost
* multiple times.
*/
startup_cost += outer_path->startup_cost + inner_path->startup_cost;
run_cost += outer_path->total_cost - outer_path->startup_cost;
if (outer_path_rows > 1)
run_cost += (outer_path_rows - 1) * inner_rescan_start_cost;
inner_run_cost = inner_path->total_cost - inner_path->startup_cost;
inner_rescan_run_cost = inner_rescan_total_cost - inner_rescan_start_cost;
if (jointype == JOIN_SEMI || jointype == JOIN_ANTI ||
extra->inner_unique)
{
/*
* With a SEMI or ANTI join, or if the innerrel is known unique, the
* executor will stop after the first match.
*
* Getting decent estimates requires inspection of the join quals,
* which we choose to postpone to final_cost_nestloop.
*/
/* Save private data for final_cost_nestloop */
workspace->inner_run_cost = inner_run_cost;
workspace->inner_rescan_run_cost = inner_rescan_run_cost;
}
else
{
/* Normal case; we'll scan whole input rel for each outer row */
run_cost += inner_run_cost;
if (outer_path_rows > 1)
run_cost += (outer_path_rows - 1) * inner_rescan_run_cost;
}
/* CPU costs left for later */
/* Public result fields */
workspace->startup_cost = startup_cost;
workspace->total_cost = startup_cost + run_cost;
/* Save private data for final_cost_nestloop */
workspace->run_cost = run_cost;
}
/*
* final_cost_nestloop
* Final estimate of the cost and result size of a nestloop join path.
*
* 'path' is already filled in except for the rows and cost fields
* 'workspace' is the result from initial_cost_nestloop
* 'extra' contains miscellaneous information about the join
*/
void
final_cost_nestloop(PlannerInfo *root, NestPath *path,
JoinCostWorkspace *workspace,
JoinPathExtraData *extra)
{
Path *outer_path = path->jpath.outerjoinpath;
Path *inner_path = path->jpath.innerjoinpath;
double outer_path_rows = outer_path->rows;
double inner_path_rows = inner_path->rows;
Cost startup_cost = workspace->startup_cost;
Cost run_cost = workspace->run_cost;
Cost cpu_per_tuple;
QualCost restrict_qual_cost;
double ntuples;
/* Protect some assumptions below that rowcounts aren't zero */
if (outer_path_rows <= 0)
outer_path_rows = 1;
if (inner_path_rows <= 0)
inner_path_rows = 1;
/* Mark the path with the correct row estimate */
if (path->jpath.path.param_info)
path->jpath.path.rows = path->jpath.path.param_info->ppi_rows;
else
path->jpath.path.rows = path->jpath.path.parent->rows;
/* For partial paths, scale row estimate. */
if (path->jpath.path.parallel_workers > 0)
{
double parallel_divisor = get_parallel_divisor(&path->jpath.path);
path->jpath.path.rows =
clamp_row_est(path->jpath.path.rows / parallel_divisor);
}
/*
* We could include disable_cost in the preliminary estimate, but that
* would amount to optimizing for the case where the join method is
* disabled, which doesn't seem like the way to bet.
*/
if (!enable_nestloop)
startup_cost += disable_cost;
/* cost of inner-relation source data (we already dealt with outer rel) */
if (path->jpath.jointype == JOIN_SEMI || path->jpath.jointype == JOIN_ANTI ||
extra->inner_unique)
{
/*
* With a SEMI or ANTI join, or if the innerrel is known unique, the
* executor will stop after the first match.
*/
Cost inner_run_cost = workspace->inner_run_cost;
Cost inner_rescan_run_cost = workspace->inner_rescan_run_cost;
double outer_matched_rows;
double outer_unmatched_rows;
Selectivity inner_scan_frac;
/*
* For an outer-rel row that has at least one match, we can expect the
* inner scan to stop after a fraction 1/(match_count+1) of the inner
* rows, if the matches are evenly distributed. Since they probably
* aren't quite evenly distributed, we apply a fuzz factor of 2.0 to
* that fraction. (If we used a larger fuzz factor, we'd have to
* clamp inner_scan_frac to at most 1.0; but since match_count is at
* least 1, no such clamp is needed now.)
*/
outer_matched_rows = rint(outer_path_rows * extra->semifactors.outer_match_frac);
outer_unmatched_rows = outer_path_rows - outer_matched_rows;
inner_scan_frac = 2.0 / (extra->semifactors.match_count + 1.0);
/*
* Compute number of tuples processed (not number emitted!). First,
* account for successfully-matched outer rows.
*/
ntuples = outer_matched_rows * inner_path_rows * inner_scan_frac;
/*
* Now we need to estimate the actual costs of scanning the inner
* relation, which may be quite a bit less than N times inner_run_cost
* due to early scan stops. We consider two cases. If the inner path
* is an indexscan using all the joinquals as indexquals, then an
* unmatched outer row results in an indexscan returning no rows,
* which is probably quite cheap. Otherwise, the executor will have
* to scan the whole inner rel for an unmatched row; not so cheap.
*/
if (has_indexed_join_quals(path))
{
/*
* Successfully-matched outer rows will only require scanning
* inner_scan_frac of the inner relation. In this case, we don't
* need to charge the full inner_run_cost even when that's more
* than inner_rescan_run_cost, because we can assume that none of
* the inner scans ever scan the whole inner relation. So it's
* okay to assume that all the inner scan executions can be
* fractions of the full cost, even if materialization is reducing
* the rescan cost. At this writing, it's impossible to get here
* for a materialized inner scan, so inner_run_cost and
* inner_rescan_run_cost will be the same anyway; but just in
* case, use inner_run_cost for the first matched tuple and
* inner_rescan_run_cost for additional ones.
*/
run_cost += inner_run_cost * inner_scan_frac;
if (outer_matched_rows > 1)
run_cost += (outer_matched_rows - 1) * inner_rescan_run_cost * inner_scan_frac;
/*
* Add the cost of inner-scan executions for unmatched outer rows.
* We estimate this as the same cost as returning the first tuple
* of a nonempty scan. We consider that these are all rescans,
* since we used inner_run_cost once already.
*/
run_cost += outer_unmatched_rows *
inner_rescan_run_cost / inner_path_rows;
/*
* We won't be evaluating any quals at all for unmatched rows, so
* don't add them to ntuples.
*/
}
else
{
/*
* Here, a complicating factor is that rescans may be cheaper than
* first scans. If we never scan all the way to the end of the
* inner rel, it might be (depending on the plan type) that we'd
* never pay the whole inner first-scan run cost. However it is
* difficult to estimate whether that will happen (and it could
* not happen if there are any unmatched outer rows!), so be
* conservative and always charge the whole first-scan cost once.
* We consider this charge to correspond to the first unmatched
* outer row, unless there isn't one in our estimate, in which
* case blame it on the first matched row.
*/
/* First, count all unmatched join tuples as being processed */
ntuples += outer_unmatched_rows * inner_path_rows;
/* Now add the forced full scan, and decrement appropriate count */
run_cost += inner_run_cost;
if (outer_unmatched_rows >= 1)
outer_unmatched_rows -= 1;
else
outer_matched_rows -= 1;
/* Add inner run cost for additional outer tuples having matches */
if (outer_matched_rows > 0)
run_cost += outer_matched_rows * inner_rescan_run_cost * inner_scan_frac;
/* Add inner run cost for additional unmatched outer tuples */
if (outer_unmatched_rows > 0)
run_cost += outer_unmatched_rows * inner_rescan_run_cost;
}
}
else
{
/* Normal-case source costs were included in preliminary estimate */
/* Compute number of tuples processed (not number emitted!) */
ntuples = outer_path_rows * inner_path_rows;
}
/* CPU costs */
cost_qual_eval(&restrict_qual_cost, path->jpath.joinrestrictinfo, root);
startup_cost += restrict_qual_cost.startup;
cpu_per_tuple = cpu_tuple_cost + restrict_qual_cost.per_tuple;
run_cost += cpu_per_tuple * ntuples;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->jpath.path.pathtarget->cost.startup;
run_cost += path->jpath.path.pathtarget->cost.per_tuple * path->jpath.path.rows;
path->jpath.path.startup_cost = startup_cost;
path->jpath.path.total_cost = startup_cost + run_cost;
}
/*
* initial_cost_mergejoin
* Preliminary estimate of the cost of a mergejoin path.
*
* This must quickly produce lower-bound estimates of the path's startup and
* total costs. If we are unable to eliminate the proposed path from
* consideration using the lower bounds, final_cost_mergejoin will be called
* to obtain the final estimates.
*
* The exact division of labor between this function and final_cost_mergejoin
* is private to them, and represents a tradeoff between speed of the initial
* estimate and getting a tight lower bound. We choose to not examine the
* join quals here, except for obtaining the scan selectivity estimate which
* is really essential (but fortunately, use of caching keeps the cost of
* getting that down to something reasonable).
* We also assume that cost_sort is cheap enough to use here.
*
* 'workspace' is to be filled with startup_cost, total_cost, and perhaps
* other data to be used by final_cost_mergejoin
* 'jointype' is the type of join to be performed
* 'mergeclauses' is the list of joinclauses to be used as merge clauses
* 'outer_path' is the outer input to the join
* 'inner_path' is the inner input to the join
* 'outersortkeys' is the list of sort keys for the outer path
* 'innersortkeys' is the list of sort keys for the inner path
* 'extra' contains miscellaneous information about the join
*
* Note: outersortkeys and innersortkeys should be NIL if no explicit
* sort is needed because the respective source path is already ordered.
*/
void
initial_cost_mergejoin(PlannerInfo *root, JoinCostWorkspace *workspace,
JoinType jointype,
List *mergeclauses,
Path *outer_path, Path *inner_path,
List *outersortkeys, List *innersortkeys,
JoinPathExtraData *extra)
{
Cost startup_cost = 0;
Cost run_cost = 0;
double outer_path_rows = outer_path->rows;
double inner_path_rows = inner_path->rows;
Cost inner_run_cost;
double outer_rows,
inner_rows,
outer_skip_rows,
inner_skip_rows;
Selectivity outerstartsel,
outerendsel,
innerstartsel,
innerendsel;
Path sort_path; /* dummy for result of cost_sort */
/* Protect some assumptions below that rowcounts aren't zero */
if (outer_path_rows <= 0)
outer_path_rows = 1;
if (inner_path_rows <= 0)
inner_path_rows = 1;
/*
* A merge join will stop as soon as it exhausts either input stream
* (unless it's an outer join, in which case the outer side has to be
* scanned all the way anyway). Estimate fraction of the left and right
* inputs that will actually need to be scanned. Likewise, we can
* estimate the number of rows that will be skipped before the first join
* pair is found, which should be factored into startup cost. We use only
* the first (most significant) merge clause for this purpose. Since
* mergejoinscansel() is a fairly expensive computation, we cache the
* results in the merge clause RestrictInfo.
*/
if (mergeclauses && jointype != JOIN_FULL)
{
RestrictInfo *firstclause = (RestrictInfo *) linitial(mergeclauses);
List *opathkeys;
List *ipathkeys;
PathKey *opathkey;
PathKey *ipathkey;
MergeScanSelCache *cache;
/* Get the input pathkeys to determine the sort-order details */
opathkeys = outersortkeys ? outersortkeys : outer_path->pathkeys;
ipathkeys = innersortkeys ? innersortkeys : inner_path->pathkeys;
Assert(opathkeys);
Assert(ipathkeys);
opathkey = (PathKey *) linitial(opathkeys);
ipathkey = (PathKey *) linitial(ipathkeys);
/* debugging check */
if (opathkey->pk_opfamily != ipathkey->pk_opfamily ||
opathkey->pk_eclass->ec_collation != ipathkey->pk_eclass->ec_collation ||
opathkey->pk_strategy != ipathkey->pk_strategy ||
opathkey->pk_nulls_first != ipathkey->pk_nulls_first)
elog(ERROR, "left and right pathkeys do not match in mergejoin");
/* Get the selectivity with caching */
cache = cached_scansel(root, firstclause, opathkey);
if (bms_is_subset(firstclause->left_relids,
outer_path->parent->relids))
{
/* left side of clause is outer */
outerstartsel = cache->leftstartsel;
outerendsel = cache->leftendsel;
innerstartsel = cache->rightstartsel;
innerendsel = cache->rightendsel;
}
else
{
/* left side of clause is inner */
outerstartsel = cache->rightstartsel;
outerendsel = cache->rightendsel;
innerstartsel = cache->leftstartsel;
innerendsel = cache->leftendsel;
}
if (jointype == JOIN_LEFT ||
jointype == JOIN_ANTI)
{
outerstartsel = 0.0;
outerendsel = 1.0;
}
else if (jointype == JOIN_RIGHT)
{
innerstartsel = 0.0;
innerendsel = 1.0;
}
}
else
{
/* cope with clauseless or full mergejoin */
outerstartsel = innerstartsel = 0.0;
outerendsel = innerendsel = 1.0;
}
/*
* Convert selectivities to row counts. We force outer_rows and
* inner_rows to be at least 1, but the skip_rows estimates can be zero.
*/
outer_skip_rows = rint(outer_path_rows * outerstartsel);
inner_skip_rows = rint(inner_path_rows * innerstartsel);
outer_rows = clamp_row_est(outer_path_rows * outerendsel);
inner_rows = clamp_row_est(inner_path_rows * innerendsel);
Assert(outer_skip_rows <= outer_rows);
Assert(inner_skip_rows <= inner_rows);
/*
* Readjust scan selectivities to account for above rounding. This is
* normally an insignificant effect, but when there are only a few rows in
* the inputs, failing to do this makes for a large percentage error.
*/
outerstartsel = outer_skip_rows / outer_path_rows;
innerstartsel = inner_skip_rows / inner_path_rows;
outerendsel = outer_rows / outer_path_rows;
innerendsel = inner_rows / inner_path_rows;
Assert(outerstartsel <= outerendsel);
Assert(innerstartsel <= innerendsel);
/* cost of source data */
if (outersortkeys) /* do we need to sort outer? */
{
cost_sort(&sort_path,
root,
outersortkeys,
outer_path->total_cost,
outer_path_rows,
outer_path->pathtarget->width,
0.0,
work_mem,
-1.0);
startup_cost += sort_path.startup_cost;
startup_cost += (sort_path.total_cost - sort_path.startup_cost)
* outerstartsel;
run_cost += (sort_path.total_cost - sort_path.startup_cost)
* (outerendsel - outerstartsel);
}
else
{
startup_cost += outer_path->startup_cost;
startup_cost += (outer_path->total_cost - outer_path->startup_cost)
* outerstartsel;
run_cost += (outer_path->total_cost - outer_path->startup_cost)
* (outerendsel - outerstartsel);
}
if (innersortkeys) /* do we need to sort inner? */
{
cost_sort(&sort_path,
root,
innersortkeys,
inner_path->total_cost,
inner_path_rows,
inner_path->pathtarget->width,
0.0,
work_mem,
-1.0);
startup_cost += sort_path.startup_cost;
startup_cost += (sort_path.total_cost - sort_path.startup_cost)
* innerstartsel;
inner_run_cost = (sort_path.total_cost - sort_path.startup_cost)
* (innerendsel - innerstartsel);
}
else
{
startup_cost += inner_path->startup_cost;
startup_cost += (inner_path->total_cost - inner_path->startup_cost)
* innerstartsel;
inner_run_cost = (inner_path->total_cost - inner_path->startup_cost)
* (innerendsel - innerstartsel);
}
/*
* We can't yet determine whether rescanning occurs, or whether
* materialization of the inner input should be done. The minimum
* possible inner input cost, regardless of rescan and materialization
* considerations, is inner_run_cost. We include that in
* workspace->total_cost, but not yet in run_cost.
*/
/* CPU costs left for later */
/* Public result fields */
workspace->startup_cost = startup_cost;
workspace->total_cost = startup_cost + run_cost + inner_run_cost;
/* Save private data for final_cost_mergejoin */
workspace->run_cost = run_cost;
workspace->inner_run_cost = inner_run_cost;
workspace->outer_rows = outer_rows;
workspace->inner_rows = inner_rows;
workspace->outer_skip_rows = outer_skip_rows;
workspace->inner_skip_rows = inner_skip_rows;
}
/*
* final_cost_mergejoin
* Final estimate of the cost and result size of a mergejoin path.
*
* Unlike other costsize functions, this routine makes two actual decisions:
* whether the executor will need to do mark/restore, and whether we should
* materialize the inner path. It would be logically cleaner to build
* separate paths testing these alternatives, but that would require repeating
* most of the cost calculations, which are not all that cheap. Since the
* choice will not affect output pathkeys or startup cost, only total cost,
* there is no possibility of wanting to keep more than one path. So it seems
* best to make the decisions here and record them in the path's
* skip_mark_restore and materialize_inner fields.
*
* Mark/restore overhead is usually required, but can be skipped if we know
* that the executor need find only one match per outer tuple, and that the
* mergeclauses are sufficient to identify a match.
*
* We materialize the inner path if we need mark/restore and either the inner
* path can't support mark/restore, or it's cheaper to use an interposed
* Material node to handle mark/restore.
*
* 'path' is already filled in except for the rows and cost fields and
* skip_mark_restore and materialize_inner
* 'workspace' is the result from initial_cost_mergejoin
* 'extra' contains miscellaneous information about the join
*/
void
final_cost_mergejoin(PlannerInfo *root, MergePath *path,
JoinCostWorkspace *workspace,
JoinPathExtraData *extra)
{
Path *outer_path = path->jpath.outerjoinpath;
Path *inner_path = path->jpath.innerjoinpath;
double inner_path_rows = inner_path->rows;
List *mergeclauses = path->path_mergeclauses;
List *innersortkeys = path->innersortkeys;
Cost startup_cost = workspace->startup_cost;
Cost run_cost = workspace->run_cost;
Cost inner_run_cost = workspace->inner_run_cost;
double outer_rows = workspace->outer_rows;
double inner_rows = workspace->inner_rows;
double outer_skip_rows = workspace->outer_skip_rows;
double inner_skip_rows = workspace->inner_skip_rows;
Cost cpu_per_tuple,
bare_inner_cost,
mat_inner_cost;
QualCost merge_qual_cost;
QualCost qp_qual_cost;
double mergejointuples,
rescannedtuples;
double rescanratio;
/* Protect some assumptions below that rowcounts aren't zero */
if (inner_path_rows <= 0)
inner_path_rows = 1;
/* Mark the path with the correct row estimate */
if (path->jpath.path.param_info)
path->jpath.path.rows = path->jpath.path.param_info->ppi_rows;
else
path->jpath.path.rows = path->jpath.path.parent->rows;
/* For partial paths, scale row estimate. */
if (path->jpath.path.parallel_workers > 0)
{
double parallel_divisor = get_parallel_divisor(&path->jpath.path);
path->jpath.path.rows =
clamp_row_est(path->jpath.path.rows / parallel_divisor);
}
/*
* We could include disable_cost in the preliminary estimate, but that
* would amount to optimizing for the case where the join method is
* disabled, which doesn't seem like the way to bet.
*/
if (!enable_mergejoin)
startup_cost += disable_cost;
/*
* Compute cost of the mergequals and qpquals (other restriction clauses)
* separately.
*/
cost_qual_eval(&merge_qual_cost, mergeclauses, root);
cost_qual_eval(&qp_qual_cost, path->jpath.joinrestrictinfo, root);
qp_qual_cost.startup -= merge_qual_cost.startup;
qp_qual_cost.per_tuple -= merge_qual_cost.per_tuple;
/*
* With a SEMI or ANTI join, or if the innerrel is known unique, the
* executor will stop scanning for matches after the first match. When
* all the joinclauses are merge clauses, this means we don't ever need to
* back up the merge, and so we can skip mark/restore overhead.
*/
if ((path->jpath.jointype == JOIN_SEMI ||
path->jpath.jointype == JOIN_ANTI ||
extra->inner_unique) &&
(list_length(path->jpath.joinrestrictinfo) ==
list_length(path->path_mergeclauses)))
path->skip_mark_restore = true;
else
path->skip_mark_restore = false;
/*
* Get approx # tuples passing the mergequals. We use approx_tuple_count
* here because we need an estimate done with JOIN_INNER semantics.
*/
mergejointuples = approx_tuple_count(root, &path->jpath, mergeclauses);
/*
* When there are equal merge keys in the outer relation, the mergejoin
* must rescan any matching tuples in the inner relation. This means
* re-fetching inner tuples; we have to estimate how often that happens.
*
* For regular inner and outer joins, the number of re-fetches can be
* estimated approximately as size of merge join output minus size of
* inner relation. Assume that the distinct key values are 1, 2, ..., and
* denote the number of values of each key in the outer relation as m1,
* m2, ...; in the inner relation, n1, n2, ... Then we have
*
* size of join = m1 * n1 + m2 * n2 + ...
*
* number of rescanned tuples = (m1 - 1) * n1 + (m2 - 1) * n2 + ... = m1 *
* n1 + m2 * n2 + ... - (n1 + n2 + ...) = size of join - size of inner
* relation
*
* This equation works correctly for outer tuples having no inner match
* (nk = 0), but not for inner tuples having no outer match (mk = 0); we
* are effectively subtracting those from the number of rescanned tuples,
* when we should not. Can we do better without expensive selectivity
* computations?
*
* The whole issue is moot if we are working from a unique-ified outer
* input, or if we know we don't need to mark/restore at all.
*/
if (IsA(outer_path, UniquePath) || path->skip_mark_restore)
rescannedtuples = 0;
else
{
rescannedtuples = mergejointuples - inner_path_rows;
/* Must clamp because of possible underestimate */
if (rescannedtuples < 0)
rescannedtuples = 0;
}
/*
* We'll inflate various costs this much to account for rescanning. Note
* that this is to be multiplied by something involving inner_rows, or
* another number related to the portion of the inner rel we'll scan.
*/
rescanratio = 1.0 + (rescannedtuples / inner_rows);
/*
* Decide whether we want to materialize the inner input to shield it from
* mark/restore and performing re-fetches. Our cost model for regular
* re-fetches is that a re-fetch costs the same as an original fetch,
* which is probably an overestimate; but on the other hand we ignore the
* bookkeeping costs of mark/restore. Not clear if it's worth developing
* a more refined model. So we just need to inflate the inner run cost by
* rescanratio.
*/
bare_inner_cost = inner_run_cost * rescanratio;
/*
* When we interpose a Material node the re-fetch cost is assumed to be
* just cpu_operator_cost per tuple, independently of the underlying
* plan's cost; and we charge an extra cpu_operator_cost per original
* fetch as well. Note that we're assuming the materialize node will
* never spill to disk, since it only has to remember tuples back to the
* last mark. (If there are a huge number of duplicates, our other cost
* factors will make the path so expensive that it probably won't get
* chosen anyway.) So we don't use cost_rescan here.
*
* Note: keep this estimate in sync with create_mergejoin_plan's labeling
* of the generated Material node.
*/
mat_inner_cost = inner_run_cost +
cpu_operator_cost * inner_rows * rescanratio;
/*
* If we don't need mark/restore at all, we don't need materialization.
*/
if (path->skip_mark_restore)
path->materialize_inner = false;
/*
* Prefer materializing if it looks cheaper, unless the user has asked to
* suppress materialization.
*/
else if (enable_material && mat_inner_cost < bare_inner_cost)
path->materialize_inner = true;
/*
* Even if materializing doesn't look cheaper, we *must* do it if the
* inner path is to be used directly (without sorting) and it doesn't
* support mark/restore.
*
* Since the inner side must be ordered, and only Sorts and IndexScans can
* create order to begin with, and they both support mark/restore, you
* might think there's no problem --- but you'd be wrong. Nestloop and
* merge joins can *preserve* the order of their inputs, so they can be
* selected as the input of a mergejoin, and they don't support
* mark/restore at present.
*
* We don't test the value of enable_material here, because
* materialization is required for correctness in this case, and turning
* it off does not entitle us to deliver an invalid plan.
*/
else if (innersortkeys == NIL &&
!ExecSupportsMarkRestore(inner_path))
path->materialize_inner = true;
/*
* Also, force materializing if the inner path is to be sorted and the
* sort is expected to spill to disk. This is because the final merge
* pass can be done on-the-fly if it doesn't have to support mark/restore.
* We don't try to adjust the cost estimates for this consideration,
* though.
*
* Since materialization is a performance optimization in this case,
* rather than necessary for correctness, we skip it if enable_material is
* off.
*/
else if (enable_material && innersortkeys != NIL &&
relation_byte_size(inner_path_rows,
inner_path->pathtarget->width) >
(work_mem * 1024L))
path->materialize_inner = true;
else
path->materialize_inner = false;
/* Charge the right incremental cost for the chosen case */
if (path->materialize_inner)
run_cost += mat_inner_cost;
else
run_cost += bare_inner_cost;
/* CPU costs */
/*
* The number of tuple comparisons needed is approximately number of outer
* rows plus number of inner rows plus number of rescanned tuples (can we
* refine this?). At each one, we need to evaluate the mergejoin quals.
*/
startup_cost += merge_qual_cost.startup;
startup_cost += merge_qual_cost.per_tuple *
(outer_skip_rows + inner_skip_rows * rescanratio);
run_cost += merge_qual_cost.per_tuple *
((outer_rows - outer_skip_rows) +
(inner_rows - inner_skip_rows) * rescanratio);
/*
* For each tuple that gets through the mergejoin proper, we charge
* cpu_tuple_cost plus the cost of evaluating additional restriction
* clauses that are to be applied at the join. (This is pessimistic since
* not all of the quals may get evaluated at each tuple.)
*
* Note: we could adjust for SEMI/ANTI joins skipping some qual
* evaluations here, but it's probably not worth the trouble.
*/
startup_cost += qp_qual_cost.startup;
cpu_per_tuple = cpu_tuple_cost + qp_qual_cost.per_tuple;
run_cost += cpu_per_tuple * mergejointuples;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->jpath.path.pathtarget->cost.startup;
run_cost += path->jpath.path.pathtarget->cost.per_tuple * path->jpath.path.rows;
path->jpath.path.startup_cost = startup_cost;
path->jpath.path.total_cost = startup_cost + run_cost;
}
/*
* run mergejoinscansel() with caching
*/
static MergeScanSelCache *
cached_scansel(PlannerInfo *root, RestrictInfo *rinfo, PathKey *pathkey)
{
MergeScanSelCache *cache;
ListCell *lc;
Selectivity leftstartsel,
leftendsel,
rightstartsel,
rightendsel;
MemoryContext oldcontext;
/* Do we have this result already? */
foreach(lc, rinfo->scansel_cache)
{
cache = (MergeScanSelCache *) lfirst(lc);
if (cache->opfamily == pathkey->pk_opfamily &&
cache->collation == pathkey->pk_eclass->ec_collation &&
cache->strategy == pathkey->pk_strategy &&
cache->nulls_first == pathkey->pk_nulls_first)
return cache;
}
/* Nope, do the computation */
mergejoinscansel(root,
(Node *) rinfo->clause,
pathkey->pk_opfamily,
pathkey->pk_strategy,
pathkey->pk_nulls_first,
&leftstartsel,
&leftendsel,
&rightstartsel,
&rightendsel);
/* Cache the result in suitably long-lived workspace */
oldcontext = MemoryContextSwitchTo(root->planner_cxt);
cache = (MergeScanSelCache *) palloc(sizeof(MergeScanSelCache));
cache->opfamily = pathkey->pk_opfamily;
cache->collation = pathkey->pk_eclass->ec_collation;
cache->strategy = pathkey->pk_strategy;
cache->nulls_first = pathkey->pk_nulls_first;
cache->leftstartsel = leftstartsel;
cache->leftendsel = leftendsel;
cache->rightstartsel = rightstartsel;
cache->rightendsel = rightendsel;
rinfo->scansel_cache = lappend(rinfo->scansel_cache, cache);
MemoryContextSwitchTo(oldcontext);
return cache;
}
/*
* initial_cost_hashjoin
* Preliminary estimate of the cost of a hashjoin path.
*
* This must quickly produce lower-bound estimates of the path's startup and
* total costs. If we are unable to eliminate the proposed path from
* consideration using the lower bounds, final_cost_hashjoin will be called
* to obtain the final estimates.
*
* The exact division of labor between this function and final_cost_hashjoin
* is private to them, and represents a tradeoff between speed of the initial
* estimate and getting a tight lower bound. We choose to not examine the
* join quals here (other than by counting the number of hash clauses),
* so we can't do much with CPU costs. We do assume that
* ExecChooseHashTableSize is cheap enough to use here.
*
* 'workspace' is to be filled with startup_cost, total_cost, and perhaps
* other data to be used by final_cost_hashjoin
* 'jointype' is the type of join to be performed
* 'hashclauses' is the list of joinclauses to be used as hash clauses
* 'outer_path' is the outer input to the join
* 'inner_path' is the inner input to the join
* 'extra' contains miscellaneous information about the join
* 'parallel_hash' indicates that inner_path is partial and that a shared
* hash table will be built in parallel
*/
void
initial_cost_hashjoin(PlannerInfo *root, JoinCostWorkspace *workspace,
JoinType jointype,
List *hashclauses,
Path *outer_path, Path *inner_path,
JoinPathExtraData *extra,
bool parallel_hash)
{
Cost startup_cost = 0;
Cost run_cost = 0;
double outer_path_rows = outer_path->rows;
double inner_path_rows = inner_path->rows;
double inner_path_rows_total = inner_path_rows;
int num_hashclauses = list_length(hashclauses);
int numbuckets;
int numbatches;
int num_skew_mcvs;
size_t space_allowed; /* unused */
/* cost of source data */
startup_cost += outer_path->startup_cost;
run_cost += outer_path->total_cost - outer_path->startup_cost;
startup_cost += inner_path->total_cost;
/*
* Cost of computing hash function: must do it once per input tuple. We
* charge one cpu_operator_cost for each column's hash function. Also,
* tack on one cpu_tuple_cost per inner row, to model the costs of
* inserting the row into the hashtable.
*
* XXX when a hashclause is more complex than a single operator, we really
* should charge the extra eval costs of the left or right side, as
* appropriate, here. This seems more work than it's worth at the moment.
*/
startup_cost += (cpu_operator_cost * num_hashclauses + cpu_tuple_cost)
* inner_path_rows;
run_cost += cpu_operator_cost * num_hashclauses * outer_path_rows;
/*
* If this is a parallel hash build, then the value we have for
* inner_rows_total currently refers only to the rows returned by each
* participant. For shared hash table size estimation, we need the total
* number, so we need to undo the division.
*/
if (parallel_hash)
inner_path_rows_total *= get_parallel_divisor(inner_path);
/*
* Get hash table size that executor would use for inner relation.
*
* XXX for the moment, always assume that skew optimization will be
* performed. As long as SKEW_HASH_MEM_PERCENT is small, it's not worth
* trying to determine that for sure.
*
* XXX at some point it might be interesting to try to account for skew
* optimization in the cost estimate, but for now, we don't.
*/
ExecChooseHashTableSize(inner_path_rows_total,
inner_path->pathtarget->width,
true, /* useskew */
parallel_hash, /* try_combined_hash_mem */
outer_path->parallel_workers,
&space_allowed,
&numbuckets,
&numbatches,
&num_skew_mcvs);
/*
* If inner relation is too big then we will need to "batch" the join,
* which implies writing and reading most of the tuples to disk an extra
* time. Charge seq_page_cost per page, since the I/O should be nice and
* sequential. Writing the inner rel counts as startup cost, all the rest
* as run cost.
*/
if (numbatches > 1)
{
double outerpages = page_size(outer_path_rows,
outer_path->pathtarget->width);
double innerpages = page_size(inner_path_rows,
inner_path->pathtarget->width);
startup_cost += seq_page_cost * innerpages;
run_cost += seq_page_cost * (innerpages + 2 * outerpages);
}
/* CPU costs left for later */
/* Public result fields */
workspace->startup_cost = startup_cost;
workspace->total_cost = startup_cost + run_cost;
/* Save private data for final_cost_hashjoin */
workspace->run_cost = run_cost;
workspace->numbuckets = numbuckets;
workspace->numbatches = numbatches;
workspace->inner_rows_total = inner_path_rows_total;
}
/*
* final_cost_hashjoin
* Final estimate of the cost and result size of a hashjoin path.
*
* Note: the numbatches estimate is also saved into 'path' for use later
*
* 'path' is already filled in except for the rows and cost fields and
* num_batches
* 'workspace' is the result from initial_cost_hashjoin
* 'extra' contains miscellaneous information about the join
*/
void
final_cost_hashjoin(PlannerInfo *root, HashPath *path,
JoinCostWorkspace *workspace,
JoinPathExtraData *extra)
{
Path *outer_path = path->jpath.outerjoinpath;
Path *inner_path = path->jpath.innerjoinpath;
double outer_path_rows = outer_path->rows;
double inner_path_rows = inner_path->rows;
double inner_path_rows_total = workspace->inner_rows_total;
List *hashclauses = path->path_hashclauses;
Cost startup_cost = workspace->startup_cost;
Cost run_cost = workspace->run_cost;
int numbuckets = workspace->numbuckets;
int numbatches = workspace->numbatches;
Cost cpu_per_tuple;
QualCost hash_qual_cost;
QualCost qp_qual_cost;
double hashjointuples;
double virtualbuckets;
Selectivity innerbucketsize;
Selectivity innermcvfreq;
ListCell *hcl;
/* Mark the path with the correct row estimate */
if (path->jpath.path.param_info)
path->jpath.path.rows = path->jpath.path.param_info->ppi_rows;
else
path->jpath.path.rows = path->jpath.path.parent->rows;
/* For partial paths, scale row estimate. */
if (path->jpath.path.parallel_workers > 0)
{
double parallel_divisor = get_parallel_divisor(&path->jpath.path);
path->jpath.path.rows =
clamp_row_est(path->jpath.path.rows / parallel_divisor);
}
/*
* We could include disable_cost in the preliminary estimate, but that
* would amount to optimizing for the case where the join method is
* disabled, which doesn't seem like the way to bet.
*/
if (!enable_hashjoin)
startup_cost += disable_cost;
/* mark the path with estimated # of batches */
path->num_batches = numbatches;
/* store the total number of tuples (sum of partial row estimates) */
path->inner_rows_total = inner_path_rows_total;
/* and compute the number of "virtual" buckets in the whole join */
virtualbuckets = (double) numbuckets * (double) numbatches;
/*
* Determine bucketsize fraction and MCV frequency for the inner relation.
* We use the smallest bucketsize or MCV frequency estimated for any
* individual hashclause; this is undoubtedly conservative.
*
* BUT: if inner relation has been unique-ified, we can assume it's good
* for hashing. This is important both because it's the right answer, and
* because we avoid contaminating the cache with a value that's wrong for
* non-unique-ified paths.
*/
if (IsA(inner_path, UniquePath))
{
innerbucketsize = 1.0 / virtualbuckets;
innermcvfreq = 0.0;
}
else
{
innerbucketsize = 1.0;
innermcvfreq = 1.0;
foreach(hcl, hashclauses)
{
RestrictInfo *restrictinfo = lfirst_node(RestrictInfo, hcl);
Selectivity thisbucketsize;
Selectivity thismcvfreq;
/*
* First we have to figure out which side of the hashjoin clause
* is the inner side.
*
* Since we tend to visit the same clauses over and over when
* planning a large query, we cache the bucket stats estimates in
* the RestrictInfo node to avoid repeated lookups of statistics.
*/
if (bms_is_subset(restrictinfo->right_relids,
inner_path->parent->relids))
{
/* righthand side is inner */
thisbucketsize = restrictinfo->right_bucketsize;
if (thisbucketsize < 0)
{
/* not cached yet */
estimate_hash_bucket_stats(root,
get_rightop(restrictinfo->clause),
virtualbuckets,
&restrictinfo->right_mcvfreq,
&restrictinfo->right_bucketsize);
thisbucketsize = restrictinfo->right_bucketsize;
}
thismcvfreq = restrictinfo->right_mcvfreq;
}
else
{
Assert(bms_is_subset(restrictinfo->left_relids,
inner_path->parent->relids));
/* lefthand side is inner */
thisbucketsize = restrictinfo->left_bucketsize;
if (thisbucketsize < 0)
{
/* not cached yet */
estimate_hash_bucket_stats(root,
get_leftop(restrictinfo->clause),
virtualbuckets,
&restrictinfo->left_mcvfreq,
&restrictinfo->left_bucketsize);
thisbucketsize = restrictinfo->left_bucketsize;
}
thismcvfreq = restrictinfo->left_mcvfreq;
}
if (innerbucketsize > thisbucketsize)
innerbucketsize = thisbucketsize;
if (innermcvfreq > thismcvfreq)
innermcvfreq = thismcvfreq;
}
}
/*
* If the bucket holding the inner MCV would exceed hash_mem, we don't
* want to hash unless there is really no other alternative, so apply
* disable_cost. (The executor normally copes with excessive memory usage
* by splitting batches, but obviously it cannot separate equal values
* that way, so it will be unable to drive the batch size below hash_mem
* when this is true.)
*/
if (relation_byte_size(clamp_row_est(inner_path_rows * innermcvfreq),
inner_path->pathtarget->width) > get_hash_memory_limit())
startup_cost += disable_cost;
/*
* Compute cost of the hashquals and qpquals (other restriction clauses)
* separately.
*/
cost_qual_eval(&hash_qual_cost, hashclauses, root);
cost_qual_eval(&qp_qual_cost, path->jpath.joinrestrictinfo, root);
qp_qual_cost.startup -= hash_qual_cost.startup;
qp_qual_cost.per_tuple -= hash_qual_cost.per_tuple;
/* CPU costs */
if (path->jpath.jointype == JOIN_SEMI ||
path->jpath.jointype == JOIN_ANTI ||
extra->inner_unique)
{
double outer_matched_rows;
Selectivity inner_scan_frac;
/*
* With a SEMI or ANTI join, or if the innerrel is known unique, the
* executor will stop after the first match.
*
* For an outer-rel row that has at least one match, we can expect the
* bucket scan to stop after a fraction 1/(match_count+1) of the
* bucket's rows, if the matches are evenly distributed. Since they
* probably aren't quite evenly distributed, we apply a fuzz factor of
* 2.0 to that fraction. (If we used a larger fuzz factor, we'd have
* to clamp inner_scan_frac to at most 1.0; but since match_count is
* at least 1, no such clamp is needed now.)
*/
outer_matched_rows = rint(outer_path_rows * extra->semifactors.outer_match_frac);
inner_scan_frac = 2.0 / (extra->semifactors.match_count + 1.0);
startup_cost += hash_qual_cost.startup;
run_cost += hash_qual_cost.per_tuple * outer_matched_rows *
clamp_row_est(inner_path_rows * innerbucketsize * inner_scan_frac) * 0.5;
/*
* For unmatched outer-rel rows, the picture is quite a lot different.
* In the first place, there is no reason to assume that these rows
* preferentially hit heavily-populated buckets; instead assume they
* are uncorrelated with the inner distribution and so they see an
* average bucket size of inner_path_rows / virtualbuckets. In the
* second place, it seems likely that they will have few if any exact
* hash-code matches and so very few of the tuples in the bucket will
* actually require eval of the hash quals. We don't have any good
* way to estimate how many will, but for the moment assume that the
* effective cost per bucket entry is one-tenth what it is for
* matchable tuples.
*/
run_cost += hash_qual_cost.per_tuple *
(outer_path_rows - outer_matched_rows) *
clamp_row_est(inner_path_rows / virtualbuckets) * 0.05;
/* Get # of tuples that will pass the basic join */
if (path->jpath.jointype == JOIN_ANTI)
hashjointuples = outer_path_rows - outer_matched_rows;
else
hashjointuples = outer_matched_rows;
}
else
{
/*
* The number of tuple comparisons needed is the number of outer
* tuples times the typical number of tuples in a hash bucket, which
* is the inner relation size times its bucketsize fraction. At each
* one, we need to evaluate the hashjoin quals. But actually,
* charging the full qual eval cost at each tuple is pessimistic,
* since we don't evaluate the quals unless the hash values match
* exactly. For lack of a better idea, halve the cost estimate to
* allow for that.
*/
startup_cost += hash_qual_cost.startup;
run_cost += hash_qual_cost.per_tuple * outer_path_rows *
clamp_row_est(inner_path_rows * innerbucketsize) * 0.5;
/*
* Get approx # tuples passing the hashquals. We use
* approx_tuple_count here because we need an estimate done with
* JOIN_INNER semantics.
*/
hashjointuples = approx_tuple_count(root, &path->jpath, hashclauses);
}
/*
* For each tuple that gets through the hashjoin proper, we charge
* cpu_tuple_cost plus the cost of evaluating additional restriction
* clauses that are to be applied at the join. (This is pessimistic since
* not all of the quals may get evaluated at each tuple.)
*/
startup_cost += qp_qual_cost.startup;
cpu_per_tuple = cpu_tuple_cost + qp_qual_cost.per_tuple;
run_cost += cpu_per_tuple * hashjointuples;
/* tlist eval costs are paid per output row, not per tuple scanned */
startup_cost += path->jpath.path.pathtarget->cost.startup;
run_cost += path->jpath.path.pathtarget->cost.per_tuple * path->jpath.path.rows;
path->jpath.path.startup_cost = startup_cost;
path->jpath.path.total_cost = startup_cost + run_cost;
}
/*
* cost_subplan
* Figure the costs for a SubPlan (or initplan).
*
* Note: we could dig the subplan's Plan out of the root list, but in practice
* all callers have it handy already, so we make them pass it.
*/
void
cost_subplan(PlannerInfo *root, SubPlan *subplan, Plan *plan)
{
QualCost sp_cost;
/* Figure any cost for evaluating the testexpr */
cost_qual_eval(&sp_cost,
make_ands_implicit((Expr *) subplan->testexpr),
root);
if (subplan->useHashTable)
{
/*
* If we are using a hash table for the subquery outputs, then the
* cost of evaluating the query is a one-time cost. We charge one
* cpu_operator_cost per tuple for the work of loading the hashtable,
* too.
*/
sp_cost.startup += plan->total_cost +
cpu_operator_cost * plan->plan_rows;
/*
* The per-tuple costs include the cost of evaluating the lefthand
* expressions, plus the cost of probing the hashtable. We already
* accounted for the lefthand expressions as part of the testexpr, and
* will also have counted one cpu_operator_cost for each comparison
* operator. That is probably too low for the probing cost, but it's
* hard to make a better estimate, so live with it for now.
*/
}
else
{
/*
* Otherwise we will be rescanning the subplan output on each
* evaluation. We need to estimate how much of the output we will
* actually need to scan. NOTE: this logic should agree with the
* tuple_fraction estimates used by make_subplan() in
* plan/subselect.c.
*/
Cost plan_run_cost = plan->total_cost - plan->startup_cost;
if (subplan->subLinkType == EXISTS_SUBLINK)
{
/* we only need to fetch 1 tuple; clamp to avoid zero divide */
sp_cost.per_tuple += plan_run_cost / clamp_row_est(plan->plan_rows);
}
else if (subplan->subLinkType == ALL_SUBLINK ||
subplan->subLinkType == ANY_SUBLINK)
{
/* assume we need 50% of the tuples */
sp_cost.per_tuple += 0.50 * plan_run_cost;
/* also charge a cpu_operator_cost per row examined */
sp_cost.per_tuple += 0.50 * plan->plan_rows * cpu_operator_cost;
}
else
{
/* assume we need all tuples */
sp_cost.per_tuple += plan_run_cost;
}
/*
* Also account for subplan's startup cost. If the subplan is
* uncorrelated or undirect correlated, AND its topmost node is one
* that materializes its output, assume that we'll only need to pay
* its startup cost once; otherwise assume we pay the startup cost
* every time.
*/
if (subplan->parParam == NIL &&
ExecMaterializesOutput(nodeTag(plan)))
sp_cost.startup += plan->startup_cost;
else
sp_cost.per_tuple += plan->startup_cost;
}
subplan->startup_cost = sp_cost.startup;
subplan->per_call_cost = sp_cost.per_tuple;
}
/*
* cost_rescan
* Given a finished Path, estimate the costs of rescanning it after
* having done so the first time. For some Path types a rescan is
* cheaper than an original scan (if no parameters change), and this
* function embodies knowledge about that. The default is to return
* the same costs stored in the Path. (Note that the cost estimates
* actually stored in Paths are always for first scans.)
*
* This function is not currently intended to model effects such as rescans
* being cheaper due to disk block caching; what we are concerned with is
* plan types wherein the executor caches results explicitly, or doesn't
* redo startup calculations, etc.
*/
static void
cost_rescan(PlannerInfo *root, Path *path,
Cost *rescan_startup_cost, /* output parameters */
Cost *rescan_total_cost)
{
switch (path->pathtype)
{
case T_FunctionScan:
/*
* Currently, nodeFunctionscan.c always executes the function to
* completion before returning any rows, and caches the results in
* a tuplestore. So the function eval cost is all startup cost
* and isn't paid over again on rescans. However, all run costs
* will be paid over again.
*/
*rescan_startup_cost = 0;
*rescan_total_cost = path->total_cost - path->startup_cost;
break;
case T_HashJoin:
/*
* If it's a single-batch join, we don't need to rebuild the hash
* table during a rescan.
*/
if (((HashPath *) path)->num_batches == 1)
{
/* Startup cost is exactly the cost of hash table building */
*rescan_startup_cost = 0;
*rescan_total_cost = path->total_cost - path->startup_cost;
}
else
{
/* Otherwise, no special treatment */
*rescan_startup_cost = path->startup_cost;
*rescan_total_cost = path->total_cost;
}
break;
case T_CteScan:
case T_WorkTableScan:
{
/*
* These plan types materialize their final result in a
* tuplestore or tuplesort object. So the rescan cost is only
* cpu_tuple_cost per tuple, unless the result is large enough
* to spill to disk.
*/
Cost run_cost = cpu_tuple_cost * path->rows;
double nbytes = relation_byte_size(path->rows,
path->pathtarget->width);
long work_mem_bytes = work_mem * 1024L;
if (nbytes > work_mem_bytes)
{
/* It will spill, so account for re-read cost */
double npages = ceil(nbytes / BLCKSZ);
run_cost += seq_page_cost * npages;
}
*rescan_startup_cost = 0;
*rescan_total_cost = run_cost;
}
break;
case T_Material:
case T_Sort:
{
/*
* These plan types not only materialize their results, but do
* not implement qual filtering or projection. So they are
* even cheaper to rescan than the ones above. We charge only
* cpu_operator_cost per tuple. (Note: keep that in sync with
* the run_cost charge in cost_sort, and also see comments in
* cost_material before you change it.)
*/
Cost run_cost = cpu_operator_cost * path->rows;
double nbytes = relation_byte_size(path->rows,
path->pathtarget->width);
long work_mem_bytes = work_mem * 1024L;
if (nbytes > work_mem_bytes)
{
/* It will spill, so account for re-read cost */
double npages = ceil(nbytes / BLCKSZ);
run_cost += seq_page_cost * npages;
}
*rescan_startup_cost = 0;
*rescan_total_cost = run_cost;
}
break;
case T_Memoize:
/* All the hard work is done by cost_memoize_rescan */
cost_memoize_rescan(root, (MemoizePath *) path,
rescan_startup_cost, rescan_total_cost);
break;
default:
*rescan_startup_cost = path->startup_cost;
*rescan_total_cost = path->total_cost;
break;
}
}
/*
* cost_qual_eval
* Estimate the CPU costs of evaluating a WHERE clause.
* The input can be either an implicitly-ANDed list of boolean
* expressions, or a list of RestrictInfo nodes. (The latter is
* preferred since it allows caching of the results.)
* The result includes both a one-time (startup) component,
* and a per-evaluation component.
*/
void
cost_qual_eval(QualCost *cost, List *quals, PlannerInfo *root)
{
cost_qual_eval_context context;
ListCell *l;
context.root = root;
context.total.startup = 0;
context.total.per_tuple = 0;
/* We don't charge any cost for the implicit ANDing at top level ... */
foreach(l, quals)
{
Node *qual = (Node *) lfirst(l);
cost_qual_eval_walker(qual, &context);
}
*cost = context.total;
}
/*
* cost_qual_eval_node
* As above, for a single RestrictInfo or expression.
*/
void
cost_qual_eval_node(QualCost *cost, Node *qual, PlannerInfo *root)
{
cost_qual_eval_context context;
context.root = root;
context.total.startup = 0;
context.total.per_tuple = 0;
cost_qual_eval_walker(qual, &context);
*cost = context.total;
}
static bool
cost_qual_eval_walker(Node *node, cost_qual_eval_context *context)
{
if (node == NULL)
return false;
/*
* RestrictInfo nodes contain an eval_cost field reserved for this
* routine's use, so that it's not necessary to evaluate the qual clause's
* cost more than once. If the clause's cost hasn't been computed yet,
* the field's startup value will contain -1.
*/
if (IsA(node, RestrictInfo))
{
RestrictInfo *rinfo = (RestrictInfo *) node;
if (rinfo->eval_cost.startup < 0)
{
cost_qual_eval_context locContext;
locContext.root = context->root;
locContext.total.startup = 0;
locContext.total.per_tuple = 0;
/*
* For an OR clause, recurse into the marked-up tree so that we
* set the eval_cost for contained RestrictInfos too.
*/
if (rinfo->orclause)
cost_qual_eval_walker((Node *) rinfo->orclause, &locContext);
else
cost_qual_eval_walker((Node *) rinfo->clause, &locContext);
/*
* If the RestrictInfo is marked pseudoconstant, it will be tested
* only once, so treat its cost as all startup cost.
*/
if (rinfo->pseudoconstant)
{
/* count one execution during startup */
locContext.total.startup += locContext.total.per_tuple;
locContext.total.per_tuple = 0;
}
rinfo->eval_cost = locContext.total;
}
context->total.startup += rinfo->eval_cost.startup;
context->total.per_tuple += rinfo->eval_cost.per_tuple;
/* do NOT recurse into children */
return false;
}
/*
* For each operator or function node in the given tree, we charge the
* estimated execution cost given by pg_proc.procost (remember to multiply
* this by cpu_operator_cost).
*
* Vars and Consts are charged zero, and so are boolean operators (AND,
* OR, NOT). Simplistic, but a lot better than no model at all.
*
* Should we try to account for the possibility of short-circuit
* evaluation of AND/OR? Probably *not*, because that would make the
* results depend on the clause ordering, and we are not in any position
* to expect that the current ordering of the clauses is the one that's
* going to end up being used. The above per-RestrictInfo caching would
* not mix well with trying to re-order clauses anyway.
*
* Another issue that is entirely ignored here is that if a set-returning
* function is below top level in the tree, the functions/operators above
* it will need to be evaluated multiple times. In practical use, such
* cases arise so seldom as to not be worth the added complexity needed;
* moreover, since our rowcount estimates for functions tend to be pretty
* phony, the results would also be pretty phony.
*/
if (IsA(node, FuncExpr))
{
add_function_cost(context->root, ((FuncExpr *) node)->funcid, node,
&context->total);
}
else if (IsA(node, OpExpr) ||
IsA(node, DistinctExpr) ||
IsA(node, NullIfExpr))
{
/* rely on struct equivalence to treat these all alike */
set_opfuncid((OpExpr *) node);
add_function_cost(context->root, ((OpExpr *) node)->opfuncid, node,
&context->total);
}
else if (IsA(node, ScalarArrayOpExpr))
{
ScalarArrayOpExpr *saop = (ScalarArrayOpExpr *) node;
Node *arraynode = (Node *) lsecond(saop->args);
QualCost sacosts;
QualCost hcosts;
int estarraylen = estimate_array_length(arraynode);
set_sa_opfuncid(saop);
sacosts.startup = sacosts.per_tuple = 0;
add_function_cost(context->root, saop->opfuncid, NULL,
&sacosts);
if (OidIsValid(saop->hashfuncid))
{
/* Handle costs for hashed ScalarArrayOpExpr */
hcosts.startup = hcosts.per_tuple = 0;
add_function_cost(context->root, saop->hashfuncid, NULL, &hcosts);
context->total.startup += sacosts.startup + hcosts.startup;
/* Estimate the cost of building the hashtable. */
context->total.startup += estarraylen * hcosts.per_tuple;
/*
* XXX should we charge a little bit for sacosts.per_tuple when
* building the table, or is it ok to assume there will be zero
* hash collision?
*/
/*
* Charge for hashtable lookups. Charge a single hash and a
* single comparison.
*/
context->total.per_tuple += hcosts.per_tuple + sacosts.per_tuple;
}
else
{
/*
* Estimate that the operator will be applied to about half of the
* array elements before the answer is determined.
*/
context->total.startup += sacosts.startup;
context->total.per_tuple += sacosts.per_tuple *
estimate_array_length(arraynode) * 0.5;
}
}
else if (IsA(node, Aggref) ||
IsA(node, WindowFunc))
{
/*
* Aggref and WindowFunc nodes are (and should be) treated like Vars,
* ie, zero execution cost in the current model, because they behave
* essentially like Vars at execution. We disregard the costs of
* their input expressions for the same reason. The actual execution
* costs of the aggregate/window functions and their arguments have to
* be factored into plan-node-specific costing of the Agg or WindowAgg
* plan node.
*/
return false; /* don't recurse into children */
}
else if (IsA(node, GroupingFunc))
{
/* Treat this as having cost 1 */
context->total.per_tuple += cpu_operator_cost;
return false; /* don't recurse into children */
}
else if (IsA(node, CoerceViaIO))
{
CoerceViaIO *iocoerce = (CoerceViaIO *) node;
Oid iofunc;
Oid typioparam;
bool typisvarlena;
/* check the result type's input function */
getTypeInputInfo(iocoerce->resulttype,
&iofunc, &typioparam);
add_function_cost(context->root, iofunc, NULL,
&context->total);
/* check the input type's output function */
getTypeOutputInfo(exprType((Node *) iocoerce->arg),
&iofunc, &typisvarlena);
add_function_cost(context->root, iofunc, NULL,
&context->total);
}
else if (IsA(node, ArrayCoerceExpr))
{
ArrayCoerceExpr *acoerce = (ArrayCoerceExpr *) node;
QualCost perelemcost;
cost_qual_eval_node(&perelemcost, (Node *) acoerce->elemexpr,
context->root);
context->total.startup += perelemcost.startup;
if (perelemcost.per_tuple > 0)
context->total.per_tuple += perelemcost.per_tuple *
estimate_array_length((Node *) acoerce->arg);
}
else if (IsA(node, RowCompareExpr))
{
/* Conservatively assume we will check all the columns */
RowCompareExpr *rcexpr = (RowCompareExpr *) node;
ListCell *lc;
foreach(lc, rcexpr->opnos)
{
Oid opid = lfirst_oid(lc);
add_function_cost(context->root, get_opcode(opid), NULL,
&context->total);
}
}
else if (IsA(node, MinMaxExpr) ||
IsA(node, SQLValueFunction) ||
IsA(node, XmlExpr) ||
IsA(node, CoerceToDomain) ||
IsA(node, NextValueExpr) ||
IsA(node, JsonExpr))
{
/* Treat all these as having cost 1 */
context->total.per_tuple += cpu_operator_cost;
}
else if (IsA(node, CurrentOfExpr))
{
/* Report high cost to prevent selection of anything but TID scan */
context->total.startup += disable_cost;
}
else if (IsA(node, SubLink))
{
/* This routine should not be applied to un-planned expressions */
elog(ERROR, "cannot handle unplanned sub-select");
}
else if (IsA(node, SubPlan))
{
/*
* A subplan node in an expression typically indicates that the
* subplan will be executed on each evaluation, so charge accordingly.
* (Sub-selects that can be executed as InitPlans have already been
* removed from the expression.)
*/
SubPlan *subplan = (SubPlan *) node;
context->total.startup += subplan->startup_cost;
context->total.per_tuple += subplan->per_call_cost;
/*
* We don't want to recurse into the testexpr, because it was already
* counted in the SubPlan node's costs. So we're done.
*/
return false;
}
else if (IsA(node, AlternativeSubPlan))
{
/*
* Arbitrarily use the first alternative plan for costing. (We should
* certainly only include one alternative, and we don't yet have
* enough information to know which one the executor is most likely to
* use.)
*/
AlternativeSubPlan *asplan = (AlternativeSubPlan *) node;
return cost_qual_eval_walker((Node *) linitial(asplan->subplans),
context);
}
else if (IsA(node, PlaceHolderVar))
{
/*
* A PlaceHolderVar should be given cost zero when considering general
* expression evaluation costs. The expense of doing the contained
* expression is charged as part of the tlist eval costs of the scan
* or join where the PHV is first computed (see set_rel_width and
* add_placeholders_to_joinrel). If we charged it again here, we'd be
* double-counting the cost for each level of plan that the PHV
* bubbles up through. Hence, return without recursing into the
* phexpr.
*/
return false;
}
/* recurse into children */
return expression_tree_walker(node, cost_qual_eval_walker,
(void *) context);
}
/*
* get_restriction_qual_cost
* Compute evaluation costs of a baserel's restriction quals, plus any
* movable join quals that have been pushed down to the scan.
* Results are returned into *qpqual_cost.
*
* This is a convenience subroutine that works for seqscans and other cases
* where all the given quals will be evaluated the hard way. It's not useful
* for cost_index(), for example, where the index machinery takes care of
* some of the quals. We assume baserestrictcost was previously set by
* set_baserel_size_estimates().
*/
static void
get_restriction_qual_cost(PlannerInfo *root, RelOptInfo *baserel,
ParamPathInfo *param_info,
QualCost *qpqual_cost)
{
if (param_info)
{
/* Include costs of pushed-down clauses */
cost_qual_eval(qpqual_cost, param_info->ppi_clauses, root);
qpqual_cost->startup += baserel->baserestrictcost.startup;
qpqual_cost->per_tuple += baserel->baserestrictcost.per_tuple;
}
else
*qpqual_cost = baserel->baserestrictcost;
}
/*
* compute_semi_anti_join_factors
* Estimate how much of the inner input a SEMI, ANTI, or inner_unique join
* can be expected to scan.
*
* In a hash or nestloop SEMI/ANTI join, the executor will stop scanning
* inner rows as soon as it finds a match to the current outer row.
* The same happens if we have detected the inner rel is unique.
* We should therefore adjust some of the cost components for this effect.
* This function computes some estimates needed for these adjustments.
* These estimates will be the same regardless of the particular paths used
* for the outer and inner relation, so we compute these once and then pass
* them to all the join cost estimation functions.
*
* Input parameters:
* joinrel: join relation under consideration
* outerrel: outer relation under consideration
* innerrel: inner relation under consideration
* jointype: if not JOIN_SEMI or JOIN_ANTI, we assume it's inner_unique
* sjinfo: SpecialJoinInfo relevant to this join
* restrictlist: join quals
* Output parameters:
* *semifactors is filled in (see pathnodes.h for field definitions)
*/
void
compute_semi_anti_join_factors(PlannerInfo *root,
RelOptInfo *joinrel,
RelOptInfo *outerrel,
RelOptInfo *innerrel,
JoinType jointype,
SpecialJoinInfo *sjinfo,
List *restrictlist,
SemiAntiJoinFactors *semifactors)
{
Selectivity jselec;
Selectivity nselec;
Selectivity avgmatch;
SpecialJoinInfo norm_sjinfo;
List *joinquals;
ListCell *l;
/*
* In an ANTI join, we must ignore clauses that are "pushed down", since
* those won't affect the match logic. In a SEMI join, we do not
* distinguish joinquals from "pushed down" quals, so just use the whole
* restrictinfo list. For other outer join types, we should consider only
* non-pushed-down quals, so that this devolves to an IS_OUTER_JOIN check.
*/
if (IS_OUTER_JOIN(jointype))
{
joinquals = NIL;
foreach(l, restrictlist)
{
RestrictInfo *rinfo = lfirst_node(RestrictInfo, l);
if (!RINFO_IS_PUSHED_DOWN(rinfo, joinrel->relids))
joinquals = lappend(joinquals, rinfo);
}
}
else
joinquals = restrictlist;
/*
* Get the JOIN_SEMI or JOIN_ANTI selectivity of the join clauses.
*/
jselec = clauselist_selectivity(root,
joinquals,
0,
(jointype == JOIN_ANTI) ? JOIN_ANTI : JOIN_SEMI,
sjinfo);
/*
* Also get the normal inner-join selectivity of the join clauses.
*/
norm_sjinfo.type = T_SpecialJoinInfo;
norm_sjinfo.min_lefthand = outerrel->relids;
norm_sjinfo.min_righthand = innerrel->relids;
norm_sjinfo.syn_lefthand = outerrel->relids;
norm_sjinfo.syn_righthand = innerrel->relids;
norm_sjinfo.jointype = JOIN_INNER;
/* we don't bother trying to make the remaining fields valid */
norm_sjinfo.lhs_strict = false;
norm_sjinfo.delay_upper_joins = false;
norm_sjinfo.semi_can_btree = false;
norm_sjinfo.semi_can_hash = false;
norm_sjinfo.semi_operators = NIL;
norm_sjinfo.semi_rhs_exprs = NIL;
nselec = clauselist_selectivity(root,
joinquals,
0,
JOIN_INNER,
&norm_sjinfo);
/* Avoid leaking a lot of ListCells */
if (IS_OUTER_JOIN(jointype))
list_free(joinquals);
/*
* jselec can be interpreted as the fraction of outer-rel rows that have
* any matches (this is true for both SEMI and ANTI cases). And nselec is
* the fraction of the Cartesian product that matches. So, the average
* number of matches for each outer-rel row that has at least one match is
* nselec * inner_rows / jselec.
*
* Note: it is correct to use the inner rel's "rows" count here, even
* though we might later be considering a parameterized inner path with
* fewer rows. This is because we have included all the join clauses in
* the selectivity estimate.
*/
if (jselec > 0) /* protect against zero divide */
{
avgmatch = nselec * innerrel->rows / jselec;
/* Clamp to sane range */
avgmatch = Max(1.0, avgmatch);
}
else
avgmatch = 1.0;
semifactors->outer_match_frac = jselec;
semifactors->match_count = avgmatch;
}
/*
* has_indexed_join_quals
* Check whether all the joinquals of a nestloop join are used as
* inner index quals.
*
* If the inner path of a SEMI/ANTI join is an indexscan (including bitmap
* indexscan) that uses all the joinquals as indexquals, we can assume that an
* unmatched outer tuple is cheap to process, whereas otherwise it's probably
* expensive.
*/
static bool
has_indexed_join_quals(NestPath *path)
{
JoinPath *joinpath = &path->jpath;
Relids joinrelids = joinpath->path.parent->relids;
Path *innerpath = joinpath->innerjoinpath;
List *indexclauses;
bool found_one;
ListCell *lc;
/* If join still has quals to evaluate, it's not fast */
if (joinpath->joinrestrictinfo != NIL)
return false;
/* Nor if the inner path isn't parameterized at all */
if (innerpath->param_info == NULL)
return false;
/* Find the indexclauses list for the inner scan */
switch (innerpath->pathtype)
{
case T_IndexScan:
case T_IndexOnlyScan:
indexclauses = ((IndexPath *) innerpath)->indexclauses;
break;
case T_BitmapHeapScan:
{
/* Accept only a simple bitmap scan, not AND/OR cases */
Path *bmqual = ((BitmapHeapPath *) innerpath)->bitmapqual;
if (IsA(bmqual, IndexPath))
indexclauses = ((IndexPath *) bmqual)->indexclauses;
else
return false;
break;
}
default:
/*
* If it's not a simple indexscan, it probably doesn't run quickly
* for zero rows out, even if it's a parameterized path using all
* the joinquals.
*/
return false;
}
/*
* Examine the inner path's param clauses. Any that are from the outer
* path must be found in the indexclauses list, either exactly or in an
* equivalent form generated by equivclass.c. Also, we must find at least
* one such clause, else it's a clauseless join which isn't fast.
*/
found_one = false;
foreach(lc, innerpath->param_info->ppi_clauses)
{
RestrictInfo *rinfo = (RestrictInfo *) lfirst(lc);
if (join_clause_is_movable_into(rinfo,
innerpath->parent->relids,
joinrelids))
{
if (!is_redundant_with_indexclauses(rinfo, indexclauses))
return false;
found_one = true;
}
}
return found_one;
}
/*
* approx_tuple_count
* Quick-and-dirty estimation of the number of join rows passing
* a set of qual conditions.
*
* The quals can be either an implicitly-ANDed list of boolean expressions,
* or a list of RestrictInfo nodes (typically the latter).
*
* We intentionally compute the selectivity under JOIN_INNER rules, even
* if it's some type of outer join. This is appropriate because we are
* trying to figure out how many tuples pass the initial merge or hash
* join step.
*
* This is quick-and-dirty because we bypass clauselist_selectivity, and
* simply multiply the independent clause selectivities together. Now
* clauselist_selectivity often can't do any better than that anyhow, but
* for some situations (such as range constraints) it is smarter. However,
* we can't effectively cache the results of clauselist_selectivity, whereas
* the individual clause selectivities can be and are cached.
*
* Since we are only using the results to estimate how many potential
* output tuples are generated and passed through qpqual checking, it
* seems OK to live with the approximation.
*/
static double
approx_tuple_count(PlannerInfo *root, JoinPath *path, List *quals)
{
double tuples;
double outer_tuples = path->outerjoinpath->rows;
double inner_tuples = path->innerjoinpath->rows;
SpecialJoinInfo sjinfo;
Selectivity selec = 1.0;
ListCell *l;
/*
* Make up a SpecialJoinInfo for JOIN_INNER semantics.
*/
sjinfo.type = T_SpecialJoinInfo;
sjinfo.min_lefthand = path->outerjoinpath->parent->relids;
sjinfo.min_righthand = path->innerjoinpath->parent->relids;
sjinfo.syn_lefthand = path->outerjoinpath->parent->relids;
sjinfo.syn_righthand = path->innerjoinpath->parent->relids;
sjinfo.jointype = JOIN_INNER;
/* we don't bother trying to make the remaining fields valid */
sjinfo.lhs_strict = false;
sjinfo.delay_upper_joins = false;
sjinfo.semi_can_btree = false;
sjinfo.semi_can_hash = false;
sjinfo.semi_operators = NIL;
sjinfo.semi_rhs_exprs = NIL;
/* Get the approximate selectivity */
foreach(l, quals)
{
Node *qual = (Node *) lfirst(l);
/* Note that clause_selectivity will be able to cache its result */
selec *= clause_selectivity(root, qual, 0, JOIN_INNER, &sjinfo);
}
/* Apply it to the input relation sizes */
tuples = selec * outer_tuples * inner_tuples;
return clamp_row_est(tuples);
}
/*
* set_baserel_size_estimates
* Set the size estimates for the given base relation.
*
* The rel's targetlist and restrictinfo list must have been constructed
* already, and rel->tuples must be set.
*
* We set the following fields of the rel node:
* rows: the estimated number of output tuples (after applying
* restriction clauses).
* width: the estimated average output tuple width in bytes.
* baserestrictcost: estimated cost of evaluating baserestrictinfo clauses.
*/
void
set_baserel_size_estimates(PlannerInfo *root, RelOptInfo *rel)
{
double nrows;
/* Should only be applied to base relations */
Assert(rel->relid > 0);
nrows = rel->tuples *
clauselist_selectivity(root,
rel->baserestrictinfo,
0,
JOIN_INNER,
NULL);
rel->rows = clamp_row_est(nrows);
cost_qual_eval(&rel->baserestrictcost, rel->baserestrictinfo, root);
set_rel_width(root, rel);
}
/*
* get_parameterized_baserel_size
* Make a size estimate for a parameterized scan of a base relation.
*
* 'param_clauses' lists the additional join clauses to be used.
*
* set_baserel_size_estimates must have been applied already.
*/
double
get_parameterized_baserel_size(PlannerInfo *root, RelOptInfo *rel,
List *param_clauses)
{
List *allclauses;
double nrows;
/*
* Estimate the number of rows returned by the parameterized scan, knowing
* that it will apply all the extra join clauses as well as the rel's own
* restriction clauses. Note that we force the clauses to be treated as
* non-join clauses during selectivity estimation.
*/
allclauses = list_concat_copy(param_clauses, rel->baserestrictinfo);
nrows = rel->tuples *
clauselist_selectivity(root,
allclauses,
rel->relid, /* do not use 0! */
JOIN_INNER,
NULL);
nrows = clamp_row_est(nrows);
/* For safety, make sure result is not more than the base estimate */
if (nrows > rel->rows)
nrows = rel->rows;
return nrows;
}
/*
* set_joinrel_size_estimates
* Set the size estimates for the given join relation.
*
* The rel's targetlist must have been constructed already, and a
* restriction clause list that matches the given component rels must
* be provided.
*
* Since there is more than one way to make a joinrel for more than two
* base relations, the results we get here could depend on which component
* rel pair is provided. In theory we should get the same answers no matter
* which pair is provided; in practice, since the selectivity estimation
* routines don't handle all cases equally well, we might not. But there's
* not much to be done about it. (Would it make sense to repeat the
* calculations for each pair of input rels that's encountered, and somehow
* average the results? Probably way more trouble than it's worth, and
* anyway we must keep the rowcount estimate the same for all paths for the
* joinrel.)
*
* We set only the rows field here. The reltarget field was already set by
* build_joinrel_tlist, and baserestrictcost is not used for join rels.
*/
void
set_joinrel_size_estimates(PlannerInfo *root, RelOptInfo *rel,
RelOptInfo *outer_rel,
RelOptInfo *inner_rel,
SpecialJoinInfo *sjinfo,
List *restrictlist)
{
rel->rows = calc_joinrel_size_estimate(root,
rel,
outer_rel,
inner_rel,
outer_rel->rows,
inner_rel->rows,
sjinfo,
restrictlist);
}
/*
* get_parameterized_joinrel_size
* Make a size estimate for a parameterized scan of a join relation.
*
* 'rel' is the joinrel under consideration.
* 'outer_path', 'inner_path' are (probably also parameterized) Paths that
* produce the relations being joined.
* 'sjinfo' is any SpecialJoinInfo relevant to this join.
* 'restrict_clauses' lists the join clauses that need to be applied at the
* join node (including any movable clauses that were moved down to this join,
* and not including any movable clauses that were pushed down into the
* child paths).
*
* set_joinrel_size_estimates must have been applied already.
*/
double
get_parameterized_joinrel_size(PlannerInfo *root, RelOptInfo *rel,
Path *outer_path,
Path *inner_path,
SpecialJoinInfo *sjinfo,
List *restrict_clauses)
{
double nrows;
/*
* Estimate the number of rows returned by the parameterized join as the
* sizes of the input paths times the selectivity of the clauses that have
* ended up at this join node.
*
* As with set_joinrel_size_estimates, the rowcount estimate could depend
* on the pair of input paths provided, though ideally we'd get the same
* estimate for any pair with the same parameterization.
*/
nrows = calc_joinrel_size_estimate(root,
rel,
outer_path->parent,
inner_path->parent,
outer_path->rows,
inner_path->rows,
sjinfo,
restrict_clauses);
/* For safety, make sure result is not more than the base estimate */
if (nrows > rel->rows)
nrows = rel->rows;
return nrows;
}
/*
* calc_joinrel_size_estimate
* Workhorse for set_joinrel_size_estimates and
* get_parameterized_joinrel_size.
*
* outer_rel/inner_rel are the relations being joined, but they should be
* assumed to have sizes outer_rows/inner_rows; those numbers might be less
* than what rel->rows says, when we are considering parameterized paths.
*/
static double
calc_joinrel_size_estimate(PlannerInfo *root,
RelOptInfo *joinrel,
RelOptInfo *outer_rel,
RelOptInfo *inner_rel,
double outer_rows,
double inner_rows,
SpecialJoinInfo *sjinfo,
List *restrictlist)
{
JoinType jointype = sjinfo->jointype;
Selectivity fkselec;
Selectivity jselec;
Selectivity pselec;
double nrows;
/*
* Compute joinclause selectivity. Note that we are only considering
* clauses that become restriction clauses at this join level; we are not
* double-counting them because they were not considered in estimating the
* sizes of the component rels.
*
* First, see whether any of the joinclauses can be matched to known FK
* constraints. If so, drop those clauses from the restrictlist, and
* instead estimate their selectivity using FK semantics. (We do this
* without regard to whether said clauses are local or "pushed down".
* Probably, an FK-matching clause could never be seen as pushed down at
* an outer join, since it would be strict and hence would be grounds for
* join strength reduction.) fkselec gets the net selectivity for
* FK-matching clauses, or 1.0 if there are none.
*/
fkselec = get_foreign_key_join_selectivity(root,
outer_rel->relids,
inner_rel->relids,
sjinfo,
&restrictlist);
/*
* For an outer join, we have to distinguish the selectivity of the join's
* own clauses (JOIN/ON conditions) from any clauses that were "pushed
* down". For inner joins we just count them all as joinclauses.
*/
if (IS_OUTER_JOIN(jointype))
{
List *joinquals = NIL;
List *pushedquals = NIL;
ListCell *l;
/* Grovel through the clauses to separate into two lists */
foreach(l, restrictlist)
{
RestrictInfo *rinfo = lfirst_node(RestrictInfo, l);
if (RINFO_IS_PUSHED_DOWN(rinfo, joinrel->relids))
pushedquals = lappend(pushedquals, rinfo);
else
joinquals = lappend(joinquals, rinfo);
}
/* Get the separate selectivities */
jselec = clauselist_selectivity(root,
joinquals,
0,
jointype,
sjinfo);
pselec = clauselist_selectivity(root,
pushedquals,
0,
jointype,
sjinfo);
/* Avoid leaking a lot of ListCells */
list_free(joinquals);
list_free(pushedquals);
}
else
{
jselec = clauselist_selectivity(root,
restrictlist,
0,
jointype,
sjinfo);
pselec = 0.0; /* not used, keep compiler quiet */
}
/*
* Basically, we multiply size of Cartesian product by selectivity.
*
* If we are doing an outer join, take that into account: the joinqual
* selectivity has to be clamped using the knowledge that the output must
* be at least as large as the non-nullable input. However, any
* pushed-down quals are applied after the outer join, so their
* selectivity applies fully.
*
* For JOIN_SEMI and JOIN_ANTI, the selectivity is defined as the fraction
* of LHS rows that have matches, and we apply that straightforwardly.
*/
switch (jointype)
{
case JOIN_INNER:
nrows = outer_rows * inner_rows * fkselec * jselec;
/* pselec not used */
break;
case JOIN_LEFT:
nrows = outer_rows * inner_rows * fkselec * jselec;
if (nrows < outer_rows)
nrows = outer_rows;
nrows *= pselec;
break;
case JOIN_FULL:
nrows = outer_rows * inner_rows * fkselec * jselec;
if (nrows < outer_rows)
nrows = outer_rows;
if (nrows < inner_rows)
nrows = inner_rows;
nrows *= pselec;
break;
case JOIN_SEMI:
nrows = outer_rows * fkselec * jselec;
/* pselec not used */
break;
case JOIN_ANTI:
nrows = outer_rows * (1.0 - fkselec * jselec);
nrows *= pselec;
break;
default:
/* other values not expected here */
elog(ERROR, "unrecognized join type: %d", (int) jointype);
nrows = 0; /* keep compiler quiet */
break;
}
return clamp_row_est(nrows);
}
/*
* get_foreign_key_join_selectivity
* Estimate join selectivity for foreign-key-related clauses.
*
* Remove any clauses that can be matched to FK constraints from *restrictlist,
* and return a substitute estimate of their selectivity. 1.0 is returned
* when there are no such clauses.
*
* The reason for treating such clauses specially is that we can get better
* estimates this way than by relying on clauselist_selectivity(), especially
* for multi-column FKs where that function's assumption that the clauses are
* independent falls down badly. But even with single-column FKs, we may be
* able to get a better answer when the pg_statistic stats are missing or out
* of date.
*/
static Selectivity
get_foreign_key_join_selectivity(PlannerInfo *root,
Relids outer_relids,
Relids inner_relids,
SpecialJoinInfo *sjinfo,
List **restrictlist)
{
Selectivity fkselec = 1.0;
JoinType jointype = sjinfo->jointype;
List *worklist = *restrictlist;
ListCell *lc;
/* Consider each FK constraint that is known to match the query */
foreach(lc, root->fkey_list)
{
ForeignKeyOptInfo *fkinfo = (ForeignKeyOptInfo *) lfirst(lc);
bool ref_is_outer;
List *removedlist;
ListCell *cell;
/*
* This FK is not relevant unless it connects a baserel on one side of
* this join to a baserel on the other side.
*/
if (bms_is_member(fkinfo->con_relid, outer_relids) &&
bms_is_member(fkinfo->ref_relid, inner_relids))
ref_is_outer = false;
else if (bms_is_member(fkinfo->ref_relid, outer_relids) &&
bms_is_member(fkinfo->con_relid, inner_relids))
ref_is_outer = true;
else
continue;
/*
* If we're dealing with a semi/anti join, and the FK's referenced
* relation is on the outside, then knowledge of the FK doesn't help
* us figure out what we need to know (which is the fraction of outer
* rows that have matches). On the other hand, if the referenced rel
* is on the inside, then all outer rows must have matches in the
* referenced table (ignoring nulls). But any restriction or join
* clauses that filter that table will reduce the fraction of matches.
* We can account for restriction clauses, but it's too hard to guess
* how many table rows would get through a join that's inside the RHS.
* Hence, if either case applies, punt and ignore the FK.
*/
if ((jointype == JOIN_SEMI || jointype == JOIN_ANTI) &&
(ref_is_outer || bms_membership(inner_relids) != BMS_SINGLETON))
continue;
/*
* Modify the restrictlist by removing clauses that match the FK (and
* putting them into removedlist instead). It seems unsafe to modify
* the originally-passed List structure, so we make a shallow copy the
* first time through.
*/
if (worklist == *restrictlist)
worklist = list_copy(worklist);
removedlist = NIL;
foreach(cell, worklist)
{
RestrictInfo *rinfo = (RestrictInfo *) lfirst(cell);
bool remove_it = false;
int i;
/* Drop this clause if it matches any column of the FK */
for (i = 0; i < fkinfo->nkeys; i++)
{
if (rinfo->parent_ec)
{
/*
* EC-derived clauses can only match by EC. It is okay to
* consider any clause derived from the same EC as
* matching the FK: even if equivclass.c chose to generate
* a clause equating some other pair of Vars, it could
* have generated one equating the FK's Vars. So for
* purposes of estimation, we can act as though it did so.
*
* Note: checking parent_ec is a bit of a cheat because
* there are EC-derived clauses that don't have parent_ec
* set; but such clauses must compare expressions that
* aren't just Vars, so they cannot match the FK anyway.
*/
if (fkinfo->eclass[i] == rinfo->parent_ec)
{
remove_it = true;
break;
}
}
else
{
/*
* Otherwise, see if rinfo was previously matched to FK as
* a "loose" clause.
*/
if (list_member_ptr(fkinfo->rinfos[i], rinfo))
{
remove_it = true;
break;
}
}
}
if (remove_it)
{
worklist = foreach_delete_current(worklist, cell);
removedlist = lappend(removedlist, rinfo);
}
}
/*
* If we failed to remove all the matching clauses we expected to
* find, chicken out and ignore this FK; applying its selectivity
* might result in double-counting. Put any clauses we did manage to
* remove back into the worklist.
*
* Since the matching clauses are known not outerjoin-delayed, they
* would normally have appeared in the initial joinclause list. If we
* didn't find them, there are two possibilities:
*
* 1. If the FK match is based on an EC that is ec_has_const, it won't
* have generated any join clauses at all. We discount such ECs while
* checking to see if we have "all" the clauses. (Below, we'll adjust
* the selectivity estimate for this case.)
*
* 2. The clauses were matched to some other FK in a previous
* iteration of this loop, and thus removed from worklist. (A likely
* case is that two FKs are matched to the same EC; there will be only
* one EC-derived clause in the initial list, so the first FK will
* consume it.) Applying both FKs' selectivity independently risks
* underestimating the join size; in particular, this would undo one
* of the main things that ECs were invented for, namely to avoid
* double-counting the selectivity of redundant equality conditions.
* Later we might think of a reasonable way to combine the estimates,
* but for now, just punt, since this is a fairly uncommon situation.
*/
if (removedlist == NIL ||
list_length(removedlist) !=
(fkinfo->nmatched_ec - fkinfo->nconst_ec + fkinfo->nmatched_ri))
{
worklist = list_concat(worklist, removedlist);
continue;
}
/*
* Finally we get to the payoff: estimate selectivity using the
* knowledge that each referencing row will match exactly one row in
* the referenced table.
*
* XXX that's not true in the presence of nulls in the referencing
* column(s), so in principle we should derate the estimate for those.
* However (1) if there are any strict restriction clauses for the
* referencing column(s) elsewhere in the query, derating here would
* be double-counting the null fraction, and (2) it's not very clear
* how to combine null fractions for multiple referencing columns. So
* we do nothing for now about correcting for nulls.
*
* XXX another point here is that if either side of an FK constraint
* is an inheritance parent, we estimate as though the constraint
* covers all its children as well. This is not an unreasonable
* assumption for a referencing table, ie the user probably applied
* identical constraints to all child tables (though perhaps we ought
* to check that). But it's not possible to have done that for a
* referenced table. Fortunately, precisely because that doesn't
* work, it is uncommon in practice to have an FK referencing a parent
* table. So, at least for now, disregard inheritance here.
*/
if (jointype == JOIN_SEMI || jointype == JOIN_ANTI)
{
/*
* For JOIN_SEMI and JOIN_ANTI, we only get here when the FK's
* referenced table is exactly the inside of the join. The join
* selectivity is defined as the fraction of LHS rows that have
* matches. The FK implies that every LHS row has a match *in the
* referenced table*; but any restriction clauses on it will
* reduce the number of matches. Hence we take the join
* selectivity as equal to the selectivity of the table's
* restriction clauses, which is rows / tuples; but we must guard
* against tuples == 0.
*/
RelOptInfo *ref_rel = find_base_rel(root, fkinfo->ref_relid);
double ref_tuples = Max(ref_rel->tuples, 1.0);
fkselec *= ref_rel->rows / ref_tuples;
}
else
{
/*
* Otherwise, selectivity is exactly 1/referenced-table-size; but
* guard against tuples == 0. Note we should use the raw table
* tuple count, not any estimate of its filtered or joined size.
*/
RelOptInfo *ref_rel = find_base_rel(root, fkinfo->ref_relid);
double ref_tuples = Max(ref_rel->tuples, 1.0);
fkselec *= 1.0 / ref_tuples;
}
/*
* If any of the FK columns participated in ec_has_const ECs, then
* equivclass.c will have generated "var = const" restrictions for
* each side of the join, thus reducing the sizes of both input
* relations. Taking the fkselec at face value would amount to
* double-counting the selectivity of the constant restriction for the
* referencing Var. Hence, look for the restriction clause(s) that
* were applied to the referencing Var(s), and divide out their
* selectivity to correct for this.
*/
if (fkinfo->nconst_ec > 0)
{
for (int i = 0; i < fkinfo->nkeys; i++)
{
EquivalenceClass *ec = fkinfo->eclass[i];
if (ec && ec->ec_has_const)
{
EquivalenceMember *em = fkinfo->fk_eclass_member[i];
RestrictInfo *rinfo = find_derived_clause_for_ec_member(ec,
em);
if (rinfo)
{
Selectivity s0;
s0 = clause_selectivity(root,
(Node *) rinfo,
0,
jointype,
sjinfo);
if (s0 > 0)
fkselec /= s0;
}
}
}
}
}
*restrictlist = worklist;
CLAMP_PROBABILITY(fkselec);
return fkselec;
}
/*
* set_subquery_size_estimates
* Set the size estimates for a base relation that is a subquery.
*
* The rel's targetlist and restrictinfo list must have been constructed
* already, and the Paths for the subquery must have been completed.
* We look at the subquery's PlannerInfo to extract data.
*
* We set the same fields as set_baserel_size_estimates.
*/
void
set_subquery_size_estimates(PlannerInfo *root, RelOptInfo *rel)
{
PlannerInfo *subroot = rel->subroot;
RelOptInfo *sub_final_rel;
ListCell *lc;
/* Should only be applied to base relations that are subqueries */
Assert(rel->relid > 0);
Assert(planner_rt_fetch(rel->relid, root)->rtekind == RTE_SUBQUERY);
/*
* Copy raw number of output rows from subquery. All of its paths should
* have the same output rowcount, so just look at cheapest-total.
*/
sub_final_rel = fetch_upper_rel(subroot, UPPERREL_FINAL, NULL);
rel->tuples = sub_final_rel->cheapest_total_path->rows;
/*
* Compute per-output-column width estimates by examining the subquery's
* targetlist. For any output that is a plain Var, get the width estimate
* that was made while planning the subquery. Otherwise, we leave it to
* set_rel_width to fill in a datatype-based default estimate.
*/
foreach(lc, subroot->parse->targetList)
{
TargetEntry *te = lfirst_node(TargetEntry, lc);
Node *texpr = (Node *) te->expr;
int32 item_width = 0;
/* junk columns aren't visible to upper query */
if (te->resjunk)
continue;
/*
* The subquery could be an expansion of a view that's had columns
* added to it since the current query was parsed, so that there are
* non-junk tlist columns in it that don't correspond to any column
* visible at our query level. Ignore such columns.
*/
if (te->resno < rel->min_attr || te->resno > rel->max_attr)
continue;
/*
* XXX This currently doesn't work for subqueries containing set
* operations, because the Vars in their tlists are bogus references
* to the first leaf subquery, which wouldn't give the right answer
* even if we could still get to its PlannerInfo.
*
* Also, the subquery could be an appendrel for which all branches are
* known empty due to constraint exclusion, in which case
* set_append_rel_pathlist will have left the attr_widths set to zero.
*
* In either case, we just leave the width estimate zero until
* set_rel_width fixes it.
*/
if (IsA(texpr, Var) &&
subroot->parse->setOperations == NULL)
{
Var *var = (Var *) texpr;
RelOptInfo *subrel = find_base_rel(subroot, var->varno);
item_width = subrel->attr_widths[var->varattno - subrel->min_attr];
}
rel->attr_widths[te->resno - rel->min_attr] = item_width;
}
/* Now estimate number of output rows, etc */
set_baserel_size_estimates(root, rel);
}
/*
* set_function_size_estimates
* Set the size estimates for a base relation that is a function call.
*
* The rel's targetlist and restrictinfo list must have been constructed
* already.
*
* We set the same fields as set_baserel_size_estimates.
*/
void
set_function_size_estimates(PlannerInfo *root, RelOptInfo *rel)
{
RangeTblEntry *rte;
ListCell *lc;
/* Should only be applied to base relations that are functions */
Assert(rel->relid > 0);
rte = planner_rt_fetch(rel->relid, root);
Assert(rte->rtekind == RTE_FUNCTION);
/*
* Estimate number of rows the functions will return. The rowcount of the
* node is that of the largest function result.
*/
rel->tuples = 0;
foreach(lc, rte->functions)
{
RangeTblFunction *rtfunc = (RangeTblFunction *) lfirst(lc);
double ntup = expression_returns_set_rows(root, rtfunc->funcexpr);
if (ntup > rel->tuples)
rel->tuples = ntup;
}
/* Now estimate number of output rows, etc */
set_baserel_size_estimates(root, rel);
}
/*
* set_function_size_estimates
* Set the size estimates for a base relation that is a function call.
*
* The rel's targetlist and restrictinfo list must have been constructed
* already.
*
* We set the same fields as set_tablefunc_size_estimates.
*/
void
set_tablefunc_size_estimates(PlannerInfo *root, RelOptInfo *rel)
{
/* Should only be applied to base relations that are functions */
Assert(rel->relid > 0);
Assert(planner_rt_fetch(rel->relid, root)->rtekind == RTE_TABLEFUNC);
rel->tuples = 100;
/* Now estimate number of output rows, etc */
set_baserel_size_estimates(root, rel);
}
/*
* set_values_size_estimates
* Set the size estimates for a base relation that is a values list.
*
* The rel's targetlist and restrictinfo list must have been constructed
* already.
*
* We set the same fields as set_baserel_size_estimates.
*/
void
set_values_size_estimates(PlannerInfo *root, RelOptInfo *rel)
{
RangeTblEntry *rte;
/* Should only be applied to base relations that are values lists */
Assert(rel->relid > 0);
rte = planner_rt_fetch(rel->relid, root);
Assert(rte->rtekind == RTE_VALUES);
/*
* Estimate number of rows the values list will return. We know this
* precisely based on the list length (well, barring set-returning
* functions in list items, but that's a refinement not catered for
* anywhere else either).
*/
rel->tuples = list_length(rte->values_lists);
/* Now estimate number of output rows, etc */
set_baserel_size_estimates(root, rel);
}
/*
* set_cte_size_estimates
* Set the size estimates for a base relation that is a CTE reference.
*
* The rel's targetlist and restrictinfo list must have been constructed
* already, and we need an estimate of the number of rows returned by the CTE
* (if a regular CTE) or the non-recursive term (if a self-reference).
*
* We set the same fields as set_baserel_size_estimates.
*/
void
set_cte_size_estimates(PlannerInfo *root, RelOptInfo *rel, double cte_rows)
{
RangeTblEntry *rte;
/* Should only be applied to base relations that are CTE references */
Assert(rel->relid > 0);
rte = planner_rt_fetch(rel->relid, root);
Assert(rte->rtekind == RTE_CTE);
if (rte->self_reference)
{
/*
* In a self-reference, we assume the average worktable size is a
* multiple of the nonrecursive term's size. The best multiplier will
* vary depending on query "fan-out", so make its value adjustable.
*/
rel->tuples = clamp_row_est(recursive_worktable_factor * cte_rows);
}
else
{
/* Otherwise just believe the CTE's rowcount estimate */
rel->tuples = cte_rows;
}
/* Now estimate number of output rows, etc */
set_baserel_size_estimates(root, rel);
}
/*
* set_namedtuplestore_size_estimates
* Set the size estimates for a base relation that is a tuplestore reference.
*
* The rel's targetlist and restrictinfo list must have been constructed
* already.
*
* We set the same fields as set_baserel_size_estimates.
*/
void
set_namedtuplestore_size_estimates(PlannerInfo *root, RelOptInfo *rel)
{
RangeTblEntry *rte;
/* Should only be applied to base relations that are tuplestore references */
Assert(rel->relid > 0);
rte = planner_rt_fetch(rel->relid, root);
Assert(rte->rtekind == RTE_NAMEDTUPLESTORE);
/*
* Use the estimate provided by the code which is generating the named
* tuplestore. In some cases, the actual number might be available; in
* others the same plan will be re-used, so a "typical" value might be
* estimated and used.
*/
rel->tuples = rte->enrtuples;
if (rel->tuples < 0)
rel->tuples = 1000;
/* Now estimate number of output rows, etc */
set_baserel_size_estimates(root, rel);
}
/*
* set_result_size_estimates
* Set the size estimates for an RTE_RESULT base relation
*
* The rel's targetlist and restrictinfo list must have been constructed
* already.
*
* We set the same fields as set_baserel_size_estimates.
*/
void
set_result_size_estimates(PlannerInfo *root, RelOptInfo *rel)
{
/* Should only be applied to RTE_RESULT base relations */
Assert(rel->relid > 0);
Assert(planner_rt_fetch(rel->relid, root)->rtekind == RTE_RESULT);
/* RTE_RESULT always generates a single row, natively */
rel->tuples = 1;
/* Now estimate number of output rows, etc */
set_baserel_size_estimates(root, rel);
}
/*
* set_foreign_size_estimates
* Set the size estimates for a base relation that is a foreign table.
*
* There is not a whole lot that we can do here; the foreign-data wrapper
* is responsible for producing useful estimates. We can do a decent job
* of estimating baserestrictcost, so we set that, and we also set up width
* using what will be purely datatype-driven estimates from the targetlist.
* There is no way to do anything sane with the rows value, so we just put
* a default estimate and hope that the wrapper can improve on it. The
* wrapper's GetForeignRelSize function will be called momentarily.
*
* The rel's targetlist and restrictinfo list must have been constructed
* already.
*/
void
set_foreign_size_estimates(PlannerInfo *root, RelOptInfo *rel)
{
/* Should only be applied to base relations */
Assert(rel->relid > 0);
rel->rows = 1000; /* entirely bogus default estimate */
cost_qual_eval(&rel->baserestrictcost, rel->baserestrictinfo, root);
set_rel_width(root, rel);
}
/*
* set_rel_width
* Set the estimated output width of a base relation.
*
* The estimated output width is the sum of the per-attribute width estimates
* for the actually-referenced columns, plus any PHVs or other expressions
* that have to be calculated at this relation. This is the amount of data
* we'd need to pass upwards in case of a sort, hash, etc.
*
* This function also sets reltarget->cost, so it's a bit misnamed now.
*
* NB: this works best on plain relations because it prefers to look at
* real Vars. For subqueries, set_subquery_size_estimates will already have
* copied up whatever per-column estimates were made within the subquery,
* and for other types of rels there isn't much we can do anyway. We fall
* back on (fairly stupid) datatype-based width estimates if we can't get
* any better number.
*
* The per-attribute width estimates are cached for possible re-use while
* building join relations or post-scan/join pathtargets.
*/
static void
set_rel_width(PlannerInfo *root, RelOptInfo *rel)
{
Oid reloid = planner_rt_fetch(rel->relid, root)->relid;
int32 tuple_width = 0;
bool have_wholerow_var = false;
ListCell *lc;
/* Vars are assumed to have cost zero, but other exprs do not */
rel->reltarget->cost.startup = 0;
rel->reltarget->cost.per_tuple = 0;
foreach(lc, rel->reltarget->exprs)
{
Node *node = (Node *) lfirst(lc);
/*
* Ordinarily, a Var in a rel's targetlist must belong to that rel;
* but there are corner cases involving LATERAL references where that
* isn't so. If the Var has the wrong varno, fall through to the
* generic case (it doesn't seem worth the trouble to be any smarter).
*/
if (IsA(node, Var) &&
((Var *) node)->varno == rel->relid)
{
Var *var = (Var *) node;
int ndx;
int32 item_width;
Assert(var->varattno >= rel->min_attr);
Assert(var->varattno <= rel->max_attr);
ndx = var->varattno - rel->min_attr;
/*
* If it's a whole-row Var, we'll deal with it below after we have
* already cached as many attr widths as possible.
*/
if (var->varattno == 0)
{
have_wholerow_var = true;
continue;
}
/*
* The width may have been cached already (especially if it's a
* subquery), so don't duplicate effort.
*/
if (rel->attr_widths[ndx] > 0)
{
tuple_width += rel->attr_widths[ndx];
continue;
}
/* Try to get column width from statistics */
if (reloid != InvalidOid && var->varattno > 0)
{
item_width = get_attavgwidth(reloid, var->varattno);
if (item_width > 0)
{
rel->attr_widths[ndx] = item_width;
tuple_width += item_width;
continue;
}
}
/*
* Not a plain relation, or can't find statistics for it. Estimate
* using just the type info.
*/
item_width = get_typavgwidth(var->vartype, var->vartypmod);
Assert(item_width > 0);
rel->attr_widths[ndx] = item_width;
tuple_width += item_width;
}
else if (IsA(node, PlaceHolderVar))
{
/*
* We will need to evaluate the PHV's contained expression while
* scanning this rel, so be sure to include it in reltarget->cost.
*/
PlaceHolderVar *phv = (PlaceHolderVar *) node;
PlaceHolderInfo *phinfo = find_placeholder_info(root, phv, false);
QualCost cost;
tuple_width += phinfo->ph_width;
cost_qual_eval_node(&cost, (Node *) phv->phexpr, root);
rel->reltarget->cost.startup += cost.startup;
rel->reltarget->cost.per_tuple += cost.per_tuple;
}
else
{
/*
* We could be looking at an expression pulled up from a subquery,
* or a ROW() representing a whole-row child Var, etc. Do what we
* can using the expression type information.
*/
int32 item_width;
QualCost cost;
item_width = get_typavgwidth(exprType(node), exprTypmod(node));
Assert(item_width > 0);
tuple_width += item_width;
/* Not entirely clear if we need to account for cost, but do so */
cost_qual_eval_node(&cost, node, root);
rel->reltarget->cost.startup += cost.startup;
rel->reltarget->cost.per_tuple += cost.per_tuple;
}
}
/*
* If we have a whole-row reference, estimate its width as the sum of
* per-column widths plus heap tuple header overhead.
*/
if (have_wholerow_var)
{
int32 wholerow_width = MAXALIGN(SizeofHeapTupleHeader);
if (reloid != InvalidOid)
{
/* Real relation, so estimate true tuple width */
wholerow_width += get_relation_data_width(reloid,
rel->attr_widths - rel->min_attr);
}
else
{
/* Do what we can with info for a phony rel */
AttrNumber i;
for (i = 1; i <= rel->max_attr; i++)
wholerow_width += rel->attr_widths[i - rel->min_attr];
}
rel->attr_widths[0 - rel->min_attr] = wholerow_width;
/*
* Include the whole-row Var as part of the output tuple. Yes, that
* really is what happens at runtime.
*/
tuple_width += wholerow_width;
}
Assert(tuple_width >= 0);
rel->reltarget->width = tuple_width;
}
/*
* set_pathtarget_cost_width
* Set the estimated eval cost and output width of a PathTarget tlist.
*
* As a notational convenience, returns the same PathTarget pointer passed in.
*
* Most, though not quite all, uses of this function occur after we've run
* set_rel_width() for base relations; so we can usually obtain cached width
* estimates for Vars. If we can't, fall back on datatype-based width
* estimates. Present early-planning uses of PathTargets don't need accurate
* widths badly enough to justify going to the catalogs for better data.
*/
PathTarget *
set_pathtarget_cost_width(PlannerInfo *root, PathTarget *target)
{
int32 tuple_width = 0;
ListCell *lc;
/* Vars are assumed to have cost zero, but other exprs do not */
target->cost.startup = 0;
target->cost.per_tuple = 0;
foreach(lc, target->exprs)
{
Node *node = (Node *) lfirst(lc);
if (IsA(node, Var))
{
Var *var = (Var *) node;
int32 item_width;
/* We should not see any upper-level Vars here */
Assert(var->varlevelsup == 0);
/* Try to get data from RelOptInfo cache */
if (!IS_SPECIAL_VARNO(var->varno) &&
var->varno < root->simple_rel_array_size)
{
RelOptInfo *rel = root->simple_rel_array[var->varno];
if (rel != NULL &&
var->varattno >= rel->min_attr &&
var->varattno <= rel->max_attr)
{
int ndx = var->varattno - rel->min_attr;
if (rel->attr_widths[ndx] > 0)
{
tuple_width += rel->attr_widths[ndx];
continue;
}
}
}
/*
* No cached data available, so estimate using just the type info.
*/
item_width = get_typavgwidth(var->vartype, var->vartypmod);
Assert(item_width > 0);
tuple_width += item_width;
}
else
{
/*
* Handle general expressions using type info.
*/
int32 item_width;
QualCost cost;
item_width = get_typavgwidth(exprType(node), exprTypmod(node));
Assert(item_width > 0);
tuple_width += item_width;
/* Account for cost, too */
cost_qual_eval_node(&cost, node, root);
target->cost.startup += cost.startup;
target->cost.per_tuple += cost.per_tuple;
}
}
Assert(tuple_width >= 0);
target->width = tuple_width;
return target;
}
/*
* relation_byte_size
* Estimate the storage space in bytes for a given number of tuples
* of a given width (size in bytes).
*/
static double
relation_byte_size(double tuples, int width)
{
return tuples * (MAXALIGN(width) + MAXALIGN(SizeofHeapTupleHeader));
}
/*
* page_size
* Returns an estimate of the number of pages covered by a given
* number of tuples of a given width (size in bytes).
*/
static double
page_size(double tuples, int width)
{
return ceil(relation_byte_size(tuples, width) / BLCKSZ);
}
/*
* Estimate the fraction of the work that each worker will do given the
* number of workers budgeted for the path.
*/
static double
get_parallel_divisor(Path *path)
{
double parallel_divisor = path->parallel_workers;
/*
* Early experience with parallel query suggests that when there is only
* one worker, the leader often makes a very substantial contribution to
* executing the parallel portion of the plan, but as more workers are
* added, it does less and less, because it's busy reading tuples from the
* workers and doing whatever non-parallel post-processing is needed. By
* the time we reach 4 workers, the leader no longer makes a meaningful
* contribution. Thus, for now, estimate that the leader spends 30% of
* its time servicing each worker, and the remainder executing the
* parallel plan.
*/
if (parallel_leader_participation)
{
double leader_contribution;
leader_contribution = 1.0 - (0.3 * path->parallel_workers);
if (leader_contribution > 0)
parallel_divisor += leader_contribution;
}
return parallel_divisor;
}
/*
* compute_bitmap_pages
*
* compute number of pages fetched from heap in bitmap heap scan.
*/
double
compute_bitmap_pages(PlannerInfo *root, RelOptInfo *baserel, Path *bitmapqual,
int loop_count, Cost *cost, double *tuple)
{
Cost indexTotalCost;
Selectivity indexSelectivity;
double T;
double pages_fetched;
double tuples_fetched;
double heap_pages;
long maxentries;
/*
* Fetch total cost of obtaining the bitmap, as well as its total
* selectivity.
*/
cost_bitmap_tree_node(bitmapqual, &indexTotalCost, &indexSelectivity);
/*
* Estimate number of main-table pages fetched.
*/
tuples_fetched = clamp_row_est(indexSelectivity * baserel->tuples);
T = (baserel->pages > 1) ? (double) baserel->pages : 1.0;
/*
* For a single scan, the number of heap pages that need to be fetched is
* the same as the Mackert and Lohman formula for the case T <= b (ie, no
* re-reads needed).
*/
pages_fetched = (2.0 * T * tuples_fetched) / (2.0 * T + tuples_fetched);
/*
* Calculate the number of pages fetched from the heap. Then based on
* current work_mem estimate get the estimated maxentries in the bitmap.
* (Note that we always do this calculation based on the number of pages
* that would be fetched in a single iteration, even if loop_count > 1.
* That's correct, because only that number of entries will be stored in
* the bitmap at one time.)
*/
heap_pages = Min(pages_fetched, baserel->pages);
maxentries = tbm_calculate_entries(work_mem * 1024L);
if (loop_count > 1)
{
/*
* For repeated bitmap scans, scale up the number of tuples fetched in
* the Mackert and Lohman formula by the number of scans, so that we
* estimate the number of pages fetched by all the scans. Then
* pro-rate for one scan.
*/
pages_fetched = index_pages_fetched(tuples_fetched * loop_count,
baserel->pages,
get_indexpath_pages(bitmapqual),
root);
pages_fetched /= loop_count;
}
if (pages_fetched >= T)
pages_fetched = T;
else
pages_fetched = ceil(pages_fetched);
if (maxentries < heap_pages)
{
double exact_pages;
double lossy_pages;
/*
* Crude approximation of the number of lossy pages. Because of the
* way tbm_lossify() is coded, the number of lossy pages increases
* very sharply as soon as we run short of memory; this formula has
* that property and seems to perform adequately in testing, but it's
* possible we could do better somehow.
*/
lossy_pages = Max(0, heap_pages - maxentries / 2);
exact_pages = heap_pages - lossy_pages;
/*
* If there are lossy pages then recompute the number of tuples
* processed by the bitmap heap node. We assume here that the chance
* of a given tuple coming from an exact page is the same as the
* chance that a given page is exact. This might not be true, but
* it's not clear how we can do any better.
*/
if (lossy_pages > 0)
tuples_fetched =
clamp_row_est(indexSelectivity *
(exact_pages / heap_pages) * baserel->tuples +
(lossy_pages / heap_pages) * baserel->tuples);
}
if (cost)
*cost = indexTotalCost;
if (tuple)
*tuple = tuples_fetched;
return pages_fetched;
}
|