summaryrefslogtreecommitdiff
path: root/src/backend/executor/nodeAgg.c
blob: a8a57b70633b4d51d6934a2f54ab973be46590b8 (plain)
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
/*-------------------------------------------------------------------------
 *
 * nodeAgg.c
 *	  Routines to handle aggregate nodes.
 *
 *	  ExecAgg normally evaluates each aggregate in the following steps:
 *
 *		 transvalue = initcond
 *		 foreach input_tuple do
 *			transvalue = transfunc(transvalue, input_value(s))
 *		 result = finalfunc(transvalue, direct_argument(s))
 *
 *	  If a finalfunc is not supplied then the result is just the ending
 *	  value of transvalue.
 *
 *	  Other behaviors can be selected by the "aggsplit" mode, which exists
 *	  to support partial aggregation.  It is possible to:
 *	  * Skip running the finalfunc, so that the output is always the
 *	  final transvalue state.
 *	  * Substitute the combinefunc for the transfunc, so that transvalue
 *	  states (propagated up from a child partial-aggregation step) are merged
 *	  rather than processing raw input rows.  (The statements below about
 *	  the transfunc apply equally to the combinefunc, when it's selected.)
 *	  * Apply the serializefunc to the output values (this only makes sense
 *	  when skipping the finalfunc, since the serializefunc works on the
 *	  transvalue data type).
 *	  * Apply the deserializefunc to the input values (this only makes sense
 *	  when using the combinefunc, for similar reasons).
 *	  It is the planner's responsibility to connect up Agg nodes using these
 *	  alternate behaviors in a way that makes sense, with partial aggregation
 *	  results being fed to nodes that expect them.
 *
 *	  If a normal aggregate call specifies DISTINCT or ORDER BY, we sort the
 *	  input tuples and eliminate duplicates (if required) before performing
 *	  the above-depicted process.  (However, we don't do that for ordered-set
 *	  aggregates; their "ORDER BY" inputs are ordinary aggregate arguments
 *	  so far as this module is concerned.)	Note that partial aggregation
 *	  is not supported in these cases, since we couldn't ensure global
 *	  ordering or distinctness of the inputs.
 *
 *	  If transfunc is marked "strict" in pg_proc and initcond is NULL,
 *	  then the first non-NULL input_value is assigned directly to transvalue,
 *	  and transfunc isn't applied until the second non-NULL input_value.
 *	  The agg's first input type and transtype must be the same in this case!
 *
 *	  If transfunc is marked "strict" then NULL input_values are skipped,
 *	  keeping the previous transvalue.  If transfunc is not strict then it
 *	  is called for every input tuple and must deal with NULL initcond
 *	  or NULL input_values for itself.
 *
 *	  If finalfunc is marked "strict" then it is not called when the
 *	  ending transvalue is NULL, instead a NULL result is created
 *	  automatically (this is just the usual handling of strict functions,
 *	  of course).  A non-strict finalfunc can make its own choice of
 *	  what to return for a NULL ending transvalue.
 *
 *	  Ordered-set aggregates are treated specially in one other way: we
 *	  evaluate any "direct" arguments and pass them to the finalfunc along
 *	  with the transition value.
 *
 *	  A finalfunc can have additional arguments beyond the transvalue and
 *	  any "direct" arguments, corresponding to the input arguments of the
 *	  aggregate.  These are always just passed as NULL.  Such arguments may be
 *	  needed to allow resolution of a polymorphic aggregate's result type.
 *
 *	  We compute aggregate input expressions and run the transition functions
 *	  in a temporary econtext (aggstate->tmpcontext).  This is reset at least
 *	  once per input tuple, so when the transvalue datatype is
 *	  pass-by-reference, we have to be careful to copy it into a longer-lived
 *	  memory context, and free the prior value to avoid memory leakage.  We
 *	  store transvalues in another set of econtexts, aggstate->aggcontexts
 *	  (one per grouping set, see below), which are also used for the hashtable
 *	  structures in AGG_HASHED mode.  These econtexts are rescanned, not just
 *	  reset, at group boundaries so that aggregate transition functions can
 *	  register shutdown callbacks via AggRegisterCallback.
 *
 *	  The node's regular econtext (aggstate->ss.ps.ps_ExprContext) is used to
 *	  run finalize functions and compute the output tuple; this context can be
 *	  reset once per output tuple.
 *
 *	  The executor's AggState node is passed as the fmgr "context" value in
 *	  all transfunc and finalfunc calls.  It is not recommended that the
 *	  transition functions look at the AggState node directly, but they can
 *	  use AggCheckCallContext() to verify that they are being called by
 *	  nodeAgg.c (and not as ordinary SQL functions).  The main reason a
 *	  transition function might want to know this is so that it can avoid
 *	  palloc'ing a fixed-size pass-by-ref transition value on every call:
 *	  it can instead just scribble on and return its left input.  Ordinarily
 *	  it is completely forbidden for functions to modify pass-by-ref inputs,
 *	  but in the aggregate case we know the left input is either the initial
 *	  transition value or a previous function result, and in either case its
 *	  value need not be preserved.  See int8inc() for an example.  Notice that
 *	  the EEOP_AGG_PLAIN_TRANS step is coded to avoid a data copy step when
 *	  the previous transition value pointer is returned.  It is also possible
 *	  to avoid repeated data copying when the transition value is an expanded
 *	  object: to do that, the transition function must take care to return
 *	  an expanded object that is in a child context of the memory context
 *	  returned by AggCheckCallContext().  Also, some transition functions want
 *	  to store working state in addition to the nominal transition value; they
 *	  can use the memory context returned by AggCheckCallContext() to do that.
 *
 *	  Note: AggCheckCallContext() is available as of PostgreSQL 9.0.  The
 *	  AggState is available as context in earlier releases (back to 8.1),
 *	  but direct examination of the node is needed to use it before 9.0.
 *
 *	  As of 9.4, aggregate transition functions can also use AggGetAggref()
 *	  to get hold of the Aggref expression node for their aggregate call.
 *	  This is mainly intended for ordered-set aggregates, which are not
 *	  supported as window functions.  (A regular aggregate function would
 *	  need some fallback logic to use this, since there's no Aggref node
 *	  for a window function.)
 *
 *	  Grouping sets:
 *
 *	  A list of grouping sets which is structurally equivalent to a ROLLUP
 *	  clause (e.g. (a,b,c), (a,b), (a)) can be processed in a single pass over
 *	  ordered data.  We do this by keeping a separate set of transition values
 *	  for each grouping set being concurrently processed; for each input tuple
 *	  we update them all, and on group boundaries we reset those states
 *	  (starting at the front of the list) whose grouping values have changed
 *	  (the list of grouping sets is ordered from most specific to least
 *	  specific).
 *
 *	  Where more complex grouping sets are used, we break them down into
 *	  "phases", where each phase has a different sort order (except phase 0
 *	  which is reserved for hashing).  During each phase but the last, the
 *	  input tuples are additionally stored in a tuplesort which is keyed to the
 *	  next phase's sort order; during each phase but the first, the input
 *	  tuples are drawn from the previously sorted data.  (The sorting of the
 *	  data for the first phase is handled by the planner, as it might be
 *	  satisfied by underlying nodes.)
 *
 *	  Hashing can be mixed with sorted grouping.  To do this, we have an
 *	  AGG_MIXED strategy that populates the hashtables during the first sorted
 *	  phase, and switches to reading them out after completing all sort phases.
 *	  We can also support AGG_HASHED with multiple hash tables and no sorting
 *	  at all.
 *
 *	  From the perspective of aggregate transition and final functions, the
 *	  only issue regarding grouping sets is this: a single call site (flinfo)
 *	  of an aggregate function may be used for updating several different
 *	  transition values in turn. So the function must not cache in the flinfo
 *	  anything which logically belongs as part of the transition value (most
 *	  importantly, the memory context in which the transition value exists).
 *	  The support API functions (AggCheckCallContext, AggRegisterCallback) are
 *	  sensitive to the grouping set for which the aggregate function is
 *	  currently being called.
 *
 *	  Plan structure:
 *
 *	  What we get from the planner is actually one "real" Agg node which is
 *	  part of the plan tree proper, but which optionally has an additional list
 *	  of Agg nodes hung off the side via the "chain" field.  This is because an
 *	  Agg node happens to be a convenient representation of all the data we
 *	  need for grouping sets.
 *
 *	  For many purposes, we treat the "real" node as if it were just the first
 *	  node in the chain.  The chain must be ordered such that hashed entries
 *	  come before sorted/plain entries; the real node is marked AGG_MIXED if
 *	  there are both types present (in which case the real node describes one
 *	  of the hashed groupings, other AGG_HASHED nodes may optionally follow in
 *	  the chain, followed in turn by AGG_SORTED or (one) AGG_PLAIN node).  If
 *	  the real node is marked AGG_HASHED or AGG_SORTED, then all the chained
 *	  nodes must be of the same type; if it is AGG_PLAIN, there can be no
 *	  chained nodes.
 *
 *	  We collect all hashed nodes into a single "phase", numbered 0, and create
 *	  a sorted phase (numbered 1..n) for each AGG_SORTED or AGG_PLAIN node.
 *	  Phase 0 is allocated even if there are no hashes, but remains unused in
 *	  that case.
 *
 *	  AGG_HASHED nodes actually refer to only a single grouping set each,
 *	  because for each hashed grouping we need a separate grpColIdx and
 *	  numGroups estimate.  AGG_SORTED nodes represent a "rollup", a list of
 *	  grouping sets that share a sort order.  Each AGG_SORTED node other than
 *	  the first one has an associated Sort node which describes the sort order
 *	  to be used; the first sorted node takes its input from the outer subtree,
 *	  which the planner has already arranged to provide ordered data.
 *
 *	  Memory and ExprContext usage:
 *
 *	  Because we're accumulating aggregate values across input rows, we need to
 *	  use more memory contexts than just simple input/output tuple contexts.
 *	  In fact, for a rollup, we need a separate context for each grouping set
 *	  so that we can reset the inner (finer-grained) aggregates on their group
 *	  boundaries while continuing to accumulate values for outer
 *	  (coarser-grained) groupings.  On top of this, we might be simultaneously
 *	  populating hashtables; however, we only need one context for all the
 *	  hashtables.
 *
 *	  So we create an array, aggcontexts, with an ExprContext for each grouping
 *	  set in the largest rollup that we're going to process, and use the
 *	  per-tuple memory context of those ExprContexts to store the aggregate
 *	  transition values.  hashcontext is the single context created to support
 *	  all hash tables.
 *
 *	  Spilling To Disk
 *
 *	  When performing hash aggregation, if the hash table memory exceeds the
 *	  limit (see hash_agg_check_limits()), we enter "spill mode". In spill
 *	  mode, we advance the transition states only for groups already in the
 *	  hash table. For tuples that would need to create a new hash table
 *	  entries (and initialize new transition states), we instead spill them to
 *	  disk to be processed later. The tuples are spilled in a partitioned
 *	  manner, so that subsequent batches are smaller and less likely to exceed
 *	  hash_mem (if a batch does exceed hash_mem, it must be spilled
 *	  recursively).
 *
 *	  Spilled data is written to logical tapes. These provide better control
 *	  over memory usage, disk space, and the number of files than if we were
 *	  to use a BufFile for each spill.  We don't know the number of tapes needed
 *	  at the start of the algorithm (because it can recurse), so a tape set is
 *	  allocated at the beginning, and individual tapes are created as needed.
 *	  As a particular tape is read, logtape.c recycles its disk space. When a
 *	  tape is read to completion, it is destroyed entirely.
 *
 *	  Tapes' buffers can take up substantial memory when many tapes are open at
 *	  once. We only need one tape open at a time in read mode (using a buffer
 *	  that's a multiple of BLCKSZ); but we need one tape open in write mode (each
 *	  requiring a buffer of size BLCKSZ) for each partition.
 *
 *	  Note that it's possible for transition states to start small but then
 *	  grow very large; for instance in the case of ARRAY_AGG. In such cases,
 *	  it's still possible to significantly exceed hash_mem. We try to avoid
 *	  this situation by estimating what will fit in the available memory, and
 *	  imposing a limit on the number of groups separately from the amount of
 *	  memory consumed.
 *
 *    Transition / Combine function invocation:
 *
 *    For performance reasons transition functions, including combine
 *    functions, aren't invoked one-by-one from nodeAgg.c after computing
 *    arguments using the expression evaluation engine. Instead
 *    ExecBuildAggTrans() builds one large expression that does both argument
 *    evaluation and transition function invocation. That avoids performance
 *    issues due to repeated uses of expression evaluation, complications due
 *    to filter expressions having to be evaluated early, and allows to JIT
 *    the entire expression into one native function.
 *
 * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * IDENTIFICATION
 *	  src/backend/executor/nodeAgg.c
 *
 *-------------------------------------------------------------------------
 */

#include "postgres.h"

#include "access/htup_details.h"
#include "access/parallel.h"
#include "catalog/objectaccess.h"
#include "catalog/pg_aggregate.h"
#include "catalog/pg_proc.h"
#include "catalog/pg_type.h"
#include "common/hashfn.h"
#include "executor/execExpr.h"
#include "executor/executor.h"
#include "executor/nodeAgg.h"
#include "lib/hyperloglog.h"
#include "miscadmin.h"
#include "nodes/makefuncs.h"
#include "nodes/nodeFuncs.h"
#include "optimizer/optimizer.h"
#include "parser/parse_agg.h"
#include "parser/parse_coerce.h"
#include "utils/acl.h"
#include "utils/builtins.h"
#include "utils/datum.h"
#include "utils/dynahash.h"
#include "utils/expandeddatum.h"
#include "utils/logtape.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
#include "utils/syscache.h"
#include "utils/tuplesort.h"

/*
 * Control how many partitions are created when spilling HashAgg to
 * disk.
 *
 * HASHAGG_PARTITION_FACTOR is multiplied by the estimated number of
 * partitions needed such that each partition will fit in memory. The factor
 * is set higher than one because there's not a high cost to having a few too
 * many partitions, and it makes it less likely that a partition will need to
 * be spilled recursively. Another benefit of having more, smaller partitions
 * is that small hash tables may perform better than large ones due to memory
 * caching effects.
 *
 * We also specify a min and max number of partitions per spill. Too few might
 * mean a lot of wasted I/O from repeated spilling of the same tuples. Too
 * many will result in lots of memory wasted buffering the spill files (which
 * could instead be spent on a larger hash table).
 */
#define HASHAGG_PARTITION_FACTOR 1.50
#define HASHAGG_MIN_PARTITIONS 4
#define HASHAGG_MAX_PARTITIONS 1024

/*
 * For reading from tapes, the buffer size must be a multiple of
 * BLCKSZ. Larger values help when reading from multiple tapes concurrently,
 * but that doesn't happen in HashAgg, so we simply use BLCKSZ. Writing to a
 * tape always uses a buffer of size BLCKSZ.
 */
#define HASHAGG_READ_BUFFER_SIZE BLCKSZ
#define HASHAGG_WRITE_BUFFER_SIZE BLCKSZ

/*
 * HyperLogLog is used for estimating the cardinality of the spilled tuples in
 * a given partition. 5 bits corresponds to a size of about 32 bytes and a
 * worst-case error of around 18%. That's effective enough to choose a
 * reasonable number of partitions when recursing.
 */
#define HASHAGG_HLL_BIT_WIDTH 5

/*
 * Estimate chunk overhead as a constant 16 bytes. XXX: should this be
 * improved?
 */
#define CHUNKHDRSZ 16

/*
 * Represents partitioned spill data for a single hashtable. Contains the
 * necessary information to route tuples to the correct partition, and to
 * transform the spilled data into new batches.
 *
 * The high bits are used for partition selection (when recursing, we ignore
 * the bits that have already been used for partition selection at an earlier
 * level).
 */
typedef struct HashAggSpill
{
	int			npartitions;	/* number of partitions */
	LogicalTape **partitions;	/* spill partition tapes */
	int64	   *ntuples;		/* number of tuples in each partition */
	uint32		mask;			/* mask to find partition from hash value */
	int			shift;			/* after masking, shift by this amount */
	hyperLogLogState *hll_card; /* cardinality estimate for contents */
} HashAggSpill;

/*
 * Represents work to be done for one pass of hash aggregation (with only one
 * grouping set).
 *
 * Also tracks the bits of the hash already used for partition selection by
 * earlier iterations, so that this batch can use new bits. If all bits have
 * already been used, no partitioning will be done (any spilled data will go
 * to a single output tape).
 */
typedef struct HashAggBatch
{
	int			setno;			/* grouping set */
	int			used_bits;		/* number of bits of hash already used */
	LogicalTape *input_tape;	/* input partition tape */
	int64		input_tuples;	/* number of tuples in this batch */
	double		input_card;		/* estimated group cardinality */
} HashAggBatch;

/* used to find referenced colnos */
typedef struct FindColsContext
{
	bool		is_aggref;		/* is under an aggref */
	Bitmapset  *aggregated;		/* column references under an aggref */
	Bitmapset  *unaggregated;	/* other column references */
} FindColsContext;

static void select_current_set(AggState *aggstate, int setno, bool is_hash);
static void initialize_phase(AggState *aggstate, int newphase);
static TupleTableSlot *fetch_input_tuple(AggState *aggstate);
static void initialize_aggregates(AggState *aggstate,
								  AggStatePerGroup *pergroups,
								  int numReset);
static void advance_transition_function(AggState *aggstate,
										AggStatePerTrans pertrans,
										AggStatePerGroup pergroupstate);
static void advance_aggregates(AggState *aggstate);
static void process_ordered_aggregate_single(AggState *aggstate,
											 AggStatePerTrans pertrans,
											 AggStatePerGroup pergroupstate);
static void process_ordered_aggregate_multi(AggState *aggstate,
											AggStatePerTrans pertrans,
											AggStatePerGroup pergroupstate);
static void finalize_aggregate(AggState *aggstate,
							   AggStatePerAgg peragg,
							   AggStatePerGroup pergroupstate,
							   Datum *resultVal, bool *resultIsNull);
static void finalize_partialaggregate(AggState *aggstate,
									  AggStatePerAgg peragg,
									  AggStatePerGroup pergroupstate,
									  Datum *resultVal, bool *resultIsNull);
static inline void prepare_hash_slot(AggStatePerHash perhash,
									 TupleTableSlot *inputslot,
									 TupleTableSlot *hashslot);
static void prepare_projection_slot(AggState *aggstate,
									TupleTableSlot *slot,
									int currentSet);
static void finalize_aggregates(AggState *aggstate,
								AggStatePerAgg peraggs,
								AggStatePerGroup pergroup);
static TupleTableSlot *project_aggregates(AggState *aggstate);
static void find_cols(AggState *aggstate, Bitmapset **aggregated,
					  Bitmapset **unaggregated);
static bool find_cols_walker(Node *node, FindColsContext *context);
static void build_hash_tables(AggState *aggstate);
static void build_hash_table(AggState *aggstate, int setno, long nbuckets);
static void hashagg_recompile_expressions(AggState *aggstate, bool minslot,
										  bool nullcheck);
static long hash_choose_num_buckets(double hashentrysize,
									long ngroups, Size memory);
static int	hash_choose_num_partitions(double input_groups,
									   double hashentrysize,
									   int used_bits,
									   int *log2_npartitions);
static void initialize_hash_entry(AggState *aggstate,
								  TupleHashTable hashtable,
								  TupleHashEntry entry);
static void lookup_hash_entries(AggState *aggstate);
static TupleTableSlot *agg_retrieve_direct(AggState *aggstate);
static void agg_fill_hash_table(AggState *aggstate);
static bool agg_refill_hash_table(AggState *aggstate);
static TupleTableSlot *agg_retrieve_hash_table(AggState *aggstate);
static TupleTableSlot *agg_retrieve_hash_table_in_memory(AggState *aggstate);
static void hash_agg_check_limits(AggState *aggstate);
static void hash_agg_enter_spill_mode(AggState *aggstate);
static void hash_agg_update_metrics(AggState *aggstate, bool from_tape,
									int npartitions);
static void hashagg_finish_initial_spills(AggState *aggstate);
static void hashagg_reset_spill_state(AggState *aggstate);
static HashAggBatch *hashagg_batch_new(LogicalTape *input_tape, int setno,
									   int64 input_tuples, double input_card,
									   int used_bits);
static MinimalTuple hashagg_batch_read(HashAggBatch *batch, uint32 *hashp);
static void hashagg_spill_init(HashAggSpill *spill, LogicalTapeSet *tapeset,
							   int used_bits, double input_groups,
							   double hashentrysize);
static Size hashagg_spill_tuple(AggState *aggstate, HashAggSpill *spill,
								TupleTableSlot *inputslot, uint32 hash);
static void hashagg_spill_finish(AggState *aggstate, HashAggSpill *spill,
								 int setno);
static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
static void build_pertrans_for_aggref(AggStatePerTrans pertrans,
									  AggState *aggstate, EState *estate,
									  Aggref *aggref, Oid transfn_oid,
									  Oid aggtranstype, Oid aggserialfn,
									  Oid aggdeserialfn, Datum initValue,
									  bool initValueIsNull, Oid *inputTypes,
									  int numArguments);


/*
 * Select the current grouping set; affects current_set and
 * curaggcontext.
 */
static void
select_current_set(AggState *aggstate, int setno, bool is_hash)
{
	/*
	 * When changing this, also adapt ExecAggPlainTransByVal() and
	 * ExecAggPlainTransByRef().
	 */
	if (is_hash)
		aggstate->curaggcontext = aggstate->hashcontext;
	else
		aggstate->curaggcontext = aggstate->aggcontexts[setno];

	aggstate->current_set = setno;
}

/*
 * Switch to phase "newphase", which must either be 0 or 1 (to reset) or
 * current_phase + 1. Juggle the tuplesorts accordingly.
 *
 * Phase 0 is for hashing, which we currently handle last in the AGG_MIXED
 * case, so when entering phase 0, all we need to do is drop open sorts.
 */
static void
initialize_phase(AggState *aggstate, int newphase)
{
	Assert(newphase <= 1 || newphase == aggstate->current_phase + 1);

	/*
	 * Whatever the previous state, we're now done with whatever input
	 * tuplesort was in use.
	 */
	if (aggstate->sort_in)
	{
		tuplesort_end(aggstate->sort_in);
		aggstate->sort_in = NULL;
	}

	if (newphase <= 1)
	{
		/*
		 * Discard any existing output tuplesort.
		 */
		if (aggstate->sort_out)
		{
			tuplesort_end(aggstate->sort_out);
			aggstate->sort_out = NULL;
		}
	}
	else
	{
		/*
		 * The old output tuplesort becomes the new input one, and this is the
		 * right time to actually sort it.
		 */
		aggstate->sort_in = aggstate->sort_out;
		aggstate->sort_out = NULL;
		Assert(aggstate->sort_in);
		tuplesort_performsort(aggstate->sort_in);
	}

	/*
	 * If this isn't the last phase, we need to sort appropriately for the
	 * next phase in sequence.
	 */
	if (newphase > 0 && newphase < aggstate->numphases - 1)
	{
		Sort	   *sortnode = aggstate->phases[newphase + 1].sortnode;
		PlanState  *outerNode = outerPlanState(aggstate);
		TupleDesc	tupDesc = ExecGetResultType(outerNode);

		aggstate->sort_out = tuplesort_begin_heap(tupDesc,
												  sortnode->numCols,
												  sortnode->sortColIdx,
												  sortnode->sortOperators,
												  sortnode->collations,
												  sortnode->nullsFirst,
												  work_mem,
												  NULL, TUPLESORT_NONE);
	}

	aggstate->current_phase = newphase;
	aggstate->phase = &aggstate->phases[newphase];
}

/*
 * Fetch a tuple from either the outer plan (for phase 1) or from the sorter
 * populated by the previous phase.  Copy it to the sorter for the next phase
 * if any.
 *
 * Callers cannot rely on memory for tuple in returned slot remaining valid
 * past any subsequently fetched tuple.
 */
static TupleTableSlot *
fetch_input_tuple(AggState *aggstate)
{
	TupleTableSlot *slot;

	if (aggstate->sort_in)
	{
		/* make sure we check for interrupts in either path through here */
		CHECK_FOR_INTERRUPTS();
		if (!tuplesort_gettupleslot(aggstate->sort_in, true, false,
									aggstate->sort_slot, NULL))
			return NULL;
		slot = aggstate->sort_slot;
	}
	else
		slot = ExecProcNode(outerPlanState(aggstate));

	if (!TupIsNull(slot) && aggstate->sort_out)
		tuplesort_puttupleslot(aggstate->sort_out, slot);

	return slot;
}

/*
 * (Re)Initialize an individual aggregate.
 *
 * This function handles only one grouping set, already set in
 * aggstate->current_set.
 *
 * When called, CurrentMemoryContext should be the per-query context.
 */
static void
initialize_aggregate(AggState *aggstate, AggStatePerTrans pertrans,
					 AggStatePerGroup pergroupstate)
{
	/*
	 * Start a fresh sort operation for each DISTINCT/ORDER BY aggregate.
	 */
	if (pertrans->aggsortrequired)
	{
		/*
		 * In case of rescan, maybe there could be an uncompleted sort
		 * operation?  Clean it up if so.
		 */
		if (pertrans->sortstates[aggstate->current_set])
			tuplesort_end(pertrans->sortstates[aggstate->current_set]);


		/*
		 * We use a plain Datum sorter when there's a single input column;
		 * otherwise sort the full tuple.  (See comments for
		 * process_ordered_aggregate_single.)
		 */
		if (pertrans->numInputs == 1)
		{
			Form_pg_attribute attr = TupleDescAttr(pertrans->sortdesc, 0);

			pertrans->sortstates[aggstate->current_set] =
				tuplesort_begin_datum(attr->atttypid,
									  pertrans->sortOperators[0],
									  pertrans->sortCollations[0],
									  pertrans->sortNullsFirst[0],
									  work_mem, NULL, TUPLESORT_NONE);
		}
		else
			pertrans->sortstates[aggstate->current_set] =
				tuplesort_begin_heap(pertrans->sortdesc,
									 pertrans->numSortCols,
									 pertrans->sortColIdx,
									 pertrans->sortOperators,
									 pertrans->sortCollations,
									 pertrans->sortNullsFirst,
									 work_mem, NULL, TUPLESORT_NONE);
	}

	/*
	 * (Re)set transValue to the initial value.
	 *
	 * Note that when the initial value is pass-by-ref, we must copy it (into
	 * the aggcontext) since we will pfree the transValue later.
	 */
	if (pertrans->initValueIsNull)
		pergroupstate->transValue = pertrans->initValue;
	else
	{
		MemoryContext oldContext;

		oldContext = MemoryContextSwitchTo(aggstate->curaggcontext->ecxt_per_tuple_memory);
		pergroupstate->transValue = datumCopy(pertrans->initValue,
											  pertrans->transtypeByVal,
											  pertrans->transtypeLen);
		MemoryContextSwitchTo(oldContext);
	}
	pergroupstate->transValueIsNull = pertrans->initValueIsNull;

	/*
	 * If the initial value for the transition state doesn't exist in the
	 * pg_aggregate table then we will let the first non-NULL value returned
	 * from the outer procNode become the initial value. (This is useful for
	 * aggregates like max() and min().) The noTransValue flag signals that we
	 * still need to do this.
	 */
	pergroupstate->noTransValue = pertrans->initValueIsNull;
}

/*
 * Initialize all aggregate transition states for a new group of input values.
 *
 * If there are multiple grouping sets, we initialize only the first numReset
 * of them (the grouping sets are ordered so that the most specific one, which
 * is reset most often, is first). As a convenience, if numReset is 0, we
 * reinitialize all sets.
 *
 * NB: This cannot be used for hash aggregates, as for those the grouping set
 * number has to be specified from further up.
 *
 * When called, CurrentMemoryContext should be the per-query context.
 */
static void
initialize_aggregates(AggState *aggstate,
					  AggStatePerGroup *pergroups,
					  int numReset)
{
	int			transno;
	int			numGroupingSets = Max(aggstate->phase->numsets, 1);
	int			setno = 0;
	int			numTrans = aggstate->numtrans;
	AggStatePerTrans transstates = aggstate->pertrans;

	if (numReset == 0)
		numReset = numGroupingSets;

	for (setno = 0; setno < numReset; setno++)
	{
		AggStatePerGroup pergroup = pergroups[setno];

		select_current_set(aggstate, setno, false);

		for (transno = 0; transno < numTrans; transno++)
		{
			AggStatePerTrans pertrans = &transstates[transno];
			AggStatePerGroup pergroupstate = &pergroup[transno];

			initialize_aggregate(aggstate, pertrans, pergroupstate);
		}
	}
}

/*
 * Given new input value(s), advance the transition function of one aggregate
 * state within one grouping set only (already set in aggstate->current_set)
 *
 * The new values (and null flags) have been preloaded into argument positions
 * 1 and up in pertrans->transfn_fcinfo, so that we needn't copy them again to
 * pass to the transition function.  We also expect that the static fields of
 * the fcinfo are already initialized; that was done by ExecInitAgg().
 *
 * It doesn't matter which memory context this is called in.
 */
static void
advance_transition_function(AggState *aggstate,
							AggStatePerTrans pertrans,
							AggStatePerGroup pergroupstate)
{
	FunctionCallInfo fcinfo = pertrans->transfn_fcinfo;
	MemoryContext oldContext;
	Datum		newVal;

	if (pertrans->transfn.fn_strict)
	{
		/*
		 * For a strict transfn, nothing happens when there's a NULL input; we
		 * just keep the prior transValue.
		 */
		int			numTransInputs = pertrans->numTransInputs;
		int			i;

		for (i = 1; i <= numTransInputs; i++)
		{
			if (fcinfo->args[i].isnull)
				return;
		}
		if (pergroupstate->noTransValue)
		{
			/*
			 * transValue has not been initialized. This is the first non-NULL
			 * input value. We use it as the initial value for transValue. (We
			 * already checked that the agg's input type is binary-compatible
			 * with its transtype, so straight copy here is OK.)
			 *
			 * We must copy the datum into aggcontext if it is pass-by-ref. We
			 * do not need to pfree the old transValue, since it's NULL.
			 */
			oldContext = MemoryContextSwitchTo(aggstate->curaggcontext->ecxt_per_tuple_memory);
			pergroupstate->transValue = datumCopy(fcinfo->args[1].value,
												  pertrans->transtypeByVal,
												  pertrans->transtypeLen);
			pergroupstate->transValueIsNull = false;
			pergroupstate->noTransValue = false;
			MemoryContextSwitchTo(oldContext);
			return;
		}
		if (pergroupstate->transValueIsNull)
		{
			/*
			 * Don't call a strict function with NULL inputs.  Note it is
			 * possible to get here despite the above tests, if the transfn is
			 * strict *and* returned a NULL on a prior cycle. If that happens
			 * we will propagate the NULL all the way to the end.
			 */
			return;
		}
	}

	/* We run the transition functions in per-input-tuple memory context */
	oldContext = MemoryContextSwitchTo(aggstate->tmpcontext->ecxt_per_tuple_memory);

	/* set up aggstate->curpertrans for AggGetAggref() */
	aggstate->curpertrans = pertrans;

	/*
	 * OK to call the transition function
	 */
	fcinfo->args[0].value = pergroupstate->transValue;
	fcinfo->args[0].isnull = pergroupstate->transValueIsNull;
	fcinfo->isnull = false;		/* just in case transfn doesn't set it */

	newVal = FunctionCallInvoke(fcinfo);

	aggstate->curpertrans = NULL;

	/*
	 * If pass-by-ref datatype, must copy the new value into aggcontext and
	 * free the prior transValue.  But if transfn returned a pointer to its
	 * first input, we don't need to do anything.
	 *
	 * It's safe to compare newVal with pergroup->transValue without regard
	 * for either being NULL, because ExecAggCopyTransValue takes care to set
	 * transValue to 0 when NULL. Otherwise we could end up accidentally not
	 * reparenting, when the transValue has the same numerical value as
	 * newValue, despite being NULL.  This is a somewhat hot path, making it
	 * undesirable to instead solve this with another branch for the common
	 * case of the transition function returning its (modified) input
	 * argument.
	 */
	if (!pertrans->transtypeByVal &&
		DatumGetPointer(newVal) != DatumGetPointer(pergroupstate->transValue))
		newVal = ExecAggCopyTransValue(aggstate, pertrans,
									   newVal, fcinfo->isnull,
									   pergroupstate->transValue,
									   pergroupstate->transValueIsNull);

	pergroupstate->transValue = newVal;
	pergroupstate->transValueIsNull = fcinfo->isnull;

	MemoryContextSwitchTo(oldContext);
}

/*
 * Advance each aggregate transition state for one input tuple.  The input
 * tuple has been stored in tmpcontext->ecxt_outertuple, so that it is
 * accessible to ExecEvalExpr.
 *
 * We have two sets of transition states to handle: one for sorted aggregation
 * and one for hashed; we do them both here, to avoid multiple evaluation of
 * the inputs.
 *
 * When called, CurrentMemoryContext should be the per-query context.
 */
static void
advance_aggregates(AggState *aggstate)
{
	bool		dummynull;

	ExecEvalExprSwitchContext(aggstate->phase->evaltrans,
							  aggstate->tmpcontext,
							  &dummynull);
}

/*
 * Run the transition function for a DISTINCT or ORDER BY aggregate
 * with only one input.  This is called after we have completed
 * entering all the input values into the sort object.  We complete the
 * sort, read out the values in sorted order, and run the transition
 * function on each value (applying DISTINCT if appropriate).
 *
 * Note that the strictness of the transition function was checked when
 * entering the values into the sort, so we don't check it again here;
 * we just apply standard SQL DISTINCT logic.
 *
 * The one-input case is handled separately from the multi-input case
 * for performance reasons: for single by-value inputs, such as the
 * common case of count(distinct id), the tuplesort_getdatum code path
 * is around 300% faster.  (The speedup for by-reference types is less
 * but still noticeable.)
 *
 * This function handles only one grouping set (already set in
 * aggstate->current_set).
 *
 * When called, CurrentMemoryContext should be the per-query context.
 */
static void
process_ordered_aggregate_single(AggState *aggstate,
								 AggStatePerTrans pertrans,
								 AggStatePerGroup pergroupstate)
{
	Datum		oldVal = (Datum) 0;
	bool		oldIsNull = true;
	bool		haveOldVal = false;
	MemoryContext workcontext = aggstate->tmpcontext->ecxt_per_tuple_memory;
	MemoryContext oldContext;
	bool		isDistinct = (pertrans->numDistinctCols > 0);
	Datum		newAbbrevVal = (Datum) 0;
	Datum		oldAbbrevVal = (Datum) 0;
	FunctionCallInfo fcinfo = pertrans->transfn_fcinfo;
	Datum	   *newVal;
	bool	   *isNull;

	Assert(pertrans->numDistinctCols < 2);

	tuplesort_performsort(pertrans->sortstates[aggstate->current_set]);

	/* Load the column into argument 1 (arg 0 will be transition value) */
	newVal = &fcinfo->args[1].value;
	isNull = &fcinfo->args[1].isnull;

	/*
	 * Note: if input type is pass-by-ref, the datums returned by the sort are
	 * freshly palloc'd in the per-query context, so we must be careful to
	 * pfree them when they are no longer needed.
	 */

	while (tuplesort_getdatum(pertrans->sortstates[aggstate->current_set],
							  true, false, newVal, isNull, &newAbbrevVal))
	{
		/*
		 * Clear and select the working context for evaluation of the equality
		 * function and transition function.
		 */
		MemoryContextReset(workcontext);
		oldContext = MemoryContextSwitchTo(workcontext);

		/*
		 * If DISTINCT mode, and not distinct from prior, skip it.
		 */
		if (isDistinct &&
			haveOldVal &&
			((oldIsNull && *isNull) ||
			 (!oldIsNull && !*isNull &&
			  oldAbbrevVal == newAbbrevVal &&
			  DatumGetBool(FunctionCall2Coll(&pertrans->equalfnOne,
											 pertrans->aggCollation,
											 oldVal, *newVal)))))
		{
			MemoryContextSwitchTo(oldContext);
			continue;
		}
		else
		{
			advance_transition_function(aggstate, pertrans, pergroupstate);

			MemoryContextSwitchTo(oldContext);

			/*
			 * Forget the old value, if any, and remember the new one for
			 * subsequent equality checks.
			 */
			if (!pertrans->inputtypeByVal)
			{
				if (!oldIsNull)
					pfree(DatumGetPointer(oldVal));
				if (!*isNull)
					oldVal = datumCopy(*newVal, pertrans->inputtypeByVal,
									   pertrans->inputtypeLen);
			}
			else
				oldVal = *newVal;
			oldAbbrevVal = newAbbrevVal;
			oldIsNull = *isNull;
			haveOldVal = true;
		}
	}

	if (!oldIsNull && !pertrans->inputtypeByVal)
		pfree(DatumGetPointer(oldVal));

	tuplesort_end(pertrans->sortstates[aggstate->current_set]);
	pertrans->sortstates[aggstate->current_set] = NULL;
}

/*
 * Run the transition function for a DISTINCT or ORDER BY aggregate
 * with more than one input.  This is called after we have completed
 * entering all the input values into the sort object.  We complete the
 * sort, read out the values in sorted order, and run the transition
 * function on each value (applying DISTINCT if appropriate).
 *
 * This function handles only one grouping set (already set in
 * aggstate->current_set).
 *
 * When called, CurrentMemoryContext should be the per-query context.
 */
static void
process_ordered_aggregate_multi(AggState *aggstate,
								AggStatePerTrans pertrans,
								AggStatePerGroup pergroupstate)
{
	ExprContext *tmpcontext = aggstate->tmpcontext;
	FunctionCallInfo fcinfo = pertrans->transfn_fcinfo;
	TupleTableSlot *slot1 = pertrans->sortslot;
	TupleTableSlot *slot2 = pertrans->uniqslot;
	int			numTransInputs = pertrans->numTransInputs;
	int			numDistinctCols = pertrans->numDistinctCols;
	Datum		newAbbrevVal = (Datum) 0;
	Datum		oldAbbrevVal = (Datum) 0;
	bool		haveOldValue = false;
	TupleTableSlot *save = aggstate->tmpcontext->ecxt_outertuple;
	int			i;

	tuplesort_performsort(pertrans->sortstates[aggstate->current_set]);

	ExecClearTuple(slot1);
	if (slot2)
		ExecClearTuple(slot2);

	while (tuplesort_gettupleslot(pertrans->sortstates[aggstate->current_set],
								  true, true, slot1, &newAbbrevVal))
	{
		CHECK_FOR_INTERRUPTS();

		tmpcontext->ecxt_outertuple = slot1;
		tmpcontext->ecxt_innertuple = slot2;

		if (numDistinctCols == 0 ||
			!haveOldValue ||
			newAbbrevVal != oldAbbrevVal ||
			!ExecQual(pertrans->equalfnMulti, tmpcontext))
		{
			/*
			 * Extract the first numTransInputs columns as datums to pass to
			 * the transfn.
			 */
			slot_getsomeattrs(slot1, numTransInputs);

			/* Load values into fcinfo */
			/* Start from 1, since the 0th arg will be the transition value */
			for (i = 0; i < numTransInputs; i++)
			{
				fcinfo->args[i + 1].value = slot1->tts_values[i];
				fcinfo->args[i + 1].isnull = slot1->tts_isnull[i];
			}

			advance_transition_function(aggstate, pertrans, pergroupstate);

			if (numDistinctCols > 0)
			{
				/* swap the slot pointers to retain the current tuple */
				TupleTableSlot *tmpslot = slot2;

				slot2 = slot1;
				slot1 = tmpslot;
				/* avoid ExecQual() calls by reusing abbreviated keys */
				oldAbbrevVal = newAbbrevVal;
				haveOldValue = true;
			}
		}

		/* Reset context each time */
		ResetExprContext(tmpcontext);

		ExecClearTuple(slot1);
	}

	if (slot2)
		ExecClearTuple(slot2);

	tuplesort_end(pertrans->sortstates[aggstate->current_set]);
	pertrans->sortstates[aggstate->current_set] = NULL;

	/* restore previous slot, potentially in use for grouping sets */
	tmpcontext->ecxt_outertuple = save;
}

/*
 * Compute the final value of one aggregate.
 *
 * This function handles only one grouping set (already set in
 * aggstate->current_set).
 *
 * The finalfn will be run, and the result delivered, in the
 * output-tuple context; caller's CurrentMemoryContext does not matter.
 * (But note that in some cases, such as when there is no finalfn, the
 * result might be a pointer to or into the agg's transition value.)
 *
 * The finalfn uses the state as set in the transno.  This also might be
 * being used by another aggregate function, so it's important that we do
 * nothing destructive here.  Moreover, the aggregate's final value might
 * get used in multiple places, so we mustn't return a R/W expanded datum.
 */
static void
finalize_aggregate(AggState *aggstate,
				   AggStatePerAgg peragg,
				   AggStatePerGroup pergroupstate,
				   Datum *resultVal, bool *resultIsNull)
{
	LOCAL_FCINFO(fcinfo, FUNC_MAX_ARGS);
	bool		anynull = false;
	MemoryContext oldContext;
	int			i;
	ListCell   *lc;
	AggStatePerTrans pertrans = &aggstate->pertrans[peragg->transno];

	oldContext = MemoryContextSwitchTo(aggstate->ss.ps.ps_ExprContext->ecxt_per_tuple_memory);

	/*
	 * Evaluate any direct arguments.  We do this even if there's no finalfn
	 * (which is unlikely anyway), so that side-effects happen as expected.
	 * The direct arguments go into arg positions 1 and up, leaving position 0
	 * for the transition state value.
	 */
	i = 1;
	foreach(lc, peragg->aggdirectargs)
	{
		ExprState  *expr = (ExprState *) lfirst(lc);

		fcinfo->args[i].value = ExecEvalExpr(expr,
											 aggstate->ss.ps.ps_ExprContext,
											 &fcinfo->args[i].isnull);
		anynull |= fcinfo->args[i].isnull;
		i++;
	}

	/*
	 * Apply the agg's finalfn if one is provided, else return transValue.
	 */
	if (OidIsValid(peragg->finalfn_oid))
	{
		int			numFinalArgs = peragg->numFinalArgs;

		/* set up aggstate->curperagg for AggGetAggref() */
		aggstate->curperagg = peragg;

		InitFunctionCallInfoData(*fcinfo, &peragg->finalfn,
								 numFinalArgs,
								 pertrans->aggCollation,
								 (void *) aggstate, NULL);

		/* Fill in the transition state value */
		fcinfo->args[0].value =
			MakeExpandedObjectReadOnly(pergroupstate->transValue,
									   pergroupstate->transValueIsNull,
									   pertrans->transtypeLen);
		fcinfo->args[0].isnull = pergroupstate->transValueIsNull;
		anynull |= pergroupstate->transValueIsNull;

		/* Fill any remaining argument positions with nulls */
		for (; i < numFinalArgs; i++)
		{
			fcinfo->args[i].value = (Datum) 0;
			fcinfo->args[i].isnull = true;
			anynull = true;
		}

		if (fcinfo->flinfo->fn_strict && anynull)
		{
			/* don't call a strict function with NULL inputs */
			*resultVal = (Datum) 0;
			*resultIsNull = true;
		}
		else
		{
			Datum		result;

			result = FunctionCallInvoke(fcinfo);
			*resultIsNull = fcinfo->isnull;
			*resultVal = MakeExpandedObjectReadOnly(result,
													fcinfo->isnull,
													peragg->resulttypeLen);
		}
		aggstate->curperagg = NULL;
	}
	else
	{
		*resultVal =
			MakeExpandedObjectReadOnly(pergroupstate->transValue,
									   pergroupstate->transValueIsNull,
									   pertrans->transtypeLen);
		*resultIsNull = pergroupstate->transValueIsNull;
	}

	MemoryContextSwitchTo(oldContext);
}

/*
 * Compute the output value of one partial aggregate.
 *
 * The serialization function will be run, and the result delivered, in the
 * output-tuple context; caller's CurrentMemoryContext does not matter.
 */
static void
finalize_partialaggregate(AggState *aggstate,
						  AggStatePerAgg peragg,
						  AggStatePerGroup pergroupstate,
						  Datum *resultVal, bool *resultIsNull)
{
	AggStatePerTrans pertrans = &aggstate->pertrans[peragg->transno];
	MemoryContext oldContext;

	oldContext = MemoryContextSwitchTo(aggstate->ss.ps.ps_ExprContext->ecxt_per_tuple_memory);

	/*
	 * serialfn_oid will be set if we must serialize the transvalue before
	 * returning it
	 */
	if (OidIsValid(pertrans->serialfn_oid))
	{
		/* Don't call a strict serialization function with NULL input. */
		if (pertrans->serialfn.fn_strict && pergroupstate->transValueIsNull)
		{
			*resultVal = (Datum) 0;
			*resultIsNull = true;
		}
		else
		{
			FunctionCallInfo fcinfo = pertrans->serialfn_fcinfo;
			Datum		result;

			fcinfo->args[0].value =
				MakeExpandedObjectReadOnly(pergroupstate->transValue,
										   pergroupstate->transValueIsNull,
										   pertrans->transtypeLen);
			fcinfo->args[0].isnull = pergroupstate->transValueIsNull;
			fcinfo->isnull = false;

			result = FunctionCallInvoke(fcinfo);
			*resultIsNull = fcinfo->isnull;
			*resultVal = MakeExpandedObjectReadOnly(result,
													fcinfo->isnull,
													peragg->resulttypeLen);
		}
	}
	else
	{
		*resultVal =
			MakeExpandedObjectReadOnly(pergroupstate->transValue,
									   pergroupstate->transValueIsNull,
									   pertrans->transtypeLen);
		*resultIsNull = pergroupstate->transValueIsNull;
	}

	MemoryContextSwitchTo(oldContext);
}

/*
 * Extract the attributes that make up the grouping key into the
 * hashslot. This is necessary to compute the hash or perform a lookup.
 */
static inline void
prepare_hash_slot(AggStatePerHash perhash,
				  TupleTableSlot *inputslot,
				  TupleTableSlot *hashslot)
{
	int			i;

	/* transfer just the needed columns into hashslot */
	slot_getsomeattrs(inputslot, perhash->largestGrpColIdx);
	ExecClearTuple(hashslot);

	for (i = 0; i < perhash->numhashGrpCols; i++)
	{
		int			varNumber = perhash->hashGrpColIdxInput[i] - 1;

		hashslot->tts_values[i] = inputslot->tts_values[varNumber];
		hashslot->tts_isnull[i] = inputslot->tts_isnull[varNumber];
	}
	ExecStoreVirtualTuple(hashslot);
}

/*
 * Prepare to finalize and project based on the specified representative tuple
 * slot and grouping set.
 *
 * In the specified tuple slot, force to null all attributes that should be
 * read as null in the context of the current grouping set.  Also stash the
 * current group bitmap where GroupingExpr can get at it.
 *
 * This relies on three conditions:
 *
 * 1) Nothing is ever going to try and extract the whole tuple from this slot,
 * only reference it in evaluations, which will only access individual
 * attributes.
 *
 * 2) No system columns are going to need to be nulled. (If a system column is
 * referenced in a group clause, it is actually projected in the outer plan
 * tlist.)
 *
 * 3) Within a given phase, we never need to recover the value of an attribute
 * once it has been set to null.
 *
 * Poking into the slot this way is a bit ugly, but the consensus is that the
 * alternative was worse.
 */
static void
prepare_projection_slot(AggState *aggstate, TupleTableSlot *slot, int currentSet)
{
	if (aggstate->phase->grouped_cols)
	{
		Bitmapset  *grouped_cols = aggstate->phase->grouped_cols[currentSet];

		aggstate->grouped_cols = grouped_cols;

		if (TTS_EMPTY(slot))
		{
			/*
			 * Force all values to be NULL if working on an empty input tuple
			 * (i.e. an empty grouping set for which no input rows were
			 * supplied).
			 */
			ExecStoreAllNullTuple(slot);
		}
		else if (aggstate->all_grouped_cols)
		{
			ListCell   *lc;

			/* all_grouped_cols is arranged in desc order */
			slot_getsomeattrs(slot, linitial_int(aggstate->all_grouped_cols));

			foreach(lc, aggstate->all_grouped_cols)
			{
				int			attnum = lfirst_int(lc);

				if (!bms_is_member(attnum, grouped_cols))
					slot->tts_isnull[attnum - 1] = true;
			}
		}
	}
}

/*
 * Compute the final value of all aggregates for one group.
 *
 * This function handles only one grouping set at a time, which the caller must
 * have selected.  It's also the caller's responsibility to adjust the supplied
 * pergroup parameter to point to the current set's transvalues.
 *
 * Results are stored in the output econtext aggvalues/aggnulls.
 */
static void
finalize_aggregates(AggState *aggstate,
					AggStatePerAgg peraggs,
					AggStatePerGroup pergroup)
{
	ExprContext *econtext = aggstate->ss.ps.ps_ExprContext;
	Datum	   *aggvalues = econtext->ecxt_aggvalues;
	bool	   *aggnulls = econtext->ecxt_aggnulls;
	int			aggno;

	/*
	 * If there were any DISTINCT and/or ORDER BY aggregates, sort their
	 * inputs and run the transition functions.
	 */
	for (int transno = 0; transno < aggstate->numtrans; transno++)
	{
		AggStatePerTrans pertrans = &aggstate->pertrans[transno];
		AggStatePerGroup pergroupstate;

		pergroupstate = &pergroup[transno];

		if (pertrans->aggsortrequired)
		{
			Assert(aggstate->aggstrategy != AGG_HASHED &&
				   aggstate->aggstrategy != AGG_MIXED);

			if (pertrans->numInputs == 1)
				process_ordered_aggregate_single(aggstate,
												 pertrans,
												 pergroupstate);
			else
				process_ordered_aggregate_multi(aggstate,
												pertrans,
												pergroupstate);
		}
		else if (pertrans->numDistinctCols > 0 && pertrans->haslast)
		{
			pertrans->haslast = false;

			if (pertrans->numDistinctCols == 1)
			{
				if (!pertrans->inputtypeByVal && !pertrans->lastisnull)
					pfree(DatumGetPointer(pertrans->lastdatum));

				pertrans->lastisnull = false;
				pertrans->lastdatum = (Datum) 0;
			}
			else
				ExecClearTuple(pertrans->uniqslot);
		}
	}

	/*
	 * Run the final functions.
	 */
	for (aggno = 0; aggno < aggstate->numaggs; aggno++)
	{
		AggStatePerAgg peragg = &peraggs[aggno];
		int			transno = peragg->transno;
		AggStatePerGroup pergroupstate;

		pergroupstate = &pergroup[transno];

		if (DO_AGGSPLIT_SKIPFINAL(aggstate->aggsplit))
			finalize_partialaggregate(aggstate, peragg, pergroupstate,
									  &aggvalues[aggno], &aggnulls[aggno]);
		else
			finalize_aggregate(aggstate, peragg, pergroupstate,
							   &aggvalues[aggno], &aggnulls[aggno]);
	}
}

/*
 * Project the result of a group (whose aggs have already been calculated by
 * finalize_aggregates). Returns the result slot, or NULL if no row is
 * projected (suppressed by qual).
 */
static TupleTableSlot *
project_aggregates(AggState *aggstate)
{
	ExprContext *econtext = aggstate->ss.ps.ps_ExprContext;

	/*
	 * Check the qual (HAVING clause); if the group does not match, ignore it.
	 */
	if (ExecQual(aggstate->ss.ps.qual, econtext))
	{
		/*
		 * Form and return projection tuple using the aggregate results and
		 * the representative input tuple.
		 */
		return ExecProject(aggstate->ss.ps.ps_ProjInfo);
	}
	else
		InstrCountFiltered1(aggstate, 1);

	return NULL;
}

/*
 * Find input-tuple columns that are needed, dividing them into
 * aggregated and unaggregated sets.
 */
static void
find_cols(AggState *aggstate, Bitmapset **aggregated, Bitmapset **unaggregated)
{
	Agg		   *agg = (Agg *) aggstate->ss.ps.plan;
	FindColsContext context;

	context.is_aggref = false;
	context.aggregated = NULL;
	context.unaggregated = NULL;

	/* Examine tlist and quals */
	(void) find_cols_walker((Node *) agg->plan.targetlist, &context);
	(void) find_cols_walker((Node *) agg->plan.qual, &context);

	/* In some cases, grouping columns will not appear in the tlist */
	for (int i = 0; i < agg->numCols; i++)
		context.unaggregated = bms_add_member(context.unaggregated,
											  agg->grpColIdx[i]);

	*aggregated = context.aggregated;
	*unaggregated = context.unaggregated;
}

static bool
find_cols_walker(Node *node, FindColsContext *context)
{
	if (node == NULL)
		return false;
	if (IsA(node, Var))
	{
		Var		   *var = (Var *) node;

		/* setrefs.c should have set the varno to OUTER_VAR */
		Assert(var->varno == OUTER_VAR);
		Assert(var->varlevelsup == 0);
		if (context->is_aggref)
			context->aggregated = bms_add_member(context->aggregated,
												 var->varattno);
		else
			context->unaggregated = bms_add_member(context->unaggregated,
												   var->varattno);
		return false;
	}
	if (IsA(node, Aggref))
	{
		Assert(!context->is_aggref);
		context->is_aggref = true;
		expression_tree_walker(node, find_cols_walker, (void *) context);
		context->is_aggref = false;
		return false;
	}
	return expression_tree_walker(node, find_cols_walker,
								  (void *) context);
}

/*
 * (Re-)initialize the hash table(s) to empty.
 *
 * To implement hashed aggregation, we need a hashtable that stores a
 * representative tuple and an array of AggStatePerGroup structs for each
 * distinct set of GROUP BY column values.  We compute the hash key from the
 * GROUP BY columns.  The per-group data is allocated in lookup_hash_entry(),
 * for each entry.
 *
 * We have a separate hashtable and associated perhash data structure for each
 * grouping set for which we're doing hashing.
 *
 * The contents of the hash tables always live in the hashcontext's per-tuple
 * memory context (there is only one of these for all tables together, since
 * they are all reset at the same time).
 */
static void
build_hash_tables(AggState *aggstate)
{
	int			setno;

	for (setno = 0; setno < aggstate->num_hashes; ++setno)
	{
		AggStatePerHash perhash = &aggstate->perhash[setno];
		long		nbuckets;
		Size		memory;

		if (perhash->hashtable != NULL)
		{
			ResetTupleHashTable(perhash->hashtable);
			continue;
		}

		Assert(perhash->aggnode->numGroups > 0);

		memory = aggstate->hash_mem_limit / aggstate->num_hashes;

		/* choose reasonable number of buckets per hashtable */
		nbuckets = hash_choose_num_buckets(aggstate->hashentrysize,
										   perhash->aggnode->numGroups,
										   memory);

		build_hash_table(aggstate, setno, nbuckets);
	}

	aggstate->hash_ngroups_current = 0;
}

/*
 * Build a single hashtable for this grouping set.
 */
static void
build_hash_table(AggState *aggstate, int setno, long nbuckets)
{
	AggStatePerHash perhash = &aggstate->perhash[setno];
	MemoryContext metacxt = aggstate->hash_metacxt;
	MemoryContext hashcxt = aggstate->hashcontext->ecxt_per_tuple_memory;
	MemoryContext tmpcxt = aggstate->tmpcontext->ecxt_per_tuple_memory;
	Size		additionalsize;

	Assert(aggstate->aggstrategy == AGG_HASHED ||
		   aggstate->aggstrategy == AGG_MIXED);

	/*
	 * Used to make sure initial hash table allocation does not exceed
	 * hash_mem. Note that the estimate does not include space for
	 * pass-by-reference transition data values, nor for the representative
	 * tuple of each group.
	 */
	additionalsize = aggstate->numtrans * sizeof(AggStatePerGroupData);

	perhash->hashtable = BuildTupleHashTableExt(&aggstate->ss.ps,
												perhash->hashslot->tts_tupleDescriptor,
												perhash->numCols,
												perhash->hashGrpColIdxHash,
												perhash->eqfuncoids,
												perhash->hashfunctions,
												perhash->aggnode->grpCollations,
												nbuckets,
												additionalsize,
												metacxt,
												hashcxt,
												tmpcxt,
												DO_AGGSPLIT_SKIPFINAL(aggstate->aggsplit));
}

/*
 * Compute columns that actually need to be stored in hashtable entries.  The
 * incoming tuples from the child plan node will contain grouping columns,
 * other columns referenced in our targetlist and qual, columns used to
 * compute the aggregate functions, and perhaps just junk columns we don't use
 * at all.  Only columns of the first two types need to be stored in the
 * hashtable, and getting rid of the others can make the table entries
 * significantly smaller.  The hashtable only contains the relevant columns,
 * and is packed/unpacked in lookup_hash_entry() / agg_retrieve_hash_table()
 * into the format of the normal input descriptor.
 *
 * Additional columns, in addition to the columns grouped by, come from two
 * sources: Firstly functionally dependent columns that we don't need to group
 * by themselves, and secondly ctids for row-marks.
 *
 * To eliminate duplicates, we build a bitmapset of the needed columns, and
 * then build an array of the columns included in the hashtable. We might
 * still have duplicates if the passed-in grpColIdx has them, which can happen
 * in edge cases from semijoins/distinct; these can't always be removed,
 * because it's not certain that the duplicate cols will be using the same
 * hash function.
 *
 * Note that the array is preserved over ExecReScanAgg, so we allocate it in
 * the per-query context (unlike the hash table itself).
 */
static void
find_hash_columns(AggState *aggstate)
{
	Bitmapset  *base_colnos;
	Bitmapset  *aggregated_colnos;
	TupleDesc	scanDesc = aggstate->ss.ss_ScanTupleSlot->tts_tupleDescriptor;
	List	   *outerTlist = outerPlanState(aggstate)->plan->targetlist;
	int			numHashes = aggstate->num_hashes;
	EState	   *estate = aggstate->ss.ps.state;
	int			j;

	/* Find Vars that will be needed in tlist and qual */
	find_cols(aggstate, &aggregated_colnos, &base_colnos);
	aggstate->colnos_needed = bms_union(base_colnos, aggregated_colnos);
	aggstate->max_colno_needed = 0;
	aggstate->all_cols_needed = true;

	for (int i = 0; i < scanDesc->natts; i++)
	{
		int			colno = i + 1;

		if (bms_is_member(colno, aggstate->colnos_needed))
			aggstate->max_colno_needed = colno;
		else
			aggstate->all_cols_needed = false;
	}

	for (j = 0; j < numHashes; ++j)
	{
		AggStatePerHash perhash = &aggstate->perhash[j];
		Bitmapset  *colnos = bms_copy(base_colnos);
		AttrNumber *grpColIdx = perhash->aggnode->grpColIdx;
		List	   *hashTlist = NIL;
		TupleDesc	hashDesc;
		int			maxCols;
		int			i;

		perhash->largestGrpColIdx = 0;

		/*
		 * If we're doing grouping sets, then some Vars might be referenced in
		 * tlist/qual for the benefit of other grouping sets, but not needed
		 * when hashing; i.e. prepare_projection_slot will null them out, so
		 * there'd be no point storing them.  Use prepare_projection_slot's
		 * logic to determine which.
		 */
		if (aggstate->phases[0].grouped_cols)
		{
			Bitmapset  *grouped_cols = aggstate->phases[0].grouped_cols[j];
			ListCell   *lc;

			foreach(lc, aggstate->all_grouped_cols)
			{
				int			attnum = lfirst_int(lc);

				if (!bms_is_member(attnum, grouped_cols))
					colnos = bms_del_member(colnos, attnum);
			}
		}

		/*
		 * Compute maximum number of input columns accounting for possible
		 * duplications in the grpColIdx array, which can happen in some edge
		 * cases where HashAggregate was generated as part of a semijoin or a
		 * DISTINCT.
		 */
		maxCols = bms_num_members(colnos) + perhash->numCols;

		perhash->hashGrpColIdxInput =
			palloc(maxCols * sizeof(AttrNumber));
		perhash->hashGrpColIdxHash =
			palloc(perhash->numCols * sizeof(AttrNumber));

		/* Add all the grouping columns to colnos */
		for (i = 0; i < perhash->numCols; i++)
			colnos = bms_add_member(colnos, grpColIdx[i]);

		/*
		 * First build mapping for columns directly hashed. These are the
		 * first, because they'll be accessed when computing hash values and
		 * comparing tuples for exact matches. We also build simple mapping
		 * for execGrouping, so it knows where to find the to-be-hashed /
		 * compared columns in the input.
		 */
		for (i = 0; i < perhash->numCols; i++)
		{
			perhash->hashGrpColIdxInput[i] = grpColIdx[i];
			perhash->hashGrpColIdxHash[i] = i + 1;
			perhash->numhashGrpCols++;
			/* delete already mapped columns */
			colnos = bms_del_member(colnos, grpColIdx[i]);
		}

		/* and add the remaining columns */
		i = -1;
		while ((i = bms_next_member(colnos, i)) >= 0)
		{
			perhash->hashGrpColIdxInput[perhash->numhashGrpCols] = i;
			perhash->numhashGrpCols++;
		}

		/* and build a tuple descriptor for the hashtable */
		for (i = 0; i < perhash->numhashGrpCols; i++)
		{
			int			varNumber = perhash->hashGrpColIdxInput[i] - 1;

			hashTlist = lappend(hashTlist, list_nth(outerTlist, varNumber));
			perhash->largestGrpColIdx =
				Max(varNumber + 1, perhash->largestGrpColIdx);
		}

		hashDesc = ExecTypeFromTL(hashTlist);

		execTuplesHashPrepare(perhash->numCols,
							  perhash->aggnode->grpOperators,
							  &perhash->eqfuncoids,
							  &perhash->hashfunctions);
		perhash->hashslot =
			ExecAllocTableSlot(&estate->es_tupleTable, hashDesc,
							   &TTSOpsMinimalTuple);

		list_free(hashTlist);
		bms_free(colnos);
	}

	bms_free(base_colnos);
}

/*
 * Estimate per-hash-table-entry overhead.
 */
Size
hash_agg_entry_size(int numTrans, Size tupleWidth, Size transitionSpace)
{
	Size		tupleChunkSize;
	Size		pergroupChunkSize;
	Size		transitionChunkSize;
	Size		tupleSize = (MAXALIGN(SizeofMinimalTupleHeader) +
							 tupleWidth);
	Size		pergroupSize = numTrans * sizeof(AggStatePerGroupData);

	tupleChunkSize = CHUNKHDRSZ + tupleSize;

	if (pergroupSize > 0)
		pergroupChunkSize = CHUNKHDRSZ + pergroupSize;
	else
		pergroupChunkSize = 0;

	if (transitionSpace > 0)
		transitionChunkSize = CHUNKHDRSZ + transitionSpace;
	else
		transitionChunkSize = 0;

	return
		sizeof(TupleHashEntryData) +
		tupleChunkSize +
		pergroupChunkSize +
		transitionChunkSize;
}

/*
 * hashagg_recompile_expressions()
 *
 * Identifies the right phase, compiles the right expression given the
 * arguments, and then sets phase->evalfunc to that expression.
 *
 * Different versions of the compiled expression are needed depending on
 * whether hash aggregation has spilled or not, and whether it's reading from
 * the outer plan or a tape. Before spilling to disk, the expression reads
 * from the outer plan and does not need to perform a NULL check. After
 * HashAgg begins to spill, new groups will not be created in the hash table,
 * and the AggStatePerGroup array may be NULL; therefore we need to add a null
 * pointer check to the expression. Then, when reading spilled data from a
 * tape, we change the outer slot type to be a fixed minimal tuple slot.
 *
 * It would be wasteful to recompile every time, so cache the compiled
 * expressions in the AggStatePerPhase, and reuse when appropriate.
 */
static void
hashagg_recompile_expressions(AggState *aggstate, bool minslot, bool nullcheck)
{
	AggStatePerPhase phase;
	int			i = minslot ? 1 : 0;
	int			j = nullcheck ? 1 : 0;

	Assert(aggstate->aggstrategy == AGG_HASHED ||
		   aggstate->aggstrategy == AGG_MIXED);

	if (aggstate->aggstrategy == AGG_HASHED)
		phase = &aggstate->phases[0];
	else						/* AGG_MIXED */
		phase = &aggstate->phases[1];

	if (phase->evaltrans_cache[i][j] == NULL)
	{
		const TupleTableSlotOps *outerops = aggstate->ss.ps.outerops;
		bool		outerfixed = aggstate->ss.ps.outeropsfixed;
		bool		dohash = true;
		bool		dosort = false;

		/*
		 * If minslot is true, that means we are processing a spilled batch
		 * (inside agg_refill_hash_table()), and we must not advance the
		 * sorted grouping sets.
		 */
		if (aggstate->aggstrategy == AGG_MIXED && !minslot)
			dosort = true;

		/* temporarily change the outerops while compiling the expression */
		if (minslot)
		{
			aggstate->ss.ps.outerops = &TTSOpsMinimalTuple;
			aggstate->ss.ps.outeropsfixed = true;
		}

		phase->evaltrans_cache[i][j] = ExecBuildAggTrans(aggstate, phase,
														 dosort, dohash,
														 nullcheck);

		/* change back */
		aggstate->ss.ps.outerops = outerops;
		aggstate->ss.ps.outeropsfixed = outerfixed;
	}

	phase->evaltrans = phase->evaltrans_cache[i][j];
}

/*
 * Set limits that trigger spilling to avoid exceeding hash_mem. Consider the
 * number of partitions we expect to create (if we do spill).
 *
 * There are two limits: a memory limit, and also an ngroups limit. The
 * ngroups limit becomes important when we expect transition values to grow
 * substantially larger than the initial value.
 */
void
hash_agg_set_limits(double hashentrysize, double input_groups, int used_bits,
					Size *mem_limit, uint64 *ngroups_limit,
					int *num_partitions)
{
	int			npartitions;
	Size		partition_mem;
	Size		hash_mem_limit = get_hash_memory_limit();

	/* if not expected to spill, use all of hash_mem */
	if (input_groups * hashentrysize <= hash_mem_limit)
	{
		if (num_partitions != NULL)
			*num_partitions = 0;
		*mem_limit = hash_mem_limit;
		*ngroups_limit = hash_mem_limit / hashentrysize;
		return;
	}

	/*
	 * Calculate expected memory requirements for spilling, which is the size
	 * of the buffers needed for all the tapes that need to be open at once.
	 * Then, subtract that from the memory available for holding hash tables.
	 */
	npartitions = hash_choose_num_partitions(input_groups,
											 hashentrysize,
											 used_bits,
											 NULL);
	if (num_partitions != NULL)
		*num_partitions = npartitions;

	partition_mem =
		HASHAGG_READ_BUFFER_SIZE +
		HASHAGG_WRITE_BUFFER_SIZE * npartitions;

	/*
	 * Don't set the limit below 3/4 of hash_mem. In that case, we are at the
	 * minimum number of partitions, so we aren't going to dramatically exceed
	 * work mem anyway.
	 */
	if (hash_mem_limit > 4 * partition_mem)
		*mem_limit = hash_mem_limit - partition_mem;
	else
		*mem_limit = hash_mem_limit * 0.75;

	if (*mem_limit > hashentrysize)
		*ngroups_limit = *mem_limit / hashentrysize;
	else
		*ngroups_limit = 1;
}

/*
 * hash_agg_check_limits
 *
 * After adding a new group to the hash table, check whether we need to enter
 * spill mode. Allocations may happen without adding new groups (for instance,
 * if the transition state size grows), so this check is imperfect.
 */
static void
hash_agg_check_limits(AggState *aggstate)
{
	uint64		ngroups = aggstate->hash_ngroups_current;
	Size		meta_mem = MemoryContextMemAllocated(aggstate->hash_metacxt,
													 true);
	Size		hashkey_mem = MemoryContextMemAllocated(aggstate->hashcontext->ecxt_per_tuple_memory,
														true);

	/*
	 * Don't spill unless there's at least one group in the hash table so we
	 * can be sure to make progress even in edge cases.
	 */
	if (aggstate->hash_ngroups_current > 0 &&
		(meta_mem + hashkey_mem > aggstate->hash_mem_limit ||
		 ngroups > aggstate->hash_ngroups_limit))
	{
		hash_agg_enter_spill_mode(aggstate);
	}
}

/*
 * Enter "spill mode", meaning that no new groups are added to any of the hash
 * tables. Tuples that would create a new group are instead spilled, and
 * processed later.
 */
static void
hash_agg_enter_spill_mode(AggState *aggstate)
{
	aggstate->hash_spill_mode = true;
	hashagg_recompile_expressions(aggstate, aggstate->table_filled, true);

	if (!aggstate->hash_ever_spilled)
	{
		Assert(aggstate->hash_tapeset == NULL);
		Assert(aggstate->hash_spills == NULL);

		aggstate->hash_ever_spilled = true;

		aggstate->hash_tapeset = LogicalTapeSetCreate(true, NULL, -1);

		aggstate->hash_spills = palloc(sizeof(HashAggSpill) * aggstate->num_hashes);

		for (int setno = 0; setno < aggstate->num_hashes; setno++)
		{
			AggStatePerHash perhash = &aggstate->perhash[setno];
			HashAggSpill *spill = &aggstate->hash_spills[setno];

			hashagg_spill_init(spill, aggstate->hash_tapeset, 0,
							   perhash->aggnode->numGroups,
							   aggstate->hashentrysize);
		}
	}
}

/*
 * Update metrics after filling the hash table.
 *
 * If reading from the outer plan, from_tape should be false; if reading from
 * another tape, from_tape should be true.
 */
static void
hash_agg_update_metrics(AggState *aggstate, bool from_tape, int npartitions)
{
	Size		meta_mem;
	Size		hashkey_mem;
	Size		buffer_mem;
	Size		total_mem;

	if (aggstate->aggstrategy != AGG_MIXED &&
		aggstate->aggstrategy != AGG_HASHED)
		return;

	/* memory for the hash table itself */
	meta_mem = MemoryContextMemAllocated(aggstate->hash_metacxt, true);

	/* memory for the group keys and transition states */
	hashkey_mem = MemoryContextMemAllocated(aggstate->hashcontext->ecxt_per_tuple_memory, true);

	/* memory for read/write tape buffers, if spilled */
	buffer_mem = npartitions * HASHAGG_WRITE_BUFFER_SIZE;
	if (from_tape)
		buffer_mem += HASHAGG_READ_BUFFER_SIZE;

	/* update peak mem */
	total_mem = meta_mem + hashkey_mem + buffer_mem;
	if (total_mem > aggstate->hash_mem_peak)
		aggstate->hash_mem_peak = total_mem;

	/* update disk usage */
	if (aggstate->hash_tapeset != NULL)
	{
		uint64		disk_used = LogicalTapeSetBlocks(aggstate->hash_tapeset) * (BLCKSZ / 1024);

		if (aggstate->hash_disk_used < disk_used)
			aggstate->hash_disk_used = disk_used;
	}

	/* update hashentrysize estimate based on contents */
	if (aggstate->hash_ngroups_current > 0)
	{
		aggstate->hashentrysize =
			sizeof(TupleHashEntryData) +
			(hashkey_mem / (double) aggstate->hash_ngroups_current);
	}
}

/*
 * Choose a reasonable number of buckets for the initial hash table size.
 */
static long
hash_choose_num_buckets(double hashentrysize, long ngroups, Size memory)
{
	long		max_nbuckets;
	long		nbuckets = ngroups;

	max_nbuckets = memory / hashentrysize;

	/*
	 * Underestimating is better than overestimating. Too many buckets crowd
	 * out space for group keys and transition state values.
	 */
	max_nbuckets >>= 1;

	if (nbuckets > max_nbuckets)
		nbuckets = max_nbuckets;

	return Max(nbuckets, 1);
}

/*
 * Determine the number of partitions to create when spilling, which will
 * always be a power of two. If log2_npartitions is non-NULL, set
 * *log2_npartitions to the log2() of the number of partitions.
 */
static int
hash_choose_num_partitions(double input_groups, double hashentrysize,
						   int used_bits, int *log2_npartitions)
{
	Size		hash_mem_limit = get_hash_memory_limit();
	double		partition_limit;
	double		mem_wanted;
	double		dpartitions;
	int			npartitions;
	int			partition_bits;

	/*
	 * Avoid creating so many partitions that the memory requirements of the
	 * open partition files are greater than 1/4 of hash_mem.
	 */
	partition_limit =
		(hash_mem_limit * 0.25 - HASHAGG_READ_BUFFER_SIZE) /
		HASHAGG_WRITE_BUFFER_SIZE;

	mem_wanted = HASHAGG_PARTITION_FACTOR * input_groups * hashentrysize;

	/* make enough partitions so that each one is likely to fit in memory */
	dpartitions = 1 + (mem_wanted / hash_mem_limit);

	if (dpartitions > partition_limit)
		dpartitions = partition_limit;

	if (dpartitions < HASHAGG_MIN_PARTITIONS)
		dpartitions = HASHAGG_MIN_PARTITIONS;
	if (dpartitions > HASHAGG_MAX_PARTITIONS)
		dpartitions = HASHAGG_MAX_PARTITIONS;

	/* HASHAGG_MAX_PARTITIONS limit makes this safe */
	npartitions = (int) dpartitions;

	/* ceil(log2(npartitions)) */
	partition_bits = my_log2(npartitions);

	/* make sure that we don't exhaust the hash bits */
	if (partition_bits + used_bits >= 32)
		partition_bits = 32 - used_bits;

	if (log2_npartitions != NULL)
		*log2_npartitions = partition_bits;

	/* number of partitions will be a power of two */
	npartitions = 1 << partition_bits;

	return npartitions;
}

/*
 * Initialize a freshly-created TupleHashEntry.
 */
static void
initialize_hash_entry(AggState *aggstate, TupleHashTable hashtable,
					  TupleHashEntry entry)
{
	AggStatePerGroup pergroup;
	int			transno;

	aggstate->hash_ngroups_current++;
	hash_agg_check_limits(aggstate);

	/* no need to allocate or initialize per-group state */
	if (aggstate->numtrans == 0)
		return;

	pergroup = (AggStatePerGroup)
		MemoryContextAlloc(hashtable->tablecxt,
						   sizeof(AggStatePerGroupData) * aggstate->numtrans);

	entry->additional = pergroup;

	/*
	 * Initialize aggregates for new tuple group, lookup_hash_entries()
	 * already has selected the relevant grouping set.
	 */
	for (transno = 0; transno < aggstate->numtrans; transno++)
	{
		AggStatePerTrans pertrans = &aggstate->pertrans[transno];
		AggStatePerGroup pergroupstate = &pergroup[transno];

		initialize_aggregate(aggstate, pertrans, pergroupstate);
	}
}

/*
 * Look up hash entries for the current tuple in all hashed grouping sets.
 *
 * Be aware that lookup_hash_entry can reset the tmpcontext.
 *
 * Some entries may be left NULL if we are in "spill mode". The same tuple
 * will belong to different groups for each grouping set, so may match a group
 * already in memory for one set and match a group not in memory for another
 * set. When in "spill mode", the tuple will be spilled for each grouping set
 * where it doesn't match a group in memory.
 *
 * NB: It's possible to spill the same tuple for several different grouping
 * sets. This may seem wasteful, but it's actually a trade-off: if we spill
 * the tuple multiple times for multiple grouping sets, it can be partitioned
 * for each grouping set, making the refilling of the hash table very
 * efficient.
 */
static void
lookup_hash_entries(AggState *aggstate)
{
	AggStatePerGroup *pergroup = aggstate->hash_pergroup;
	TupleTableSlot *outerslot = aggstate->tmpcontext->ecxt_outertuple;
	int			setno;

	for (setno = 0; setno < aggstate->num_hashes; setno++)
	{
		AggStatePerHash perhash = &aggstate->perhash[setno];
		TupleHashTable hashtable = perhash->hashtable;
		TupleTableSlot *hashslot = perhash->hashslot;
		TupleHashEntry entry;
		uint32		hash;
		bool		isnew = false;
		bool	   *p_isnew;

		/* if hash table already spilled, don't create new entries */
		p_isnew = aggstate->hash_spill_mode ? NULL : &isnew;

		select_current_set(aggstate, setno, true);
		prepare_hash_slot(perhash,
						  outerslot,
						  hashslot);

		entry = LookupTupleHashEntry(hashtable, hashslot,
									 p_isnew, &hash);

		if (entry != NULL)
		{
			if (isnew)
				initialize_hash_entry(aggstate, hashtable, entry);
			pergroup[setno] = entry->additional;
		}
		else
		{
			HashAggSpill *spill = &aggstate->hash_spills[setno];
			TupleTableSlot *slot = aggstate->tmpcontext->ecxt_outertuple;

			if (spill->partitions == NULL)
				hashagg_spill_init(spill, aggstate->hash_tapeset, 0,
								   perhash->aggnode->numGroups,
								   aggstate->hashentrysize);

			hashagg_spill_tuple(aggstate, spill, slot, hash);
			pergroup[setno] = NULL;
		}
	}
}

/*
 * ExecAgg -
 *
 *	  ExecAgg receives tuples from its outer subplan and aggregates over
 *	  the appropriate attribute for each aggregate function use (Aggref
 *	  node) appearing in the targetlist or qual of the node.  The number
 *	  of tuples to aggregate over depends on whether grouped or plain
 *	  aggregation is selected.  In grouped aggregation, we produce a result
 *	  row for each group; in plain aggregation there's a single result row
 *	  for the whole query.  In either case, the value of each aggregate is
 *	  stored in the expression context to be used when ExecProject evaluates
 *	  the result tuple.
 */
static TupleTableSlot *
ExecAgg(PlanState *pstate)
{
	AggState   *node = castNode(AggState, pstate);
	TupleTableSlot *result = NULL;

	CHECK_FOR_INTERRUPTS();

	if (!node->agg_done)
	{
		/* Dispatch based on strategy */
		switch (node->phase->aggstrategy)
		{
			case AGG_HASHED:
				if (!node->table_filled)
					agg_fill_hash_table(node);
				/* FALLTHROUGH */
			case AGG_MIXED:
				result = agg_retrieve_hash_table(node);
				break;
			case AGG_PLAIN:
			case AGG_SORTED:
				result = agg_retrieve_direct(node);
				break;
		}

		if (!TupIsNull(result))
			return result;
	}

	return NULL;
}

/*
 * ExecAgg for non-hashed case
 */
static TupleTableSlot *
agg_retrieve_direct(AggState *aggstate)
{
	Agg		   *node = aggstate->phase->aggnode;
	ExprContext *econtext;
	ExprContext *tmpcontext;
	AggStatePerAgg peragg;
	AggStatePerGroup *pergroups;
	TupleTableSlot *outerslot;
	TupleTableSlot *firstSlot;
	TupleTableSlot *result;
	bool		hasGroupingSets = aggstate->phase->numsets > 0;
	int			numGroupingSets = Max(aggstate->phase->numsets, 1);
	int			currentSet;
	int			nextSetSize;
	int			numReset;
	int			i;

	/*
	 * get state info from node
	 *
	 * econtext is the per-output-tuple expression context
	 *
	 * tmpcontext is the per-input-tuple expression context
	 */
	econtext = aggstate->ss.ps.ps_ExprContext;
	tmpcontext = aggstate->tmpcontext;

	peragg = aggstate->peragg;
	pergroups = aggstate->pergroups;
	firstSlot = aggstate->ss.ss_ScanTupleSlot;

	/*
	 * We loop retrieving groups until we find one matching
	 * aggstate->ss.ps.qual
	 *
	 * For grouping sets, we have the invariant that aggstate->projected_set
	 * is either -1 (initial call) or the index (starting from 0) in
	 * gset_lengths for the group we just completed (either by projecting a
	 * row or by discarding it in the qual).
	 */
	while (!aggstate->agg_done)
	{
		/*
		 * Clear the per-output-tuple context for each group, as well as
		 * aggcontext (which contains any pass-by-ref transvalues of the old
		 * group).  Some aggregate functions store working state in child
		 * contexts; those now get reset automatically without us needing to
		 * do anything special.
		 *
		 * We use ReScanExprContext not just ResetExprContext because we want
		 * any registered shutdown callbacks to be called.  That allows
		 * aggregate functions to ensure they've cleaned up any non-memory
		 * resources.
		 */
		ReScanExprContext(econtext);

		/*
		 * Determine how many grouping sets need to be reset at this boundary.
		 */
		if (aggstate->projected_set >= 0 &&
			aggstate->projected_set < numGroupingSets)
			numReset = aggstate->projected_set + 1;
		else
			numReset = numGroupingSets;

		/*
		 * numReset can change on a phase boundary, but that's OK; we want to
		 * reset the contexts used in _this_ phase, and later, after possibly
		 * changing phase, initialize the right number of aggregates for the
		 * _new_ phase.
		 */

		for (i = 0; i < numReset; i++)
		{
			ReScanExprContext(aggstate->aggcontexts[i]);
		}

		/*
		 * Check if input is complete and there are no more groups to project
		 * in this phase; move to next phase or mark as done.
		 */
		if (aggstate->input_done == true &&
			aggstate->projected_set >= (numGroupingSets - 1))
		{
			if (aggstate->current_phase < aggstate->numphases - 1)
			{
				initialize_phase(aggstate, aggstate->current_phase + 1);
				aggstate->input_done = false;
				aggstate->projected_set = -1;
				numGroupingSets = Max(aggstate->phase->numsets, 1);
				node = aggstate->phase->aggnode;
				numReset = numGroupingSets;
			}
			else if (aggstate->aggstrategy == AGG_MIXED)
			{
				/*
				 * Mixed mode; we've output all the grouped stuff and have
				 * full hashtables, so switch to outputting those.
				 */
				initialize_phase(aggstate, 0);
				aggstate->table_filled = true;
				ResetTupleHashIterator(aggstate->perhash[0].hashtable,
									   &aggstate->perhash[0].hashiter);
				select_current_set(aggstate, 0, true);
				return agg_retrieve_hash_table(aggstate);
			}
			else
			{
				aggstate->agg_done = true;
				break;
			}
		}

		/*
		 * Get the number of columns in the next grouping set after the last
		 * projected one (if any). This is the number of columns to compare to
		 * see if we reached the boundary of that set too.
		 */
		if (aggstate->projected_set >= 0 &&
			aggstate->projected_set < (numGroupingSets - 1))
			nextSetSize = aggstate->phase->gset_lengths[aggstate->projected_set + 1];
		else
			nextSetSize = 0;

		/*----------
		 * If a subgroup for the current grouping set is present, project it.
		 *
		 * We have a new group if:
		 *	- we're out of input but haven't projected all grouping sets
		 *	  (checked above)
		 * OR
		 *	  - we already projected a row that wasn't from the last grouping
		 *		set
		 *	  AND
		 *	  - the next grouping set has at least one grouping column (since
		 *		empty grouping sets project only once input is exhausted)
		 *	  AND
		 *	  - the previous and pending rows differ on the grouping columns
		 *		of the next grouping set
		 *----------
		 */
		tmpcontext->ecxt_innertuple = econtext->ecxt_outertuple;
		if (aggstate->input_done ||
			(node->aggstrategy != AGG_PLAIN &&
			 aggstate->projected_set != -1 &&
			 aggstate->projected_set < (numGroupingSets - 1) &&
			 nextSetSize > 0 &&
			 !ExecQualAndReset(aggstate->phase->eqfunctions[nextSetSize - 1],
							   tmpcontext)))
		{
			aggstate->projected_set += 1;

			Assert(aggstate->projected_set < numGroupingSets);
			Assert(nextSetSize > 0 || aggstate->input_done);
		}
		else
		{
			/*
			 * We no longer care what group we just projected, the next
			 * projection will always be the first (or only) grouping set
			 * (unless the input proves to be empty).
			 */
			aggstate->projected_set = 0;

			/*
			 * If we don't already have the first tuple of the new group,
			 * fetch it from the outer plan.
			 */
			if (aggstate->grp_firstTuple == NULL)
			{
				outerslot = fetch_input_tuple(aggstate);
				if (!TupIsNull(outerslot))
				{
					/*
					 * Make a copy of the first input tuple; we will use this
					 * for comparisons (in group mode) and for projection.
					 */
					aggstate->grp_firstTuple = ExecCopySlotHeapTuple(outerslot);
				}
				else
				{
					/* outer plan produced no tuples at all */
					if (hasGroupingSets)
					{
						/*
						 * If there was no input at all, we need to project
						 * rows only if there are grouping sets of size 0.
						 * Note that this implies that there can't be any
						 * references to ungrouped Vars, which would otherwise
						 * cause issues with the empty output slot.
						 *
						 * XXX: This is no longer true, we currently deal with
						 * this in finalize_aggregates().
						 */
						aggstate->input_done = true;

						while (aggstate->phase->gset_lengths[aggstate->projected_set] > 0)
						{
							aggstate->projected_set += 1;
							if (aggstate->projected_set >= numGroupingSets)
							{
								/*
								 * We can't set agg_done here because we might
								 * have more phases to do, even though the
								 * input is empty. So we need to restart the
								 * whole outer loop.
								 */
								break;
							}
						}

						if (aggstate->projected_set >= numGroupingSets)
							continue;
					}
					else
					{
						aggstate->agg_done = true;
						/* If we are grouping, we should produce no tuples too */
						if (node->aggstrategy != AGG_PLAIN)
							return NULL;
					}
				}
			}

			/*
			 * Initialize working state for a new input tuple group.
			 */
			initialize_aggregates(aggstate, pergroups, numReset);

			if (aggstate->grp_firstTuple != NULL)
			{
				/*
				 * Store the copied first input tuple in the tuple table slot
				 * reserved for it.  The tuple will be deleted when it is
				 * cleared from the slot.
				 */
				ExecForceStoreHeapTuple(aggstate->grp_firstTuple,
										firstSlot, true);
				aggstate->grp_firstTuple = NULL;	/* don't keep two pointers */

				/* set up for first advance_aggregates call */
				tmpcontext->ecxt_outertuple = firstSlot;

				/*
				 * Process each outer-plan tuple, and then fetch the next one,
				 * until we exhaust the outer plan or cross a group boundary.
				 */
				for (;;)
				{
					/*
					 * During phase 1 only of a mixed agg, we need to update
					 * hashtables as well in advance_aggregates.
					 */
					if (aggstate->aggstrategy == AGG_MIXED &&
						aggstate->current_phase == 1)
					{
						lookup_hash_entries(aggstate);
					}

					/* Advance the aggregates (or combine functions) */
					advance_aggregates(aggstate);

					/* Reset per-input-tuple context after each tuple */
					ResetExprContext(tmpcontext);

					outerslot = fetch_input_tuple(aggstate);
					if (TupIsNull(outerslot))
					{
						/* no more outer-plan tuples available */

						/* if we built hash tables, finalize any spills */
						if (aggstate->aggstrategy == AGG_MIXED &&
							aggstate->current_phase == 1)
							hashagg_finish_initial_spills(aggstate);

						if (hasGroupingSets)
						{
							aggstate->input_done = true;
							break;
						}
						else
						{
							aggstate->agg_done = true;
							break;
						}
					}
					/* set up for next advance_aggregates call */
					tmpcontext->ecxt_outertuple = outerslot;

					/*
					 * If we are grouping, check whether we've crossed a group
					 * boundary.
					 */
					if (node->aggstrategy != AGG_PLAIN && node->numCols > 0)
					{
						tmpcontext->ecxt_innertuple = firstSlot;
						if (!ExecQual(aggstate->phase->eqfunctions[node->numCols - 1],
									  tmpcontext))
						{
							aggstate->grp_firstTuple = ExecCopySlotHeapTuple(outerslot);
							break;
						}
					}
				}
			}

			/*
			 * Use the representative input tuple for any references to
			 * non-aggregated input columns in aggregate direct args, the node
			 * qual, and the tlist.  (If we are not grouping, and there are no
			 * input rows at all, we will come here with an empty firstSlot
			 * ... but if not grouping, there can't be any references to
			 * non-aggregated input columns, so no problem.)
			 */
			econtext->ecxt_outertuple = firstSlot;
		}

		Assert(aggstate->projected_set >= 0);

		currentSet = aggstate->projected_set;

		prepare_projection_slot(aggstate, econtext->ecxt_outertuple, currentSet);

		select_current_set(aggstate, currentSet, false);

		finalize_aggregates(aggstate,
							peragg,
							pergroups[currentSet]);

		/*
		 * If there's no row to project right now, we must continue rather
		 * than returning a null since there might be more groups.
		 */
		result = project_aggregates(aggstate);
		if (result)
			return result;
	}

	/* No more groups */
	return NULL;
}

/*
 * ExecAgg for hashed case: read input and build hash table
 */
static void
agg_fill_hash_table(AggState *aggstate)
{
	TupleTableSlot *outerslot;
	ExprContext *tmpcontext = aggstate->tmpcontext;

	/*
	 * Process each outer-plan tuple, and then fetch the next one, until we
	 * exhaust the outer plan.
	 */
	for (;;)
	{
		outerslot = fetch_input_tuple(aggstate);
		if (TupIsNull(outerslot))
			break;

		/* set up for lookup_hash_entries and advance_aggregates */
		tmpcontext->ecxt_outertuple = outerslot;

		/* Find or build hashtable entries */
		lookup_hash_entries(aggstate);

		/* Advance the aggregates (or combine functions) */
		advance_aggregates(aggstate);

		/*
		 * Reset per-input-tuple context after each tuple, but note that the
		 * hash lookups do this too
		 */
		ResetExprContext(aggstate->tmpcontext);
	}

	/* finalize spills, if any */
	hashagg_finish_initial_spills(aggstate);

	aggstate->table_filled = true;
	/* Initialize to walk the first hash table */
	select_current_set(aggstate, 0, true);
	ResetTupleHashIterator(aggstate->perhash[0].hashtable,
						   &aggstate->perhash[0].hashiter);
}

/*
 * If any data was spilled during hash aggregation, reset the hash table and
 * reprocess one batch of spilled data. After reprocessing a batch, the hash
 * table will again contain data, ready to be consumed by
 * agg_retrieve_hash_table_in_memory().
 *
 * Should only be called after all in memory hash table entries have been
 * finalized and emitted.
 *
 * Return false when input is exhausted and there's no more work to be done;
 * otherwise return true.
 */
static bool
agg_refill_hash_table(AggState *aggstate)
{
	HashAggBatch *batch;
	AggStatePerHash perhash;
	HashAggSpill spill;
	LogicalTapeSet *tapeset = aggstate->hash_tapeset;
	bool		spill_initialized = false;

	if (aggstate->hash_batches == NIL)
		return false;

	/* hash_batches is a stack, with the top item at the end of the list */
	batch = llast(aggstate->hash_batches);
	aggstate->hash_batches = list_delete_last(aggstate->hash_batches);

	hash_agg_set_limits(aggstate->hashentrysize, batch->input_card,
						batch->used_bits, &aggstate->hash_mem_limit,
						&aggstate->hash_ngroups_limit, NULL);

	/*
	 * Each batch only processes one grouping set; set the rest to NULL so
	 * that advance_aggregates() knows to ignore them. We don't touch
	 * pergroups for sorted grouping sets here, because they will be needed if
	 * we rescan later. The expressions for sorted grouping sets will not be
	 * evaluated after we recompile anyway.
	 */
	MemSet(aggstate->hash_pergroup, 0,
		   sizeof(AggStatePerGroup) * aggstate->num_hashes);

	/* free memory and reset hash tables */
	ReScanExprContext(aggstate->hashcontext);
	for (int setno = 0; setno < aggstate->num_hashes; setno++)
		ResetTupleHashTable(aggstate->perhash[setno].hashtable);

	aggstate->hash_ngroups_current = 0;

	/*
	 * In AGG_MIXED mode, hash aggregation happens in phase 1 and the output
	 * happens in phase 0. So, we switch to phase 1 when processing a batch,
	 * and back to phase 0 after the batch is done.
	 */
	Assert(aggstate->current_phase == 0);
	if (aggstate->phase->aggstrategy == AGG_MIXED)
	{
		aggstate->current_phase = 1;
		aggstate->phase = &aggstate->phases[aggstate->current_phase];
	}

	select_current_set(aggstate, batch->setno, true);

	perhash = &aggstate->perhash[aggstate->current_set];

	/*
	 * Spilled tuples are always read back as MinimalTuples, which may be
	 * different from the outer plan, so recompile the aggregate expressions.
	 *
	 * We still need the NULL check, because we are only processing one
	 * grouping set at a time and the rest will be NULL.
	 */
	hashagg_recompile_expressions(aggstate, true, true);

	for (;;)
	{
		TupleTableSlot *spillslot = aggstate->hash_spill_rslot;
		TupleTableSlot *hashslot = perhash->hashslot;
		TupleHashEntry entry;
		MinimalTuple tuple;
		uint32		hash;
		bool		isnew = false;
		bool	   *p_isnew = aggstate->hash_spill_mode ? NULL : &isnew;

		CHECK_FOR_INTERRUPTS();

		tuple = hashagg_batch_read(batch, &hash);
		if (tuple == NULL)
			break;

		ExecStoreMinimalTuple(tuple, spillslot, true);
		aggstate->tmpcontext->ecxt_outertuple = spillslot;

		prepare_hash_slot(perhash,
						  aggstate->tmpcontext->ecxt_outertuple,
						  hashslot);
		entry = LookupTupleHashEntryHash(perhash->hashtable, hashslot,
										 p_isnew, hash);

		if (entry != NULL)
		{
			if (isnew)
				initialize_hash_entry(aggstate, perhash->hashtable, entry);
			aggstate->hash_pergroup[batch->setno] = entry->additional;
			advance_aggregates(aggstate);
		}
		else
		{
			if (!spill_initialized)
			{
				/*
				 * Avoid initializing the spill until we actually need it so
				 * that we don't assign tapes that will never be used.
				 */
				spill_initialized = true;
				hashagg_spill_init(&spill, tapeset, batch->used_bits,
								   batch->input_card, aggstate->hashentrysize);
			}
			/* no memory for a new group, spill */
			hashagg_spill_tuple(aggstate, &spill, spillslot, hash);

			aggstate->hash_pergroup[batch->setno] = NULL;
		}

		/*
		 * Reset per-input-tuple context after each tuple, but note that the
		 * hash lookups do this too
		 */
		ResetExprContext(aggstate->tmpcontext);
	}

	LogicalTapeClose(batch->input_tape);

	/* change back to phase 0 */
	aggstate->current_phase = 0;
	aggstate->phase = &aggstate->phases[aggstate->current_phase];

	if (spill_initialized)
	{
		hashagg_spill_finish(aggstate, &spill, batch->setno);
		hash_agg_update_metrics(aggstate, true, spill.npartitions);
	}
	else
		hash_agg_update_metrics(aggstate, true, 0);

	aggstate->hash_spill_mode = false;

	/* prepare to walk the first hash table */
	select_current_set(aggstate, batch->setno, true);
	ResetTupleHashIterator(aggstate->perhash[batch->setno].hashtable,
						   &aggstate->perhash[batch->setno].hashiter);

	pfree(batch);

	return true;
}

/*
 * ExecAgg for hashed case: retrieving groups from hash table
 *
 * After exhausting in-memory tuples, also try refilling the hash table using
 * previously-spilled tuples. Only returns NULL after all in-memory and
 * spilled tuples are exhausted.
 */
static TupleTableSlot *
agg_retrieve_hash_table(AggState *aggstate)
{
	TupleTableSlot *result = NULL;

	while (result == NULL)
	{
		result = agg_retrieve_hash_table_in_memory(aggstate);
		if (result == NULL)
		{
			if (!agg_refill_hash_table(aggstate))
			{
				aggstate->agg_done = true;
				break;
			}
		}
	}

	return result;
}

/*
 * Retrieve the groups from the in-memory hash tables without considering any
 * spilled tuples.
 */
static TupleTableSlot *
agg_retrieve_hash_table_in_memory(AggState *aggstate)
{
	ExprContext *econtext;
	AggStatePerAgg peragg;
	AggStatePerGroup pergroup;
	TupleHashEntryData *entry;
	TupleTableSlot *firstSlot;
	TupleTableSlot *result;
	AggStatePerHash perhash;

	/*
	 * get state info from node.
	 *
	 * econtext is the per-output-tuple expression context.
	 */
	econtext = aggstate->ss.ps.ps_ExprContext;
	peragg = aggstate->peragg;
	firstSlot = aggstate->ss.ss_ScanTupleSlot;

	/*
	 * Note that perhash (and therefore anything accessed through it) can
	 * change inside the loop, as we change between grouping sets.
	 */
	perhash = &aggstate->perhash[aggstate->current_set];

	/*
	 * We loop retrieving groups until we find one satisfying
	 * aggstate->ss.ps.qual
	 */
	for (;;)
	{
		TupleTableSlot *hashslot = perhash->hashslot;
		int			i;

		CHECK_FOR_INTERRUPTS();

		/*
		 * Find the next entry in the hash table
		 */
		entry = ScanTupleHashTable(perhash->hashtable, &perhash->hashiter);
		if (entry == NULL)
		{
			int			nextset = aggstate->current_set + 1;

			if (nextset < aggstate->num_hashes)
			{
				/*
				 * Switch to next grouping set, reinitialize, and restart the
				 * loop.
				 */
				select_current_set(aggstate, nextset, true);

				perhash = &aggstate->perhash[aggstate->current_set];

				ResetTupleHashIterator(perhash->hashtable, &perhash->hashiter);

				continue;
			}
			else
			{
				return NULL;
			}
		}

		/*
		 * Clear the per-output-tuple context for each group
		 *
		 * We intentionally don't use ReScanExprContext here; if any aggs have
		 * registered shutdown callbacks, they mustn't be called yet, since we
		 * might not be done with that agg.
		 */
		ResetExprContext(econtext);

		/*
		 * Transform representative tuple back into one with the right
		 * columns.
		 */
		ExecStoreMinimalTuple(entry->firstTuple, hashslot, false);
		slot_getallattrs(hashslot);

		ExecClearTuple(firstSlot);
		memset(firstSlot->tts_isnull, true,
			   firstSlot->tts_tupleDescriptor->natts * sizeof(bool));

		for (i = 0; i < perhash->numhashGrpCols; i++)
		{
			int			varNumber = perhash->hashGrpColIdxInput[i] - 1;

			firstSlot->tts_values[varNumber] = hashslot->tts_values[i];
			firstSlot->tts_isnull[varNumber] = hashslot->tts_isnull[i];
		}
		ExecStoreVirtualTuple(firstSlot);

		pergroup = (AggStatePerGroup) entry->additional;

		/*
		 * Use the representative input tuple for any references to
		 * non-aggregated input columns in the qual and tlist.
		 */
		econtext->ecxt_outertuple = firstSlot;

		prepare_projection_slot(aggstate,
								econtext->ecxt_outertuple,
								aggstate->current_set);

		finalize_aggregates(aggstate, peragg, pergroup);

		result = project_aggregates(aggstate);
		if (result)
			return result;
	}

	/* No more groups */
	return NULL;
}

/*
 * hashagg_spill_init
 *
 * Called after we determined that spilling is necessary. Chooses the number
 * of partitions to create, and initializes them.
 */
static void
hashagg_spill_init(HashAggSpill *spill, LogicalTapeSet *tapeset, int used_bits,
				   double input_groups, double hashentrysize)
{
	int			npartitions;
	int			partition_bits;

	npartitions = hash_choose_num_partitions(input_groups, hashentrysize,
											 used_bits, &partition_bits);

	spill->partitions = palloc0(sizeof(LogicalTape *) * npartitions);
	spill->ntuples = palloc0(sizeof(int64) * npartitions);
	spill->hll_card = palloc0(sizeof(hyperLogLogState) * npartitions);

	for (int i = 0; i < npartitions; i++)
		spill->partitions[i] = LogicalTapeCreate(tapeset);

	spill->shift = 32 - used_bits - partition_bits;
	spill->mask = (npartitions - 1) << spill->shift;
	spill->npartitions = npartitions;

	for (int i = 0; i < npartitions; i++)
		initHyperLogLog(&spill->hll_card[i], HASHAGG_HLL_BIT_WIDTH);
}

/*
 * hashagg_spill_tuple
 *
 * No room for new groups in the hash table. Save for later in the appropriate
 * partition.
 */
static Size
hashagg_spill_tuple(AggState *aggstate, HashAggSpill *spill,
					TupleTableSlot *inputslot, uint32 hash)
{
	TupleTableSlot *spillslot;
	int			partition;
	MinimalTuple tuple;
	LogicalTape *tape;
	int			total_written = 0;
	bool		shouldFree;

	Assert(spill->partitions != NULL);

	/* spill only attributes that we actually need */
	if (!aggstate->all_cols_needed)
	{
		spillslot = aggstate->hash_spill_wslot;
		slot_getsomeattrs(inputslot, aggstate->max_colno_needed);
		ExecClearTuple(spillslot);
		for (int i = 0; i < spillslot->tts_tupleDescriptor->natts; i++)
		{
			if (bms_is_member(i + 1, aggstate->colnos_needed))
			{
				spillslot->tts_values[i] = inputslot->tts_values[i];
				spillslot->tts_isnull[i] = inputslot->tts_isnull[i];
			}
			else
				spillslot->tts_isnull[i] = true;
		}
		ExecStoreVirtualTuple(spillslot);
	}
	else
		spillslot = inputslot;

	tuple = ExecFetchSlotMinimalTuple(spillslot, &shouldFree);

	partition = (hash & spill->mask) >> spill->shift;
	spill->ntuples[partition]++;

	/*
	 * All hash values destined for a given partition have some bits in
	 * common, which causes bad HLL cardinality estimates. Hash the hash to
	 * get a more uniform distribution.
	 */
	addHyperLogLog(&spill->hll_card[partition], hash_bytes_uint32(hash));

	tape = spill->partitions[partition];

	LogicalTapeWrite(tape, &hash, sizeof(uint32));
	total_written += sizeof(uint32);

	LogicalTapeWrite(tape, tuple, tuple->t_len);
	total_written += tuple->t_len;

	if (shouldFree)
		pfree(tuple);

	return total_written;
}

/*
 * hashagg_batch_new
 *
 * Construct a HashAggBatch item, which represents one iteration of HashAgg to
 * be done.
 */
static HashAggBatch *
hashagg_batch_new(LogicalTape *input_tape, int setno,
				  int64 input_tuples, double input_card, int used_bits)
{
	HashAggBatch *batch = palloc0(sizeof(HashAggBatch));

	batch->setno = setno;
	batch->used_bits = used_bits;
	batch->input_tape = input_tape;
	batch->input_tuples = input_tuples;
	batch->input_card = input_card;

	return batch;
}

/*
 * hashagg_batch_read
 * 		read the next tuple from a batch's tape.  Return NULL if no more.
 */
static MinimalTuple
hashagg_batch_read(HashAggBatch *batch, uint32 *hashp)
{
	LogicalTape *tape = batch->input_tape;
	MinimalTuple tuple;
	uint32		t_len;
	size_t		nread;
	uint32		hash;

	nread = LogicalTapeRead(tape, &hash, sizeof(uint32));
	if (nread == 0)
		return NULL;
	if (nread != sizeof(uint32))
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("unexpected EOF for tape %p: requested %zu bytes, read %zu bytes",
						tape, sizeof(uint32), nread)));
	if (hashp != NULL)
		*hashp = hash;

	nread = LogicalTapeRead(tape, &t_len, sizeof(t_len));
	if (nread != sizeof(uint32))
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("unexpected EOF for tape %p: requested %zu bytes, read %zu bytes",
						tape, sizeof(uint32), nread)));

	tuple = (MinimalTuple) palloc(t_len);
	tuple->t_len = t_len;

	nread = LogicalTapeRead(tape,
							(char *) tuple + sizeof(uint32),
							t_len - sizeof(uint32));
	if (nread != t_len - sizeof(uint32))
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("unexpected EOF for tape %p: requested %zu bytes, read %zu bytes",
						tape, t_len - sizeof(uint32), nread)));

	return tuple;
}

/*
 * hashagg_finish_initial_spills
 *
 * After a HashAggBatch has been processed, it may have spilled tuples to
 * disk. If so, turn the spilled partitions into new batches that must later
 * be executed.
 */
static void
hashagg_finish_initial_spills(AggState *aggstate)
{
	int			setno;
	int			total_npartitions = 0;

	if (aggstate->hash_spills != NULL)
	{
		for (setno = 0; setno < aggstate->num_hashes; setno++)
		{
			HashAggSpill *spill = &aggstate->hash_spills[setno];

			total_npartitions += spill->npartitions;
			hashagg_spill_finish(aggstate, spill, setno);
		}

		/*
		 * We're not processing tuples from outer plan any more; only
		 * processing batches of spilled tuples. The initial spill structures
		 * are no longer needed.
		 */
		pfree(aggstate->hash_spills);
		aggstate->hash_spills = NULL;
	}

	hash_agg_update_metrics(aggstate, false, total_npartitions);
	aggstate->hash_spill_mode = false;
}

/*
 * hashagg_spill_finish
 *
 * Transform spill partitions into new batches.
 */
static void
hashagg_spill_finish(AggState *aggstate, HashAggSpill *spill, int setno)
{
	int			i;
	int			used_bits = 32 - spill->shift;

	if (spill->npartitions == 0)
		return;					/* didn't spill */

	for (i = 0; i < spill->npartitions; i++)
	{
		LogicalTape *tape = spill->partitions[i];
		HashAggBatch *new_batch;
		double		cardinality;

		/* if the partition is empty, don't create a new batch of work */
		if (spill->ntuples[i] == 0)
			continue;

		cardinality = estimateHyperLogLog(&spill->hll_card[i]);
		freeHyperLogLog(&spill->hll_card[i]);

		/* rewinding frees the buffer while not in use */
		LogicalTapeRewindForRead(tape, HASHAGG_READ_BUFFER_SIZE);

		new_batch = hashagg_batch_new(tape, setno,
									  spill->ntuples[i], cardinality,
									  used_bits);
		aggstate->hash_batches = lappend(aggstate->hash_batches, new_batch);
		aggstate->hash_batches_used++;
	}

	pfree(spill->ntuples);
	pfree(spill->hll_card);
	pfree(spill->partitions);
}

/*
 * Free resources related to a spilled HashAgg.
 */
static void
hashagg_reset_spill_state(AggState *aggstate)
{
	/* free spills from initial pass */
	if (aggstate->hash_spills != NULL)
	{
		int			setno;

		for (setno = 0; setno < aggstate->num_hashes; setno++)
		{
			HashAggSpill *spill = &aggstate->hash_spills[setno];

			pfree(spill->ntuples);
			pfree(spill->partitions);
		}
		pfree(aggstate->hash_spills);
		aggstate->hash_spills = NULL;
	}

	/* free batches */
	list_free_deep(aggstate->hash_batches);
	aggstate->hash_batches = NIL;

	/* close tape set */
	if (aggstate->hash_tapeset != NULL)
	{
		LogicalTapeSetClose(aggstate->hash_tapeset);
		aggstate->hash_tapeset = NULL;
	}
}


/* -----------------
 * ExecInitAgg
 *
 *	Creates the run-time information for the agg node produced by the
 *	planner and initializes its outer subtree.
 *
 * -----------------
 */
AggState *
ExecInitAgg(Agg *node, EState *estate, int eflags)
{
	AggState   *aggstate;
	AggStatePerAgg peraggs;
	AggStatePerTrans pertransstates;
	AggStatePerGroup *pergroups;
	Plan	   *outerPlan;
	ExprContext *econtext;
	TupleDesc	scanDesc;
	int			max_aggno;
	int			max_transno;
	int			numaggrefs;
	int			numaggs;
	int			numtrans;
	int			phase;
	int			phaseidx;
	ListCell   *l;
	Bitmapset  *all_grouped_cols = NULL;
	int			numGroupingSets = 1;
	int			numPhases;
	int			numHashes;
	int			i = 0;
	int			j = 0;
	bool		use_hashing = (node->aggstrategy == AGG_HASHED ||
							   node->aggstrategy == AGG_MIXED);

	/* check for unsupported flags */
	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));

	/*
	 * create state structure
	 */
	aggstate = makeNode(AggState);
	aggstate->ss.ps.plan = (Plan *) node;
	aggstate->ss.ps.state = estate;
	aggstate->ss.ps.ExecProcNode = ExecAgg;

	aggstate->aggs = NIL;
	aggstate->numaggs = 0;
	aggstate->numtrans = 0;
	aggstate->aggstrategy = node->aggstrategy;
	aggstate->aggsplit = node->aggsplit;
	aggstate->maxsets = 0;
	aggstate->projected_set = -1;
	aggstate->current_set = 0;
	aggstate->peragg = NULL;
	aggstate->pertrans = NULL;
	aggstate->curperagg = NULL;
	aggstate->curpertrans = NULL;
	aggstate->input_done = false;
	aggstate->agg_done = false;
	aggstate->pergroups = NULL;
	aggstate->grp_firstTuple = NULL;
	aggstate->sort_in = NULL;
	aggstate->sort_out = NULL;

	/*
	 * phases[0] always exists, but is dummy in sorted/plain mode
	 */
	numPhases = (use_hashing ? 1 : 2);
	numHashes = (use_hashing ? 1 : 0);

	/*
	 * Calculate the maximum number of grouping sets in any phase; this
	 * determines the size of some allocations.  Also calculate the number of
	 * phases, since all hashed/mixed nodes contribute to only a single phase.
	 */
	if (node->groupingSets)
	{
		numGroupingSets = list_length(node->groupingSets);

		foreach(l, node->chain)
		{
			Agg		   *agg = lfirst(l);

			numGroupingSets = Max(numGroupingSets,
								  list_length(agg->groupingSets));

			/*
			 * additional AGG_HASHED aggs become part of phase 0, but all
			 * others add an extra phase.
			 */
			if (agg->aggstrategy != AGG_HASHED)
				++numPhases;
			else
				++numHashes;
		}
	}

	aggstate->maxsets = numGroupingSets;
	aggstate->numphases = numPhases;

	aggstate->aggcontexts = (ExprContext **)
		palloc0(sizeof(ExprContext *) * numGroupingSets);

	/*
	 * Create expression contexts.  We need three or more, one for
	 * per-input-tuple processing, one for per-output-tuple processing, one
	 * for all the hashtables, and one for each grouping set.  The per-tuple
	 * memory context of the per-grouping-set ExprContexts (aggcontexts)
	 * replaces the standalone memory context formerly used to hold transition
	 * values.  We cheat a little by using ExecAssignExprContext() to build
	 * all of them.
	 *
	 * NOTE: the details of what is stored in aggcontexts and what is stored
	 * in the regular per-query memory context are driven by a simple
	 * decision: we want to reset the aggcontext at group boundaries (if not
	 * hashing) and in ExecReScanAgg to recover no-longer-wanted space.
	 */
	ExecAssignExprContext(estate, &aggstate->ss.ps);
	aggstate->tmpcontext = aggstate->ss.ps.ps_ExprContext;

	for (i = 0; i < numGroupingSets; ++i)
	{
		ExecAssignExprContext(estate, &aggstate->ss.ps);
		aggstate->aggcontexts[i] = aggstate->ss.ps.ps_ExprContext;
	}

	if (use_hashing)
		aggstate->hashcontext = CreateWorkExprContext(estate);

	ExecAssignExprContext(estate, &aggstate->ss.ps);

	/*
	 * Initialize child nodes.
	 *
	 * If we are doing a hashed aggregation then the child plan does not need
	 * to handle REWIND efficiently; see ExecReScanAgg.
	 */
	if (node->aggstrategy == AGG_HASHED)
		eflags &= ~EXEC_FLAG_REWIND;
	outerPlan = outerPlan(node);
	outerPlanState(aggstate) = ExecInitNode(outerPlan, estate, eflags);

	/*
	 * initialize source tuple type.
	 */
	aggstate->ss.ps.outerops =
		ExecGetResultSlotOps(outerPlanState(&aggstate->ss),
							 &aggstate->ss.ps.outeropsfixed);
	aggstate->ss.ps.outeropsset = true;

	ExecCreateScanSlotFromOuterPlan(estate, &aggstate->ss,
									aggstate->ss.ps.outerops);
	scanDesc = aggstate->ss.ss_ScanTupleSlot->tts_tupleDescriptor;

	/*
	 * If there are more than two phases (including a potential dummy phase
	 * 0), input will be resorted using tuplesort. Need a slot for that.
	 */
	if (numPhases > 2)
	{
		aggstate->sort_slot = ExecInitExtraTupleSlot(estate, scanDesc,
													 &TTSOpsMinimalTuple);

		/*
		 * The output of the tuplesort, and the output from the outer child
		 * might not use the same type of slot. In most cases the child will
		 * be a Sort, and thus return a TTSOpsMinimalTuple type slot - but the
		 * input can also be presorted due an index, in which case it could be
		 * a different type of slot.
		 *
		 * XXX: For efficiency it would be good to instead/additionally
		 * generate expressions with corresponding settings of outerops* for
		 * the individual phases - deforming is often a bottleneck for
		 * aggregations with lots of rows per group. If there's multiple
		 * sorts, we know that all but the first use TTSOpsMinimalTuple (via
		 * the nodeAgg.c internal tuplesort).
		 */
		if (aggstate->ss.ps.outeropsfixed &&
			aggstate->ss.ps.outerops != &TTSOpsMinimalTuple)
			aggstate->ss.ps.outeropsfixed = false;
	}

	/*
	 * Initialize result type, slot and projection.
	 */
	ExecInitResultTupleSlotTL(&aggstate->ss.ps, &TTSOpsVirtual);
	ExecAssignProjectionInfo(&aggstate->ss.ps, NULL);

	/*
	 * initialize child expressions
	 *
	 * We expect the parser to have checked that no aggs contain other agg
	 * calls in their arguments (and just to be sure, we verify it again while
	 * initializing the plan node).  This would make no sense under SQL
	 * semantics, and it's forbidden by the spec.  Because it is true, we
	 * don't need to worry about evaluating the aggs in any particular order.
	 *
	 * Note: execExpr.c finds Aggrefs for us, and adds them to aggstate->aggs.
	 * Aggrefs in the qual are found here; Aggrefs in the targetlist are found
	 * during ExecAssignProjectionInfo, above.
	 */
	aggstate->ss.ps.qual =
		ExecInitQual(node->plan.qual, (PlanState *) aggstate);

	/*
	 * We should now have found all Aggrefs in the targetlist and quals.
	 */
	numaggrefs = list_length(aggstate->aggs);
	max_aggno = -1;
	max_transno = -1;
	foreach(l, aggstate->aggs)
	{
		Aggref	   *aggref = (Aggref *) lfirst(l);

		max_aggno = Max(max_aggno, aggref->aggno);
		max_transno = Max(max_transno, aggref->aggtransno);
	}
	numaggs = max_aggno + 1;
	numtrans = max_transno + 1;

	/*
	 * For each phase, prepare grouping set data and fmgr lookup data for
	 * compare functions.  Accumulate all_grouped_cols in passing.
	 */
	aggstate->phases = palloc0(numPhases * sizeof(AggStatePerPhaseData));

	aggstate->num_hashes = numHashes;
	if (numHashes)
	{
		aggstate->perhash = palloc0(sizeof(AggStatePerHashData) * numHashes);
		aggstate->phases[0].numsets = 0;
		aggstate->phases[0].gset_lengths = palloc(numHashes * sizeof(int));
		aggstate->phases[0].grouped_cols = palloc(numHashes * sizeof(Bitmapset *));
	}

	phase = 0;
	for (phaseidx = 0; phaseidx <= list_length(node->chain); ++phaseidx)
	{
		Agg		   *aggnode;
		Sort	   *sortnode;

		if (phaseidx > 0)
		{
			aggnode = list_nth_node(Agg, node->chain, phaseidx - 1);
			sortnode = castNode(Sort, outerPlan(aggnode));
		}
		else
		{
			aggnode = node;
			sortnode = NULL;
		}

		Assert(phase <= 1 || sortnode);

		if (aggnode->aggstrategy == AGG_HASHED
			|| aggnode->aggstrategy == AGG_MIXED)
		{
			AggStatePerPhase phasedata = &aggstate->phases[0];
			AggStatePerHash perhash;
			Bitmapset  *cols = NULL;

			Assert(phase == 0);
			i = phasedata->numsets++;
			perhash = &aggstate->perhash[i];

			/* phase 0 always points to the "real" Agg in the hash case */
			phasedata->aggnode = node;
			phasedata->aggstrategy = node->aggstrategy;

			/* but the actual Agg node representing this hash is saved here */
			perhash->aggnode = aggnode;

			phasedata->gset_lengths[i] = perhash->numCols = aggnode->numCols;

			for (j = 0; j < aggnode->numCols; ++j)
				cols = bms_add_member(cols, aggnode->grpColIdx[j]);

			phasedata->grouped_cols[i] = cols;

			all_grouped_cols = bms_add_members(all_grouped_cols, cols);
			continue;
		}
		else
		{
			AggStatePerPhase phasedata = &aggstate->phases[++phase];
			int			num_sets;

			phasedata->numsets = num_sets = list_length(aggnode->groupingSets);

			if (num_sets)
			{
				phasedata->gset_lengths = palloc(num_sets * sizeof(int));
				phasedata->grouped_cols = palloc(num_sets * sizeof(Bitmapset *));

				i = 0;
				foreach(l, aggnode->groupingSets)
				{
					int			current_length = list_length(lfirst(l));
					Bitmapset  *cols = NULL;

					/* planner forces this to be correct */
					for (j = 0; j < current_length; ++j)
						cols = bms_add_member(cols, aggnode->grpColIdx[j]);

					phasedata->grouped_cols[i] = cols;
					phasedata->gset_lengths[i] = current_length;

					++i;
				}

				all_grouped_cols = bms_add_members(all_grouped_cols,
												   phasedata->grouped_cols[0]);
			}
			else
			{
				Assert(phaseidx == 0);

				phasedata->gset_lengths = NULL;
				phasedata->grouped_cols = NULL;
			}

			/*
			 * If we are grouping, precompute fmgr lookup data for inner loop.
			 */
			if (aggnode->aggstrategy == AGG_SORTED)
			{
				/*
				 * Build a separate function for each subset of columns that
				 * need to be compared.
				 */
				phasedata->eqfunctions =
					(ExprState **) palloc0(aggnode->numCols * sizeof(ExprState *));

				/* for each grouping set */
				for (int k = 0; k < phasedata->numsets; k++)
				{
					int			length = phasedata->gset_lengths[k];

					/* nothing to do for empty grouping set */
					if (length == 0)
						continue;

					/* if we already had one of this length, it'll do */
					if (phasedata->eqfunctions[length - 1] != NULL)
						continue;

					phasedata->eqfunctions[length - 1] =
						execTuplesMatchPrepare(scanDesc,
											   length,
											   aggnode->grpColIdx,
											   aggnode->grpOperators,
											   aggnode->grpCollations,
											   (PlanState *) aggstate);
				}

				/* and for all grouped columns, unless already computed */
				if (aggnode->numCols > 0 &&
					phasedata->eqfunctions[aggnode->numCols - 1] == NULL)
				{
					phasedata->eqfunctions[aggnode->numCols - 1] =
						execTuplesMatchPrepare(scanDesc,
											   aggnode->numCols,
											   aggnode->grpColIdx,
											   aggnode->grpOperators,
											   aggnode->grpCollations,
											   (PlanState *) aggstate);
				}
			}

			phasedata->aggnode = aggnode;
			phasedata->aggstrategy = aggnode->aggstrategy;
			phasedata->sortnode = sortnode;
		}
	}

	/*
	 * Convert all_grouped_cols to a descending-order list.
	 */
	i = -1;
	while ((i = bms_next_member(all_grouped_cols, i)) >= 0)
		aggstate->all_grouped_cols = lcons_int(i, aggstate->all_grouped_cols);

	/*
	 * Set up aggregate-result storage in the output expr context, and also
	 * allocate my private per-agg working storage
	 */
	econtext = aggstate->ss.ps.ps_ExprContext;
	econtext->ecxt_aggvalues = (Datum *) palloc0(sizeof(Datum) * numaggs);
	econtext->ecxt_aggnulls = (bool *) palloc0(sizeof(bool) * numaggs);

	peraggs = (AggStatePerAgg) palloc0(sizeof(AggStatePerAggData) * numaggs);
	pertransstates = (AggStatePerTrans) palloc0(sizeof(AggStatePerTransData) * numtrans);

	aggstate->peragg = peraggs;
	aggstate->pertrans = pertransstates;


	aggstate->all_pergroups =
		(AggStatePerGroup *) palloc0(sizeof(AggStatePerGroup)
									 * (numGroupingSets + numHashes));
	pergroups = aggstate->all_pergroups;

	if (node->aggstrategy != AGG_HASHED)
	{
		for (i = 0; i < numGroupingSets; i++)
		{
			pergroups[i] = (AggStatePerGroup) palloc0(sizeof(AggStatePerGroupData)
													  * numaggs);
		}

		aggstate->pergroups = pergroups;
		pergroups += numGroupingSets;
	}

	/*
	 * Hashing can only appear in the initial phase.
	 */
	if (use_hashing)
	{
		Plan	   *outerplan = outerPlan(node);
		uint64		totalGroups = 0;

		aggstate->hash_metacxt = AllocSetContextCreate(aggstate->ss.ps.state->es_query_cxt,
													   "HashAgg meta context",
													   ALLOCSET_DEFAULT_SIZES);
		aggstate->hash_spill_rslot = ExecInitExtraTupleSlot(estate, scanDesc,
															&TTSOpsMinimalTuple);
		aggstate->hash_spill_wslot = ExecInitExtraTupleSlot(estate, scanDesc,
															&TTSOpsVirtual);

		/* this is an array of pointers, not structures */
		aggstate->hash_pergroup = pergroups;

		aggstate->hashentrysize = hash_agg_entry_size(aggstate->numtrans,
													  outerplan->plan_width,
													  node->transitionSpace);

		/*
		 * Consider all of the grouping sets together when setting the limits
		 * and estimating the number of partitions. This can be inaccurate
		 * when there is more than one grouping set, but should still be
		 * reasonable.
		 */
		for (int k = 0; k < aggstate->num_hashes; k++)
			totalGroups += aggstate->perhash[k].aggnode->numGroups;

		hash_agg_set_limits(aggstate->hashentrysize, totalGroups, 0,
							&aggstate->hash_mem_limit,
							&aggstate->hash_ngroups_limit,
							&aggstate->hash_planned_partitions);
		find_hash_columns(aggstate);

		/* Skip massive memory allocation if we are just doing EXPLAIN */
		if (!(eflags & EXEC_FLAG_EXPLAIN_ONLY))
			build_hash_tables(aggstate);

		aggstate->table_filled = false;

		/* Initialize this to 1, meaning nothing spilled, yet */
		aggstate->hash_batches_used = 1;
	}

	/*
	 * Initialize current phase-dependent values to initial phase. The initial
	 * phase is 1 (first sort pass) for all strategies that use sorting (if
	 * hashing is being done too, then phase 0 is processed last); but if only
	 * hashing is being done, then phase 0 is all there is.
	 */
	if (node->aggstrategy == AGG_HASHED)
	{
		aggstate->current_phase = 0;
		initialize_phase(aggstate, 0);
		select_current_set(aggstate, 0, true);
	}
	else
	{
		aggstate->current_phase = 1;
		initialize_phase(aggstate, 1);
		select_current_set(aggstate, 0, false);
	}

	/*
	 * Perform lookups of aggregate function info, and initialize the
	 * unchanging fields of the per-agg and per-trans data.
	 */
	foreach(l, aggstate->aggs)
	{
		Aggref	   *aggref = lfirst(l);
		AggStatePerAgg peragg;
		AggStatePerTrans pertrans;
		Oid			aggTransFnInputTypes[FUNC_MAX_ARGS];
		int			numAggTransFnArgs;
		int			numDirectArgs;
		HeapTuple	aggTuple;
		Form_pg_aggregate aggform;
		AclResult	aclresult;
		Oid			finalfn_oid;
		Oid			serialfn_oid,
					deserialfn_oid;
		Oid			aggOwner;
		Expr	   *finalfnexpr;
		Oid			aggtranstype;

		/* Planner should have assigned aggregate to correct level */
		Assert(aggref->agglevelsup == 0);
		/* ... and the split mode should match */
		Assert(aggref->aggsplit == aggstate->aggsplit);

		peragg = &peraggs[aggref->aggno];

		/* Check if we initialized the state for this aggregate already. */
		if (peragg->aggref != NULL)
			continue;

		peragg->aggref = aggref;
		peragg->transno = aggref->aggtransno;

		/* Fetch the pg_aggregate row */
		aggTuple = SearchSysCache1(AGGFNOID,
								   ObjectIdGetDatum(aggref->aggfnoid));
		if (!HeapTupleIsValid(aggTuple))
			elog(ERROR, "cache lookup failed for aggregate %u",
				 aggref->aggfnoid);
		aggform = (Form_pg_aggregate) GETSTRUCT(aggTuple);

		/* Check permission to call aggregate function */
		aclresult = object_aclcheck(ProcedureRelationId, aggref->aggfnoid, GetUserId(),
									 ACL_EXECUTE);
		if (aclresult != ACLCHECK_OK)
			aclcheck_error(aclresult, OBJECT_AGGREGATE,
						   get_func_name(aggref->aggfnoid));
		InvokeFunctionExecuteHook(aggref->aggfnoid);

		/* planner recorded transition state type in the Aggref itself */
		aggtranstype = aggref->aggtranstype;
		Assert(OidIsValid(aggtranstype));

		/* Final function only required if we're finalizing the aggregates */
		if (DO_AGGSPLIT_SKIPFINAL(aggstate->aggsplit))
			peragg->finalfn_oid = finalfn_oid = InvalidOid;
		else
			peragg->finalfn_oid = finalfn_oid = aggform->aggfinalfn;

		serialfn_oid = InvalidOid;
		deserialfn_oid = InvalidOid;

		/*
		 * Check if serialization/deserialization is required.  We only do it
		 * for aggregates that have transtype INTERNAL.
		 */
		if (aggtranstype == INTERNALOID)
		{
			/*
			 * The planner should only have generated a serialize agg node if
			 * every aggregate with an INTERNAL state has a serialization
			 * function.  Verify that.
			 */
			if (DO_AGGSPLIT_SERIALIZE(aggstate->aggsplit))
			{
				/* serialization only valid when not running finalfn */
				Assert(DO_AGGSPLIT_SKIPFINAL(aggstate->aggsplit));

				if (!OidIsValid(aggform->aggserialfn))
					elog(ERROR, "serialfunc not provided for serialization aggregation");
				serialfn_oid = aggform->aggserialfn;
			}

			/* Likewise for deserialization functions */
			if (DO_AGGSPLIT_DESERIALIZE(aggstate->aggsplit))
			{
				/* deserialization only valid when combining states */
				Assert(DO_AGGSPLIT_COMBINE(aggstate->aggsplit));

				if (!OidIsValid(aggform->aggdeserialfn))
					elog(ERROR, "deserialfunc not provided for deserialization aggregation");
				deserialfn_oid = aggform->aggdeserialfn;
			}
		}

		/* Check that aggregate owner has permission to call component fns */
		{
			HeapTuple	procTuple;

			procTuple = SearchSysCache1(PROCOID,
										ObjectIdGetDatum(aggref->aggfnoid));
			if (!HeapTupleIsValid(procTuple))
				elog(ERROR, "cache lookup failed for function %u",
					 aggref->aggfnoid);
			aggOwner = ((Form_pg_proc) GETSTRUCT(procTuple))->proowner;
			ReleaseSysCache(procTuple);

			if (OidIsValid(finalfn_oid))
			{
				aclresult = object_aclcheck(ProcedureRelationId, finalfn_oid, aggOwner,
											 ACL_EXECUTE);
				if (aclresult != ACLCHECK_OK)
					aclcheck_error(aclresult, OBJECT_FUNCTION,
								   get_func_name(finalfn_oid));
				InvokeFunctionExecuteHook(finalfn_oid);
			}
			if (OidIsValid(serialfn_oid))
			{
				aclresult = object_aclcheck(ProcedureRelationId, serialfn_oid, aggOwner,
											 ACL_EXECUTE);
				if (aclresult != ACLCHECK_OK)
					aclcheck_error(aclresult, OBJECT_FUNCTION,
								   get_func_name(serialfn_oid));
				InvokeFunctionExecuteHook(serialfn_oid);
			}
			if (OidIsValid(deserialfn_oid))
			{
				aclresult = object_aclcheck(ProcedureRelationId, deserialfn_oid, aggOwner,
											 ACL_EXECUTE);
				if (aclresult != ACLCHECK_OK)
					aclcheck_error(aclresult, OBJECT_FUNCTION,
								   get_func_name(deserialfn_oid));
				InvokeFunctionExecuteHook(deserialfn_oid);
			}
		}

		/*
		 * Get actual datatypes of the (nominal) aggregate inputs.  These
		 * could be different from the agg's declared input types, when the
		 * agg accepts ANY or a polymorphic type.
		 */
		numAggTransFnArgs = get_aggregate_argtypes(aggref,
												   aggTransFnInputTypes);

		/* Count the "direct" arguments, if any */
		numDirectArgs = list_length(aggref->aggdirectargs);

		/* Detect how many arguments to pass to the finalfn */
		if (aggform->aggfinalextra)
			peragg->numFinalArgs = numAggTransFnArgs + 1;
		else
			peragg->numFinalArgs = numDirectArgs + 1;

		/* Initialize any direct-argument expressions */
		peragg->aggdirectargs = ExecInitExprList(aggref->aggdirectargs,
												 (PlanState *) aggstate);

		/*
		 * build expression trees using actual argument & result types for the
		 * finalfn, if it exists and is required.
		 */
		if (OidIsValid(finalfn_oid))
		{
			build_aggregate_finalfn_expr(aggTransFnInputTypes,
										 peragg->numFinalArgs,
										 aggtranstype,
										 aggref->aggtype,
										 aggref->inputcollid,
										 finalfn_oid,
										 &finalfnexpr);
			fmgr_info(finalfn_oid, &peragg->finalfn);
			fmgr_info_set_expr((Node *) finalfnexpr, &peragg->finalfn);
		}

		/* get info about the output value's datatype */
		get_typlenbyval(aggref->aggtype,
						&peragg->resulttypeLen,
						&peragg->resulttypeByVal);

		/*
		 * Build working state for invoking the transition function, if we
		 * haven't done it already.
		 */
		pertrans = &pertransstates[aggref->aggtransno];
		if (pertrans->aggref == NULL)
		{
			Datum		textInitVal;
			Datum		initValue;
			bool		initValueIsNull;
			Oid			transfn_oid;

			/*
			 * If this aggregation is performing state combines, then instead
			 * of using the transition function, we'll use the combine
			 * function.
			 */
			if (DO_AGGSPLIT_COMBINE(aggstate->aggsplit))
			{
				transfn_oid = aggform->aggcombinefn;

				/* If not set then the planner messed up */
				if (!OidIsValid(transfn_oid))
					elog(ERROR, "combinefn not set for aggregate function");
			}
			else
				transfn_oid = aggform->aggtransfn;

			aclresult = object_aclcheck(ProcedureRelationId, transfn_oid, aggOwner, ACL_EXECUTE);
			if (aclresult != ACLCHECK_OK)
				aclcheck_error(aclresult, OBJECT_FUNCTION,
							   get_func_name(transfn_oid));
			InvokeFunctionExecuteHook(transfn_oid);

			/*
			 * initval is potentially null, so don't try to access it as a
			 * struct field. Must do it the hard way with SysCacheGetAttr.
			 */
			textInitVal = SysCacheGetAttr(AGGFNOID, aggTuple,
										  Anum_pg_aggregate_agginitval,
										  &initValueIsNull);
			if (initValueIsNull)
				initValue = (Datum) 0;
			else
				initValue = GetAggInitVal(textInitVal, aggtranstype);

			if (DO_AGGSPLIT_COMBINE(aggstate->aggsplit))
			{
				Oid			combineFnInputTypes[] = {aggtranstype,
				aggtranstype};

				/*
				 * When combining there's only one input, the to-be-combined
				 * transition value.  The transition value is not counted
				 * here.
				 */
				pertrans->numTransInputs = 1;

				/* aggcombinefn always has two arguments of aggtranstype */
				build_pertrans_for_aggref(pertrans, aggstate, estate,
										  aggref, transfn_oid, aggtranstype,
										  serialfn_oid, deserialfn_oid,
										  initValue, initValueIsNull,
										  combineFnInputTypes, 2);

				/*
				 * Ensure that a combine function to combine INTERNAL states
				 * is not strict. This should have been checked during CREATE
				 * AGGREGATE, but the strict property could have been changed
				 * since then.
				 */
				if (pertrans->transfn.fn_strict && aggtranstype == INTERNALOID)
					ereport(ERROR,
							(errcode(ERRCODE_INVALID_FUNCTION_DEFINITION),
							 errmsg("combine function with transition type %s must not be declared STRICT",
									format_type_be(aggtranstype))));
			}
			else
			{
				/* Detect how many arguments to pass to the transfn */
				if (AGGKIND_IS_ORDERED_SET(aggref->aggkind))
					pertrans->numTransInputs = list_length(aggref->args);
				else
					pertrans->numTransInputs = numAggTransFnArgs;

				build_pertrans_for_aggref(pertrans, aggstate, estate,
										  aggref, transfn_oid, aggtranstype,
										  serialfn_oid, deserialfn_oid,
										  initValue, initValueIsNull,
										  aggTransFnInputTypes,
										  numAggTransFnArgs);

				/*
				 * If the transfn is strict and the initval is NULL, make sure
				 * input type and transtype are the same (or at least
				 * binary-compatible), so that it's OK to use the first
				 * aggregated input value as the initial transValue.  This
				 * should have been checked at agg definition time, but we
				 * must check again in case the transfn's strictness property
				 * has been changed.
				 */
				if (pertrans->transfn.fn_strict && pertrans->initValueIsNull)
				{
					if (numAggTransFnArgs <= numDirectArgs ||
						!IsBinaryCoercible(aggTransFnInputTypes[numDirectArgs],
										   aggtranstype))
						ereport(ERROR,
								(errcode(ERRCODE_INVALID_FUNCTION_DEFINITION),
								 errmsg("aggregate %u needs to have compatible input type and transition type",
										aggref->aggfnoid)));
				}
			}
		}
		else
			pertrans->aggshared = true;
		ReleaseSysCache(aggTuple);
	}

	/*
	 * Update aggstate->numaggs to be the number of unique aggregates found.
	 * Also set numstates to the number of unique transition states found.
	 */
	aggstate->numaggs = numaggs;
	aggstate->numtrans = numtrans;

	/*
	 * Last, check whether any more aggregates got added onto the node while
	 * we processed the expressions for the aggregate arguments (including not
	 * only the regular arguments and FILTER expressions handled immediately
	 * above, but any direct arguments we might've handled earlier).  If so,
	 * we have nested aggregate functions, which is semantically nonsensical,
	 * so complain.  (This should have been caught by the parser, so we don't
	 * need to work hard on a helpful error message; but we defend against it
	 * here anyway, just to be sure.)
	 */
	if (numaggrefs != list_length(aggstate->aggs))
		ereport(ERROR,
				(errcode(ERRCODE_GROUPING_ERROR),
				 errmsg("aggregate function calls cannot be nested")));

	/*
	 * Build expressions doing all the transition work at once. We build a
	 * different one for each phase, as the number of transition function
	 * invocation can differ between phases. Note this'll work both for
	 * transition and combination functions (although there'll only be one
	 * phase in the latter case).
	 */
	for (phaseidx = 0; phaseidx < aggstate->numphases; phaseidx++)
	{
		AggStatePerPhase phase = &aggstate->phases[phaseidx];
		bool		dohash = false;
		bool		dosort = false;

		/* phase 0 doesn't necessarily exist */
		if (!phase->aggnode)
			continue;

		if (aggstate->aggstrategy == AGG_MIXED && phaseidx == 1)
		{
			/*
			 * Phase one, and only phase one, in a mixed agg performs both
			 * sorting and aggregation.
			 */
			dohash = true;
			dosort = true;
		}
		else if (aggstate->aggstrategy == AGG_MIXED && phaseidx == 0)
		{
			/*
			 * No need to compute a transition function for an AGG_MIXED phase
			 * 0 - the contents of the hashtables will have been computed
			 * during phase 1.
			 */
			continue;
		}
		else if (phase->aggstrategy == AGG_PLAIN ||
				 phase->aggstrategy == AGG_SORTED)
		{
			dohash = false;
			dosort = true;
		}
		else if (phase->aggstrategy == AGG_HASHED)
		{
			dohash = true;
			dosort = false;
		}
		else
			Assert(false);

		phase->evaltrans = ExecBuildAggTrans(aggstate, phase, dosort, dohash,
											 false);

		/* cache compiled expression for outer slot without NULL check */
		phase->evaltrans_cache[0][0] = phase->evaltrans;
	}

	return aggstate;
}

/*
 * Build the state needed to calculate a state value for an aggregate.
 *
 * This initializes all the fields in 'pertrans'. 'aggref' is the aggregate
 * to initialize the state for. 'transfn_oid', 'aggtranstype', and the rest
 * of the arguments could be calculated from 'aggref', but the caller has
 * calculated them already, so might as well pass them.
 *
 * 'transfn_oid' may be either the Oid of the aggtransfn or the aggcombinefn.
 */
static void
build_pertrans_for_aggref(AggStatePerTrans pertrans,
						  AggState *aggstate, EState *estate,
						  Aggref *aggref,
						  Oid transfn_oid, Oid aggtranstype,
						  Oid aggserialfn, Oid aggdeserialfn,
						  Datum initValue, bool initValueIsNull,
						  Oid *inputTypes, int numArguments)
{
	int			numGroupingSets = Max(aggstate->maxsets, 1);
	Expr	   *transfnexpr;
	int			numTransArgs;
	Expr	   *serialfnexpr = NULL;
	Expr	   *deserialfnexpr = NULL;
	ListCell   *lc;
	int			numInputs;
	int			numDirectArgs;
	List	   *sortlist;
	int			numSortCols;
	int			numDistinctCols;
	int			i;

	/* Begin filling in the pertrans data */
	pertrans->aggref = aggref;
	pertrans->aggshared = false;
	pertrans->aggCollation = aggref->inputcollid;
	pertrans->transfn_oid = transfn_oid;
	pertrans->serialfn_oid = aggserialfn;
	pertrans->deserialfn_oid = aggdeserialfn;
	pertrans->initValue = initValue;
	pertrans->initValueIsNull = initValueIsNull;

	/* Count the "direct" arguments, if any */
	numDirectArgs = list_length(aggref->aggdirectargs);

	/* Count the number of aggregated input columns */
	pertrans->numInputs = numInputs = list_length(aggref->args);

	pertrans->aggtranstype = aggtranstype;

	/* account for the current transition state */
	numTransArgs = pertrans->numTransInputs + 1;

	/*
	 * Set up infrastructure for calling the transfn.  Note that invtransfn is
	 * not needed here.
	 */
	build_aggregate_transfn_expr(inputTypes,
								 numArguments,
								 numDirectArgs,
								 aggref->aggvariadic,
								 aggtranstype,
								 aggref->inputcollid,
								 transfn_oid,
								 InvalidOid,
								 &transfnexpr,
								 NULL);

	fmgr_info(transfn_oid, &pertrans->transfn);
	fmgr_info_set_expr((Node *) transfnexpr, &pertrans->transfn);

	pertrans->transfn_fcinfo =
		(FunctionCallInfo) palloc(SizeForFunctionCallInfo(numTransArgs));
	InitFunctionCallInfoData(*pertrans->transfn_fcinfo,
							 &pertrans->transfn,
							 numTransArgs,
							 pertrans->aggCollation,
							 (void *) aggstate, NULL);

	/* get info about the state value's datatype */
	get_typlenbyval(aggtranstype,
					&pertrans->transtypeLen,
					&pertrans->transtypeByVal);

	if (OidIsValid(aggserialfn))
	{
		build_aggregate_serialfn_expr(aggserialfn,
									  &serialfnexpr);
		fmgr_info(aggserialfn, &pertrans->serialfn);
		fmgr_info_set_expr((Node *) serialfnexpr, &pertrans->serialfn);

		pertrans->serialfn_fcinfo =
			(FunctionCallInfo) palloc(SizeForFunctionCallInfo(1));
		InitFunctionCallInfoData(*pertrans->serialfn_fcinfo,
								 &pertrans->serialfn,
								 1,
								 InvalidOid,
								 (void *) aggstate, NULL);
	}

	if (OidIsValid(aggdeserialfn))
	{
		build_aggregate_deserialfn_expr(aggdeserialfn,
										&deserialfnexpr);
		fmgr_info(aggdeserialfn, &pertrans->deserialfn);
		fmgr_info_set_expr((Node *) deserialfnexpr, &pertrans->deserialfn);

		pertrans->deserialfn_fcinfo =
			(FunctionCallInfo) palloc(SizeForFunctionCallInfo(2));
		InitFunctionCallInfoData(*pertrans->deserialfn_fcinfo,
								 &pertrans->deserialfn,
								 2,
								 InvalidOid,
								 (void *) aggstate, NULL);
	}

	/*
	 * If we're doing either DISTINCT or ORDER BY for a plain agg, then we
	 * have a list of SortGroupClause nodes; fish out the data in them and
	 * stick them into arrays.  We ignore ORDER BY for an ordered-set agg,
	 * however; the agg's transfn and finalfn are responsible for that.
	 *
	 * When the planner has set the aggpresorted flag, the input to the
	 * aggregate is already correctly sorted.  For ORDER BY aggregates we can
	 * simply treat these as normal aggregates.  For presorted DISTINCT
	 * aggregates an extra step must be added to remove duplicate consecutive
	 * inputs.
	 *
	 * Note that by construction, if there is a DISTINCT clause then the ORDER
	 * BY clause is a prefix of it (see transformDistinctClause).
	 */
	if (AGGKIND_IS_ORDERED_SET(aggref->aggkind))
	{
		sortlist = NIL;
		numSortCols = numDistinctCols = 0;
		pertrans->aggsortrequired = false;
	}
	else if (aggref->aggpresorted && aggref->aggdistinct == NIL)
	{
		sortlist = NIL;
		numSortCols = numDistinctCols = 0;
		pertrans->aggsortrequired = false;
	}
	else if (aggref->aggdistinct)
	{
		sortlist = aggref->aggdistinct;
		numSortCols = numDistinctCols = list_length(sortlist);
		Assert(numSortCols >= list_length(aggref->aggorder));
		pertrans->aggsortrequired = !aggref->aggpresorted;
	}
	else
	{
		sortlist = aggref->aggorder;
		numSortCols = list_length(sortlist);
		numDistinctCols = 0;
		pertrans->aggsortrequired = (numSortCols > 0);
	}

	pertrans->numSortCols = numSortCols;
	pertrans->numDistinctCols = numDistinctCols;

	/*
	 * If we have either sorting or filtering to do, create a tupledesc and
	 * slot corresponding to the aggregated inputs (including sort
	 * expressions) of the agg.
	 */
	if (numSortCols > 0 || aggref->aggfilter)
	{
		pertrans->sortdesc = ExecTypeFromTL(aggref->args);
		pertrans->sortslot =
			ExecInitExtraTupleSlot(estate, pertrans->sortdesc,
								   &TTSOpsMinimalTuple);
	}

	if (numSortCols > 0)
	{
		/*
		 * We don't implement DISTINCT or ORDER BY aggs in the HASHED case
		 * (yet)
		 */
		Assert(aggstate->aggstrategy != AGG_HASHED && aggstate->aggstrategy != AGG_MIXED);

		/* ORDER BY aggregates are not supported with partial aggregation */
		Assert(!DO_AGGSPLIT_COMBINE(aggstate->aggsplit));

		/* If we have only one input, we need its len/byval info. */
		if (numInputs == 1)
		{
			get_typlenbyval(inputTypes[numDirectArgs],
							&pertrans->inputtypeLen,
							&pertrans->inputtypeByVal);
		}
		else if (numDistinctCols > 0)
		{
			/* we will need an extra slot to store prior values */
			pertrans->uniqslot =
				ExecInitExtraTupleSlot(estate, pertrans->sortdesc,
									   &TTSOpsMinimalTuple);
		}

		/* Extract the sort information for use later */
		pertrans->sortColIdx =
			(AttrNumber *) palloc(numSortCols * sizeof(AttrNumber));
		pertrans->sortOperators =
			(Oid *) palloc(numSortCols * sizeof(Oid));
		pertrans->sortCollations =
			(Oid *) palloc(numSortCols * sizeof(Oid));
		pertrans->sortNullsFirst =
			(bool *) palloc(numSortCols * sizeof(bool));

		i = 0;
		foreach(lc, sortlist)
		{
			SortGroupClause *sortcl = (SortGroupClause *) lfirst(lc);
			TargetEntry *tle = get_sortgroupclause_tle(sortcl, aggref->args);

			/* the parser should have made sure of this */
			Assert(OidIsValid(sortcl->sortop));

			pertrans->sortColIdx[i] = tle->resno;
			pertrans->sortOperators[i] = sortcl->sortop;
			pertrans->sortCollations[i] = exprCollation((Node *) tle->expr);
			pertrans->sortNullsFirst[i] = sortcl->nulls_first;
			i++;
		}
		Assert(i == numSortCols);
	}

	if (aggref->aggdistinct)
	{
		Oid		   *ops;

		Assert(numArguments > 0);
		Assert(list_length(aggref->aggdistinct) == numDistinctCols);

		ops = palloc(numDistinctCols * sizeof(Oid));

		i = 0;
		foreach(lc, aggref->aggdistinct)
			ops[i++] = ((SortGroupClause *) lfirst(lc))->eqop;

		/* lookup / build the necessary comparators */
		if (numDistinctCols == 1)
			fmgr_info(get_opcode(ops[0]), &pertrans->equalfnOne);
		else
			pertrans->equalfnMulti =
				execTuplesMatchPrepare(pertrans->sortdesc,
									   numDistinctCols,
									   pertrans->sortColIdx,
									   ops,
									   pertrans->sortCollations,
									   &aggstate->ss.ps);
		pfree(ops);
	}

	pertrans->sortstates = (Tuplesortstate **)
		palloc0(sizeof(Tuplesortstate *) * numGroupingSets);
}


static Datum
GetAggInitVal(Datum textInitVal, Oid transtype)
{
	Oid			typinput,
				typioparam;
	char	   *strInitVal;
	Datum		initVal;

	getTypeInputInfo(transtype, &typinput, &typioparam);
	strInitVal = TextDatumGetCString(textInitVal);
	initVal = OidInputFunctionCall(typinput, strInitVal,
								   typioparam, -1);
	pfree(strInitVal);
	return initVal;
}

void
ExecEndAgg(AggState *node)
{
	PlanState  *outerPlan;
	int			transno;
	int			numGroupingSets = Max(node->maxsets, 1);
	int			setno;

	/*
	 * When ending a parallel worker, copy the statistics gathered by the
	 * worker back into shared memory so that it can be picked up by the main
	 * process to report in EXPLAIN ANALYZE.
	 */
	if (node->shared_info && IsParallelWorker())
	{
		AggregateInstrumentation *si;

		Assert(ParallelWorkerNumber <= node->shared_info->num_workers);
		si = &node->shared_info->sinstrument[ParallelWorkerNumber];
		si->hash_batches_used = node->hash_batches_used;
		si->hash_disk_used = node->hash_disk_used;
		si->hash_mem_peak = node->hash_mem_peak;
	}

	/* Make sure we have closed any open tuplesorts */

	if (node->sort_in)
		tuplesort_end(node->sort_in);
	if (node->sort_out)
		tuplesort_end(node->sort_out);

	hashagg_reset_spill_state(node);

	if (node->hash_metacxt != NULL)
	{
		MemoryContextDelete(node->hash_metacxt);
		node->hash_metacxt = NULL;
	}

	for (transno = 0; transno < node->numtrans; transno++)
	{
		AggStatePerTrans pertrans = &node->pertrans[transno];

		for (setno = 0; setno < numGroupingSets; setno++)
		{
			if (pertrans->sortstates[setno])
				tuplesort_end(pertrans->sortstates[setno]);
		}
	}

	/* And ensure any agg shutdown callbacks have been called */
	for (setno = 0; setno < numGroupingSets; setno++)
		ReScanExprContext(node->aggcontexts[setno]);
	if (node->hashcontext)
		ReScanExprContext(node->hashcontext);

	/*
	 * We don't actually free any ExprContexts here (see comment in
	 * ExecFreeExprContext), just unlinking the output one from the plan node
	 * suffices.
	 */
	ExecFreeExprContext(&node->ss.ps);

	/* clean up tuple table */
	ExecClearTuple(node->ss.ss_ScanTupleSlot);

	outerPlan = outerPlanState(node);
	ExecEndNode(outerPlan);
}

void
ExecReScanAgg(AggState *node)
{
	ExprContext *econtext = node->ss.ps.ps_ExprContext;
	PlanState  *outerPlan = outerPlanState(node);
	Agg		   *aggnode = (Agg *) node->ss.ps.plan;
	int			transno;
	int			numGroupingSets = Max(node->maxsets, 1);
	int			setno;

	node->agg_done = false;

	if (node->aggstrategy == AGG_HASHED)
	{
		/*
		 * In the hashed case, if we haven't yet built the hash table then we
		 * can just return; nothing done yet, so nothing to undo. If subnode's
		 * chgParam is not NULL then it will be re-scanned by ExecProcNode,
		 * else no reason to re-scan it at all.
		 */
		if (!node->table_filled)
			return;

		/*
		 * If we do have the hash table, and it never spilled, and the subplan
		 * does not have any parameter changes, and none of our own parameter
		 * changes affect input expressions of the aggregated functions, then
		 * we can just rescan the existing hash table; no need to build it
		 * again.
		 */
		if (outerPlan->chgParam == NULL && !node->hash_ever_spilled &&
			!bms_overlap(node->ss.ps.chgParam, aggnode->aggParams))
		{
			ResetTupleHashIterator(node->perhash[0].hashtable,
								   &node->perhash[0].hashiter);
			select_current_set(node, 0, true);
			return;
		}
	}

	/* Make sure we have closed any open tuplesorts */
	for (transno = 0; transno < node->numtrans; transno++)
	{
		for (setno = 0; setno < numGroupingSets; setno++)
		{
			AggStatePerTrans pertrans = &node->pertrans[transno];

			if (pertrans->sortstates[setno])
			{
				tuplesort_end(pertrans->sortstates[setno]);
				pertrans->sortstates[setno] = NULL;
			}
		}
	}

	/*
	 * We don't need to ReScanExprContext the output tuple context here;
	 * ExecReScan already did it. But we do need to reset our per-grouping-set
	 * contexts, which may have transvalues stored in them. (We use rescan
	 * rather than just reset because transfns may have registered callbacks
	 * that need to be run now.) For the AGG_HASHED case, see below.
	 */

	for (setno = 0; setno < numGroupingSets; setno++)
	{
		ReScanExprContext(node->aggcontexts[setno]);
	}

	/* Release first tuple of group, if we have made a copy */
	if (node->grp_firstTuple != NULL)
	{
		heap_freetuple(node->grp_firstTuple);
		node->grp_firstTuple = NULL;
	}
	ExecClearTuple(node->ss.ss_ScanTupleSlot);

	/* Forget current agg values */
	MemSet(econtext->ecxt_aggvalues, 0, sizeof(Datum) * node->numaggs);
	MemSet(econtext->ecxt_aggnulls, 0, sizeof(bool) * node->numaggs);

	/*
	 * With AGG_HASHED/MIXED, the hash table is allocated in a sub-context of
	 * the hashcontext. This used to be an issue, but now, resetting a context
	 * automatically deletes sub-contexts too.
	 */
	if (node->aggstrategy == AGG_HASHED || node->aggstrategy == AGG_MIXED)
	{
		hashagg_reset_spill_state(node);

		node->hash_ever_spilled = false;
		node->hash_spill_mode = false;
		node->hash_ngroups_current = 0;

		ReScanExprContext(node->hashcontext);
		/* Rebuild an empty hash table */
		build_hash_tables(node);
		node->table_filled = false;
		/* iterator will be reset when the table is filled */

		hashagg_recompile_expressions(node, false, false);
	}

	if (node->aggstrategy != AGG_HASHED)
	{
		/*
		 * Reset the per-group state (in particular, mark transvalues null)
		 */
		for (setno = 0; setno < numGroupingSets; setno++)
		{
			MemSet(node->pergroups[setno], 0,
				   sizeof(AggStatePerGroupData) * node->numaggs);
		}

		/* reset to phase 1 */
		initialize_phase(node, 1);

		node->input_done = false;
		node->projected_set = -1;
	}

	if (outerPlan->chgParam == NULL)
		ExecReScan(outerPlan);
}


/***********************************************************************
 * API exposed to aggregate functions
 ***********************************************************************/


/*
 * AggCheckCallContext - test if a SQL function is being called as an aggregate
 *
 * The transition and/or final functions of an aggregate may want to verify
 * that they are being called as aggregates, rather than as plain SQL
 * functions.  They should use this function to do so.  The return value
 * is nonzero if being called as an aggregate, or zero if not.  (Specific
 * nonzero values are AGG_CONTEXT_AGGREGATE or AGG_CONTEXT_WINDOW, but more
 * values could conceivably appear in future.)
 *
 * If aggcontext isn't NULL, the function also stores at *aggcontext the
 * identity of the memory context that aggregate transition values are being
 * stored in.  Note that the same aggregate call site (flinfo) may be called
 * interleaved on different transition values in different contexts, so it's
 * not kosher to cache aggcontext under fn_extra.  It is, however, kosher to
 * cache it in the transvalue itself (for internal-type transvalues).
 */
int
AggCheckCallContext(FunctionCallInfo fcinfo, MemoryContext *aggcontext)
{
	if (fcinfo->context && IsA(fcinfo->context, AggState))
	{
		if (aggcontext)
		{
			AggState   *aggstate = ((AggState *) fcinfo->context);
			ExprContext *cxt = aggstate->curaggcontext;

			*aggcontext = cxt->ecxt_per_tuple_memory;
		}
		return AGG_CONTEXT_AGGREGATE;
	}
	if (fcinfo->context && IsA(fcinfo->context, WindowAggState))
	{
		if (aggcontext)
			*aggcontext = ((WindowAggState *) fcinfo->context)->curaggcontext;
		return AGG_CONTEXT_WINDOW;
	}

	/* this is just to prevent "uninitialized variable" warnings */
	if (aggcontext)
		*aggcontext = NULL;
	return 0;
}

/*
 * AggGetAggref - allow an aggregate support function to get its Aggref
 *
 * If the function is being called as an aggregate support function,
 * return the Aggref node for the aggregate call.  Otherwise, return NULL.
 *
 * Aggregates sharing the same inputs and transition functions can get
 * merged into a single transition calculation.  If the transition function
 * calls AggGetAggref, it will get some one of the Aggrefs for which it is
 * executing.  It must therefore not pay attention to the Aggref fields that
 * relate to the final function, as those are indeterminate.  But if a final
 * function calls AggGetAggref, it will get a precise result.
 *
 * Note that if an aggregate is being used as a window function, this will
 * return NULL.  We could provide a similar function to return the relevant
 * WindowFunc node in such cases, but it's not needed yet.
 */
Aggref *
AggGetAggref(FunctionCallInfo fcinfo)
{
	if (fcinfo->context && IsA(fcinfo->context, AggState))
	{
		AggState   *aggstate = (AggState *) fcinfo->context;
		AggStatePerAgg curperagg;
		AggStatePerTrans curpertrans;

		/* check curperagg (valid when in a final function) */
		curperagg = aggstate->curperagg;

		if (curperagg)
			return curperagg->aggref;

		/* check curpertrans (valid when in a transition function) */
		curpertrans = aggstate->curpertrans;

		if (curpertrans)
			return curpertrans->aggref;
	}
	return NULL;
}

/*
 * AggGetTempMemoryContext - fetch short-term memory context for aggregates
 *
 * This is useful in agg final functions; the context returned is one that
 * the final function can safely reset as desired.  This isn't useful for
 * transition functions, since the context returned MAY (we don't promise)
 * be the same as the context those are called in.
 *
 * As above, this is currently not useful for aggs called as window functions.
 */
MemoryContext
AggGetTempMemoryContext(FunctionCallInfo fcinfo)
{
	if (fcinfo->context && IsA(fcinfo->context, AggState))
	{
		AggState   *aggstate = (AggState *) fcinfo->context;

		return aggstate->tmpcontext->ecxt_per_tuple_memory;
	}
	return NULL;
}

/*
 * AggStateIsShared - find out whether transition state is shared
 *
 * If the function is being called as an aggregate support function,
 * return true if the aggregate's transition state is shared across
 * multiple aggregates, false if it is not.
 *
 * Returns true if not called as an aggregate support function.
 * This is intended as a conservative answer, ie "no you'd better not
 * scribble on your input".  In particular, will return true if the
 * aggregate is being used as a window function, which is a scenario
 * in which changing the transition state is a bad idea.  We might
 * want to refine the behavior for the window case in future.
 */
bool
AggStateIsShared(FunctionCallInfo fcinfo)
{
	if (fcinfo->context && IsA(fcinfo->context, AggState))
	{
		AggState   *aggstate = (AggState *) fcinfo->context;
		AggStatePerAgg curperagg;
		AggStatePerTrans curpertrans;

		/* check curperagg (valid when in a final function) */
		curperagg = aggstate->curperagg;

		if (curperagg)
			return aggstate->pertrans[curperagg->transno].aggshared;

		/* check curpertrans (valid when in a transition function) */
		curpertrans = aggstate->curpertrans;

		if (curpertrans)
			return curpertrans->aggshared;
	}
	return true;
}

/*
 * AggRegisterCallback - register a cleanup callback for an aggregate
 *
 * This is useful for aggs to register shutdown callbacks, which will ensure
 * that non-memory resources are freed.  The callback will occur just before
 * the associated aggcontext (as returned by AggCheckCallContext) is reset,
 * either between groups or as a result of rescanning the query.  The callback
 * will NOT be called on error paths.  The typical use-case is for freeing of
 * tuplestores or tuplesorts maintained in aggcontext, or pins held by slots
 * created by the agg functions.  (The callback will not be called until after
 * the result of the finalfn is no longer needed, so it's safe for the finalfn
 * to return data that will be freed by the callback.)
 *
 * As above, this is currently not useful for aggs called as window functions.
 */
void
AggRegisterCallback(FunctionCallInfo fcinfo,
					ExprContextCallbackFunction func,
					Datum arg)
{
	if (fcinfo->context && IsA(fcinfo->context, AggState))
	{
		AggState   *aggstate = (AggState *) fcinfo->context;
		ExprContext *cxt = aggstate->curaggcontext;

		RegisterExprContextCallback(cxt, func, arg);

		return;
	}
	elog(ERROR, "aggregate function cannot register a callback in this context");
}


/* ----------------------------------------------------------------
 *						Parallel Query Support
 * ----------------------------------------------------------------
 */

 /* ----------------------------------------------------------------
  *		ExecAggEstimate
  *
  *		Estimate space required to propagate aggregate statistics.
  * ----------------------------------------------------------------
  */
void
ExecAggEstimate(AggState *node, ParallelContext *pcxt)
{
	Size		size;

	/* don't need this if not instrumenting or no workers */
	if (!node->ss.ps.instrument || pcxt->nworkers == 0)
		return;

	size = mul_size(pcxt->nworkers, sizeof(AggregateInstrumentation));
	size = add_size(size, offsetof(SharedAggInfo, sinstrument));
	shm_toc_estimate_chunk(&pcxt->estimator, size);
	shm_toc_estimate_keys(&pcxt->estimator, 1);
}

/* ----------------------------------------------------------------
 *		ExecAggInitializeDSM
 *
 *		Initialize DSM space for aggregate statistics.
 * ----------------------------------------------------------------
 */
void
ExecAggInitializeDSM(AggState *node, ParallelContext *pcxt)
{
	Size		size;

	/* don't need this if not instrumenting or no workers */
	if (!node->ss.ps.instrument || pcxt->nworkers == 0)
		return;

	size = offsetof(SharedAggInfo, sinstrument)
		+ pcxt->nworkers * sizeof(AggregateInstrumentation);
	node->shared_info = shm_toc_allocate(pcxt->toc, size);
	/* ensure any unfilled slots will contain zeroes */
	memset(node->shared_info, 0, size);
	node->shared_info->num_workers = pcxt->nworkers;
	shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id,
				   node->shared_info);
}

/* ----------------------------------------------------------------
 *		ExecAggInitializeWorker
 *
 *		Attach worker to DSM space for aggregate statistics.
 * ----------------------------------------------------------------
 */
void
ExecAggInitializeWorker(AggState *node, ParallelWorkerContext *pwcxt)
{
	node->shared_info =
		shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, true);
}

/* ----------------------------------------------------------------
 *		ExecAggRetrieveInstrumentation
 *
 *		Transfer aggregate statistics from DSM to private memory.
 * ----------------------------------------------------------------
 */
void
ExecAggRetrieveInstrumentation(AggState *node)
{
	Size		size;
	SharedAggInfo *si;

	if (node->shared_info == NULL)
		return;

	size = offsetof(SharedAggInfo, sinstrument)
		+ node->shared_info->num_workers * sizeof(AggregateInstrumentation);
	si = palloc(size);
	memcpy(si, node->shared_info, size);
	node->shared_info = si;
}