summaryrefslogtreecommitdiffstats
path: root/src/backend/postmaster/autovacuum.c
blob: 72a5c4aefe99a17d3de7751404c773220ac7dca7 (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
/*-------------------------------------------------------------------------
 *
 * autovacuum.c
 *
 * PostgreSQL Integrated Autovacuum Daemon
 *
 * The autovacuum system is structured in two different kinds of processes: the
 * autovacuum launcher and the autovacuum worker.  The launcher is an
 * always-running process, started by the postmaster when the autovacuum GUC
 * parameter is set.  The launcher schedules autovacuum workers to be started
 * when appropriate.  The workers are the processes which execute the actual
 * vacuuming; they connect to a database as determined in the launcher, and
 * once connected they examine the catalogs to select the tables to vacuum.
 *
 * The autovacuum launcher cannot start the worker processes by itself,
 * because doing so would cause robustness issues (namely, failure to shut
 * them down on exceptional conditions, and also, since the launcher is
 * connected to shared memory and is thus subject to corruption there, it is
 * not as robust as the postmaster).  So it leaves that task to the postmaster.
 *
 * There is an autovacuum shared memory area, where the launcher stores
 * information about the database it wants vacuumed.  When it wants a new
 * worker to start, it sets a flag in shared memory and sends a signal to the
 * postmaster.  Then postmaster knows nothing more than it must start a worker;
 * so it forks a new child, which turns into a worker.  This new process
 * connects to shared memory, and there it can inspect the information that the
 * launcher has set up.
 *
 * If the fork() call fails in the postmaster, it sets a flag in the shared
 * memory area, and sends a signal to the launcher.  The launcher, upon
 * noticing the flag, can try starting the worker again by resending the
 * signal.  Note that the failure can only be transient (fork failure due to
 * high load, memory pressure, too many processes, etc); more permanent
 * problems, like failure to connect to a database, are detected later in the
 * worker and dealt with just by having the worker exit normally.  The launcher
 * will launch a new worker again later, per schedule.
 *
 * When the worker is done vacuuming it sends SIGUSR2 to the launcher.  The
 * launcher then wakes up and is able to launch another worker, if the schedule
 * is so tight that a new worker is needed immediately.  At this time the
 * launcher can also balance the settings for the various remaining workers'
 * cost-based vacuum delay feature.
 *
 * Note that there can be more than one worker in a database concurrently.
 * They will store the table they are currently vacuuming in shared memory, so
 * that other workers avoid being blocked waiting for the vacuum lock for that
 * table.  They will also fetch the last time the table was vacuumed from
 * pgstats just before vacuuming each table, to avoid vacuuming a table that
 * was just finished being vacuumed by another worker and thus is no longer
 * noted in shared memory.  However, there is a small window (due to not yet
 * holding the relation lock) during which a worker may choose a table that was
 * already vacuumed; this is a bug in the current design.
 *
 * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  src/backend/postmaster/autovacuum.c
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include <signal.h>
#include <sys/time.h>
#include <unistd.h>

#include "access/heapam.h"
#include "access/htup_details.h"
#include "access/multixact.h"
#include "access/reloptions.h"
#include "access/tableam.h"
#include "access/transam.h"
#include "access/xact.h"
#include "catalog/dependency.h"
#include "catalog/namespace.h"
#include "catalog/pg_database.h"
#include "commands/dbcommands.h"
#include "commands/vacuum.h"
#include "lib/ilist.h"
#include "libpq/pqsignal.h"
#include "miscadmin.h"
#include "nodes/makefuncs.h"
#include "pgstat.h"
#include "postmaster/autovacuum.h"
#include "postmaster/fork_process.h"
#include "postmaster/interrupt.h"
#include "postmaster/postmaster.h"
#include "storage/bufmgr.h"
#include "storage/ipc.h"
#include "storage/latch.h"
#include "storage/lmgr.h"
#include "storage/pmsignal.h"
#include "storage/proc.h"
#include "storage/procsignal.h"
#include "storage/sinvaladt.h"
#include "storage/smgr.h"
#include "tcop/tcopprot.h"
#include "utils/fmgroids.h"
#include "utils/fmgrprotos.h"
#include "utils/lsyscache.h"
#include "utils/memutils.h"
#include "utils/ps_status.h"
#include "utils/rel.h"
#include "utils/snapmgr.h"
#include "utils/syscache.h"
#include "utils/timeout.h"
#include "utils/timestamp.h"


/*
 * GUC parameters
 */
bool		autovacuum_start_daemon = false;
int			autovacuum_max_workers;
int			autovacuum_work_mem = -1;
int			autovacuum_naptime;
int			autovacuum_vac_thresh;
double		autovacuum_vac_scale;
int			autovacuum_vac_ins_thresh;
double		autovacuum_vac_ins_scale;
int			autovacuum_anl_thresh;
double		autovacuum_anl_scale;
int			autovacuum_freeze_max_age;
int			autovacuum_multixact_freeze_max_age;

double		autovacuum_vac_cost_delay;
int			autovacuum_vac_cost_limit;

int			Log_autovacuum_min_duration = 600000;

/* the minimum allowed time between two awakenings of the launcher */
#define MIN_AUTOVAC_SLEEPTIME 100.0 /* milliseconds */
#define MAX_AUTOVAC_SLEEPTIME 300	/* seconds */

/* Flags to tell if we are in an autovacuum process */
static bool am_autovacuum_launcher = false;
static bool am_autovacuum_worker = false;

/* Flags set by signal handlers */
static volatile sig_atomic_t got_SIGUSR2 = false;

/* Comparison points for determining whether freeze_max_age is exceeded */
static TransactionId recentXid;
static MultiXactId recentMulti;

/* Default freeze ages to use for autovacuum (varies by database) */
static int	default_freeze_min_age;
static int	default_freeze_table_age;
static int	default_multixact_freeze_min_age;
static int	default_multixact_freeze_table_age;

/* Memory context for long-lived data */
static MemoryContext AutovacMemCxt;

/* struct to keep track of databases in launcher */
typedef struct avl_dbase
{
	Oid			adl_datid;		/* hash key -- must be first */
	TimestampTz adl_next_worker;
	int			adl_score;
	dlist_node	adl_node;
} avl_dbase;

/* struct to keep track of databases in worker */
typedef struct avw_dbase
{
	Oid			adw_datid;
	char	   *adw_name;
	TransactionId adw_frozenxid;
	MultiXactId adw_minmulti;
	PgStat_StatDBEntry *adw_entry;
} avw_dbase;

/* struct to keep track of tables to vacuum and/or analyze, in 1st pass */
typedef struct av_relation
{
	Oid			ar_toastrelid;	/* hash key - must be first */
	Oid			ar_relid;
	bool		ar_hasrelopts;
	AutoVacOpts ar_reloptions;	/* copy of AutoVacOpts from the main table's
								 * reloptions, or NULL if none */
} av_relation;

/* struct to keep track of tables to vacuum and/or analyze, after rechecking */
typedef struct autovac_table
{
	Oid			at_relid;
	VacuumParams at_params;
	double		at_vacuum_cost_delay;
	int			at_vacuum_cost_limit;
	bool		at_dobalance;
	bool		at_sharedrel;
	char	   *at_relname;
	char	   *at_nspname;
	char	   *at_datname;
} autovac_table;

/*-------------
 * This struct holds information about a single worker's whereabouts.  We keep
 * an array of these in shared memory, sized according to
 * autovacuum_max_workers.
 *
 * wi_links		entry into free list or running list
 * wi_dboid		OID of the database this worker is supposed to work on
 * wi_tableoid	OID of the table currently being vacuumed, if any
 * wi_sharedrel flag indicating whether table is marked relisshared
 * wi_proc		pointer to PGPROC of the running worker, NULL if not started
 * wi_launchtime Time at which this worker was launched
 * wi_cost_*	Vacuum cost-based delay parameters current in this worker
 *
 * All fields are protected by AutovacuumLock, except for wi_tableoid and
 * wi_sharedrel which are protected by AutovacuumScheduleLock (note these
 * two fields are read-only for everyone except that worker itself).
 *-------------
 */
typedef struct WorkerInfoData
{
	dlist_node	wi_links;
	Oid			wi_dboid;
	Oid			wi_tableoid;
	PGPROC	   *wi_proc;
	TimestampTz wi_launchtime;
	bool		wi_dobalance;
	bool		wi_sharedrel;
	double		wi_cost_delay;
	int			wi_cost_limit;
	int			wi_cost_limit_base;
} WorkerInfoData;

typedef struct WorkerInfoData *WorkerInfo;

/*
 * Possible signals received by the launcher from remote processes.  These are
 * stored atomically in shared memory so that other processes can set them
 * without locking.
 */
typedef enum
{
	AutoVacForkFailed,			/* failed trying to start a worker */
	AutoVacRebalance,			/* rebalance the cost limits */
	AutoVacNumSignals			/* must be last */
}			AutoVacuumSignal;

/*
 * Autovacuum workitem array, stored in AutoVacuumShmem->av_workItems.  This
 * list is mostly protected by AutovacuumLock, except that if an item is
 * marked 'active' other processes must not modify the work-identifying
 * members.
 */
typedef struct AutoVacuumWorkItem
{
	AutoVacuumWorkItemType avw_type;
	bool		avw_used;		/* below data is valid */
	bool		avw_active;		/* being processed */
	Oid			avw_database;
	Oid			avw_relation;
	BlockNumber avw_blockNumber;
} AutoVacuumWorkItem;

#define NUM_WORKITEMS	256

/*-------------
 * The main autovacuum shmem struct.  On shared memory we store this main
 * struct and the array of WorkerInfo structs.  This struct keeps:
 *
 * av_signal		set by other processes to indicate various conditions
 * av_launcherpid	the PID of the autovacuum launcher
 * av_freeWorkers	the WorkerInfo freelist
 * av_runningWorkers the WorkerInfo non-free queue
 * av_startingWorker pointer to WorkerInfo currently being started (cleared by
 *					the worker itself as soon as it's up and running)
 * av_workItems		work item array
 *
 * This struct is protected by AutovacuumLock, except for av_signal and parts
 * of the worker list (see above).
 *-------------
 */
typedef struct
{
	sig_atomic_t av_signal[AutoVacNumSignals];
	pid_t		av_launcherpid;
	dlist_head	av_freeWorkers;
	dlist_head	av_runningWorkers;
	WorkerInfo	av_startingWorker;
	AutoVacuumWorkItem av_workItems[NUM_WORKITEMS];
} AutoVacuumShmemStruct;

static AutoVacuumShmemStruct *AutoVacuumShmem;

/*
 * the database list (of avl_dbase elements) in the launcher, and the context
 * that contains it
 */
static dlist_head DatabaseList = DLIST_STATIC_INIT(DatabaseList);
static MemoryContext DatabaseListCxt = NULL;

/* Pointer to my own WorkerInfo, valid on each worker */
static WorkerInfo MyWorkerInfo = NULL;

/* PID of launcher, valid only in worker while shutting down */
int			AutovacuumLauncherPid = 0;

#ifdef EXEC_BACKEND
static pid_t avlauncher_forkexec(void);
static pid_t avworker_forkexec(void);
#endif
NON_EXEC_STATIC void AutoVacWorkerMain(int argc, char *argv[]) pg_attribute_noreturn();
NON_EXEC_STATIC void AutoVacLauncherMain(int argc, char *argv[]) pg_attribute_noreturn();

static Oid	do_start_worker(void);
static void HandleAutoVacLauncherInterrupts(void);
static void AutoVacLauncherShutdown(void) pg_attribute_noreturn();
static void launcher_determine_sleep(bool canlaunch, bool recursing,
									 struct timeval *nap);
static void launch_worker(TimestampTz now);
static List *get_database_list(void);
static void rebuild_database_list(Oid newdb);
static int	db_comparator(const void *a, const void *b);
static void autovac_balance_cost(void);

static void do_autovacuum(void);
static void FreeWorkerInfo(int code, Datum arg);

static autovac_table *table_recheck_autovac(Oid relid, HTAB *table_toast_map,
											TupleDesc pg_class_desc,
											int effective_multixact_freeze_max_age);
static void recheck_relation_needs_vacanalyze(Oid relid, AutoVacOpts *avopts,
											  Form_pg_class classForm,
											  int effective_multixact_freeze_max_age,
											  bool *dovacuum, bool *doanalyze, bool *wraparound);
static void relation_needs_vacanalyze(Oid relid, AutoVacOpts *relopts,
									  Form_pg_class classForm,
									  PgStat_StatTabEntry *tabentry,
									  int effective_multixact_freeze_max_age,
									  bool *dovacuum, bool *doanalyze, bool *wraparound);

static void autovacuum_do_vac_analyze(autovac_table *tab,
									  BufferAccessStrategy bstrategy);
static AutoVacOpts *extract_autovac_opts(HeapTuple tup,
										 TupleDesc pg_class_desc);
static void perform_work_item(AutoVacuumWorkItem *workitem);
static void autovac_report_activity(autovac_table *tab);
static void autovac_report_workitem(AutoVacuumWorkItem *workitem,
									const char *nspname, const char *relname);
static void avl_sigusr2_handler(SIGNAL_ARGS);



/********************************************************************
 *					  AUTOVACUUM LAUNCHER CODE
 ********************************************************************/

#ifdef EXEC_BACKEND
/*
 * forkexec routine for the autovacuum launcher process.
 *
 * Format up the arglist, then fork and exec.
 */
static pid_t
avlauncher_forkexec(void)
{
	char	   *av[10];
	int			ac = 0;

	av[ac++] = "postgres";
	av[ac++] = "--forkavlauncher";
	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
	av[ac] = NULL;

	Assert(ac < lengthof(av));

	return postmaster_forkexec(ac, av);
}

/*
 * We need this set from the outside, before InitProcess is called
 */
void
AutovacuumLauncherIAm(void)
{
	am_autovacuum_launcher = true;
}
#endif

/*
 * Main entry point for autovacuum launcher process, to be called from the
 * postmaster.
 */
int
StartAutoVacLauncher(void)
{
	pid_t		AutoVacPID;

#ifdef EXEC_BACKEND
	switch ((AutoVacPID = avlauncher_forkexec()))
#else
	switch ((AutoVacPID = fork_process()))
#endif
	{
		case -1:
			ereport(LOG,
					(errmsg("could not fork autovacuum launcher process: %m")));
			return 0;

#ifndef EXEC_BACKEND
		case 0:
			/* in postmaster child ... */
			InitPostmasterChild();

			/* Close the postmaster's sockets */
			ClosePostmasterPorts(false);

			AutoVacLauncherMain(0, NULL);
			break;
#endif
		default:
			return (int) AutoVacPID;
	}

	/* shouldn't get here */
	return 0;
}

/*
 * Main loop for the autovacuum launcher process.
 */
NON_EXEC_STATIC void
AutoVacLauncherMain(int argc, char *argv[])
{
	sigjmp_buf	local_sigjmp_buf;

	am_autovacuum_launcher = true;

	MyBackendType = B_AUTOVAC_LAUNCHER;
	init_ps_display(NULL);

	ereport(DEBUG1,
			(errmsg_internal("autovacuum launcher started")));

	if (PostAuthDelay)
		pg_usleep(PostAuthDelay * 1000000L);

	SetProcessingMode(InitProcessing);

	/*
	 * Set up signal handlers.  We operate on databases much like a regular
	 * backend, so we use the same signal handling.  See equivalent code in
	 * tcop/postgres.c.
	 */
	pqsignal(SIGHUP, SignalHandlerForConfigReload);
	pqsignal(SIGINT, StatementCancelHandler);
	pqsignal(SIGTERM, SignalHandlerForShutdownRequest);
	/* SIGQUIT handler was already set up by InitPostmasterChild */

	InitializeTimeouts();		/* establishes SIGALRM handler */

	pqsignal(SIGPIPE, SIG_IGN);
	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
	pqsignal(SIGUSR2, avl_sigusr2_handler);
	pqsignal(SIGFPE, FloatExceptionHandler);
	pqsignal(SIGCHLD, SIG_DFL);

	/*
	 * Create a per-backend PGPROC struct in shared memory, except in the
	 * EXEC_BACKEND case where this was done in SubPostmasterMain. We must do
	 * this before we can use LWLocks (and in the EXEC_BACKEND case we already
	 * had to do some stuff with LWLocks).
	 */
#ifndef EXEC_BACKEND
	InitProcess();
#endif

	/* Early initialization */
	BaseInit();

	InitPostgres(NULL, InvalidOid, NULL, InvalidOid, false, false, NULL);

	SetProcessingMode(NormalProcessing);

	/*
	 * Create a memory context that we will do all our work in.  We do this so
	 * that we can reset the context during error recovery and thereby avoid
	 * possible memory leaks.
	 */
	AutovacMemCxt = AllocSetContextCreate(TopMemoryContext,
										  "Autovacuum Launcher",
										  ALLOCSET_DEFAULT_SIZES);
	MemoryContextSwitchTo(AutovacMemCxt);

	/*
	 * If an exception is encountered, processing resumes here.
	 *
	 * This code is a stripped down version of PostgresMain error recovery.
	 *
	 * Note that we use sigsetjmp(..., 1), so that the prevailing signal mask
	 * (to wit, BlockSig) will be restored when longjmp'ing to here.  Thus,
	 * signals other than SIGQUIT will be blocked until we complete error
	 * recovery.  It might seem that this policy makes the HOLD_INTERRUPTS()
	 * call redundant, but it is not since InterruptPending might be set
	 * already.
	 */
	if (sigsetjmp(local_sigjmp_buf, 1) != 0)
	{
		/* since not using PG_TRY, must reset error stack by hand */
		error_context_stack = NULL;

		/* Prevents interrupts while cleaning up */
		HOLD_INTERRUPTS();

		/* Forget any pending QueryCancel or timeout request */
		disable_all_timeouts(false);
		QueryCancelPending = false; /* second to avoid race condition */

		/* Report the error to the server log */
		EmitErrorReport();

		/* Abort the current transaction in order to recover */
		AbortCurrentTransaction();

		/*
		 * Release any other resources, for the case where we were not in a
		 * transaction.
		 */
		LWLockReleaseAll();
		pgstat_report_wait_end();
		AbortBufferIO();
		UnlockBuffers();
		/* this is probably dead code, but let's be safe: */
		if (AuxProcessResourceOwner)
			ReleaseAuxProcessResources(false);
		AtEOXact_Buffers(false);
		AtEOXact_SMgr();
		AtEOXact_Files(false);
		AtEOXact_HashTables(false);

		/*
		 * Now return to normal top-level context and clear ErrorContext for
		 * next time.
		 */
		MemoryContextSwitchTo(AutovacMemCxt);
		FlushErrorState();

		/* Flush any leaked data in the top-level context */
		MemoryContextResetAndDeleteChildren(AutovacMemCxt);

		/* don't leave dangling pointers to freed memory */
		DatabaseListCxt = NULL;
		dlist_init(&DatabaseList);

		/* Now we can allow interrupts again */
		RESUME_INTERRUPTS();

		/* if in shutdown mode, no need for anything further; just go away */
		if (ShutdownRequestPending)
			AutoVacLauncherShutdown();

		/*
		 * Sleep at least 1 second after any error.  We don't want to be
		 * filling the error logs as fast as we can.
		 */
		pg_usleep(1000000L);
	}

	/* We can now handle ereport(ERROR) */
	PG_exception_stack = &local_sigjmp_buf;

	/* must unblock signals before calling rebuild_database_list */
	PG_SETMASK(&UnBlockSig);

	/*
	 * Set always-secure search path.  Launcher doesn't connect to a database,
	 * so this has no effect.
	 */
	SetConfigOption("search_path", "", PGC_SUSET, PGC_S_OVERRIDE);

	/*
	 * Force zero_damaged_pages OFF in the autovac process, even if it is set
	 * in postgresql.conf.  We don't really want such a dangerous option being
	 * applied non-interactively.
	 */
	SetConfigOption("zero_damaged_pages", "false", PGC_SUSET, PGC_S_OVERRIDE);

	/*
	 * Force settable timeouts off to avoid letting these settings prevent
	 * regular maintenance from being executed.
	 */
	SetConfigOption("statement_timeout", "0", PGC_SUSET, PGC_S_OVERRIDE);
	SetConfigOption("lock_timeout", "0", PGC_SUSET, PGC_S_OVERRIDE);
	SetConfigOption("idle_in_transaction_session_timeout", "0",
					PGC_SUSET, PGC_S_OVERRIDE);

	/*
	 * Force default_transaction_isolation to READ COMMITTED.  We don't want
	 * to pay the overhead of serializable mode, nor add any risk of causing
	 * deadlocks or delaying other transactions.
	 */
	SetConfigOption("default_transaction_isolation", "read committed",
					PGC_SUSET, PGC_S_OVERRIDE);

	/*
	 * Even when system is configured to use a different fetch consistency,
	 * for autovac we always want fresh stats.
	 */
	SetConfigOption("stats_fetch_consistency", "none", PGC_SUSET, PGC_S_OVERRIDE);

	/*
	 * In emergency mode, just start a worker (unless shutdown was requested)
	 * and go away.
	 */
	if (!AutoVacuumingActive())
	{
		if (!ShutdownRequestPending)
			do_start_worker();
		proc_exit(0);			/* done */
	}

	AutoVacuumShmem->av_launcherpid = MyProcPid;

	/*
	 * Create the initial database list.  The invariant we want this list to
	 * keep is that it's ordered by decreasing next_time.  As soon as an entry
	 * is updated to a higher time, it will be moved to the front (which is
	 * correct because the only operation is to add autovacuum_naptime to the
	 * entry, and time always increases).
	 */
	rebuild_database_list(InvalidOid);

	/* loop until shutdown request */
	while (!ShutdownRequestPending)
	{
		struct timeval nap;
		TimestampTz current_time = 0;
		bool		can_launch;

		/*
		 * This loop is a bit different from the normal use of WaitLatch,
		 * because we'd like to sleep before the first launch of a child
		 * process.  So it's WaitLatch, then ResetLatch, then check for
		 * wakening conditions.
		 */

		launcher_determine_sleep(!dlist_is_empty(&AutoVacuumShmem->av_freeWorkers),
								 false, &nap);

		/*
		 * Wait until naptime expires or we get some type of signal (all the
		 * signal handlers will wake us by calling SetLatch).
		 */
		(void) WaitLatch(MyLatch,
						 WL_LATCH_SET | WL_TIMEOUT | WL_EXIT_ON_PM_DEATH,
						 (nap.tv_sec * 1000L) + (nap.tv_usec / 1000L),
						 WAIT_EVENT_AUTOVACUUM_MAIN);

		ResetLatch(MyLatch);

		HandleAutoVacLauncherInterrupts();

		/*
		 * a worker finished, or postmaster signaled failure to start a worker
		 */
		if (got_SIGUSR2)
		{
			got_SIGUSR2 = false;

			/* rebalance cost limits, if needed */
			if (AutoVacuumShmem->av_signal[AutoVacRebalance])
			{
				LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);
				AutoVacuumShmem->av_signal[AutoVacRebalance] = false;
				autovac_balance_cost();
				LWLockRelease(AutovacuumLock);
			}

			if (AutoVacuumShmem->av_signal[AutoVacForkFailed])
			{
				/*
				 * If the postmaster failed to start a new worker, we sleep
				 * for a little while and resend the signal.  The new worker's
				 * state is still in memory, so this is sufficient.  After
				 * that, we restart the main loop.
				 *
				 * XXX should we put a limit to the number of times we retry?
				 * I don't think it makes much sense, because a future start
				 * of a worker will continue to fail in the same way.
				 */
				AutoVacuumShmem->av_signal[AutoVacForkFailed] = false;
				pg_usleep(1000000L);	/* 1s */
				SendPostmasterSignal(PMSIGNAL_START_AUTOVAC_WORKER);
				continue;
			}
		}

		/*
		 * There are some conditions that we need to check before trying to
		 * start a worker.  First, we need to make sure that there is a worker
		 * slot available.  Second, we need to make sure that no other worker
		 * failed while starting up.
		 */

		current_time = GetCurrentTimestamp();
		LWLockAcquire(AutovacuumLock, LW_SHARED);

		can_launch = !dlist_is_empty(&AutoVacuumShmem->av_freeWorkers);

		if (AutoVacuumShmem->av_startingWorker != NULL)
		{
			int			waittime;
			WorkerInfo	worker = AutoVacuumShmem->av_startingWorker;

			/*
			 * We can't launch another worker when another one is still
			 * starting up (or failed while doing so), so just sleep for a bit
			 * more; that worker will wake us up again as soon as it's ready.
			 * We will only wait autovacuum_naptime seconds (up to a maximum
			 * of 60 seconds) for this to happen however.  Note that failure
			 * to connect to a particular database is not a problem here,
			 * because the worker removes itself from the startingWorker
			 * pointer before trying to connect.  Problems detected by the
			 * postmaster (like fork() failure) are also reported and handled
			 * differently.  The only problems that may cause this code to
			 * fire are errors in the earlier sections of AutoVacWorkerMain,
			 * before the worker removes the WorkerInfo from the
			 * startingWorker pointer.
			 */
			waittime = Min(autovacuum_naptime, 60) * 1000;
			if (TimestampDifferenceExceeds(worker->wi_launchtime, current_time,
										   waittime))
			{
				LWLockRelease(AutovacuumLock);
				LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);

				/*
				 * No other process can put a worker in starting mode, so if
				 * startingWorker is still INVALID after exchanging our lock,
				 * we assume it's the same one we saw above (so we don't
				 * recheck the launch time).
				 */
				if (AutoVacuumShmem->av_startingWorker != NULL)
				{
					worker = AutoVacuumShmem->av_startingWorker;
					worker->wi_dboid = InvalidOid;
					worker->wi_tableoid = InvalidOid;
					worker->wi_sharedrel = false;
					worker->wi_proc = NULL;
					worker->wi_launchtime = 0;
					dlist_push_head(&AutoVacuumShmem->av_freeWorkers,
									&worker->wi_links);
					AutoVacuumShmem->av_startingWorker = NULL;
					ereport(WARNING,
							errmsg("autovacuum worker took too long to start; canceled"));
				}
			}
			else
				can_launch = false;
		}
		LWLockRelease(AutovacuumLock);	/* either shared or exclusive */

		/* if we can't do anything, just go back to sleep */
		if (!can_launch)
			continue;

		/* We're OK to start a new worker */

		if (dlist_is_empty(&DatabaseList))
		{
			/*
			 * Special case when the list is empty: start a worker right away.
			 * This covers the initial case, when no database is in pgstats
			 * (thus the list is empty).  Note that the constraints in
			 * launcher_determine_sleep keep us from starting workers too
			 * quickly (at most once every autovacuum_naptime when the list is
			 * empty).
			 */
			launch_worker(current_time);
		}
		else
		{
			/*
			 * because rebuild_database_list constructs a list with most
			 * distant adl_next_worker first, we obtain our database from the
			 * tail of the list.
			 */
			avl_dbase  *avdb;

			avdb = dlist_tail_element(avl_dbase, adl_node, &DatabaseList);

			/*
			 * launch a worker if next_worker is right now or it is in the
			 * past
			 */
			if (TimestampDifferenceExceeds(avdb->adl_next_worker,
										   current_time, 0))
				launch_worker(current_time);
		}
	}

	AutoVacLauncherShutdown();
}

/*
 * Process any new interrupts.
 */
static void
HandleAutoVacLauncherInterrupts(void)
{
	/* the normal shutdown case */
	if (ShutdownRequestPending)
		AutoVacLauncherShutdown();

	if (ConfigReloadPending)
	{
		ConfigReloadPending = false;
		ProcessConfigFile(PGC_SIGHUP);

		/* shutdown requested in config file? */
		if (!AutoVacuumingActive())
			AutoVacLauncherShutdown();

		/* rebalance in case the default cost parameters changed */
		LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);
		autovac_balance_cost();
		LWLockRelease(AutovacuumLock);

		/* rebuild the list in case the naptime changed */
		rebuild_database_list(InvalidOid);
	}

	/* Process barrier events */
	if (ProcSignalBarrierPending)
		ProcessProcSignalBarrier();

	/* Perform logging of memory contexts of this process */
	if (LogMemoryContextPending)
		ProcessLogMemoryContextInterrupt();

	/* Process sinval catchup interrupts that happened while sleeping */
	ProcessCatchupInterrupt();
}

/*
 * Perform a normal exit from the autovac launcher.
 */
static void
AutoVacLauncherShutdown(void)
{
	ereport(DEBUG1,
			(errmsg_internal("autovacuum launcher shutting down")));
	AutoVacuumShmem->av_launcherpid = 0;

	proc_exit(0);				/* done */
}

/*
 * Determine the time to sleep, based on the database list.
 *
 * The "canlaunch" parameter indicates whether we can start a worker right now,
 * for example due to the workers being all busy.  If this is false, we will
 * cause a long sleep, which will be interrupted when a worker exits.
 */
static void
launcher_determine_sleep(bool canlaunch, bool recursing, struct timeval *nap)
{
	/*
	 * We sleep until the next scheduled vacuum.  We trust that when the
	 * database list was built, care was taken so that no entries have times
	 * in the past; if the first entry has too close a next_worker value, or a
	 * time in the past, we will sleep a small nominal time.
	 */
	if (!canlaunch)
	{
		nap->tv_sec = autovacuum_naptime;
		nap->tv_usec = 0;
	}
	else if (!dlist_is_empty(&DatabaseList))
	{
		TimestampTz current_time = GetCurrentTimestamp();
		TimestampTz next_wakeup;
		avl_dbase  *avdb;
		long		secs;
		int			usecs;

		avdb = dlist_tail_element(avl_dbase, adl_node, &DatabaseList);

		next_wakeup = avdb->adl_next_worker;
		TimestampDifference(current_time, next_wakeup, &secs, &usecs);

		nap->tv_sec = secs;
		nap->tv_usec = usecs;
	}
	else
	{
		/* list is empty, sleep for whole autovacuum_naptime seconds  */
		nap->tv_sec = autovacuum_naptime;
		nap->tv_usec = 0;
	}

	/*
	 * If the result is exactly zero, it means a database had an entry with
	 * time in the past.  Rebuild the list so that the databases are evenly
	 * distributed again, and recalculate the time to sleep.  This can happen
	 * if there are more tables needing vacuum than workers, and they all take
	 * longer to vacuum than autovacuum_naptime.
	 *
	 * We only recurse once.  rebuild_database_list should always return times
	 * in the future, but it seems best not to trust too much on that.
	 */
	if (nap->tv_sec == 0 && nap->tv_usec == 0 && !recursing)
	{
		rebuild_database_list(InvalidOid);
		launcher_determine_sleep(canlaunch, true, nap);
		return;
	}

	/* The smallest time we'll allow the launcher to sleep. */
	if (nap->tv_sec <= 0 && nap->tv_usec <= MIN_AUTOVAC_SLEEPTIME * 1000)
	{
		nap->tv_sec = 0;
		nap->tv_usec = MIN_AUTOVAC_SLEEPTIME * 1000;
	}

	/*
	 * If the sleep time is too large, clamp it to an arbitrary maximum (plus
	 * any fractional seconds, for simplicity).  This avoids an essentially
	 * infinite sleep in strange cases like the system clock going backwards a
	 * few years.
	 */
	if (nap->tv_sec > MAX_AUTOVAC_SLEEPTIME)
		nap->tv_sec = MAX_AUTOVAC_SLEEPTIME;
}

/*
 * Build an updated DatabaseList.  It must only contain databases that appear
 * in pgstats, and must be sorted by next_worker from highest to lowest,
 * distributed regularly across the next autovacuum_naptime interval.
 *
 * Receives the Oid of the database that made this list be generated (we call
 * this the "new" database, because when the database was already present on
 * the list, we expect that this function is not called at all).  The
 * preexisting list, if any, will be used to preserve the order of the
 * databases in the autovacuum_naptime period.  The new database is put at the
 * end of the interval.  The actual values are not saved, which should not be
 * much of a problem.
 */
static void
rebuild_database_list(Oid newdb)
{
	List	   *dblist;
	ListCell   *cell;
	MemoryContext newcxt;
	MemoryContext oldcxt;
	MemoryContext tmpcxt;
	HASHCTL		hctl;
	int			score;
	int			nelems;
	HTAB	   *dbhash;
	dlist_iter	iter;

	newcxt = AllocSetContextCreate(AutovacMemCxt,
								   "Autovacuum database list",
								   ALLOCSET_DEFAULT_SIZES);
	tmpcxt = AllocSetContextCreate(newcxt,
								   "Autovacuum database list (tmp)",
								   ALLOCSET_DEFAULT_SIZES);
	oldcxt = MemoryContextSwitchTo(tmpcxt);

	/*
	 * Implementing this is not as simple as it sounds, because we need to put
	 * the new database at the end of the list; next the databases that were
	 * already on the list, and finally (at the tail of the list) all the
	 * other databases that are not on the existing list.
	 *
	 * To do this, we build an empty hash table of scored databases.  We will
	 * start with the lowest score (zero) for the new database, then
	 * increasing scores for the databases in the existing list, in order, and
	 * lastly increasing scores for all databases gotten via
	 * get_database_list() that are not already on the hash.
	 *
	 * Then we will put all the hash elements into an array, sort the array by
	 * score, and finally put the array elements into the new doubly linked
	 * list.
	 */
	hctl.keysize = sizeof(Oid);
	hctl.entrysize = sizeof(avl_dbase);
	hctl.hcxt = tmpcxt;
	dbhash = hash_create("autovacuum db hash", 20, &hctl,	/* magic number here
															 * FIXME */
						 HASH_ELEM | HASH_BLOBS | HASH_CONTEXT);

	/* start by inserting the new database */
	score = 0;
	if (OidIsValid(newdb))
	{
		avl_dbase  *db;
		PgStat_StatDBEntry *entry;

		/* only consider this database if it has a pgstat entry */
		entry = pgstat_fetch_stat_dbentry(newdb);
		if (entry != NULL)
		{
			/* we assume it isn't found because the hash was just created */
			db = hash_search(dbhash, &newdb, HASH_ENTER, NULL);

			/* hash_search already filled in the key */
			db->adl_score = score++;
			/* next_worker is filled in later */
		}
	}

	/* Now insert the databases from the existing list */
	dlist_foreach(iter, &DatabaseList)
	{
		avl_dbase  *avdb = dlist_container(avl_dbase, adl_node, iter.cur);
		avl_dbase  *db;
		bool		found;
		PgStat_StatDBEntry *entry;

		/*
		 * skip databases with no stat entries -- in particular, this gets rid
		 * of dropped databases
		 */
		entry = pgstat_fetch_stat_dbentry(avdb->adl_datid);
		if (entry == NULL)
			continue;

		db = hash_search(dbhash, &(avdb->adl_datid), HASH_ENTER, &found);

		if (!found)
		{
			/* hash_search already filled in the key */
			db->adl_score = score++;
			/* next_worker is filled in later */
		}
	}

	/* finally, insert all qualifying databases not previously inserted */
	dblist = get_database_list();
	foreach(cell, dblist)
	{
		avw_dbase  *avdb = lfirst(cell);
		avl_dbase  *db;
		bool		found;
		PgStat_StatDBEntry *entry;

		/* only consider databases with a pgstat entry */
		entry = pgstat_fetch_stat_dbentry(avdb->adw_datid);
		if (entry == NULL)
			continue;

		db = hash_search(dbhash, &(avdb->adw_datid), HASH_ENTER, &found);
		/* only update the score if the database was not already on the hash */
		if (!found)
		{
			/* hash_search already filled in the key */
			db->adl_score = score++;
			/* next_worker is filled in later */
		}
	}
	nelems = score;

	/* from here on, the allocated memory belongs to the new list */
	MemoryContextSwitchTo(newcxt);
	dlist_init(&DatabaseList);

	if (nelems > 0)
	{
		TimestampTz current_time;
		int			millis_increment;
		avl_dbase  *dbary;
		avl_dbase  *db;
		HASH_SEQ_STATUS seq;
		int			i;

		/* put all the hash elements into an array */
		dbary = palloc(nelems * sizeof(avl_dbase));

		i = 0;
		hash_seq_init(&seq, dbhash);
		while ((db = hash_seq_search(&seq)) != NULL)
			memcpy(&(dbary[i++]), db, sizeof(avl_dbase));

		/* sort the array */
		qsort(dbary, nelems, sizeof(avl_dbase), db_comparator);

		/*
		 * Determine the time interval between databases in the schedule. If
		 * we see that the configured naptime would take us to sleep times
		 * lower than our min sleep time (which launcher_determine_sleep is
		 * coded not to allow), silently use a larger naptime (but don't touch
		 * the GUC variable).
		 */
		millis_increment = 1000.0 * autovacuum_naptime / nelems;
		if (millis_increment <= MIN_AUTOVAC_SLEEPTIME)
			millis_increment = MIN_AUTOVAC_SLEEPTIME * 1.1;

		current_time = GetCurrentTimestamp();

		/*
		 * move the elements from the array into the dlist, setting the
		 * next_worker while walking the array
		 */
		for (i = 0; i < nelems; i++)
		{
			avl_dbase  *db = &(dbary[i]);

			current_time = TimestampTzPlusMilliseconds(current_time,
													   millis_increment);
			db->adl_next_worker = current_time;

			/* later elements should go closer to the head of the list */
			dlist_push_head(&DatabaseList, &db->adl_node);
		}
	}

	/* all done, clean up memory */
	if (DatabaseListCxt != NULL)
		MemoryContextDelete(DatabaseListCxt);
	MemoryContextDelete(tmpcxt);
	DatabaseListCxt = newcxt;
	MemoryContextSwitchTo(oldcxt);
}

/* qsort comparator for avl_dbase, using adl_score */
static int
db_comparator(const void *a, const void *b)
{
	if (((const avl_dbase *) a)->adl_score == ((const avl_dbase *) b)->adl_score)
		return 0;
	else
		return (((const avl_dbase *) a)->adl_score < ((const avl_dbase *) b)->adl_score) ? 1 : -1;
}

/*
 * do_start_worker
 *
 * Bare-bones procedure for starting an autovacuum worker from the launcher.
 * It determines what database to work on, sets up shared memory stuff and
 * signals postmaster to start the worker.  It fails gracefully if invoked when
 * autovacuum_workers are already active.
 *
 * Return value is the OID of the database that the worker is going to process,
 * or InvalidOid if no worker was actually started.
 */
static Oid
do_start_worker(void)
{
	List	   *dblist;
	ListCell   *cell;
	TransactionId xidForceLimit;
	MultiXactId multiForceLimit;
	bool		for_xid_wrap;
	bool		for_multi_wrap;
	avw_dbase  *avdb;
	TimestampTz current_time;
	bool		skipit = false;
	Oid			retval = InvalidOid;
	MemoryContext tmpcxt,
				oldcxt;

	/* return quickly when there are no free workers */
	LWLockAcquire(AutovacuumLock, LW_SHARED);
	if (dlist_is_empty(&AutoVacuumShmem->av_freeWorkers))
	{
		LWLockRelease(AutovacuumLock);
		return InvalidOid;
	}
	LWLockRelease(AutovacuumLock);

	/*
	 * Create and switch to a temporary context to avoid leaking the memory
	 * allocated for the database list.
	 */
	tmpcxt = AllocSetContextCreate(CurrentMemoryContext,
								   "Autovacuum start worker (tmp)",
								   ALLOCSET_DEFAULT_SIZES);
	oldcxt = MemoryContextSwitchTo(tmpcxt);

	/* Get a list of databases */
	dblist = get_database_list();

	/*
	 * Determine the oldest datfrozenxid/relfrozenxid that we will allow to
	 * pass without forcing a vacuum.  (This limit can be tightened for
	 * particular tables, but not loosened.)
	 */
	recentXid = ReadNextTransactionId();
	xidForceLimit = recentXid - autovacuum_freeze_max_age;
	/* ensure it's a "normal" XID, else TransactionIdPrecedes misbehaves */
	/* this can cause the limit to go backwards by 3, but that's OK */
	if (xidForceLimit < FirstNormalTransactionId)
		xidForceLimit -= FirstNormalTransactionId;

	/* Also determine the oldest datminmxid we will consider. */
	recentMulti = ReadNextMultiXactId();
	multiForceLimit = recentMulti - MultiXactMemberFreezeThreshold();
	if (multiForceLimit < FirstMultiXactId)
		multiForceLimit -= FirstMultiXactId;

	/*
	 * Choose a database to connect to.  We pick the database that was least
	 * recently auto-vacuumed, or one that needs vacuuming to prevent Xid
	 * wraparound-related data loss.  If any db at risk of Xid wraparound is
	 * found, we pick the one with oldest datfrozenxid, independently of
	 * autovacuum times; similarly we pick the one with the oldest datminmxid
	 * if any is in MultiXactId wraparound.  Note that those in Xid wraparound
	 * danger are given more priority than those in multi wraparound danger.
	 *
	 * Note that a database with no stats entry is not considered, except for
	 * Xid wraparound purposes.  The theory is that if no one has ever
	 * connected to it since the stats were last initialized, it doesn't need
	 * vacuuming.
	 *
	 * XXX This could be improved if we had more info about whether it needs
	 * vacuuming before connecting to it.  Perhaps look through the pgstats
	 * data for the database's tables?  One idea is to keep track of the
	 * number of new and dead tuples per database in pgstats.  However it
	 * isn't clear how to construct a metric that measures that and not cause
	 * starvation for less busy databases.
	 */
	avdb = NULL;
	for_xid_wrap = false;
	for_multi_wrap = false;
	current_time = GetCurrentTimestamp();
	foreach(cell, dblist)
	{
		avw_dbase  *tmp = lfirst(cell);
		dlist_iter	iter;

		/* Check to see if this one is at risk of wraparound */
		if (TransactionIdPrecedes(tmp->adw_frozenxid, xidForceLimit))
		{
			if (avdb == NULL ||
				TransactionIdPrecedes(tmp->adw_frozenxid,
									  avdb->adw_frozenxid))
				avdb = tmp;
			for_xid_wrap = true;
			continue;
		}
		else if (for_xid_wrap)
			continue;			/* ignore not-at-risk DBs */
		else if (MultiXactIdPrecedes(tmp->adw_minmulti, multiForceLimit))
		{
			if (avdb == NULL ||
				MultiXactIdPrecedes(tmp->adw_minmulti, avdb->adw_minmulti))
				avdb = tmp;
			for_multi_wrap = true;
			continue;
		}
		else if (for_multi_wrap)
			continue;			/* ignore not-at-risk DBs */

		/* Find pgstat entry if any */
		tmp->adw_entry = pgstat_fetch_stat_dbentry(tmp->adw_datid);

		/*
		 * Skip a database with no pgstat entry; it means it hasn't seen any
		 * activity.
		 */
		if (!tmp->adw_entry)
			continue;

		/*
		 * Also, skip a database that appears on the database list as having
		 * been processed recently (less than autovacuum_naptime seconds ago).
		 * We do this so that we don't select a database which we just
		 * selected, but that pgstat hasn't gotten around to updating the last
		 * autovacuum time yet.
		 */
		skipit = false;

		dlist_reverse_foreach(iter, &DatabaseList)
		{
			avl_dbase  *dbp = dlist_container(avl_dbase, adl_node, iter.cur);

			if (dbp->adl_datid == tmp->adw_datid)
			{
				/*
				 * Skip this database if its next_worker value falls between
				 * the current time and the current time plus naptime.
				 */
				if (!TimestampDifferenceExceeds(dbp->adl_next_worker,
												current_time, 0) &&
					!TimestampDifferenceExceeds(current_time,
												dbp->adl_next_worker,
												autovacuum_naptime * 1000))
					skipit = true;

				break;
			}
		}
		if (skipit)
			continue;

		/*
		 * Remember the db with oldest autovac time.  (If we are here, both
		 * tmp->entry and db->entry must be non-null.)
		 */
		if (avdb == NULL ||
			tmp->adw_entry->last_autovac_time < avdb->adw_entry->last_autovac_time)
			avdb = tmp;
	}

	/* Found a database -- process it */
	if (avdb != NULL)
	{
		WorkerInfo	worker;
		dlist_node *wptr;

		LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);

		/*
		 * Get a worker entry from the freelist.  We checked above, so there
		 * really should be a free slot.
		 */
		wptr = dlist_pop_head_node(&AutoVacuumShmem->av_freeWorkers);

		worker = dlist_container(WorkerInfoData, wi_links, wptr);
		worker->wi_dboid = avdb->adw_datid;
		worker->wi_proc = NULL;
		worker->wi_launchtime = GetCurrentTimestamp();

		AutoVacuumShmem->av_startingWorker = worker;

		LWLockRelease(AutovacuumLock);

		SendPostmasterSignal(PMSIGNAL_START_AUTOVAC_WORKER);

		retval = avdb->adw_datid;
	}
	else if (skipit)
	{
		/*
		 * If we skipped all databases on the list, rebuild it, because it
		 * probably contains a dropped database.
		 */
		rebuild_database_list(InvalidOid);
	}

	MemoryContextSwitchTo(oldcxt);
	MemoryContextDelete(tmpcxt);

	return retval;
}

/*
 * launch_worker
 *
 * Wrapper for starting a worker from the launcher.  Besides actually starting
 * it, update the database list to reflect the next time that another one will
 * need to be started on the selected database.  The actual database choice is
 * left to do_start_worker.
 *
 * This routine is also expected to insert an entry into the database list if
 * the selected database was previously absent from the list.
 */
static void
launch_worker(TimestampTz now)
{
	Oid			dbid;
	dlist_iter	iter;

	dbid = do_start_worker();
	if (OidIsValid(dbid))
	{
		bool		found = false;

		/*
		 * Walk the database list and update the corresponding entry.  If the
		 * database is not on the list, we'll recreate the list.
		 */
		dlist_foreach(iter, &DatabaseList)
		{
			avl_dbase  *avdb = dlist_container(avl_dbase, adl_node, iter.cur);

			if (avdb->adl_datid == dbid)
			{
				found = true;

				/*
				 * add autovacuum_naptime seconds to the current time, and use
				 * that as the new "next_worker" field for this database.
				 */
				avdb->adl_next_worker =
					TimestampTzPlusMilliseconds(now, autovacuum_naptime * 1000);

				dlist_move_head(&DatabaseList, iter.cur);
				break;
			}
		}

		/*
		 * If the database was not present in the database list, we rebuild
		 * the list.  It's possible that the database does not get into the
		 * list anyway, for example if it's a database that doesn't have a
		 * pgstat entry, but this is not a problem because we don't want to
		 * schedule workers regularly into those in any case.
		 */
		if (!found)
			rebuild_database_list(dbid);
	}
}

/*
 * Called from postmaster to signal a failure to fork a process to become
 * worker.  The postmaster should kill(SIGUSR2) the launcher shortly
 * after calling this function.
 */
void
AutoVacWorkerFailed(void)
{
	AutoVacuumShmem->av_signal[AutoVacForkFailed] = true;
}

/* SIGUSR2: a worker is up and running, or just finished, or failed to fork */
static void
avl_sigusr2_handler(SIGNAL_ARGS)
{
	int			save_errno = errno;

	got_SIGUSR2 = true;
	SetLatch(MyLatch);

	errno = save_errno;
}


/********************************************************************
 *					  AUTOVACUUM WORKER CODE
 ********************************************************************/

#ifdef EXEC_BACKEND
/*
 * forkexec routines for the autovacuum worker.
 *
 * Format up the arglist, then fork and exec.
 */
static pid_t
avworker_forkexec(void)
{
	char	   *av[10];
	int			ac = 0;

	av[ac++] = "postgres";
	av[ac++] = "--forkavworker";
	av[ac++] = NULL;			/* filled in by postmaster_forkexec */
	av[ac] = NULL;

	Assert(ac < lengthof(av));

	return postmaster_forkexec(ac, av);
}

/*
 * We need this set from the outside, before InitProcess is called
 */
void
AutovacuumWorkerIAm(void)
{
	am_autovacuum_worker = true;
}
#endif

/*
 * Main entry point for autovacuum worker process.
 *
 * This code is heavily based on pgarch.c, q.v.
 */
int
StartAutoVacWorker(void)
{
	pid_t		worker_pid;

#ifdef EXEC_BACKEND
	switch ((worker_pid = avworker_forkexec()))
#else
	switch ((worker_pid = fork_process()))
#endif
	{
		case -1:
			ereport(LOG,
					(errmsg("could not fork autovacuum worker process: %m")));
			return 0;

#ifndef EXEC_BACKEND
		case 0:
			/* in postmaster child ... */
			InitPostmasterChild();

			/* Close the postmaster's sockets */
			ClosePostmasterPorts(false);

			AutoVacWorkerMain(0, NULL);
			break;
#endif
		default:
			return (int) worker_pid;
	}

	/* shouldn't get here */
	return 0;
}

/*
 * AutoVacWorkerMain
 */
NON_EXEC_STATIC void
AutoVacWorkerMain(int argc, char *argv[])
{
	sigjmp_buf	local_sigjmp_buf;
	Oid			dbid;

	am_autovacuum_worker = true;

	MyBackendType = B_AUTOVAC_WORKER;
	init_ps_display(NULL);

	SetProcessingMode(InitProcessing);

	/*
	 * Set up signal handlers.  We operate on databases much like a regular
	 * backend, so we use the same signal handling.  See equivalent code in
	 * tcop/postgres.c.
	 */
	pqsignal(SIGHUP, SignalHandlerForConfigReload);

	/*
	 * SIGINT is used to signal canceling the current table's vacuum; SIGTERM
	 * means abort and exit cleanly, and SIGQUIT means abandon ship.
	 */
	pqsignal(SIGINT, StatementCancelHandler);
	pqsignal(SIGTERM, die);
	/* SIGQUIT handler was already set up by InitPostmasterChild */

	InitializeTimeouts();		/* establishes SIGALRM handler */

	pqsignal(SIGPIPE, SIG_IGN);
	pqsignal(SIGUSR1, procsignal_sigusr1_handler);
	pqsignal(SIGUSR2, SIG_IGN);
	pqsignal(SIGFPE, FloatExceptionHandler);
	pqsignal(SIGCHLD, SIG_DFL);

	/*
	 * Create a per-backend PGPROC struct in shared memory, except in the
	 * EXEC_BACKEND case where this was done in SubPostmasterMain. We must do
	 * this before we can use LWLocks (and in the EXEC_BACKEND case we already
	 * had to do some stuff with LWLocks).
	 */
#ifndef EXEC_BACKEND
	InitProcess();
#endif

	/* Early initialization */
	BaseInit();

	/*
	 * If an exception is encountered, processing resumes here.
	 *
	 * Unlike most auxiliary processes, we don't attempt to continue
	 * processing after an error; we just clean up and exit.  The autovac
	 * launcher is responsible for spawning another worker later.
	 *
	 * Note that we use sigsetjmp(..., 1), so that the prevailing signal mask
	 * (to wit, BlockSig) will be restored when longjmp'ing to here.  Thus,
	 * signals other than SIGQUIT will be blocked until we exit.  It might
	 * seem that this policy makes the HOLD_INTERRUPTS() call redundant, but
	 * it is not since InterruptPending might be set already.
	 */
	if (sigsetjmp(local_sigjmp_buf, 1) != 0)
	{
		/* since not using PG_TRY, must reset error stack by hand */
		error_context_stack = NULL;

		/* Prevents interrupts while cleaning up */
		HOLD_INTERRUPTS();

		/* Report the error to the server log */
		EmitErrorReport();

		/*
		 * We can now go away.  Note that because we called InitProcess, a
		 * callback was registered to do ProcKill, which will clean up
		 * necessary state.
		 */
		proc_exit(0);
	}

	/* We can now handle ereport(ERROR) */
	PG_exception_stack = &local_sigjmp_buf;

	PG_SETMASK(&UnBlockSig);

	/*
	 * Set always-secure search path, so malicious users can't redirect user
	 * code (e.g. pg_index.indexprs).  (That code runs in a
	 * SECURITY_RESTRICTED_OPERATION sandbox, so malicious users could not
	 * take control of the entire autovacuum worker in any case.)
	 */
	SetConfigOption("search_path", "", PGC_SUSET, PGC_S_OVERRIDE);

	/*
	 * Force zero_damaged_pages OFF in the autovac process, even if it is set
	 * in postgresql.conf.  We don't really want such a dangerous option being
	 * applied non-interactively.
	 */
	SetConfigOption("zero_damaged_pages", "false", PGC_SUSET, PGC_S_OVERRIDE);

	/*
	 * Force settable timeouts off to avoid letting these settings prevent
	 * regular maintenance from being executed.
	 */
	SetConfigOption("statement_timeout", "0", PGC_SUSET, PGC_S_OVERRIDE);
	SetConfigOption("lock_timeout", "0", PGC_SUSET, PGC_S_OVERRIDE);
	SetConfigOption("idle_in_transaction_session_timeout", "0",
					PGC_SUSET, PGC_S_OVERRIDE);

	/*
	 * Force default_transaction_isolation to READ COMMITTED.  We don't want
	 * to pay the overhead of serializable mode, nor add any risk of causing
	 * deadlocks or delaying other transactions.
	 */
	SetConfigOption("default_transaction_isolation", "read committed",
					PGC_SUSET, PGC_S_OVERRIDE);

	/*
	 * Force synchronous replication off to allow regular maintenance even if
	 * we are waiting for standbys to connect. This is important to ensure we
	 * aren't blocked from performing anti-wraparound tasks.
	 */
	if (synchronous_commit > SYNCHRONOUS_COMMIT_LOCAL_FLUSH)
		SetConfigOption("synchronous_commit", "local",
						PGC_SUSET, PGC_S_OVERRIDE);

	/*
	 * Even when system is configured to use a different fetch consistency,
	 * for autovac we always want fresh stats.
	 */
	SetConfigOption("stats_fetch_consistency", "none", PGC_SUSET, PGC_S_OVERRIDE);

	/*
	 * Get the info about the database we're going to work on.
	 */
	LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);

	/*
	 * beware of startingWorker being INVALID; this should normally not
	 * happen, but if a worker fails after forking and before this, the
	 * launcher might have decided to remove it from the queue and start
	 * again.
	 */
	if (AutoVacuumShmem->av_startingWorker != NULL)
	{
		MyWorkerInfo = AutoVacuumShmem->av_startingWorker;
		dbid = MyWorkerInfo->wi_dboid;
		MyWorkerInfo->wi_proc = MyProc;

		/* insert into the running list */
		dlist_push_head(&AutoVacuumShmem->av_runningWorkers,
						&MyWorkerInfo->wi_links);

		/*
		 * remove from the "starting" pointer, so that the launcher can start
		 * a new worker if required
		 */
		AutoVacuumShmem->av_startingWorker = NULL;
		LWLockRelease(AutovacuumLock);

		on_shmem_exit(FreeWorkerInfo, 0);

		/* wake up the launcher */
		if (AutoVacuumShmem->av_launcherpid != 0)
			kill(AutoVacuumShmem->av_launcherpid, SIGUSR2);
	}
	else
	{
		/* no worker entry for me, go away */
		elog(WARNING, "autovacuum worker started without a worker entry");
		dbid = InvalidOid;
		LWLockRelease(AutovacuumLock);
	}

	if (OidIsValid(dbid))
	{
		char		dbname[NAMEDATALEN];

		/*
		 * Report autovac startup to the cumulative stats system.  We
		 * deliberately do this before InitPostgres, so that the
		 * last_autovac_time will get updated even if the connection attempt
		 * fails.  This is to prevent autovac from getting "stuck" repeatedly
		 * selecting an unopenable database, rather than making any progress
		 * on stuff it can connect to.
		 */
		pgstat_report_autovac(dbid);

		/*
		 * Connect to the selected database, specifying no particular user
		 *
		 * Note: if we have selected a just-deleted database (due to using
		 * stale stats info), we'll fail and exit here.
		 */
		InitPostgres(NULL, dbid, NULL, InvalidOid, false, false,
					 dbname);
		SetProcessingMode(NormalProcessing);
		set_ps_display(dbname);
		ereport(DEBUG1,
				(errmsg_internal("autovacuum: processing database \"%s\"", dbname)));

		if (PostAuthDelay)
			pg_usleep(PostAuthDelay * 1000000L);

		/* And do an appropriate amount of work */
		recentXid = ReadNextTransactionId();
		recentMulti = ReadNextMultiXactId();
		do_autovacuum();
	}

	/*
	 * The launcher will be notified of my death in ProcKill, *if* we managed
	 * to get a worker slot at all
	 */

	/* All done, go away */
	proc_exit(0);
}

/*
 * Return a WorkerInfo to the free list
 */
static void
FreeWorkerInfo(int code, Datum arg)
{
	if (MyWorkerInfo != NULL)
	{
		LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);

		/*
		 * Wake the launcher up so that he can launch a new worker immediately
		 * if required.  We only save the launcher's PID in local memory here;
		 * the actual signal will be sent when the PGPROC is recycled.  Note
		 * that we always do this, so that the launcher can rebalance the cost
		 * limit setting of the remaining workers.
		 *
		 * We somewhat ignore the risk that the launcher changes its PID
		 * between us reading it and the actual kill; we expect ProcKill to be
		 * called shortly after us, and we assume that PIDs are not reused too
		 * quickly after a process exits.
		 */
		AutovacuumLauncherPid = AutoVacuumShmem->av_launcherpid;

		dlist_delete(&MyWorkerInfo->wi_links);
		MyWorkerInfo->wi_dboid = InvalidOid;
		MyWorkerInfo->wi_tableoid = InvalidOid;
		MyWorkerInfo->wi_sharedrel = false;
		MyWorkerInfo->wi_proc = NULL;
		MyWorkerInfo->wi_launchtime = 0;
		MyWorkerInfo->wi_dobalance = false;
		MyWorkerInfo->wi_cost_delay = 0;
		MyWorkerInfo->wi_cost_limit = 0;
		MyWorkerInfo->wi_cost_limit_base = 0;
		dlist_push_head(&AutoVacuumShmem->av_freeWorkers,
						&MyWorkerInfo->wi_links);
		/* not mine anymore */
		MyWorkerInfo = NULL;

		/*
		 * now that we're inactive, cause a rebalancing of the surviving
		 * workers
		 */
		AutoVacuumShmem->av_signal[AutoVacRebalance] = true;
		LWLockRelease(AutovacuumLock);
	}
}

/*
 * Update the cost-based delay parameters, so that multiple workers consume
 * each a fraction of the total available I/O.
 */
void
AutoVacuumUpdateDelay(void)
{
	if (MyWorkerInfo)
	{
		VacuumCostDelay = MyWorkerInfo->wi_cost_delay;
		VacuumCostLimit = MyWorkerInfo->wi_cost_limit;
	}
}

/*
 * autovac_balance_cost
 *		Recalculate the cost limit setting for each active worker.
 *
 * Caller must hold the AutovacuumLock in exclusive mode.
 */
static void
autovac_balance_cost(void)
{
	/*
	 * The idea here is that we ration out I/O equally.  The amount of I/O
	 * that a worker can consume is determined by cost_limit/cost_delay, so we
	 * try to equalize those ratios rather than the raw limit settings.
	 *
	 * note: in cost_limit, zero also means use value from elsewhere, because
	 * zero is not a valid value.
	 */
	int			vac_cost_limit = (autovacuum_vac_cost_limit > 0 ?
								  autovacuum_vac_cost_limit : VacuumCostLimit);
	double		vac_cost_delay = (autovacuum_vac_cost_delay >= 0 ?
								  autovacuum_vac_cost_delay : VacuumCostDelay);
	double		cost_total;
	double		cost_avail;
	dlist_iter	iter;

	/* not set? nothing to do */
	if (vac_cost_limit <= 0 || vac_cost_delay <= 0)
		return;

	/* calculate the total base cost limit of participating active workers */
	cost_total = 0.0;
	dlist_foreach(iter, &AutoVacuumShmem->av_runningWorkers)
	{
		WorkerInfo	worker = dlist_container(WorkerInfoData, wi_links, iter.cur);

		if (worker->wi_proc != NULL &&
			worker->wi_dobalance &&
			worker->wi_cost_limit_base > 0 && worker->wi_cost_delay > 0)
			cost_total +=
				(double) worker->wi_cost_limit_base / worker->wi_cost_delay;
	}

	/* there are no cost limits -- nothing to do */
	if (cost_total <= 0)
		return;

	/*
	 * Adjust cost limit of each active worker to balance the total of cost
	 * limit to autovacuum_vacuum_cost_limit.
	 */
	cost_avail = (double) vac_cost_limit / vac_cost_delay;
	dlist_foreach(iter, &AutoVacuumShmem->av_runningWorkers)
	{
		WorkerInfo	worker = dlist_container(WorkerInfoData, wi_links, iter.cur);

		if (worker->wi_proc != NULL &&
			worker->wi_dobalance &&
			worker->wi_cost_limit_base > 0 && worker->wi_cost_delay > 0)
		{
			int			limit = (int)
			(cost_avail * worker->wi_cost_limit_base / cost_total);

			/*
			 * We put a lower bound of 1 on the cost_limit, to avoid division-
			 * by-zero in the vacuum code.  Also, in case of roundoff trouble
			 * in these calculations, let's be sure we don't ever set
			 * cost_limit to more than the base value.
			 */
			worker->wi_cost_limit = Max(Min(limit,
											worker->wi_cost_limit_base),
										1);
		}

		if (worker->wi_proc != NULL)
			elog(DEBUG2, "autovac_balance_cost(pid=%d db=%u, rel=%u, dobalance=%s cost_limit=%d, cost_limit_base=%d, cost_delay=%g)",
				 worker->wi_proc->pid, worker->wi_dboid, worker->wi_tableoid,
				 worker->wi_dobalance ? "yes" : "no",
				 worker->wi_cost_limit, worker->wi_cost_limit_base,
				 worker->wi_cost_delay);
	}
}

/*
 * get_database_list
 *		Return a list of all databases found in pg_database.
 *
 * The list and associated data is allocated in the caller's memory context,
 * which is in charge of ensuring that it's properly cleaned up afterwards.
 *
 * Note: this is the only function in which the autovacuum launcher uses a
 * transaction.  Although we aren't attached to any particular database and
 * therefore can't access most catalogs, we do have enough infrastructure
 * to do a seqscan on pg_database.
 */
static List *
get_database_list(void)
{
	List	   *dblist = NIL;
	Relation	rel;
	TableScanDesc scan;
	HeapTuple	tup;
	MemoryContext resultcxt;

	/* This is the context that we will allocate our output data in */
	resultcxt = CurrentMemoryContext;

	/*
	 * Start a transaction so we can access pg_database, and get a snapshot.
	 * We don't have a use for the snapshot itself, but we're interested in
	 * the secondary effect that it sets RecentGlobalXmin.  (This is critical
	 * for anything that reads heap pages, because HOT may decide to prune
	 * them even if the process doesn't attempt to modify any tuples.)
	 *
	 * FIXME: This comment is inaccurate / the code buggy. A snapshot that is
	 * not pushed/active does not reliably prevent HOT pruning (->xmin could
	 * e.g. be cleared when cache invalidations are processed).
	 */
	StartTransactionCommand();
	(void) GetTransactionSnapshot();

	rel = table_open(DatabaseRelationId, AccessShareLock);
	scan = table_beginscan_catalog(rel, 0, NULL);

	while (HeapTupleIsValid(tup = heap_getnext(scan, ForwardScanDirection)))
	{
		Form_pg_database pgdatabase = (Form_pg_database) GETSTRUCT(tup);
		avw_dbase  *avdb;
		MemoryContext oldcxt;

		/*
		 * If database has partially been dropped, we can't, nor need to,
		 * vacuum it.
		 */
		if (database_is_invalid_form(pgdatabase))
		{
			elog(DEBUG2,
				 "autovacuum: skipping invalid database \"%s\"",
				 NameStr(pgdatabase->datname));
			continue;
		}

		/*
		 * Allocate our results in the caller's context, not the
		 * transaction's. We do this inside the loop, and restore the original
		 * context at the end, so that leaky things like heap_getnext() are
		 * not called in a potentially long-lived context.
		 */
		oldcxt = MemoryContextSwitchTo(resultcxt);

		avdb = (avw_dbase *) palloc(sizeof(avw_dbase));

		avdb->adw_datid = pgdatabase->oid;
		avdb->adw_name = pstrdup(NameStr(pgdatabase->datname));
		avdb->adw_frozenxid = pgdatabase->datfrozenxid;
		avdb->adw_minmulti = pgdatabase->datminmxid;
		/* this gets set later: */
		avdb->adw_entry = NULL;

		dblist = lappend(dblist, avdb);
		MemoryContextSwitchTo(oldcxt);
	}

	table_endscan(scan);
	table_close(rel, AccessShareLock);

	CommitTransactionCommand();

	/* Be sure to restore caller's memory context */
	MemoryContextSwitchTo(resultcxt);

	return dblist;
}

/*
 * Process a database table-by-table
 *
 * Note that CHECK_FOR_INTERRUPTS is supposed to be used in certain spots in
 * order not to ignore shutdown commands for too long.
 */
static void
do_autovacuum(void)
{
	Relation	classRel;
	HeapTuple	tuple;
	TableScanDesc relScan;
	Form_pg_database dbForm;
	List	   *table_oids = NIL;
	List	   *orphan_oids = NIL;
	HASHCTL		ctl;
	HTAB	   *table_toast_map;
	ListCell   *volatile cell;
	BufferAccessStrategy bstrategy;
	ScanKeyData key;
	TupleDesc	pg_class_desc;
	int			effective_multixact_freeze_max_age;
	bool		did_vacuum = false;
	bool		found_concurrent_worker = false;
	int			i;

	/*
	 * StartTransactionCommand and CommitTransactionCommand will automatically
	 * switch to other contexts.  We need this one to keep the list of
	 * relations to vacuum/analyze across transactions.
	 */
	AutovacMemCxt = AllocSetContextCreate(TopMemoryContext,
										  "Autovacuum worker",
										  ALLOCSET_DEFAULT_SIZES);
	MemoryContextSwitchTo(AutovacMemCxt);

	/* Start a transaction so our commands have one to play into. */
	StartTransactionCommand();

	/*
	 * Compute the multixact age for which freezing is urgent.  This is
	 * normally autovacuum_multixact_freeze_max_age, but may be less if we are
	 * short of multixact member space.
	 */
	effective_multixact_freeze_max_age = MultiXactMemberFreezeThreshold();

	/*
	 * Find the pg_database entry and select the default freeze ages. We use
	 * zero in template and nonconnectable databases, else the system-wide
	 * default.
	 */
	tuple = SearchSysCache1(DATABASEOID, ObjectIdGetDatum(MyDatabaseId));
	if (!HeapTupleIsValid(tuple))
		elog(ERROR, "cache lookup failed for database %u", MyDatabaseId);
	dbForm = (Form_pg_database) GETSTRUCT(tuple);

	if (dbForm->datistemplate || !dbForm->datallowconn)
	{
		default_freeze_min_age = 0;
		default_freeze_table_age = 0;
		default_multixact_freeze_min_age = 0;
		default_multixact_freeze_table_age = 0;
	}
	else
	{
		default_freeze_min_age = vacuum_freeze_min_age;
		default_freeze_table_age = vacuum_freeze_table_age;
		default_multixact_freeze_min_age = vacuum_multixact_freeze_min_age;
		default_multixact_freeze_table_age = vacuum_multixact_freeze_table_age;
	}

	ReleaseSysCache(tuple);

	/* StartTransactionCommand changed elsewhere */
	MemoryContextSwitchTo(AutovacMemCxt);

	classRel = table_open(RelationRelationId, AccessShareLock);

	/* create a copy so we can use it after closing pg_class */
	pg_class_desc = CreateTupleDescCopy(RelationGetDescr(classRel));

	/* create hash table for toast <-> main relid mapping */
	ctl.keysize = sizeof(Oid);
	ctl.entrysize = sizeof(av_relation);

	table_toast_map = hash_create("TOAST to main relid map",
								  100,
								  &ctl,
								  HASH_ELEM | HASH_BLOBS);

	/*
	 * Scan pg_class to determine which tables to vacuum.
	 *
	 * We do this in two passes: on the first one we collect the list of plain
	 * relations and materialized views, and on the second one we collect
	 * TOAST tables. The reason for doing the second pass is that during it we
	 * want to use the main relation's pg_class.reloptions entry if the TOAST
	 * table does not have any, and we cannot obtain it unless we know
	 * beforehand what's the main table OID.
	 *
	 * We need to check TOAST tables separately because in cases with short,
	 * wide tables there might be proportionally much more activity in the
	 * TOAST table than in its parent.
	 */
	relScan = table_beginscan_catalog(classRel, 0, NULL);

	/*
	 * On the first pass, we collect main tables to vacuum, and also the main
	 * table relid to TOAST relid mapping.
	 */
	while ((tuple = heap_getnext(relScan, ForwardScanDirection)) != NULL)
	{
		Form_pg_class classForm = (Form_pg_class) GETSTRUCT(tuple);
		PgStat_StatTabEntry *tabentry;
		AutoVacOpts *relopts;
		Oid			relid;
		bool		dovacuum;
		bool		doanalyze;
		bool		wraparound;

		if (classForm->relkind != RELKIND_RELATION &&
			classForm->relkind != RELKIND_MATVIEW)
			continue;

		relid = classForm->oid;

		/*
		 * Check if it is a temp table (presumably, of some other backend's).
		 * We cannot safely process other backends' temp tables.
		 */
		if (classForm->relpersistence == RELPERSISTENCE_TEMP)
		{
			/*
			 * We just ignore it if the owning backend is still active and
			 * using the temporary schema.  Also, for safety, ignore it if the
			 * namespace doesn't exist or isn't a temp namespace after all.
			 */
			if (checkTempNamespaceStatus(classForm->relnamespace) == TEMP_NAMESPACE_IDLE)
			{
				/*
				 * The table seems to be orphaned -- although it might be that
				 * the owning backend has already deleted it and exited; our
				 * pg_class scan snapshot is not necessarily up-to-date
				 * anymore, so we could be looking at a committed-dead entry.
				 * Remember it so we can try to delete it later.
				 */
				orphan_oids = lappend_oid(orphan_oids, relid);
			}
			continue;
		}

		/* Fetch reloptions and the pgstat entry for this table */
		relopts = extract_autovac_opts(tuple, pg_class_desc);
		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
												  relid);

		/* Check if it needs vacuum or analyze */
		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
								  effective_multixact_freeze_max_age,
								  &dovacuum, &doanalyze, &wraparound);

		/* Relations that need work are added to table_oids */
		if (dovacuum || doanalyze)
			table_oids = lappend_oid(table_oids, relid);

		/*
		 * Remember TOAST associations for the second pass.  Note: we must do
		 * this whether or not the table is going to be vacuumed, because we
		 * don't automatically vacuum toast tables along the parent table.
		 */
		if (OidIsValid(classForm->reltoastrelid))
		{
			av_relation *hentry;
			bool		found;

			hentry = hash_search(table_toast_map,
								 &classForm->reltoastrelid,
								 HASH_ENTER, &found);

			if (!found)
			{
				/* hash_search already filled in the key */
				hentry->ar_relid = relid;
				hentry->ar_hasrelopts = false;
				if (relopts != NULL)
				{
					hentry->ar_hasrelopts = true;
					memcpy(&hentry->ar_reloptions, relopts,
						   sizeof(AutoVacOpts));
				}
			}
		}
	}

	table_endscan(relScan);

	/* second pass: check TOAST tables */
	ScanKeyInit(&key,
				Anum_pg_class_relkind,
				BTEqualStrategyNumber, F_CHAREQ,
				CharGetDatum(RELKIND_TOASTVALUE));

	relScan = table_beginscan_catalog(classRel, 1, &key);
	while ((tuple = heap_getnext(relScan, ForwardScanDirection)) != NULL)
	{
		Form_pg_class classForm = (Form_pg_class) GETSTRUCT(tuple);
		PgStat_StatTabEntry *tabentry;
		Oid			relid;
		AutoVacOpts *relopts = NULL;
		bool		dovacuum;
		bool		doanalyze;
		bool		wraparound;

		/*
		 * We cannot safely process other backends' temp tables, so skip 'em.
		 */
		if (classForm->relpersistence == RELPERSISTENCE_TEMP)
			continue;

		relid = classForm->oid;

		/*
		 * fetch reloptions -- if this toast table does not have them, try the
		 * main rel
		 */
		relopts = extract_autovac_opts(tuple, pg_class_desc);
		if (relopts == NULL)
		{
			av_relation *hentry;
			bool		found;

			hentry = hash_search(table_toast_map, &relid, HASH_FIND, &found);
			if (found && hentry->ar_hasrelopts)
				relopts = &hentry->ar_reloptions;
		}

		/* Fetch the pgstat entry for this table */
		tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
												  relid);

		relation_needs_vacanalyze(relid, relopts, classForm, tabentry,
								  effective_multixact_freeze_max_age,
								  &dovacuum, &doanalyze, &wraparound);

		/* ignore analyze for toast tables */
		if (dovacuum)
			table_oids = lappend_oid(table_oids, relid);
	}

	table_endscan(relScan);
	table_close(classRel, AccessShareLock);

	/*
	 * Recheck orphan temporary tables, and if they still seem orphaned, drop
	 * them.  We'll eat a transaction per dropped table, which might seem
	 * excessive, but we should only need to do anything as a result of a
	 * previous backend crash, so this should not happen often enough to
	 * justify "optimizing".  Using separate transactions ensures that we
	 * don't bloat the lock table if there are many temp tables to be dropped,
	 * and it ensures that we don't lose work if a deletion attempt fails.
	 */
	foreach(cell, orphan_oids)
	{
		Oid			relid = lfirst_oid(cell);
		Form_pg_class classForm;
		ObjectAddress object;

		/*
		 * Check for user-requested abort.
		 */
		CHECK_FOR_INTERRUPTS();

		/*
		 * Try to lock the table.  If we can't get the lock immediately,
		 * somebody else is using (or dropping) the table, so it's not our
		 * concern anymore.  Having the lock prevents race conditions below.
		 */
		if (!ConditionalLockRelationOid(relid, AccessExclusiveLock))
			continue;

		/*
		 * Re-fetch the pg_class tuple and re-check whether it still seems to
		 * be an orphaned temp table.  If it's not there or no longer the same
		 * relation, ignore it.
		 */
		tuple = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
		if (!HeapTupleIsValid(tuple))
		{
			/* be sure to drop useless lock so we don't bloat lock table */
			UnlockRelationOid(relid, AccessExclusiveLock);
			continue;
		}
		classForm = (Form_pg_class) GETSTRUCT(tuple);

		/*
		 * Make all the same tests made in the loop above.  In event of OID
		 * counter wraparound, the pg_class entry we have now might be
		 * completely unrelated to the one we saw before.
		 */
		if (!((classForm->relkind == RELKIND_RELATION ||
			   classForm->relkind == RELKIND_MATVIEW) &&
			  classForm->relpersistence == RELPERSISTENCE_TEMP))
		{
			UnlockRelationOid(relid, AccessExclusiveLock);
			continue;
		}

		if (checkTempNamespaceStatus(classForm->relnamespace) != TEMP_NAMESPACE_IDLE)
		{
			UnlockRelationOid(relid, AccessExclusiveLock);
			continue;
		}

		/* OK, let's delete it */
		ereport(LOG,
				(errmsg("autovacuum: dropping orphan temp table \"%s.%s.%s\"",
						get_database_name(MyDatabaseId),
						get_namespace_name(classForm->relnamespace),
						NameStr(classForm->relname))));

		object.classId = RelationRelationId;
		object.objectId = relid;
		object.objectSubId = 0;
		performDeletion(&object, DROP_CASCADE,
						PERFORM_DELETION_INTERNAL |
						PERFORM_DELETION_QUIETLY |
						PERFORM_DELETION_SKIP_EXTENSIONS);

		/*
		 * To commit the deletion, end current transaction and start a new
		 * one.  Note this also releases the lock we took.
		 */
		CommitTransactionCommand();
		StartTransactionCommand();

		/* StartTransactionCommand changed current memory context */
		MemoryContextSwitchTo(AutovacMemCxt);
	}

	/*
	 * Create a buffer access strategy object for VACUUM to use.  We want to
	 * use the same one across all the vacuum operations we perform, since the
	 * point is for VACUUM not to blow out the shared cache.
	 */
	bstrategy = GetAccessStrategy(BAS_VACUUM);

	/*
	 * create a memory context to act as fake PortalContext, so that the
	 * contexts created in the vacuum code are cleaned up for each table.
	 */
	PortalContext = AllocSetContextCreate(AutovacMemCxt,
										  "Autovacuum Portal",
										  ALLOCSET_DEFAULT_SIZES);

	/*
	 * Perform operations on collected tables.
	 */
	foreach(cell, table_oids)
	{
		Oid			relid = lfirst_oid(cell);
		HeapTuple	classTup;
		autovac_table *tab;
		bool		isshared;
		bool		skipit;
		double		stdVacuumCostDelay;
		int			stdVacuumCostLimit;
		dlist_iter	iter;

		CHECK_FOR_INTERRUPTS();

		/*
		 * Check for config changes before processing each collected table.
		 */
		if (ConfigReloadPending)
		{
			ConfigReloadPending = false;
			ProcessConfigFile(PGC_SIGHUP);

			/*
			 * You might be tempted to bail out if we see autovacuum is now
			 * disabled.  Must resist that temptation -- this might be a
			 * for-wraparound emergency worker, in which case that would be
			 * entirely inappropriate.
			 */
		}

		/*
		 * Find out whether the table is shared or not.  (It's slightly
		 * annoying to fetch the syscache entry just for this, but in typical
		 * cases it adds little cost because table_recheck_autovac would
		 * refetch the entry anyway.  We could buy that back by copying the
		 * tuple here and passing it to table_recheck_autovac, but that
		 * increases the odds of that function working with stale data.)
		 */
		classTup = SearchSysCache1(RELOID, ObjectIdGetDatum(relid));
		if (!HeapTupleIsValid(classTup))
			continue;			/* somebody deleted the rel, forget it */
		isshared = ((Form_pg_class) GETSTRUCT(classTup))->relisshared;
		ReleaseSysCache(classTup);

		/*
		 * Hold schedule lock from here until we've claimed the table.  We
		 * also need the AutovacuumLock to walk the worker array, but that one
		 * can just be a shared lock.
		 */
		LWLockAcquire(AutovacuumScheduleLock, LW_EXCLUSIVE);
		LWLockAcquire(AutovacuumLock, LW_SHARED);

		/*
		 * Check whether the table is being vacuumed concurrently by another
		 * worker.
		 */
		skipit = false;
		dlist_foreach(iter, &AutoVacuumShmem->av_runningWorkers)
		{
			WorkerInfo	worker = dlist_container(WorkerInfoData, wi_links, iter.cur);

			/* ignore myself */
			if (worker == MyWorkerInfo)
				continue;

			/* ignore workers in other databases (unless table is shared) */
			if (!worker->wi_sharedrel && worker->wi_dboid != MyDatabaseId)
				continue;

			if (worker->wi_tableoid == relid)
			{
				skipit = true;
				found_concurrent_worker = true;
				break;
			}
		}
		LWLockRelease(AutovacuumLock);
		if (skipit)
		{
			LWLockRelease(AutovacuumScheduleLock);
			continue;
		}

		/*
		 * Store the table's OID in shared memory before releasing the
		 * schedule lock, so that other workers don't try to vacuum it
		 * concurrently.  (We claim it here so as not to hold
		 * AutovacuumScheduleLock while rechecking the stats.)
		 */
		MyWorkerInfo->wi_tableoid = relid;
		MyWorkerInfo->wi_sharedrel = isshared;
		LWLockRelease(AutovacuumScheduleLock);

		/*
		 * Check whether pgstat data still says we need to vacuum this table.
		 * It could have changed if something else processed the table while
		 * we weren't looking. This doesn't entirely close the race condition,
		 * but it is very small.
		 */
		MemoryContextSwitchTo(AutovacMemCxt);
		tab = table_recheck_autovac(relid, table_toast_map, pg_class_desc,
									effective_multixact_freeze_max_age);
		if (tab == NULL)
		{
			/* someone else vacuumed the table, or it went away */
			LWLockAcquire(AutovacuumScheduleLock, LW_EXCLUSIVE);
			MyWorkerInfo->wi_tableoid = InvalidOid;
			MyWorkerInfo->wi_sharedrel = false;
			LWLockRelease(AutovacuumScheduleLock);
			continue;
		}

		/*
		 * Remember the prevailing values of the vacuum cost GUCs.  We have to
		 * restore these at the bottom of the loop, else we'll compute wrong
		 * values in the next iteration of autovac_balance_cost().
		 */
		stdVacuumCostDelay = VacuumCostDelay;
		stdVacuumCostLimit = VacuumCostLimit;

		/* Must hold AutovacuumLock while mucking with cost balance info */
		LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);

		/* advertise my cost delay parameters for the balancing algorithm */
		MyWorkerInfo->wi_dobalance = tab->at_dobalance;
		MyWorkerInfo->wi_cost_delay = tab->at_vacuum_cost_delay;
		MyWorkerInfo->wi_cost_limit = tab->at_vacuum_cost_limit;
		MyWorkerInfo->wi_cost_limit_base = tab->at_vacuum_cost_limit;

		/* do a balance */
		autovac_balance_cost();

		/* set the active cost parameters from the result of that */
		AutoVacuumUpdateDelay();

		/* done */
		LWLockRelease(AutovacuumLock);

		/* clean up memory before each iteration */
		MemoryContextResetAndDeleteChildren(PortalContext);

		/*
		 * Save the relation name for a possible error message, to avoid a
		 * catalog lookup in case of an error.  If any of these return NULL,
		 * then the relation has been dropped since last we checked; skip it.
		 * Note: they must live in a long-lived memory context because we call
		 * vacuum and analyze in different transactions.
		 */

		tab->at_relname = get_rel_name(tab->at_relid);
		tab->at_nspname = get_namespace_name(get_rel_namespace(tab->at_relid));
		tab->at_datname = get_database_name(MyDatabaseId);
		if (!tab->at_relname || !tab->at_nspname || !tab->at_datname)
			goto deleted;

		/*
		 * We will abort vacuuming the current table if something errors out,
		 * and continue with the next one in schedule; in particular, this
		 * happens if we are interrupted with SIGINT.
		 */
		PG_TRY();
		{
			/* Use PortalContext for any per-table allocations */
			MemoryContextSwitchTo(PortalContext);

			/* have at it */
			autovacuum_do_vac_analyze(tab, bstrategy);

			/*
			 * Clear a possible query-cancel signal, to avoid a late reaction
			 * to an automatically-sent signal because of vacuuming the
			 * current table (we're done with it, so it would make no sense to
			 * cancel at this point.)
			 */
			QueryCancelPending = false;
		}
		PG_CATCH();
		{
			/*
			 * Abort the transaction, start a new one, and proceed with the
			 * next table in our list.
			 */
			HOLD_INTERRUPTS();
			if (tab->at_params.options & VACOPT_VACUUM)
				errcontext("automatic vacuum of table \"%s.%s.%s\"",
						   tab->at_datname, tab->at_nspname, tab->at_relname);
			else
				errcontext("automatic analyze of table \"%s.%s.%s\"",
						   tab->at_datname, tab->at_nspname, tab->at_relname);
			EmitErrorReport();

			/* this resets ProcGlobal->statusFlags[i] too */
			AbortOutOfAnyTransaction();
			FlushErrorState();
			MemoryContextResetAndDeleteChildren(PortalContext);

			/* restart our transaction for the following operations */
			StartTransactionCommand();
			RESUME_INTERRUPTS();
		}
		PG_END_TRY();

		/* Make sure we're back in AutovacMemCxt */
		MemoryContextSwitchTo(AutovacMemCxt);

		did_vacuum = true;

		/* ProcGlobal->statusFlags[i] are reset at the next end of xact */

		/* be tidy */
deleted:
		if (tab->at_datname != NULL)
			pfree(tab->at_datname);
		if (tab->at_nspname != NULL)
			pfree(tab->at_nspname);
		if (tab->at_relname != NULL)
			pfree(tab->at_relname);
		pfree(tab);

		/*
		 * Remove my info from shared memory.  We could, but intentionally
		 * don't, clear wi_cost_limit and friends --- this is on the
		 * assumption that we probably have more to do with similar cost
		 * settings, so we don't want to give up our share of I/O for a very
		 * short interval and thereby thrash the global balance.
		 */
		LWLockAcquire(AutovacuumScheduleLock, LW_EXCLUSIVE);
		MyWorkerInfo->wi_tableoid = InvalidOid;
		MyWorkerInfo->wi_sharedrel = false;
		LWLockRelease(AutovacuumScheduleLock);

		/* restore vacuum cost GUCs for the next iteration */
		VacuumCostDelay = stdVacuumCostDelay;
		VacuumCostLimit = stdVacuumCostLimit;
	}

	/*
	 * Perform additional work items, as requested by backends.
	 */
	LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);
	for (i = 0; i < NUM_WORKITEMS; i++)
	{
		AutoVacuumWorkItem *workitem = &AutoVacuumShmem->av_workItems[i];

		if (!workitem->avw_used)
			continue;
		if (workitem->avw_active)
			continue;
		if (workitem->avw_database != MyDatabaseId)
			continue;

		/* claim this one, and release lock while performing it */
		workitem->avw_active = true;
		LWLockRelease(AutovacuumLock);

		perform_work_item(workitem);

		/*
		 * Check for config changes before acquiring lock for further jobs.
		 */
		CHECK_FOR_INTERRUPTS();
		if (ConfigReloadPending)
		{
			ConfigReloadPending = false;
			ProcessConfigFile(PGC_SIGHUP);
		}

		LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);

		/* and mark it done */
		workitem->avw_active = false;
		workitem->avw_used = false;
	}
	LWLockRelease(AutovacuumLock);

	/*
	 * We leak table_toast_map here (among other things), but since we're
	 * going away soon, it's not a problem.
	 */

	/*
	 * Update pg_database.datfrozenxid, and truncate pg_xact if possible. We
	 * only need to do this once, not after each table.
	 *
	 * Even if we didn't vacuum anything, it may still be important to do
	 * this, because one indirect effect of vac_update_datfrozenxid() is to
	 * update ShmemVariableCache->xidVacLimit.  That might need to be done
	 * even if we haven't vacuumed anything, because relations with older
	 * relfrozenxid values or other databases with older datfrozenxid values
	 * might have been dropped, allowing xidVacLimit to advance.
	 *
	 * However, it's also important not to do this blindly in all cases,
	 * because when autovacuum=off this will restart the autovacuum launcher.
	 * If we're not careful, an infinite loop can result, where workers find
	 * no work to do and restart the launcher, which starts another worker in
	 * the same database that finds no work to do.  To prevent that, we skip
	 * this if (1) we found no work to do and (2) we skipped at least one
	 * table due to concurrent autovacuum activity.  In that case, the other
	 * worker has already done it, or will do so when it finishes.
	 */
	if (did_vacuum || !found_concurrent_worker)
		vac_update_datfrozenxid();

	/* Finally close out the last transaction. */
	CommitTransactionCommand();
}

/*
 * Execute a previously registered work item.
 */
static void
perform_work_item(AutoVacuumWorkItem *workitem)
{
	char	   *cur_datname = NULL;
	char	   *cur_nspname = NULL;
	char	   *cur_relname = NULL;

	/*
	 * Note we do not store table info in MyWorkerInfo, since this is not
	 * vacuuming proper.
	 */

	/*
	 * Save the relation name for a possible error message, to avoid a catalog
	 * lookup in case of an error.  If any of these return NULL, then the
	 * relation has been dropped since last we checked; skip it.
	 */
	Assert(CurrentMemoryContext == AutovacMemCxt);

	cur_relname = get_rel_name(workitem->avw_relation);
	cur_nspname = get_namespace_name(get_rel_namespace(workitem->avw_relation));
	cur_datname = get_database_name(MyDatabaseId);
	if (!cur_relname || !cur_nspname || !cur_datname)
		goto deleted2;

	autovac_report_workitem(workitem, cur_nspname, cur_relname);

	/* clean up memory before each work item */
	MemoryContextResetAndDeleteChildren(PortalContext);

	/*
	 * We will abort the current work item if something errors out, and
	 * continue with the next one; in particular, this happens if we are
	 * interrupted with SIGINT.  Note that this means that the work item list
	 * can be lossy.
	 */
	PG_TRY();
	{
		/* Use PortalContext for any per-work-item allocations */
		MemoryContextSwitchTo(PortalContext);

		/* have at it */
		switch (workitem->avw_type)
		{
			case AVW_BRINSummarizeRange:
				DirectFunctionCall2(brin_summarize_range,
									ObjectIdGetDatum(workitem->avw_relation),
									Int64GetDatum((int64) workitem->avw_blockNumber));
				break;
			default:
				elog(WARNING, "unrecognized work item found: type %d",
					 workitem->avw_type);
				break;
		}

		/*
		 * Clear a possible query-cancel signal, to avoid a late reaction to
		 * an automatically-sent signal because of vacuuming the current table
		 * (we're done with it, so it would make no sense to cancel at this
		 * point.)
		 */
		QueryCancelPending = false;
	}
	PG_CATCH();
	{
		/*
		 * Abort the transaction, start a new one, and proceed with the next
		 * table in our list.
		 */
		HOLD_INTERRUPTS();
		errcontext("processing work entry for relation \"%s.%s.%s\"",
				   cur_datname, cur_nspname, cur_relname);
		EmitErrorReport();

		/* this resets ProcGlobal->statusFlags[i] too */
		AbortOutOfAnyTransaction();
		FlushErrorState();
		MemoryContextResetAndDeleteChildren(PortalContext);

		/* restart our transaction for the following operations */
		StartTransactionCommand();
		RESUME_INTERRUPTS();
	}
	PG_END_TRY();

	/* Make sure we're back in AutovacMemCxt */
	MemoryContextSwitchTo(AutovacMemCxt);

	/* We intentionally do not set did_vacuum here */

	/* be tidy */
deleted2:
	if (cur_datname)
		pfree(cur_datname);
	if (cur_nspname)
		pfree(cur_nspname);
	if (cur_relname)
		pfree(cur_relname);
}

/*
 * extract_autovac_opts
 *
 * Given a relation's pg_class tuple, return the AutoVacOpts portion of
 * reloptions, if set; otherwise, return NULL.
 *
 * Note: callers do not have a relation lock on the table at this point,
 * so the table could have been dropped, and its catalog rows gone, after
 * we acquired the pg_class row.  If pg_class had a TOAST table, this would
 * be a risk; fortunately, it doesn't.
 */
static AutoVacOpts *
extract_autovac_opts(HeapTuple tup, TupleDesc pg_class_desc)
{
	bytea	   *relopts;
	AutoVacOpts *av;

	Assert(((Form_pg_class) GETSTRUCT(tup))->relkind == RELKIND_RELATION ||
		   ((Form_pg_class) GETSTRUCT(tup))->relkind == RELKIND_MATVIEW ||
		   ((Form_pg_class) GETSTRUCT(tup))->relkind == RELKIND_TOASTVALUE);

	relopts = extractRelOptions(tup, pg_class_desc, NULL);
	if (relopts == NULL)
		return NULL;

	av = palloc(sizeof(AutoVacOpts));
	memcpy(av, &(((StdRdOptions *) relopts)->autovacuum), sizeof(AutoVacOpts));
	pfree(relopts);

	return av;
}


/*
 * table_recheck_autovac
 *
 * Recheck whether a table still needs vacuum or analyze.  Return value is a
 * valid autovac_table pointer if it does, NULL otherwise.
 *
 * Note that the returned autovac_table does not have the name fields set.
 */
static autovac_table *
table_recheck_autovac(Oid relid, HTAB *table_toast_map,
					  TupleDesc pg_class_desc,
					  int effective_multixact_freeze_max_age)
{
	Form_pg_class classForm;
	HeapTuple	classTup;
	bool		dovacuum;
	bool		doanalyze;
	autovac_table *tab = NULL;
	bool		wraparound;
	AutoVacOpts *avopts;

	/* fetch the relation's relcache entry */
	classTup = SearchSysCacheCopy1(RELOID, ObjectIdGetDatum(relid));
	if (!HeapTupleIsValid(classTup))
		return NULL;
	classForm = (Form_pg_class) GETSTRUCT(classTup);

	/*
	 * Get the applicable reloptions.  If it is a TOAST table, try to get the
	 * main table reloptions if the toast table itself doesn't have.
	 */
	avopts = extract_autovac_opts(classTup, pg_class_desc);
	if (classForm->relkind == RELKIND_TOASTVALUE &&
		avopts == NULL && table_toast_map != NULL)
	{
		av_relation *hentry;
		bool		found;

		hentry = hash_search(table_toast_map, &relid, HASH_FIND, &found);
		if (found && hentry->ar_hasrelopts)
			avopts = &hentry->ar_reloptions;
	}

	recheck_relation_needs_vacanalyze(relid, avopts, classForm,
									  effective_multixact_freeze_max_age,
									  &dovacuum, &doanalyze, &wraparound);

	/* OK, it needs something done */
	if (doanalyze || dovacuum)
	{
		int			freeze_min_age;
		int			freeze_table_age;
		int			multixact_freeze_min_age;
		int			multixact_freeze_table_age;
		int			vac_cost_limit;
		double		vac_cost_delay;
		int			log_min_duration;

		/*
		 * Calculate the vacuum cost parameters and the freeze ages.  If there
		 * are options set in pg_class.reloptions, use them; in the case of a
		 * toast table, try the main table too.  Otherwise use the GUC
		 * defaults, autovacuum's own first and plain vacuum second.
		 */

		/* -1 in autovac setting means use plain vacuum_cost_delay */
		vac_cost_delay = (avopts && avopts->vacuum_cost_delay >= 0)
			? avopts->vacuum_cost_delay
			: (autovacuum_vac_cost_delay >= 0)
			? autovacuum_vac_cost_delay
			: VacuumCostDelay;

		/* 0 or -1 in autovac setting means use plain vacuum_cost_limit */
		vac_cost_limit = (avopts && avopts->vacuum_cost_limit > 0)
			? avopts->vacuum_cost_limit
			: (autovacuum_vac_cost_limit > 0)
			? autovacuum_vac_cost_limit
			: VacuumCostLimit;

		/* -1 in autovac setting means use log_autovacuum_min_duration */
		log_min_duration = (avopts && avopts->log_min_duration >= 0)
			? avopts->log_min_duration
			: Log_autovacuum_min_duration;

		/* these do not have autovacuum-specific settings */
		freeze_min_age = (avopts && avopts->freeze_min_age >= 0)
			? avopts->freeze_min_age
			: default_freeze_min_age;

		freeze_table_age = (avopts && avopts->freeze_table_age >= 0)
			? avopts->freeze_table_age
			: default_freeze_table_age;

		multixact_freeze_min_age = (avopts &&
									avopts->multixact_freeze_min_age >= 0)
			? avopts->multixact_freeze_min_age
			: default_multixact_freeze_min_age;

		multixact_freeze_table_age = (avopts &&
									  avopts->multixact_freeze_table_age >= 0)
			? avopts->multixact_freeze_table_age
			: default_multixact_freeze_table_age;

		tab = palloc(sizeof(autovac_table));
		tab->at_relid = relid;
		tab->at_sharedrel = classForm->relisshared;

		/* Note that this skips toast relations */
		tab->at_params.options = (dovacuum ? VACOPT_VACUUM : 0) |
			(doanalyze ? VACOPT_ANALYZE : 0) |
			(!wraparound ? VACOPT_SKIP_LOCKED : 0);

		/*
		 * index_cleanup and truncate are unspecified at first in autovacuum.
		 * They will be filled in with usable values using their reloptions
		 * (or reloption defaults) later.
		 */
		tab->at_params.index_cleanup = VACOPTVALUE_UNSPECIFIED;
		tab->at_params.truncate = VACOPTVALUE_UNSPECIFIED;
		/* As of now, we don't support parallel vacuum for autovacuum */
		tab->at_params.nworkers = -1;
		tab->at_params.freeze_min_age = freeze_min_age;
		tab->at_params.freeze_table_age = freeze_table_age;
		tab->at_params.multixact_freeze_min_age = multixact_freeze_min_age;
		tab->at_params.multixact_freeze_table_age = multixact_freeze_table_age;
		tab->at_params.is_wraparound = wraparound;
		tab->at_params.log_min_duration = log_min_duration;
		tab->at_vacuum_cost_limit = vac_cost_limit;
		tab->at_vacuum_cost_delay = vac_cost_delay;
		tab->at_relname = NULL;
		tab->at_nspname = NULL;
		tab->at_datname = NULL;

		/*
		 * If any of the cost delay parameters has been set individually for
		 * this table, disable the balancing algorithm.
		 */
		tab->at_dobalance =
			!(avopts && (avopts->vacuum_cost_limit > 0 ||
						 avopts->vacuum_cost_delay >= 0));
	}

	heap_freetuple(classTup);
	return tab;
}

/*
 * recheck_relation_needs_vacanalyze
 *
 * Subroutine for table_recheck_autovac.
 *
 * Fetch the pgstat of a relation and recheck whether a relation
 * needs to be vacuumed or analyzed.
 */
static void
recheck_relation_needs_vacanalyze(Oid relid,
								  AutoVacOpts *avopts,
								  Form_pg_class classForm,
								  int effective_multixact_freeze_max_age,
								  bool *dovacuum,
								  bool *doanalyze,
								  bool *wraparound)
{
	PgStat_StatTabEntry *tabentry;

	/* fetch the pgstat table entry */
	tabentry = pgstat_fetch_stat_tabentry_ext(classForm->relisshared,
											  relid);

	relation_needs_vacanalyze(relid, avopts, classForm, tabentry,
							  effective_multixact_freeze_max_age,
							  dovacuum, doanalyze, wraparound);

	/* ignore ANALYZE for toast tables */
	if (classForm->relkind == RELKIND_TOASTVALUE)
		*doanalyze = false;
}

/*
 * relation_needs_vacanalyze
 *
 * Check whether a relation needs to be vacuumed or analyzed; return each into
 * "dovacuum" and "doanalyze", respectively.  Also return whether the vacuum is
 * being forced because of Xid or multixact wraparound.
 *
 * relopts is a pointer to the AutoVacOpts options (either for itself in the
 * case of a plain table, or for either itself or its parent table in the case
 * of a TOAST table), NULL if none; tabentry is the pgstats entry, which can be
 * NULL.
 *
 * A table needs to be vacuumed if the number of dead tuples exceeds a
 * threshold.  This threshold is calculated as
 *
 * threshold = vac_base_thresh + vac_scale_factor * reltuples
 *
 * For analyze, the analysis done is that the number of tuples inserted,
 * deleted and updated since the last analyze exceeds a threshold calculated
 * in the same fashion as above.  Note that the cumulative stats system stores
 * the number of tuples (both live and dead) that there were as of the last
 * analyze.  This is asymmetric to the VACUUM case.
 *
 * We also force vacuum if the table's relfrozenxid is more than freeze_max_age
 * transactions back, and if its relminmxid is more than
 * multixact_freeze_max_age multixacts back.
 *
 * A table whose autovacuum_enabled option is false is
 * automatically skipped (unless we have to vacuum it due to freeze_max_age).
 * Thus autovacuum can be disabled for specific tables. Also, when the cumulative
 * stats system does not have data about a table, it will be skipped.
 *
 * A table whose vac_base_thresh value is < 0 takes the base value from the
 * autovacuum_vacuum_threshold GUC variable.  Similarly, a vac_scale_factor
 * value < 0 is substituted with the value of
 * autovacuum_vacuum_scale_factor GUC variable.  Ditto for analyze.
 */
static void
relation_needs_vacanalyze(Oid relid,
						  AutoVacOpts *relopts,
						  Form_pg_class classForm,
						  PgStat_StatTabEntry *tabentry,
						  int effective_multixact_freeze_max_age,
 /* output params below */
						  bool *dovacuum,
						  bool *doanalyze,
						  bool *wraparound)
{
	bool		force_vacuum;
	bool		av_enabled;
	float4		reltuples;		/* pg_class.reltuples */

	/* constants from reloptions or GUC variables */
	int			vac_base_thresh,
				vac_ins_base_thresh,
				anl_base_thresh;
	float4		vac_scale_factor,
				vac_ins_scale_factor,
				anl_scale_factor;

	/* thresholds calculated from above constants */
	float4		vacthresh,
				vacinsthresh,
				anlthresh;

	/* number of vacuum (resp. analyze) tuples at this time */
	float4		vactuples,
				instuples,
				anltuples;

	/* freeze parameters */
	int			freeze_max_age;
	int			multixact_freeze_max_age;
	TransactionId xidForceLimit;
	MultiXactId multiForceLimit;

	AssertArg(classForm != NULL);
	AssertArg(OidIsValid(relid));

	/*
	 * Determine vacuum/analyze equation parameters.  We have two possible
	 * sources: the passed reloptions (which could be a main table or a toast
	 * table), or the autovacuum GUC variables.
	 */

	/* -1 in autovac setting means use plain vacuum_scale_factor */
	vac_scale_factor = (relopts && relopts->vacuum_scale_factor >= 0)
		? relopts->vacuum_scale_factor
		: autovacuum_vac_scale;

	vac_base_thresh = (relopts && relopts->vacuum_threshold >= 0)
		? relopts->vacuum_threshold
		: autovacuum_vac_thresh;

	vac_ins_scale_factor = (relopts && relopts->vacuum_ins_scale_factor >= 0)
		? relopts->vacuum_ins_scale_factor
		: autovacuum_vac_ins_scale;

	/* -1 is used to disable insert vacuums */
	vac_ins_base_thresh = (relopts && relopts->vacuum_ins_threshold >= -1)
		? relopts->vacuum_ins_threshold
		: autovacuum_vac_ins_thresh;

	anl_scale_factor = (relopts && relopts->analyze_scale_factor >= 0)
		? relopts->analyze_scale_factor
		: autovacuum_anl_scale;

	anl_base_thresh = (relopts && relopts->analyze_threshold >= 0)
		? relopts->analyze_threshold
		: autovacuum_anl_thresh;

	freeze_max_age = (relopts && relopts->freeze_max_age >= 0)
		? Min(relopts->freeze_max_age, autovacuum_freeze_max_age)
		: autovacuum_freeze_max_age;

	multixact_freeze_max_age = (relopts && relopts->multixact_freeze_max_age >= 0)
		? Min(relopts->multixact_freeze_max_age, effective_multixact_freeze_max_age)
		: effective_multixact_freeze_max_age;

	av_enabled = (relopts ? relopts->enabled : true);

	/* Force vacuum if table is at risk of wraparound */
	xidForceLimit = recentXid - freeze_max_age;
	if (xidForceLimit < FirstNormalTransactionId)
		xidForceLimit -= FirstNormalTransactionId;
	force_vacuum = (TransactionIdIsNormal(classForm->relfrozenxid) &&
					TransactionIdPrecedes(classForm->relfrozenxid,
										  xidForceLimit));
	if (!force_vacuum)
	{
		multiForceLimit = recentMulti - multixact_freeze_max_age;
		if (multiForceLimit < FirstMultiXactId)
			multiForceLimit -= FirstMultiXactId;
		force_vacuum = MultiXactIdIsValid(classForm->relminmxid) &&
			MultiXactIdPrecedes(classForm->relminmxid, multiForceLimit);
	}
	*wraparound = force_vacuum;

	/* User disabled it in pg_class.reloptions?  (But ignore if at risk) */
	if (!av_enabled && !force_vacuum)
	{
		*doanalyze = false;
		*dovacuum = false;
		return;
	}

	/*
	 * If we found stats for the table, and autovacuum is currently enabled,
	 * make a threshold-based decision whether to vacuum and/or analyze.  If
	 * autovacuum is currently disabled, we must be here for anti-wraparound
	 * vacuuming only, so don't vacuum (or analyze) anything that's not being
	 * forced.
	 */
	if (PointerIsValid(tabentry) && AutoVacuumingActive())
	{
		reltuples = classForm->reltuples;
		vactuples = tabentry->n_dead_tuples;
		instuples = tabentry->inserts_since_vacuum;
		anltuples = tabentry->changes_since_analyze;

		/* If the table hasn't yet been vacuumed, take reltuples as zero */
		if (reltuples < 0)
			reltuples = 0;

		vacthresh = (float4) vac_base_thresh + vac_scale_factor * reltuples;
		vacinsthresh = (float4) vac_ins_base_thresh + vac_ins_scale_factor * reltuples;
		anlthresh = (float4) anl_base_thresh + anl_scale_factor * reltuples;

		/*
		 * Note that we don't need to take special consideration for stat
		 * reset, because if that happens, the last vacuum and analyze counts
		 * will be reset too.
		 */
		if (vac_ins_base_thresh >= 0)
			elog(DEBUG3, "%s: vac: %.0f (threshold %.0f), ins: %.0f (threshold %.0f), anl: %.0f (threshold %.0f)",
				 NameStr(classForm->relname),
				 vactuples, vacthresh, instuples, vacinsthresh, anltuples, anlthresh);
		else
			elog(DEBUG3, "%s: vac: %.0f (threshold %.0f), ins: (disabled), anl: %.0f (threshold %.0f)",
				 NameStr(classForm->relname),
				 vactuples, vacthresh, anltuples, anlthresh);

		/* Determine if this table needs vacuum or analyze. */
		*dovacuum = force_vacuum || (vactuples > vacthresh) ||
			(vac_ins_base_thresh >= 0 && instuples > vacinsthresh);
		*doanalyze = (anltuples > anlthresh);
	}
	else
	{
		/*
		 * Skip a table not found in stat hash, unless we have to force vacuum
		 * for anti-wrap purposes.  If it's not acted upon, there's no need to
		 * vacuum it.
		 */
		*dovacuum = force_vacuum;
		*doanalyze = false;
	}

	/* ANALYZE refuses to work with pg_statistic */
	if (relid == StatisticRelationId)
		*doanalyze = false;
}

/*
 * autovacuum_do_vac_analyze
 *		Vacuum and/or analyze the specified table
 */
static void
autovacuum_do_vac_analyze(autovac_table *tab, BufferAccessStrategy bstrategy)
{
	RangeVar   *rangevar;
	VacuumRelation *rel;
	List	   *rel_list;

	/* Let pgstat know what we're doing */
	autovac_report_activity(tab);

	/* Set up one VacuumRelation target, identified by OID, for vacuum() */
	rangevar = makeRangeVar(tab->at_nspname, tab->at_relname, -1);
	rel = makeVacuumRelation(rangevar, tab->at_relid, NIL);
	rel_list = list_make1(rel);

	vacuum(rel_list, &tab->at_params, bstrategy, true);
}

/*
 * autovac_report_activity
 *		Report to pgstat what autovacuum is doing
 *
 * We send a SQL string corresponding to what the user would see if the
 * equivalent command was to be issued manually.
 *
 * Note we assume that we are going to report the next command as soon as we're
 * done with the current one, and exit right after the last one, so we don't
 * bother to report "<IDLE>" or some such.
 */
static void
autovac_report_activity(autovac_table *tab)
{
#define MAX_AUTOVAC_ACTIV_LEN (NAMEDATALEN * 2 + 56)
	char		activity[MAX_AUTOVAC_ACTIV_LEN];
	int			len;

	/* Report the command and possible options */
	if (tab->at_params.options & VACOPT_VACUUM)
		snprintf(activity, MAX_AUTOVAC_ACTIV_LEN,
				 "autovacuum: VACUUM%s",
				 tab->at_params.options & VACOPT_ANALYZE ? " ANALYZE" : "");
	else
		snprintf(activity, MAX_AUTOVAC_ACTIV_LEN,
				 "autovacuum: ANALYZE");

	/*
	 * Report the qualified name of the relation.
	 */
	len = strlen(activity);

	snprintf(activity + len, MAX_AUTOVAC_ACTIV_LEN - len,
			 " %s.%s%s", tab->at_nspname, tab->at_relname,
			 tab->at_params.is_wraparound ? " (to prevent wraparound)" : "");

	/* Set statement_timestamp() to current time for pg_stat_activity */
	SetCurrentStatementStartTimestamp();

	pgstat_report_activity(STATE_RUNNING, activity);
}

/*
 * autovac_report_workitem
 *		Report to pgstat that autovacuum is processing a work item
 */
static void
autovac_report_workitem(AutoVacuumWorkItem *workitem,
						const char *nspname, const char *relname)
{
	char		activity[MAX_AUTOVAC_ACTIV_LEN + 12 + 2];
	char		blk[12 + 2];
	int			len;

	switch (workitem->avw_type)
	{
		case AVW_BRINSummarizeRange:
			snprintf(activity, MAX_AUTOVAC_ACTIV_LEN,
					 "autovacuum: BRIN summarize");
			break;
	}

	/*
	 * Report the qualified name of the relation, and the block number if any
	 */
	len = strlen(activity);

	if (BlockNumberIsValid(workitem->avw_blockNumber))
		snprintf(blk, sizeof(blk), " %u", workitem->avw_blockNumber);
	else
		blk[0] = '\0';

	snprintf(activity + len, MAX_AUTOVAC_ACTIV_LEN - len,
			 " %s.%s%s", nspname, relname, blk);

	/* Set statement_timestamp() to current time for pg_stat_activity */
	SetCurrentStatementStartTimestamp();

	pgstat_report_activity(STATE_RUNNING, activity);
}

/*
 * AutoVacuumingActive
 *		Check GUC vars and report whether the autovacuum process should be
 *		running.
 */
bool
AutoVacuumingActive(void)
{
	if (!autovacuum_start_daemon || !pgstat_track_counts)
		return false;
	return true;
}

/*
 * Request one work item to the next autovacuum run processing our database.
 * Return false if the request can't be recorded.
 */
bool
AutoVacuumRequestWork(AutoVacuumWorkItemType type, Oid relationId,
					  BlockNumber blkno)
{
	int			i;
	bool		result = false;

	LWLockAcquire(AutovacuumLock, LW_EXCLUSIVE);

	/*
	 * Locate an unused work item and fill it with the given data.
	 */
	for (i = 0; i < NUM_WORKITEMS; i++)
	{
		AutoVacuumWorkItem *workitem = &AutoVacuumShmem->av_workItems[i];

		if (workitem->avw_used)
			continue;

		workitem->avw_used = true;
		workitem->avw_active = false;
		workitem->avw_type = type;
		workitem->avw_database = MyDatabaseId;
		workitem->avw_relation = relationId;
		workitem->avw_blockNumber = blkno;
		result = true;

		/* done */
		break;
	}

	LWLockRelease(AutovacuumLock);

	return result;
}

/*
 * autovac_init
 *		This is called at postmaster initialization.
 *
 * All we do here is annoy the user if he got it wrong.
 */
void
autovac_init(void)
{
	if (autovacuum_start_daemon && !pgstat_track_counts)
		ereport(WARNING,
				(errmsg("autovacuum not started because of misconfiguration"),
				 errhint("Enable the \"track_counts\" option.")));
}

/*
 * IsAutoVacuum functions
 *		Return whether this is either a launcher autovacuum process or a worker
 *		process.
 */
bool
IsAutoVacuumLauncherProcess(void)
{
	return am_autovacuum_launcher;
}

bool
IsAutoVacuumWorkerProcess(void)
{
	return am_autovacuum_worker;
}


/*
 * AutoVacuumShmemSize
 *		Compute space needed for autovacuum-related shared memory
 */
Size
AutoVacuumShmemSize(void)
{
	Size		size;

	/*
	 * Need the fixed struct and the array of WorkerInfoData.
	 */
	size = sizeof(AutoVacuumShmemStruct);
	size = MAXALIGN(size);
	size = add_size(size, mul_size(autovacuum_max_workers,
								   sizeof(WorkerInfoData)));
	return size;
}

/*
 * AutoVacuumShmemInit
 *		Allocate and initialize autovacuum-related shared memory
 */
void
AutoVacuumShmemInit(void)
{
	bool		found;

	AutoVacuumShmem = (AutoVacuumShmemStruct *)
		ShmemInitStruct("AutoVacuum Data",
						AutoVacuumShmemSize(),
						&found);

	if (!IsUnderPostmaster)
	{
		WorkerInfo	worker;
		int			i;

		Assert(!found);

		AutoVacuumShmem->av_launcherpid = 0;
		dlist_init(&AutoVacuumShmem->av_freeWorkers);
		dlist_init(&AutoVacuumShmem->av_runningWorkers);
		AutoVacuumShmem->av_startingWorker = NULL;
		memset(AutoVacuumShmem->av_workItems, 0,
			   sizeof(AutoVacuumWorkItem) * NUM_WORKITEMS);

		worker = (WorkerInfo) ((char *) AutoVacuumShmem +
							   MAXALIGN(sizeof(AutoVacuumShmemStruct)));

		/* initialize the WorkerInfo free list */
		for (i = 0; i < autovacuum_max_workers; i++)
			dlist_push_head(&AutoVacuumShmem->av_freeWorkers,
							&worker[i].wi_links);
	}
	else
		Assert(found);
}