Source

pgdevel / src / backend / access / transam / xlog.c

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
7791
7792
7793
7794
7795
7796
7797
7798
7799
7800
7801
7802
7803
7804
7805
7806
7807
7808
7809
7810
7811
7812
7813
7814
7815
7816
7817
7818
7819
7820
7821
7822
7823
7824
7825
7826
7827
7828
7829
7830
7831
7832
7833
7834
7835
7836
7837
7838
7839
7840
7841
7842
7843
7844
7845
7846
7847
7848
7849
7850
7851
7852
7853
7854
7855
7856
7857
7858
7859
7860
7861
7862
7863
7864
7865
7866
7867
7868
7869
7870
7871
7872
7873
7874
7875
7876
7877
7878
7879
7880
7881
7882
7883
7884
7885
7886
7887
7888
7889
7890
7891
7892
7893
7894
7895
7896
7897
7898
7899
7900
7901
7902
7903
7904
7905
7906
7907
7908
7909
7910
7911
7912
7913
7914
7915
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
8127
8128
8129
8130
8131
8132
8133
8134
8135
8136
8137
8138
8139
8140
8141
8142
8143
8144
8145
8146
8147
8148
8149
8150
8151
8152
8153
8154
8155
8156
8157
8158
8159
8160
8161
8162
8163
8164
8165
8166
8167
8168
8169
8170
8171
8172
8173
8174
8175
8176
8177
8178
8179
8180
8181
8182
8183
8184
8185
8186
8187
8188
8189
8190
8191
8192
8193
8194
8195
8196
8197
8198
8199
8200
8201
8202
8203
8204
8205
8206
8207
8208
8209
8210
8211
8212
8213
8214
8215
8216
8217
8218
8219
8220
8221
8222
8223
8224
8225
8226
8227
8228
8229
8230
8231
8232
8233
8234
8235
8236
8237
8238
8239
8240
8241
8242
8243
8244
8245
8246
8247
8248
8249
8250
8251
8252
8253
8254
8255
8256
8257
8258
8259
8260
8261
8262
8263
8264
8265
8266
8267
8268
8269
8270
8271
8272
8273
8274
8275
8276
8277
8278
8279
8280
8281
8282
8283
8284
8285
8286
8287
8288
8289
8290
8291
8292
8293
8294
8295
8296
8297
8298
8299
8300
8301
8302
8303
8304
8305
8306
8307
8308
8309
8310
8311
8312
8313
8314
8315
8316
8317
8318
8319
8320
8321
8322
8323
8324
8325
8326
8327
8328
8329
8330
8331
8332
8333
8334
8335
8336
8337
8338
8339
8340
8341
8342
8343
8344
8345
8346
8347
8348
8349
8350
8351
8352
8353
8354
8355
8356
8357
8358
8359
8360
8361
8362
8363
8364
8365
8366
8367
8368
8369
8370
8371
8372
8373
8374
8375
8376
8377
8378
8379
8380
8381
8382
8383
8384
8385
8386
8387
8388
8389
8390
8391
8392
8393
8394
8395
8396
8397
8398
8399
8400
8401
8402
8403
8404
8405
8406
8407
8408
8409
8410
8411
8412
8413
8414
8415
8416
8417
8418
8419
8420
8421
8422
8423
8424
8425
8426
8427
8428
8429
8430
8431
8432
8433
8434
8435
8436
8437
8438
8439
8440
8441
8442
8443
8444
8445
8446
8447
8448
8449
8450
8451
8452
8453
8454
8455
8456
8457
8458
8459
8460
8461
8462
8463
8464
8465
8466
8467
8468
8469
8470
8471
8472
8473
8474
8475
8476
8477
8478
8479
8480
8481
8482
8483
8484
8485
8486
8487
8488
8489
8490
8491
8492
8493
8494
8495
8496
8497
8498
8499
8500
8501
8502
8503
8504
8505
8506
8507
8508
8509
8510
8511
8512
8513
8514
8515
8516
8517
8518
8519
8520
8521
8522
8523
8524
8525
8526
8527
8528
8529
8530
8531
8532
8533
8534
8535
8536
8537
8538
8539
8540
8541
8542
8543
8544
8545
8546
8547
8548
8549
8550
8551
8552
8553
8554
8555
8556
8557
8558
8559
8560
8561
8562
8563
8564
8565
8566
8567
8568
8569
8570
8571
8572
8573
8574
8575
8576
8577
8578
8579
8580
8581
8582
8583
8584
8585
8586
8587
8588
8589
8590
8591
8592
8593
8594
8595
8596
8597
8598
8599
8600
8601
8602
8603
8604
8605
8606
8607
8608
8609
8610
8611
8612
8613
8614
8615
8616
8617
8618
8619
8620
8621
8622
8623
8624
8625
8626
8627
8628
8629
8630
8631
8632
8633
8634
8635
8636
8637
8638
8639
8640
8641
8642
8643
8644
8645
8646
8647
8648
8649
8650
8651
8652
8653
8654
8655
8656
8657
8658
8659
8660
8661
8662
8663
8664
8665
8666
8667
8668
8669
8670
8671
8672
8673
8674
8675
8676
8677
8678
8679
8680
8681
8682
8683
8684
8685
8686
8687
8688
8689
8690
8691
8692
8693
8694
8695
8696
8697
8698
8699
8700
8701
8702
8703
8704
8705
8706
8707
8708
8709
8710
8711
8712
8713
8714
8715
8716
8717
8718
8719
8720
8721
8722
8723
8724
8725
8726
8727
8728
8729
8730
8731
8732
8733
8734
8735
8736
8737
8738
8739
8740
8741
8742
8743
8744
8745
8746
8747
8748
8749
8750
8751
8752
8753
8754
8755
8756
8757
8758
8759
8760
8761
8762
8763
8764
8765
8766
8767
8768
8769
8770
8771
8772
8773
8774
8775
8776
8777
8778
8779
8780
8781
8782
8783
8784
8785
8786
8787
8788
8789
8790
8791
8792
8793
8794
8795
8796
8797
8798
8799
8800
8801
8802
8803
8804
8805
8806
8807
8808
8809
8810
8811
8812
8813
8814
8815
8816
8817
8818
8819
8820
8821
8822
8823
8824
8825
8826
8827
8828
8829
8830
8831
8832
8833
8834
8835
8836
8837
8838
8839
8840
8841
8842
8843
8844
8845
8846
8847
8848
8849
8850
8851
8852
8853
8854
8855
8856
8857
8858
8859
8860
8861
8862
8863
8864
8865
8866
8867
8868
8869
8870
8871
8872
8873
8874
8875
8876
8877
8878
8879
8880
8881
8882
8883
8884
8885
8886
8887
8888
8889
8890
8891
8892
8893
8894
8895
8896
8897
8898
8899
8900
8901
8902
8903
8904
8905
8906
8907
8908
8909
8910
8911
8912
8913
8914
8915
8916
8917
8918
8919
8920
8921
8922
8923
8924
8925
8926
8927
8928
8929
8930
8931
8932
8933
8934
8935
8936
8937
8938
8939
8940
8941
8942
8943
8944
8945
8946
8947
8948
8949
8950
8951
8952
8953
8954
8955
8956
8957
8958
8959
8960
8961
8962
8963
8964
8965
8966
8967
8968
8969
8970
8971
8972
8973
8974
8975
8976
8977
8978
8979
8980
8981
8982
8983
8984
8985
8986
8987
8988
8989
8990
8991
8992
8993
8994
8995
8996
8997
8998
8999
9000
9001
9002
9003
9004
9005
9006
9007
9008
9009
9010
9011
9012
9013
9014
9015
9016
9017
9018
9019
9020
9021
9022
9023
9024
9025
9026
9027
9028
9029
9030
9031
9032
9033
9034
9035
9036
9037
9038
9039
9040
9041
9042
9043
9044
9045
9046
9047
9048
9049
9050
9051
9052
9053
9054
9055
9056
9057
9058
9059
9060
9061
9062
9063
9064
9065
9066
9067
9068
9069
9070
9071
9072
9073
9074
9075
9076
9077
9078
9079
9080
9081
9082
9083
9084
9085
9086
9087
9088
9089
9090
9091
9092
9093
9094
9095
9096
9097
9098
9099
9100
9101
9102
9103
9104
9105
9106
9107
9108
9109
9110
9111
9112
9113
9114
9115
9116
9117
9118
9119
9120
9121
9122
9123
9124
9125
9126
9127
9128
9129
9130
9131
9132
9133
9134
9135
9136
9137
9138
9139
9140
9141
9142
9143
9144
9145
9146
9147
9148
9149
9150
9151
9152
9153
9154
9155
9156
9157
9158
9159
9160
9161
9162
9163
9164
9165
9166
9167
9168
9169
9170
9171
9172
9173
9174
9175
9176
9177
9178
9179
9180
9181
9182
9183
9184
9185
9186
9187
9188
9189
9190
9191
9192
9193
9194
9195
9196
9197
9198
9199
9200
9201
9202
9203
9204
9205
9206
9207
9208
9209
9210
9211
9212
9213
9214
9215
9216
9217
9218
9219
9220
9221
9222
9223
9224
9225
9226
9227
9228
9229
9230
9231
9232
9233
9234
9235
9236
9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
9252
9253
9254
9255
9256
9257
9258
9259
9260
9261
9262
9263
9264
9265
9266
9267
9268
9269
9270
9271
9272
9273
9274
9275
9276
9277
9278
9279
9280
9281
9282
9283
9284
9285
9286
9287
9288
9289
9290
9291
9292
9293
9294
9295
9296
9297
9298
9299
9300
9301
9302
9303
9304
9305
9306
9307
9308
9309
9310
9311
9312
9313
9314
9315
9316
9317
9318
9319
9320
9321
9322
9323
9324
9325
9326
9327
9328
9329
9330
9331
9332
9333
9334
9335
9336
9337
9338
9339
9340
9341
9342
9343
9344
9345
9346
9347
9348
9349
9350
9351
9352
9353
9354
9355
9356
9357
9358
9359
9360
9361
9362
9363
9364
9365
9366
9367
9368
9369
9370
9371
9372
9373
9374
9375
9376
9377
9378
9379
9380
9381
9382
9383
9384
9385
9386
9387
9388
9389
9390
9391
9392
9393
9394
9395
9396
9397
9398
9399
9400
9401
9402
9403
9404
9405
9406
9407
9408
9409
9410
9411
9412
9413
9414
9415
9416
9417
9418
9419
9420
9421
9422
9423
9424
9425
9426
9427
9428
9429
9430
9431
9432
9433
9434
9435
9436
9437
9438
9439
9440
9441
9442
9443
9444
9445
9446
9447
9448
9449
9450
9451
9452
9453
9454
9455
9456
9457
9458
9459
9460
9461
9462
9463
9464
9465
9466
9467
9468
9469
9470
9471
9472
9473
9474
9475
9476
9477
9478
9479
9480
9481
9482
9483
9484
9485
9486
9487
9488
9489
9490
9491
9492
9493
9494
9495
9496
9497
9498
9499
9500
9501
9502
9503
9504
9505
9506
9507
9508
9509
9510
9511
9512
9513
9514
9515
9516
9517
9518
9519
9520
9521
9522
9523
9524
9525
9526
9527
9528
9529
9530
9531
9532
9533
9534
9535
9536
9537
9538
9539
9540
9541
9542
9543
9544
9545
9546
9547
9548
9549
9550
9551
9552
9553
9554
9555
9556
9557
9558
9559
9560
9561
9562
9563
9564
9565
9566
9567
9568
9569
9570
9571
9572
9573
9574
9575
9576
9577
9578
9579
9580
9581
9582
9583
9584
9585
9586
9587
9588
9589
9590
9591
9592
9593
9594
9595
9596
9597
9598
9599
9600
9601
9602
9603
9604
9605
9606
9607
9608
9609
9610
9611
9612
9613
9614
9615
9616
9617
9618
9619
9620
9621
9622
9623
9624
9625
9626
9627
9628
9629
9630
9631
9632
9633
9634
9635
9636
9637
9638
9639
9640
9641
9642
9643
9644
9645
9646
9647
9648
9649
9650
9651
9652
9653
9654
9655
9656
9657
9658
9659
9660
9661
9662
9663
9664
9665
9666
9667
9668
9669
9670
9671
9672
9673
9674
9675
9676
9677
9678
9679
9680
9681
9682
/*-------------------------------------------------------------------------
 *
 * xlog.c
 *		PostgreSQL transaction log manager
 *
 *
 * Portions Copyright (c) 1996-2012, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * src/backend/access/transam/xlog.c
 *
 *-------------------------------------------------------------------------
 */

#include "postgres.h"

#include <ctype.h>
#include <time.h>
#include <fcntl.h>
#include <sys/stat.h>
#include <sys/time.h>
#include <unistd.h>

#include "access/clog.h"
#include "access/multixact.h"
#include "access/subtrans.h"
#include "access/timeline.h"
#include "access/transam.h"
#include "access/tuptoaster.h"
#include "access/twophase.h"
#include "access/xact.h"
#include "access/xlog_internal.h"
#include "access/xlogutils.h"
#include "catalog/catversion.h"
#include "catalog/pg_control.h"
#include "catalog/pg_database.h"
#include "libpq/pqsignal.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "postmaster/bgwriter.h"
#include "postmaster/startup.h"
#include "replication/walreceiver.h"
#include "replication/walsender.h"
#include "storage/bufmgr.h"
#include "storage/fd.h"
#include "storage/ipc.h"
#include "storage/latch.h"
#include "storage/pmsignal.h"
#include "storage/predicate.h"
#include "storage/proc.h"
#include "storage/procarray.h"
#include "storage/reinit.h"
#include "storage/smgr.h"
#include "storage/spin.h"
#include "utils/builtins.h"
#include "utils/guc.h"
#include "utils/ps_status.h"
#include "utils/relmapper.h"
#include "utils/snapmgr.h"
#include "utils/timestamp.h"
#include "pg_trace.h"


/* File path names (all relative to $PGDATA) */
#define RECOVERY_COMMAND_FILE	"recovery.conf"
#define RECOVERY_COMMAND_DONE	"recovery.done"
#define PROMOTE_SIGNAL_FILE "promote"


/* User-settable parameters */
int			CheckPointSegments = 3;
int			wal_keep_segments = 0;
int			XLOGbuffers = -1;
int			XLogArchiveTimeout = 0;
bool		XLogArchiveMode = false;
char	   *XLogArchiveCommand = NULL;
bool		EnableHotStandby = false;
bool		fullPageWrites = true;
bool		log_checkpoints = false;
int			sync_method = DEFAULT_SYNC_METHOD;
int			wal_level = WAL_LEVEL_MINIMAL;
int			CommitDelay = 0;	/* precommit delay in microseconds */
int			CommitSiblings = 5; /* # concurrent xacts needed to sleep */

#ifdef WAL_DEBUG
bool		XLOG_DEBUG = false;
#endif

/*
 * XLOGfileslop is the maximum number of preallocated future XLOG segments.
 * When we are done with an old XLOG segment file, we will recycle it as a
 * future XLOG segment as long as there aren't already XLOGfileslop future
 * segments; else we'll delete it.  This could be made a separate GUC
 * variable, but at present I think it's sufficient to hardwire it as
 * 2*CheckPointSegments+1.	Under normal conditions, a checkpoint will free
 * no more than 2*CheckPointSegments log segments, and we want to recycle all
 * of them; the +1 allows boundary cases to happen without wasting a
 * delete/create-segment cycle.
 */
#define XLOGfileslop	(2*CheckPointSegments + 1)


/*
 * GUC support
 */
const struct config_enum_entry sync_method_options[] = {
	{"fsync", SYNC_METHOD_FSYNC, false},
#ifdef HAVE_FSYNC_WRITETHROUGH
	{"fsync_writethrough", SYNC_METHOD_FSYNC_WRITETHROUGH, false},
#endif
#ifdef HAVE_FDATASYNC
	{"fdatasync", SYNC_METHOD_FDATASYNC, false},
#endif
#ifdef OPEN_SYNC_FLAG
	{"open_sync", SYNC_METHOD_OPEN, false},
#endif
#ifdef OPEN_DATASYNC_FLAG
	{"open_datasync", SYNC_METHOD_OPEN_DSYNC, false},
#endif
	{NULL, 0, false}
};

/*
 * Statistics for current checkpoint are collected in this global struct.
 * Because only the background writer or a stand-alone backend can perform
 * checkpoints, this will be unused in normal backends.
 */
CheckpointStatsData CheckpointStats;

/*
 * ThisTimeLineID will be same in all backends --- it identifies current
 * WAL timeline for the database system.
 */
TimeLineID	ThisTimeLineID = 0;

/*
 * Are we doing recovery from XLOG?
 *
 * This is only ever true in the startup process; it should be read as meaning
 * "this process is replaying WAL records", rather than "the system is in
 * recovery mode".  It should be examined primarily by functions that need
 * to act differently when called from a WAL redo function (e.g., to skip WAL
 * logging).  To check whether the system is in recovery regardless of which
 * process you're running in, use RecoveryInProgress() but only after shared
 * memory startup and lock initialization.
 */
bool		InRecovery = false;

/* Are we in Hot Standby mode? Only valid in startup process, see xlog.h */
HotStandbyState standbyState = STANDBY_DISABLED;

static XLogRecPtr LastRec;

/* Local copy of WalRcv->receivedUpto */
static XLogRecPtr receivedUpto = 0;

/*
 * During recovery, lastFullPageWrites keeps track of full_page_writes that
 * the replayed WAL records indicate. It's initialized with full_page_writes
 * that the recovery starting checkpoint record indicates, and then updated
 * each time XLOG_FPW_CHANGE record is replayed.
 */
static bool lastFullPageWrites;

/*
 * Local copy of SharedRecoveryInProgress variable. True actually means "not
 * known, need to check the shared state".
 */
static bool LocalRecoveryInProgress = true;

/*
 * Local copy of SharedHotStandbyActive variable. False actually means "not
 * known, need to check the shared state".
 */
static bool LocalHotStandbyActive = false;

/*
 * Local state for XLogInsertAllowed():
 *		1: unconditionally allowed to insert XLOG
 *		0: unconditionally not allowed to insert XLOG
 *		-1: must check RecoveryInProgress(); disallow until it is false
 * Most processes start with -1 and transition to 1 after seeing that recovery
 * is not in progress.	But we can also force the value for special cases.
 * The coding in XLogInsertAllowed() depends on the first two of these states
 * being numerically the same as bool true and false.
 */
static int	LocalXLogInsertAllowed = -1;

/* Are we recovering using offline XLOG archives? (only valid in the startup process) */
bool InArchiveRecovery = false;

/* Was the last xlog file restored from archive, or local? */
static bool restoredFromArchive = false;

/* options taken from recovery.conf for archive recovery */
char *recoveryRestoreCommand = NULL;
static char *recoveryEndCommand = NULL;
static char *archiveCleanupCommand = NULL;
static RecoveryTargetType recoveryTarget = RECOVERY_TARGET_UNSET;
static bool recoveryTargetInclusive = true;
static bool recoveryPauseAtTarget = true;
static TransactionId recoveryTargetXid;
static TimestampTz recoveryTargetTime;
static char *recoveryTargetName;

/* options taken from recovery.conf for XLOG streaming */
bool StandbyMode = false;
static char *PrimaryConnInfo = NULL;
static char *TriggerFile = NULL;

/* if recoveryStopsHere returns true, it saves actual stop xid/time/name here */
static TransactionId recoveryStopXid;
static TimestampTz recoveryStopTime;
static char recoveryStopName[MAXFNAMELEN];
static bool recoveryStopAfter;

/*
 * During normal operation, the only timeline we care about is ThisTimeLineID.
 * During recovery, however, things are more complicated.  To simplify life
 * for rmgr code, we keep ThisTimeLineID set to the "current" timeline as we
 * scan through the WAL history (that is, it is the line that was active when
 * the currently-scanned WAL record was generated).  We also need these
 * timeline values:
 *
 * recoveryTargetTLI: the desired timeline that we want to end in.
 *
 * recoveryTargetIsLatest: was the requested target timeline 'latest'?
 *
 * expectedTLIs: an integer list of recoveryTargetTLI and the TLIs of
 * its known parents, newest first (so recoveryTargetTLI is always the
 * first list member).	Only these TLIs are expected to be seen in the WAL
 * segments we read, and indeed only these TLIs will be considered as
 * candidate WAL files to open at all.
 *
 * curFileTLI: the TLI appearing in the name of the current input WAL file.
 * (This is not necessarily the same as ThisTimeLineID, because we could
 * be scanning data that was copied from an ancestor timeline when the current
 * file was created.)  During a sequential scan we do not allow this value
 * to decrease.
 */
static TimeLineID recoveryTargetTLI;
static bool recoveryTargetIsLatest = false;
static List *expectedTLIs;
static TimeLineID curFileTLI;

/*
 * ProcLastRecPtr points to the start of the last XLOG record inserted by the
 * current backend.  It is updated for all inserts.  XactLastRecEnd points to
 * end+1 of the last record, and is reset when we end a top-level transaction,
 * or start a new one; so it can be used to tell if the current transaction has
 * created any XLOG records.
 */
static XLogRecPtr ProcLastRecPtr = InvalidXLogRecPtr;

XLogRecPtr	XactLastRecEnd = InvalidXLogRecPtr;

/*
 * RedoRecPtr is this backend's local copy of the REDO record pointer
 * (which is almost but not quite the same as a pointer to the most recent
 * CHECKPOINT record).	We update this from the shared-memory copy,
 * XLogCtl->Insert.RedoRecPtr, whenever we can safely do so (ie, when we
 * hold the Insert lock).  See XLogInsert for details.	We are also allowed
 * to update from XLogCtl->Insert.RedoRecPtr if we hold the info_lck;
 * see GetRedoRecPtr.  A freshly spawned backend obtains the value during
 * InitXLOGAccess.
 */
static XLogRecPtr RedoRecPtr;

/*
 * RedoStartLSN points to the checkpoint's REDO location which is specified
 * in a backup label file, backup history file or control file. In standby
 * mode, XLOG streaming usually starts from the position where an invalid
 * record was found. But if we fail to read even the initial checkpoint
 * record, we use the REDO location instead of the checkpoint location as
 * the start position of XLOG streaming. Otherwise we would have to jump
 * backwards to the REDO location after reading the checkpoint record,
 * because the REDO record can precede the checkpoint record.
 */
static XLogRecPtr RedoStartLSN = InvalidXLogRecPtr;

/*----------
 * Shared-memory data structures for XLOG control
 *
 * LogwrtRqst indicates a byte position that we need to write and/or fsync
 * the log up to (all records before that point must be written or fsynced).
 * LogwrtResult indicates the byte positions we have already written/fsynced.
 * These structs are identical but are declared separately to indicate their
 * slightly different functions.
 *
 * To read XLogCtl->LogwrtResult, you must hold either info_lck or
 * WALWriteLock.  To update it, you need to hold both locks.  The point of
 * this arrangement is that the value can be examined by code that already
 * holds WALWriteLock without needing to grab info_lck as well.  In addition
 * to the shared variable, each backend has a private copy of LogwrtResult,
 * which is updated when convenient.
 *
 * The request bookkeeping is simpler: there is a shared XLogCtl->LogwrtRqst
 * (protected by info_lck), but we don't need to cache any copies of it.
 *
 * info_lck is only held long enough to read/update the protected variables,
 * so it's a plain spinlock.  The other locks are held longer (potentially
 * over I/O operations), so we use LWLocks for them.  These locks are:
 *
 * WALInsertLock: must be held to insert a record into the WAL buffers.
 *
 * WALWriteLock: must be held to write WAL buffers to disk (XLogWrite or
 * XLogFlush).
 *
 * ControlFileLock: must be held to read/update control file or create
 * new log file.
 *
 * CheckpointLock: must be held to do a checkpoint or restartpoint (ensures
 * only one checkpointer at a time; currently, with all checkpoints done by
 * the checkpointer, this is just pro forma).
 *
 *----------
 */

typedef struct XLogwrtRqst
{
	XLogRecPtr	Write;			/* last byte + 1 to write out */
	XLogRecPtr	Flush;			/* last byte + 1 to flush */
} XLogwrtRqst;

typedef struct XLogwrtResult
{
	XLogRecPtr	Write;			/* last byte + 1 written out */
	XLogRecPtr	Flush;			/* last byte + 1 flushed */
} XLogwrtResult;

/*
 * Shared state data for XLogInsert.
 */
typedef struct XLogCtlInsert
{
	XLogRecPtr	PrevRecord;		/* start of previously-inserted record */
	int			curridx;		/* current block index in cache */
	XLogPageHeader currpage;	/* points to header of block in cache */
	char	   *currpos;		/* current insertion point in cache */
	XLogRecPtr	RedoRecPtr;		/* current redo point for insertions */
	bool		forcePageWrites;	/* forcing full-page writes for PITR? */

	/*
	 * fullPageWrites is the master copy used by all backends to determine
	 * whether to write full-page to WAL, instead of using process-local one.
	 * This is required because, when full_page_writes is changed by SIGHUP,
	 * we must WAL-log it before it actually affects WAL-logging by backends.
	 * Checkpointer sets at startup or after SIGHUP.
	 */
	bool		fullPageWrites;

	/*
	 * exclusiveBackup is true if a backup started with pg_start_backup() is
	 * in progress, and nonExclusiveBackups is a counter indicating the number
	 * of streaming base backups currently in progress. forcePageWrites is set
	 * to true when either of these is non-zero. lastBackupStart is the latest
	 * checkpoint redo location used as a starting point for an online backup.
	 */
	bool		exclusiveBackup;
	int			nonExclusiveBackups;
	XLogRecPtr	lastBackupStart;
} XLogCtlInsert;

/*
 * Shared state data for XLogWrite/XLogFlush.
 */
typedef struct XLogCtlWrite
{
	int			curridx;		/* cache index of next block to write */
	pg_time_t	lastSegSwitchTime;		/* time of last xlog segment switch */
} XLogCtlWrite;

/*
 * Total shared-memory state for XLOG.
 */
typedef struct XLogCtlData
{
	/* Protected by WALInsertLock: */
	XLogCtlInsert Insert;

	/* Protected by info_lck: */
	XLogwrtRqst LogwrtRqst;
	uint32		ckptXidEpoch;	/* nextXID & epoch of latest checkpoint */
	TransactionId ckptXid;
	XLogRecPtr	asyncXactLSN;	/* LSN of newest async commit/abort */
	XLogSegNo	lastRemovedSegNo; /* latest removed/recycled XLOG segment */

	/* Protected by WALWriteLock: */
	XLogCtlWrite Write;

	/*
	 * Protected by info_lck and WALWriteLock (you must hold either lock to
	 * read it, but both to update)
	 */
	XLogwrtResult LogwrtResult;

	/*
	 * These values do not change after startup, although the pointed-to pages
	 * and xlblocks values certainly do.  Permission to read/write the pages
	 * and xlblocks values depends on WALInsertLock and WALWriteLock.
	 */
	char	   *pages;			/* buffers for unwritten XLOG pages */
	XLogRecPtr *xlblocks;		/* 1st byte ptr-s + XLOG_BLCKSZ */
	int			XLogCacheBlck;	/* highest allocated xlog buffer index */
	TimeLineID	ThisTimeLineID;

	/*
	 * archiveCleanupCommand is read from recovery.conf but needs to be in
	 * shared memory so that the checkpointer process can access it.
	 */
	char		archiveCleanupCommand[MAXPGPATH];

	/*
	 * SharedRecoveryInProgress indicates if we're still in crash or archive
	 * recovery.  Protected by info_lck.
	 */
	bool		SharedRecoveryInProgress;

	/*
	 * SharedHotStandbyActive indicates if we're still in crash or archive
	 * recovery.  Protected by info_lck.
	 */
	bool		SharedHotStandbyActive;

	/*
	 * WalWriterSleeping indicates whether the WAL writer is currently in
	 * low-power mode (and hence should be nudged if an async commit occurs).
	 * Protected by info_lck.
	 */
	bool		WalWriterSleeping;

	/*
	 * recoveryWakeupLatch is used to wake up the startup process to continue
	 * WAL replay, if it is waiting for WAL to arrive or failover trigger file
	 * to appear.
	 */
	Latch		recoveryWakeupLatch;

	/*
	 * During recovery, we keep a copy of the latest checkpoint record here.
	 * Used by the background writer when it wants to create a restartpoint.
	 *
	 * Protected by info_lck.
	 */
	XLogRecPtr	lastCheckPointRecPtr;
	CheckPoint	lastCheckPoint;

	/* end+1 of the last record replayed (or being replayed) */
	XLogRecPtr	replayEndRecPtr;
	/* end+1 of the last record replayed */
	XLogRecPtr	recoveryLastRecPtr;
	/* timestamp of last COMMIT/ABORT record replayed (or being replayed) */
	TimestampTz recoveryLastXTime;
	/* current effective recovery target timeline */
	TimeLineID	RecoveryTargetTLI;

	/*
	 * timestamp of when we started replaying the current chunk of WAL data,
	 * only relevant for replication or archive recovery
	 */
	TimestampTz currentChunkStartTime;
	/* Are we requested to pause recovery? */
	bool		recoveryPause;

	/*
	 * lastFpwDisableRecPtr points to the start of the last replayed
	 * XLOG_FPW_CHANGE record that instructs full_page_writes is disabled.
	 */
	XLogRecPtr	lastFpwDisableRecPtr;

	slock_t		info_lck;		/* locks shared variables shown above */
} XLogCtlData;

static XLogCtlData *XLogCtl = NULL;

/*
 * We maintain an image of pg_control in shared memory.
 */
static ControlFileData *ControlFile = NULL;

/*
 * Macros for managing XLogInsert state.  In most cases, the calling routine
 * has local copies of XLogCtl->Insert and/or XLogCtl->Insert->curridx,
 * so these are passed as parameters instead of being fetched via XLogCtl.
 */

/* Free space remaining in the current xlog page buffer */
#define INSERT_FREESPACE(Insert)  \
	(XLOG_BLCKSZ - ((Insert)->currpos - (char *) (Insert)->currpage))

/* Construct XLogRecPtr value for current insertion point */
#define INSERT_RECPTR(recptr,Insert,curridx)  \
		(recptr) = XLogCtl->xlblocks[curridx] - INSERT_FREESPACE(Insert)

#define PrevBufIdx(idx)		\
		(((idx) == 0) ? XLogCtl->XLogCacheBlck : ((idx) - 1))

#define NextBufIdx(idx)		\
		(((idx) == XLogCtl->XLogCacheBlck) ? 0 : ((idx) + 1))

/*
 * Private, possibly out-of-date copy of shared LogwrtResult.
 * See discussion above.
 */
static XLogwrtResult LogwrtResult = {0, 0};

/*
 * Codes indicating where we got a WAL file from during recovery, or where
 * to attempt to get one.  These are chosen so that they can be OR'd together
 * in a bitmask state variable.
 */
#define XLOG_FROM_ARCHIVE		(1<<0)	/* Restored using restore_command */
#define XLOG_FROM_PG_XLOG		(1<<1)	/* Existing file in pg_xlog */
#define XLOG_FROM_STREAM		(1<<2)	/* Streamed from master */

/*
 * openLogFile is -1 or a kernel FD for an open log file segment.
 * When it's open, openLogOff is the current seek offset in the file.
 * openLogSegNo identifies the segment.  These variables are only
 * used to write the XLOG, and so will normally refer to the active segment.
 */
static int	openLogFile = -1;
static XLogSegNo openLogSegNo = 0;
static uint32 openLogOff = 0;

/*
 * These variables are used similarly to the ones above, but for reading
 * the XLOG.  Note, however, that readOff generally represents the offset
 * of the page just read, not the seek position of the FD itself, which
 * will be just past that page. readLen indicates how much of the current
 * page has been read into readBuf, and readSource indicates where we got
 * the currently open file from.
 */
static int	readFile = -1;
static XLogSegNo readSegNo = 0;
static uint32 readOff = 0;
static uint32 readLen = 0;
static bool	readFileHeaderValidated = false;
static int	readSource = 0;		/* XLOG_FROM_* code */

/*
 * Keeps track of which sources we've tried to read the current WAL
 * record from and failed.
 */
static int	failedSources = 0;	/* OR of XLOG_FROM_* codes */

/*
 * These variables track when we last obtained some WAL data to process,
 * and where we got it from.  (XLogReceiptSource is initially the same as
 * readSource, but readSource gets reset to zero when we don't have data
 * to process right now.)
 */
static TimestampTz XLogReceiptTime = 0;
static int	XLogReceiptSource = 0;		/* XLOG_FROM_* code */

/* Buffer for currently read page (XLOG_BLCKSZ bytes) */
static char *readBuf = NULL;

/* Buffer for current ReadRecord result (expandable) */
static char *readRecordBuf = NULL;
static uint32 readRecordBufSize = 0;

/* State information for XLOG reading */
static XLogRecPtr ReadRecPtr;	/* start of last record read */
static XLogRecPtr EndRecPtr;	/* end+1 of last record read */
static TimeLineID lastPageTLI = 0;
static TimeLineID lastSegmentTLI = 0;

static XLogRecPtr minRecoveryPoint;		/* local copy of
										 * ControlFile->minRecoveryPoint */
static bool updateMinRecoveryPoint = true;

/*
 * Have we reached a consistent database state? In crash recovery, we have
 * to replay all the WAL, so reachedConsistency is never set. During archive
 * recovery, the database is consistent once minRecoveryPoint is reached.
 */
bool		reachedConsistency = false;

static bool InRedo = false;

/* Have we launched bgwriter during recovery? */
static bool bgwriterLaunched = false;


static void readRecoveryCommandFile(void);
static void exitArchiveRecovery(TimeLineID endTLI, XLogSegNo endLogSegNo);
static bool recoveryStopsHere(XLogRecord *record, bool *includeThis);
static void recoveryPausesHere(void);
static void SetLatestXTime(TimestampTz xtime);
static void SetCurrentChunkStartTime(TimestampTz xtime);
static void CheckRequiredParameterValues(void);
static void XLogReportParameters(void);
static void LocalSetXLogInsertAllowed(void);
static void CheckPointGuts(XLogRecPtr checkPointRedo, int flags);
static void KeepLogSeg(XLogRecPtr recptr, XLogSegNo *logSegNo);

static bool XLogCheckBuffer(XLogRecData *rdata, bool doPageWrites,
				XLogRecPtr *lsn, BkpBlock *bkpb);
static bool AdvanceXLInsertBuffer(bool new_segment);
static bool XLogCheckpointNeeded(XLogSegNo new_segno);
static void XLogWrite(XLogwrtRqst WriteRqst, bool flexible, bool xlog_switch);
static bool InstallXLogFileSegment(XLogSegNo *segno, char *tmppath,
					   bool find_free, int *max_advance,
					   bool use_lock);
static int XLogFileRead(XLogSegNo segno, int emode, TimeLineID tli,
			 int source, bool notexistOk);
static int XLogFileReadAnyTLI(XLogSegNo segno, int emode, int sources);
static bool XLogPageRead(XLogRecPtr *RecPtr, int emode, bool fetching_ckpt,
			 bool randAccess);
static bool WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess,
							bool fetching_ckpt);
static int	emode_for_corrupt_record(int emode, XLogRecPtr RecPtr);
static void XLogFileClose(void);
static void PreallocXlogFiles(XLogRecPtr endptr);
static void RemoveOldXlogFiles(XLogSegNo segno, XLogRecPtr endptr);
static void UpdateLastRemovedPtr(char *filename);
static void ValidateXLOGDirectoryStructure(void);
static void CleanupBackupHistory(void);
static void UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force);
static XLogRecord *ReadRecord(XLogRecPtr *RecPtr, int emode, bool fetching_ckpt);
static void CheckRecoveryConsistency(void);
static bool ValidXLogPageHeader(XLogPageHeader hdr, int emode, bool segmentonly);
static bool ValidXLogRecordHeader(XLogRecPtr *RecPtr, XLogRecord *record,
					  int emode, bool randAccess);
static XLogRecord *ReadCheckpointRecord(XLogRecPtr RecPtr, int whichChkpt);
static bool rescanLatestTimeLine(void);
static void WriteControlFile(void);
static void ReadControlFile(void);
static char *str_time(pg_time_t tnow);
static bool CheckForStandbyTrigger(void);

#ifdef WAL_DEBUG
static void xlog_outrec(StringInfo buf, XLogRecord *record);
#endif
static void pg_start_backup_callback(int code, Datum arg);
static bool read_backup_label(XLogRecPtr *checkPointLoc,
				  bool *backupEndRequired, bool *backupFromStandby);
static void rm_redo_error_callback(void *arg);
static int	get_sync_bit(int method);


/*
 * Insert an XLOG record having the specified RMID and info bytes,
 * with the body of the record being the data chunk(s) described by
 * the rdata chain (see xlog.h for notes about rdata).
 *
 * Returns XLOG pointer to end of record (beginning of next record).
 * This can be used as LSN for data pages affected by the logged action.
 * (LSN is the XLOG point up to which the XLOG must be flushed to disk
 * before the data page can be written out.  This implements the basic
 * WAL rule "write the log before the data".)
 *
 * NB: this routine feels free to scribble on the XLogRecData structs,
 * though not on the data they reference.  This is OK since the XLogRecData
 * structs are always just temporaries in the calling code.
 */
XLogRecPtr
XLogInsert(RmgrId rmid, uint8 info, XLogRecData *rdata)
{
	XLogCtlInsert *Insert = &XLogCtl->Insert;
	XLogRecPtr	RecPtr;
	XLogRecPtr	WriteRqst;
	uint32		freespace;
	int			curridx;
	XLogRecData *rdt;
	XLogRecData *rdt_lastnormal;
	Buffer		dtbuf[XLR_MAX_BKP_BLOCKS];
	bool		dtbuf_bkp[XLR_MAX_BKP_BLOCKS];
	BkpBlock	dtbuf_xlg[XLR_MAX_BKP_BLOCKS];
	XLogRecPtr	dtbuf_lsn[XLR_MAX_BKP_BLOCKS];
	XLogRecData dtbuf_rdt1[XLR_MAX_BKP_BLOCKS];
	XLogRecData dtbuf_rdt2[XLR_MAX_BKP_BLOCKS];
	XLogRecData dtbuf_rdt3[XLR_MAX_BKP_BLOCKS];
	XLogRecData hdr_rdt;
	pg_crc32	rdata_crc;
	uint32		len,
				write_len;
	unsigned	i;
	bool		updrqst;
	bool		doPageWrites;
	bool		isLogSwitch = (rmid == RM_XLOG_ID && info == XLOG_SWITCH);
	uint8		info_orig = info;
	static XLogRecord *rechdr;

	if (rechdr == NULL)
	{
		rechdr = malloc(SizeOfXLogRecord);
		if (rechdr == NULL)
			elog(ERROR, "out of memory");
		MemSet(rechdr, 0, SizeOfXLogRecord);
	}

	/* cross-check on whether we should be here or not */
	if (!XLogInsertAllowed())
		elog(ERROR, "cannot make new WAL entries during recovery");

	/* info's high bits are reserved for use by me */
	if (info & XLR_INFO_MASK)
		elog(PANIC, "invalid xlog info mask %02X", info);

	TRACE_POSTGRESQL_XLOG_INSERT(rmid, info);

	/*
	 * In bootstrap mode, we don't actually log anything but XLOG resources;
	 * return a phony record pointer.
	 */
	if (IsBootstrapProcessingMode() && rmid != RM_XLOG_ID)
	{
		RecPtr = SizeOfXLogLongPHD;		/* start of 1st chkpt record */
		return RecPtr;
	}

	/*
	 * Here we scan the rdata chain, to determine which buffers must be backed
	 * up.
	 *
	 * We may have to loop back to here if a race condition is detected below.
	 * We could prevent the race by doing all this work while holding the
	 * insert lock, but it seems better to avoid doing CRC calculations while
	 * holding the lock.
	 *
	 * We add entries for backup blocks to the chain, so that they don't need
	 * any special treatment in the critical section where the chunks are
	 * copied into the WAL buffers. Those entries have to be unlinked from the
	 * chain if we have to loop back here.
	 */
begin:;
	for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
	{
		dtbuf[i] = InvalidBuffer;
		dtbuf_bkp[i] = false;
	}

	/*
	 * Decide if we need to do full-page writes in this XLOG record: true if
	 * full_page_writes is on or we have a PITR request for it.  Since we
	 * don't yet have the insert lock, fullPageWrites and forcePageWrites
	 * could change under us, but we'll recheck them once we have the lock.
	 */
	doPageWrites = Insert->fullPageWrites || Insert->forcePageWrites;

	len = 0;
	for (rdt = rdata;;)
	{
		if (rdt->buffer == InvalidBuffer)
		{
			/* Simple data, just include it */
			len += rdt->len;
		}
		else
		{
			/* Find info for buffer */
			for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
			{
				if (rdt->buffer == dtbuf[i])
				{
					/* Buffer already referenced by earlier chain item */
					if (dtbuf_bkp[i])
					{
						rdt->data = NULL;
						rdt->len = 0;
					}
					else if (rdt->data)
						len += rdt->len;
					break;
				}
				if (dtbuf[i] == InvalidBuffer)
				{
					/* OK, put it in this slot */
					dtbuf[i] = rdt->buffer;
					if (XLogCheckBuffer(rdt, doPageWrites,
										&(dtbuf_lsn[i]), &(dtbuf_xlg[i])))
					{
						dtbuf_bkp[i] = true;
						rdt->data = NULL;
						rdt->len = 0;
					}
					else if (rdt->data)
						len += rdt->len;
					break;
				}
			}
			if (i >= XLR_MAX_BKP_BLOCKS)
				elog(PANIC, "can backup at most %d blocks per xlog record",
					 XLR_MAX_BKP_BLOCKS);
		}
		/* Break out of loop when rdt points to last chain item */
		if (rdt->next == NULL)
			break;
		rdt = rdt->next;
	}

	/*
	 * NOTE: We disallow len == 0 because it provides a useful bit of extra
	 * error checking in ReadRecord.  This means that all callers of
	 * XLogInsert must supply at least some not-in-a-buffer data.  However, we
	 * make an exception for XLOG SWITCH records because we don't want them to
	 * ever cross a segment boundary.
	 */
	if (len == 0 && !isLogSwitch)
		elog(PANIC, "invalid xlog record length %u", len);

	/*
	 * Make additional rdata chain entries for the backup blocks, so that we
	 * don't need to special-case them in the write loop.  This modifies the
	 * original rdata chain, but we keep a pointer to the last regular entry,
	 * rdt_lastnormal, so that we can undo this if we have to loop back to the
	 * beginning.
	 *
	 * At the exit of this loop, write_len includes the backup block data.
	 *
	 * Also set the appropriate info bits to show which buffers were backed
	 * up. The XLR_BKP_BLOCK(N) bit corresponds to the N'th distinct buffer
	 * value (ignoring InvalidBuffer) appearing in the rdata chain.
	 */
	rdt_lastnormal = rdt;
	write_len = len;
	for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
	{
		BkpBlock   *bkpb;
		char	   *page;

		if (!dtbuf_bkp[i])
			continue;

		info |= XLR_BKP_BLOCK(i);

		bkpb = &(dtbuf_xlg[i]);
		page = (char *) BufferGetBlock(dtbuf[i]);

		rdt->next = &(dtbuf_rdt1[i]);
		rdt = rdt->next;

		rdt->data = (char *) bkpb;
		rdt->len = sizeof(BkpBlock);
		write_len += sizeof(BkpBlock);

		rdt->next = &(dtbuf_rdt2[i]);
		rdt = rdt->next;

		if (bkpb->hole_length == 0)
		{
			rdt->data = page;
			rdt->len = BLCKSZ;
			write_len += BLCKSZ;
			rdt->next = NULL;
		}
		else
		{
			/* must skip the hole */
			rdt->data = page;
			rdt->len = bkpb->hole_offset;
			write_len += bkpb->hole_offset;

			rdt->next = &(dtbuf_rdt3[i]);
			rdt = rdt->next;

			rdt->data = page + (bkpb->hole_offset + bkpb->hole_length);
			rdt->len = BLCKSZ - (bkpb->hole_offset + bkpb->hole_length);
			write_len += rdt->len;
			rdt->next = NULL;
		}
	}

	/*
	 * Calculate CRC of the data, including all the backup blocks
	 *
	 * Note that the record header isn't added into the CRC initially since we
	 * don't know the prev-link yet.  Thus, the CRC will represent the CRC of
	 * the whole record in the order: rdata, then backup blocks, then record
	 * header.
	 */
	INIT_CRC32(rdata_crc);
	for (rdt = rdata; rdt != NULL; rdt = rdt->next)
		COMP_CRC32(rdata_crc, rdt->data, rdt->len);

	/*
	 * Construct record header (prev-link and CRC are filled in later), and
	 * make that the first chunk in the chain.
	 */
	rechdr->xl_xid = GetCurrentTransactionIdIfAny();
	rechdr->xl_tot_len = SizeOfXLogRecord + write_len;
	rechdr->xl_len = len;		/* doesn't include backup blocks */
	rechdr->xl_info = info;
	rechdr->xl_rmid = rmid;

	hdr_rdt.next = rdata;
	hdr_rdt.data = (char *) rechdr;
	hdr_rdt.len = SizeOfXLogRecord;

	write_len += SizeOfXLogRecord;

	START_CRIT_SECTION();

	/* Now wait to get insert lock */
	LWLockAcquire(WALInsertLock, LW_EXCLUSIVE);

	/*
	 * Check to see if my RedoRecPtr is out of date.  If so, may have to go
	 * back and recompute everything.  This can only happen just after a
	 * checkpoint, so it's better to be slow in this case and fast otherwise.
	 *
	 * If we aren't doing full-page writes then RedoRecPtr doesn't actually
	 * affect the contents of the XLOG record, so we'll update our local copy
	 * but not force a recomputation.
	 */
	if (!XLByteEQ(RedoRecPtr, Insert->RedoRecPtr))
	{
		Assert(XLByteLT(RedoRecPtr, Insert->RedoRecPtr));
		RedoRecPtr = Insert->RedoRecPtr;

		if (doPageWrites)
		{
			for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
			{
				if (dtbuf[i] == InvalidBuffer)
					continue;
				if (dtbuf_bkp[i] == false &&
					XLByteLE(dtbuf_lsn[i], RedoRecPtr))
				{
					/*
					 * Oops, this buffer now needs to be backed up, but we
					 * didn't think so above.  Start over.
					 */
					LWLockRelease(WALInsertLock);
					END_CRIT_SECTION();
					rdt_lastnormal->next = NULL;
					info = info_orig;
					goto begin;
				}
			}
		}
	}

	/*
	 * Also check to see if fullPageWrites or forcePageWrites was just turned
	 * on; if we weren't already doing full-page writes then go back and
	 * recompute. (If it was just turned off, we could recompute the record
	 * without full pages, but we choose not to bother.)
	 */
	if ((Insert->fullPageWrites || Insert->forcePageWrites) && !doPageWrites)
	{
		/* Oops, must redo it with full-page data. */
		LWLockRelease(WALInsertLock);
		END_CRIT_SECTION();
		rdt_lastnormal->next = NULL;
		info = info_orig;
		goto begin;
	}

	/*
	 * If the current page is completely full, the record goes to the next
	 * page, right after the page header.
	 */
	updrqst = false;
	freespace = INSERT_FREESPACE(Insert);
	if (freespace == 0)
	{
		updrqst = AdvanceXLInsertBuffer(false);
		freespace = INSERT_FREESPACE(Insert);
	}

	/* Compute record's XLOG location */
	curridx = Insert->curridx;
	INSERT_RECPTR(RecPtr, Insert, curridx);

	/*
	 * If the record is an XLOG_SWITCH, and we are exactly at the start of a
	 * segment, we need not insert it (and don't want to because we'd like
	 * consecutive switch requests to be no-ops).  Instead, make sure
	 * everything is written and flushed through the end of the prior segment,
	 * and return the prior segment's end address.
	 */
	if (isLogSwitch && (RecPtr % XLogSegSize) == SizeOfXLogLongPHD)
	{
		/* We can release insert lock immediately */
		LWLockRelease(WALInsertLock);

		RecPtr -= SizeOfXLogLongPHD;

		LWLockAcquire(WALWriteLock, LW_EXCLUSIVE);
		LogwrtResult = XLogCtl->LogwrtResult;
		if (!XLByteLE(RecPtr, LogwrtResult.Flush))
		{
			XLogwrtRqst FlushRqst;

			FlushRqst.Write = RecPtr;
			FlushRqst.Flush = RecPtr;
			XLogWrite(FlushRqst, false, false);
		}
		LWLockRelease(WALWriteLock);

		END_CRIT_SECTION();

		/* wake up walsenders now that we've released heavily contended locks */
		WalSndWakeupProcessRequests();
		return RecPtr;
	}

	/* Finish the record header */
	rechdr->xl_prev = Insert->PrevRecord;

	/* Now we can finish computing the record's CRC */
	COMP_CRC32(rdata_crc, (char *) rechdr, offsetof(XLogRecord, xl_crc));
	FIN_CRC32(rdata_crc);
	rechdr->xl_crc = rdata_crc;

#ifdef WAL_DEBUG
	if (XLOG_DEBUG)
	{
		StringInfoData buf;

		initStringInfo(&buf);
		appendStringInfo(&buf, "INSERT @ %X/%X: ",
						 (uint32) (RecPtr >> 32), (uint32) RecPtr);
		xlog_outrec(&buf, rechdr);
		if (rdata->data != NULL)
		{
			appendStringInfo(&buf, " - ");
			RmgrTable[rechdr->xl_rmid].rm_desc(&buf, rechdr->xl_info, rdata->data);
		}
		elog(LOG, "%s", buf.data);
		pfree(buf.data);
	}
#endif

	/* Record begin of record in appropriate places */
	ProcLastRecPtr = RecPtr;
	Insert->PrevRecord = RecPtr;

	/*
	 * Append the data, including backup blocks if any
	 */
	rdata = &hdr_rdt;
	while (write_len)
	{
		while (rdata->data == NULL)
			rdata = rdata->next;

		if (freespace > 0)
		{
			if (rdata->len > freespace)
			{
				memcpy(Insert->currpos, rdata->data, freespace);
				rdata->data += freespace;
				rdata->len -= freespace;
				write_len -= freespace;
			}
			else
			{
				memcpy(Insert->currpos, rdata->data, rdata->len);
				freespace -= rdata->len;
				write_len -= rdata->len;
				Insert->currpos += rdata->len;
				rdata = rdata->next;
				continue;
			}
		}

		/* Use next buffer */
		updrqst = AdvanceXLInsertBuffer(false);
		curridx = Insert->curridx;
		/* Mark page header to indicate this record continues on the page */
		Insert->currpage->xlp_info |= XLP_FIRST_IS_CONTRECORD;
		Insert->currpage->xlp_rem_len = write_len;
		freespace = INSERT_FREESPACE(Insert);
	}

	/* Ensure next record will be properly aligned */
	Insert->currpos = (char *) Insert->currpage +
		MAXALIGN(Insert->currpos - (char *) Insert->currpage);
	freespace = INSERT_FREESPACE(Insert);

	/*
	 * The recptr I return is the beginning of the *next* record. This will be
	 * stored as LSN for changed data pages...
	 */
	INSERT_RECPTR(RecPtr, Insert, curridx);

	/*
	 * If the record is an XLOG_SWITCH, we must now write and flush all the
	 * existing data, and then forcibly advance to the start of the next
	 * segment.  It's not good to do this I/O while holding the insert lock,
	 * but there seems too much risk of confusion if we try to release the
	 * lock sooner.  Fortunately xlog switch needn't be a high-performance
	 * operation anyway...
	 */
	if (isLogSwitch)
	{
		XLogwrtRqst FlushRqst;
		XLogRecPtr	OldSegEnd;

		TRACE_POSTGRESQL_XLOG_SWITCH();

		LWLockAcquire(WALWriteLock, LW_EXCLUSIVE);

		/*
		 * Flush through the end of the page containing XLOG_SWITCH, and
		 * perform end-of-segment actions (eg, notifying archiver).
		 */
		WriteRqst = XLogCtl->xlblocks[curridx];
		FlushRqst.Write = WriteRqst;
		FlushRqst.Flush = WriteRqst;
		XLogWrite(FlushRqst, false, true);

		/* Set up the next buffer as first page of next segment */
		/* Note: AdvanceXLInsertBuffer cannot need to do I/O here */
		(void) AdvanceXLInsertBuffer(true);

		/* There should be no unwritten data */
		curridx = Insert->curridx;
		Assert(curridx == XLogCtl->Write.curridx);

		/* Compute end address of old segment */
		OldSegEnd = XLogCtl->xlblocks[curridx];
		OldSegEnd -= XLOG_BLCKSZ;

		/* Make it look like we've written and synced all of old segment */
		LogwrtResult.Write = OldSegEnd;
		LogwrtResult.Flush = OldSegEnd;

		/*
		 * Update shared-memory status --- this code should match XLogWrite
		 */
		{
			/* use volatile pointer to prevent code rearrangement */
			volatile XLogCtlData *xlogctl = XLogCtl;

			SpinLockAcquire(&xlogctl->info_lck);
			xlogctl->LogwrtResult = LogwrtResult;
			if (XLByteLT(xlogctl->LogwrtRqst.Write, LogwrtResult.Write))
				xlogctl->LogwrtRqst.Write = LogwrtResult.Write;
			if (XLByteLT(xlogctl->LogwrtRqst.Flush, LogwrtResult.Flush))
				xlogctl->LogwrtRqst.Flush = LogwrtResult.Flush;
			SpinLockRelease(&xlogctl->info_lck);
		}

		LWLockRelease(WALWriteLock);

		updrqst = false;		/* done already */
	}
	else
	{
		/* normal case, ie not xlog switch */

		/* Need to update shared LogwrtRqst if some block was filled up */
		if (freespace == 0)
		{
			/* curridx is filled and available for writing out */
			updrqst = true;
		}
		else
		{
			/* if updrqst already set, write through end of previous buf */
			curridx = PrevBufIdx(curridx);
		}
		WriteRqst = XLogCtl->xlblocks[curridx];
	}

	LWLockRelease(WALInsertLock);

	if (updrqst)
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		SpinLockAcquire(&xlogctl->info_lck);
		/* advance global request to include new block(s) */
		if (XLByteLT(xlogctl->LogwrtRqst.Write, WriteRqst))
			xlogctl->LogwrtRqst.Write = WriteRqst;
		/* update local result copy while I have the chance */
		LogwrtResult = xlogctl->LogwrtResult;
		SpinLockRelease(&xlogctl->info_lck);
	}

	XactLastRecEnd = RecPtr;

	END_CRIT_SECTION();

	/* wake up walsenders now that we've released heavily contended locks */
	WalSndWakeupProcessRequests();

	return RecPtr;
}

/*
 * Determine whether the buffer referenced by an XLogRecData item has to
 * be backed up, and if so fill a BkpBlock struct for it.  In any case
 * save the buffer's LSN at *lsn.
 */
static bool
XLogCheckBuffer(XLogRecData *rdata, bool doPageWrites,
				XLogRecPtr *lsn, BkpBlock *bkpb)
{
	Page		page;

	page = BufferGetPage(rdata->buffer);

	/*
	 * XXX We assume page LSN is first data on *every* page that can be passed
	 * to XLogInsert, whether it otherwise has the standard page layout or
	 * not.
	 */
	*lsn = PageGetLSN(page);

	if (doPageWrites &&
		XLByteLE(PageGetLSN(page), RedoRecPtr))
	{
		/*
		 * The page needs to be backed up, so set up *bkpb
		 */
		BufferGetTag(rdata->buffer, &bkpb->node, &bkpb->fork, &bkpb->block);

		if (rdata->buffer_std)
		{
			/* Assume we can omit data between pd_lower and pd_upper */
			uint16		lower = ((PageHeader) page)->pd_lower;
			uint16		upper = ((PageHeader) page)->pd_upper;

			if (lower >= SizeOfPageHeaderData &&
				upper > lower &&
				upper <= BLCKSZ)
			{
				bkpb->hole_offset = lower;
				bkpb->hole_length = upper - lower;
			}
			else
			{
				/* No "hole" to compress out */
				bkpb->hole_offset = 0;
				bkpb->hole_length = 0;
			}
		}
		else
		{
			/* Not a standard page header, don't try to eliminate "hole" */
			bkpb->hole_offset = 0;
			bkpb->hole_length = 0;
		}

		return true;			/* buffer requires backup */
	}

	return false;				/* buffer does not need to be backed up */
}

/*
 * Advance the Insert state to the next buffer page, writing out the next
 * buffer if it still contains unwritten data.
 *
 * If new_segment is TRUE then we set up the next buffer page as the first
 * page of the next xlog segment file, possibly but not usually the next
 * consecutive file page.
 *
 * The global LogwrtRqst.Write pointer needs to be advanced to include the
 * just-filled page.  If we can do this for free (without an extra lock),
 * we do so here.  Otherwise the caller must do it.  We return TRUE if the
 * request update still needs to be done, FALSE if we did it internally.
 *
 * Must be called with WALInsertLock held.
 */
static bool
AdvanceXLInsertBuffer(bool new_segment)
{
	XLogCtlInsert *Insert = &XLogCtl->Insert;
	int			nextidx = NextBufIdx(Insert->curridx);
	bool		update_needed = true;
	XLogRecPtr	OldPageRqstPtr;
	XLogwrtRqst WriteRqst;
	XLogRecPtr	NewPageEndPtr;
	XLogRecPtr	NewPageBeginPtr;
	XLogPageHeader NewPage;

	/*
	 * Get ending-offset of the buffer page we need to replace (this may be
	 * zero if the buffer hasn't been used yet).  Fall through if it's already
	 * written out.
	 */
	OldPageRqstPtr = XLogCtl->xlblocks[nextidx];
	if (!XLByteLE(OldPageRqstPtr, LogwrtResult.Write))
	{
		/* nope, got work to do... */
		XLogRecPtr	FinishedPageRqstPtr;

		FinishedPageRqstPtr = XLogCtl->xlblocks[Insert->curridx];

		/* Before waiting, get info_lck and update LogwrtResult */
		{
			/* use volatile pointer to prevent code rearrangement */
			volatile XLogCtlData *xlogctl = XLogCtl;

			SpinLockAcquire(&xlogctl->info_lck);
			if (XLByteLT(xlogctl->LogwrtRqst.Write, FinishedPageRqstPtr))
				xlogctl->LogwrtRqst.Write = FinishedPageRqstPtr;
			LogwrtResult = xlogctl->LogwrtResult;
			SpinLockRelease(&xlogctl->info_lck);
		}

		update_needed = false;	/* Did the shared-request update */

		/*
		 * Now that we have an up-to-date LogwrtResult value, see if we still
		 * need to write it or if someone else already did.
		 */
		if (!XLByteLE(OldPageRqstPtr, LogwrtResult.Write))
		{
			/* Must acquire write lock */
			LWLockAcquire(WALWriteLock, LW_EXCLUSIVE);
			LogwrtResult = XLogCtl->LogwrtResult;
			if (XLByteLE(OldPageRqstPtr, LogwrtResult.Write))
			{
				/* OK, someone wrote it already */
				LWLockRelease(WALWriteLock);
			}
			else
			{
				/*
				 * Have to write buffers while holding insert lock. This is
				 * not good, so only write as much as we absolutely must.
				 */
				TRACE_POSTGRESQL_WAL_BUFFER_WRITE_DIRTY_START();
				WriteRqst.Write = OldPageRqstPtr;
				WriteRqst.Flush = 0;
				XLogWrite(WriteRqst, false, false);
				LWLockRelease(WALWriteLock);
				TRACE_POSTGRESQL_WAL_BUFFER_WRITE_DIRTY_DONE();
			}
		}
	}

	/*
	 * Now the next buffer slot is free and we can set it up to be the next
	 * output page.
	 */
	NewPageBeginPtr = XLogCtl->xlblocks[Insert->curridx];

	if (new_segment)
	{
		/* force it to a segment start point */
		if (NewPageBeginPtr % XLogSegSize != 0)
			XLByteAdvance(NewPageBeginPtr,
						  XLogSegSize - NewPageBeginPtr % XLogSegSize);
	}

	NewPageEndPtr = NewPageBeginPtr;
	XLByteAdvance(NewPageEndPtr, XLOG_BLCKSZ);
	XLogCtl->xlblocks[nextidx] = NewPageEndPtr;
	NewPage = (XLogPageHeader) (XLogCtl->pages + nextidx * (Size) XLOG_BLCKSZ);

	Insert->curridx = nextidx;
	Insert->currpage = NewPage;

	Insert->currpos = ((char *) NewPage) +SizeOfXLogShortPHD;

	/*
	 * Be sure to re-zero the buffer so that bytes beyond what we've written
	 * will look like zeroes and not valid XLOG records...
	 */
	MemSet((char *) NewPage, 0, XLOG_BLCKSZ);

	/*
	 * Fill the new page's header
	 */
	NewPage   ->xlp_magic = XLOG_PAGE_MAGIC;

	/* NewPage->xlp_info = 0; */	/* done by memset */
	NewPage   ->xlp_tli = ThisTimeLineID;
	NewPage   ->xlp_pageaddr = NewPageBeginPtr;

	/*
	 * If online backup is not in progress, mark the header to indicate that
	 * WAL records beginning in this page have removable backup blocks.  This
	 * allows the WAL archiver to know whether it is safe to compress archived
	 * WAL data by transforming full-block records into the non-full-block
	 * format.	It is sufficient to record this at the page level because we
	 * force a page switch (in fact a segment switch) when starting a backup,
	 * so the flag will be off before any records can be written during the
	 * backup.	At the end of a backup, the last page will be marked as all
	 * unsafe when perhaps only part is unsafe, but at worst the archiver
	 * would miss the opportunity to compress a few records.
	 */
	if (!Insert->forcePageWrites)
		NewPage   ->xlp_info |= XLP_BKP_REMOVABLE;

	/*
	 * If first page of an XLOG segment file, make it a long header.
	 */
	if ((NewPage->xlp_pageaddr % XLogSegSize) == 0)
	{
		XLogLongPageHeader NewLongPage = (XLogLongPageHeader) NewPage;

		NewLongPage->xlp_sysid = ControlFile->system_identifier;
		NewLongPage->xlp_seg_size = XLogSegSize;
		NewLongPage->xlp_xlog_blcksz = XLOG_BLCKSZ;
		NewPage   ->xlp_info |= XLP_LONG_HEADER;

		Insert->currpos = ((char *) NewPage) +SizeOfXLogLongPHD;
	}

	return update_needed;
}

/*
 * Check whether we've consumed enough xlog space that a checkpoint is needed.
 *
 * new_segno indicates a log file that has just been filled up (or read
 * during recovery). We measure the distance from RedoRecPtr to new_segno
 * and see if that exceeds CheckPointSegments.
 *
 * Note: it is caller's responsibility that RedoRecPtr is up-to-date.
 */
static bool
XLogCheckpointNeeded(XLogSegNo new_segno)
{
	XLogSegNo	old_segno;

	XLByteToSeg(RedoRecPtr, old_segno);

	if (new_segno >= old_segno + (uint64) (CheckPointSegments - 1))
		return true;
	return false;
}

/*
 * Write and/or fsync the log at least as far as WriteRqst indicates.
 *
 * If flexible == TRUE, we don't have to write as far as WriteRqst, but
 * may stop at any convenient boundary (such as a cache or logfile boundary).
 * This option allows us to avoid uselessly issuing multiple writes when a
 * single one would do.
 *
 * If xlog_switch == TRUE, we are intending an xlog segment switch, so
 * perform end-of-segment actions after writing the last page, even if
 * it's not physically the end of its segment.  (NB: this will work properly
 * only if caller specifies WriteRqst == page-end and flexible == false,
 * and there is some data to write.)
 *
 * Must be called with WALWriteLock held.
 */
static void
XLogWrite(XLogwrtRqst WriteRqst, bool flexible, bool xlog_switch)
{
	XLogCtlWrite *Write = &XLogCtl->Write;
	bool		ispartialpage;
	bool		last_iteration;
	bool		finishing_seg;
	bool		use_existent;
	int			curridx;
	int			npages;
	int			startidx;
	uint32		startoffset;

	/* We should always be inside a critical section here */
	Assert(CritSectionCount > 0);

	/*
	 * Update local LogwrtResult (caller probably did this already, but...)
	 */
	LogwrtResult = XLogCtl->LogwrtResult;

	/*
	 * Since successive pages in the xlog cache are consecutively allocated,
	 * we can usually gather multiple pages together and issue just one
	 * write() call.  npages is the number of pages we have determined can be
	 * written together; startidx is the cache block index of the first one,
	 * and startoffset is the file offset at which it should go. The latter
	 * two variables are only valid when npages > 0, but we must initialize
	 * all of them to keep the compiler quiet.
	 */
	npages = 0;
	startidx = 0;
	startoffset = 0;

	/*
	 * Within the loop, curridx is the cache block index of the page to
	 * consider writing.  We advance Write->curridx only after successfully
	 * writing pages.  (Right now, this refinement is useless since we are
	 * going to PANIC if any error occurs anyway; but someday it may come in
	 * useful.)
	 */
	curridx = Write->curridx;

	while (XLByteLT(LogwrtResult.Write, WriteRqst.Write))
	{
		/*
		 * Make sure we're not ahead of the insert process.  This could happen
		 * if we're passed a bogus WriteRqst.Write that is past the end of the
		 * last page that's been initialized by AdvanceXLInsertBuffer.
		 */
		if (!XLByteLT(LogwrtResult.Write, XLogCtl->xlblocks[curridx]))
			elog(PANIC, "xlog write request %X/%X is past end of log %X/%X",
				 (uint32) (LogwrtResult.Write >> 32), (uint32) LogwrtResult.Write,
				 (uint32) (XLogCtl->xlblocks[curridx] >> 32),
				 (uint32) XLogCtl->xlblocks[curridx]);

		/* Advance LogwrtResult.Write to end of current buffer page */
		LogwrtResult.Write = XLogCtl->xlblocks[curridx];
		ispartialpage = XLByteLT(WriteRqst.Write, LogwrtResult.Write);

		if (!XLByteInPrevSeg(LogwrtResult.Write, openLogSegNo))
		{
			/*
			 * Switch to new logfile segment.  We cannot have any pending
			 * pages here (since we dump what we have at segment end).
			 */
			Assert(npages == 0);
			if (openLogFile >= 0)
				XLogFileClose();
			XLByteToPrevSeg(LogwrtResult.Write, openLogSegNo);

			/* create/use new log file */
			use_existent = true;
			openLogFile = XLogFileInit(openLogSegNo, &use_existent, true);
			openLogOff = 0;
		}

		/* Make sure we have the current logfile open */
		if (openLogFile < 0)
		{
			XLByteToPrevSeg(LogwrtResult.Write, openLogSegNo);
			openLogFile = XLogFileOpen(openLogSegNo);
			openLogOff = 0;
		}

		/* Add current page to the set of pending pages-to-dump */
		if (npages == 0)
		{
			/* first of group */
			startidx = curridx;
			startoffset = (LogwrtResult.Write - XLOG_BLCKSZ) % XLogSegSize;
		}
		npages++;

		/*
		 * Dump the set if this will be the last loop iteration, or if we are
		 * at the last page of the cache area (since the next page won't be
		 * contiguous in memory), or if we are at the end of the logfile
		 * segment.
		 */
		last_iteration = !XLByteLT(LogwrtResult.Write, WriteRqst.Write);

		finishing_seg = !ispartialpage &&
			(startoffset + npages * XLOG_BLCKSZ) >= XLogSegSize;

		if (last_iteration ||
			curridx == XLogCtl->XLogCacheBlck ||
			finishing_seg)
		{
			char	   *from;
			Size		nbytes;

			/* Need to seek in the file? */
			if (openLogOff != startoffset)
			{
				if (lseek(openLogFile, (off_t) startoffset, SEEK_SET) < 0)
					ereport(PANIC,
							(errcode_for_file_access(),
							 errmsg("could not seek in log file %s to offset %u: %m",
									XLogFileNameP(ThisTimeLineID, openLogSegNo),
									startoffset)));
				openLogOff = startoffset;
			}

			/* OK to write the page(s) */
			from = XLogCtl->pages + startidx * (Size) XLOG_BLCKSZ;
			nbytes = npages * (Size) XLOG_BLCKSZ;
			errno = 0;
			if (write(openLogFile, from, nbytes) != nbytes)
			{
				/* if write didn't set errno, assume no disk space */
				if (errno == 0)
					errno = ENOSPC;
				ereport(PANIC,
						(errcode_for_file_access(),
						 errmsg("could not write to log file %s "
								"at offset %u, length %lu: %m",
								XLogFileNameP(ThisTimeLineID, openLogSegNo),
								openLogOff, (unsigned long) nbytes)));
			}

			/* Update state for write */
			openLogOff += nbytes;
			Write->curridx = ispartialpage ? curridx : NextBufIdx(curridx);
			npages = 0;

			/*
			 * If we just wrote the whole last page of a logfile segment,
			 * fsync the segment immediately.  This avoids having to go back
			 * and re-open prior segments when an fsync request comes along
			 * later. Doing it here ensures that one and only one backend will
			 * perform this fsync.
			 *
			 * We also do this if this is the last page written for an xlog
			 * switch.
			 *
			 * This is also the right place to notify the Archiver that the
			 * segment is ready to copy to archival storage, and to update the
			 * timer for archive_timeout, and to signal for a checkpoint if
			 * too many logfile segments have been used since the last
			 * checkpoint.
			 */
			if (finishing_seg || (xlog_switch && last_iteration))
			{
				issue_xlog_fsync(openLogFile, openLogSegNo);

				/* signal that we need to wakeup walsenders later */
				WalSndWakeupRequest();

				LogwrtResult.Flush = LogwrtResult.Write;		/* end of page */

				if (XLogArchivingActive())
					XLogArchiveNotifySeg(openLogSegNo);

				Write->lastSegSwitchTime = (pg_time_t) time(NULL);

				/*
				 * Request a checkpoint if we've consumed too much xlog since
				 * the last one.  For speed, we first check using the local
				 * copy of RedoRecPtr, which might be out of date; if it looks
				 * like a checkpoint is needed, forcibly update RedoRecPtr and
				 * recheck.
				 */
				if (IsUnderPostmaster && XLogCheckpointNeeded(openLogSegNo))
				{
					(void) GetRedoRecPtr();
					if (XLogCheckpointNeeded(openLogSegNo))
						RequestCheckpoint(CHECKPOINT_CAUSE_XLOG);
				}
			}
		}

		if (ispartialpage)
		{
			/* Only asked to write a partial page */
			LogwrtResult.Write = WriteRqst.Write;
			break;
		}
		curridx = NextBufIdx(curridx);

		/* If flexible, break out of loop as soon as we wrote something */
		if (flexible && npages == 0)
			break;
	}

	Assert(npages == 0);
	Assert(curridx == Write->curridx);

	/*
	 * If asked to flush, do so
	 */
	if (XLByteLT(LogwrtResult.Flush, WriteRqst.Flush) &&
		XLByteLT(LogwrtResult.Flush, LogwrtResult.Write))
	{
		/*
		 * Could get here without iterating above loop, in which case we might
		 * have no open file or the wrong one.	However, we do not need to
		 * fsync more than one file.
		 */
		if (sync_method != SYNC_METHOD_OPEN &&
			sync_method != SYNC_METHOD_OPEN_DSYNC)
		{
			if (openLogFile >= 0 &&
				!XLByteInPrevSeg(LogwrtResult.Write, openLogSegNo))
				XLogFileClose();
			if (openLogFile < 0)
			{
				XLByteToPrevSeg(LogwrtResult.Write, openLogSegNo);
				openLogFile = XLogFileOpen(openLogSegNo);
				openLogOff = 0;
			}

			issue_xlog_fsync(openLogFile, openLogSegNo);
		}

		/* signal that we need to wakeup walsenders later */
		WalSndWakeupRequest();

		LogwrtResult.Flush = LogwrtResult.Write;
	}

	/*
	 * Update shared-memory status
	 *
	 * We make sure that the shared 'request' values do not fall behind the
	 * 'result' values.  This is not absolutely essential, but it saves some
	 * code in a couple of places.
	 */
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		SpinLockAcquire(&xlogctl->info_lck);
		xlogctl->LogwrtResult = LogwrtResult;
		if (XLByteLT(xlogctl->LogwrtRqst.Write, LogwrtResult.Write))
			xlogctl->LogwrtRqst.Write = LogwrtResult.Write;
		if (XLByteLT(xlogctl->LogwrtRqst.Flush, LogwrtResult.Flush))
			xlogctl->LogwrtRqst.Flush = LogwrtResult.Flush;
		SpinLockRelease(&xlogctl->info_lck);
	}
}

/*
 * Record the LSN for an asynchronous transaction commit/abort
 * and nudge the WALWriter if there is work for it to do.
 * (This should not be called for synchronous commits.)
 */
void
XLogSetAsyncXactLSN(XLogRecPtr asyncXactLSN)
{
	XLogRecPtr	WriteRqstPtr = asyncXactLSN;
	bool		sleeping;

	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;

	SpinLockAcquire(&xlogctl->info_lck);
	LogwrtResult = xlogctl->LogwrtResult;
	sleeping = xlogctl->WalWriterSleeping;
	if (XLByteLT(xlogctl->asyncXactLSN, asyncXactLSN))
		xlogctl->asyncXactLSN = asyncXactLSN;
	SpinLockRelease(&xlogctl->info_lck);

	/*
	 * If the WALWriter is sleeping, we should kick it to make it come out of
	 * low-power mode.	Otherwise, determine whether there's a full page of
	 * WAL available to write.
	 */
	if (!sleeping)
	{
		/* back off to last completed page boundary */
		WriteRqstPtr -= WriteRqstPtr % XLOG_BLCKSZ;

		/* if we have already flushed that far, we're done */
		if (XLByteLE(WriteRqstPtr, LogwrtResult.Flush))
			return;
	}

	/*
	 * Nudge the WALWriter: it has a full page of WAL to write, or we want it
	 * to come out of low-power mode so that this async commit will reach disk
	 * within the expected amount of time.
	 */
	if (ProcGlobal->walwriterLatch)
		SetLatch(ProcGlobal->walwriterLatch);
}

/*
 * Advance minRecoveryPoint in control file.
 *
 * If we crash during recovery, we must reach this point again before the
 * database is consistent.
 *
 * If 'force' is true, 'lsn' argument is ignored. Otherwise, minRecoveryPoint
 * is only updated if it's not already greater than or equal to 'lsn'.
 */
static void
UpdateMinRecoveryPoint(XLogRecPtr lsn, bool force)
{
	/* Quick check using our local copy of the variable */
	if (!updateMinRecoveryPoint || (!force && XLByteLE(lsn, minRecoveryPoint)))
		return;

	LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);

	/* update local copy */
	minRecoveryPoint = ControlFile->minRecoveryPoint;

	/*
	 * An invalid minRecoveryPoint means that we need to recover all the WAL,
	 * i.e., we're doing crash recovery.  We never modify the control file's
	 * value in that case, so we can short-circuit future checks here too.
	 */
	if (minRecoveryPoint == 0)
		updateMinRecoveryPoint = false;
	else if (force || XLByteLT(minRecoveryPoint, lsn))
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;
		XLogRecPtr	newMinRecoveryPoint;

		/*
		 * To avoid having to update the control file too often, we update it
		 * all the way to the last record being replayed, even though 'lsn'
		 * would suffice for correctness.  This also allows the 'force' case
		 * to not need a valid 'lsn' value.
		 *
		 * Another important reason for doing it this way is that the passed
		 * 'lsn' value could be bogus, i.e., past the end of available WAL, if
		 * the caller got it from a corrupted heap page.  Accepting such a
		 * value as the min recovery point would prevent us from coming up at
		 * all.  Instead, we just log a warning and continue with recovery.
		 * (See also the comments about corrupt LSNs in XLogFlush.)
		 */
		SpinLockAcquire(&xlogctl->info_lck);
		newMinRecoveryPoint = xlogctl->replayEndRecPtr;
		SpinLockRelease(&xlogctl->info_lck);

		if (!force && XLByteLT(newMinRecoveryPoint, lsn))
			elog(WARNING,
			   "xlog min recovery request %X/%X is past current point %X/%X",
				 (uint32) (lsn >> 32) , (uint32) lsn,
				 (uint32) (newMinRecoveryPoint >> 32),
				 (uint32) newMinRecoveryPoint);

		/* update control file */
		if (XLByteLT(ControlFile->minRecoveryPoint, newMinRecoveryPoint))
		{
			ControlFile->minRecoveryPoint = newMinRecoveryPoint;
			UpdateControlFile();
			minRecoveryPoint = newMinRecoveryPoint;

			ereport(DEBUG2,
					(errmsg("updated min recovery point to %X/%X",
							(uint32) (minRecoveryPoint >> 32),
							(uint32) minRecoveryPoint)));
		}
	}
	LWLockRelease(ControlFileLock);
}

/*
 * Ensure that all XLOG data through the given position is flushed to disk.
 *
 * NOTE: this differs from XLogWrite mainly in that the WALWriteLock is not
 * already held, and we try to avoid acquiring it if possible.
 */
void
XLogFlush(XLogRecPtr record)
{
	XLogRecPtr	WriteRqstPtr;
	XLogwrtRqst WriteRqst;

	/*
	 * During REDO, we are reading not writing WAL.  Therefore, instead of
	 * trying to flush the WAL, we should update minRecoveryPoint instead. We
	 * test XLogInsertAllowed(), not InRecovery, because we need checkpointer
	 * to act this way too, and because when it tries to write the
	 * end-of-recovery checkpoint, it should indeed flush.
	 */
	if (!XLogInsertAllowed())
	{
		UpdateMinRecoveryPoint(record, false);
		return;
	}

	/* Quick exit if already known flushed */
	if (XLByteLE(record, LogwrtResult.Flush))
		return;

#ifdef WAL_DEBUG
	if (XLOG_DEBUG)
		elog(LOG, "xlog flush request %X/%X; write %X/%X; flush %X/%X",
			 (uint32) (record >> 32), (uint32) record,
			 (uint32) (LogwrtResult.Write >> 32), (uint32) LogwrtResult.Write,
			 (uint32) (LogwrtResult.Flush >> 32), (uint32) LogwrtResult.Flush);
#endif

	START_CRIT_SECTION();

	/*
	 * Since fsync is usually a horribly expensive operation, we try to
	 * piggyback as much data as we can on each fsync: if we see any more data
	 * entered into the xlog buffer, we'll write and fsync that too, so that
	 * the final value of LogwrtResult.Flush is as large as possible. This
	 * gives us some chance of avoiding another fsync immediately after.
	 */

	/* initialize to given target; may increase below */
	WriteRqstPtr = record;

	/*
	 * Now wait until we get the write lock, or someone else does the flush
	 * for us.
	 */
	for (;;)
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		/* read LogwrtResult and update local state */
		SpinLockAcquire(&xlogctl->info_lck);
		if (XLByteLT(WriteRqstPtr, xlogctl->LogwrtRqst.Write))
			WriteRqstPtr = xlogctl->LogwrtRqst.Write;
		LogwrtResult = xlogctl->LogwrtResult;
		SpinLockRelease(&xlogctl->info_lck);

		/* done already? */
		if (XLByteLE(record, LogwrtResult.Flush))
			break;

		/*
		 * Try to get the write lock. If we can't get it immediately, wait
		 * until it's released, and recheck if we still need to do the flush
		 * or if the backend that held the lock did it for us already. This
		 * helps to maintain a good rate of group committing when the system
		 * is bottlenecked by the speed of fsyncing.
		 */
		if (!LWLockAcquireOrWait(WALWriteLock, LW_EXCLUSIVE))
		{
			/*
			 * The lock is now free, but we didn't acquire it yet. Before we
			 * do, loop back to check if someone else flushed the record for
			 * us already.
			 */
			continue;
		}

		/* Got the lock; recheck whether request is satisfied */
		LogwrtResult = XLogCtl->LogwrtResult;
		if (XLByteLE(record, LogwrtResult.Flush))
		{
			LWLockRelease(WALWriteLock);
			break;
		}

		/*
		 * Sleep before flush! By adding a delay here, we may give further
		 * backends the opportunity to join the backlog of group commit
		 * followers; this can significantly improve transaction throughput, at
		 * the risk of increasing transaction latency.
		 *
		 * We do not sleep if enableFsync is not turned on, nor if there are
		 * fewer than CommitSiblings other backends with active transactions.
		 */
		if (CommitDelay > 0 && enableFsync &&
			MinimumActiveBackends(CommitSiblings))
			pg_usleep(CommitDelay);

		/* try to write/flush later additions to XLOG as well */
		if (LWLockConditionalAcquire(WALInsertLock, LW_EXCLUSIVE))
		{
			XLogCtlInsert *Insert = &XLogCtl->Insert;
			uint32		freespace = INSERT_FREESPACE(Insert);

			if (freespace == 0)		/* buffer is full */
				WriteRqstPtr = XLogCtl->xlblocks[Insert->curridx];
			else
			{
				WriteRqstPtr = XLogCtl->xlblocks[Insert->curridx];
				WriteRqstPtr -= freespace;
			}
			LWLockRelease(WALInsertLock);
			WriteRqst.Write = WriteRqstPtr;
			WriteRqst.Flush = WriteRqstPtr;
		}
		else
		{
			WriteRqst.Write = WriteRqstPtr;
			WriteRqst.Flush = record;
		}
		XLogWrite(WriteRqst, false, false);

		LWLockRelease(WALWriteLock);
		/* done */
		break;
	}

	END_CRIT_SECTION();

	/* wake up walsenders now that we've released heavily contended locks */
	WalSndWakeupProcessRequests();

	/*
	 * If we still haven't flushed to the request point then we have a
	 * problem; most likely, the requested flush point is past end of XLOG.
	 * This has been seen to occur when a disk page has a corrupted LSN.
	 *
	 * Formerly we treated this as a PANIC condition, but that hurts the
	 * system's robustness rather than helping it: we do not want to take down
	 * the whole system due to corruption on one data page.  In particular, if
	 * the bad page is encountered again during recovery then we would be
	 * unable to restart the database at all!  (This scenario actually
	 * happened in the field several times with 7.1 releases.)	As of 8.4, bad
	 * LSNs encountered during recovery are UpdateMinRecoveryPoint's problem;
	 * the only time we can reach here during recovery is while flushing the
	 * end-of-recovery checkpoint record, and we don't expect that to have a
	 * bad LSN.
	 *
	 * Note that for calls from xact.c, the ERROR will be promoted to PANIC
	 * since xact.c calls this routine inside a critical section.  However,
	 * calls from bufmgr.c are not within critical sections and so we will not
	 * force a restart for a bad LSN on a data page.
	 */
	if (XLByteLT(LogwrtResult.Flush, record))
		elog(ERROR,
		"xlog flush request %X/%X is not satisfied --- flushed only to %X/%X",
			 (uint32) (record >> 32), (uint32) record,
			 (uint32) (LogwrtResult.Flush >> 32), (uint32) LogwrtResult.Flush);
}

/*
 * Flush xlog, but without specifying exactly where to flush to.
 *
 * We normally flush only completed blocks; but if there is nothing to do on
 * that basis, we check for unflushed async commits in the current incomplete
 * block, and flush through the latest one of those.  Thus, if async commits
 * are not being used, we will flush complete blocks only.	We can guarantee
 * that async commits reach disk after at most three cycles; normally only
 * one or two.	(When flushing complete blocks, we allow XLogWrite to write
 * "flexibly", meaning it can stop at the end of the buffer ring; this makes a
 * difference only with very high load or long wal_writer_delay, but imposes
 * one extra cycle for the worst case for async commits.)
 *
 * This routine is invoked periodically by the background walwriter process.
 *
 * Returns TRUE if we flushed anything.
 */
bool
XLogBackgroundFlush(void)
{
	XLogRecPtr	WriteRqstPtr;
	bool		flexible = true;
	bool		wrote_something = false;

	/* XLOG doesn't need flushing during recovery */
	if (RecoveryInProgress())
		return false;

	/* read LogwrtResult and update local state */
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		SpinLockAcquire(&xlogctl->info_lck);
		LogwrtResult = xlogctl->LogwrtResult;
		WriteRqstPtr = xlogctl->LogwrtRqst.Write;
		SpinLockRelease(&xlogctl->info_lck);
	}

	/* back off to last completed page boundary */
	WriteRqstPtr -= WriteRqstPtr % XLOG_BLCKSZ;

	/* if we have already flushed that far, consider async commit records */
	if (XLByteLE(WriteRqstPtr, LogwrtResult.Flush))
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		SpinLockAcquire(&xlogctl->info_lck);
		WriteRqstPtr = xlogctl->asyncXactLSN;
		SpinLockRelease(&xlogctl->info_lck);
		flexible = false;		/* ensure it all gets written */
	}

	/*
	 * If already known flushed, we're done. Just need to check if we are
	 * holding an open file handle to a logfile that's no longer in use,
	 * preventing the file from being deleted.
	 */
	if (XLByteLE(WriteRqstPtr, LogwrtResult.Flush))
	{
		if (openLogFile >= 0)
		{
			if (!XLByteInPrevSeg(LogwrtResult.Write, openLogSegNo))
			{
				XLogFileClose();
			}
		}
		return false;
	}

#ifdef WAL_DEBUG
	if (XLOG_DEBUG)
		elog(LOG, "xlog bg flush request %X/%X; write %X/%X; flush %X/%X",
			 (uint32) (WriteRqstPtr >> 32), (uint32) WriteRqstPtr,
			 (uint32) (LogwrtResult.Write >> 32), (uint32) LogwrtResult.Write,
			 (uint32) (LogwrtResult.Flush >> 32), (uint32) LogwrtResult.Flush);
#endif

	START_CRIT_SECTION();

	/* now wait for the write lock */
	LWLockAcquire(WALWriteLock, LW_EXCLUSIVE);
	LogwrtResult = XLogCtl->LogwrtResult;
	if (!XLByteLE(WriteRqstPtr, LogwrtResult.Flush))
	{
		XLogwrtRqst WriteRqst;

		WriteRqst.Write = WriteRqstPtr;
		WriteRqst.Flush = WriteRqstPtr;
		XLogWrite(WriteRqst, flexible, false);
		wrote_something = true;
	}
	LWLockRelease(WALWriteLock);

	END_CRIT_SECTION();

	/* wake up walsenders now that we've released heavily contended locks */
	WalSndWakeupProcessRequests();

	return wrote_something;
}

/*
 * Test whether XLOG data has been flushed up to (at least) the given position.
 *
 * Returns true if a flush is still needed.  (It may be that someone else
 * is already in process of flushing that far, however.)
 */
bool
XLogNeedsFlush(XLogRecPtr record)
{
	/*
	 * During recovery, we don't flush WAL but update minRecoveryPoint
	 * instead. So "needs flush" is taken to mean whether minRecoveryPoint
	 * would need to be updated.
	 */
	if (RecoveryInProgress())
	{
		/* Quick exit if already known updated */
		if (XLByteLE(record, minRecoveryPoint) || !updateMinRecoveryPoint)
			return false;

		/*
		 * Update local copy of minRecoveryPoint. But if the lock is busy,
		 * just return a conservative guess.
		 */
		if (!LWLockConditionalAcquire(ControlFileLock, LW_SHARED))
			return true;
		minRecoveryPoint = ControlFile->minRecoveryPoint;
		LWLockRelease(ControlFileLock);

		/*
		 * An invalid minRecoveryPoint means that we need to recover all the
		 * WAL, i.e., we're doing crash recovery.  We never modify the control
		 * file's value in that case, so we can short-circuit future checks
		 * here too.
		 */
		if (minRecoveryPoint == 0)
			updateMinRecoveryPoint = false;

		/* check again */
		if (XLByteLE(record, minRecoveryPoint) || !updateMinRecoveryPoint)
			return false;
		else
			return true;
	}

	/* Quick exit if already known flushed */
	if (XLByteLE(record, LogwrtResult.Flush))
		return false;

	/* read LogwrtResult and update local state */
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		SpinLockAcquire(&xlogctl->info_lck);
		LogwrtResult = xlogctl->LogwrtResult;
		SpinLockRelease(&xlogctl->info_lck);
	}

	/* check again */
	if (XLByteLE(record, LogwrtResult.Flush))
		return false;

	return true;
}

/*
 * Create a new XLOG file segment, or open a pre-existing one.
 *
 * log, seg: identify segment to be created/opened.
 *
 * *use_existent: if TRUE, OK to use a pre-existing file (else, any
 * pre-existing file will be deleted).	On return, TRUE if a pre-existing
 * file was used.
 *
 * use_lock: if TRUE, acquire ControlFileLock while moving file into
 * place.  This should be TRUE except during bootstrap log creation.  The
 * caller must *not* hold the lock at call.
 *
 * Returns FD of opened file.
 *
 * Note: errors here are ERROR not PANIC because we might or might not be
 * inside a critical section (eg, during checkpoint there is no reason to
 * take down the system on failure).  They will promote to PANIC if we are
 * in a critical section.
 */
int
XLogFileInit(XLogSegNo logsegno, bool *use_existent, bool use_lock)
{
	char		path[MAXPGPATH];
	char		tmppath[MAXPGPATH];
	char	   *zbuffer;
	XLogSegNo	installed_segno;
	int			max_advance;
	int			fd;
	int			nbytes;

	XLogFilePath(path, ThisTimeLineID, logsegno);

	/*
	 * Try to use existent file (checkpoint maker may have created it already)
	 */
	if (*use_existent)
	{
		fd = BasicOpenFile(path, O_RDWR | PG_BINARY | get_sync_bit(sync_method),
						   S_IRUSR | S_IWUSR);
		if (fd < 0)
		{
			if (errno != ENOENT)
				ereport(ERROR,
						(errcode_for_file_access(),
						 errmsg("could not open file \"%s\": %m", path)));
		}
		else
			return fd;
	}

	/*
	 * Initialize an empty (all zeroes) segment.  NOTE: it is possible that
	 * another process is doing the same thing.  If so, we will end up
	 * pre-creating an extra log segment.  That seems OK, and better than
	 * holding the lock throughout this lengthy process.
	 */
	elog(DEBUG2, "creating and filling new WAL file");

	snprintf(tmppath, MAXPGPATH, XLOGDIR "/xlogtemp.%d", (int) getpid());

	unlink(tmppath);

	/*
	 * Allocate a buffer full of zeros. This is done before opening the file
	 * so that we don't leak the file descriptor if palloc fails.
	 *
	 * Note: palloc zbuffer, instead of just using a local char array, to
	 * ensure it is reasonably well-aligned; this may save a few cycles
	 * transferring data to the kernel.
	 */
	zbuffer = (char *) palloc0(XLOG_BLCKSZ);

	/* do not use get_sync_bit() here --- want to fsync only at end of fill */
	fd = BasicOpenFile(tmppath, O_RDWR | O_CREAT | O_EXCL | PG_BINARY,
					   S_IRUSR | S_IWUSR);
	if (fd < 0)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not create file \"%s\": %m", tmppath)));

	/*
	 * Zero-fill the file.	We have to do this the hard way to ensure that all
	 * the file space has really been allocated --- on platforms that allow
	 * "holes" in files, just seeking to the end doesn't allocate intermediate
	 * space.  This way, we know that we have all the space and (after the
	 * fsync below) that all the indirect blocks are down on disk.	Therefore,
	 * fdatasync(2) or O_DSYNC will be sufficient to sync future writes to the
	 * log file.
	 */
	for (nbytes = 0; nbytes < XLogSegSize; nbytes += XLOG_BLCKSZ)
	{
		errno = 0;
		if ((int) write(fd, zbuffer, XLOG_BLCKSZ) != (int) XLOG_BLCKSZ)
		{
			int			save_errno = errno;

			/*
			 * If we fail to make the file, delete it to release disk space
			 */
			unlink(tmppath);

			close(fd);

			/* if write didn't set errno, assume problem is no disk space */
			errno = save_errno ? save_errno : ENOSPC;

			ereport(ERROR,
					(errcode_for_file_access(),
					 errmsg("could not write to file \"%s\": %m", tmppath)));
		}
	}
	pfree(zbuffer);

	if (pg_fsync(fd) != 0)
	{
		close(fd);
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not fsync file \"%s\": %m", tmppath)));
	}

	if (close(fd))
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not close file \"%s\": %m", tmppath)));

	/*
	 * Now move the segment into place with its final name.
	 *
	 * If caller didn't want to use a pre-existing file, get rid of any
	 * pre-existing file.  Otherwise, cope with possibility that someone else
	 * has created the file while we were filling ours: if so, use ours to
	 * pre-create a future log segment.
	 */
	installed_segno = logsegno;
	max_advance = XLOGfileslop;
	if (!InstallXLogFileSegment(&installed_segno, tmppath,
								*use_existent, &max_advance,
								use_lock))
	{
		/*
		 * No need for any more future segments, or InstallXLogFileSegment()
		 * failed to rename the file into place. If the rename failed, opening
		 * the file below will fail.
		 */
		unlink(tmppath);
	}

	/* Set flag to tell caller there was no existent file */
	*use_existent = false;

	/* Now open original target segment (might not be file I just made) */
	fd = BasicOpenFile(path, O_RDWR | PG_BINARY | get_sync_bit(sync_method),
					   S_IRUSR | S_IWUSR);
	if (fd < 0)
		ereport(ERROR,
				(errcode_for_file_access(),
		   errmsg("could not open file \"%s\": %m", path)));

	elog(DEBUG2, "done creating and filling new WAL file");

	return fd;
}

/*
 * Create a new XLOG file segment by copying a pre-existing one.
 *
 * destsegno: identify segment to be created.
 *
 * srcTLI, srclog, srcseg: identify segment to be copied (could be from
 *		a different timeline)
 *
 * Currently this is only used during recovery, and so there are no locking
 * considerations.	But we should be just as tense as XLogFileInit to avoid
 * emplacing a bogus file.
 */
static void
XLogFileCopy(XLogSegNo destsegno, TimeLineID srcTLI, XLogSegNo srcsegno)
{
	char		path[MAXPGPATH];
	char		tmppath[MAXPGPATH];
	char		buffer[XLOG_BLCKSZ];
	int			srcfd;
	int			fd;
	int			nbytes;

	/*
	 * Open the source file
	 */
	XLogFilePath(path, srcTLI, srcsegno);
	srcfd = OpenTransientFile(path, O_RDONLY | PG_BINARY, 0);
	if (srcfd < 0)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not open file \"%s\": %m", path)));

	/*
	 * Copy into a temp file name.
	 */
	snprintf(tmppath, MAXPGPATH, XLOGDIR "/xlogtemp.%d", (int) getpid());

	unlink(tmppath);

	/* do not use get_sync_bit() here --- want to fsync only at end of fill */
	fd = OpenTransientFile(tmppath, O_RDWR | O_CREAT | O_EXCL | PG_BINARY,
						   S_IRUSR | S_IWUSR);
	if (fd < 0)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not create file \"%s\": %m", tmppath)));

	/*
	 * Do the data copying.
	 */
	for (nbytes = 0; nbytes < XLogSegSize; nbytes += sizeof(buffer))
	{
		errno = 0;
		if ((int) read(srcfd, buffer, sizeof(buffer)) != (int) sizeof(buffer))
		{
			if (errno != 0)
				ereport(ERROR,
						(errcode_for_file_access(),
						 errmsg("could not read file \"%s\": %m", path)));
			else
				ereport(ERROR,
						(errmsg("not enough data in file \"%s\"", path)));
		}
		errno = 0;
		if ((int) write(fd, buffer, sizeof(buffer)) != (int) sizeof(buffer))
		{
			int			save_errno = errno;

			/*
			 * If we fail to make the file, delete it to release disk space
			 */
			unlink(tmppath);
			/* if write didn't set errno, assume problem is no disk space */
			errno = save_errno ? save_errno : ENOSPC;

			ereport(ERROR,
					(errcode_for_file_access(),
					 errmsg("could not write to file \"%s\": %m", tmppath)));
		}
	}

	if (pg_fsync(fd) != 0)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not fsync file \"%s\": %m", tmppath)));

	if (CloseTransientFile(fd))
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not close file \"%s\": %m", tmppath)));

	CloseTransientFile(srcfd);

	/*
	 * Now move the segment into place with its final name.
	 */
	if (!InstallXLogFileSegment(&destsegno, tmppath, false, NULL, false))
		elog(ERROR, "InstallXLogFileSegment should not have failed");
}

/*
 * Install a new XLOG segment file as a current or future log segment.
 *
 * This is used both to install a newly-created segment (which has a temp
 * filename while it's being created) and to recycle an old segment.
 *
 * *segno: identify segment to install as (or first possible target).
 * When find_free is TRUE, this is modified on return to indicate the
 * actual installation location or last segment searched.
 *
 * tmppath: initial name of file to install.  It will be renamed into place.
 *
 * find_free: if TRUE, install the new segment at the first empty segno
 * number at or after the passed numbers.  If FALSE, install the new segment
 * exactly where specified, deleting any existing segment file there.
 *
 * *max_advance: maximum number of segno slots to advance past the starting
 * point.  Fail if no free slot is found in this range.  On return, reduced
 * by the number of slots skipped over.  (Irrelevant, and may be NULL,
 * when find_free is FALSE.)
 *
 * use_lock: if TRUE, acquire ControlFileLock while moving file into
 * place.  This should be TRUE except during bootstrap log creation.  The
 * caller must *not* hold the lock at call.
 *
 * Returns TRUE if the file was installed successfully.  FALSE indicates that
 * max_advance limit was exceeded, or an error occurred while renaming the
 * file into place.
 */
static bool
InstallXLogFileSegment(XLogSegNo *segno, char *tmppath,
					   bool find_free, int *max_advance,
					   bool use_lock)
{
	char		path[MAXPGPATH];
	struct stat stat_buf;

	XLogFilePath(path, ThisTimeLineID, *segno);

	/*
	 * We want to be sure that only one process does this at a time.
	 */
	if (use_lock)
		LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);

	if (!find_free)
	{
		/* Force installation: get rid of any pre-existing segment file */
		unlink(path);
	}
	else
	{
		/* Find a free slot to put it in */
		while (stat(path, &stat_buf) == 0)
		{
			if (*max_advance <= 0)
			{
				/* Failed to find a free slot within specified range */
				if (use_lock)
					LWLockRelease(ControlFileLock);
				return false;
			}
			(*segno)++;
			(*max_advance)--;
			XLogFilePath(path, ThisTimeLineID, *segno);
		}
	}

	/*
	 * Prefer link() to rename() here just to be really sure that we don't
	 * overwrite an existing logfile.  However, there shouldn't be one, so
	 * rename() is an acceptable substitute except for the truly paranoid.
	 */
#if HAVE_WORKING_LINK
	if (link(tmppath, path) < 0)
	{
		if (use_lock)
			LWLockRelease(ControlFileLock);
		ereport(LOG,
				(errcode_for_file_access(),
				 errmsg("could not link file \"%s\" to \"%s\" (initialization of log file): %m",
						tmppath, path)));
		return false;
	}
	unlink(tmppath);
#else
	if (rename(tmppath, path) < 0)
	{
		if (use_lock)
			LWLockRelease(ControlFileLock);
		ereport(LOG,
				(errcode_for_file_access(),
				 errmsg("could not rename file \"%s\" to \"%s\" (initialization of log file): %m",
						tmppath, path)));
		return false;
	}
#endif

	if (use_lock)
		LWLockRelease(ControlFileLock);

	return true;
}

/*
 * Open a pre-existing logfile segment for writing.
 */
int
XLogFileOpen(XLogSegNo segno)
{
	char		path[MAXPGPATH];
	int			fd;

	XLogFilePath(path, ThisTimeLineID, segno);

	fd = BasicOpenFile(path, O_RDWR | PG_BINARY | get_sync_bit(sync_method),
					   S_IRUSR | S_IWUSR);
	if (fd < 0)
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not open xlog file \"%s\": %m", path)));

	return fd;
}

/*
 * Open a logfile segment for reading (during recovery).
 *
 * If source = XLOG_FROM_ARCHIVE, the segment is retrieved from archive.
 * Otherwise, it's assumed to be already available in pg_xlog.
 */
static int
XLogFileRead(XLogSegNo segno, int emode, TimeLineID tli,
			 int source, bool notfoundOk)
{
	char		xlogfname[MAXFNAMELEN];
	char		activitymsg[MAXFNAMELEN + 16];
	char		path[MAXPGPATH];
	int			fd;

	XLogFileName(xlogfname, tli, segno);

	switch (source)
	{
		case XLOG_FROM_ARCHIVE:
			/* Report recovery progress in PS display */
			snprintf(activitymsg, sizeof(activitymsg), "waiting for %s",
					 xlogfname);
			set_ps_display(activitymsg, false);

			restoredFromArchive = RestoreArchivedFile(path, xlogfname,
													  "RECOVERYXLOG",
													  XLogSegSize,
													  InRedo);
			if (!restoredFromArchive)
				return -1;
			break;

		case XLOG_FROM_PG_XLOG:
		case XLOG_FROM_STREAM:
			XLogFilePath(path, tli, segno);
			restoredFromArchive = false;
			break;

		default:
			elog(ERROR, "invalid XLogFileRead source %d", source);
	}

	/*
	 * If the segment was fetched from archival storage, replace the existing
	 * xlog segment (if any) with the archival version.
	 */
	if (source == XLOG_FROM_ARCHIVE)
	{
		char		xlogfpath[MAXPGPATH];
		bool		reload = false;
		struct stat statbuf;

		XLogFilePath(xlogfpath, tli, segno);
		if (stat(xlogfpath, &statbuf) == 0)
		{
			char oldpath[MAXPGPATH];
#ifdef WIN32
			static unsigned int deletedcounter = 1;
			/*
			 * On Windows, if another process (e.g a walsender process) holds
			 * the file open in FILE_SHARE_DELETE mode, unlink will succeed,
			 * but the file will still show up in directory listing until the
			 * last handle is closed, and we cannot rename the new file in its
			 * place until that. To avoid that problem, rename the old file to
			 * a temporary name first. Use a counter to create a unique
			 * filename, because the same file might be restored from the
			 * archive multiple times, and a walsender could still be holding
			 * onto an old deleted version of it.
			 */
			snprintf(oldpath, MAXPGPATH, "%s.deleted%u",
					 xlogfpath, deletedcounter++);
			if (rename(xlogfpath, oldpath) != 0)
			{
				ereport(ERROR,
						(errcode_for_file_access(),
						 errmsg("could not rename file \"%s\" to \"%s\": %m",
								xlogfpath, oldpath)));
			}
#else
			strncpy(oldpath, xlogfpath, MAXPGPATH);
#endif
			if (unlink(oldpath) != 0)
				ereport(FATAL,
						(errcode_for_file_access(),
						 errmsg("could not remove file \"%s\": %m",
								xlogfpath)));
			reload = true;
		}

		if (rename(path, xlogfpath) < 0)
			ereport(ERROR,
					(errcode_for_file_access(),
					 errmsg("could not rename file \"%s\" to \"%s\": %m",
							path, xlogfpath)));

		/*
		 * Set path to point at the new file in pg_xlog.
		 */
		strncpy(path, xlogfpath, MAXPGPATH);

		/*
		 * If the existing segment was replaced, since walsenders might have
		 * it open, request them to reload a currently-open segment.
		 */
		if (reload)
			WalSndRqstFileReload();

		/* Signal walsender that new WAL has arrived */
		if (AllowCascadeReplication())
			WalSndWakeup();
	}

	fd = BasicOpenFile(path, O_RDONLY | PG_BINARY, 0);
	if (fd >= 0)
	{
		/* Success! */
		curFileTLI = tli;

		/* Report recovery progress in PS display */
		snprintf(activitymsg, sizeof(activitymsg), "recovering %s",
				 xlogfname);
		set_ps_display(activitymsg, false);

		/* Track source of data in assorted state variables */
		readSource = source;
		XLogReceiptSource = source;
		/* In FROM_STREAM case, caller tracks receipt time, not me */
		if (source != XLOG_FROM_STREAM)
			XLogReceiptTime = GetCurrentTimestamp();

		/* The file header needs to be validated on first access */
		readFileHeaderValidated = false;

		return fd;
	}
	if (errno != ENOENT || !notfoundOk) /* unexpected failure? */
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not open file \"%s\": %m", path)));
	return -1;
}

/*
 * Open a logfile segment for reading (during recovery).
 *
 * This version searches for the segment with any TLI listed in expectedTLIs.
 */
static int
XLogFileReadAnyTLI(XLogSegNo segno, int emode, int sources)
{
	char		path[MAXPGPATH];
	ListCell   *cell;
	int			fd;

	/*
	 * Loop looking for a suitable timeline ID: we might need to read any of
	 * the timelines listed in expectedTLIs.
	 *
	 * We expect curFileTLI on entry to be the TLI of the preceding file in
	 * sequence, or 0 if there was no predecessor.	We do not allow curFileTLI
	 * to go backwards; this prevents us from picking up the wrong file when a
	 * parent timeline extends to higher segment numbers than the child we
	 * want to read.
	 */
	foreach(cell, expectedTLIs)
	{
		TimeLineID	tli = (TimeLineID) lfirst_int(cell);

		if (tli < curFileTLI)
			break;				/* don't bother looking at too-old TLIs */

		if (sources & XLOG_FROM_ARCHIVE)
		{
			fd = XLogFileRead(segno, emode, tli, XLOG_FROM_ARCHIVE, true);
			if (fd != -1)
			{
				elog(DEBUG1, "got WAL segment from archive");
				return fd;
			}
		}

		if (sources & XLOG_FROM_PG_XLOG)
		{
			fd = XLogFileRead(segno, emode, tli, XLOG_FROM_PG_XLOG, true);
			if (fd != -1)
				return fd;
		}
	}

	/* Couldn't find it.  For simplicity, complain about front timeline */
	XLogFilePath(path, recoveryTargetTLI, segno);
	errno = ENOENT;
	ereport(emode,
			(errcode_for_file_access(),
			 errmsg("could not open file \"%s\": %m", path)));
	return -1;
}

/*
 * Close the current logfile segment for writing.
 */
static void
XLogFileClose(void)
{
	Assert(openLogFile >= 0);

	/*
	 * WAL segment files will not be re-read in normal operation, so we advise
	 * the OS to release any cached pages.	But do not do so if WAL archiving
	 * or streaming is active, because archiver and walsender process could
	 * use the cache to read the WAL segment.
	 */
#if defined(USE_POSIX_FADVISE) && defined(POSIX_FADV_DONTNEED)
	if (!XLogIsNeeded())
		(void) posix_fadvise(openLogFile, 0, 0, POSIX_FADV_DONTNEED);
#endif

	if (close(openLogFile))
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not close log file %s: %m",
						XLogFileNameP(ThisTimeLineID, openLogSegNo))));
	openLogFile = -1;
}

/*
 * Preallocate log files beyond the specified log endpoint.
 *
 * XXX this is currently extremely conservative, since it forces only one
 * future log segment to exist, and even that only if we are 75% done with
 * the current one.  This is only appropriate for very low-WAL-volume systems.
 * High-volume systems will be OK once they've built up a sufficient set of
 * recycled log segments, but the startup transient is likely to include
 * a lot of segment creations by foreground processes, which is not so good.
 */
static void
PreallocXlogFiles(XLogRecPtr endptr)
{
	XLogSegNo	_logSegNo;
	int			lf;
	bool		use_existent;

	XLByteToPrevSeg(endptr, _logSegNo);
	if ((endptr - 1) % XLogSegSize >= (uint32) (0.75 * XLogSegSize))
	{
		_logSegNo++;
		use_existent = true;
		lf = XLogFileInit(_logSegNo, &use_existent, true);
		close(lf);
		if (!use_existent)
			CheckpointStats.ckpt_segs_added++;
	}
}

/*
 * Get the segno of the latest removed or recycled WAL segment.
 * Returns 0/0 if no WAL segments have been removed since startup.
 */
void
XLogGetLastRemoved(XLogSegNo *segno)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;

	SpinLockAcquire(&xlogctl->info_lck);
	*segno = xlogctl->lastRemovedSegNo;
	SpinLockRelease(&xlogctl->info_lck);
}

/*
 * Update the last removed segno pointer in shared memory, to reflect
 * that the given XLOG file has been removed.
 */
static void
UpdateLastRemovedPtr(char *filename)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;
	uint32		tli;
	XLogSegNo	segno;

	XLogFromFileName(filename, &tli, &segno);

	SpinLockAcquire(&xlogctl->info_lck);
	if (segno > xlogctl->lastRemovedSegNo)
		xlogctl->lastRemovedSegNo = segno;
	SpinLockRelease(&xlogctl->info_lck);
}

/*
 * Recycle or remove all log files older or equal to passed segno
 *
 * endptr is current (or recent) end of xlog; this is used to determine
 * whether we want to recycle rather than delete no-longer-wanted log files.
 */
static void
RemoveOldXlogFiles(XLogSegNo segno, XLogRecPtr endptr)
{
	XLogSegNo	endlogSegNo;
	int			max_advance;
	DIR		   *xldir;
	struct dirent *xlde;
	char		lastoff[MAXFNAMELEN];
	char		path[MAXPGPATH];

#ifdef WIN32
	char		newpath[MAXPGPATH];
#endif
	struct stat statbuf;

	/*
	 * Initialize info about where to try to recycle to.  We allow recycling
	 * segments up to XLOGfileslop segments beyond the current XLOG location.
	 */
	XLByteToPrevSeg(endptr, endlogSegNo);
	max_advance = XLOGfileslop;

	xldir = AllocateDir(XLOGDIR);
	if (xldir == NULL)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not open transaction log directory \"%s\": %m",
						XLOGDIR)));

	XLogFileName(lastoff, ThisTimeLineID, segno);

	elog(DEBUG2, "attempting to remove WAL segments older than log file %s",
		 lastoff);

	while ((xlde = ReadDir(xldir, XLOGDIR)) != NULL)
	{
		/*
		 * We ignore the timeline part of the XLOG segment identifiers in
		 * deciding whether a segment is still needed.	This ensures that we
		 * won't prematurely remove a segment from a parent timeline. We could
		 * probably be a little more proactive about removing segments of
		 * non-parent timelines, but that would be a whole lot more
		 * complicated.
		 *
		 * We use the alphanumeric sorting property of the filenames to decide
		 * which ones are earlier than the lastoff segment.
		 */
		if (strlen(xlde->d_name) == 24 &&
			strspn(xlde->d_name, "0123456789ABCDEF") == 24 &&
			strcmp(xlde->d_name + 8, lastoff + 8) <= 0)
		{
			if (RecoveryInProgress() || XLogArchiveCheckDone(xlde->d_name))
			{
				snprintf(path, MAXPGPATH, XLOGDIR "/%s", xlde->d_name);

				/* Update the last removed location in shared memory first */
				UpdateLastRemovedPtr(xlde->d_name);

				/*
				 * Before deleting the file, see if it can be recycled as a
				 * future log segment. Only recycle normal files, pg_standby
				 * for example can create symbolic links pointing to a
				 * separate archive directory.
				 */
				if (lstat(path, &statbuf) == 0 && S_ISREG(statbuf.st_mode) &&
					InstallXLogFileSegment(&endlogSegNo, path,
										   true, &max_advance, true))
				{
					ereport(DEBUG2,
							(errmsg("recycled transaction log file \"%s\"",
									xlde->d_name)));
					CheckpointStats.ckpt_segs_recycled++;
					/* Needn't recheck that slot on future iterations */
					if (max_advance > 0)
					{
						endlogSegNo++;
						max_advance--;
					}
				}
				else
				{
					/* No need for any more future segments... */
					int			rc;

					ereport(DEBUG2,
							(errmsg("removing transaction log file \"%s\"",
									xlde->d_name)));

#ifdef WIN32

					/*
					 * On Windows, if another process (e.g another backend)
					 * holds the file open in FILE_SHARE_DELETE mode, unlink
					 * will succeed, but the file will still show up in
					 * directory listing until the last handle is closed. To
					 * avoid confusing the lingering deleted file for a live
					 * WAL file that needs to be archived, rename it before
					 * deleting it.
					 *
					 * If another process holds the file open without
					 * FILE_SHARE_DELETE flag, rename will fail. We'll try
					 * again at the next checkpoint.
					 */
					snprintf(newpath, MAXPGPATH, "%s.deleted", path);
					if (rename(path, newpath) != 0)
					{
						ereport(LOG,
								(errcode_for_file_access(),
								 errmsg("could not rename old transaction log file \"%s\": %m",
										path)));
						continue;
					}
					rc = unlink(newpath);
#else
					rc = unlink(path);
#endif
					if (rc != 0)
					{
						ereport(LOG,
								(errcode_for_file_access(),
								 errmsg("could not remove old transaction log file \"%s\": %m",
										path)));
						continue;
					}
					CheckpointStats.ckpt_segs_removed++;
				}

				XLogArchiveCleanup(xlde->d_name);
			}
		}
	}

	FreeDir(xldir);
}

/*
 * Verify whether pg_xlog and pg_xlog/archive_status exist.
 * If the latter does not exist, recreate it.
 *
 * It is not the goal of this function to verify the contents of these
 * directories, but to help in cases where someone has performed a cluster
 * copy for PITR purposes but omitted pg_xlog from the copy.
 *
 * We could also recreate pg_xlog if it doesn't exist, but a deliberate
 * policy decision was made not to.  It is fairly common for pg_xlog to be
 * a symlink, and if that was the DBA's intent then automatically making a
 * plain directory would result in degraded performance with no notice.
 */
static void
ValidateXLOGDirectoryStructure(void)
{
	char		path[MAXPGPATH];
	struct stat stat_buf;

	/* Check for pg_xlog; if it doesn't exist, error out */
	if (stat(XLOGDIR, &stat_buf) != 0 ||
		!S_ISDIR(stat_buf.st_mode))
		ereport(FATAL,
				(errmsg("required WAL directory \"%s\" does not exist",
						XLOGDIR)));

	/* Check for archive_status */
	snprintf(path, MAXPGPATH, XLOGDIR "/archive_status");
	if (stat(path, &stat_buf) == 0)
	{
		/* Check for weird cases where it exists but isn't a directory */
		if (!S_ISDIR(stat_buf.st_mode))
			ereport(FATAL,
					(errmsg("required WAL directory \"%s\" does not exist",
							path)));
	}
	else
	{
		ereport(LOG,
				(errmsg("creating missing WAL directory \"%s\"", path)));
		if (mkdir(path, S_IRWXU) < 0)
			ereport(FATAL,
					(errmsg("could not create missing directory \"%s\": %m",
							path)));
	}
}

/*
 * Remove previous backup history files.  This also retries creation of
 * .ready files for any backup history files for which XLogArchiveNotify
 * failed earlier.
 */
static void
CleanupBackupHistory(void)
{
	DIR		   *xldir;
	struct dirent *xlde;
	char		path[MAXPGPATH];

	xldir = AllocateDir(XLOGDIR);
	if (xldir == NULL)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not open transaction log directory \"%s\": %m",
						XLOGDIR)));

	while ((xlde = ReadDir(xldir, XLOGDIR)) != NULL)
	{
		if (strlen(xlde->d_name) > 24 &&
			strspn(xlde->d_name, "0123456789ABCDEF") == 24 &&
			strcmp(xlde->d_name + strlen(xlde->d_name) - strlen(".backup"),
				   ".backup") == 0)
		{
			if (XLogArchiveCheckDone(xlde->d_name))
			{
				ereport(DEBUG2,
				(errmsg("removing transaction log backup history file \"%s\"",
						xlde->d_name)));
				snprintf(path, MAXPGPATH, XLOGDIR "/%s", xlde->d_name);
				unlink(path);
				XLogArchiveCleanup(xlde->d_name);
			}
		}
	}

	FreeDir(xldir);
}

/*
 * Restore a full-page image from a backup block attached to an XLOG record.
 *
 * lsn: LSN of the XLOG record being replayed
 * record: the complete XLOG record
 * block_index: which backup block to restore (0 .. XLR_MAX_BKP_BLOCKS - 1)
 * get_cleanup_lock: TRUE to get a cleanup rather than plain exclusive lock
 * keep_buffer: TRUE to return the buffer still locked and pinned
 *
 * Returns the buffer number containing the page.  Note this is not terribly
 * useful unless keep_buffer is specified as TRUE.
 *
 * Note: when a backup block is available in XLOG, we restore it
 * unconditionally, even if the page in the database appears newer.
 * This is to protect ourselves against database pages that were partially
 * or incorrectly written during a crash.  We assume that the XLOG data
 * must be good because it has passed a CRC check, while the database
 * page might not be.  This will force us to replay all subsequent
 * modifications of the page that appear in XLOG, rather than possibly
 * ignoring them as already applied, but that's not a huge drawback.
 *
 * If 'get_cleanup_lock' is true, a cleanup lock is obtained on the buffer,
 * else a normal exclusive lock is used.  During crash recovery, that's just
 * pro forma because there can't be any regular backends in the system, but
 * in hot standby mode the distinction is important.
 *
 * If 'keep_buffer' is true, return without releasing the buffer lock and pin;
 * then caller is responsible for doing UnlockReleaseBuffer() later.  This
 * is needed in some cases when replaying XLOG records that touch multiple
 * pages, to prevent inconsistent states from being visible to other backends.
 * (Again, that's only important in hot standby mode.)
 */
Buffer
RestoreBackupBlock(XLogRecPtr lsn, XLogRecord *record, int block_index,
				   bool get_cleanup_lock, bool keep_buffer)
{
	Buffer		buffer;
	Page		page;
	BkpBlock	bkpb;
	char	   *blk;
	int			i;

	/* Locate requested BkpBlock in the record */
	blk = (char *) XLogRecGetData(record) + record->xl_len;
	for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
	{
		if (!(record->xl_info & XLR_BKP_BLOCK(i)))
			continue;

		memcpy(&bkpb, blk, sizeof(BkpBlock));
		blk += sizeof(BkpBlock);

		if (i == block_index)
		{
			/* Found it, apply the update */
			buffer = XLogReadBufferExtended(bkpb.node, bkpb.fork, bkpb.block,
											RBM_ZERO);
			Assert(BufferIsValid(buffer));
			if (get_cleanup_lock)
				LockBufferForCleanup(buffer);
			else
				LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);

			page = (Page) BufferGetPage(buffer);

			if (bkpb.hole_length == 0)
			{
				memcpy((char *) page, blk, BLCKSZ);
			}
			else
			{
				memcpy((char *) page, blk, bkpb.hole_offset);
				/* must zero-fill the hole */
				MemSet((char *) page + bkpb.hole_offset, 0, bkpb.hole_length);
				memcpy((char *) page + (bkpb.hole_offset + bkpb.hole_length),
					   blk + bkpb.hole_offset,
					   BLCKSZ - (bkpb.hole_offset + bkpb.hole_length));
			}

			PageSetLSN(page, lsn);
			PageSetTLI(page, ThisTimeLineID);
			MarkBufferDirty(buffer);

			if (!keep_buffer)
				UnlockReleaseBuffer(buffer);

			return buffer;
		}

		blk += BLCKSZ - bkpb.hole_length;
	}

	/* Caller specified a bogus block_index */
	elog(ERROR, "failed to restore block_index %d", block_index);
	return InvalidBuffer;		/* keep compiler quiet */
}

/*
 * CRC-check an XLOG record.  We do not believe the contents of an XLOG
 * record (other than to the minimal extent of computing the amount of
 * data to read in) until we've checked the CRCs.
 *
 * We assume all of the record (that is, xl_tot_len bytes) has been read
 * into memory at *record.  Also, ValidXLogRecordHeader() has accepted the
 * record's header, which means in particular that xl_tot_len is at least
 * SizeOfXlogRecord, so it is safe to fetch xl_len.
 */
static bool
RecordIsValid(XLogRecord *record, XLogRecPtr recptr, int emode)
{
	pg_crc32	crc;
	int			i;
	uint32		len = record->xl_len;
	BkpBlock	bkpb;
	char	   *blk;
	size_t		remaining = record->xl_tot_len;

	/* First the rmgr data */
	if (remaining < SizeOfXLogRecord + len)
	{
		/* ValidXLogRecordHeader() should've caught this already... */
		ereport(emode_for_corrupt_record(emode, recptr),
				(errmsg("invalid record length at %X/%X",
						(uint32) (recptr >> 32), (uint32) recptr)));
		return false;
	}
	remaining -= SizeOfXLogRecord + len;
	INIT_CRC32(crc);
	COMP_CRC32(crc, XLogRecGetData(record), len);

	/* Add in the backup blocks, if any */
	blk = (char *) XLogRecGetData(record) + len;
	for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
	{
		uint32		blen;

		if (!(record->xl_info & XLR_BKP_BLOCK(i)))
			continue;

		if (remaining < sizeof(BkpBlock))
		{
			ereport(emode_for_corrupt_record(emode, recptr),
					(errmsg("invalid backup block size in record at %X/%X",
							(uint32) (recptr >> 32), (uint32) recptr)));
			return false;
		}
		memcpy(&bkpb, blk, sizeof(BkpBlock));

		if (bkpb.hole_offset + bkpb.hole_length > BLCKSZ)
		{
			ereport(emode_for_corrupt_record(emode, recptr),
					(errmsg("incorrect hole size in record at %X/%X",
							(uint32) (recptr >> 32), (uint32) recptr)));
			return false;
		}
		blen = sizeof(BkpBlock) + BLCKSZ - bkpb.hole_length;

		if (remaining < blen)
		{
			ereport(emode_for_corrupt_record(emode, recptr),
					(errmsg("invalid backup block size in record at %X/%X",
							(uint32) (recptr >> 32), (uint32) recptr)));
			return false;
		}
		remaining -= blen;
		COMP_CRC32(crc, blk, blen);
		blk += blen;
	}

	/* Check that xl_tot_len agrees with our calculation */
	if (remaining != 0)
	{
		ereport(emode_for_corrupt_record(emode, recptr),
				(errmsg("incorrect total length in record at %X/%X",
						(uint32) (recptr >> 32), (uint32) recptr)));
		return false;
	}

	/* Finally include the record header */
	COMP_CRC32(crc, (char *) record, offsetof(XLogRecord, xl_crc));
	FIN_CRC32(crc);

	if (!EQ_CRC32(record->xl_crc, crc))
	{
		ereport(emode_for_corrupt_record(emode, recptr),
		(errmsg("incorrect resource manager data checksum in record at %X/%X",
				(uint32) (recptr >> 32), (uint32) recptr)));
		return false;
	}

	return true;
}

/*
 * Attempt to read an XLOG record.
 *
 * If RecPtr is not NULL, try to read a record at that position.  Otherwise
 * try to read a record just after the last one previously read.
 *
 * If no valid record is available, returns NULL, or fails if emode is PANIC.
 * (emode must be either PANIC, LOG)
 *
 * The record is copied into readRecordBuf, so that on successful return,
 * the returned record pointer always points there.
 */
static XLogRecord *
ReadRecord(XLogRecPtr *RecPtr, int emode, bool fetching_ckpt)
{
	XLogRecord *record;
	XLogRecPtr	tmpRecPtr = EndRecPtr;
	bool		randAccess = false;
	uint32		len,
				total_len;
	uint32		targetRecOff;
	uint32		pageHeaderSize;
	bool		gotheader;

	if (readBuf == NULL)
	{
		/*
		 * First time through, permanently allocate readBuf.  We do it this
		 * way, rather than just making a static array, for two reasons: (1)
		 * no need to waste the storage in most instantiations of the backend;
		 * (2) a static char array isn't guaranteed to have any particular
		 * alignment, whereas malloc() will provide MAXALIGN'd storage.
		 */
		readBuf = (char *) malloc(XLOG_BLCKSZ);
		Assert(readBuf != NULL);
	}

	if (RecPtr == NULL)
	{
		RecPtr = &tmpRecPtr;

		/*
		 * RecPtr is pointing to end+1 of the previous WAL record.  If
		 * we're at a page boundary, no more records can fit on the current
		 * page. We must skip over the page header, but we can't do that
		 * until we've read in the page, since the header size is variable.
		 */
	}
	else
	{
		/*
		 * In this case, the passed-in record pointer should already be
		 * pointing to a valid record starting position.
		 */
		if (!XRecOffIsValid(*RecPtr))
			ereport(PANIC,
					(errmsg("invalid record offset at %X/%X",
							(uint32) (*RecPtr >> 32), (uint32) *RecPtr)));

		/*
		 * Since we are going to a random position in WAL, forget any prior
		 * state about what timeline we were in, and allow it to be any
		 * timeline in expectedTLIs.  We also set a flag to allow curFileTLI
		 * to go backwards (but we can't reset that variable right here, since
		 * we might not change files at all).
		 */
		/* see comment in ValidXLogPageHeader */
		lastPageTLI = lastSegmentTLI = 0;
		randAccess = true;		/* allow curFileTLI to go backwards too */
	}

	/* This is the first try to read this page. */
	failedSources = 0;
retry:
	/* Read the page containing the record */
	if (!XLogPageRead(RecPtr, emode, fetching_ckpt, randAccess))
		return NULL;

	pageHeaderSize = XLogPageHeaderSize((XLogPageHeader) readBuf);
	targetRecOff = (*RecPtr) % XLOG_BLCKSZ;
	if (targetRecOff == 0)
	{
		/*
		 * At page start, so skip over page header.  The Assert checks that
		 * we're not scribbling on caller's record pointer; it's OK because we
		 * can only get here in the continuing-from-prev-record case, since
		 * XRecOffIsValid rejected the zero-page-offset case otherwise.
		 */
		Assert(RecPtr == &tmpRecPtr);
		(*RecPtr) += pageHeaderSize;
		targetRecOff = pageHeaderSize;
	}
	else if (targetRecOff < pageHeaderSize)
	{
		ereport(emode_for_corrupt_record(emode, *RecPtr),
				(errmsg("invalid record offset at %X/%X",
						(uint32) ((*RecPtr) >> 32), (uint32) *RecPtr)));
		goto next_record_is_invalid;
	}
	if ((((XLogPageHeader) readBuf)->xlp_info & XLP_FIRST_IS_CONTRECORD) &&
		targetRecOff == pageHeaderSize)
	{
		ereport(emode_for_corrupt_record(emode, *RecPtr),
				(errmsg("contrecord is requested by %X/%X",
						(uint32) ((*RecPtr) >> 32), (uint32) *RecPtr)));
		goto next_record_is_invalid;
	}

	/*
	 * Read the record length.
	 *
	 * NB: Even though we use an XLogRecord pointer here, the whole record
	 * header might not fit on this page. xl_tot_len is the first field of
	 * the struct, so it must be on this page (the records are MAXALIGNed),
	 * but we cannot access any other fields until we've verified that we
	 * got the whole header.
	 */
	record = (XLogRecord *) (readBuf + (*RecPtr) % XLOG_BLCKSZ);
	total_len = record->xl_tot_len;

	/*
	 * If the whole record header is on this page, validate it immediately.
	 * Otherwise do just a basic sanity check on xl_tot_len, and validate the
	 * rest of the header after reading it from the next page.  The xl_tot_len
	 * check is necessary here to ensure that we enter the "Need to reassemble
	 * record" code path below; otherwise we might fail to apply
	 * ValidXLogRecordHeader at all.
	 */
	if (targetRecOff <= XLOG_BLCKSZ - SizeOfXLogRecord)
	{
		if (!ValidXLogRecordHeader(RecPtr, record, emode, randAccess))
			goto next_record_is_invalid;
		gotheader = true;
	}
	else
	{
		if (total_len < SizeOfXLogRecord)
		{
			ereport(emode_for_corrupt_record(emode, *RecPtr),
					(errmsg("invalid record length at %X/%X",
							(uint32) ((*RecPtr) >> 32), (uint32) *RecPtr)));
			goto next_record_is_invalid;
		}
		gotheader = false;
	}

	/*
	 * Allocate or enlarge readRecordBuf as needed.  To avoid useless small
	 * increases, round its size to a multiple of XLOG_BLCKSZ, and make sure
	 * it's at least 4*Max(BLCKSZ, XLOG_BLCKSZ) to start with.  (That is
	 * enough for all "normal" records, but very large commit or abort records
	 * might need more space.)
	 */
	if (total_len > readRecordBufSize)
	{
		uint32		newSize = total_len;

		newSize += XLOG_BLCKSZ - (newSize % XLOG_BLCKSZ);
		newSize = Max(newSize, 4 * Max(BLCKSZ, XLOG_BLCKSZ));
		if (readRecordBuf)
			free(readRecordBuf);
		readRecordBuf = (char *) malloc(newSize);
		if (!readRecordBuf)
		{
			readRecordBufSize = 0;
			/* We treat this as a "bogus data" condition */
			ereport(emode_for_corrupt_record(emode, *RecPtr),
					(errmsg("record length %u at %X/%X too long",
							total_len, (uint32) ((*RecPtr) >> 32), (uint32) *RecPtr)));
			goto next_record_is_invalid;
		}
		readRecordBufSize = newSize;
	}

	len = XLOG_BLCKSZ - (*RecPtr) % XLOG_BLCKSZ;
	if (total_len > len)
	{
		/* Need to reassemble record */
		char	   *contrecord;
		XLogPageHeader pageHeader;
		XLogRecPtr	pagelsn;
		char	   *buffer;
		uint32		gotlen;

		/* Initialize pagelsn to the beginning of the page this record is on */
		pagelsn = ((*RecPtr) / XLOG_BLCKSZ) * XLOG_BLCKSZ;

		/* Copy the first fragment of the record from the first page. */
		memcpy(readRecordBuf, readBuf + (*RecPtr) % XLOG_BLCKSZ, len);
		buffer = readRecordBuf + len;
		gotlen = len;

		do
		{
			/* Calculate pointer to beginning of next page */
			XLByteAdvance(pagelsn, XLOG_BLCKSZ);
			/* Wait for the next page to become available */
			if (!XLogPageRead(&pagelsn, emode, false, false))
				return NULL;

			/* Check that the continuation on next page looks valid */
			pageHeader = (XLogPageHeader) readBuf;
			if (!(pageHeader->xlp_info & XLP_FIRST_IS_CONTRECORD))
			{
				ereport(emode_for_corrupt_record(emode, *RecPtr),
						(errmsg("there is no contrecord flag in log segment %s, offset %u",
								XLogFileNameP(curFileTLI, readSegNo),
								readOff)));
				goto next_record_is_invalid;
			}
			/*
			 * Cross-check that xlp_rem_len agrees with how much of the record
			 * we expect there to be left.
			 */
			if (pageHeader->xlp_rem_len == 0 ||
				total_len != (pageHeader->xlp_rem_len + gotlen))
			{
				ereport(emode_for_corrupt_record(emode, *RecPtr),
						(errmsg("invalid contrecord length %u in log segment %s, offset %u",
								pageHeader->xlp_rem_len,
								XLogFileNameP(curFileTLI, readSegNo),
								readOff)));
				goto next_record_is_invalid;
			}

			/* Append the continuation from this page to the buffer */
			pageHeaderSize = XLogPageHeaderSize(pageHeader);
			contrecord = (char *) readBuf + pageHeaderSize;
			len = XLOG_BLCKSZ - pageHeaderSize;
			if (pageHeader->xlp_rem_len < len)
				len = pageHeader->xlp_rem_len;
			memcpy(buffer, (char *) contrecord, len);
			buffer += len;
			gotlen += len;

			/* If we just reassembled the record header, validate it. */
			if (!gotheader)
			{
				record = (XLogRecord *) readRecordBuf;
				if (!ValidXLogRecordHeader(RecPtr, record, emode, randAccess))
					goto next_record_is_invalid;
				gotheader = true;
			}
		} while (pageHeader->xlp_rem_len > len);

		record = (XLogRecord *) readRecordBuf;
		if (!RecordIsValid(record, *RecPtr, emode))
			goto next_record_is_invalid;
		pageHeaderSize = XLogPageHeaderSize((XLogPageHeader) readBuf);
		XLogSegNoOffsetToRecPtr(
			readSegNo,
			readOff + pageHeaderSize + MAXALIGN(pageHeader->xlp_rem_len),
			EndRecPtr);
		ReadRecPtr = *RecPtr;
	}
	else
	{
		/* Record does not cross a page boundary */
		if (!RecordIsValid(record, *RecPtr, emode))
			goto next_record_is_invalid;
		EndRecPtr = *RecPtr + MAXALIGN(total_len);

		ReadRecPtr = *RecPtr;
		memcpy(readRecordBuf, record, total_len);
	}

	/*
	 * Special processing if it's an XLOG SWITCH record
	 */
	if (record->xl_rmid == RM_XLOG_ID && record->xl_info == XLOG_SWITCH)
	{
		/* Pretend it extends to end of segment */
		EndRecPtr += XLogSegSize - 1;
		EndRecPtr -= EndRecPtr % XLogSegSize;

		/*
		 * Pretend that readBuf contains the last page of the segment. This is
		 * just to avoid Assert failure in StartupXLOG if XLOG ends with this
		 * segment.
		 */
		readOff = XLogSegSize - XLOG_BLCKSZ;
	}
	return record;

next_record_is_invalid:
	failedSources |= readSource;

	if (readFile >= 0)
	{
		close(readFile);
		readFile = -1;
	}

	/* In standby-mode, keep trying */
	if (StandbyMode)
		goto retry;
	else
		return NULL;
}

/*
 * Check whether the xlog header of a page just read in looks valid.
 *
 * This is just a convenience subroutine to avoid duplicated code in
 * ReadRecord.	It's not intended for use from anywhere else.
 */
static bool
ValidXLogPageHeader(XLogPageHeader hdr, int emode, bool segmentonly)
{
	XLogRecPtr	recaddr;

	XLogSegNoOffsetToRecPtr(readSegNo, readOff, recaddr);

	if (hdr->xlp_magic != XLOG_PAGE_MAGIC)
	{
		ereport(emode_for_corrupt_record(emode, recaddr),
				(errmsg("invalid magic number %04X in log segment %s, offset %u",
						hdr->xlp_magic,
						XLogFileNameP(curFileTLI, readSegNo),
						readOff)));
		return false;
	}
	if ((hdr->xlp_info & ~XLP_ALL_FLAGS) != 0)
	{
		ereport(emode_for_corrupt_record(emode, recaddr),
				(errmsg("invalid info bits %04X in log segment %s, offset %u",
						hdr->xlp_info,
						XLogFileNameP(curFileTLI, readSegNo),
						readOff)));
		return false;
	}
	if (hdr->xlp_info & XLP_LONG_HEADER)
	{
		XLogLongPageHeader longhdr = (XLogLongPageHeader) hdr;

		if (longhdr->xlp_sysid != ControlFile->system_identifier)
		{
			char		fhdrident_str[32];
			char		sysident_str[32];

			/*
			 * Format sysids separately to keep platform-dependent format code
			 * out of the translatable message string.
			 */
			snprintf(fhdrident_str, sizeof(fhdrident_str), UINT64_FORMAT,
					 longhdr->xlp_sysid);
			snprintf(sysident_str, sizeof(sysident_str), UINT64_FORMAT,
					 ControlFile->system_identifier);
			ereport(emode_for_corrupt_record(emode, recaddr),
					(errmsg("WAL file is from different database system"),
					 errdetail("WAL file database system identifier is %s, pg_control database system identifier is %s.",
							   fhdrident_str, sysident_str)));
			return false;
		}
		if (longhdr->xlp_seg_size != XLogSegSize)
		{
			ereport(emode_for_corrupt_record(emode, recaddr),
					(errmsg("WAL file is from different database system"),
					 errdetail("Incorrect XLOG_SEG_SIZE in page header.")));
			return false;
		}
		if (longhdr->xlp_xlog_blcksz != XLOG_BLCKSZ)
		{
			ereport(emode_for_corrupt_record(emode, recaddr),
					(errmsg("WAL file is from different database system"),
					 errdetail("Incorrect XLOG_BLCKSZ in page header.")));
			return false;
		}
	}
	else if (readOff == 0)
	{
		/* hmm, first page of file doesn't have a long header? */
		ereport(emode_for_corrupt_record(emode, recaddr),
				(errmsg("invalid info bits %04X in log segment %s, offset %u",
						hdr->xlp_info,
						XLogFileNameP(curFileTLI, readSegNo),
						readOff)));
		return false;
	}

	if (!XLByteEQ(hdr->xlp_pageaddr, recaddr))
	{
		ereport(emode_for_corrupt_record(emode, recaddr),
				(errmsg("unexpected pageaddr %X/%X in log segment %s, offset %u",
						(uint32) (hdr->xlp_pageaddr >> 32), (uint32) hdr->xlp_pageaddr,
						XLogFileNameP(curFileTLI, readSegNo),
						readOff)));
		return false;
	}

	/*
	 * Check page TLI is one of the expected values.
	 */
	if (!list_member_int(expectedTLIs, (int) hdr->xlp_tli))
	{
		ereport(emode_for_corrupt_record(emode, recaddr),
				(errmsg("unexpected timeline ID %u in log segment %s, offset %u",
						hdr->xlp_tli,
						XLogFileNameP(curFileTLI, readSegNo),
						readOff)));
		return false;
	}

	/*
	 * Since child timelines are always assigned a TLI greater than their
	 * immediate parent's TLI, we should never see TLI go backwards across
	 * successive pages of a consistent WAL sequence.
	 *
	 * Of course this check should only be applied when advancing sequentially
	 * across pages; therefore ReadRecord resets lastPageTLI and
	 * lastSegmentTLI to zero when going to a random page.
	 *
	 * Sometimes we re-open a segment that's already been partially replayed.
	 * In that case we cannot perform the normal TLI check: if there is a
	 * timeline switch within the segment, the first page has a smaller TLI
	 * than later pages following the timeline switch, and we might've read
	 * them already. As a weaker test, we still check that it's not smaller
	 * than the TLI we last saw at the beginning of a segment. Pass
	 * segmentonly = true when re-validating the first page like that, and the
	 * page you're actually interested in comes later.
	 */
	if (hdr->xlp_tli < (segmentonly ? lastSegmentTLI : lastPageTLI))
	{
		ereport(emode_for_corrupt_record(emode, recaddr),
				(errmsg("out-of-sequence timeline ID %u (after %u) in log segment %s, offset %u",
						hdr->xlp_tli,
						segmentonly ? lastSegmentTLI : lastPageTLI,
						XLogFileNameP(curFileTLI, readSegNo),
						readOff)));
		return false;
	}
	lastPageTLI = hdr->xlp_tli;
	if (readOff == 0)
		lastSegmentTLI = hdr->xlp_tli;

	return true;
}

/*
 * Validate an XLOG record header.
 *
 * This is just a convenience subroutine to avoid duplicated code in
 * ReadRecord.	It's not intended for use from anywhere else.
 */
static bool
ValidXLogRecordHeader(XLogRecPtr *RecPtr, XLogRecord *record, int emode,
					  bool randAccess)
{
	/*
	 * xl_len == 0 is bad data for everything except XLOG SWITCH, where it is
	 * required.
	 */
	if (record->xl_rmid == RM_XLOG_ID && record->xl_info == XLOG_SWITCH)
	{
		if (record->xl_len != 0)
		{
			ereport(emode_for_corrupt_record(emode, *RecPtr),
					(errmsg("invalid xlog switch record at %X/%X",
							(uint32) ((*RecPtr) >> 32), (uint32) *RecPtr)));
			return false;
		}
	}
	else if (record->xl_len == 0)
	{
		ereport(emode_for_corrupt_record(emode, *RecPtr),
				(errmsg("record with zero length at %X/%X",
						(uint32) ((*RecPtr) >> 32), (uint32) *RecPtr)));
		return false;
	}
	if (record->xl_tot_len < SizeOfXLogRecord + record->xl_len ||
		record->xl_tot_len > SizeOfXLogRecord + record->xl_len +
		XLR_MAX_BKP_BLOCKS * (sizeof(BkpBlock) + BLCKSZ))
	{
		ereport(emode_for_corrupt_record(emode, *RecPtr),
				(errmsg("invalid record length at %X/%X",
						(uint32) ((*RecPtr) >> 32), (uint32) *RecPtr)));
		return false;
	}
	if (record->xl_rmid > RM_MAX_ID)
	{
		ereport(emode_for_corrupt_record(emode, *RecPtr),
				(errmsg("invalid resource manager ID %u at %X/%X",
						record->xl_rmid, (uint32) ((*RecPtr) >> 32), (uint32) *RecPtr)));
		return false;
	}
	if (randAccess)
	{
		/*
		 * We can't exactly verify the prev-link, but surely it should be less
		 * than the record's own address.
		 */
		if (!XLByteLT(record->xl_prev, *RecPtr))
		{
			ereport(emode_for_corrupt_record(emode, *RecPtr),
					(errmsg("record with incorrect prev-link %X/%X at %X/%X",
							(uint32) (record->xl_prev >> 32), (uint32) record->xl_prev,
							(uint32) ((*RecPtr) >> 32), (uint32) *RecPtr)));
			return false;
		}
	}
	else
	{
		/*
		 * Record's prev-link should exactly match our previous location. This
		 * check guards against torn WAL pages where a stale but valid-looking
		 * WAL record starts on a sector boundary.
		 */
		if (!XLByteEQ(record->xl_prev, ReadRecPtr))
		{
			ereport(emode_for_corrupt_record(emode, *RecPtr),
					(errmsg("record with incorrect prev-link %X/%X at %X/%X",
							(uint32) (record->xl_prev >> 32), (uint32) record->xl_prev,
							(uint32) ((*RecPtr) >> 32), (uint32) *RecPtr)));
			return false;
		}
	}

	return true;
}

/*
 * Scan for new timelines that might have appeared in the archive since we
 * started recovery.
 *
 * If there are any, the function changes recovery target TLI to the latest
 * one and returns 'true'.
 */
static bool
rescanLatestTimeLine(void)
{
	TimeLineID	newtarget;

	newtarget = findNewestTimeLine(recoveryTargetTLI);
	if (newtarget != recoveryTargetTLI)
	{
		/*
		 * Determine the list of expected TLIs for the new TLI
		 */
		List	   *newExpectedTLIs;

		newExpectedTLIs = readTimeLineHistory(newtarget);

		/*
		 * If the current timeline is not part of the history of the new
		 * timeline, we cannot proceed to it.
		 *
		 * XXX This isn't foolproof: The new timeline might have forked from
		 * the current one, but before the current recovery location. In that
		 * case we will still switch to the new timeline and proceed replaying
		 * from it even though the history doesn't match what we already
		 * replayed. That's not good. We will likely notice at the next online
		 * checkpoint, as the TLI won't match what we expected, but it's not
		 * guaranteed. The admin needs to make sure that doesn't happen.
		 */
		if (!list_member_int(newExpectedTLIs,
							 (int) recoveryTargetTLI))
			ereport(LOG,
					(errmsg("new timeline %u is not a child of database system timeline %u",
							newtarget,
							ThisTimeLineID)));
		else
		{
			/* use volatile pointer to prevent code rearrangement */
			volatile XLogCtlData *xlogctl = XLogCtl;

			/* Switch target */
			recoveryTargetTLI = newtarget;
			list_free(expectedTLIs);
			expectedTLIs = newExpectedTLIs;

			SpinLockAcquire(&xlogctl->info_lck);
			xlogctl->RecoveryTargetTLI = recoveryTargetTLI;
			SpinLockRelease(&xlogctl->info_lck);

			ereport(LOG,
					(errmsg("new target timeline is %u",
							recoveryTargetTLI)));
			return true;
		}
	}
	return false;
}

/*
 * I/O routines for pg_control
 *
 * *ControlFile is a buffer in shared memory that holds an image of the
 * contents of pg_control.	WriteControlFile() initializes pg_control
 * given a preloaded buffer, ReadControlFile() loads the buffer from
 * the pg_control file (during postmaster or standalone-backend startup),
 * and UpdateControlFile() rewrites pg_control after we modify xlog state.
 *
 * For simplicity, WriteControlFile() initializes the fields of pg_control
 * that are related to checking backend/database compatibility, and
 * ReadControlFile() verifies they are correct.  We could split out the
 * I/O and compatibility-check functions, but there seems no need currently.
 */
static void
WriteControlFile(void)
{
	int			fd;
	char		buffer[PG_CONTROL_SIZE];		/* need not be aligned */

	/*
	 * Initialize version and compatibility-check fields
	 */
	ControlFile->pg_control_version = PG_CONTROL_VERSION;
	ControlFile->catalog_version_no = CATALOG_VERSION_NO;

	ControlFile->maxAlign = MAXIMUM_ALIGNOF;
	ControlFile->floatFormat = FLOATFORMAT_VALUE;

	ControlFile->blcksz = BLCKSZ;
	ControlFile->relseg_size = RELSEG_SIZE;
	ControlFile->xlog_blcksz = XLOG_BLCKSZ;
	ControlFile->xlog_seg_size = XLOG_SEG_SIZE;

	ControlFile->nameDataLen = NAMEDATALEN;
	ControlFile->indexMaxKeys = INDEX_MAX_KEYS;

	ControlFile->toast_max_chunk_size = TOAST_MAX_CHUNK_SIZE;

#ifdef HAVE_INT64_TIMESTAMP
	ControlFile->enableIntTimes = true;
#else
	ControlFile->enableIntTimes = false;
#endif
	ControlFile->float4ByVal = FLOAT4PASSBYVAL;
	ControlFile->float8ByVal = FLOAT8PASSBYVAL;

	/* Contents are protected with a CRC */
	INIT_CRC32(ControlFile->crc);
	COMP_CRC32(ControlFile->crc,
			   (char *) ControlFile,
			   offsetof(ControlFileData, crc));
	FIN_CRC32(ControlFile->crc);

	/*
	 * We write out PG_CONTROL_SIZE bytes into pg_control, zero-padding the
	 * excess over sizeof(ControlFileData).  This reduces the odds of
	 * premature-EOF errors when reading pg_control.  We'll still fail when we
	 * check the contents of the file, but hopefully with a more specific
	 * error than "couldn't read pg_control".
	 */
	if (sizeof(ControlFileData) > PG_CONTROL_SIZE)
		elog(PANIC, "sizeof(ControlFileData) is larger than PG_CONTROL_SIZE; fix either one");

	memset(buffer, 0, PG_CONTROL_SIZE);
	memcpy(buffer, ControlFile, sizeof(ControlFileData));

	fd = BasicOpenFile(XLOG_CONTROL_FILE,
					   O_RDWR | O_CREAT | O_EXCL | PG_BINARY,
					   S_IRUSR | S_IWUSR);
	if (fd < 0)
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not create control file \"%s\": %m",
						XLOG_CONTROL_FILE)));

	errno = 0;
	if (write(fd, buffer, PG_CONTROL_SIZE) != PG_CONTROL_SIZE)
	{
		/* if write didn't set errno, assume problem is no disk space */
		if (errno == 0)
			errno = ENOSPC;
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not write to control file: %m")));
	}

	if (pg_fsync(fd) != 0)
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not fsync control file: %m")));

	if (close(fd))
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not close control file: %m")));
}

static void
ReadControlFile(void)
{
	pg_crc32	crc;
	int			fd;

	/*
	 * Read data...
	 */
	fd = BasicOpenFile(XLOG_CONTROL_FILE,
					   O_RDWR | PG_BINARY,
					   S_IRUSR | S_IWUSR);
	if (fd < 0)
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not open control file \"%s\": %m",
						XLOG_CONTROL_FILE)));

	if (read(fd, ControlFile, sizeof(ControlFileData)) != sizeof(ControlFileData))
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not read from control file: %m")));

	close(fd);

	/*
	 * Check for expected pg_control format version.  If this is wrong, the
	 * CRC check will likely fail because we'll be checking the wrong number
	 * of bytes.  Complaining about wrong version will probably be more
	 * enlightening than complaining about wrong CRC.
	 */

	if (ControlFile->pg_control_version != PG_CONTROL_VERSION && ControlFile->pg_control_version % 65536 == 0 && ControlFile->pg_control_version / 65536 != 0)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
				 errdetail("The database cluster was initialized with PG_CONTROL_VERSION %d (0x%08x),"
		 " but the server was compiled with PG_CONTROL_VERSION %d (0x%08x).",
			ControlFile->pg_control_version, ControlFile->pg_control_version,
						   PG_CONTROL_VERSION, PG_CONTROL_VERSION),
				 errhint("This could be a problem of mismatched byte ordering.  It looks like you need to initdb.")));

	if (ControlFile->pg_control_version != PG_CONTROL_VERSION)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
				 errdetail("The database cluster was initialized with PG_CONTROL_VERSION %d,"
				  " but the server was compiled with PG_CONTROL_VERSION %d.",
						ControlFile->pg_control_version, PG_CONTROL_VERSION),
				 errhint("It looks like you need to initdb.")));

	/* Now check the CRC. */
	INIT_CRC32(crc);
	COMP_CRC32(crc,
			   (char *) ControlFile,
			   offsetof(ControlFileData, crc));
	FIN_CRC32(crc);

	if (!EQ_CRC32(crc, ControlFile->crc))
		ereport(FATAL,
				(errmsg("incorrect checksum in control file")));

	/*
	 * Do compatibility checking immediately.  If the database isn't
	 * compatible with the backend executable, we want to abort before we can
	 * possibly do any damage.
	 */
	if (ControlFile->catalog_version_no != CATALOG_VERSION_NO)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
				 errdetail("The database cluster was initialized with CATALOG_VERSION_NO %d,"
				  " but the server was compiled with CATALOG_VERSION_NO %d.",
						ControlFile->catalog_version_no, CATALOG_VERSION_NO),
				 errhint("It looks like you need to initdb.")));
	if (ControlFile->maxAlign != MAXIMUM_ALIGNOF)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
		   errdetail("The database cluster was initialized with MAXALIGN %d,"
					 " but the server was compiled with MAXALIGN %d.",
					 ControlFile->maxAlign, MAXIMUM_ALIGNOF),
				 errhint("It looks like you need to initdb.")));
	if (ControlFile->floatFormat != FLOATFORMAT_VALUE)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
				 errdetail("The database cluster appears to use a different floating-point number format than the server executable."),
				 errhint("It looks like you need to initdb.")));
	if (ControlFile->blcksz != BLCKSZ)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
			 errdetail("The database cluster was initialized with BLCKSZ %d,"
					   " but the server was compiled with BLCKSZ %d.",
					   ControlFile->blcksz, BLCKSZ),
				 errhint("It looks like you need to recompile or initdb.")));
	if (ControlFile->relseg_size != RELSEG_SIZE)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
		errdetail("The database cluster was initialized with RELSEG_SIZE %d,"
				  " but the server was compiled with RELSEG_SIZE %d.",
				  ControlFile->relseg_size, RELSEG_SIZE),
				 errhint("It looks like you need to recompile or initdb.")));
	if (ControlFile->xlog_blcksz != XLOG_BLCKSZ)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
		errdetail("The database cluster was initialized with XLOG_BLCKSZ %d,"
				  " but the server was compiled with XLOG_BLCKSZ %d.",
				  ControlFile->xlog_blcksz, XLOG_BLCKSZ),
				 errhint("It looks like you need to recompile or initdb.")));
	if (ControlFile->xlog_seg_size != XLOG_SEG_SIZE)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
				 errdetail("The database cluster was initialized with XLOG_SEG_SIZE %d,"
					   " but the server was compiled with XLOG_SEG_SIZE %d.",
						   ControlFile->xlog_seg_size, XLOG_SEG_SIZE),
				 errhint("It looks like you need to recompile or initdb.")));
	if (ControlFile->nameDataLen != NAMEDATALEN)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
		errdetail("The database cluster was initialized with NAMEDATALEN %d,"
				  " but the server was compiled with NAMEDATALEN %d.",
				  ControlFile->nameDataLen, NAMEDATALEN),
				 errhint("It looks like you need to recompile or initdb.")));
	if (ControlFile->indexMaxKeys != INDEX_MAX_KEYS)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
				 errdetail("The database cluster was initialized with INDEX_MAX_KEYS %d,"
					  " but the server was compiled with INDEX_MAX_KEYS %d.",
						   ControlFile->indexMaxKeys, INDEX_MAX_KEYS),
				 errhint("It looks like you need to recompile or initdb.")));
	if (ControlFile->toast_max_chunk_size != TOAST_MAX_CHUNK_SIZE)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
				 errdetail("The database cluster was initialized with TOAST_MAX_CHUNK_SIZE %d,"
				" but the server was compiled with TOAST_MAX_CHUNK_SIZE %d.",
			  ControlFile->toast_max_chunk_size, (int) TOAST_MAX_CHUNK_SIZE),
				 errhint("It looks like you need to recompile or initdb.")));

#ifdef HAVE_INT64_TIMESTAMP
	if (ControlFile->enableIntTimes != true)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
				 errdetail("The database cluster was initialized without HAVE_INT64_TIMESTAMP"
				  " but the server was compiled with HAVE_INT64_TIMESTAMP."),
				 errhint("It looks like you need to recompile or initdb.")));
#else
	if (ControlFile->enableIntTimes != false)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
				 errdetail("The database cluster was initialized with HAVE_INT64_TIMESTAMP"
			   " but the server was compiled without HAVE_INT64_TIMESTAMP."),
				 errhint("It looks like you need to recompile or initdb.")));
#endif

#ifdef USE_FLOAT4_BYVAL
	if (ControlFile->float4ByVal != true)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
				 errdetail("The database cluster was initialized without USE_FLOAT4_BYVAL"
					  " but the server was compiled with USE_FLOAT4_BYVAL."),
				 errhint("It looks like you need to recompile or initdb.")));
#else
	if (ControlFile->float4ByVal != false)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
		errdetail("The database cluster was initialized with USE_FLOAT4_BYVAL"
				  " but the server was compiled without USE_FLOAT4_BYVAL."),
				 errhint("It looks like you need to recompile or initdb.")));
#endif

#ifdef USE_FLOAT8_BYVAL
	if (ControlFile->float8ByVal != true)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
				 errdetail("The database cluster was initialized without USE_FLOAT8_BYVAL"
					  " but the server was compiled with USE_FLOAT8_BYVAL."),
				 errhint("It looks like you need to recompile or initdb.")));
#else
	if (ControlFile->float8ByVal != false)
		ereport(FATAL,
				(errmsg("database files are incompatible with server"),
		errdetail("The database cluster was initialized with USE_FLOAT8_BYVAL"
				  " but the server was compiled without USE_FLOAT8_BYVAL."),
				 errhint("It looks like you need to recompile or initdb.")));
#endif
}

void
UpdateControlFile(void)
{
	int			fd;

	INIT_CRC32(ControlFile->crc);
	COMP_CRC32(ControlFile->crc,
			   (char *) ControlFile,
			   offsetof(ControlFileData, crc));
	FIN_CRC32(ControlFile->crc);

	fd = BasicOpenFile(XLOG_CONTROL_FILE,
					   O_RDWR | PG_BINARY,
					   S_IRUSR | S_IWUSR);
	if (fd < 0)
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not open control file \"%s\": %m",
						XLOG_CONTROL_FILE)));

	errno = 0;
	if (write(fd, ControlFile, sizeof(ControlFileData)) != sizeof(ControlFileData))
	{
		/* if write didn't set errno, assume problem is no disk space */
		if (errno == 0)
			errno = ENOSPC;
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not write to control file: %m")));
	}

	if (pg_fsync(fd) != 0)
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not fsync control file: %m")));

	if (close(fd))
		ereport(PANIC,
				(errcode_for_file_access(),
				 errmsg("could not close control file: %m")));
}

/*
 * Returns the unique system identifier from control file.
 */
uint64
GetSystemIdentifier(void)
{
	Assert(ControlFile != NULL);
	return ControlFile->system_identifier;
}

/*
 * Auto-tune the number of XLOG buffers.
 *
 * The preferred setting for wal_buffers is about 3% of shared_buffers, with
 * a maximum of one XLOG segment (there is little reason to think that more
 * is helpful, at least so long as we force an fsync when switching log files)
 * and a minimum of 8 blocks (which was the default value prior to PostgreSQL
 * 9.1, when auto-tuning was added).
 *
 * This should not be called until NBuffers has received its final value.
 */
static int
XLOGChooseNumBuffers(void)
{
	int			xbuffers;

	xbuffers = NBuffers / 32;
	if (xbuffers > XLOG_SEG_SIZE / XLOG_BLCKSZ)
		xbuffers = XLOG_SEG_SIZE / XLOG_BLCKSZ;
	if (xbuffers < 8)
		xbuffers = 8;
	return xbuffers;
}

/*
 * GUC check_hook for wal_buffers
 */
bool
check_wal_buffers(int *newval, void **extra, GucSource source)
{
	/*
	 * -1 indicates a request for auto-tune.
	 */
	if (*newval == -1)
	{
		/*
		 * If we haven't yet changed the boot_val default of -1, just let it
		 * be.	We'll fix it when XLOGShmemSize is called.
		 */
		if (XLOGbuffers == -1)
			return true;

		/* Otherwise, substitute the auto-tune value */
		*newval = XLOGChooseNumBuffers();
	}

	/*
	 * We clamp manually-set values to at least 4 blocks.  Prior to PostgreSQL
	 * 9.1, a minimum of 4 was enforced by guc.c, but since that is no longer
	 * the case, we just silently treat such values as a request for the
	 * minimum.  (We could throw an error instead, but that doesn't seem very
	 * helpful.)
	 */
	if (*newval < 4)
		*newval = 4;

	return true;
}

/*
 * Initialization of shared memory for XLOG
 */
Size
XLOGShmemSize(void)
{
	Size		size;

	/*
	 * If the value of wal_buffers is -1, use the preferred auto-tune value.
	 * This isn't an amazingly clean place to do this, but we must wait till
	 * NBuffers has received its final value, and must do it before using the
	 * value of XLOGbuffers to do anything important.
	 */
	if (XLOGbuffers == -1)
	{
		char		buf[32];

		snprintf(buf, sizeof(buf), "%d", XLOGChooseNumBuffers());
		SetConfigOption("wal_buffers", buf, PGC_POSTMASTER, PGC_S_OVERRIDE);
	}
	Assert(XLOGbuffers > 0);

	/* XLogCtl */
	size = sizeof(XLogCtlData);
	/* xlblocks array */
	size = add_size(size, mul_size(sizeof(XLogRecPtr), XLOGbuffers));
	/* extra alignment padding for XLOG I/O buffers */
	size = add_size(size, ALIGNOF_XLOG_BUFFER);
	/* and the buffers themselves */
	size = add_size(size, mul_size(XLOG_BLCKSZ, XLOGbuffers));

	/*
	 * Note: we don't count ControlFileData, it comes out of the "slop factor"
	 * added by CreateSharedMemoryAndSemaphores.  This lets us use this
	 * routine again below to compute the actual allocation size.
	 */

	return size;
}

void
XLOGShmemInit(void)
{
	bool		foundCFile,
				foundXLog;
	char	   *allocptr;

	ControlFile = (ControlFileData *)
		ShmemInitStruct("Control File", sizeof(ControlFileData), &foundCFile);
	XLogCtl = (XLogCtlData *)
		ShmemInitStruct("XLOG Ctl", XLOGShmemSize(), &foundXLog);

	if (foundCFile || foundXLog)
	{
		/* both should be present or neither */
		Assert(foundCFile && foundXLog);
		return;
	}

	memset(XLogCtl, 0, sizeof(XLogCtlData));

	/*
	 * Since XLogCtlData contains XLogRecPtr fields, its sizeof should be a
	 * multiple of the alignment for same, so no extra alignment padding is
	 * needed here.
	 */
	allocptr = ((char *) XLogCtl) + sizeof(XLogCtlData);
	XLogCtl->xlblocks = (XLogRecPtr *) allocptr;
	memset(XLogCtl->xlblocks, 0, sizeof(XLogRecPtr) * XLOGbuffers);
	allocptr += sizeof(XLogRecPtr) * XLOGbuffers;

	/*
	 * Align the start of the page buffers to an ALIGNOF_XLOG_BUFFER boundary.
	 */
	allocptr = (char *) TYPEALIGN(ALIGNOF_XLOG_BUFFER, allocptr);
	XLogCtl->pages = allocptr;
	memset(XLogCtl->pages, 0, (Size) XLOG_BLCKSZ * XLOGbuffers);

	/*
	 * Do basic initialization of XLogCtl shared data. (StartupXLOG will fill
	 * in additional info.)
	 */
	XLogCtl->XLogCacheBlck = XLOGbuffers - 1;
	XLogCtl->SharedRecoveryInProgress = true;
	XLogCtl->SharedHotStandbyActive = false;
	XLogCtl->WalWriterSleeping = false;
	XLogCtl->Insert.currpage = (XLogPageHeader) (XLogCtl->pages);
	SpinLockInit(&XLogCtl->info_lck);
	InitSharedLatch(&XLogCtl->recoveryWakeupLatch);

	/*
	 * If we are not in bootstrap mode, pg_control should already exist. Read
	 * and validate it immediately (see comments in ReadControlFile() for the
	 * reasons why).
	 */
	if (!IsBootstrapProcessingMode())
		ReadControlFile();
}

/*
 * This func must be called ONCE on system install.  It creates pg_control
 * and the initial XLOG segment.
 */
void
BootStrapXLOG(void)
{
	CheckPoint	checkPoint;
	char	   *buffer;
	XLogPageHeader page;
	XLogLongPageHeader longpage;
	XLogRecord *record;
	bool		use_existent;
	uint64		sysidentifier;
	struct timeval tv;
	pg_crc32	crc;

	/*
	 * Select a hopefully-unique system identifier code for this installation.
	 * We use the result of gettimeofday(), including the fractional seconds
	 * field, as being about as unique as we can easily get.  (Think not to
	 * use random(), since it hasn't been seeded and there's no portable way
	 * to seed it other than the system clock value...)  The upper half of the
	 * uint64 value is just the tv_sec part, while the lower half is the XOR
	 * of tv_sec and tv_usec.  This is to ensure that we don't lose uniqueness
	 * unnecessarily if "uint64" is really only 32 bits wide.  A person
	 * knowing this encoding can determine the initialization time of the
	 * installation, which could perhaps be useful sometimes.
	 */
	gettimeofday(&tv, NULL);
	sysidentifier = ((uint64) tv.tv_sec) << 32;
	sysidentifier |= (uint32) (tv.tv_sec | tv.tv_usec);

	/* First timeline ID is always 1 */
	ThisTimeLineID = 1;

	/* page buffer must be aligned suitably for O_DIRECT */
	buffer = (char *) palloc(XLOG_BLCKSZ + ALIGNOF_XLOG_BUFFER);
	page = (XLogPageHeader) TYPEALIGN(ALIGNOF_XLOG_BUFFER, buffer);
	memset(page, 0, XLOG_BLCKSZ);

	/*
	 * Set up information for the initial checkpoint record
	 *
	 * The initial checkpoint record is written to the beginning of the WAL
	 * segment with logid=0 logseg=1. The very first WAL segment, 0/0, is not
	 * used, so that we can use 0/0 to mean "before any valid WAL segment".
	 */
	checkPoint.redo = XLogSegSize + SizeOfXLogLongPHD;
	checkPoint.ThisTimeLineID = ThisTimeLineID;
	checkPoint.fullPageWrites = fullPageWrites;
	checkPoint.nextXidEpoch = 0;
	checkPoint.nextXid = FirstNormalTransactionId;
	checkPoint.nextOid = FirstBootstrapObjectId;
	checkPoint.nextMulti = FirstMultiXactId;
	checkPoint.nextMultiOffset = 0;
	checkPoint.oldestXid = FirstNormalTransactionId;
	checkPoint.oldestXidDB = TemplateDbOid;
	checkPoint.time = (pg_time_t) time(NULL);
	checkPoint.oldestActiveXid = InvalidTransactionId;

	ShmemVariableCache->nextXid = checkPoint.nextXid;
	ShmemVariableCache->nextOid = checkPoint.nextOid;
	ShmemVariableCache->oidCount = 0;
	MultiXactSetNextMXact(checkPoint.nextMulti, checkPoint.nextMultiOffset);
	SetTransactionIdLimit(checkPoint.oldestXid, checkPoint.oldestXidDB);

	/* Set up the XLOG page header */
	page->xlp_magic = XLOG_PAGE_MAGIC;
	page->xlp_info = XLP_LONG_HEADER;
	page->xlp_tli = ThisTimeLineID;
	page->xlp_pageaddr = XLogSegSize;
	longpage = (XLogLongPageHeader) page;
	longpage->xlp_sysid = sysidentifier;
	longpage->xlp_seg_size = XLogSegSize;
	longpage->xlp_xlog_blcksz = XLOG_BLCKSZ;

	/* Insert the initial checkpoint record */
	record = (XLogRecord *) ((char *) page + SizeOfXLogLongPHD);
	record->xl_prev = 0;
	record->xl_xid = InvalidTransactionId;
	record->xl_tot_len = SizeOfXLogRecord + sizeof(checkPoint);
	record->xl_len = sizeof(checkPoint);
	record->xl_info = XLOG_CHECKPOINT_SHUTDOWN;
	record->xl_rmid = RM_XLOG_ID;
	memcpy(XLogRecGetData(record), &checkPoint, sizeof(checkPoint));

	INIT_CRC32(crc);
	COMP_CRC32(crc, &checkPoint, sizeof(checkPoint));
	COMP_CRC32(crc, (char *) record, offsetof(XLogRecord, xl_crc));
	FIN_CRC32(crc);
	record->xl_crc = crc;

	/* Create first XLOG segment file */
	use_existent = false;
	openLogFile = XLogFileInit(1, &use_existent, false);

	/* Write the first page with the initial record */
	errno = 0;
	if (write(openLogFile, page, XLOG_BLCKSZ) != XLOG_BLCKSZ)
	{
		/* if write didn't set errno, assume problem is no disk space */
		if (errno == 0)
			errno = ENOSPC;
		ereport(PANIC,
				(errcode_for_file_access(),
			  errmsg("could not write bootstrap transaction log file: %m")));
	}

	if (pg_fsync(openLogFile) != 0)
		ereport(PANIC,
				(errcode_for_file_access(),
			  errmsg("could not fsync bootstrap transaction log file: %m")));

	if (close(openLogFile))
		ereport(PANIC,
				(errcode_for_file_access(),
			  errmsg("could not close bootstrap transaction log file: %m")));

	openLogFile = -1;

	/* Now create pg_control */

	memset(ControlFile, 0, sizeof(ControlFileData));
	/* Initialize pg_control status fields */
	ControlFile->system_identifier = sysidentifier;
	ControlFile->state = DB_SHUTDOWNED;
	ControlFile->time = checkPoint.time;
	ControlFile->checkPoint = checkPoint.redo;
	ControlFile->checkPointCopy = checkPoint;

	/* Set important parameter values for use when replaying WAL */
	ControlFile->MaxConnections = MaxConnections;
	ControlFile->max_prepared_xacts = max_prepared_xacts;
	ControlFile->max_locks_per_xact = max_locks_per_xact;
	ControlFile->wal_level = wal_level;

	/* some additional ControlFile fields are set in WriteControlFile() */

	WriteControlFile();

	/* Bootstrap the commit log, too */
	BootStrapCLOG();
	BootStrapSUBTRANS();
	BootStrapMultiXact();

	pfree(buffer);
}

static char *
str_time(pg_time_t tnow)
{
	static char buf[128];

	pg_strftime(buf, sizeof(buf),
				"%Y-%m-%d %H:%M:%S %Z",
				pg_localtime(&tnow, log_timezone));

	return buf;
}

/*
 * See if there is a recovery command file (recovery.conf), and if so
 * read in parameters for archive recovery and XLOG streaming.
 *
 * The file is parsed using the main configuration parser.
 */
static void
readRecoveryCommandFile(void)
{
	FILE	   *fd;
	TimeLineID	rtli = 0;
	bool		rtliGiven = false;
	ConfigVariable *item,
			   *head = NULL,
			   *tail = NULL;

	fd = AllocateFile(RECOVERY_COMMAND_FILE, "r");
	if (fd == NULL)
	{
		if (errno == ENOENT)
			return;				/* not there, so no archive recovery */
		ereport(FATAL,
				(errcode_for_file_access(),
				 errmsg("could not open recovery command file \"%s\": %m",
						RECOVERY_COMMAND_FILE)));
	}

	/*
	 * Since we're asking ParseConfigFp() to report errors as FATAL, there's
	 * no need to check the return value.
	 */
	(void) ParseConfigFp(fd, RECOVERY_COMMAND_FILE, 0, FATAL, &head, &tail);

	FreeFile(fd);

	for (item = head; item; item = item->next)
	{
		if (strcmp(item->name, "restore_command") == 0)
		{
			recoveryRestoreCommand = pstrdup(item->value);
			ereport(DEBUG2,
					(errmsg_internal("restore_command = '%s'",
									 recoveryRestoreCommand)));
		}
		else if (strcmp(item->name, "recovery_end_command") == 0)
		{
			recoveryEndCommand = pstrdup(item->value);
			ereport(DEBUG2,
					(errmsg_internal("recovery_end_command = '%s'",
									 recoveryEndCommand)));
		}
		else if (strcmp(item->name, "archive_cleanup_command") == 0)
		{
			archiveCleanupCommand = pstrdup(item->value);
			ereport(DEBUG2,
					(errmsg_internal("archive_cleanup_command = '%s'",
									 archiveCleanupCommand)));
		}
		else if (strcmp(item->name, "pause_at_recovery_target") == 0)
		{
			if (!parse_bool(item->value, &recoveryPauseAtTarget))
				ereport(ERROR,
						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
						 errmsg("parameter \"%s\" requires a Boolean value", "pause_at_recovery_target")));
			ereport(DEBUG2,
					(errmsg_internal("pause_at_recovery_target = '%s'",
									 item->value)));
		}
		else if (strcmp(item->name, "recovery_target_timeline") == 0)
		{
			rtliGiven = true;
			if (strcmp(item->value, "latest") == 0)
				rtli = 0;
			else
			{
				errno = 0;
				rtli = (TimeLineID) strtoul(item->value, NULL, 0);
				if (errno == EINVAL || errno == ERANGE)
					ereport(FATAL,
							(errmsg("recovery_target_timeline is not a valid number: \"%s\"",
									item->value)));
			}
			if (rtli)
				ereport(DEBUG2,
				   (errmsg_internal("recovery_target_timeline = %u", rtli)));
			else
				ereport(DEBUG2,
					 (errmsg_internal("recovery_target_timeline = latest")));
		}
		else if (strcmp(item->name, "recovery_target_xid") == 0)
		{
			errno = 0;
			recoveryTargetXid = (TransactionId) strtoul(item->value, NULL, 0);
			if (errno == EINVAL || errno == ERANGE)
				ereport(FATAL,
				 (errmsg("recovery_target_xid is not a valid number: \"%s\"",
						 item->value)));
			ereport(DEBUG2,
					(errmsg_internal("recovery_target_xid = %u",
									 recoveryTargetXid)));
			recoveryTarget = RECOVERY_TARGET_XID;
		}
		else if (strcmp(item->name, "recovery_target_time") == 0)
		{
			/*
			 * if recovery_target_xid or recovery_target_name specified, then
			 * this overrides recovery_target_time
			 */
			if (recoveryTarget == RECOVERY_TARGET_XID ||
				recoveryTarget == RECOVERY_TARGET_NAME)
				continue;
			recoveryTarget = RECOVERY_TARGET_TIME;

			/*
			 * Convert the time string given by the user to TimestampTz form.
			 */
			recoveryTargetTime =
				DatumGetTimestampTz(DirectFunctionCall3(timestamptz_in,
												CStringGetDatum(item->value),
												ObjectIdGetDatum(InvalidOid),
														Int32GetDatum(-1)));
			ereport(DEBUG2,
					(errmsg_internal("recovery_target_time = '%s'",
								   timestamptz_to_str(recoveryTargetTime))));
		}
		else if (strcmp(item->name, "recovery_target_name") == 0)
		{
			/*
			 * if recovery_target_xid specified, then this overrides
			 * recovery_target_name
			 */
			if (recoveryTarget == RECOVERY_TARGET_XID)
				continue;
			recoveryTarget = RECOVERY_TARGET_NAME;

			recoveryTargetName = pstrdup(item->value);
			if (strlen(recoveryTargetName) >= MAXFNAMELEN)
				ereport(FATAL,
						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
						 errmsg("recovery_target_name is too long (maximum %d characters)",
								MAXFNAMELEN - 1)));

			ereport(DEBUG2,
					(errmsg_internal("recovery_target_name = '%s'",
									 recoveryTargetName)));
		}
		else if (strcmp(item->name, "recovery_target_inclusive") == 0)
		{
			/*
			 * does nothing if a recovery_target is not also set
			 */
			if (!parse_bool(item->value, &recoveryTargetInclusive))
				ereport(ERROR,
						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
						 errmsg("parameter \"%s\" requires a Boolean value",
								"recovery_target_inclusive")));
			ereport(DEBUG2,
					(errmsg_internal("recovery_target_inclusive = %s",
									 item->value)));
		}
		else if (strcmp(item->name, "standby_mode") == 0)
		{
			if (!parse_bool(item->value, &StandbyMode))
				ereport(ERROR,
						(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
						 errmsg("parameter \"%s\" requires a Boolean value",
								"standby_mode")));
			ereport(DEBUG2,
					(errmsg_internal("standby_mode = '%s'", item->value)));
		}
		else if (strcmp(item->name, "primary_conninfo") == 0)
		{
			PrimaryConnInfo = pstrdup(item->value);
			ereport(DEBUG2,
					(errmsg_internal("primary_conninfo = '%s'",
									 PrimaryConnInfo)));
		}
		else if (strcmp(item->name, "trigger_file") == 0)
		{
			TriggerFile = pstrdup(item->value);
			ereport(DEBUG2,
					(errmsg_internal("trigger_file = '%s'",
									 TriggerFile)));
		}
		else
			ereport(FATAL,
					(errmsg("unrecognized recovery parameter \"%s\"",
							item->name)));
	}

	/*
	 * Check for compulsory parameters
	 */
	if (StandbyMode)
	{
		if (PrimaryConnInfo == NULL && recoveryRestoreCommand == NULL)
			ereport(WARNING,
					(errmsg("recovery command file \"%s\" specified neither primary_conninfo nor restore_command",
							RECOVERY_COMMAND_FILE),
					 errhint("The database server will regularly poll the pg_xlog subdirectory to check for files placed there.")));
	}
	else
	{
		if (recoveryRestoreCommand == NULL)
			ereport(FATAL,
					(errmsg("recovery command file \"%s\" must specify restore_command when standby mode is not enabled",
							RECOVERY_COMMAND_FILE)));
	}

	/* Enable fetching from archive recovery area */
	InArchiveRecovery = true;

	/*
	 * If user specified recovery_target_timeline, validate it or compute the
	 * "latest" value.	We can't do this until after we've gotten the restore
	 * command and set InArchiveRecovery, because we need to fetch timeline
	 * history files from the archive.
	 */
	if (rtliGiven)
	{
		if (rtli)
		{
			/* Timeline 1 does not have a history file, all else should */
			if (rtli != 1 && !existsTimeLineHistory(rtli))
				ereport(FATAL,
						(errmsg("recovery target timeline %u does not exist",
								rtli)));
			recoveryTargetTLI = rtli;
			recoveryTargetIsLatest = false;
		}
		else
		{
			/* We start the "latest" search from pg_control's timeline */
			recoveryTargetTLI = findNewestTimeLine(recoveryTargetTLI);
			recoveryTargetIsLatest = true;
		}
	}

	FreeConfigVariables(head);
}

/*
 * Exit archive-recovery state
 */
static void
exitArchiveRecovery(TimeLineID endTLI, XLogSegNo endLogSegNo)
{
	char		recoveryPath[MAXPGPATH];
	char		xlogpath[MAXPGPATH];

	/*
	 * We are no longer in archive recovery state.
	 */
	InArchiveRecovery = false;

	/*
	 * Update min recovery point one last time.
	 */
	UpdateMinRecoveryPoint(InvalidXLogRecPtr, true);

	/*
	 * If the ending log segment is still open, close it (to avoid problems on
	 * Windows with trying to rename or delete an open file).
	 */
	if (readFile >= 0)
	{
		close(readFile);
		readFile = -1;
	}

	/*
	 * If we are establishing a new timeline, we have to copy data from the
	 * last WAL segment of the old timeline to create a starting WAL segment
	 * for the new timeline.
	 *
	 * Notify the archiver that the last WAL segment of the old timeline is
	 * ready to copy to archival storage. Otherwise, it is not archived for a
	 * while.
	 */
	if (endTLI != ThisTimeLineID)
	{
		XLogFileCopy(endLogSegNo, endTLI, endLogSegNo);

		if (XLogArchivingActive())
		{
			XLogFileName(xlogpath, endTLI, endLogSegNo);
			XLogArchiveNotify(xlogpath);
		}
	}

	/*
	 * Let's just make real sure there are not .ready or .done flags posted
	 * for the new segment.
	 */
	XLogFileName(xlogpath, ThisTimeLineID, endLogSegNo);
	XLogArchiveCleanup(xlogpath);

	/*
	 * Since there might be a partial WAL segment named RECOVERYXLOG, get rid
	 * of it.
	 */
	snprintf(recoveryPath, MAXPGPATH, XLOGDIR "/RECOVERYXLOG");
	unlink(recoveryPath);		/* ignore any error */

	/* Get rid of any remaining recovered timeline-history file, too */
	snprintf(recoveryPath, MAXPGPATH, XLOGDIR "/RECOVERYHISTORY");
	unlink(recoveryPath);		/* ignore any error */

	/*
	 * Rename the config file out of the way, so that we don't accidentally
	 * re-enter archive recovery mode in a subsequent crash.
	 */
	unlink(RECOVERY_COMMAND_DONE);
	if (rename(RECOVERY_COMMAND_FILE, RECOVERY_COMMAND_DONE) != 0)
		ereport(FATAL,
				(errcode_for_file_access(),
				 errmsg("could not rename file \"%s\" to \"%s\": %m",
						RECOVERY_COMMAND_FILE, RECOVERY_COMMAND_DONE)));

	ereport(LOG,
			(errmsg("archive recovery complete")));
}

/*
 * For point-in-time recovery, this function decides whether we want to
 * stop applying the XLOG at or after the current record.
 *
 * Returns TRUE if we are stopping, FALSE otherwise.  On TRUE return,
 * *includeThis is set TRUE if we should apply this record before stopping.
 *
 * We also track the timestamp of the latest applied COMMIT/ABORT
 * record in XLogCtl->recoveryLastXTime, for logging purposes.
 * Also, some information is saved in recoveryStopXid et al for use in
 * annotating the new timeline's history file.
 */
static bool
recoveryStopsHere(XLogRecord *record, bool *includeThis)
{
	bool		stopsHere;
	uint8		record_info;
	TimestampTz recordXtime;
	char		recordRPName[MAXFNAMELEN];

	/* We only consider stopping at COMMIT, ABORT or RESTORE POINT records */
	if (record->xl_rmid != RM_XACT_ID && record->xl_rmid != RM_XLOG_ID)
		return false;
	record_info = record->xl_info & ~XLR_INFO_MASK;
	if (record->xl_rmid == RM_XACT_ID && record_info == XLOG_XACT_COMMIT_COMPACT)
	{
		xl_xact_commit_compact *recordXactCommitData;

		recordXactCommitData = (xl_xact_commit_compact *) XLogRecGetData(record);
		recordXtime = recordXactCommitData->xact_time;
	}
	else if (record->xl_rmid == RM_XACT_ID && record_info == XLOG_XACT_COMMIT)
	{
		xl_xact_commit *recordXactCommitData;

		recordXactCommitData = (xl_xact_commit *) XLogRecGetData(record);
		recordXtime = recordXactCommitData->xact_time;
	}
	else if (record->xl_rmid == RM_XACT_ID && record_info == XLOG_XACT_ABORT)
	{
		xl_xact_abort *recordXactAbortData;

		recordXactAbortData = (xl_xact_abort *) XLogRecGetData(record);
		recordXtime = recordXactAbortData->xact_time;
	}
	else if (record->xl_rmid == RM_XLOG_ID && record_info == XLOG_RESTORE_POINT)
	{
		xl_restore_point *recordRestorePointData;

		recordRestorePointData = (xl_restore_point *) XLogRecGetData(record);
		recordXtime = recordRestorePointData->rp_time;
		strncpy(recordRPName, recordRestorePointData->rp_name, MAXFNAMELEN);
	}
	else
		return false;

	/* Do we have a PITR target at all? */
	if (recoveryTarget == RECOVERY_TARGET_UNSET)
	{
		/*
		 * Save timestamp of latest transaction commit/abort if this is a
		 * transaction record
		 */
		if (record->xl_rmid == RM_XACT_ID)
			SetLatestXTime(recordXtime);
		return false;
	}

	if (recoveryTarget == RECOVERY_TARGET_XID)
	{
		/*
		 * There can be only one transaction end record with this exact
		 * transactionid
		 *
		 * when testing for an xid, we MUST test for equality only, since
		 * transactions are numbered in the order they start, not the order
		 * they complete. A higher numbered xid will complete before you about
		 * 50% of the time...
		 */
		stopsHere = (record->xl_xid == recoveryTargetXid);
		if (stopsHere)
			*includeThis = recoveryTargetInclusive;
	}
	else if (recoveryTarget == RECOVERY_TARGET_NAME)
	{
		/*
		 * There can be many restore points that share the same name, so we
		 * stop at the first one
		 */
		stopsHere = (strcmp(recordRPName, recoveryTargetName) == 0);

		/*
		 * Ignore recoveryTargetInclusive because this is not a transaction
		 * record
		 */
		*includeThis = false;
	}
	else
	{
		/*
		 * There can be many transactions that share the same commit time, so
		 * we stop after the last one, if we are inclusive, or stop at the
		 * first one if we are exclusive
		 */
		if (recoveryTargetInclusive)
			stopsHere = (recordXtime > recoveryTargetTime);
		else
			stopsHere = (recordXtime >= recoveryTargetTime);
		if (stopsHere)
			*includeThis = false;
	}

	if (stopsHere)
	{
		recoveryStopXid = record->xl_xid;
		recoveryStopTime = recordXtime;
		recoveryStopAfter = *includeThis;

		if (record_info == XLOG_XACT_COMMIT_COMPACT || record_info == XLOG_XACT_COMMIT)
		{
			if (recoveryStopAfter)
				ereport(LOG,
						(errmsg("recovery stopping after commit of transaction %u, time %s",
								recoveryStopXid,
								timestamptz_to_str(recoveryStopTime))));
			else
				ereport(LOG,
						(errmsg("recovery stopping before commit of transaction %u, time %s",
								recoveryStopXid,
								timestamptz_to_str(recoveryStopTime))));
		}
		else if (record_info == XLOG_XACT_ABORT)
		{
			if (recoveryStopAfter)
				ereport(LOG,
						(errmsg("recovery stopping after abort of transaction %u, time %s",
								recoveryStopXid,
								timestamptz_to_str(recoveryStopTime))));
			else
				ereport(LOG,
						(errmsg("recovery stopping before abort of transaction %u, time %s",
								recoveryStopXid,
								timestamptz_to_str(recoveryStopTime))));
		}
		else
		{
			strncpy(recoveryStopName, recordRPName, MAXFNAMELEN);

			ereport(LOG,
				(errmsg("recovery stopping at restore point \"%s\", time %s",
						recoveryStopName,
						timestamptz_to_str(recoveryStopTime))));
		}

		/*
		 * Note that if we use a RECOVERY_TARGET_TIME then we can stop at a
		 * restore point since they are timestamped, though the latest
		 * transaction time is not updated.
		 */
		if (record->xl_rmid == RM_XACT_ID && recoveryStopAfter)
			SetLatestXTime(recordXtime);
	}
	else if (record->xl_rmid == RM_XACT_ID)
		SetLatestXTime(recordXtime);

	return stopsHere;
}

/*
 * Recheck shared recoveryPause by polling.
 *
 * XXX Can also be done with shared latch.
 */
static void
recoveryPausesHere(void)
{
	ereport(LOG,
			(errmsg("recovery has paused"),
			 errhint("Execute pg_xlog_replay_resume() to continue.")));

	while (RecoveryIsPaused())
	{
		pg_usleep(1000000L);	/* 1000 ms */
		HandleStartupProcInterrupts();
	}
}

bool
RecoveryIsPaused(void)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;
	bool		recoveryPause;

	SpinLockAcquire(&xlogctl->info_lck);
	recoveryPause = xlogctl->recoveryPause;
	SpinLockRelease(&xlogctl->info_lck);

	return recoveryPause;
}

void
SetRecoveryPause(bool recoveryPause)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;

	SpinLockAcquire(&xlogctl->info_lck);
	xlogctl->recoveryPause = recoveryPause;
	SpinLockRelease(&xlogctl->info_lck);
}

/*
 * Save timestamp of latest processed commit/abort record.
 *
 * We keep this in XLogCtl, not a simple static variable, so that it can be
 * seen by processes other than the startup process.  Note in particular
 * that CreateRestartPoint is executed in the checkpointer.
 */
static void
SetLatestXTime(TimestampTz xtime)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;

	SpinLockAcquire(&xlogctl->info_lck);
	xlogctl->recoveryLastXTime = xtime;
	SpinLockRelease(&xlogctl->info_lck);
}

/*
 * Fetch timestamp of latest processed commit/abort record.
 */
TimestampTz
GetLatestXTime(void)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;
	TimestampTz xtime;

	SpinLockAcquire(&xlogctl->info_lck);
	xtime = xlogctl->recoveryLastXTime;
	SpinLockRelease(&xlogctl->info_lck);

	return xtime;
}

/*
 * Save timestamp of the next chunk of WAL records to apply.
 *
 * We keep this in XLogCtl, not a simple static variable, so that it can be
 * seen by all backends.
 */
static void
SetCurrentChunkStartTime(TimestampTz xtime)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;

	SpinLockAcquire(&xlogctl->info_lck);
	xlogctl->currentChunkStartTime = xtime;
	SpinLockRelease(&xlogctl->info_lck);
}

/*
 * Fetch timestamp of latest processed commit/abort record.
 * Startup process maintains an accurate local copy in XLogReceiptTime
 */
TimestampTz
GetCurrentChunkReplayStartTime(void)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;
	TimestampTz xtime;

	SpinLockAcquire(&xlogctl->info_lck);
	xtime = xlogctl->currentChunkStartTime;
	SpinLockRelease(&xlogctl->info_lck);

	return xtime;
}

/*
 * Returns time of receipt of current chunk of XLOG data, as well as
 * whether it was received from streaming replication or from archives.
 */
void
GetXLogReceiptTime(TimestampTz *rtime, bool *fromStream)
{
	/*
	 * This must be executed in the startup process, since we don't export the
	 * relevant state to shared memory.
	 */
	Assert(InRecovery);

	*rtime = XLogReceiptTime;
	*fromStream = (XLogReceiptSource == XLOG_FROM_STREAM);
}

/*
 * Note that text field supplied is a parameter name and does not require
 * translation
 */
#define RecoveryRequiresIntParameter(param_name, currValue, minValue) \
do { \
	if ((currValue) < (minValue)) \
		ereport(ERROR, \
				(errcode(ERRCODE_INVALID_PARAMETER_VALUE), \
				 errmsg("hot standby is not possible because " \
						"%s = %d is a lower setting than on the master server " \
						"(its value was %d)", \
						param_name, \
						currValue, \
						minValue))); \
} while(0)

/*
 * Check to see if required parameters are set high enough on this server
 * for various aspects of recovery operation.
 */
static void
CheckRequiredParameterValues(void)
{
	/*
	 * For archive recovery, the WAL must be generated with at least 'archive'
	 * wal_level.
	 */
	if (InArchiveRecovery && ControlFile->wal_level == WAL_LEVEL_MINIMAL)
	{
		ereport(WARNING,
				(errmsg("WAL was generated with wal_level=minimal, data may be missing"),
				 errhint("This happens if you temporarily set wal_level=minimal without taking a new base backup.")));
	}

	/*
	 * For Hot Standby, the WAL must be generated with 'hot_standby' mode, and
	 * we must have at least as many backend slots as the primary.
	 */
	if (InArchiveRecovery && EnableHotStandby)
	{
		if (ControlFile->wal_level < WAL_LEVEL_HOT_STANDBY)
			ereport(ERROR,
					(errmsg("hot standby is not possible because wal_level was not set to \"hot_standby\" on the master server"),
					 errhint("Either set wal_level to \"hot_standby\" on the master, or turn off hot_standby here.")));

		/* We ignore autovacuum_max_workers when we make this test. */
		RecoveryRequiresIntParameter("max_connections",
									 MaxConnections,
									 ControlFile->MaxConnections);
		RecoveryRequiresIntParameter("max_prepared_transactions",
									 max_prepared_xacts,
									 ControlFile->max_prepared_xacts);
		RecoveryRequiresIntParameter("max_locks_per_transaction",
									 max_locks_per_xact,
									 ControlFile->max_locks_per_xact);
	}
}

/*
 * This must be called ONCE during postmaster or standalone-backend startup
 */
void
StartupXLOG(void)
{
	XLogCtlInsert *Insert;
	CheckPoint	checkPoint;
	bool		wasShutdown;
	bool		reachedStopPoint = false;
	bool		haveBackupLabel = false;
	XLogRecPtr	RecPtr,
				checkPointLoc,
				EndOfLog;
	XLogSegNo	endLogSegNo;
	XLogRecord *record;
	uint32		freespace;
	TransactionId oldestActiveXID;
	bool		backupEndRequired = false;
	bool		backupFromStandby = false;
	DBState		dbstate_at_startup;

	/*
	 * Read control file and check XLOG status looks valid.
	 *
	 * Note: in most control paths, *ControlFile is already valid and we need
	 * not do ReadControlFile() here, but might as well do it to be sure.
	 */
	ReadControlFile();

	if (ControlFile->state < DB_SHUTDOWNED ||
		ControlFile->state > DB_IN_PRODUCTION ||
		!XRecOffIsValid(ControlFile->checkPoint))
		ereport(FATAL,
				(errmsg("control file contains invalid data")));

	if (ControlFile->state == DB_SHUTDOWNED)
		ereport(LOG,
				(errmsg("database system was shut down at %s",
						str_time(ControlFile->time))));
	else if (ControlFile->state == DB_SHUTDOWNED_IN_RECOVERY)
		ereport(LOG,
				(errmsg("database system was shut down in recovery at %s",
						str_time(ControlFile->time))));
	else if (ControlFile->state == DB_SHUTDOWNING)
		ereport(LOG,
				(errmsg("database system shutdown was interrupted; last known up at %s",
						str_time(ControlFile->time))));
	else if (ControlFile->state == DB_IN_CRASH_RECOVERY)
		ereport(LOG,
		   (errmsg("database system was interrupted while in recovery at %s",
				   str_time(ControlFile->time)),
			errhint("This probably means that some data is corrupted and"
					" you will have to use the last backup for recovery.")));
	else if (ControlFile->state == DB_IN_ARCHIVE_RECOVERY)
		ereport(LOG,
				(errmsg("database system was interrupted while in recovery at log time %s",
						str_time(ControlFile->checkPointCopy.time)),
				 errhint("If this has occurred more than once some data might be corrupted"
			  " and you might need to choose an earlier recovery target.")));
	else if (ControlFile->state == DB_IN_PRODUCTION)
		ereport(LOG,
			  (errmsg("database system was interrupted; last known up at %s",
					  str_time(ControlFile->time))));

	/* This is just to allow attaching to startup process with a debugger */
#ifdef XLOG_REPLAY_DELAY
	if (ControlFile->state != DB_SHUTDOWNED)
		pg_usleep(60000000L);
#endif

	/*
	 * Verify that pg_xlog and pg_xlog/archive_status exist.  In cases where
	 * someone has performed a copy for PITR, these directories may have been
	 * excluded and need to be re-created.
	 */
	ValidateXLOGDirectoryStructure();

	/*
	 * Clear out any old relcache cache files.	This is *necessary* if we do
	 * any WAL replay, since that would probably result in the cache files
	 * being out of sync with database reality.  In theory we could leave them
	 * in place if the database had been cleanly shut down, but it seems
	 * safest to just remove them always and let them be rebuilt during the
	 * first backend startup.
	 */
	RelationCacheInitFileRemove();

	/*
	 * Initialize on the assumption we want to recover to the same timeline
	 * that's active according to pg_control.
	 */
	recoveryTargetTLI = ControlFile->checkPointCopy.ThisTimeLineID;

	/*
	 * Check for recovery control file, and if so set up state for offline
	 * recovery
	 */
	readRecoveryCommandFile();

	/* Now we can determine the list of expected TLIs */
	expectedTLIs = readTimeLineHistory(recoveryTargetTLI);

	/*
	 * If pg_control's timeline is not in expectedTLIs, then we cannot
	 * proceed: the backup is not part of the history of the requested
	 * timeline.
	 */
	if (!list_member_int(expectedTLIs,
						 (int) ControlFile->checkPointCopy.ThisTimeLineID))
		ereport(FATAL,
				(errmsg("requested timeline %u is not a child of database system timeline %u",
						recoveryTargetTLI,
						ControlFile->checkPointCopy.ThisTimeLineID)));

	/*
	 * Save the selected recovery target timeline ID and
	 * archive_cleanup_command in shared memory so that other processes can
	 * see them
	 */
	XLogCtl->RecoveryTargetTLI = recoveryTargetTLI;
	strncpy(XLogCtl->archiveCleanupCommand,
			archiveCleanupCommand ? archiveCleanupCommand : "",
			sizeof(XLogCtl->archiveCleanupCommand));

	if (InArchiveRecovery)
	{
		if (StandbyMode)
			ereport(LOG,
					(errmsg("entering standby mode")));
		else if (recoveryTarget == RECOVERY_TARGET_XID)
			ereport(LOG,
					(errmsg("starting point-in-time recovery to XID %u",
							recoveryTargetXid)));
		else if (recoveryTarget == RECOVERY_TARGET_TIME)
			ereport(LOG,
					(errmsg("starting point-in-time recovery to %s",
							timestamptz_to_str(recoveryTargetTime))));
		else if (recoveryTarget == RECOVERY_TARGET_NAME)
			ereport(LOG,
					(errmsg("starting point-in-time recovery to \"%s\"",
							recoveryTargetName)));
		else
			ereport(LOG,
					(errmsg("starting archive recovery")));
	}

	/*
	 * Take ownership of the wakeup latch if we're going to sleep during
	 * recovery.
	 */
	if (StandbyMode)
		OwnLatch(&XLogCtl->recoveryWakeupLatch);

	if (read_backup_label(&checkPointLoc, &backupEndRequired,
						  &backupFromStandby))
	{
		/*
		 * When a backup_label file is present, we want to roll forward from
		 * the checkpoint it identifies, rather than using pg_control.
		 */
		record = ReadCheckpointRecord(checkPointLoc, 0);
		if (record != NULL)
		{
			memcpy(&checkPoint, XLogRecGetData(record), sizeof(CheckPoint));
			wasShutdown = (record->xl_info == XLOG_CHECKPOINT_SHUTDOWN);
			ereport(DEBUG1,
					(errmsg("checkpoint record is at %X/%X",
							(uint32) (checkPointLoc >> 32), (uint32) checkPointLoc)));
			InRecovery = true;	/* force recovery even if SHUTDOWNED */

			/*
			 * Make sure that REDO location exists. This may not be the case
			 * if there was a crash during an online backup, which left a
			 * backup_label around that references a WAL segment that's
			 * already been archived.
			 */
			if (XLByteLT(checkPoint.redo, checkPointLoc))
			{
				if (!ReadRecord(&(checkPoint.redo), LOG, false))
					ereport(FATAL,
							(errmsg("could not find redo location referenced by checkpoint record"),
							 errhint("If you are not restoring from a backup, try removing the file \"%s/backup_label\".", DataDir)));
			}
		}
		else
		{
			ereport(FATAL,
					(errmsg("could not locate required checkpoint record"),
					 errhint("If you are not restoring from a backup, try removing the file \"%s/backup_label\".", DataDir)));
			wasShutdown = false;	/* keep compiler quiet */
		}
		/* set flag to delete it later */
		haveBackupLabel = true;
	}
	else
	{
		/*
		 * Get the last valid checkpoint record.  If the latest one according
		 * to pg_control is broken, try the next-to-last one.
		 */
		checkPointLoc = ControlFile->checkPoint;
		RedoStartLSN = ControlFile->checkPointCopy.redo;
		record = ReadCheckpointRecord(checkPointLoc, 1);
		if (record != NULL)
		{
			ereport(DEBUG1,
					(errmsg("checkpoint record is at %X/%X",
							(uint32) (checkPointLoc >> 32), (uint32) checkPointLoc)));
		}
		else if (StandbyMode)
		{
			/*
			 * The last valid checkpoint record required for a streaming
			 * recovery exists in neither standby nor the primary.
			 */
			ereport(PANIC,
					(errmsg("could not locate a valid checkpoint record")));
		}
		else
		{
			checkPointLoc = ControlFile->prevCheckPoint;
			record = ReadCheckpointRecord(checkPointLoc, 2);
			if (record != NULL)
			{
				ereport(LOG,
						(errmsg("using previous checkpoint record at %X/%X",
								(uint32) (checkPointLoc >> 32), (uint32) checkPointLoc)));
				InRecovery = true;		/* force recovery even if SHUTDOWNED */
			}
			else
				ereport(PANIC,
					 (errmsg("could not locate a valid checkpoint record")));
		}
		memcpy(&checkPoint, XLogRecGetData(record), sizeof(CheckPoint));
		wasShutdown = (record->xl_info == XLOG_CHECKPOINT_SHUTDOWN);
	}

	LastRec = RecPtr = checkPointLoc;

	ereport(DEBUG1,
			(errmsg("redo record is at %X/%X; shutdown %s",
					(uint32) (checkPoint.redo >> 32), (uint32) checkPoint.redo,
					wasShutdown ? "TRUE" : "FALSE")));
	ereport(DEBUG1,
			(errmsg("next transaction ID: %u/%u; next OID: %u",
					checkPoint.nextXidEpoch, checkPoint.nextXid,
					checkPoint.nextOid)));
	ereport(DEBUG1,
			(errmsg("next MultiXactId: %u; next MultiXactOffset: %u",
					checkPoint.nextMulti, checkPoint.nextMultiOffset)));
	ereport(DEBUG1,
			(errmsg("oldest unfrozen transaction ID: %u, in database %u",
					checkPoint.oldestXid, checkPoint.oldestXidDB)));
	if (!TransactionIdIsNormal(checkPoint.nextXid))
		ereport(PANIC,
				(errmsg("invalid next transaction ID")));

	/* initialize shared memory variables from the checkpoint record */
	ShmemVariableCache->nextXid = checkPoint.nextXid;
	ShmemVariableCache->nextOid = checkPoint.nextOid;
	ShmemVariableCache->oidCount = 0;
	MultiXactSetNextMXact(checkPoint.nextMulti, checkPoint.nextMultiOffset);
	SetTransactionIdLimit(checkPoint.oldestXid, checkPoint.oldestXidDB);
	XLogCtl->ckptXidEpoch = checkPoint.nextXidEpoch;
	XLogCtl->ckptXid = checkPoint.nextXid;

	/*
	 * We must replay WAL entries using the same TimeLineID they were created
	 * under, so temporarily adopt the TLI indicated by the checkpoint (see
	 * also xlog_redo()).
	 */
	ThisTimeLineID = checkPoint.ThisTimeLineID;

	lastFullPageWrites = checkPoint.fullPageWrites;

	RedoRecPtr = XLogCtl->Insert.RedoRecPtr = checkPoint.redo;

	if (XLByteLT(RecPtr, checkPoint.redo))
		ereport(PANIC,
				(errmsg("invalid redo in checkpoint record")));

	/*
	 * Check whether we need to force recovery from WAL.  If it appears to
	 * have been a clean shutdown and we did not have a recovery.conf file,
	 * then assume no recovery needed.
	 */
	if (XLByteLT(checkPoint.redo, RecPtr))
	{
		if (wasShutdown)
			ereport(PANIC,
					(errmsg("invalid redo record in shutdown checkpoint")));
		InRecovery = true;
	}
	else if (ControlFile->state != DB_SHUTDOWNED)
		InRecovery = true;
	else if (InArchiveRecovery)
	{
		/* force recovery due to presence of recovery.conf */
		InRecovery = true;
	}

	/* REDO */
	if (InRecovery)
	{
		int			rmid;

		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		/*
		 * Update pg_control to show that we are recovering and to show the
		 * selected checkpoint as the place we are starting from. We also mark
		 * pg_control with any minimum recovery stop point obtained from a
		 * backup history file.
		 */
		dbstate_at_startup = ControlFile->state;
		if (InArchiveRecovery)
			ControlFile->state = DB_IN_ARCHIVE_RECOVERY;
		else
		{
			ereport(LOG,
					(errmsg("database system was not properly shut down; "
							"automatic recovery in progress")));
			ControlFile->state = DB_IN_CRASH_RECOVERY;
		}
		ControlFile->prevCheckPoint = ControlFile->checkPoint;
		ControlFile->checkPoint = checkPointLoc;
		ControlFile->checkPointCopy = checkPoint;
		if (InArchiveRecovery)
		{
			/* initialize minRecoveryPoint if not set yet */
			if (XLByteLT(ControlFile->minRecoveryPoint, checkPoint.redo))
				ControlFile->minRecoveryPoint = checkPoint.redo;
		}

		/*
		 * Set backupStartPoint if we're starting recovery from a base backup.
		 *
		 * Set backupEndPoint and use minRecoveryPoint as the backup end
		 * location if we're starting recovery from a base backup which was
		 * taken from the standby. In this case, the database system status in
		 * pg_control must indicate DB_IN_ARCHIVE_RECOVERY. If not, which
		 * means that backup is corrupted, so we cancel recovery.
		 */
		if (haveBackupLabel)
		{
			ControlFile->backupStartPoint = checkPoint.redo;
			ControlFile->backupEndRequired = backupEndRequired;

			if (backupFromStandby)
			{
				if (dbstate_at_startup != DB_IN_ARCHIVE_RECOVERY)
					ereport(FATAL,
							(errmsg("backup_label contains data inconsistent with control file"),
							 errhint("This means that the backup is corrupted and you will "
							   "have to use another backup for recovery.")));
				ControlFile->backupEndPoint = ControlFile->minRecoveryPoint;
			}
		}
		ControlFile->time = (pg_time_t) time(NULL);
		/* No need to hold ControlFileLock yet, we aren't up far enough */
		UpdateControlFile();

		/* initialize our local copy of minRecoveryPoint */
		minRecoveryPoint = ControlFile->minRecoveryPoint;

		/*
		 * Reset pgstat data, because it may be invalid after recovery.
		 */
		pgstat_reset_all();

		/*
		 * If there was a backup label file, it's done its job and the info
		 * has now been propagated into pg_control.  We must get rid of the
		 * label file so that if we crash during recovery, we'll pick up at
		 * the latest recovery restartpoint instead of going all the way back
		 * to the backup start point.  It seems prudent though to just rename
		 * the file out of the way rather than delete it completely.
		 */
		if (haveBackupLabel)
		{
			unlink(BACKUP_LABEL_OLD);
			if (rename(BACKUP_LABEL_FILE, BACKUP_LABEL_OLD) != 0)
				ereport(FATAL,
						(errcode_for_file_access(),
						 errmsg("could not rename file \"%s\" to \"%s\": %m",
								BACKUP_LABEL_FILE, BACKUP_LABEL_OLD)));
		}

		/* Check that the GUCs used to generate the WAL allow recovery */
		CheckRequiredParameterValues();

		/*
		 * We're in recovery, so unlogged relations may be trashed and must be
		 * reset.  This should be done BEFORE allowing Hot Standby
		 * connections, so that read-only backends don't try to read whatever
		 * garbage is left over from before.
		 */
		ResetUnloggedRelations(UNLOGGED_RELATION_CLEANUP);

		/*
		 * Likewise, delete any saved transaction snapshot files that got left
		 * behind by crashed backends.
		 */
		DeleteAllExportedSnapshotFiles();

		/*
		 * Initialize for Hot Standby, if enabled. We won't let backends in
		 * yet, not until we've reached the min recovery point specified in
		 * control file and we've established a recovery snapshot from a
		 * running-xacts WAL record.
		 */
		if (InArchiveRecovery && EnableHotStandby)
		{
			TransactionId *xids;
			int			nxids;

			ereport(DEBUG1,
					(errmsg("initializing for hot standby")));

			InitRecoveryTransactionEnvironment();

			if (wasShutdown)
				oldestActiveXID = PrescanPreparedTransactions(&xids, &nxids);
			else
				oldestActiveXID = checkPoint.oldestActiveXid;
			Assert(TransactionIdIsValid(oldestActiveXID));

			/*
			 * Startup commit log and subtrans only. Other SLRUs are not
			 * maintained during recovery and need not be started yet.
			 */
			StartupCLOG();
			StartupSUBTRANS(oldestActiveXID);

			/*
			 * If we're beginning at a shutdown checkpoint, we know that
			 * nothing was running on the master at this point. So fake-up an
			 * empty running-xacts record and use that here and now. Recover
			 * additional standby state for prepared transactions.
			 */
			if (wasShutdown)
			{
				RunningTransactionsData running;
				TransactionId latestCompletedXid;

				/*
				 * Construct a RunningTransactions snapshot representing a
				 * shut down server, with only prepared transactions still
				 * alive. We're never overflowed at this point because all
				 * subxids are listed with their parent prepared transactions.
				 */
				running.xcnt = nxids;
				running.subxid_overflow = false;
				running.nextXid = checkPoint.nextXid;
				running.oldestRunningXid = oldestActiveXID;
				latestCompletedXid = checkPoint.nextXid;
				TransactionIdRetreat(latestCompletedXid);
				Assert(TransactionIdIsNormal(latestCompletedXid));
				running.latestCompletedXid = latestCompletedXid;
				running.xids = xids;

				ProcArrayApplyRecoveryInfo(&running);

				StandbyRecoverPreparedTransactions(false);
			}
		}

		/* Initialize resource managers */
		for (rmid = 0; rmid <= RM_MAX_ID; rmid++)
		{
			if (RmgrTable[rmid].rm_startup != NULL)
				RmgrTable[rmid].rm_startup();
		}

		/*
		 * Initialize shared replayEndRecPtr, recoveryLastRecPtr, and
		 * recoveryLastXTime.
		 *
		 * This is slightly confusing if we're starting from an online
		 * checkpoint; we've just read and replayed the chekpoint record, but
		 * we're going to start replay from its redo pointer, which precedes
		 * the location of the checkpoint record itself. So even though the
		 * last record we've replayed is indeed ReadRecPtr, we haven't
		 * replayed all the preceding records yet. That's OK for the current
		 * use of these variables.
		 */
		SpinLockAcquire(&xlogctl->info_lck);
		xlogctl->replayEndRecPtr = ReadRecPtr;
		xlogctl->recoveryLastRecPtr = EndRecPtr;
		xlogctl->recoveryLastXTime = 0;
		xlogctl->currentChunkStartTime = 0;
		xlogctl->recoveryPause = false;
		SpinLockRelease(&xlogctl->info_lck);

		/* Also ensure XLogReceiptTime has a sane value */
		XLogReceiptTime = GetCurrentTimestamp();

		/*
		 * Let postmaster know we've started redo now, so that it can launch
		 * checkpointer to perform restartpoints.  We don't bother during
		 * crash recovery as restartpoints can only be performed during
		 * archive recovery.  And we'd like to keep crash recovery simple, to
		 * avoid introducing bugs that could affect you when recovering after
		 * crash.
		 *
		 * After this point, we can no longer assume that we're the only
		 * process in addition to postmaster!  Also, fsync requests are
		 * subsequently to be handled by the checkpointer, not locally.
		 */
		if (InArchiveRecovery && IsUnderPostmaster)
		{
			PublishStartupProcessInformation();
			SetForwardFsyncRequests();
			SendPostmasterSignal(PMSIGNAL_RECOVERY_STARTED);
			bgwriterLaunched = true;
		}

		/*
		 * Allow read-only connections immediately if we're consistent
		 * already.
		 */
		CheckRecoveryConsistency();

		/*
		 * Find the first record that logically follows the checkpoint --- it
		 * might physically precede it, though.
		 */
		if (XLByteLT(checkPoint.redo, RecPtr))
		{
			/* back up to find the record */
			record = ReadRecord(&(checkPoint.redo), PANIC, false);
		}
		else
		{
			/* just have to read next record after CheckPoint */
			record = ReadRecord(NULL, LOG, false);
		}

		if (record != NULL)
		{
			bool		recoveryContinue = true;
			bool		recoveryApply = true;
			bool		recoveryPause = false;
			ErrorContextCallback errcallback;
			TimestampTz xtime;

			InRedo = true;

			ereport(LOG,
					(errmsg("redo starts at %X/%X",
							(uint32) (ReadRecPtr >> 32), (uint32) ReadRecPtr)));

			/*
			 * main redo apply loop
			 */
			do
			{
#ifdef WAL_DEBUG
				if (XLOG_DEBUG ||
				 (rmid == RM_XACT_ID && trace_recovery_messages <= DEBUG2) ||
					(rmid != RM_XACT_ID && trace_recovery_messages <= DEBUG3))
				{
					StringInfoData buf;

					initStringInfo(&buf);
					appendStringInfo(&buf, "REDO @ %X/%X; LSN %X/%X: ",
									 (uint32) (ReadRecPtr >> 32), (uint32) ReadRecPtr,
									 (uint32) (EndRecPtr >> 32), (uint32) EndRecPtr);
					xlog_outrec(&buf, record);
					appendStringInfo(&buf, " - ");
					RmgrTable[record->xl_rmid].rm_desc(&buf,
													   record->xl_info,
													 XLogRecGetData(record));
					elog(LOG, "%s", buf.data);
					pfree(buf.data);
				}
#endif

				/* Handle interrupt signals of startup process */
				HandleStartupProcInterrupts();

				/* Allow read-only connections if we're consistent now */
				CheckRecoveryConsistency();

				/*
				 * Have we reached our recovery target?
				 */
				if (recoveryStopsHere(record, &recoveryApply))
				{
					/*
					 * Pause only if users can connect to send a resume
					 * message
					 */
					if (recoveryPauseAtTarget && standbyState == STANDBY_SNAPSHOT_READY)
					{
						SetRecoveryPause(true);
						recoveryPausesHere();
					}
					reachedStopPoint = true;	/* see below */
					recoveryContinue = false;
					if (!recoveryApply)
						break;
				}

				/* Setup error traceback support for ereport() */
				errcallback.callback = rm_redo_error_callback;
				errcallback.arg = (void *) record;
				errcallback.previous = error_context_stack;
				error_context_stack = &errcallback;

				/*
				 * ShmemVariableCache->nextXid must be beyond record's xid.
				 *
				 * We don't expect anyone else to modify nextXid, hence we
				 * don't need to hold a lock while examining it.  We still
				 * acquire the lock to modify it, though.
				 */
				if (TransactionIdFollowsOrEquals(record->xl_xid,
												 ShmemVariableCache->nextXid))
				{
					LWLockAcquire(XidGenLock, LW_EXCLUSIVE);
					ShmemVariableCache->nextXid = record->xl_xid;
					TransactionIdAdvance(ShmemVariableCache->nextXid);
					LWLockRelease(XidGenLock);
				}

				/*
				 * Update shared replayEndRecPtr before replaying this record,
				 * so that XLogFlush will update minRecoveryPoint correctly.
				 */
				SpinLockAcquire(&xlogctl->info_lck);
				xlogctl->replayEndRecPtr = EndRecPtr;
				recoveryPause = xlogctl->recoveryPause;
				SpinLockRelease(&xlogctl->info_lck);

				/*
				 * Pause only if users can connect to send a resume message
				 */
				if (recoveryPause && standbyState == STANDBY_SNAPSHOT_READY)
					recoveryPausesHere();

				/*
				 * If we are attempting to enter Hot Standby mode, process
				 * XIDs we see
				 */
				if (standbyState >= STANDBY_INITIALIZED &&
					TransactionIdIsValid(record->xl_xid))
					RecordKnownAssignedTransactionIds(record->xl_xid);

				/* Now apply the WAL record itself */
				RmgrTable[record->xl_rmid].rm_redo(EndRecPtr, record);

				/* Pop the error context stack */
				error_context_stack = errcallback.previous;

				if (!XLogRecPtrIsInvalid(ControlFile->backupEndPoint) &&
					XLByteLE(ControlFile->backupEndPoint, EndRecPtr))
				{
					/*
					 * We have reached the end of base backup, the point where
					 * the minimum recovery point in pg_control indicates. The
					 * data on disk is now consistent. Reset backupStartPoint
					 * and backupEndPoint.
					 */
					elog(DEBUG1, "end of backup reached");

					LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);

					MemSet(&ControlFile->backupStartPoint, 0, sizeof(XLogRecPtr));
					MemSet(&ControlFile->backupEndPoint, 0, sizeof(XLogRecPtr));
					ControlFile->backupEndRequired = false;
					UpdateControlFile();

					LWLockRelease(ControlFileLock);
				}

				/*
				 * Update shared recoveryLastRecPtr after this record has been
				 * replayed.
				 */
				SpinLockAcquire(&xlogctl->info_lck);
				xlogctl->recoveryLastRecPtr = EndRecPtr;
				SpinLockRelease(&xlogctl->info_lck);

				LastRec = ReadRecPtr;

				record = ReadRecord(NULL, LOG, false);
			} while (record != NULL && recoveryContinue);

			/*
			 * end of main redo apply loop
			 */

			ereport(LOG,
					(errmsg("redo done at %X/%X",
							(uint32) (ReadRecPtr >> 32), (uint32) ReadRecPtr)));
			xtime = GetLatestXTime();
			if (xtime)
				ereport(LOG,
					 (errmsg("last completed transaction was at log time %s",
							 timestamptz_to_str(xtime))));
			InRedo = false;
		}
		else
		{
			/* there are no WAL records following the checkpoint */
			ereport(LOG,
					(errmsg("redo is not required")));
		}
	}

	/*
	 * Kill WAL receiver, if it's still running, before we continue to write
	 * the startup checkpoint record. It will trump over the checkpoint and
	 * subsequent records if it's still alive when we start writing WAL.
	 */
	ShutdownWalRcv();

	/*
	 * We don't need the latch anymore. It's not strictly necessary to disown
	 * it, but let's do it for the sake of tidiness.
	 */
	if (StandbyMode)
		DisownLatch(&XLogCtl->recoveryWakeupLatch);

	/*
	 * We are now done reading the xlog from stream. Turn off streaming
	 * recovery to force fetching the files (which would be required at end of
	 * recovery, e.g., timeline history file) from archive or pg_xlog.
	 */
	StandbyMode = false;

	/*
	 * Re-fetch the last valid or last applied record, so we can identify the
	 * exact endpoint of what we consider the valid portion of WAL.
	 */
	record = ReadRecord(&LastRec, PANIC, false);
	EndOfLog = EndRecPtr;
	XLByteToPrevSeg(EndOfLog, endLogSegNo);

	/*
	 * Complain if we did not roll forward far enough to render the backup
	 * dump consistent.  Note: it is indeed okay to look at the local variable
	 * minRecoveryPoint here, even though ControlFile->minRecoveryPoint might
	 * be further ahead --- ControlFile->minRecoveryPoint cannot have been
	 * advanced beyond the WAL we processed.
	 */
	if (InRecovery &&
		(XLByteLT(EndOfLog, minRecoveryPoint) ||
		 !XLogRecPtrIsInvalid(ControlFile->backupStartPoint)))
	{
		if (reachedStopPoint)
		{
			/* stopped because of stop request */
			ereport(FATAL,
					(errmsg("requested recovery stop point is before consistent recovery point")));
		}

		/*
		 * Ran off end of WAL before reaching end-of-backup WAL record, or
		 * minRecoveryPoint. That's usually a bad sign, indicating that you
		 * tried to recover from an online backup but never called
		 * pg_stop_backup(), or you didn't archive all the WAL up to that
		 * point. However, this also happens in crash recovery, if the system
		 * crashes while an online backup is in progress. We must not treat
		 * that as an error, or the database will refuse to start up.
		 */
		if (InArchiveRecovery || ControlFile->backupEndRequired)
		{
			if (ControlFile->backupEndRequired)
				ereport(FATAL,
						(errmsg("WAL ends before end of online backup"),
						 errhint("All WAL generated while online backup was taken must be available at recovery.")));
			else if (!XLogRecPtrIsInvalid(ControlFile->backupStartPoint))
				ereport(FATAL,
						(errmsg("WAL ends before end of online backup"),
						 errhint("Online backup started with pg_start_backup() must be ended with pg_stop_backup(), and all WAL up to that point must be available at recovery.")));
			else
				ereport(FATAL,
					  (errmsg("WAL ends before consistent recovery point")));
		}
	}

	/*
	 * Consider whether we need to assign a new timeline ID.
	 *
	 * If we are doing an archive recovery, we always assign a new ID.	This
	 * handles a couple of issues.	If we stopped short of the end of WAL
	 * during recovery, then we are clearly generating a new timeline and must
	 * assign it a unique new ID.  Even if we ran to the end, modifying the
	 * current last segment is problematic because it may result in trying to
	 * overwrite an already-archived copy of that segment, and we encourage
	 * DBAs to make their archive_commands reject that.  We can dodge the
	 * problem by making the new active segment have a new timeline ID.
	 *
	 * In a normal crash recovery, we can just extend the timeline we were in.
	 */
	if (InArchiveRecovery)
	{
		char	reason[200];

		ThisTimeLineID = findNewestTimeLine(recoveryTargetTLI) + 1;
		ereport(LOG,
				(errmsg("selected new timeline ID: %u", ThisTimeLineID)));

		/*
		 * Write comment to history file to explain why and where timeline
		 * changed. Comment varies according to the recovery target used.
		 */
		if (recoveryTarget == RECOVERY_TARGET_XID)
			snprintf(reason, sizeof(reason),
					 "%s transaction %u",
					 recoveryStopAfter ? "after" : "before",
					 recoveryStopXid);
		else if (recoveryTarget == RECOVERY_TARGET_TIME)
			snprintf(reason, sizeof(reason),
					 "%s %s\n",
					 recoveryStopAfter ? "after" : "before",
					 timestamptz_to_str(recoveryStopTime));
		else if (recoveryTarget == RECOVERY_TARGET_NAME)
			snprintf(reason, sizeof(reason),
					 "at restore point \"%s\"",
					 recoveryStopName);
		else
			snprintf(reason, sizeof(reason), "no recovery target specified");

		writeTimeLineHistory(ThisTimeLineID, recoveryTargetTLI,
							 curFileTLI, endLogSegNo, reason);
	}

	/* Save the selected TimeLineID in shared memory, too */
	XLogCtl->ThisTimeLineID = ThisTimeLineID;

	/*
	 * We are now done reading the old WAL.  Turn off archive fetching if it
	 * was active, and make a writable copy of the last WAL segment. (Note
	 * that we also have a copy of the last block of the old WAL in readBuf;
	 * we will use that below.)
	 */
	if (InArchiveRecovery)
		exitArchiveRecovery(curFileTLI, endLogSegNo);

	/*
	 * Prepare to write WAL starting at EndOfLog position, and init xlog
	 * buffer cache using the block containing the last record from the
	 * previous incarnation.
	 */
	openLogSegNo = endLogSegNo;
	openLogFile = XLogFileOpen(openLogSegNo);
	openLogOff = 0;
	Insert = &XLogCtl->Insert;
	Insert->PrevRecord = LastRec;
	XLogCtl->xlblocks[0] = ((EndOfLog - 1) / XLOG_BLCKSZ + 1) * XLOG_BLCKSZ;

	/*
	 * Tricky point here: readBuf contains the *last* block that the LastRec
	 * record spans, not the one it starts in.	The last block is indeed the
	 * one we want to use.
	 */
	Assert(readOff == (XLogCtl->xlblocks[0] - XLOG_BLCKSZ) % XLogSegSize);
	memcpy((char *) Insert->currpage, readBuf, XLOG_BLCKSZ);
	Insert->currpos = (char *) Insert->currpage +
		(EndOfLog + XLOG_BLCKSZ - XLogCtl->xlblocks[0]);

	LogwrtResult.Write = LogwrtResult.Flush = EndOfLog;

	XLogCtl->LogwrtResult = LogwrtResult;

	XLogCtl->LogwrtRqst.Write = EndOfLog;
	XLogCtl->LogwrtRqst.Flush = EndOfLog;

	freespace = INSERT_FREESPACE(Insert);
	if (freespace > 0)
	{
		/* Make sure rest of page is zero */
		MemSet(Insert->currpos, 0, freespace);
		XLogCtl->Write.curridx = 0;
	}
	else
	{
		/*
		 * Whenever LogwrtResult points to exactly the end of a page,
		 * Write.curridx must point to the *next* page (see XLogWrite()).
		 *
		 * Note: it might seem we should do AdvanceXLInsertBuffer() here, but
		 * this is sufficient.	The first actual attempt to insert a log
		 * record will advance the insert state.
		 */
		XLogCtl->Write.curridx = NextBufIdx(0);
	}

	/* Pre-scan prepared transactions to find out the range of XIDs present */
	oldestActiveXID = PrescanPreparedTransactions(NULL, NULL);

	/*
	 * Update full_page_writes in shared memory and write an XLOG_FPW_CHANGE
	 * record before resource manager writes cleanup WAL records or checkpoint
	 * record is written.
	 */
	Insert->fullPageWrites = lastFullPageWrites;
	LocalSetXLogInsertAllowed();
	UpdateFullPageWrites();
	LocalXLogInsertAllowed = -1;

	if (InRecovery)
	{
		int			rmid;

		/*
		 * Resource managers might need to write WAL records, eg, to record
		 * index cleanup actions.  So temporarily enable XLogInsertAllowed in
		 * this process only.
		 */
		LocalSetXLogInsertAllowed();

		/*
		 * Allow resource managers to do any required cleanup.
		 */
		for (rmid = 0; rmid <= RM_MAX_ID; rmid++)
		{
			if (RmgrTable[rmid].rm_cleanup != NULL)
				RmgrTable[rmid].rm_cleanup();
		}

		/* Disallow XLogInsert again */
		LocalXLogInsertAllowed = -1;

		/*
		 * Perform a checkpoint to update all our recovery activity to disk.
		 *
		 * Note that we write a shutdown checkpoint rather than an on-line
		 * one. This is not particularly critical, but since we may be
		 * assigning a new TLI, using a shutdown checkpoint allows us to have
		 * the rule that TLI only changes in shutdown checkpoints, which
		 * allows some extra error checking in xlog_redo.
		 */
		if (bgwriterLaunched)
			RequestCheckpoint(CHECKPOINT_END_OF_RECOVERY |
							  CHECKPOINT_IMMEDIATE |
							  CHECKPOINT_WAIT);
		else
			CreateCheckPoint(CHECKPOINT_END_OF_RECOVERY | CHECKPOINT_IMMEDIATE);

		/*
		 * And finally, execute the recovery_end_command, if any.
		 */
		if (recoveryEndCommand)
			ExecuteRecoveryCommand(recoveryEndCommand,
								   "recovery_end_command",
								   true);
	}

	/*
	 * Preallocate additional log files, if wanted.
	 */
	PreallocXlogFiles(EndOfLog);

	/*
	 * Reset initial contents of unlogged relations.  This has to be done
	 * AFTER recovery is complete so that any unlogged relations created
	 * during recovery also get picked up.
	 */
	if (InRecovery)
		ResetUnloggedRelations(UNLOGGED_RELATION_INIT);

	/*
	 * Okay, we're officially UP.
	 */
	InRecovery = false;

	LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
	ControlFile->state = DB_IN_PRODUCTION;
	ControlFile->time = (pg_time_t) time(NULL);
	UpdateControlFile();
	LWLockRelease(ControlFileLock);

	/* start the archive_timeout timer running */
	XLogCtl->Write.lastSegSwitchTime = (pg_time_t) time(NULL);

	/* also initialize latestCompletedXid, to nextXid - 1 */
	LWLockAcquire(ProcArrayLock, LW_EXCLUSIVE);
	ShmemVariableCache->latestCompletedXid = ShmemVariableCache->nextXid;
	TransactionIdRetreat(ShmemVariableCache->latestCompletedXid);
	LWLockRelease(ProcArrayLock);

	/*
	 * Start up the commit log and subtrans, if not already done for hot
	 * standby.
	 */
	if (standbyState == STANDBY_DISABLED)
	{
		StartupCLOG();
		StartupSUBTRANS(oldestActiveXID);
	}

	/*
	 * Perform end of recovery actions for any SLRUs that need it.
	 */
	StartupMultiXact();
	TrimCLOG();

	/* Reload shared-memory state for prepared transactions */
	RecoverPreparedTransactions();

	/*
	 * Shutdown the recovery environment. This must occur after
	 * RecoverPreparedTransactions(), see notes for lock_twophase_recover()
	 */
	if (standbyState != STANDBY_DISABLED)
		ShutdownRecoveryTransactionEnvironment();

	/* Shut down readFile facility, free space */
	if (readFile >= 0)
	{
		close(readFile);
		readFile = -1;
	}
	if (readBuf)
	{
		free(readBuf);
		readBuf = NULL;
	}
	if (readRecordBuf)
	{
		free(readRecordBuf);
		readRecordBuf = NULL;
		readRecordBufSize = 0;
	}

	/*
	 * If any of the critical GUCs have changed, log them before we allow
	 * backends to write WAL.
	 */
	LocalSetXLogInsertAllowed();
	XLogReportParameters();

	/*
	 * All done.  Allow backends to write WAL.	(Although the bool flag is
	 * probably atomic in itself, we use the info_lck here to ensure that
	 * there are no race conditions concerning visibility of other recent
	 * updates to shared memory.)
	 */
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		SpinLockAcquire(&xlogctl->info_lck);
		xlogctl->SharedRecoveryInProgress = false;
		SpinLockRelease(&xlogctl->info_lck);
	}
}

/*
 * Checks if recovery has reached a consistent state. When consistency is
 * reached and we have a valid starting standby snapshot, tell postmaster
 * that it can start accepting read-only connections.
 */
static void
CheckRecoveryConsistency(void)
{
	/*
	 * During crash recovery, we don't reach a consistent state until we've
	 * replayed all the WAL.
	 */
	if (XLogRecPtrIsInvalid(minRecoveryPoint))
		return;

	/*
	 * Have we passed our safe starting point?
	 */
	if (!reachedConsistency &&
		XLByteLE(minRecoveryPoint, EndRecPtr) &&
		XLogRecPtrIsInvalid(ControlFile->backupStartPoint))
	{
		/*
		 * Check to see if the XLOG sequence contained any unresolved
		 * references to uninitialized pages.
		 */
		XLogCheckInvalidPages();

		reachedConsistency = true;
		ereport(LOG,
				(errmsg("consistent recovery state reached at %X/%X",
						(uint32) (EndRecPtr >> 32), (uint32) EndRecPtr)));
	}

	/*
	 * Have we got a valid starting snapshot that will allow queries to be
	 * run? If so, we can tell postmaster that the database is consistent now,
	 * enabling connections.
	 */
	if (standbyState == STANDBY_SNAPSHOT_READY &&
		!LocalHotStandbyActive &&
		reachedConsistency &&
		IsUnderPostmaster)
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		SpinLockAcquire(&xlogctl->info_lck);
		xlogctl->SharedHotStandbyActive = true;
		SpinLockRelease(&xlogctl->info_lck);

		LocalHotStandbyActive = true;

		SendPostmasterSignal(PMSIGNAL_BEGIN_HOT_STANDBY);
	}
}

/*
 * Is the system still in recovery?
 *
 * Unlike testing InRecovery, this works in any process that's connected to
 * shared memory.
 *
 * As a side-effect, we initialize the local TimeLineID and RedoRecPtr
 * variables the first time we see that recovery is finished.
 */
bool
RecoveryInProgress(void)
{
	/*
	 * We check shared state each time only until we leave recovery mode. We
	 * can't re-enter recovery, so there's no need to keep checking after the
	 * shared variable has once been seen false.
	 */
	if (!LocalRecoveryInProgress)
		return false;
	else
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		/* spinlock is essential on machines with weak memory ordering! */
		SpinLockAcquire(&xlogctl->info_lck);
		LocalRecoveryInProgress = xlogctl->SharedRecoveryInProgress;
		SpinLockRelease(&xlogctl->info_lck);

		/*
		 * Initialize TimeLineID and RedoRecPtr when we discover that recovery
		 * is finished. InitPostgres() relies upon this behaviour to ensure
		 * that InitXLOGAccess() is called at backend startup.	(If you change
		 * this, see also LocalSetXLogInsertAllowed.)
		 */
		if (!LocalRecoveryInProgress)
			InitXLOGAccess();

		return LocalRecoveryInProgress;
	}
}

/*
 * Is HotStandby active yet? This is only important in special backends
 * since normal backends won't ever be able to connect until this returns
 * true. Postmaster knows this by way of signal, not via shared memory.
 *
 * Unlike testing standbyState, this works in any process that's connected to
 * shared memory.
 */
bool
HotStandbyActive(void)
{
	/*
	 * We check shared state each time only until Hot Standby is active. We
	 * can't de-activate Hot Standby, so there's no need to keep checking
	 * after the shared variable has once been seen true.
	 */
	if (LocalHotStandbyActive)
		return true;
	else
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		/* spinlock is essential on machines with weak memory ordering! */
		SpinLockAcquire(&xlogctl->info_lck);
		LocalHotStandbyActive = xlogctl->SharedHotStandbyActive;
		SpinLockRelease(&xlogctl->info_lck);

		return LocalHotStandbyActive;
	}
}

/*
 * Is this process allowed to insert new WAL records?
 *
 * Ordinarily this is essentially equivalent to !RecoveryInProgress().
 * But we also have provisions for forcing the result "true" or "false"
 * within specific processes regardless of the global state.
 */
bool
XLogInsertAllowed(void)
{
	/*
	 * If value is "unconditionally true" or "unconditionally false", just
	 * return it.  This provides the normal fast path once recovery is known
	 * done.
	 */
	if (LocalXLogInsertAllowed >= 0)
		return (bool) LocalXLogInsertAllowed;

	/*
	 * Else, must check to see if we're still in recovery.
	 */
	if (RecoveryInProgress())
		return false;

	/*
	 * On exit from recovery, reset to "unconditionally true", since there is
	 * no need to keep checking.
	 */
	LocalXLogInsertAllowed = 1;
	return true;
}

/*
 * Make XLogInsertAllowed() return true in the current process only.
 *
 * Note: it is allowed to switch LocalXLogInsertAllowed back to -1 later,
 * and even call LocalSetXLogInsertAllowed() again after that.
 */
static void
LocalSetXLogInsertAllowed(void)
{
	Assert(LocalXLogInsertAllowed == -1);
	LocalXLogInsertAllowed = 1;

	/* Initialize as RecoveryInProgress() would do when switching state */
	InitXLOGAccess();
}

/*
 * Subroutine to try to fetch and validate a prior checkpoint record.
 *
 * whichChkpt identifies the checkpoint (merely for reporting purposes).
 * 1 for "primary", 2 for "secondary", 0 for "other" (backup_label)
 */
static XLogRecord *
ReadCheckpointRecord(XLogRecPtr RecPtr, int whichChkpt)
{
	XLogRecord *record;

	if (!XRecOffIsValid(RecPtr))
	{
		switch (whichChkpt)
		{
			case 1:
				ereport(LOG,
				(errmsg("invalid primary checkpoint link in control file")));
				break;
			case 2:
				ereport(LOG,
						(errmsg("invalid secondary checkpoint link in control file")));
				break;
			default:
				ereport(LOG,
				   (errmsg("invalid checkpoint link in backup_label file")));
				break;
		}
		return NULL;
	}

	record = ReadRecord(&RecPtr, LOG, true);

	if (record == NULL)
	{
		switch (whichChkpt)
		{
			case 1:
				ereport(LOG,
						(errmsg("invalid primary checkpoint record")));
				break;
			case 2:
				ereport(LOG,
						(errmsg("invalid secondary checkpoint record")));
				break;
			default:
				ereport(LOG,
						(errmsg("invalid checkpoint record")));
				break;
		}
		return NULL;
	}
	if (record->xl_rmid != RM_XLOG_ID)
	{
		switch (whichChkpt)
		{
			case 1:
				ereport(LOG,
						(errmsg("invalid resource manager ID in primary checkpoint record")));
				break;
			case 2:
				ereport(LOG,
						(errmsg("invalid resource manager ID in secondary checkpoint record")));
				break;
			default:
				ereport(LOG,
				(errmsg("invalid resource manager ID in checkpoint record")));
				break;
		}
		return NULL;
	}
	if (record->xl_info != XLOG_CHECKPOINT_SHUTDOWN &&
		record->xl_info != XLOG_CHECKPOINT_ONLINE)
	{
		switch (whichChkpt)
		{
			case 1:
				ereport(LOG,
				   (errmsg("invalid xl_info in primary checkpoint record")));
				break;
			case 2:
				ereport(LOG,
				 (errmsg("invalid xl_info in secondary checkpoint record")));
				break;
			default:
				ereport(LOG,
						(errmsg("invalid xl_info in checkpoint record")));
				break;
		}
		return NULL;
	}
	if (record->xl_len != sizeof(CheckPoint) ||
		record->xl_tot_len != SizeOfXLogRecord + sizeof(CheckPoint))
	{
		switch (whichChkpt)
		{
			case 1:
				ereport(LOG,
					(errmsg("invalid length of primary checkpoint record")));
				break;
			case 2:
				ereport(LOG,
				  (errmsg("invalid length of secondary checkpoint record")));
				break;
			default:
				ereport(LOG,
						(errmsg("invalid length of checkpoint record")));
				break;
		}
		return NULL;
	}
	return record;
}

/*
 * This must be called during startup of a backend process, except that
 * it need not be called in a standalone backend (which does StartupXLOG
 * instead).  We need to initialize the local copies of ThisTimeLineID and
 * RedoRecPtr.
 *
 * Note: before Postgres 8.0, we went to some effort to keep the postmaster
 * process's copies of ThisTimeLineID and RedoRecPtr valid too.  This was
 * unnecessary however, since the postmaster itself never touches XLOG anyway.
 */
void
InitXLOGAccess(void)
{
	/* ThisTimeLineID doesn't change so we need no lock to copy it */
	ThisTimeLineID = XLogCtl->ThisTimeLineID;
	Assert(ThisTimeLineID != 0 || IsBootstrapProcessingMode());

	/* Use GetRedoRecPtr to copy the RedoRecPtr safely */
	(void) GetRedoRecPtr();
}

/*
 * Once spawned, a backend may update its local RedoRecPtr from
 * XLogCtl->Insert.RedoRecPtr; it must hold the insert lock or info_lck
 * to do so.  This is done in XLogInsert() or GetRedoRecPtr().
 */
XLogRecPtr
GetRedoRecPtr(void)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;

	SpinLockAcquire(&xlogctl->info_lck);
	Assert(XLByteLE(RedoRecPtr, xlogctl->Insert.RedoRecPtr));
	RedoRecPtr = xlogctl->Insert.RedoRecPtr;
	SpinLockRelease(&xlogctl->info_lck);

	return RedoRecPtr;
}

/*
 * GetInsertRecPtr -- Returns the current insert position.
 *
 * NOTE: The value *actually* returned is the position of the last full
 * xlog page. It lags behind the real insert position by at most 1 page.
 * For that, we don't need to acquire WALInsertLock which can be quite
 * heavily contended, and an approximation is enough for the current
 * usage of this function.
 */
XLogRecPtr
GetInsertRecPtr(void)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;
	XLogRecPtr	recptr;

	SpinLockAcquire(&xlogctl->info_lck);
	recptr = xlogctl->LogwrtRqst.Write;
	SpinLockRelease(&xlogctl->info_lck);

	return recptr;
}

/*
 * GetFlushRecPtr -- Returns the current flush position, ie, the last WAL
 * position known to be fsync'd to disk.
 */
XLogRecPtr
GetFlushRecPtr(void)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;
	XLogRecPtr	recptr;

	SpinLockAcquire(&xlogctl->info_lck);
	recptr = xlogctl->LogwrtResult.Flush;
	SpinLockRelease(&xlogctl->info_lck);

	return recptr;
}

/*
 * Get the time of the last xlog segment switch
 */
pg_time_t
GetLastSegSwitchTime(void)
{
	pg_time_t	result;

	/* Need WALWriteLock, but shared lock is sufficient */
	LWLockAcquire(WALWriteLock, LW_SHARED);
	result = XLogCtl->Write.lastSegSwitchTime;
	LWLockRelease(WALWriteLock);

	return result;
}

/*
 * GetNextXidAndEpoch - get the current nextXid value and associated epoch
 *
 * This is exported for use by code that would like to have 64-bit XIDs.
 * We don't really support such things, but all XIDs within the system
 * can be presumed "close to" the result, and thus the epoch associated
 * with them can be determined.
 */
void
GetNextXidAndEpoch(TransactionId *xid, uint32 *epoch)
{
	uint32		ckptXidEpoch;
	TransactionId ckptXid;
	TransactionId nextXid;

	/* Must read checkpoint info first, else have race condition */
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		SpinLockAcquire(&xlogctl->info_lck);
		ckptXidEpoch = xlogctl->ckptXidEpoch;
		ckptXid = xlogctl->ckptXid;
		SpinLockRelease(&xlogctl->info_lck);
	}

	/* Now fetch current nextXid */
	nextXid = ReadNewTransactionId();

	/*
	 * nextXid is certainly logically later than ckptXid.  So if it's
	 * numerically less, it must have wrapped into the next epoch.
	 */
	if (nextXid < ckptXid)
		ckptXidEpoch++;

	*xid = nextXid;
	*epoch = ckptXidEpoch;
}

/*
 * GetRecoveryTargetTLI - get the current recovery target timeline ID
 */
TimeLineID
GetRecoveryTargetTLI(void)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;
	TimeLineID result;

	SpinLockAcquire(&xlogctl->info_lck);
	result = xlogctl->RecoveryTargetTLI;
	SpinLockRelease(&xlogctl->info_lck);

	return result;
}

/*
 * This must be called ONCE during postmaster or standalone-backend shutdown
 */
void
ShutdownXLOG(int code, Datum arg)
{
	ereport(LOG,
			(errmsg("shutting down")));

	if (RecoveryInProgress())
		CreateRestartPoint(CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_IMMEDIATE);
	else
	{
		/*
		 * If archiving is enabled, rotate the last XLOG file so that all the
		 * remaining records are archived (postmaster wakes up the archiver
		 * process one more time at the end of shutdown). The checkpoint
		 * record will go to the next XLOG file and won't be archived (yet).
		 */
		if (XLogArchivingActive() && XLogArchiveCommandSet())
			RequestXLogSwitch();

		CreateCheckPoint(CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_IMMEDIATE);
	}
	ShutdownCLOG();
	ShutdownSUBTRANS();
	ShutdownMultiXact();

	ereport(LOG,
			(errmsg("database system is shut down")));
}

/*
 * Log start of a checkpoint.
 */
static void
LogCheckpointStart(int flags, bool restartpoint)
{
	const char *msg;

	/*
	 * XXX: This is hopelessly untranslatable. We could call gettext_noop for
	 * the main message, but what about all the flags?
	 */
	if (restartpoint)
		msg = "restartpoint starting:%s%s%s%s%s%s%s";
	else
		msg = "checkpoint starting:%s%s%s%s%s%s%s";

	elog(LOG, msg,
		 (flags & CHECKPOINT_IS_SHUTDOWN) ? " shutdown" : "",
		 (flags & CHECKPOINT_END_OF_RECOVERY) ? " end-of-recovery" : "",
		 (flags & CHECKPOINT_IMMEDIATE) ? " immediate" : "",
		 (flags & CHECKPOINT_FORCE) ? " force" : "",
		 (flags & CHECKPOINT_WAIT) ? " wait" : "",
		 (flags & CHECKPOINT_CAUSE_XLOG) ? " xlog" : "",
		 (flags & CHECKPOINT_CAUSE_TIME) ? " time" : "");
}

/*
 * Log end of a checkpoint.
 */
static void
LogCheckpointEnd(bool restartpoint)
{
	long		write_secs,
				sync_secs,
				total_secs,
				longest_secs,
				average_secs;
	int			write_usecs,
				sync_usecs,
				total_usecs,
				longest_usecs,
				average_usecs;
	uint64		average_sync_time;

	CheckpointStats.ckpt_end_t = GetCurrentTimestamp();

	TimestampDifference(CheckpointStats.ckpt_write_t,
						CheckpointStats.ckpt_sync_t,
						&write_secs, &write_usecs);

	TimestampDifference(CheckpointStats.ckpt_sync_t,
						CheckpointStats.ckpt_sync_end_t,
						&sync_secs, &sync_usecs);

	/* Accumulate checkpoint timing summary data, in milliseconds. */
	BgWriterStats.m_checkpoint_write_time +=
		write_secs * 1000 + write_usecs / 1000;
	BgWriterStats.m_checkpoint_sync_time +=
		sync_secs * 1000 + sync_usecs / 1000;

	/*
	 * All of the published timing statistics are accounted for.  Only
	 * continue if a log message is to be written.
	 */
	if (!log_checkpoints)
		return;

	TimestampDifference(CheckpointStats.ckpt_start_t,
						CheckpointStats.ckpt_end_t,
						&total_secs, &total_usecs);

	/*
	 * Timing values returned from CheckpointStats are in microseconds.
	 * Convert to the second plus microsecond form that TimestampDifference
	 * returns for homogeneous printing.
	 */
	longest_secs = (long) (CheckpointStats.ckpt_longest_sync / 1000000);
	longest_usecs = CheckpointStats.ckpt_longest_sync -
		(uint64) longest_secs *1000000;

	average_sync_time = 0;
	if (CheckpointStats.ckpt_sync_rels > 0)
		average_sync_time = CheckpointStats.ckpt_agg_sync_time /
			CheckpointStats.ckpt_sync_rels;
	average_secs = (long) (average_sync_time / 1000000);
	average_usecs = average_sync_time - (uint64) average_secs *1000000;

	if (restartpoint)
		elog(LOG, "restartpoint complete: wrote %d buffers (%.1f%%); "
			 "%d transaction log file(s) added, %d removed, %d recycled; "
			 "write=%ld.%03d s, sync=%ld.%03d s, total=%ld.%03d s; "
			 "sync files=%d, longest=%ld.%03d s, average=%ld.%03d s",
			 CheckpointStats.ckpt_bufs_written,
			 (double) CheckpointStats.ckpt_bufs_written * 100 / NBuffers,
			 CheckpointStats.ckpt_segs_added,
			 CheckpointStats.ckpt_segs_removed,
			 CheckpointStats.ckpt_segs_recycled,
			 write_secs, write_usecs / 1000,
			 sync_secs, sync_usecs / 1000,
			 total_secs, total_usecs / 1000,
			 CheckpointStats.ckpt_sync_rels,
			 longest_secs, longest_usecs / 1000,
			 average_secs, average_usecs / 1000);
	else
		elog(LOG, "checkpoint complete: wrote %d buffers (%.1f%%); "
			 "%d transaction log file(s) added, %d removed, %d recycled; "
			 "write=%ld.%03d s, sync=%ld.%03d s, total=%ld.%03d s; "
			 "sync files=%d, longest=%ld.%03d s, average=%ld.%03d s",
			 CheckpointStats.ckpt_bufs_written,
			 (double) CheckpointStats.ckpt_bufs_written * 100 / NBuffers,
			 CheckpointStats.ckpt_segs_added,
			 CheckpointStats.ckpt_segs_removed,
			 CheckpointStats.ckpt_segs_recycled,
			 write_secs, write_usecs / 1000,
			 sync_secs, sync_usecs / 1000,
			 total_secs, total_usecs / 1000,
			 CheckpointStats.ckpt_sync_rels,
			 longest_secs, longest_usecs / 1000,
			 average_secs, average_usecs / 1000);
}

/*
 * Perform a checkpoint --- either during shutdown, or on-the-fly
 *
 * flags is a bitwise OR of the following:
 *	CHECKPOINT_IS_SHUTDOWN: checkpoint is for database shutdown.
 *	CHECKPOINT_END_OF_RECOVERY: checkpoint is for end of WAL recovery.
 *	CHECKPOINT_IMMEDIATE: finish the checkpoint ASAP,
 *		ignoring checkpoint_completion_target parameter.
 *	CHECKPOINT_FORCE: force a checkpoint even if no XLOG activity has occurred
 *		since the last one (implied by CHECKPOINT_IS_SHUTDOWN or
 *		CHECKPOINT_END_OF_RECOVERY).
 *
 * Note: flags contains other bits, of interest here only for logging purposes.
 * In particular note that this routine is synchronous and does not pay
 * attention to CHECKPOINT_WAIT.
 *
 * If !shutdown then we are writing an online checkpoint. This is a very special
 * kind of operation and WAL record because the checkpoint action occurs over
 * a period of time yet logically occurs at just a single LSN. The logical
 * position of the WAL record (redo ptr) is the same or earlier than the
 * physical position. When we replay WAL we locate the checkpoint via its
 * physical position then read the redo ptr and actually start replay at the
 * earlier logical position. Note that we don't write *anything* to WAL at
 * the logical position, so that location could be any other kind of WAL record.
 * All of this mechanism allows us to continue working while we checkpoint.
 * As a result, timing of actions is critical here and be careful to note that
 * this function will likely take minutes to execute on a busy system.
 */
void
CreateCheckPoint(int flags)
{
	bool		shutdown;
	CheckPoint	checkPoint;
	XLogRecPtr	recptr;
	XLogCtlInsert *Insert = &XLogCtl->Insert;
	XLogRecData rdata;
	uint32		freespace;
	XLogSegNo	_logSegNo;
	TransactionId *inCommitXids;
	int			nInCommit;

	/*
	 * An end-of-recovery checkpoint is really a shutdown checkpoint, just
	 * issued at a different time.
	 */
	if (flags & (CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_END_OF_RECOVERY))
		shutdown = true;
	else
		shutdown = false;

	/* sanity check */
	if (RecoveryInProgress() && (flags & CHECKPOINT_END_OF_RECOVERY) == 0)
		elog(ERROR, "can't create a checkpoint during recovery");

	/*
	 * Acquire CheckpointLock to ensure only one checkpoint happens at a time.
	 * (This is just pro forma, since in the present system structure there is
	 * only one process that is allowed to issue checkpoints at any given
	 * time.)
	 */
	LWLockAcquire(CheckpointLock, LW_EXCLUSIVE);

	/*
	 * Prepare to accumulate statistics.
	 *
	 * Note: because it is possible for log_checkpoints to change while a
	 * checkpoint proceeds, we always accumulate stats, even if
	 * log_checkpoints is currently off.
	 */
	MemSet(&CheckpointStats, 0, sizeof(CheckpointStats));
	CheckpointStats.ckpt_start_t = GetCurrentTimestamp();

	/*
	 * Use a critical section to force system panic if we have trouble.
	 */
	START_CRIT_SECTION();

	if (shutdown)
	{
		LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
		ControlFile->state = DB_SHUTDOWNING;
		ControlFile->time = (pg_time_t) time(NULL);
		UpdateControlFile();
		LWLockRelease(ControlFileLock);
	}

	/*
	 * Let smgr prepare for checkpoint; this has to happen before we determine
	 * the REDO pointer.  Note that smgr must not do anything that'd have to
	 * be undone if we decide no checkpoint is needed.
	 */
	smgrpreckpt();

	/* Begin filling in the checkpoint WAL record */
	MemSet(&checkPoint, 0, sizeof(checkPoint));
	checkPoint.time = (pg_time_t) time(NULL);

	/*
	 * For Hot Standby, derive the oldestActiveXid before we fix the redo
	 * pointer. This allows us to begin accumulating changes to assemble our
	 * starting snapshot of locks and transactions.
	 */
	if (!shutdown && XLogStandbyInfoActive())
		checkPoint.oldestActiveXid = GetOldestActiveTransactionId();
	else
		checkPoint.oldestActiveXid = InvalidTransactionId;

	/*
	 * We must hold WALInsertLock while examining insert state to determine
	 * the checkpoint REDO pointer.
	 */
	LWLockAcquire(WALInsertLock, LW_EXCLUSIVE);

	/*
	 * If this isn't a shutdown or forced checkpoint, and we have not inserted
	 * any XLOG records since the start of the last checkpoint, skip the
	 * checkpoint.	The idea here is to avoid inserting duplicate checkpoints
	 * when the system is idle. That wastes log space, and more importantly it
	 * exposes us to possible loss of both current and previous checkpoint
	 * records if the machine crashes just as we're writing the update.
	 * (Perhaps it'd make even more sense to checkpoint only when the previous
	 * checkpoint record is in a different xlog page?)
	 *
	 * We have to make two tests to determine that nothing has happened since
	 * the start of the last checkpoint: current insertion point must match
	 * the end of the last checkpoint record, and its redo pointer must point
	 * to itself.
	 */
	if ((flags & (CHECKPOINT_IS_SHUTDOWN | CHECKPOINT_END_OF_RECOVERY |
				  CHECKPOINT_FORCE)) == 0)
	{
		XLogRecPtr	curInsert;

		INSERT_RECPTR(curInsert, Insert, Insert->curridx);
		if (curInsert == ControlFile->checkPoint + 
			MAXALIGN(SizeOfXLogRecord + sizeof(CheckPoint)) &&
			ControlFile->checkPoint == ControlFile->checkPointCopy.redo)
		{
			LWLockRelease(WALInsertLock);
			LWLockRelease(CheckpointLock);
			END_CRIT_SECTION();
			return;
		}
	}

	/*
	 * An end-of-recovery checkpoint is created before anyone is allowed to
	 * write WAL. To allow us to write the checkpoint record, temporarily
	 * enable XLogInsertAllowed.  (This also ensures ThisTimeLineID is
	 * initialized, which we need here and in AdvanceXLInsertBuffer.)
	 */
	if (flags & CHECKPOINT_END_OF_RECOVERY)
		LocalSetXLogInsertAllowed();

	checkPoint.ThisTimeLineID = ThisTimeLineID;
	checkPoint.fullPageWrites = Insert->fullPageWrites;

	/*
	 * Compute new REDO record ptr = location of next XLOG record.
	 *
	 * NB: this is NOT necessarily where the checkpoint record itself will be,
	 * since other backends may insert more XLOG records while we're off doing
	 * the buffer flush work.  Those XLOG records are logically after the
	 * checkpoint, even though physically before it.  Got that?
	 */
	freespace = INSERT_FREESPACE(Insert);
	if (freespace == 0)
	{
		(void) AdvanceXLInsertBuffer(false);
		/* OK to ignore update return flag, since we will do flush anyway */
		freespace = INSERT_FREESPACE(Insert);
	}
	INSERT_RECPTR(checkPoint.redo, Insert, Insert->curridx);

	/*
	 * Here we update the shared RedoRecPtr for future XLogInsert calls; this
	 * must be done while holding the insert lock AND the info_lck.
	 *
	 * Note: if we fail to complete the checkpoint, RedoRecPtr will be left
	 * pointing past where it really needs to point.  This is okay; the only
	 * consequence is that XLogInsert might back up whole buffers that it
	 * didn't really need to.  We can't postpone advancing RedoRecPtr because
	 * XLogInserts that happen while we are dumping buffers must assume that
	 * their buffer changes are not included in the checkpoint.
	 */
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		SpinLockAcquire(&xlogctl->info_lck);
		RedoRecPtr = xlogctl->Insert.RedoRecPtr = checkPoint.redo;
		SpinLockRelease(&xlogctl->info_lck);
	}

	/*
	 * Now we can release WAL insert lock, allowing other xacts to proceed
	 * while we are flushing disk buffers.
	 */
	LWLockRelease(WALInsertLock);

	/*
	 * If enabled, log checkpoint start.  We postpone this until now so as not
	 * to log anything if we decided to skip the checkpoint.
	 */
	if (log_checkpoints)
		LogCheckpointStart(flags, false);

	TRACE_POSTGRESQL_CHECKPOINT_START(flags);

	/*
	 * Before flushing data, we must wait for any transactions that are
	 * currently in their commit critical sections.  If an xact inserted its
	 * commit record into XLOG just before the REDO point, then a crash
	 * restart from the REDO point would not replay that record, which means
	 * that our flushing had better include the xact's update of pg_clog.  So
	 * we wait till he's out of his commit critical section before proceeding.
	 * See notes in RecordTransactionCommit().
	 *
	 * Because we've already released WALInsertLock, this test is a bit fuzzy:
	 * it is possible that we will wait for xacts we didn't really need to
	 * wait for.  But the delay should be short and it seems better to make
	 * checkpoint take a bit longer than to hold locks longer than necessary.
	 * (In fact, the whole reason we have this issue is that xact.c does
	 * commit record XLOG insertion and clog update as two separate steps
	 * protected by different locks, but again that seems best on grounds of
	 * minimizing lock contention.)
	 *
	 * A transaction that has not yet set inCommit when we look cannot be at
	 * risk, since he's not inserted his commit record yet; and one that's
	 * already cleared it is not at risk either, since he's done fixing clog
	 * and we will correctly flush the update below.  So we cannot miss any
	 * xacts we need to wait for.
	 */
	nInCommit = GetTransactionsInCommit(&inCommitXids);
	if (nInCommit > 0)
	{
		do
		{
			pg_usleep(10000L);	/* wait for 10 msec */
		} while (HaveTransactionsInCommit(inCommitXids, nInCommit));
	}
	pfree(inCommitXids);

	/*
	 * Get the other info we need for the checkpoint record.
	 */
	LWLockAcquire(XidGenLock, LW_SHARED);
	checkPoint.nextXid = ShmemVariableCache->nextXid;
	checkPoint.oldestXid = ShmemVariableCache->oldestXid;
	checkPoint.oldestXidDB = ShmemVariableCache->oldestXidDB;
	LWLockRelease(XidGenLock);

	/* Increase XID epoch if we've wrapped around since last checkpoint */
	checkPoint.nextXidEpoch = ControlFile->checkPointCopy.nextXidEpoch;
	if (checkPoint.nextXid < ControlFile->checkPointCopy.nextXid)
		checkPoint.nextXidEpoch++;

	LWLockAcquire(OidGenLock, LW_SHARED);
	checkPoint.nextOid = ShmemVariableCache->nextOid;
	if (!shutdown)
		checkPoint.nextOid += ShmemVariableCache->oidCount;
	LWLockRelease(OidGenLock);

	MultiXactGetCheckptMulti(shutdown,
							 &checkPoint.nextMulti,
							 &checkPoint.nextMultiOffset);

	/*
	 * Having constructed the checkpoint record, ensure all shmem disk buffers
	 * and commit-log buffers are flushed to disk.
	 *
	 * This I/O could fail for various reasons.  If so, we will fail to
	 * complete the checkpoint, but there is no reason to force a system
	 * panic. Accordingly, exit critical section while doing it.
	 */
	END_CRIT_SECTION();

	CheckPointGuts(checkPoint.redo, flags);

	/*
	 * Take a snapshot of running transactions and write this to WAL. This
	 * allows us to reconstruct the state of running transactions during
	 * archive recovery, if required. Skip, if this info disabled.
	 *
	 * If we are shutting down, or Startup process is completing crash
	 * recovery we don't need to write running xact data.
	 *
	 * Update checkPoint.nextXid since we may have a later value. If we
	 * do update the value, and we have wrapped, increment epoch also.
	 */
	if (!shutdown && XLogStandbyInfoActive())
	{
		TransactionId prevXid = checkPoint.nextXid;

		LogStandbySnapshot(&checkPoint.nextXid);
		if (checkPoint.nextXid < prevXid)
			checkPoint.nextXidEpoch++;
	}

	START_CRIT_SECTION();

	/*
	 * Now insert the checkpoint record into XLOG.
	 */
	rdata.data = (char *) (&checkPoint);
	rdata.len = sizeof(checkPoint);
	rdata.buffer = InvalidBuffer;
	rdata.next = NULL;

	recptr = XLogInsert(RM_XLOG_ID,
						shutdown ? XLOG_CHECKPOINT_SHUTDOWN :
						XLOG_CHECKPOINT_ONLINE,
						&rdata);

	XLogFlush(recptr);

	/*
	 * We mustn't write any new WAL after a shutdown checkpoint, or it will be
	 * overwritten at next startup.  No-one should even try, this just allows
	 * sanity-checking.  In the case of an end-of-recovery checkpoint, we want
	 * to just temporarily disable writing until the system has exited
	 * recovery.
	 */
	if (shutdown)
	{
		if (flags & CHECKPOINT_END_OF_RECOVERY)
			LocalXLogInsertAllowed = -1;		/* return to "check" state */
		else
			LocalXLogInsertAllowed = 0; /* never again write WAL */
	}

	/*
	 * We now have ProcLastRecPtr = start of actual checkpoint record, recptr
	 * = end of actual checkpoint record.
	 */
	if (shutdown && !XLByteEQ(checkPoint.redo, ProcLastRecPtr))
		ereport(PANIC,
				(errmsg("concurrent transaction log activity while database system is shutting down")));

	/*
	 * Select point at which we can truncate the log, which we base on the
	 * prior checkpoint's earliest info.
	 */
	XLByteToSeg(ControlFile->checkPointCopy.redo, _logSegNo);

	/*
	 * Update the control file.
	 */
	LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
	if (shutdown)
		ControlFile->state = DB_SHUTDOWNED;
	ControlFile->prevCheckPoint = ControlFile->checkPoint;
	ControlFile->checkPoint = ProcLastRecPtr;
	ControlFile->checkPointCopy = checkPoint;
	ControlFile->time = (pg_time_t) time(NULL);
	/* crash recovery should always recover to the end of WAL */
	MemSet(&ControlFile->minRecoveryPoint, 0, sizeof(XLogRecPtr));
	UpdateControlFile();
	LWLockRelease(ControlFileLock);

	/* Update shared-memory copy of checkpoint XID/epoch */
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		SpinLockAcquire(&xlogctl->info_lck);
		xlogctl->ckptXidEpoch = checkPoint.nextXidEpoch;
		xlogctl->ckptXid = checkPoint.nextXid;
		SpinLockRelease(&xlogctl->info_lck);
	}

	/*
	 * We are now done with critical updates; no need for system panic if we
	 * have trouble while fooling with old log segments.
	 */
	END_CRIT_SECTION();

	/*
	 * Let smgr do post-checkpoint cleanup (eg, deleting old files).
	 */
	smgrpostckpt();

	/*
	 * Delete old log files (those no longer needed even for previous
	 * checkpoint or the standbys in XLOG streaming).
	 */
	if (_logSegNo)
	{
		KeepLogSeg(recptr, &_logSegNo);
		_logSegNo--;
		RemoveOldXlogFiles(_logSegNo, recptr);
	}

	/*
	 * Make more log segments if needed.  (Do this after recycling old log
	 * segments, since that may supply some of the needed files.)
	 */
	if (!shutdown)
		PreallocXlogFiles(recptr);

	/*
	 * Truncate pg_subtrans if possible.  We can throw away all data before
	 * the oldest XMIN of any running transaction.	No future transaction will
	 * attempt to reference any pg_subtrans entry older than that (see Asserts
	 * in subtrans.c).	During recovery, though, we mustn't do this because
	 * StartupSUBTRANS hasn't been called yet.
	 */
	if (!RecoveryInProgress())
		TruncateSUBTRANS(GetOldestXmin(true, false));

	/* Real work is done, but log and update stats before releasing lock. */
	LogCheckpointEnd(false);

	TRACE_POSTGRESQL_CHECKPOINT_DONE(CheckpointStats.ckpt_bufs_written,
									 NBuffers,
									 CheckpointStats.ckpt_segs_added,
									 CheckpointStats.ckpt_segs_removed,
									 CheckpointStats.ckpt_segs_recycled);

	LWLockRelease(CheckpointLock);
}

/*
 * Flush all data in shared memory to disk, and fsync
 *
 * This is the common code shared between regular checkpoints and
 * recovery restartpoints.
 */
static void
CheckPointGuts(XLogRecPtr checkPointRedo, int flags)
{
	CheckPointCLOG();
	CheckPointSUBTRANS();
	CheckPointMultiXact();
	CheckPointPredicate();
	CheckPointRelationMap();
	CheckPointBuffers(flags);	/* performs all required fsyncs */
	/* We deliberately delay 2PC checkpointing as long as possible */
	CheckPointTwoPhase(checkPointRedo);
}

/*
 * Save a checkpoint for recovery restart if appropriate
 *
 * This function is called each time a checkpoint record is read from XLOG.
 * It must determine whether the checkpoint represents a safe restartpoint or
 * not.  If so, the checkpoint record is stashed in shared memory so that
 * CreateRestartPoint can consult it.  (Note that the latter function is
 * executed by the checkpointer, while this one will be executed by the
 * startup process.)
 */
static void
RecoveryRestartPoint(const CheckPoint *checkPoint)
{
	int			rmid;

	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;

	/*
	 * Is it safe to restartpoint?	We must ask each of the resource managers
	 * whether they have any partial state information that might prevent a
	 * correct restart from this point.  If so, we skip this opportunity, but
	 * return at the next checkpoint record for another try.
	 */
	for (rmid = 0; rmid <= RM_MAX_ID; rmid++)
	{
		if (RmgrTable[rmid].rm_safe_restartpoint != NULL)
			if (!(RmgrTable[rmid].rm_safe_restartpoint()))
			{
				elog(trace_recovery(DEBUG2),
					 "RM %d not safe to record restart point at %X/%X",
					 rmid,
					 (uint32) (checkPoint->redo >> 32),
					 (uint32) checkPoint->redo);
				return;
			}
	}

	/*
	 * Also refrain from creating a restartpoint if we have seen any
	 * references to non-existent pages. Restarting recovery from the
	 * restartpoint would not see the references, so we would lose the
	 * cross-check that the pages belonged to a relation that was dropped
	 * later.
	 */
	if (XLogHaveInvalidPages())
	{
		elog(trace_recovery(DEBUG2),
			 "could not record restart point at %X/%X because there "
			 "are unresolved references to invalid pages",
			 (uint32) (checkPoint->redo >> 32),
			 (uint32) checkPoint->redo);
		return;
	}

	/*
	 * Copy the checkpoint record to shared memory, so that checkpointer can
	 * work out the next time it wants to perform a restartpoint.
	 */
	SpinLockAcquire(&xlogctl->info_lck);
	xlogctl->lastCheckPointRecPtr = ReadRecPtr;
	xlogctl->lastCheckPoint = *checkPoint;
	SpinLockRelease(&xlogctl->info_lck);
}

/*
 * Establish a restartpoint if possible.
 *
 * This is similar to CreateCheckPoint, but is used during WAL recovery
 * to establish a point from which recovery can roll forward without
 * replaying the entire recovery log.
 *
 * Returns true if a new restartpoint was established. We can only establish
 * a restartpoint if we have replayed a safe checkpoint record since last
 * restartpoint.
 */
bool
CreateRestartPoint(int flags)
{
	XLogRecPtr	lastCheckPointRecPtr;
	CheckPoint	lastCheckPoint;
	XLogSegNo	_logSegNo;
	TimestampTz xtime;

	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;

	/*
	 * Acquire CheckpointLock to ensure only one restartpoint or checkpoint
	 * happens at a time.
	 */
	LWLockAcquire(CheckpointLock, LW_EXCLUSIVE);

	/* Get a local copy of the last safe checkpoint record. */
	SpinLockAcquire(&xlogctl->info_lck);
	lastCheckPointRecPtr = xlogctl->lastCheckPointRecPtr;
	lastCheckPoint = xlogctl->lastCheckPoint;
	SpinLockRelease(&xlogctl->info_lck);

	/*
	 * Check that we're still in recovery mode. It's ok if we exit recovery
	 * mode after this check, the restart point is valid anyway.
	 */
	if (!RecoveryInProgress())
	{
		ereport(DEBUG2,
			  (errmsg("skipping restartpoint, recovery has already ended")));
		LWLockRelease(CheckpointLock);
		return false;
	}

	/*
	 * If the last checkpoint record we've replayed is already our last
	 * restartpoint, we can't perform a new restart point. We still update
	 * minRecoveryPoint in that case, so that if this is a shutdown restart
	 * point, we won't start up earlier than before. That's not strictly
	 * necessary, but when hot standby is enabled, it would be rather weird if
	 * the database opened up for read-only connections at a point-in-time
	 * before the last shutdown. Such time travel is still possible in case of
	 * immediate shutdown, though.
	 *
	 * We don't explicitly advance minRecoveryPoint when we do create a
	 * restartpoint. It's assumed that flushing the buffers will do that as a
	 * side-effect.
	 */
	if (XLogRecPtrIsInvalid(lastCheckPointRecPtr) ||
		XLByteLE(lastCheckPoint.redo, ControlFile->checkPointCopy.redo))
	{
		ereport(DEBUG2,
				(errmsg("skipping restartpoint, already performed at %X/%X",
						(uint32) (lastCheckPoint.redo >> 32), (uint32) lastCheckPoint.redo)));

		UpdateMinRecoveryPoint(InvalidXLogRecPtr, true);
		if (flags & CHECKPOINT_IS_SHUTDOWN)
		{
			LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
			ControlFile->state = DB_SHUTDOWNED_IN_RECOVERY;
			ControlFile->time = (pg_time_t) time(NULL);
			UpdateControlFile();
			LWLockRelease(ControlFileLock);
		}
		LWLockRelease(CheckpointLock);
		return false;
	}

	/*
	 * Update the shared RedoRecPtr so that the startup process can calculate
	 * the number of segments replayed since last restartpoint, and request a
	 * restartpoint if it exceeds checkpoint_segments.
	 *
	 * You need to hold WALInsertLock and info_lck to update it, although
	 * during recovery acquiring WALInsertLock is just pro forma, because
	 * there is no other processes updating Insert.RedoRecPtr.
	 */
	LWLockAcquire(WALInsertLock, LW_EXCLUSIVE);
	SpinLockAcquire(&xlogctl->info_lck);
	xlogctl->Insert.RedoRecPtr = lastCheckPoint.redo;
	SpinLockRelease(&xlogctl->info_lck);
	LWLockRelease(WALInsertLock);

	/*
	 * Prepare to accumulate statistics.
	 *
	 * Note: because it is possible for log_checkpoints to change while a
	 * checkpoint proceeds, we always accumulate stats, even if
	 * log_checkpoints is currently off.
	 */
	MemSet(&CheckpointStats, 0, sizeof(CheckpointStats));
	CheckpointStats.ckpt_start_t = GetCurrentTimestamp();

	if (log_checkpoints)
		LogCheckpointStart(flags, true);

	CheckPointGuts(lastCheckPoint.redo, flags);

	/*
	 * Select point at which we can truncate the xlog, which we base on the
	 * prior checkpoint's earliest info.
	 */
	XLByteToSeg(ControlFile->checkPointCopy.redo, _logSegNo);

	/*
	 * Update pg_control, using current time.  Check that it still shows
	 * IN_ARCHIVE_RECOVERY state and an older checkpoint, else do nothing;
	 * this is a quick hack to make sure nothing really bad happens if somehow
	 * we get here after the end-of-recovery checkpoint.
	 */
	LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
	if (ControlFile->state == DB_IN_ARCHIVE_RECOVERY &&
		XLByteLT(ControlFile->checkPointCopy.redo, lastCheckPoint.redo))
	{
		ControlFile->prevCheckPoint = ControlFile->checkPoint;
		ControlFile->checkPoint = lastCheckPointRecPtr;
		ControlFile->checkPointCopy = lastCheckPoint;
		ControlFile->time = (pg_time_t) time(NULL);
		if (flags & CHECKPOINT_IS_SHUTDOWN)
			ControlFile->state = DB_SHUTDOWNED_IN_RECOVERY;
		UpdateControlFile();
	}
	LWLockRelease(ControlFileLock);

	/*
	 * Delete old log files (those no longer needed even for previous
	 * checkpoint/restartpoint) to prevent the disk holding the xlog from
	 * growing full.
	 */
	if (_logSegNo)
	{
		XLogRecPtr	endptr;

		/* Get the current (or recent) end of xlog */
		endptr = GetStandbyFlushRecPtr(NULL);

		KeepLogSeg(endptr, &_logSegNo);
		_logSegNo--;
		RemoveOldXlogFiles(_logSegNo, endptr);

		/*
		 * Make more log segments if needed.  (Do this after recycling old log
		 * segments, since that may supply some of the needed files.)
		 */
		PreallocXlogFiles(endptr);
	}

	/*
	 * Truncate pg_subtrans if possible.  We can throw away all data before
	 * the oldest XMIN of any running transaction.	No future transaction will
	 * attempt to reference any pg_subtrans entry older than that (see Asserts
	 * in subtrans.c).	When hot standby is disabled, though, we mustn't do
	 * this because StartupSUBTRANS hasn't been called yet.
	 */
	if (EnableHotStandby)
		TruncateSUBTRANS(GetOldestXmin(true, false));

	/* Real work is done, but log and update before releasing lock. */
	LogCheckpointEnd(true);

	xtime = GetLatestXTime();
	ereport((log_checkpoints ? LOG : DEBUG2),
			(errmsg("recovery restart point at %X/%X",
					(uint32) (lastCheckPoint.redo >> 32), (uint32) lastCheckPoint.redo),
		   xtime ? errdetail("last completed transaction was at log time %s",
							 timestamptz_to_str(xtime)) : 0));

	LWLockRelease(CheckpointLock);

	/*
	 * Finally, execute archive_cleanup_command, if any.
	 */
	if (XLogCtl->archiveCleanupCommand[0])
		ExecuteRecoveryCommand(XLogCtl->archiveCleanupCommand,
							   "archive_cleanup_command",
							   false);

	return true;
}

/*
 * Calculate the last segment that we need to retain because of
 * wal_keep_segments, by subtracting wal_keep_segments from
 * the given xlog location, recptr.
 */
static void
KeepLogSeg(XLogRecPtr recptr, XLogSegNo *logSegNo)
{
	XLogSegNo	segno;

	if (wal_keep_segments == 0)
		return;

	XLByteToSeg(recptr, segno);

	/* avoid underflow, don't go below 1 */
	if (segno <= wal_keep_segments)
		segno = 1;
	else
		segno = *logSegNo - wal_keep_segments;

	/* don't delete WAL segments newer than the calculated segment */
	if (segno < *logSegNo)
		*logSegNo = segno;
}

/*
 * Write a NEXTOID log record
 */
void
XLogPutNextOid(Oid nextOid)
{
	XLogRecData rdata;

	rdata.data = (char *) (&nextOid);
	rdata.len = sizeof(Oid);
	rdata.buffer = InvalidBuffer;
	rdata.next = NULL;
	(void) XLogInsert(RM_XLOG_ID, XLOG_NEXTOID, &rdata);

	/*
	 * We need not flush the NEXTOID record immediately, because any of the
	 * just-allocated OIDs could only reach disk as part of a tuple insert or
	 * update that would have its own XLOG record that must follow the NEXTOID
	 * record.	Therefore, the standard buffer LSN interlock applied to those
	 * records will ensure no such OID reaches disk before the NEXTOID record
	 * does.
	 *
	 * Note, however, that the above statement only covers state "within" the
	 * database.  When we use a generated OID as a file or directory name, we
	 * are in a sense violating the basic WAL rule, because that filesystem
	 * change may reach disk before the NEXTOID WAL record does.  The impact
	 * of this is that if a database crash occurs immediately afterward, we
	 * might after restart re-generate the same OID and find that it conflicts
	 * with the leftover file or directory.  But since for safety's sake we
	 * always loop until finding a nonconflicting filename, this poses no real
	 * problem in practice. See pgsql-hackers discussion 27-Sep-2006.
	 */
}

/*
 * Write an XLOG SWITCH record.
 *
 * Here we just blindly issue an XLogInsert request for the record.
 * All the magic happens inside XLogInsert.
 *
 * The return value is either the end+1 address of the switch record,
 * or the end+1 address of the prior segment if we did not need to
 * write a switch record because we are already at segment start.
 */
XLogRecPtr
RequestXLogSwitch(void)
{
	XLogRecPtr	RecPtr;
	XLogRecData rdata;

	/* XLOG SWITCH, alone among xlog record types, has no data */
	rdata.buffer = InvalidBuffer;
	rdata.data = NULL;
	rdata.len = 0;
	rdata.next = NULL;

	RecPtr = XLogInsert(RM_XLOG_ID, XLOG_SWITCH, &rdata);

	return RecPtr;
}

/*
 * Write a RESTORE POINT record
 */
XLogRecPtr
XLogRestorePoint(const char *rpName)
{
	XLogRecPtr	RecPtr;
	XLogRecData rdata;
	xl_restore_point xlrec;

	xlrec.rp_time = GetCurrentTimestamp();
	strncpy(xlrec.rp_name, rpName, MAXFNAMELEN);

	rdata.buffer = InvalidBuffer;
	rdata.data = (char *) &xlrec;
	rdata.len = sizeof(xl_restore_point);
	rdata.next = NULL;

	RecPtr = XLogInsert(RM_XLOG_ID, XLOG_RESTORE_POINT, &rdata);

	ereport(LOG,
			(errmsg("restore point \"%s\" created at %X/%X",
					rpName, (uint32) (RecPtr >> 32), (uint32) RecPtr)));

	return RecPtr;
}

/*
 * Check if any of the GUC parameters that are critical for hot standby
 * have changed, and update the value in pg_control file if necessary.
 */
static void
XLogReportParameters(void)
{
	if (wal_level != ControlFile->wal_level ||
		MaxConnections != ControlFile->MaxConnections ||
		max_prepared_xacts != ControlFile->max_prepared_xacts ||
		max_locks_per_xact != ControlFile->max_locks_per_xact)
	{
		/*
		 * The change in number of backend slots doesn't need to be WAL-logged
		 * if archiving is not enabled, as you can't start archive recovery
		 * with wal_level=minimal anyway. We don't really care about the
		 * values in pg_control either if wal_level=minimal, but seems better
		 * to keep them up-to-date to avoid confusion.
		 */
		if (wal_level != ControlFile->wal_level || XLogIsNeeded())
		{
			XLogRecData rdata;
			xl_parameter_change xlrec;

			xlrec.MaxConnections = MaxConnections;
			xlrec.max_prepared_xacts = max_prepared_xacts;
			xlrec.max_locks_per_xact = max_locks_per_xact;
			xlrec.wal_level = wal_level;

			rdata.buffer = InvalidBuffer;
			rdata.data = (char *) &xlrec;
			rdata.len = sizeof(xlrec);
			rdata.next = NULL;

			XLogInsert(RM_XLOG_ID, XLOG_PARAMETER_CHANGE, &rdata);
		}

		ControlFile->MaxConnections = MaxConnections;
		ControlFile->max_prepared_xacts = max_prepared_xacts;
		ControlFile->max_locks_per_xact = max_locks_per_xact;
		ControlFile->wal_level = wal_level;
		UpdateControlFile();
	}
}

/*
 * Update full_page_writes in shared memory, and write an
 * XLOG_FPW_CHANGE record if necessary.
 *
 * Note: this function assumes there is no other process running
 * concurrently that could update it.
 */
void
UpdateFullPageWrites(void)
{
	XLogCtlInsert *Insert = &XLogCtl->Insert;

	/*
	 * Do nothing if full_page_writes has not been changed.
	 *
	 * It's safe to check the shared full_page_writes without the lock,
	 * because we assume that there is no concurrently running process which
	 * can update it.
	 */
	if (fullPageWrites == Insert->fullPageWrites)
		return;

	START_CRIT_SECTION();

	/*
	 * It's always safe to take full page images, even when not strictly
	 * required, but not the other round. So if we're setting full_page_writes
	 * to true, first set it true and then write the WAL record. If we're
	 * setting it to false, first write the WAL record and then set the global
	 * flag.
	 */
	if (fullPageWrites)
	{
		LWLockAcquire(WALInsertLock, LW_EXCLUSIVE);
		Insert->fullPageWrites = true;
		LWLockRelease(WALInsertLock);
	}

	/*
	 * Write an XLOG_FPW_CHANGE record. This allows us to keep track of
	 * full_page_writes during archive recovery, if required.
	 */
	if (XLogStandbyInfoActive() && !RecoveryInProgress())
	{
		XLogRecData rdata;

		rdata.data = (char *) (&fullPageWrites);
		rdata.len = sizeof(bool);
		rdata.buffer = InvalidBuffer;
		rdata.next = NULL;

		XLogInsert(RM_XLOG_ID, XLOG_FPW_CHANGE, &rdata);
	}

	if (!fullPageWrites)
	{
		LWLockAcquire(WALInsertLock, LW_EXCLUSIVE);
		Insert->fullPageWrites = false;
		LWLockRelease(WALInsertLock);
	}
	END_CRIT_SECTION();
}

/*
 * XLOG resource manager's routines
 *
 * Definitions of info values are in include/catalog/pg_control.h, though
 * not all record types are related to control file updates.
 */
void
xlog_redo(XLogRecPtr lsn, XLogRecord *record)
{
	uint8		info = record->xl_info & ~XLR_INFO_MASK;

	/* Backup blocks are not used in xlog records */
	Assert(!(record->xl_info & XLR_BKP_BLOCK_MASK));

	if (info == XLOG_NEXTOID)
	{
		Oid			nextOid;

		/*
		 * We used to try to take the maximum of ShmemVariableCache->nextOid
		 * and the recorded nextOid, but that fails if the OID counter wraps
		 * around.	Since no OID allocation should be happening during replay
		 * anyway, better to just believe the record exactly.  We still take
		 * OidGenLock while setting the variable, just in case.
		 */
		memcpy(&nextOid, XLogRecGetData(record), sizeof(Oid));
		LWLockAcquire(OidGenLock, LW_EXCLUSIVE);
		ShmemVariableCache->nextOid = nextOid;
		ShmemVariableCache->oidCount = 0;
		LWLockRelease(OidGenLock);
	}
	else if (info == XLOG_CHECKPOINT_SHUTDOWN)
	{
		CheckPoint	checkPoint;

		memcpy(&checkPoint, XLogRecGetData(record), sizeof(CheckPoint));
		/* In a SHUTDOWN checkpoint, believe the counters exactly */
		LWLockAcquire(XidGenLock, LW_EXCLUSIVE);
		ShmemVariableCache->nextXid = checkPoint.nextXid;
		LWLockRelease(XidGenLock);
		LWLockAcquire(OidGenLock, LW_EXCLUSIVE);
		ShmemVariableCache->nextOid = checkPoint.nextOid;
		ShmemVariableCache->oidCount = 0;
		LWLockRelease(OidGenLock);
		MultiXactSetNextMXact(checkPoint.nextMulti,
							  checkPoint.nextMultiOffset);
		SetTransactionIdLimit(checkPoint.oldestXid, checkPoint.oldestXidDB);

		/*
		 * If we see a shutdown checkpoint while waiting for an end-of-backup
		 * record, the backup was canceled and the end-of-backup record will
		 * never arrive.
		 */
		if (InArchiveRecovery &&
			!XLogRecPtrIsInvalid(ControlFile->backupStartPoint) &&
			XLogRecPtrIsInvalid(ControlFile->backupEndPoint))
			ereport(PANIC,
			(errmsg("online backup was canceled, recovery cannot continue")));

		/*
		 * If we see a shutdown checkpoint, we know that nothing was running
		 * on the master at this point. So fake-up an empty running-xacts
		 * record and use that here and now. Recover additional standby state
		 * for prepared transactions.
		 */
		if (standbyState >= STANDBY_INITIALIZED)
		{
			TransactionId *xids;
			int			nxids;
			TransactionId oldestActiveXID;
			TransactionId latestCompletedXid;
			RunningTransactionsData running;

			oldestActiveXID = PrescanPreparedTransactions(&xids, &nxids);

			/*
			 * Construct a RunningTransactions snapshot representing a shut
			 * down server, with only prepared transactions still alive. We're
			 * never overflowed at this point because all subxids are listed
			 * with their parent prepared transactions.
			 */
			running.xcnt = nxids;
			running.subxid_overflow = false;
			running.nextXid = checkPoint.nextXid;
			running.oldestRunningXid = oldestActiveXID;
			latestCompletedXid = checkPoint.nextXid;
			TransactionIdRetreat(latestCompletedXid);
			Assert(TransactionIdIsNormal(latestCompletedXid));
			running.latestCompletedXid = latestCompletedXid;
			running.xids = xids;

			ProcArrayApplyRecoveryInfo(&running);

			StandbyRecoverPreparedTransactions(true);
		}

		/* ControlFile->checkPointCopy always tracks the latest ckpt XID */
		ControlFile->checkPointCopy.nextXidEpoch = checkPoint.nextXidEpoch;
		ControlFile->checkPointCopy.nextXid = checkPoint.nextXid;

		/* Update shared-memory copy of checkpoint XID/epoch */
		{
			/* use volatile pointer to prevent code rearrangement */
			volatile XLogCtlData *xlogctl = XLogCtl;

			SpinLockAcquire(&xlogctl->info_lck);
			xlogctl->ckptXidEpoch = checkPoint.nextXidEpoch;
			xlogctl->ckptXid = checkPoint.nextXid;
			SpinLockRelease(&xlogctl->info_lck);
		}

		/*
		 * TLI may change in a shutdown checkpoint, but it shouldn't decrease
		 */
		if (checkPoint.ThisTimeLineID != ThisTimeLineID)
		{
			if (checkPoint.ThisTimeLineID < ThisTimeLineID ||
				!list_member_int(expectedTLIs,
								 (int) checkPoint.ThisTimeLineID))
				ereport(PANIC,
						(errmsg("unexpected timeline ID %u (after %u) in checkpoint record",
								checkPoint.ThisTimeLineID, ThisTimeLineID)));
			/* Following WAL records should be run with new TLI */
			ThisTimeLineID = checkPoint.ThisTimeLineID;
		}

		RecoveryRestartPoint(&checkPoint);
	}
	else if (info == XLOG_CHECKPOINT_ONLINE)
	{
		CheckPoint	checkPoint;

		memcpy(&checkPoint, XLogRecGetData(record), sizeof(CheckPoint));
		/* In an ONLINE checkpoint, treat the XID counter as a minimum */
		LWLockAcquire(XidGenLock, LW_EXCLUSIVE);
		if (TransactionIdPrecedes(ShmemVariableCache->nextXid,
								  checkPoint.nextXid))
			ShmemVariableCache->nextXid = checkPoint.nextXid;
		LWLockRelease(XidGenLock);
		/* ... but still treat OID counter as exact */
		LWLockAcquire(OidGenLock, LW_EXCLUSIVE);
		ShmemVariableCache->nextOid = checkPoint.nextOid;
		ShmemVariableCache->oidCount = 0;
		LWLockRelease(OidGenLock);
		MultiXactAdvanceNextMXact(checkPoint.nextMulti,
								  checkPoint.nextMultiOffset);
		if (TransactionIdPrecedes(ShmemVariableCache->oldestXid,
								  checkPoint.oldestXid))
			SetTransactionIdLimit(checkPoint.oldestXid,
								  checkPoint.oldestXidDB);

		/* ControlFile->checkPointCopy always tracks the latest ckpt XID */
		ControlFile->checkPointCopy.nextXidEpoch = checkPoint.nextXidEpoch;
		ControlFile->checkPointCopy.nextXid = checkPoint.nextXid;

		/* Update shared-memory copy of checkpoint XID/epoch */
		{
			/* use volatile pointer to prevent code rearrangement */
			volatile XLogCtlData *xlogctl = XLogCtl;

			SpinLockAcquire(&xlogctl->info_lck);
			xlogctl->ckptXidEpoch = checkPoint.nextXidEpoch;
			xlogctl->ckptXid = checkPoint.nextXid;
			SpinLockRelease(&xlogctl->info_lck);
		}

		/* TLI should not change in an on-line checkpoint */
		if (checkPoint.ThisTimeLineID != ThisTimeLineID)
			ereport(PANIC,
					(errmsg("unexpected timeline ID %u (should be %u) in checkpoint record",
							checkPoint.ThisTimeLineID, ThisTimeLineID)));

		RecoveryRestartPoint(&checkPoint);
	}
	else if (info == XLOG_NOOP)
	{
		/* nothing to do here */
	}
	else if (info == XLOG_SWITCH)
	{
		/* nothing to do here */
	}
	else if (info == XLOG_RESTORE_POINT)
	{
		/* nothing to do here */
	}
	else if (info == XLOG_BACKUP_END)
	{
		XLogRecPtr	startpoint;

		memcpy(&startpoint, XLogRecGetData(record), sizeof(startpoint));

		if (XLByteEQ(ControlFile->backupStartPoint, startpoint))
		{
			/*
			 * We have reached the end of base backup, the point where
			 * pg_stop_backup() was done. The data on disk is now consistent.
			 * Reset backupStartPoint, and update minRecoveryPoint to make
			 * sure we don't allow starting up at an earlier point even if
			 * recovery is stopped and restarted soon after this.
			 */
			elog(DEBUG1, "end of backup reached");

			LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);

			if (XLByteLT(ControlFile->minRecoveryPoint, lsn))
				ControlFile->minRecoveryPoint = lsn;
			MemSet(&ControlFile->backupStartPoint, 0, sizeof(XLogRecPtr));
			ControlFile->backupEndRequired = false;
			UpdateControlFile();

			LWLockRelease(ControlFileLock);
		}
	}
	else if (info == XLOG_PARAMETER_CHANGE)
	{
		xl_parameter_change xlrec;

		/* Update our copy of the parameters in pg_control */
		memcpy(&xlrec, XLogRecGetData(record), sizeof(xl_parameter_change));

		LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
		ControlFile->MaxConnections = xlrec.MaxConnections;
		ControlFile->max_prepared_xacts = xlrec.max_prepared_xacts;
		ControlFile->max_locks_per_xact = xlrec.max_locks_per_xact;
		ControlFile->wal_level = xlrec.wal_level;

		/*
		 * Update minRecoveryPoint to ensure that if recovery is aborted, we
		 * recover back up to this point before allowing hot standby again.
		 * This is particularly important if wal_level was set to 'archive'
		 * before, and is now 'hot_standby', to ensure you don't run queries
		 * against the WAL preceding the wal_level change. Same applies to
		 * decreasing max_* settings.
		 */
		minRecoveryPoint = ControlFile->minRecoveryPoint;
		if (minRecoveryPoint != 0 && XLByteLT(minRecoveryPoint, lsn))
		{
			ControlFile->minRecoveryPoint = lsn;
		}

		UpdateControlFile();
		LWLockRelease(ControlFileLock);

		/* Check to see if any changes to max_connections give problems */
		CheckRequiredParameterValues();
	}
	else if (info == XLOG_FPW_CHANGE)
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;
		bool		fpw;

		memcpy(&fpw, XLogRecGetData(record), sizeof(bool));

		/*
		 * Update the LSN of the last replayed XLOG_FPW_CHANGE record so that
		 * do_pg_start_backup() and do_pg_stop_backup() can check whether
		 * full_page_writes has been disabled during online backup.
		 */
		if (!fpw)
		{
			SpinLockAcquire(&xlogctl->info_lck);
			if (XLByteLT(xlogctl->lastFpwDisableRecPtr, ReadRecPtr))
				xlogctl->lastFpwDisableRecPtr = ReadRecPtr;
			SpinLockRelease(&xlogctl->info_lck);
		}

		/* Keep track of full_page_writes */
		lastFullPageWrites = fpw;
	}
}

#ifdef WAL_DEBUG

static void
xlog_outrec(StringInfo buf, XLogRecord *record)
{
	int			i;

	appendStringInfo(buf, "prev %X/%X; xid %u",
					 (uint32) (record->xl_prev >> 32),
					 (uint32) record->xl_prev,
					 record->xl_xid);

	appendStringInfo(buf, "; len %u",
					 record->xl_len);

	for (i = 0; i < XLR_MAX_BKP_BLOCKS; i++)
	{
		if (record->xl_info & XLR_BKP_BLOCK(i))
			appendStringInfo(buf, "; bkpb%d", i);
	}

	appendStringInfo(buf, ": %s", RmgrTable[record->xl_rmid].rm_name);
}
#endif   /* WAL_DEBUG */


/*
 * Return the (possible) sync flag used for opening a file, depending on the
 * value of the GUC wal_sync_method.
 */
static int
get_sync_bit(int method)
{
	int			o_direct_flag = 0;

	/* If fsync is disabled, never open in sync mode */
	if (!enableFsync)
		return 0;

	/*
	 * Optimize writes by bypassing kernel cache with O_DIRECT when using
	 * O_SYNC/O_FSYNC and O_DSYNC.	But only if archiving and streaming are
	 * disabled, otherwise the archive command or walsender process will read
	 * the WAL soon after writing it, which is guaranteed to cause a physical
	 * read if we bypassed the kernel cache. We also skip the
	 * posix_fadvise(POSIX_FADV_DONTNEED) call in XLogFileClose() for the same
	 * reason.
	 *
	 * Never use O_DIRECT in walreceiver process for similar reasons; the WAL
	 * written by walreceiver is normally read by the startup process soon
	 * after its written. Also, walreceiver performs unaligned writes, which
	 * don't work with O_DIRECT, so it is required for correctness too.
	 */
	if (!XLogIsNeeded() && !AmWalReceiverProcess())
		o_direct_flag = PG_O_DIRECT;

	switch (method)
	{
			/*
			 * enum values for all sync options are defined even if they are
			 * not supported on the current platform.  But if not, they are
			 * not included in the enum option array, and therefore will never
			 * be seen here.
			 */
		case SYNC_METHOD_FSYNC:
		case SYNC_METHOD_FSYNC_WRITETHROUGH:
		case SYNC_METHOD_FDATASYNC:
			return 0;
#ifdef OPEN_SYNC_FLAG
		case SYNC_METHOD_OPEN:
			return OPEN_SYNC_FLAG | o_direct_flag;
#endif
#ifdef OPEN_DATASYNC_FLAG
		case SYNC_METHOD_OPEN_DSYNC:
			return OPEN_DATASYNC_FLAG | o_direct_flag;
#endif
		default:
			/* can't happen (unless we are out of sync with option array) */
			elog(ERROR, "unrecognized wal_sync_method: %d", method);
			return 0;			/* silence warning */
	}
}

/*
 * GUC support
 */
void
assign_xlog_sync_method(int new_sync_method, void *extra)
{
	if (sync_method != new_sync_method)
	{
		/*
		 * To ensure that no blocks escape unsynced, force an fsync on the
		 * currently open log segment (if any).  Also, if the open flag is
		 * changing, close the log file so it will be reopened (with new flag
		 * bit) at next use.
		 */
		if (openLogFile >= 0)
		{
			if (pg_fsync(openLogFile) != 0)
				ereport(PANIC,
						(errcode_for_file_access(),
						 errmsg("could not fsync log segment %s: %m",
								XLogFileNameP(ThisTimeLineID, openLogSegNo))));
			if (get_sync_bit(sync_method) != get_sync_bit(new_sync_method))
				XLogFileClose();
		}
	}
}


/*
 * Issue appropriate kind of fsync (if any) for an XLOG output file.
 *
 * 'fd' is a file descriptor for the XLOG file to be fsync'd.
 * 'log' and 'seg' are for error reporting purposes.
 */
void
issue_xlog_fsync(int fd, XLogSegNo segno)
{
	switch (sync_method)
	{
		case SYNC_METHOD_FSYNC:
			if (pg_fsync_no_writethrough(fd) != 0)
				ereport(PANIC,
						(errcode_for_file_access(),
						 errmsg("could not fsync log file %s: %m",
								XLogFileNameP(ThisTimeLineID, segno))));
			break;
#ifdef HAVE_FSYNC_WRITETHROUGH
		case SYNC_METHOD_FSYNC_WRITETHROUGH:
			if (pg_fsync_writethrough(fd) != 0)
				ereport(PANIC,
						(errcode_for_file_access(),
						 errmsg("could not fsync write-through log file %s: %m",
								XLogFileNameP(ThisTimeLineID, segno))));
			break;
#endif
#ifdef HAVE_FDATASYNC
		case SYNC_METHOD_FDATASYNC:
			if (pg_fdatasync(fd) != 0)
				ereport(PANIC,
						(errcode_for_file_access(),
						 errmsg("could not fdatasync log file %s: %m",
								XLogFileNameP(ThisTimeLineID, segno))));
			break;
#endif
		case SYNC_METHOD_OPEN:
		case SYNC_METHOD_OPEN_DSYNC:
			/* write synced it already */
			break;
		default:
			elog(PANIC, "unrecognized wal_sync_method: %d", sync_method);
			break;
	}
}

/*
 * Return the filename of given log segment, as a palloc'd string.
 */
char *
XLogFileNameP(TimeLineID tli, XLogSegNo segno)
{
	char	   *result = palloc(MAXFNAMELEN);
	XLogFileName(result, tli, segno);
	return result;
}

/*
 * do_pg_start_backup is the workhorse of the user-visible pg_start_backup()
 * function. It creates the necessary starting checkpoint and constructs the
 * backup label file.
 *
 * There are two kind of backups: exclusive and non-exclusive. An exclusive
 * backup is started with pg_start_backup(), and there can be only one active
 * at a time. The backup label file of an exclusive backup is written to
 * $PGDATA/backup_label, and it is removed by pg_stop_backup().
 *
 * A non-exclusive backup is used for the streaming base backups (see
 * src/backend/replication/basebackup.c). The difference to exclusive backups
 * is that the backup label file is not written to disk. Instead, its would-be
 * contents are returned in *labelfile, and the caller is responsible for
 * including it in the backup archive as 'backup_label'. There can be many
 * non-exclusive backups active at the same time, and they don't conflict
 * with an exclusive backup either.
 *
 * Every successfully started non-exclusive backup must be stopped by calling
 * do_pg_stop_backup() or do_pg_abort_backup().
 */
XLogRecPtr
do_pg_start_backup(const char *backupidstr, bool fast, char **labelfile)
{
	bool		exclusive = (labelfile == NULL);
	bool		backup_started_in_recovery = false;
	XLogRecPtr	checkpointloc;
	XLogRecPtr	startpoint;
	pg_time_t	stamp_time;
	char		strfbuf[128];
	char		xlogfilename[MAXFNAMELEN];
	XLogSegNo	_logSegNo;
	struct stat stat_buf;
	FILE	   *fp;
	StringInfoData labelfbuf;

	backup_started_in_recovery = RecoveryInProgress();

	if (!superuser() && !is_authenticated_user_replication_role())
		ereport(ERROR,
				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
		   errmsg("must be superuser or replication role to run a backup")));

	/*
	 * Currently only non-exclusive backup can be taken during recovery.
	 */
	if (backup_started_in_recovery && exclusive)
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("recovery is in progress"),
				 errhint("WAL control functions cannot be executed during recovery.")));

	/*
	 * During recovery, we don't need to check WAL level. Because, if WAL
	 * level is not sufficient, it's impossible to get here during recovery.
	 */
	if (!backup_started_in_recovery && !XLogIsNeeded())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
			  errmsg("WAL level not sufficient for making an online backup"),
				 errhint("wal_level must be set to \"archive\" or \"hot_standby\" at server start.")));

	if (strlen(backupidstr) > MAXPGPATH)
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
				 errmsg("backup label too long (max %d bytes)",
						MAXPGPATH)));

	/*
	 * Mark backup active in shared memory.  We must do full-page WAL writes
	 * during an on-line backup even if not doing so at other times, because
	 * it's quite possible for the backup dump to obtain a "torn" (partially
	 * written) copy of a database page if it reads the page concurrently with
	 * our write to the same page.	This can be fixed as long as the first
	 * write to the page in the WAL sequence is a full-page write. Hence, we
	 * turn on forcePageWrites and then force a CHECKPOINT, to ensure there
	 * are no dirty pages in shared memory that might get dumped while the
	 * backup is in progress without having a corresponding WAL record.  (Once
	 * the backup is complete, we need not force full-page writes anymore,
	 * since we expect that any pages not modified during the backup interval
	 * must have been correctly captured by the backup.)
	 *
	 * Note that forcePageWrites has no effect during an online backup from
	 * the standby.
	 *
	 * We must hold WALInsertLock to change the value of forcePageWrites, to
	 * ensure adequate interlocking against XLogInsert().
	 */
	LWLockAcquire(WALInsertLock, LW_EXCLUSIVE);
	if (exclusive)
	{
		if (XLogCtl->Insert.exclusiveBackup)
		{
			LWLockRelease(WALInsertLock);
			ereport(ERROR,
					(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
					 errmsg("a backup is already in progress"),
					 errhint("Run pg_stop_backup() and try again.")));
		}
		XLogCtl->Insert.exclusiveBackup = true;
	}
	else
		XLogCtl->Insert.nonExclusiveBackups++;
	XLogCtl->Insert.forcePageWrites = true;
	LWLockRelease(WALInsertLock);

	/* Ensure we release forcePageWrites if fail below */
	PG_ENSURE_ERROR_CLEANUP(pg_start_backup_callback, (Datum) BoolGetDatum(exclusive));
	{
		bool		gotUniqueStartpoint = false;

		/*
		 * Force an XLOG file switch before the checkpoint, to ensure that the
		 * WAL segment the checkpoint is written to doesn't contain pages with
		 * old timeline IDs.  That would otherwise happen if you called
		 * pg_start_backup() right after restoring from a PITR archive: the
		 * first WAL segment containing the startup checkpoint has pages in
		 * the beginning with the old timeline ID.	That can cause trouble at
		 * recovery: we won't have a history file covering the old timeline if
		 * pg_xlog directory was not included in the base backup and the WAL
		 * archive was cleared too before starting the backup.
		 *
		 * This also ensures that we have emitted a WAL page header that has
		 * XLP_BKP_REMOVABLE off before we emit the checkpoint record.
		 * Therefore, if a WAL archiver (such as pglesslog) is trying to
		 * compress out removable backup blocks, it won't remove any that
		 * occur after this point.
		 *
		 * During recovery, we skip forcing XLOG file switch, which means that
		 * the backup taken during recovery is not available for the special
		 * recovery case described above.
		 */
		if (!backup_started_in_recovery)
			RequestXLogSwitch();

		do
		{
			bool		checkpointfpw;

			/*
			 * Force a CHECKPOINT.	Aside from being necessary to prevent torn
			 * page problems, this guarantees that two successive backup runs
			 * will have different checkpoint positions and hence different
			 * history file names, even if nothing happened in between.
			 *
			 * During recovery, establish a restartpoint if possible. We use
			 * the last restartpoint as the backup starting checkpoint. This
			 * means that two successive backup runs can have same checkpoint
			 * positions.
			 *
			 * Since the fact that we are executing do_pg_start_backup()
			 * during recovery means that checkpointer is running, we can use
			 * RequestCheckpoint() to establish a restartpoint.
			 *
			 * We use CHECKPOINT_IMMEDIATE only if requested by user (via
			 * passing fast = true).  Otherwise this can take awhile.
			 */
			RequestCheckpoint(CHECKPOINT_FORCE | CHECKPOINT_WAIT |
							  (fast ? CHECKPOINT_IMMEDIATE : 0));

			/*
			 * Now we need to fetch the checkpoint record location, and also
			 * its REDO pointer.  The oldest point in WAL that would be needed
			 * to restore starting from the checkpoint is precisely the REDO
			 * pointer.
			 */
			LWLockAcquire(ControlFileLock, LW_SHARED);
			checkpointloc = ControlFile->checkPoint;
			startpoint = ControlFile->checkPointCopy.redo;
			checkpointfpw = ControlFile->checkPointCopy.fullPageWrites;
			LWLockRelease(ControlFileLock);

			if (backup_started_in_recovery)
			{
				/* use volatile pointer to prevent code rearrangement */
				volatile XLogCtlData *xlogctl = XLogCtl;
				XLogRecPtr	recptr;

				/*
				 * Check to see if all WAL replayed during online backup
				 * (i.e., since last restartpoint used as backup starting
				 * checkpoint) contain full-page writes.
				 */
				SpinLockAcquire(&xlogctl->info_lck);
				recptr = xlogctl->lastFpwDisableRecPtr;
				SpinLockRelease(&xlogctl->info_lck);

				if (!checkpointfpw || XLByteLE(startpoint, recptr))
					ereport(ERROR,
						  (errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
						   errmsg("WAL generated with full_page_writes=off was replayed "
								  "since last restartpoint"),
						   errhint("This means that the backup being taken on standby "
								   "is corrupt and should not be used. "
								   "Enable full_page_writes and run CHECKPOINT on the master, "
								   "and then try an online backup again.")));

				/*
				 * During recovery, since we don't use the end-of-backup WAL
				 * record and don't write the backup history file, the
				 * starting WAL location doesn't need to be unique. This means
				 * that two base backups started at the same time might use
				 * the same checkpoint as starting locations.
				 */
				gotUniqueStartpoint = true;
			}

			/*
			 * If two base backups are started at the same time (in WAL sender
			 * processes), we need to make sure that they use different
			 * checkpoints as starting locations, because we use the starting
			 * WAL location as a unique identifier for the base backup in the
			 * end-of-backup WAL record and when we write the backup history
			 * file. Perhaps it would be better generate a separate unique ID
			 * for each backup instead of forcing another checkpoint, but
			 * taking a checkpoint right after another is not that expensive
			 * either because only few buffers have been dirtied yet.
			 */
			LWLockAcquire(WALInsertLock, LW_SHARED);
			if (XLByteLT(XLogCtl->Insert.lastBackupStart, startpoint))
			{
				XLogCtl->Insert.lastBackupStart = startpoint;
				gotUniqueStartpoint = true;
			}
			LWLockRelease(WALInsertLock);
		} while (!gotUniqueStartpoint);

		XLByteToSeg(startpoint, _logSegNo);
		XLogFileName(xlogfilename, ThisTimeLineID, _logSegNo);

		/*
		 * Construct backup label file
		 */
		initStringInfo(&labelfbuf);

		/* Use the log timezone here, not the session timezone */
		stamp_time = (pg_time_t) time(NULL);
		pg_strftime(strfbuf, sizeof(strfbuf),
					"%Y-%m-%d %H:%M:%S %Z",
					pg_localtime(&stamp_time, log_timezone));
		appendStringInfo(&labelfbuf, "START WAL LOCATION: %X/%X (file %s)\n",
						 (uint32) (startpoint >> 32), (uint32) startpoint, xlogfilename);
		appendStringInfo(&labelfbuf, "CHECKPOINT LOCATION: %X/%X\n",
						 (uint32) (checkpointloc >> 32), (uint32) checkpointloc);
		appendStringInfo(&labelfbuf, "BACKUP METHOD: %s\n",
						 exclusive ? "pg_start_backup" : "streamed");
		appendStringInfo(&labelfbuf, "BACKUP FROM: %s\n",
						 backup_started_in_recovery ? "standby" : "master");
		appendStringInfo(&labelfbuf, "START TIME: %s\n", strfbuf);
		appendStringInfo(&labelfbuf, "LABEL: %s\n", backupidstr);

		/*
		 * Okay, write the file, or return its contents to caller.
		 */
		if (exclusive)
		{
			/*
			 * Check for existing backup label --- implies a backup is already
			 * running.  (XXX given that we checked exclusiveBackup above,
			 * maybe it would be OK to just unlink any such label file?)
			 */
			if (stat(BACKUP_LABEL_FILE, &stat_buf) != 0)
			{
				if (errno != ENOENT)
					ereport(ERROR,
							(errcode_for_file_access(),
							 errmsg("could not stat file \"%s\": %m",
									BACKUP_LABEL_FILE)));
			}
			else
				ereport(ERROR,
						(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
						 errmsg("a backup is already in progress"),
						 errhint("If you're sure there is no backup in progress, remove file \"%s\" and try again.",
								 BACKUP_LABEL_FILE)));

			fp = AllocateFile(BACKUP_LABEL_FILE, "w");

			if (!fp)
				ereport(ERROR,
						(errcode_for_file_access(),
						 errmsg("could not create file \"%s\": %m",
								BACKUP_LABEL_FILE)));
			if (fwrite(labelfbuf.data, labelfbuf.len, 1, fp) != 1 ||
				fflush(fp) != 0 ||
				pg_fsync(fileno(fp)) != 0 ||
				ferror(fp) ||
				FreeFile(fp))
				ereport(ERROR,
						(errcode_for_file_access(),
						 errmsg("could not write file \"%s\": %m",
								BACKUP_LABEL_FILE)));
			pfree(labelfbuf.data);
		}
		else
			*labelfile = labelfbuf.data;
	}
	PG_END_ENSURE_ERROR_CLEANUP(pg_start_backup_callback, (Datum) BoolGetDatum(exclusive));

	/*
	 * We're done.  As a convenience, return the starting WAL location.
	 */
	return startpoint;
}

/* Error cleanup callback for pg_start_backup */
static void
pg_start_backup_callback(int code, Datum arg)
{
	bool		exclusive = DatumGetBool(arg);

	/* Update backup counters and forcePageWrites on failure */
	LWLockAcquire(WALInsertLock, LW_EXCLUSIVE);
	if (exclusive)
	{
		Assert(XLogCtl->Insert.exclusiveBackup);
		XLogCtl->Insert.exclusiveBackup = false;
	}
	else
	{
		Assert(XLogCtl->Insert.nonExclusiveBackups > 0);
		XLogCtl->Insert.nonExclusiveBackups--;
	}

	if (!XLogCtl->Insert.exclusiveBackup &&
		XLogCtl->Insert.nonExclusiveBackups == 0)
	{
		XLogCtl->Insert.forcePageWrites = false;
	}
	LWLockRelease(WALInsertLock);
}

/*
 * do_pg_stop_backup is the workhorse of the user-visible pg_stop_backup()
 * function.

 * If labelfile is NULL, this stops an exclusive backup. Otherwise this stops
 * the non-exclusive backup specified by 'labelfile'.
 */
XLogRecPtr
do_pg_stop_backup(char *labelfile, bool waitforarchive)
{
	bool		exclusive = (labelfile == NULL);
	bool		backup_started_in_recovery = false;
	XLogRecPtr	startpoint;
	XLogRecPtr	stoppoint;
	XLogRecData rdata;
	pg_time_t	stamp_time;
	char		strfbuf[128];
	char		histfilepath[MAXPGPATH];
	char		startxlogfilename[MAXFNAMELEN];
	char		stopxlogfilename[MAXFNAMELEN];
	char		lastxlogfilename[MAXFNAMELEN];
	char		histfilename[MAXFNAMELEN];
	char		backupfrom[20];
	XLogSegNo	_logSegNo;
	FILE	   *lfp;
	FILE	   *fp;
	char		ch;
	int			seconds_before_warning;
	int			waits = 0;
	bool		reported_waiting = false;
	char	   *remaining;
	char	   *ptr;
	uint32		hi,
				lo;

	backup_started_in_recovery = RecoveryInProgress();

	if (!superuser() && !is_authenticated_user_replication_role())
		ereport(ERROR,
				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
		 (errmsg("must be superuser or replication role to run a backup"))));

	/*
	 * Currently only non-exclusive backup can be taken during recovery.
	 */
	if (backup_started_in_recovery && exclusive)
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("recovery is in progress"),
				 errhint("WAL control functions cannot be executed during recovery.")));

	/*
	 * During recovery, we don't need to check WAL level. Because, if WAL
	 * level is not sufficient, it's impossible to get here during recovery.
	 */
	if (!backup_started_in_recovery && !XLogIsNeeded())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
			  errmsg("WAL level not sufficient for making an online backup"),
				 errhint("wal_level must be set to \"archive\" or \"hot_standby\" at server start.")));

	/*
	 * OK to update backup counters and forcePageWrites
	 */
	LWLockAcquire(WALInsertLock, LW_EXCLUSIVE);
	if (exclusive)
		XLogCtl->Insert.exclusiveBackup = false;
	else
	{
		/*
		 * The user-visible pg_start/stop_backup() functions that operate on
		 * exclusive backups can be called at any time, but for non-exclusive
		 * backups, it is expected that each do_pg_start_backup() call is
		 * matched by exactly one do_pg_stop_backup() call.
		 */
		Assert(XLogCtl->Insert.nonExclusiveBackups > 0);
		XLogCtl->Insert.nonExclusiveBackups--;
	}

	if (!XLogCtl->Insert.exclusiveBackup &&
		XLogCtl->Insert.nonExclusiveBackups == 0)
	{
		XLogCtl->Insert.forcePageWrites = false;
	}
	LWLockRelease(WALInsertLock);

	if (exclusive)
	{
		/*
		 * Read the existing label file into memory.
		 */
		struct stat statbuf;
		int			r;

		if (stat(BACKUP_LABEL_FILE, &statbuf))
		{
			if (errno != ENOENT)
				ereport(ERROR,
						(errcode_for_file_access(),
						 errmsg("could not stat file \"%s\": %m",
								BACKUP_LABEL_FILE)));
			ereport(ERROR,
					(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
					 errmsg("a backup is not in progress")));
		}

		lfp = AllocateFile(BACKUP_LABEL_FILE, "r");
		if (!lfp)
		{
			ereport(ERROR,
					(errcode_for_file_access(),
					 errmsg("could not read file \"%s\": %m",
							BACKUP_LABEL_FILE)));
		}
		labelfile = palloc(statbuf.st_size + 1);
		r = fread(labelfile, statbuf.st_size, 1, lfp);
		labelfile[statbuf.st_size] = '\0';

		/*
		 * Close and remove the backup label file
		 */
		if (r != 1 || ferror(lfp) || FreeFile(lfp))
			ereport(ERROR,
					(errcode_for_file_access(),
					 errmsg("could not read file \"%s\": %m",
							BACKUP_LABEL_FILE)));
		if (unlink(BACKUP_LABEL_FILE) != 0)
			ereport(ERROR,
					(errcode_for_file_access(),
					 errmsg("could not remove file \"%s\": %m",
							BACKUP_LABEL_FILE)));
	}

	/*
	 * Read and parse the START WAL LOCATION line (this code is pretty crude,
	 * but we are not expecting any variability in the file format).
	 */
	if (sscanf(labelfile, "START WAL LOCATION: %X/%X (file %24s)%c",
			   &hi, &lo, startxlogfilename,
			   &ch) != 4 || ch != '\n')
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("invalid data in file \"%s\"", BACKUP_LABEL_FILE)));
	startpoint = ((uint64) hi) << 32 | lo;
	remaining = strchr(labelfile, '\n') + 1;	/* %n is not portable enough */

	/*
	 * Parse the BACKUP FROM line. If we are taking an online backup from the
	 * standby, we confirm that the standby has not been promoted during the
	 * backup.
	 */
	ptr = strstr(remaining, "BACKUP FROM:");
	if (!ptr || sscanf(ptr, "BACKUP FROM: %19s\n", backupfrom) != 1)
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("invalid data in file \"%s\"", BACKUP_LABEL_FILE)));
	if (strcmp(backupfrom, "standby") == 0 && !backup_started_in_recovery)
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("the standby was promoted during online backup"),
				 errhint("This means that the backup being taken is corrupt "
						 "and should not be used. "
						 "Try taking another online backup.")));

	/*
	 * During recovery, we don't write an end-of-backup record. We assume that
	 * pg_control was backed up last and its minimum recovery point can be
	 * available as the backup end location. Since we don't have an
	 * end-of-backup record, we use the pg_control value to check whether
	 * we've reached the end of backup when starting recovery from this
	 * backup. We have no way of checking if pg_control wasn't backed up last
	 * however.
	 *
	 * We don't force a switch to new WAL file and wait for all the required
	 * files to be archived. This is okay if we use the backup to start the
	 * standby. But, if it's for an archive recovery, to ensure all the
	 * required files are available, a user should wait for them to be
	 * archived, or include them into the backup.
	 *
	 * We return the current minimum recovery point as the backup end
	 * location. Note that it can be greater than the exact backup end
	 * location if the minimum recovery point is updated after the backup of
	 * pg_control. This is harmless for current uses.
	 *
	 * XXX currently a backup history file is for informational and debug
	 * purposes only. It's not essential for an online backup. Furthermore,
	 * even if it's created, it will not be archived during recovery because
	 * an archiver is not invoked. So it doesn't seem worthwhile to write a
	 * backup history file during recovery.
	 */
	if (backup_started_in_recovery)
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;
		XLogRecPtr	recptr;

		/*
		 * Check to see if all WAL replayed during online backup contain
		 * full-page writes.
		 */
		SpinLockAcquire(&xlogctl->info_lck);
		recptr = xlogctl->lastFpwDisableRecPtr;
		SpinLockRelease(&xlogctl->info_lck);

		if (XLByteLE(startpoint, recptr))
			ereport(ERROR,
					(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
			   errmsg("WAL generated with full_page_writes=off was replayed "
					  "during online backup"),
				 errhint("This means that the backup being taken on standby "
						 "is corrupt and should not be used. "
				 "Enable full_page_writes and run CHECKPOINT on the master, "
						 "and then try an online backup again.")));


		LWLockAcquire(ControlFileLock, LW_SHARED);
		stoppoint = ControlFile->minRecoveryPoint;
		LWLockRelease(ControlFileLock);

		return stoppoint;
	}

	/*
	 * Write the backup-end xlog record
	 */
	rdata.data = (char *) (&startpoint);
	rdata.len = sizeof(startpoint);
	rdata.buffer = InvalidBuffer;
	rdata.next = NULL;
	stoppoint = XLogInsert(RM_XLOG_ID, XLOG_BACKUP_END, &rdata);

	/*
	 * Force a switch to a new xlog segment file, so that the backup is valid
	 * as soon as archiver moves out the current segment file.
	 */
	RequestXLogSwitch();

	XLByteToPrevSeg(stoppoint, _logSegNo);
	XLogFileName(stopxlogfilename, ThisTimeLineID, _logSegNo);

	/* Use the log timezone here, not the session timezone */
	stamp_time = (pg_time_t) time(NULL);
	pg_strftime(strfbuf, sizeof(strfbuf),
				"%Y-%m-%d %H:%M:%S %Z",
				pg_localtime(&stamp_time, log_timezone));

	/*
	 * Write the backup history file
	 */
	XLByteToSeg(startpoint, _logSegNo);
	BackupHistoryFilePath(histfilepath, ThisTimeLineID, _logSegNo,
						  (uint32) (startpoint % XLogSegSize));
	fp = AllocateFile(histfilepath, "w");
	if (!fp)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not create file \"%s\": %m",
						histfilepath)));
	fprintf(fp, "START WAL LOCATION: %X/%X (file %s)\n",
			(uint32) (startpoint >> 32), (uint32) startpoint, startxlogfilename);
	fprintf(fp, "STOP WAL LOCATION: %X/%X (file %s)\n",
			(uint32) (stoppoint >> 32), (uint32) stoppoint, stopxlogfilename);
	/* transfer remaining lines from label to history file */
	fprintf(fp, "%s", remaining);
	fprintf(fp, "STOP TIME: %s\n", strfbuf);
	if (fflush(fp) || ferror(fp) || FreeFile(fp))
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not write file \"%s\": %m",
						histfilepath)));

	/*
	 * Clean out any no-longer-needed history files.  As a side effect, this
	 * will post a .ready file for the newly created history file, notifying
	 * the archiver that history file may be archived immediately.
	 */
	CleanupBackupHistory();

	/*
	 * If archiving is enabled, wait for all the required WAL files to be
	 * archived before returning. If archiving isn't enabled, the required WAL
	 * needs to be transported via streaming replication (hopefully with
	 * wal_keep_segments set high enough), or some more exotic mechanism like
	 * polling and copying files from pg_xlog with script. We have no
	 * knowledge of those mechanisms, so it's up to the user to ensure that he
	 * gets all the required WAL.
	 *
	 * We wait until both the last WAL file filled during backup and the
	 * history file have been archived, and assume that the alphabetic sorting
	 * property of the WAL files ensures any earlier WAL files are safely
	 * archived as well.
	 *
	 * We wait forever, since archive_command is supposed to work and we
	 * assume the admin wanted his backup to work completely. If you don't
	 * wish to wait, you can set statement_timeout.  Also, some notices are
	 * issued to clue in anyone who might be doing this interactively.
	 */
	if (waitforarchive && XLogArchivingActive())
	{
		XLByteToPrevSeg(stoppoint, _logSegNo);
		XLogFileName(lastxlogfilename, ThisTimeLineID, _logSegNo);

		XLByteToSeg(startpoint, _logSegNo);
		BackupHistoryFileName(histfilename, ThisTimeLineID, _logSegNo,
							  (uint32) (startpoint % XLogSegSize));

		seconds_before_warning = 60;
		waits = 0;

		while (XLogArchiveIsBusy(lastxlogfilename) ||
			   XLogArchiveIsBusy(histfilename))
		{
			CHECK_FOR_INTERRUPTS();

			if (!reported_waiting && waits > 5)
			{
				ereport(NOTICE,
						(errmsg("pg_stop_backup cleanup done, waiting for required WAL segments to be archived")));
				reported_waiting = true;
			}

			pg_usleep(1000000L);

			if (++waits >= seconds_before_warning)
			{
				seconds_before_warning *= 2;	/* This wraps in >10 years... */
				ereport(WARNING,
						(errmsg("pg_stop_backup still waiting for all required WAL segments to be archived (%d seconds elapsed)",
								waits),
						 errhint("Check that your archive_command is executing properly.  "
								 "pg_stop_backup can be canceled safely, "
								 "but the database backup will not be usable without all the WAL segments.")));
			}
		}

		ereport(NOTICE,
				(errmsg("pg_stop_backup complete, all required WAL segments have been archived")));
	}
	else if (waitforarchive)
		ereport(NOTICE,
				(errmsg("WAL archiving is not enabled; you must ensure that all required WAL segments are copied through other means to complete the backup")));

	/*
	 * We're done.  As a convenience, return the ending WAL location.
	 */
	return stoppoint;
}


/*
 * do_pg_abort_backup: abort a running backup
 *
 * This does just the most basic steps of do_pg_stop_backup(), by taking the
 * system out of backup mode, thus making it a lot more safe to call from
 * an error handler.
 *
 * NB: This is only for aborting a non-exclusive backup that doesn't write
 * backup_label. A backup started with pg_stop_backup() needs to be finished
 * with pg_stop_backup().
 */
void
do_pg_abort_backup(void)
{
	LWLockAcquire(WALInsertLock, LW_EXCLUSIVE);
	Assert(XLogCtl->Insert.nonExclusiveBackups > 0);
	XLogCtl->Insert.nonExclusiveBackups--;

	if (!XLogCtl->Insert.exclusiveBackup &&
		XLogCtl->Insert.nonExclusiveBackups == 0)
	{
		XLogCtl->Insert.forcePageWrites = false;
	}
	LWLockRelease(WALInsertLock);
}

/*
 * Get latest redo apply position.
 *
 * Optionally, returns the current recovery target timeline. Callers not
 * interested in that may pass NULL for targetTLI.
 *
 * Exported to allow WALReceiver to read the pointer directly.
 */
XLogRecPtr
GetXLogReplayRecPtr(TimeLineID *targetTLI)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;
	XLogRecPtr	recptr;

	SpinLockAcquire(&xlogctl->info_lck);
	recptr = xlogctl->recoveryLastRecPtr;
	if (targetTLI)
		*targetTLI = xlogctl->RecoveryTargetTLI;
	SpinLockRelease(&xlogctl->info_lck);

	return recptr;
}

/*
 * Get current standby flush position, ie, the last WAL position
 * known to be fsync'd to disk in standby.
 *
 * If 'targetTLI' is not NULL, it's set to the current recovery target
 * timeline.
 */
XLogRecPtr
GetStandbyFlushRecPtr(TimeLineID *targetTLI)
{
	XLogRecPtr	receivePtr;
	XLogRecPtr	replayPtr;

	receivePtr = GetWalRcvWriteRecPtr(NULL);
	replayPtr = GetXLogReplayRecPtr(targetTLI);

	if (XLByteLT(receivePtr, replayPtr))
		return replayPtr;
	else
		return receivePtr;
}

/*
 * Get latest WAL insert pointer
 */
XLogRecPtr
GetXLogInsertRecPtr(void)
{
	XLogCtlInsert *Insert = &XLogCtl->Insert;
	XLogRecPtr	current_recptr;

	LWLockAcquire(WALInsertLock, LW_SHARED);
	INSERT_RECPTR(current_recptr, Insert, Insert->curridx);
	LWLockRelease(WALInsertLock);

	return current_recptr;
}

/*
 * Get latest WAL write pointer
 */
XLogRecPtr
GetXLogWriteRecPtr(void)
{
	{
		/* use volatile pointer to prevent code rearrangement */
		volatile XLogCtlData *xlogctl = XLogCtl;

		SpinLockAcquire(&xlogctl->info_lck);
		LogwrtResult = xlogctl->LogwrtResult;
		SpinLockRelease(&xlogctl->info_lck);
	}

	return LogwrtResult.Write;
}

/*
 * Returns the redo pointer of the last checkpoint or restartpoint. This is
 * the oldest point in WAL that we still need, if we have to restart recovery.
 */
void
GetOldestRestartPoint(XLogRecPtr *oldrecptr, TimeLineID *oldtli)
{
	LWLockAcquire(ControlFileLock, LW_SHARED);
	*oldrecptr = ControlFile->checkPointCopy.redo;
	*oldtli = ControlFile->checkPointCopy.ThisTimeLineID;
	LWLockRelease(ControlFileLock);
}

/*
 * read_backup_label: check to see if a backup_label file is present
 *
 * If we see a backup_label during recovery, we assume that we are recovering
 * from a backup dump file, and we therefore roll forward from the checkpoint
 * identified by the label file, NOT what pg_control says.	This avoids the
 * problem that pg_control might have been archived one or more checkpoints
 * later than the start of the dump, and so if we rely on it as the start
 * point, we will fail to restore a consistent database state.
 *
 * Returns TRUE if a backup_label was found (and fills the checkpoint
 * location and its REDO location into *checkPointLoc and RedoStartLSN,
 * respectively); returns FALSE if not. If this backup_label came from a
 * streamed backup, *backupEndRequired is set to TRUE. If this backup_label
 * was created during recovery, *backupFromStandby is set to TRUE.
 */
static bool
read_backup_label(XLogRecPtr *checkPointLoc, bool *backupEndRequired,
				  bool *backupFromStandby)
{
	char		startxlogfilename[MAXFNAMELEN];
	TimeLineID	tli;
	FILE	   *lfp;
	char		ch;
	char		backuptype[20];
	char		backupfrom[20];
	uint32		hi,
				lo;

	*backupEndRequired = false;
	*backupFromStandby = false;

	/*
	 * See if label file is present
	 */
	lfp = AllocateFile(BACKUP_LABEL_FILE, "r");
	if (!lfp)
	{
		if (errno != ENOENT)
			ereport(FATAL,
					(errcode_for_file_access(),
					 errmsg("could not read file \"%s\": %m",
							BACKUP_LABEL_FILE)));
		return false;			/* it's not there, all is fine */
	}

	/*
	 * Read and parse the START WAL LOCATION and CHECKPOINT lines (this code
	 * is pretty crude, but we are not expecting any variability in the file
	 * format).
	 */
	if (fscanf(lfp, "START WAL LOCATION: %X/%X (file %08X%16s)%c",
			   &hi, &lo, &tli, startxlogfilename, &ch) != 5 || ch != '\n')
		ereport(FATAL,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("invalid data in file \"%s\"", BACKUP_LABEL_FILE)));
	RedoStartLSN = ((uint64) hi) << 32 | lo;
	if (fscanf(lfp, "CHECKPOINT LOCATION: %X/%X%c",
			   &hi, &lo, &ch) != 3 || ch != '\n')
		ereport(FATAL,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("invalid data in file \"%s\"", BACKUP_LABEL_FILE)));
	*checkPointLoc = ((uint64) hi) << 32 | lo;

	/*
	 * BACKUP METHOD and BACKUP FROM lines are new in 9.2. We can't restore
	 * from an older backup anyway, but since the information on it is not
	 * strictly required, don't error out if it's missing for some reason.
	 */
	if (fscanf(lfp, "BACKUP METHOD: %19s\n", backuptype) == 1)
	{
		if (strcmp(backuptype, "streamed") == 0)
			*backupEndRequired = true;
	}

	if (fscanf(lfp, "BACKUP FROM: %19s\n", backupfrom) == 1)
	{
		if (strcmp(backupfrom, "standby") == 0)
			*backupFromStandby = true;
	}

	if (ferror(lfp) || FreeFile(lfp))
		ereport(FATAL,
				(errcode_for_file_access(),
				 errmsg("could not read file \"%s\": %m",
						BACKUP_LABEL_FILE)));

	return true;
}

/*
 * Error context callback for errors occurring during rm_redo().
 */
static void
rm_redo_error_callback(void *arg)
{
	XLogRecord *record = (XLogRecord *) arg;
	StringInfoData buf;

	initStringInfo(&buf);
	RmgrTable[record->xl_rmid].rm_desc(&buf,
									   record->xl_info,
									   XLogRecGetData(record));

	/* don't bother emitting empty description */
	if (buf.len > 0)
		errcontext("xlog redo %s", buf.data);

	pfree(buf.data);
}

/*
 * BackupInProgress: check if online backup mode is active
 *
 * This is done by checking for existence of the "backup_label" file.
 */
bool
BackupInProgress(void)
{
	struct stat stat_buf;

	return (stat(BACKUP_LABEL_FILE, &stat_buf) == 0);
}

/*
 * CancelBackup: rename the "backup_label" file to cancel backup mode
 *
 * If the "backup_label" file exists, it will be renamed to "backup_label.old".
 * Note that this will render an online backup in progress useless.
 * To correctly finish an online backup, pg_stop_backup must be called.
 */
void
CancelBackup(void)
{
	struct stat stat_buf;

	/* if the file is not there, return */
	if (stat(BACKUP_LABEL_FILE, &stat_buf) < 0)
		return;

	/* remove leftover file from previously canceled backup if it exists */
	unlink(BACKUP_LABEL_OLD);

	if (rename(BACKUP_LABEL_FILE, BACKUP_LABEL_OLD) == 0)
	{
		ereport(LOG,
				(errmsg("online backup mode canceled"),
				 errdetail("\"%s\" was renamed to \"%s\".",
						   BACKUP_LABEL_FILE, BACKUP_LABEL_OLD)));
	}
	else
	{
		ereport(WARNING,
				(errcode_for_file_access(),
				 errmsg("online backup mode was not canceled"),
				 errdetail("Could not rename \"%s\" to \"%s\": %m.",
						   BACKUP_LABEL_FILE, BACKUP_LABEL_OLD)));
	}
}

/*
 * Read the XLOG page containing RecPtr into readBuf (if not read already).
 * Returns true if the page is read successfully.
 *
 * This is responsible for restoring files from archive as needed, as well
 * as for waiting for the requested WAL record to arrive in standby mode.
 *
 * 'emode' specifies the log level used for reporting "file not found" or
 * "end of WAL" situations in archive recovery, or in standby mode when a
 * trigger file is found. If set to WARNING or below, XLogPageRead() returns
 * false in those situations, on higher log levels the ereport() won't
 * return.
 *
 * In standby mode, if after a successful return of XLogPageRead() the
 * caller finds the record it's interested in to be broken, it should
 * ereport the error with the level determined by
 * emode_for_corrupt_record(), and then set "failedSources |= readSource"
 * and call XLogPageRead() again with the same arguments. This lets
 * XLogPageRead() to try fetching the record from another source, or to
 * sleep and retry.
 */
static bool
XLogPageRead(XLogRecPtr *RecPtr, int emode, bool fetching_ckpt,
			 bool randAccess)
{
	uint32		targetPageOff;
	uint32		targetRecOff;
	XLogSegNo	targetSegNo;

	XLByteToSeg(*RecPtr, targetSegNo);
	targetPageOff = (((*RecPtr) % XLogSegSize) / XLOG_BLCKSZ) * XLOG_BLCKSZ;
	targetRecOff = (*RecPtr) % XLOG_BLCKSZ;

	/* Fast exit if we have read the record in the current buffer already */
	if (failedSources == 0 && targetSegNo == readSegNo &&
		targetPageOff == readOff && targetRecOff < readLen)
		return true;

	/*
	 * See if we need to switch to a new segment because the requested record
	 * is not in the currently open one.
	 */
	if (readFile >= 0 && !XLByteInSeg(*RecPtr, readSegNo))
	{
		/*
		 * Request a restartpoint if we've replayed too much xlog since the
		 * last one.
		 */
		if (StandbyMode && bgwriterLaunched)
		{
			if (XLogCheckpointNeeded(readSegNo))
			{
				(void) GetRedoRecPtr();
				if (XLogCheckpointNeeded(readSegNo))
					RequestCheckpoint(CHECKPOINT_CAUSE_XLOG);
			}
		}

		close(readFile);
		readFile = -1;
		readSource = 0;
	}

	XLByteToSeg(*RecPtr, readSegNo);

retry:
	/* See if we need to retrieve more data */
	if (readFile < 0 ||
		(readSource == XLOG_FROM_STREAM && !XLByteLT(*RecPtr, receivedUpto)))
	{
		if (StandbyMode)
		{
			if (!WaitForWALToBecomeAvailable(*RecPtr, randAccess,
											 fetching_ckpt))
				goto triggered;
		}
		else
		{
			/* In archive or crash recovery. */
			if (readFile < 0)
			{
				int			sources;

				/* Reset curFileTLI if random fetch. */
				if (randAccess)
					curFileTLI = 0;

				sources = XLOG_FROM_PG_XLOG;
				if (InArchiveRecovery)
					sources |= XLOG_FROM_ARCHIVE;

				readFile = XLogFileReadAnyTLI(readSegNo, emode, sources);
				if (readFile < 0)
					return false;
			}
		}
	}

	/*
	 * At this point, we have the right segment open and if we're streaming we
	 * know the requested record is in it.
	 */
	Assert(readFile != -1);

	/*
	 * If the current segment is being streamed from master, calculate how
	 * much of the current page we have received already. We know the
	 * requested record has been received, but this is for the benefit of
	 * future calls, to allow quick exit at the top of this function.
	 */
	if (readSource == XLOG_FROM_STREAM)
	{
		if (((*RecPtr) / XLOG_BLCKSZ) != (receivedUpto / XLOG_BLCKSZ))
		{
			readLen = XLOG_BLCKSZ;
		}
		else
			readLen = receivedUpto % XLogSegSize - targetPageOff;
	}
	else
		readLen = XLOG_BLCKSZ;

	if (!readFileHeaderValidated && targetPageOff != 0)
	{
		/*
		 * Whenever switching to a new WAL segment, we read the first page of
		 * the file and validate its header, even if that's not where the
		 * target record is.  This is so that we can check the additional
		 * identification info that is present in the first page's "long"
		 * header.
		 */
		readOff = 0;
		if (read(readFile, readBuf, XLOG_BLCKSZ) != XLOG_BLCKSZ)
		{
			char fname[MAXFNAMELEN];
			XLogFileName(fname, curFileTLI, readSegNo);
			ereport(emode_for_corrupt_record(emode, *RecPtr),
					(errcode_for_file_access(),
					 errmsg("could not read from log segment %s, offset %u: %m",
							fname, readOff)));
			goto next_record_is_invalid;
		}
		if (!ValidXLogPageHeader((XLogPageHeader) readBuf, emode, true))
			goto next_record_is_invalid;
	}

	/* Read the requested page */
	readOff = targetPageOff;
	if (lseek(readFile, (off_t) readOff, SEEK_SET) < 0)
	{
		char fname[MAXFNAMELEN];
		XLogFileName(fname, curFileTLI, readSegNo);
		ereport(emode_for_corrupt_record(emode, *RecPtr),
				(errcode_for_file_access(),
		 errmsg("could not seek in log segment %s to offset %u: %m",
				fname, readOff)));
		goto next_record_is_invalid;
	}
	if (read(readFile, readBuf, XLOG_BLCKSZ) != XLOG_BLCKSZ)
	{
		char fname[MAXFNAMELEN];
		XLogFileName(fname, curFileTLI, readSegNo);
		ereport(emode_for_corrupt_record(emode, *RecPtr),
				(errcode_for_file_access(),
		 errmsg("could not read from log segment %s, offset %u: %m",
				fname, readOff)));
		goto next_record_is_invalid;
	}
	if (!ValidXLogPageHeader((XLogPageHeader) readBuf, emode, false))
		goto next_record_is_invalid;

	readFileHeaderValidated = true;

	Assert(targetSegNo == readSegNo);
	Assert(targetPageOff == readOff);
	Assert(targetRecOff < readLen);

	return true;

next_record_is_invalid:
	failedSources |= readSource;

	if (readFile >= 0)
		close(readFile);
	readFile = -1;
	readLen = 0;
	readSource = 0;

	/* In standby-mode, keep trying */
	if (StandbyMode)
		goto retry;
	else
		return false;

triggered:
	if (readFile >= 0)
		close(readFile);
	readFile = -1;
	readLen = 0;
	readSource = 0;

	return false;
}

/*
 * In standby mode, wait for the requested record to become available, either
 * via restore_command succeeding to restore the segment, or via walreceiver
 * having streamed the record (or via someone copying the segment directly to
 * pg_xlog, but that is not documented or recommended).
 *
 * When the requested record becomes available, the function opens the file
 * containing it (if not open already), and returns true. When end of standby
 * mode is triggered by the user, and there is no more WAL available, returns
 * false.
 */
static bool
WaitForWALToBecomeAvailable(XLogRecPtr RecPtr, bool randAccess,
							bool fetching_ckpt)
{
	static pg_time_t last_fail_time = 0;

	for (;;)
	{
		if (WalRcvInProgress())
		{
			bool		havedata;

			/*
			 * If we find an invalid record in the WAL streamed from master,
			 * something is seriously wrong. There's little chance that the
			 * problem will just go away, but PANIC is not good for
			 * availability either, especially in hot standby mode.
			 * Disconnect, and retry from archive/pg_xlog again. The WAL in
			 * the archive should be identical to what was streamed, so it's
			 * unlikely that it helps, but one can hope...
			 */
			if (failedSources & XLOG_FROM_STREAM)
			{
				ShutdownWalRcv();
				continue;
			}

			/*
			 * Walreceiver is active, so see if new data has arrived.
			 *
			 * We only advance XLogReceiptTime when we obtain fresh WAL from
			 * walreceiver and observe that we had already processed
			 * everything before the most recent "chunk" that it flushed to
			 * disk.  In steady state where we are keeping up with the
			 * incoming data, XLogReceiptTime will be updated on each cycle.
			 * When we are behind, XLogReceiptTime will not advance, so the
			 * grace time allotted to conflicting queries will decrease.
			 */
			if (XLByteLT(RecPtr, receivedUpto))
				havedata = true;
			else
			{
				XLogRecPtr	latestChunkStart;

				receivedUpto = GetWalRcvWriteRecPtr(&latestChunkStart);
				if (XLByteLT(RecPtr, receivedUpto))
				{
					havedata = true;
					if (!XLByteLT(RecPtr, latestChunkStart))
					{
						XLogReceiptTime = GetCurrentTimestamp();
						SetCurrentChunkStartTime(XLogReceiptTime);
					}
				}
				else
					havedata = false;
			}
			if (havedata)
			{
				/*
				 * Great, streamed far enough.  Open the file if it's not open
				 * already.  Use XLOG_FROM_STREAM so that source info is set
				 * correctly and XLogReceiptTime isn't changed.
				 */
				if (readFile < 0)
				{
					readFile = XLogFileRead(readSegNo, PANIC,
											recoveryTargetTLI,
											XLOG_FROM_STREAM, false);
					Assert(readFile >= 0);
				}
				else
				{
					/* just make sure source info is correct... */
					readSource = XLOG_FROM_STREAM;
					XLogReceiptSource = XLOG_FROM_STREAM;
				}
				break;
			}

			/*
			 * Data not here yet, so check for trigger then sleep for five
			 * seconds like in the WAL file polling case below.
			 */
			if (CheckForStandbyTrigger())
				return false;

			/*
			 * Wait for more WAL to arrive, or timeout to be reached
			 */
			WaitLatch(&XLogCtl->recoveryWakeupLatch,
					  WL_LATCH_SET | WL_TIMEOUT,
					  5000L);
			ResetLatch(&XLogCtl->recoveryWakeupLatch);
		}
		else
		{
			/*
			 * WAL receiver is not active. Poll the archive.
			 */
			int			sources;
			pg_time_t	now;

			if (readFile >= 0)
			{
				close(readFile);
				readFile = -1;
			}
			/* Reset curFileTLI if random fetch. */
			if (randAccess)
				curFileTLI = 0;

			/*
			 * Try to restore the file from archive, or read an existing file
			 * from pg_xlog.
			 */
			sources = XLOG_FROM_ARCHIVE | XLOG_FROM_PG_XLOG;
			if (!(sources & ~failedSources))
			{
				/*
				 * We've exhausted all options for retrieving the file. Retry.
				 */
				failedSources = 0;

				/*
				 * Before we sleep, re-scan for possible new timelines if we
				 * were requested to recover to the latest timeline.
				 */
				if (recoveryTargetIsLatest)
				{
					if (rescanLatestTimeLine())
						continue;
				}

				/*
				 * If it hasn't been long since last attempt, sleep to avoid
				 * busy-waiting.
				 */
				now = (pg_time_t) time(NULL);
				if ((now - last_fail_time) < 5)
				{
					pg_usleep(1000000L * (5 - (now - last_fail_time)));
					now = (pg_time_t) time(NULL);
				}
				last_fail_time = now;

				/*
				 * If primary_conninfo is set, launch walreceiver to try to
				 * stream the missing WAL, before retrying to restore from
				 * archive/pg_xlog.
				 *
				 * If fetching_ckpt is TRUE, RecPtr points to the initial
				 * checkpoint location. In that case, we use RedoStartLSN as
				 * the streaming start position instead of RecPtr, so that
				 * when we later jump backwards to start redo at RedoStartLSN,
				 * we will have the logs streamed already.
				 */
				if (PrimaryConnInfo)
				{
					XLogRecPtr ptr = fetching_ckpt ? RedoStartLSN : RecPtr;

					RequestXLogStreaming(ptr, PrimaryConnInfo);
					continue;
				}
			}
			/* Don't try to read from a source that just failed */
			sources &= ~failedSources;
			readFile = XLogFileReadAnyTLI(readSegNo, DEBUG2, sources);
			if (readFile >= 0)
				break;

			/*
			 * Nope, not found in archive and/or pg_xlog.
			 */
			failedSources |= sources;

			/*
			 * Check to see if the trigger file exists. Note that we do this
			 * only after failure, so when you create the trigger file, we
			 * still finish replaying as much as we can from archive and
			 * pg_xlog before failover.
			 */
			if (CheckForStandbyTrigger())
				return false;
		}

		/*
		 * This possibly-long loop needs to handle interrupts of startup
		 * process.
		 */
		HandleStartupProcInterrupts();
	}

	return true;
}

/*
 * Determine what log level should be used to report a corrupt WAL record
 * in the current WAL page, previously read by XLogPageRead().
 *
 * 'emode' is the error mode that would be used to report a file-not-found
 * or legitimate end-of-WAL situation.	 Generally, we use it as-is, but if
 * we're retrying the exact same record that we've tried previously, only
 * complain the first time to keep the noise down.	However, we only do when
 * reading from pg_xlog, because we don't expect any invalid records in archive
 * or in records streamed from master. Files in the archive should be complete,
 * and we should never hit the end of WAL because we stop and wait for more WAL
 * to arrive before replaying it.
 *
 * NOTE: This function remembers the RecPtr value it was last called with,
 * to suppress repeated messages about the same record. Only call this when
 * you are about to ereport(), or you might cause a later message to be
 * erroneously suppressed.
 */
static int
emode_for_corrupt_record(int emode, XLogRecPtr RecPtr)
{
	static XLogRecPtr lastComplaint = 0;

	if (readSource == XLOG_FROM_PG_XLOG && emode == LOG)
	{
		if (XLByteEQ(RecPtr, lastComplaint))
			emode = DEBUG1;
		else
			lastComplaint = RecPtr;
	}
	return emode;
}

/*
 * Check to see whether the user-specified trigger file exists and whether a
 * promote request has arrived.  If either condition holds, request postmaster
 * to shut down walreceiver, wait for it to exit, and return true.
 */
static bool
CheckForStandbyTrigger(void)
{
	struct stat stat_buf;
	static bool triggered = false;

	if (triggered)
		return true;

	if (IsPromoteTriggered())
	{
		ereport(LOG,
				(errmsg("received promote request")));
		ShutdownWalRcv();
		ResetPromoteTriggered();
		triggered = true;
		return true;
	}

	if (TriggerFile == NULL)
		return false;

	if (stat(TriggerFile, &stat_buf) == 0)
	{
		ereport(LOG,
				(errmsg("trigger file found: %s", TriggerFile)));
		ShutdownWalRcv();
		unlink(TriggerFile);
		triggered = true;
		return true;
	}
	return false;
}

/*
 * Check to see if a promote request has arrived. Should be
 * called by postmaster after receiving SIGUSR1.
 */
bool
CheckPromoteSignal(void)
{
	struct stat stat_buf;

	if (stat(PROMOTE_SIGNAL_FILE, &stat_buf) == 0)
	{
		/*
		 * Since we are in a signal handler, it's not safe to elog. We
		 * silently ignore any error from unlink.
		 */
		unlink(PROMOTE_SIGNAL_FILE);
		return true;
	}
	return false;
}

/*
 * Wake up startup process to replay newly arrived WAL, or to notice that
 * failover has been requested.
 */
void
WakeupRecovery(void)
{
	SetLatch(&XLogCtl->recoveryWakeupLatch);
}

/*
 * Update the WalWriterSleeping flag.
 */
void
SetWalWriterSleeping(bool sleeping)
{
	/* use volatile pointer to prevent code rearrangement */
	volatile XLogCtlData *xlogctl = XLogCtl;

	SpinLockAcquire(&xlogctl->info_lck);
	xlogctl->WalWriterSleeping = sleeping;
	SpinLockRelease(&xlogctl->info_lck);
}