~drizzle-trunk/drizzle/development

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
/*   Innobase relational database engine; Copyright (C) 2001 Innobase Oy

     This program is free software; you can redistribute it and/or modify
     it under the terms of the GNU General Public License 2
     as published by the Free Software Foundation in June 1991.

     This program is distributed in the hope that it will be useful,
     but WITHOUT ANY WARRANTY; without even the implied warranty of
     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
     GNU General Public License for more details.

     You should have received a copy of the GNU General Public License 2
     along with this program (in file COPYING); if not, write to the Free
     Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */
/******************************************************
The database buffer buf_pool

(c) 1995 Innobase Oy

Created 11/5/1995 Heikki Tuuri
*******************************************************/

#include "buf0buf.h"

#ifdef UNIV_NONINL
#include "buf0buf.ic"
#endif

#include "mem0mem.h"
#include "btr0btr.h"
#include "fil0fil.h"
#include "lock0lock.h"
#include "btr0sea.h"
#include "ibuf0ibuf.h"
#include "dict0dict.h"
#include "log0recv.h"
#include "log0log.h"
#include "trx0undo.h"
#include "srv0srv.h"

/*
		IMPLEMENTATION OF THE BUFFER POOL
		=================================

Performance improvement:
------------------------
Thread scheduling in NT may be so slow that the OS wait mechanism should
not be used even in waiting for disk reads to complete.
Rather, we should put waiting query threads to the queue of
waiting jobs, and let the OS thread do something useful while the i/o
is processed. In this way we could remove most OS thread switches in
an i/o-intensive benchmark like TPC-C.

A possibility is to put a user space thread library between the database
and NT. User space thread libraries might be very fast.

SQL Server 7.0 can be configured to use 'fibers' which are lightweight
threads in NT. These should be studied.

		Buffer frames and blocks
		------------------------
Following the terminology of Gray and Reuter, we call the memory
blocks where file pages are loaded buffer frames. For each buffer
frame there is a control block, or shortly, a block, in the buffer
control array. The control info which does not need to be stored
in the file along with the file page, resides in the control block.

		Buffer pool struct
		------------------
The buffer buf_pool contains a single mutex which protects all the
control data structures of the buf_pool. The content of a buffer frame is
protected by a separate read-write lock in its control block, though.
These locks can be locked and unlocked without owning the buf_pool mutex.
The OS events in the buf_pool struct can be waited for without owning the
buf_pool mutex.

The buf_pool mutex is a hot-spot in main memory, causing a lot of
memory bus traffic on multiprocessor systems when processors
alternately access the mutex. On our Pentium, the mutex is accessed
maybe every 10 microseconds. We gave up the solution to have mutexes
for each control block, for instance, because it seemed to be
complicated.

A solution to reduce mutex contention of the buf_pool mutex is to
create a separate mutex for the page hash table. On Pentium,
accessing the hash table takes 2 microseconds, about half
of the total buf_pool mutex hold time.

		Control blocks
		--------------

The control block contains, for instance, the bufferfix count
which is incremented when a thread wants a file page to be fixed
in a buffer frame. The bufferfix operation does not lock the
contents of the frame, however. For this purpose, the control
block contains a read-write lock.

The buffer frames have to be aligned so that the start memory
address of a frame is divisible by the universal page size, which
is a power of two.

We intend to make the buffer buf_pool size on-line reconfigurable,
that is, the buf_pool size can be changed without closing the database.
Then the database administarator may adjust it to be bigger
at night, for example. The control block array must
contain enough control blocks for the maximum buffer buf_pool size
which is used in the particular database.
If the buf_pool size is cut, we exploit the virtual memory mechanism of
the OS, and just refrain from using frames at high addresses. Then the OS
can swap them to disk.

The control blocks containing file pages are put to a hash table
according to the file address of the page.
We could speed up the access to an individual page by using
"pointer swizzling": we could replace the page references on
non-leaf index pages by direct pointers to the page, if it exists
in the buf_pool. We could make a separate hash table where we could
chain all the page references in non-leaf pages residing in the buf_pool,
using the page reference as the hash key,
and at the time of reading of a page update the pointers accordingly.
Drawbacks of this solution are added complexity and,
possibly, extra space required on non-leaf pages for memory pointers.
A simpler solution is just to speed up the hash table mechanism
in the database, using tables whose size is a power of 2.

		Lists of blocks
		---------------

There are several lists of control blocks. The free list contains
blocks which are currently not used.

The LRU-list contains all the blocks holding a file page
except those for which the bufferfix count is non-zero.
The pages are in the LRU list roughly in the order of the last
access to the page, so that the oldest pages are at the end of the
list. We also keep a pointer to near the end of the LRU list,
which we can use when we want to artificially age a page in the
buf_pool. This is used if we know that some page is not needed
again for some time: we insert the block right after the pointer,
causing it to be replaced sooner than would noramlly be the case.
Currently this aging mechanism is used for read-ahead mechanism
of pages, and it can also be used when there is a scan of a full
table which cannot fit in the memory. Putting the pages near the
of the LRU list, we make sure that most of the buf_pool stays in the
main memory, undisturbed.

The chain of modified blocks contains the blocks
holding file pages that have been modified in the memory
but not written to disk yet. The block with the oldest modification
which has not yet been written to disk is at the end of the chain.

		Loading a file page
		-------------------

First, a victim block for replacement has to be found in the
buf_pool. It is taken from the free list or searched for from the
end of the LRU-list. An exclusive lock is reserved for the frame,
the io_fix field is set in the block fixing the block in buf_pool,
and the io-operation for loading the page is queued. The io-handler thread
releases the X-lock on the frame and resets the io_fix field
when the io operation completes.

A thread may request the above operation using the function
buf_page_get(). It may then continue to request a lock on the frame.
The lock is granted when the io-handler releases the x-lock.

		Read-ahead
		----------

The read-ahead mechanism is intended to be intelligent and
isolated from the semantically higher levels of the database
index management. From the higher level we only need the
information if a file page has a natural successor or
predecessor page. On the leaf level of a B-tree index,
these are the next and previous pages in the natural
order of the pages.

Let us first explain the read-ahead mechanism when the leafs
of a B-tree are scanned in an ascending or descending order.
When a read page is the first time referenced in the buf_pool,
the buffer manager checks if it is at the border of a so-called
linear read-ahead area. The tablespace is divided into these
areas of size 64 blocks, for example. So if the page is at the
border of such an area, the read-ahead mechanism checks if
all the other blocks in the area have been accessed in an
ascending or descending order. If this is the case, the system
looks at the natural successor or predecessor of the page,
checks if that is at the border of another area, and in this case
issues read-requests for all the pages in that area. Maybe
we could relax the condition that all the pages in the area
have to be accessed: if data is deleted from a table, there may
appear holes of unused pages in the area.

A different read-ahead mechanism is used when there appears
to be a random access pattern to a file.
If a new page is referenced in the buf_pool, and several pages
of its random access area (for instance, 32 consecutive pages
in a tablespace) have recently been referenced, we may predict
that the whole area may be needed in the near future, and issue
the read requests for the whole area.

		AWE implementation
		------------------

By a 'block' we mean the buffer header of type buf_block_t. By a 'page'
we mean the physical 16 kB memory area allocated from RAM for that block.
By a 'frame' we mean a 16 kB area in the virtual address space of the
process, in the frame_mem of buf_pool.

We can map pages to the frames of the buffer pool.

1) A buffer block allocated to use as a non-data page, e.g., to the lock
table, is always mapped to a frame.
2) A bufferfixed or io-fixed data page is always mapped to a frame.
3) When we need to map a block to frame, we look from the list
awe_LRU_free_mapped and try to unmap its last block, but note that
bufferfixed or io-fixed pages cannot be unmapped.
4) For every frame in the buffer pool there is always a block whose page is
mapped to it. When we create the buffer pool, we map the first elements
in the free list to the frames.
5) When we have AWE enabled, we disable adaptive hash indexes.
*/

/* Value in microseconds */
static const int WAIT_FOR_READ	= 20000;

buf_pool_t*	buf_pool = NULL; /* The buffer buf_pool of the database */

#ifdef UNIV_DEBUG
ulint		buf_dbg_counter	= 0; /* This is used to insert validation
					operations in excution in the
					debug version */
ibool		buf_debug_prints = FALSE; /* If this is set TRUE,
					the program prints info whenever
					read-ahead or flush occurs */
#endif /* UNIV_DEBUG */
/************************************************************************
Calculates a page checksum which is stored to the page when it is written
to a file. Note that we must be careful to calculate the same value on
32-bit and 64-bit architectures. */

ulint
buf_calc_page_new_checksum(
/*=======================*/
			/* out: checksum */
	byte*	 page)	/* in: buffer page */
{
	ulint checksum;

	/* Since the field FIL_PAGE_FILE_FLUSH_LSN, and in versions <= 4.1.x
	..._ARCH_LOG_NO, are written outside the buffer pool to the first
	pages of data files, we have to skip them in the page checksum
	calculation.
	We must also skip the field FIL_PAGE_SPACE_OR_CHKSUM where the
	checksum is stored, and also the last 8 bytes of page because
	there we store the old formula checksum. */

	checksum = ut_fold_binary(page + FIL_PAGE_OFFSET,
				  FIL_PAGE_FILE_FLUSH_LSN - FIL_PAGE_OFFSET)
		+ ut_fold_binary(page + FIL_PAGE_DATA,
				 UNIV_PAGE_SIZE - FIL_PAGE_DATA
				 - FIL_PAGE_END_LSN_OLD_CHKSUM);
	checksum = checksum & 0xFFFFFFFFUL;

	return(checksum);
}

/************************************************************************
In versions < 4.0.14 and < 4.1.1 there was a bug that the checksum only
looked at the first few bytes of the page. This calculates that old
checksum.
NOTE: we must first store the new formula checksum to
FIL_PAGE_SPACE_OR_CHKSUM before calculating and storing this old checksum
because this takes that field as an input! */

ulint
buf_calc_page_old_checksum(
/*=======================*/
			/* out: checksum */
	byte*	 page)	/* in: buffer page */
{
	ulint checksum;

	checksum = ut_fold_binary(page, FIL_PAGE_FILE_FLUSH_LSN);

	checksum = checksum & 0xFFFFFFFFUL;

	return(checksum);
}

/************************************************************************
Checks if a page is corrupt. */

ibool
buf_page_is_corrupted(
/*==================*/
				/* out: TRUE if corrupted */
	byte*	read_buf)	/* in: a database page */
{
	ulint	checksum;
	ulint	old_checksum;
	ulint	checksum_field;
	ulint	old_checksum_field;
#ifndef UNIV_HOTBACKUP
	dulint	current_lsn;
#endif
	if (mach_read_from_4(read_buf + FIL_PAGE_LSN + 4)
	    != mach_read_from_4(read_buf + UNIV_PAGE_SIZE
				- FIL_PAGE_END_LSN_OLD_CHKSUM + 4)) {

		/* Stored log sequence numbers at the start and the end
		of page do not match */

		return(TRUE);
	}

#ifndef UNIV_HOTBACKUP
	if (recv_lsn_checks_on && log_peek_lsn(&current_lsn)) {
		if (ut_dulint_cmp(current_lsn,
				  mach_read_from_8(read_buf + FIL_PAGE_LSN))
		    < 0) {
			ut_print_timestamp(stderr);

			fprintf(stderr,
				"  InnoDB: Error: page %lu log sequence number"
				" %lu %lu\n"
				"InnoDB: is in the future! Current system "
				"log sequence number %lu %lu.\n"
				"InnoDB: Your database may be corrupt or "
				"you may have copied the InnoDB\n"
				"InnoDB: tablespace but not the InnoDB "
				"log files. See\n"
				"InnoDB: http://dev.mysql.com/doc/refman/"
				"5.1/en/forcing-recovery.html\n"
				"InnoDB: for more information.\n",
				(ulong) mach_read_from_4(read_buf
							 + FIL_PAGE_OFFSET),
				(ulong) ut_dulint_get_high
				(mach_read_from_8(read_buf + FIL_PAGE_LSN)),
				(ulong) ut_dulint_get_low
				(mach_read_from_8(read_buf + FIL_PAGE_LSN)),
				(ulong) ut_dulint_get_high(current_lsn),
				(ulong) ut_dulint_get_low(current_lsn));
		}
	}
#endif

	/* If we use checksums validation, make additional check before
	returning TRUE to ensure that the checksum is not equal to
	BUF_NO_CHECKSUM_MAGIC which might be stored by InnoDB with checksums
	disabled. Otherwise, skip checksum calculation and return FALSE */

	if (srv_use_checksums) {
		old_checksum = buf_calc_page_old_checksum(read_buf);

		old_checksum_field = mach_read_from_4(
			read_buf + UNIV_PAGE_SIZE
			- FIL_PAGE_END_LSN_OLD_CHKSUM);

		/* There are 2 valid formulas for old_checksum_field:

		1. Very old versions of InnoDB only stored 8 byte lsn to the
		start and the end of the page.

		2. Newer InnoDB versions store the old formula checksum
		there. */

		if (old_checksum_field != mach_read_from_4(read_buf
							   + FIL_PAGE_LSN)
		    && old_checksum_field != old_checksum
		    && old_checksum_field != BUF_NO_CHECKSUM_MAGIC) {

			return(TRUE);
		}

		checksum = buf_calc_page_new_checksum(read_buf);
		checksum_field = mach_read_from_4(read_buf
						  + FIL_PAGE_SPACE_OR_CHKSUM);

		/* InnoDB versions < 4.0.14 and < 4.1.1 stored the space id
		(always equal to 0), to FIL_PAGE_SPACE_SPACE_OR_CHKSUM */

		if (checksum_field != 0 && checksum_field != checksum
		    && checksum_field != BUF_NO_CHECKSUM_MAGIC) {

			return(TRUE);
		}
	}

	return(FALSE);
}

/************************************************************************
Prints a page to stderr. */

void
buf_page_print(
/*===========*/
	byte*	read_buf)	/* in: a database page */
{
	dict_index_t*	index;
	ulint		checksum;
	ulint		old_checksum;

	ut_print_timestamp(stderr);
	fprintf(stderr, "  InnoDB: Page dump in ascii and hex (%lu bytes):\n",
		(ulint)UNIV_PAGE_SIZE);
	ut_print_buf(stderr, read_buf, UNIV_PAGE_SIZE);
	fputs("InnoDB: End of page dump\n", stderr);

	checksum = srv_use_checksums
		? buf_calc_page_new_checksum(read_buf) : BUF_NO_CHECKSUM_MAGIC;
	old_checksum = srv_use_checksums
		? buf_calc_page_old_checksum(read_buf) : BUF_NO_CHECKSUM_MAGIC;

	ut_print_timestamp(stderr);
	fprintf(stderr,
		"  InnoDB: Page checksum %lu, prior-to-4.0.14-form"
		" checksum %lu\n"
		"InnoDB: stored checksum %lu, prior-to-4.0.14-form"
		" stored checksum %lu\n"
		"InnoDB: Page lsn %lu %lu, low 4 bytes of lsn"
		" at page end %lu\n"
		"InnoDB: Page number (if stored to page already) %lu,\n"
		"InnoDB: space id (if created with >= MySQL-4.1.1"
		" and stored already) %lu\n",
		(ulong) checksum, (ulong) old_checksum,
		(ulong) mach_read_from_4(read_buf + FIL_PAGE_SPACE_OR_CHKSUM),
		(ulong) mach_read_from_4(read_buf + UNIV_PAGE_SIZE
					 - FIL_PAGE_END_LSN_OLD_CHKSUM),
		(ulong) mach_read_from_4(read_buf + FIL_PAGE_LSN),
		(ulong) mach_read_from_4(read_buf + FIL_PAGE_LSN + 4),
		(ulong) mach_read_from_4(read_buf + UNIV_PAGE_SIZE
					 - FIL_PAGE_END_LSN_OLD_CHKSUM + 4),
		(ulong) mach_read_from_4(read_buf + FIL_PAGE_OFFSET),
		(ulong) mach_read_from_4(read_buf
					 + FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID));

	if (mach_read_from_2(read_buf + TRX_UNDO_PAGE_HDR + TRX_UNDO_PAGE_TYPE)
	    == TRX_UNDO_INSERT) {
		fprintf(stderr,
			"InnoDB: Page may be an insert undo log page\n");
	} else if (mach_read_from_2(read_buf + TRX_UNDO_PAGE_HDR
				    + TRX_UNDO_PAGE_TYPE)
		   == TRX_UNDO_UPDATE) {
		fprintf(stderr,
			"InnoDB: Page may be an update undo log page\n");
	}

	switch (fil_page_get_type(read_buf)) {
	case FIL_PAGE_INDEX:
		fprintf(stderr,
			"InnoDB: Page may be an index page where"
			" index id is %lu %lu\n",
			(ulong) ut_dulint_get_high
			(btr_page_get_index_id(read_buf)),
			(ulong) ut_dulint_get_low
			(btr_page_get_index_id(read_buf)));

		/* If the code is in ibbackup, dict_sys may be uninitialized,
		i.e., NULL */

		if (dict_sys != NULL) {

			index = dict_index_find_on_id_low(
				btr_page_get_index_id(read_buf));
			if (index) {
				fputs("InnoDB: (", stderr);
				dict_index_name_print(stderr, NULL, index);
				fputs(")\n", stderr);
			}
		}
		break;
	case FIL_PAGE_INODE:
		fputs("InnoDB: Page may be an 'inode' page\n", stderr);
		break;
	case FIL_PAGE_IBUF_FREE_LIST:
		fputs("InnoDB: Page may be an insert buffer free list page\n",
		      stderr);
		break;
	case FIL_PAGE_TYPE_ALLOCATED:
		fputs("InnoDB: Page may be a freshly allocated page\n",
		      stderr);
		break;
	case FIL_PAGE_IBUF_BITMAP:
		fputs("InnoDB: Page may be an insert buffer bitmap page\n",
		      stderr);
		break;
	case FIL_PAGE_TYPE_SYS:
		fputs("InnoDB: Page may be a system page\n",
		      stderr);
		break;
	case FIL_PAGE_TYPE_TRX_SYS:
		fputs("InnoDB: Page may be a transaction system page\n",
		      stderr);
		break;
	case FIL_PAGE_TYPE_FSP_HDR:
		fputs("InnoDB: Page may be a file space header page\n",
		      stderr);
		break;
	case FIL_PAGE_TYPE_XDES:
		fputs("InnoDB: Page may be an extent descriptor page\n",
		      stderr);
		break;
	case FIL_PAGE_TYPE_BLOB:
		fputs("InnoDB: Page may be a BLOB page\n",
		      stderr);
		break;
	}
}

/************************************************************************
Initializes a buffer control block when the buf_pool is created. */
static
void
buf_block_init(
/*===========*/
	buf_block_t*	block,	/* in: pointer to control block */
	byte*		frame)	/* in: pointer to buffer frame, or NULL if in
				the case of AWE there is no frame */
{
	block->magic_n = 0;

	block->state = BUF_BLOCK_NOT_USED;

	block->frame = frame;

	block->awe_info = NULL;

	block->buf_fix_count = 0;
	block->io_fix = 0;

	block->modify_clock = ut_dulint_zero;

	block->file_page_was_freed = FALSE;

	block->check_index_page_at_flush = FALSE;
	block->index = NULL;

	block->in_free_list = FALSE;
	block->in_LRU_list = FALSE;

	block->n_pointers = 0;

	mutex_create(&block->mutex, SYNC_BUF_BLOCK);

	rw_lock_create(&block->lock, SYNC_LEVEL_VARYING);
	ut_ad(rw_lock_validate(&(block->lock)));

#ifdef UNIV_SYNC_DEBUG
	rw_lock_create(&block->debug_latch, SYNC_NO_ORDER_CHECK);
#endif /* UNIV_SYNC_DEBUG */
}

/************************************************************************
Creates the buffer pool. */

buf_pool_t*
buf_pool_init(
/*==========*/
				/* out, own: buf_pool object, NULL if not
				enough memory or error */
	ulint	max_size,	/* in: maximum size of the buf_pool in
				blocks */
	ulint	curr_size,	/* in: current size to use, must be <=
				max_size, currently must be equal to
				max_size */
	ulint	n_frames)	/* in: number of frames; if AWE is used,
				this is the size of the address space window
				where physical memory pages are mapped; if
				AWE is not used then this must be the same
				as max_size */
{
	byte*		frame;
	ulint		i;
	buf_block_t*	block;

	ut_a(max_size == curr_size);
	ut_a(srv_use_awe || n_frames == max_size);

	if (n_frames > curr_size) {
		fprintf(stderr,
			"InnoDB: AWE: Error: you must specify in my.cnf"
			" .._awe_mem_mb larger\n"
			"InnoDB: than .._buffer_pool_size. Now the former"
			" is %lu pages,\n"
			"InnoDB: the latter %lu pages.\n",
			(ulong) curr_size, (ulong) n_frames);

		return(NULL);
	}

	buf_pool = mem_alloc(sizeof(buf_pool_t));

	/* 1. Initialize general fields
	---------------------------- */
	mutex_create(&buf_pool->mutex, SYNC_BUF_POOL);

	mutex_enter(&(buf_pool->mutex));

	if (srv_use_awe) {
		/*----------------------------------------*/
		/* Allocate the virtual address space window, i.e., the
		buffer pool frames */

		buf_pool->frame_mem = os_awe_allocate_virtual_mem_window(
			UNIV_PAGE_SIZE * (n_frames + 1));

		/* Allocate the physical memory for AWE and the AWE info array
		for buf_pool */

		if ((curr_size % ((1024 * 1024) / UNIV_PAGE_SIZE)) != 0) {

			fprintf(stderr,
				"InnoDB: AWE: Error: physical memory must be"
				" allocated in full megabytes.\n"
				"InnoDB: Trying to allocate %lu"
				" database pages.\n",
				(ulong) curr_size);

			return(NULL);
		}

		if (!os_awe_allocate_physical_mem(&(buf_pool->awe_info),
						  curr_size
						  / ((1024 * 1024)
						     / UNIV_PAGE_SIZE))) {

			return(NULL);
		}
		/*----------------------------------------*/
	} else {
		buf_pool->frame_mem = os_mem_alloc_large(
			UNIV_PAGE_SIZE * (n_frames + 1), TRUE, FALSE);
	}

	if (buf_pool->frame_mem == NULL) {

		return(NULL);
	}

	buf_pool->blocks = ut_malloc(sizeof(buf_block_t) * max_size);

	if (buf_pool->blocks == NULL) {

		return(NULL);
	}

	buf_pool->max_size = max_size;
	buf_pool->curr_size = curr_size;

	buf_pool->n_frames = n_frames;

	/* Align pointer to the first frame */

	frame = ut_align(buf_pool->frame_mem, UNIV_PAGE_SIZE);

	buf_pool->frame_zero = frame;
	buf_pool->high_end = frame + UNIV_PAGE_SIZE * n_frames;

	if (srv_use_awe) {
		/*----------------------------------------*/
		/* Map an initial part of the allocated physical memory to
		the window */

		os_awe_map_physical_mem_to_window(buf_pool->frame_zero,
						  n_frames
						  * (UNIV_PAGE_SIZE
						     / OS_AWE_X86_PAGE_SIZE),
						  buf_pool->awe_info);
		/*----------------------------------------*/
	}

	buf_pool->blocks_of_frames = ut_malloc(sizeof(void*) * n_frames);

	if (buf_pool->blocks_of_frames == NULL) {

		return(NULL);
	}

	/* Init block structs and assign frames for them; in the case of
	AWE there are less frames than blocks. Then we assign the frames
	to the first blocks (we already mapped the memory above). We also
	init the awe_info for every block. */

	for (i = 0; i < max_size; i++) {

		block = buf_pool_get_nth_block(buf_pool, i);

		if (i < n_frames) {
			frame = buf_pool->frame_zero + i * UNIV_PAGE_SIZE;
			*(buf_pool->blocks_of_frames + i) = block;
		} else {
			frame = NULL;
		}

		buf_block_init(block, frame);

		if (srv_use_awe) {
			/*----------------------------------------*/
			block->awe_info = buf_pool->awe_info
				+ i * (UNIV_PAGE_SIZE / OS_AWE_X86_PAGE_SIZE);
			/*----------------------------------------*/
		}
	}

	buf_pool->page_hash = hash_create(2 * max_size);

	buf_pool->n_pend_reads = 0;

	buf_pool->last_printout_time = time(NULL);

	buf_pool->n_pages_read = 0;
	buf_pool->n_pages_written = 0;
	buf_pool->n_pages_created = 0;
	buf_pool->n_pages_awe_remapped = 0;

	buf_pool->n_page_gets = 0;
	buf_pool->n_page_gets_old = 0;
	buf_pool->n_pages_read_old = 0;
	buf_pool->n_pages_written_old = 0;
	buf_pool->n_pages_created_old = 0;
	buf_pool->n_pages_awe_remapped_old = 0;

	/* 2. Initialize flushing fields
	---------------------------- */
	UT_LIST_INIT(buf_pool->flush_list);

	for (i = BUF_FLUSH_LRU; i <= BUF_FLUSH_LIST; i++) {
		buf_pool->n_flush[i] = 0;
		buf_pool->init_flush[i] = FALSE;
		buf_pool->no_flush[i] = os_event_create(NULL);
	}

	buf_pool->LRU_flush_ended = 0;

	buf_pool->ulint_clock = 1;
	buf_pool->freed_page_clock = 0;

	/* 3. Initialize LRU fields
	---------------------------- */
	UT_LIST_INIT(buf_pool->LRU);

	buf_pool->LRU_old = NULL;

	UT_LIST_INIT(buf_pool->awe_LRU_free_mapped);

	/* Add control blocks to the free list */
	UT_LIST_INIT(buf_pool->free);

	for (i = 0; i < curr_size; i++) {

		block = buf_pool_get_nth_block(buf_pool, i);

		if (block->frame) {
			/* Wipe contents of frame to eliminate a Purify
			warning */

#ifdef HAVE_purify
			memset(block->frame, '\0', UNIV_PAGE_SIZE);
#endif
			if (srv_use_awe) {
				/* Add to the list of blocks mapped to
				frames */

				UT_LIST_ADD_LAST(awe_LRU_free_mapped,
						 buf_pool->awe_LRU_free_mapped,
						 block);
			}
		}

		UT_LIST_ADD_LAST(free, buf_pool->free, block);
		block->in_free_list = TRUE;
	}

	mutex_exit(&(buf_pool->mutex));

	if (srv_use_adaptive_hash_indexes) {
		btr_search_sys_create(curr_size * UNIV_PAGE_SIZE
				      / sizeof(void*) / 64);
	} else {
		/* Create only a small dummy system */
		btr_search_sys_create(1000);
	}

	return(buf_pool);
}

/************************************************************************
Maps the page of block to a frame, if not mapped yet. Unmaps some page
from the end of the awe_LRU_free_mapped. */

void
buf_awe_map_page_to_frame(
/*======================*/
	buf_block_t*	block,		/* in: block whose page should be
					mapped to a frame */
	ibool		add_to_mapped_list) /* in: TRUE if we in the case
					we need to map the page should also
					add the block to the
					awe_LRU_free_mapped list */
{
	buf_block_t*	bck;

	ut_ad(mutex_own(&(buf_pool->mutex)));
	ut_ad(block);

	if (block->frame) {

		return;
	}

	/* Scan awe_LRU_free_mapped from the end and try to find a block
	which is not bufferfixed or io-fixed */

	bck = UT_LIST_GET_LAST(buf_pool->awe_LRU_free_mapped);

	while (bck) {
		ibool skip;

		mutex_enter(&bck->mutex);

		skip = (bck->state == BUF_BLOCK_FILE_PAGE
			&& (bck->buf_fix_count != 0 || bck->io_fix != 0));

		if (skip) {
			mutex_exit(&bck->mutex);

			/* We have to skip this */
			bck = UT_LIST_GET_PREV(awe_LRU_free_mapped, bck);
		} else {
			/* We can map block to the frame of bck */

			os_awe_map_physical_mem_to_window(
				bck->frame,
				UNIV_PAGE_SIZE / OS_AWE_X86_PAGE_SIZE,
				block->awe_info);

			block->frame = bck->frame;

			*(buf_pool->blocks_of_frames
			  + (((ulint)(block->frame
				      - buf_pool->frame_zero))
			     >> UNIV_PAGE_SIZE_SHIFT))
				= block;

			bck->frame = NULL;
			UT_LIST_REMOVE(awe_LRU_free_mapped,
				       buf_pool->awe_LRU_free_mapped,
				       bck);

			if (add_to_mapped_list) {
				UT_LIST_ADD_FIRST(
					awe_LRU_free_mapped,
					buf_pool->awe_LRU_free_mapped,
					block);
			}

			buf_pool->n_pages_awe_remapped++;

			mutex_exit(&bck->mutex);

			return;
		}
	}

	fprintf(stderr,
		"InnoDB: AWE: Fatal error: cannot find a page to unmap\n"
		"InnoDB: awe_LRU_free_mapped list length %lu\n",
		(ulong) UT_LIST_GET_LEN(buf_pool->awe_LRU_free_mapped));

	ut_a(0);
}

/************************************************************************
Allocates a buffer block. */
UNIV_INLINE
buf_block_t*
buf_block_alloc(void)
/*=================*/
				/* out, own: the allocated block; also if AWE
				is used it is guaranteed that the page is
				mapped to a frame */
{
	buf_block_t*	block;

	block = buf_LRU_get_free_block();

	return(block);
}

/************************************************************************
Moves to the block to the start of the LRU list if there is a danger
that the block would drift out of the buffer pool. */
UNIV_INLINE
void
buf_block_make_young(
/*=================*/
	buf_block_t*	block)	/* in: block to make younger */
{
	ut_ad(!mutex_own(&(buf_pool->mutex)));

	/* Note that we read freed_page_clock's without holding any mutex:
	this is allowed since the result is used only in heuristics */

	if (buf_block_peek_if_too_old(block)) {

		mutex_enter(&buf_pool->mutex);
		/* There has been freeing activity in the LRU list:
		best to move to the head of the LRU list */

		buf_LRU_make_block_young(block);
		mutex_exit(&buf_pool->mutex);
	}
}

/************************************************************************
Moves a page to the start of the buffer pool LRU list. This high-level
function can be used to prevent an important page from from slipping out of
the buffer pool. */

void
buf_page_make_young(
/*================*/
	buf_frame_t*	frame)	/* in: buffer frame of a file page */
{
	buf_block_t*	block;

	mutex_enter(&(buf_pool->mutex));

	block = buf_block_align(frame);

	ut_a(block->state == BUF_BLOCK_FILE_PAGE);

	buf_LRU_make_block_young(block);

	mutex_exit(&(buf_pool->mutex));
}

/************************************************************************
Frees a buffer block which does not contain a file page. */
UNIV_INLINE
void
buf_block_free(
/*===========*/
	buf_block_t*	block)	/* in, own: block to be freed */
{
	mutex_enter(&(buf_pool->mutex));

	mutex_enter(&block->mutex);

	ut_a(block->state != BUF_BLOCK_FILE_PAGE);

	buf_LRU_block_free_non_file_page(block);

	mutex_exit(&block->mutex);

	mutex_exit(&(buf_pool->mutex));
}

/*************************************************************************
Allocates a buffer frame. */

buf_frame_t*
buf_frame_alloc(void)
/*=================*/
				/* out: buffer frame */
{
	return(buf_block_alloc()->frame);
}

/*************************************************************************
Frees a buffer frame which does not contain a file page. */

void
buf_frame_free(
/*===========*/
	buf_frame_t*	frame)	/* in: buffer frame */
{
	buf_block_free(buf_block_align(frame));
}

/************************************************************************
Returns the buffer control block if the page can be found in the buffer
pool. NOTE that it is possible that the page is not yet read
from disk, though. This is a very low-level function: use with care! */

buf_block_t*
buf_page_peek_block(
/*================*/
			/* out: control block if found from page hash table,
			otherwise NULL; NOTE that the page is not necessarily
			yet read from disk! */
	ulint	space,	/* in: space id */
	ulint	offset)	/* in: page number */
{
	buf_block_t*	block;

	mutex_enter_fast(&(buf_pool->mutex));

	block = buf_page_hash_get(space, offset);

	mutex_exit(&(buf_pool->mutex));

	return(block);
}

/************************************************************************
Resets the check_index_page_at_flush field of a page if found in the buffer
pool. */

void
buf_reset_check_index_page_at_flush(
/*================================*/
	ulint	space,	/* in: space id */
	ulint	offset)	/* in: page number */
{
	buf_block_t*	block;

	mutex_enter_fast(&(buf_pool->mutex));

	block = buf_page_hash_get(space, offset);

	if (block) {
		block->check_index_page_at_flush = FALSE;
	}

	mutex_exit(&(buf_pool->mutex));
}

/************************************************************************
Returns the current state of is_hashed of a page. FALSE if the page is
not in the pool. NOTE that this operation does not fix the page in the
pool if it is found there. */

ibool
buf_page_peek_if_search_hashed(
/*===========================*/
			/* out: TRUE if page hash index is built in search
			system */
	ulint	space,	/* in: space id */
	ulint	offset)	/* in: page number */
{
	buf_block_t*	block;
	ibool		is_hashed;

	mutex_enter_fast(&(buf_pool->mutex));

	block = buf_page_hash_get(space, offset);

	if (!block) {
		is_hashed = FALSE;
	} else {
		is_hashed = block->is_hashed;
	}

	mutex_exit(&(buf_pool->mutex));

	return(is_hashed);
}

/************************************************************************
Returns TRUE if the page can be found in the buffer pool hash table. NOTE
that it is possible that the page is not yet read from disk, though. */

ibool
buf_page_peek(
/*==========*/
			/* out: TRUE if found from page hash table,
			NOTE that the page is not necessarily yet read
			from disk! */
	ulint	space,	/* in: space id */
	ulint	offset)	/* in: page number */
{
	if (buf_page_peek_block(space, offset)) {

		return(TRUE);
	}

	return(FALSE);
}

/************************************************************************
Sets file_page_was_freed TRUE if the page is found in the buffer pool.
This function should be called when we free a file page and want the
debug version to check that it is not accessed any more unless
reallocated. */

buf_block_t*
buf_page_set_file_page_was_freed(
/*=============================*/
			/* out: control block if found from page hash table,
			otherwise NULL */
	ulint	space,	/* in: space id */
	ulint	offset)	/* in: page number */
{
	buf_block_t*	block;

	mutex_enter_fast(&(buf_pool->mutex));

	block = buf_page_hash_get(space, offset);

	if (block) {
		block->file_page_was_freed = TRUE;
	}

	mutex_exit(&(buf_pool->mutex));

	return(block);
}

/************************************************************************
Sets file_page_was_freed FALSE if the page is found in the buffer pool.
This function should be called when we free a file page and want the
debug version to check that it is not accessed any more unless
reallocated. */

buf_block_t*
buf_page_reset_file_page_was_freed(
/*===============================*/
			/* out: control block if found from page hash table,
			otherwise NULL */
	ulint	space,	/* in: space id */
	ulint	offset)	/* in: page number */
{
	buf_block_t*	block;

	mutex_enter_fast(&(buf_pool->mutex));

	block = buf_page_hash_get(space, offset);

	if (block) {
		block->file_page_was_freed = FALSE;
	}

	mutex_exit(&(buf_pool->mutex));

	return(block);
}

/************************************************************************
This is the general function used to get access to a database page. */

buf_frame_t*
buf_page_get_gen(
/*=============*/
				/* out: pointer to the frame or NULL */
	ulint		space,	/* in: space id */
	ulint		offset,	/* in: page number */
	ulint		rw_latch,/* in: RW_S_LATCH, RW_X_LATCH, RW_NO_LATCH */
	buf_frame_t*	guess,	/* in: guessed frame or NULL */
	ulint		mode,	/* in: BUF_GET, BUF_GET_IF_IN_POOL,
				BUF_GET_NO_LATCH, BUF_GET_NOWAIT */
	const char*	file,	/* in: file name */
	ulint		line,	/* in: line where called */
	mtr_t*		mtr)	/* in: mini-transaction */
{
	buf_block_t*	block;
	ibool		accessed;
	ulint		fix_type;
	ibool		success;
	ibool		must_read;

	ut_ad(mtr);
	ut_ad((rw_latch == RW_S_LATCH)
	      || (rw_latch == RW_X_LATCH)
	      || (rw_latch == RW_NO_LATCH));
	ut_ad((mode != BUF_GET_NO_LATCH) || (rw_latch == RW_NO_LATCH));
	ut_ad((mode == BUF_GET) || (mode == BUF_GET_IF_IN_POOL)
	      || (mode == BUF_GET_NO_LATCH) || (mode == BUF_GET_NOWAIT));
#ifndef UNIV_LOG_DEBUG
	ut_ad(!ibuf_inside() || ibuf_page(space, offset));
#endif
	buf_pool->n_page_gets++;
loop:
	block = NULL;
	mutex_enter_fast(&(buf_pool->mutex));

	if (guess) {
		block = buf_block_align(guess);

		if ((offset != block->offset) || (space != block->space)
		    || (block->state != BUF_BLOCK_FILE_PAGE)) {

			block = NULL;
		}
	}

	if (block == NULL) {
		block = buf_page_hash_get(space, offset);
	}

	if (block == NULL) {
		/* Page not in buf_pool: needs to be read from file */

		mutex_exit(&(buf_pool->mutex));

		if (mode == BUF_GET_IF_IN_POOL) {

			return(NULL);
		}

		buf_read_page(space, offset);

#ifdef UNIV_DEBUG
		buf_dbg_counter++;

		if (buf_dbg_counter % 37 == 0) {
			ut_ad(buf_validate());
		}
#endif
		goto loop;
	}

	mutex_enter(&block->mutex);

	ut_a(block->state == BUF_BLOCK_FILE_PAGE);

	must_read = FALSE;

	if (block->io_fix == BUF_IO_READ) {

		must_read = TRUE;

		if (mode == BUF_GET_IF_IN_POOL) {
			/* The page is only being read to buffer */
			mutex_exit(&buf_pool->mutex);
			mutex_exit(&block->mutex);

			return(NULL);
		}
	}

	/* If AWE is enabled and the page is not mapped to a frame, then
	map it */

	if (block->frame == NULL) {
		ut_a(srv_use_awe);

		/* We set second parameter TRUE because the block is in the
		LRU list and we must put it to awe_LRU_free_mapped list once
		mapped to a frame */

		buf_awe_map_page_to_frame(block, TRUE);
	}

#ifdef UNIV_SYNC_DEBUG
	buf_block_buf_fix_inc_debug(block, file, line);
#else
	buf_block_buf_fix_inc(block);
#endif
	mutex_exit(&buf_pool->mutex);

	/* Check if this is the first access to the page */

	accessed = block->accessed;

	block->accessed = TRUE;

	mutex_exit(&block->mutex);

	buf_block_make_young(block);

#ifdef UNIV_DEBUG_FILE_ACCESSES
	ut_a(block->file_page_was_freed == FALSE);
#endif

#ifdef UNIV_DEBUG
	buf_dbg_counter++;

	if (buf_dbg_counter % 5771 == 0) {
		ut_ad(buf_validate());
	}
#endif
	ut_ad(block->buf_fix_count > 0);
	ut_ad(block->state == BUF_BLOCK_FILE_PAGE);

	if (mode == BUF_GET_NOWAIT) {
		if (rw_latch == RW_S_LATCH) {
			success = rw_lock_s_lock_func_nowait(&(block->lock),
							     file, line);
			fix_type = MTR_MEMO_PAGE_S_FIX;
		} else {
			ut_ad(rw_latch == RW_X_LATCH);
			success = rw_lock_x_lock_func_nowait(&(block->lock),
							     file, line);
			fix_type = MTR_MEMO_PAGE_X_FIX;
		}

		if (!success) {
			mutex_enter(&block->mutex);

			block->buf_fix_count--;

			mutex_exit(&block->mutex);
#ifdef UNIV_SYNC_DEBUG
			rw_lock_s_unlock(&(block->debug_latch));
#endif

			return(NULL);
		}
	} else if (rw_latch == RW_NO_LATCH) {

		if (must_read) {
			/* Let us wait until the read operation
			completes */

			for (;;) {
				mutex_enter(&block->mutex);

				if (block->io_fix == BUF_IO_READ) {

					mutex_exit(&block->mutex);

					os_thread_sleep(WAIT_FOR_READ);
				} else {

					mutex_exit(&block->mutex);

					break;
				}
			}
		}

		fix_type = MTR_MEMO_BUF_FIX;
	} else if (rw_latch == RW_S_LATCH) {

		rw_lock_s_lock_func(&(block->lock), 0, file, line);

		fix_type = MTR_MEMO_PAGE_S_FIX;
	} else {
		rw_lock_x_lock_func(&(block->lock), 0, file, line);

		fix_type = MTR_MEMO_PAGE_X_FIX;
	}

	mtr_memo_push(mtr, block, fix_type);

	if (!accessed) {
		/* In the case of a first access, try to apply linear
		read-ahead */

		buf_read_ahead_linear(space, offset);
	}

#ifdef UNIV_IBUF_DEBUG
	ut_a(ibuf_count_get(block->space, block->offset) == 0);
#endif
	return(block->frame);
}

/************************************************************************
This is the general function used to get optimistic access to a database
page. */

ibool
buf_page_optimistic_get_func(
/*=========================*/
				/* out: TRUE if success */
	ulint		rw_latch,/* in: RW_S_LATCH, RW_X_LATCH */
	buf_block_t*	block,	/* in: guessed buffer block */
	buf_frame_t*	guess,	/* in: guessed frame; note that AWE may move
				frames */
	dulint		modify_clock,/* in: modify clock value if mode is
				..._GUESS_ON_CLOCK */
	const char*	file,	/* in: file name */
	ulint		line,	/* in: line where called */
	mtr_t*		mtr)	/* in: mini-transaction */
{
	ibool		accessed;
	ibool		success;
	ulint		fix_type;

	ut_ad(mtr && block);
	ut_ad((rw_latch == RW_S_LATCH) || (rw_latch == RW_X_LATCH));

	/* If AWE is used, block may have a different frame now, e.g., NULL */

	mutex_enter(&block->mutex);

	if (UNIV_UNLIKELY(block->state != BUF_BLOCK_FILE_PAGE)
	    || UNIV_UNLIKELY(block->frame != guess)) {

		mutex_exit(&block->mutex);

		return(FALSE);
	}

#ifdef UNIV_SYNC_DEBUG
	buf_block_buf_fix_inc_debug(block, file, line);
#else
	buf_block_buf_fix_inc(block);
#endif
	accessed = block->accessed;
	block->accessed = TRUE;

	mutex_exit(&block->mutex);

	buf_block_make_young(block);

	/* Check if this is the first access to the page */

	ut_ad(!ibuf_inside() || ibuf_page(block->space, block->offset));

	if (rw_latch == RW_S_LATCH) {
		success = rw_lock_s_lock_func_nowait(&(block->lock),
						     file, line);
		fix_type = MTR_MEMO_PAGE_S_FIX;
	} else {
		success = rw_lock_x_lock_func_nowait(&(block->lock),
						     file, line);
		fix_type = MTR_MEMO_PAGE_X_FIX;
	}

	if (UNIV_UNLIKELY(!success)) {
		mutex_enter(&block->mutex);

		block->buf_fix_count--;

		mutex_exit(&block->mutex);

#ifdef UNIV_SYNC_DEBUG
		rw_lock_s_unlock(&(block->debug_latch));
#endif
		return(FALSE);
	}

	if (UNIV_UNLIKELY(!UT_DULINT_EQ(modify_clock, block->modify_clock))) {
#ifdef UNIV_SYNC_DEBUG
		buf_page_dbg_add_level(block->frame, SYNC_NO_ORDER_CHECK);
#endif /* UNIV_SYNC_DEBUG */
		if (rw_latch == RW_S_LATCH) {
			rw_lock_s_unlock(&(block->lock));
		} else {
			rw_lock_x_unlock(&(block->lock));
		}

		mutex_enter(&block->mutex);

		block->buf_fix_count--;

		mutex_exit(&block->mutex);

#ifdef UNIV_SYNC_DEBUG
		rw_lock_s_unlock(&(block->debug_latch));
#endif
		return(FALSE);
	}

	mtr_memo_push(mtr, block, fix_type);

#ifdef UNIV_DEBUG
	buf_dbg_counter++;

	if (buf_dbg_counter % 5771 == 0) {
		ut_ad(buf_validate());
	}
#endif
	ut_ad(block->buf_fix_count > 0);
	ut_ad(block->state == BUF_BLOCK_FILE_PAGE);

#ifdef UNIV_DEBUG_FILE_ACCESSES
	ut_a(block->file_page_was_freed == FALSE);
#endif
	if (UNIV_UNLIKELY(!accessed)) {
		/* In the case of a first access, try to apply linear
		read-ahead */

		buf_read_ahead_linear(buf_frame_get_space_id(guess),
				      buf_frame_get_page_no(guess));
	}

#ifdef UNIV_IBUF_DEBUG
	ut_a(ibuf_count_get(block->space, block->offset) == 0);
#endif
	buf_pool->n_page_gets++;

	return(TRUE);
}

/************************************************************************
This is used to get access to a known database page, when no waiting can be
done. For example, if a search in an adaptive hash index leads us to this
frame. */

ibool
buf_page_get_known_nowait(
/*======================*/
				/* out: TRUE if success */
	ulint		rw_latch,/* in: RW_S_LATCH, RW_X_LATCH */
	buf_frame_t*	guess,	/* in: the known page frame */
	ulint		mode,	/* in: BUF_MAKE_YOUNG or BUF_KEEP_OLD */
	const char*	file,	/* in: file name */
	ulint		line,	/* in: line where called */
	mtr_t*		mtr)	/* in: mini-transaction */
{
	buf_block_t*	block;
	ibool		success;
	ulint		fix_type;

	ut_ad(mtr);
	ut_ad((rw_latch == RW_S_LATCH) || (rw_latch == RW_X_LATCH));

	block = buf_block_align(guess);

	mutex_enter(&block->mutex);

	if (block->state == BUF_BLOCK_REMOVE_HASH) {
		/* Another thread is just freeing the block from the LRU list
		of the buffer pool: do not try to access this page; this
		attempt to access the page can only come through the hash
		index because when the buffer block state is ..._REMOVE_HASH,
		we have already removed it from the page address hash table
		of the buffer pool. */

		mutex_exit(&block->mutex);

		return(FALSE);
	}

	ut_a(block->state == BUF_BLOCK_FILE_PAGE);

#ifdef UNIV_SYNC_DEBUG
	buf_block_buf_fix_inc_debug(block, file, line);
#else
	buf_block_buf_fix_inc(block);
#endif
	mutex_exit(&block->mutex);

	if (mode == BUF_MAKE_YOUNG) {
		buf_block_make_young(block);
	}

	ut_ad(!ibuf_inside() || (mode == BUF_KEEP_OLD));

	if (rw_latch == RW_S_LATCH) {
		success = rw_lock_s_lock_func_nowait(&(block->lock),
						     file, line);
		fix_type = MTR_MEMO_PAGE_S_FIX;
	} else {
		success = rw_lock_x_lock_func_nowait(&(block->lock),
						     file, line);
		fix_type = MTR_MEMO_PAGE_X_FIX;
	}

	if (!success) {
		mutex_enter(&block->mutex);

		block->buf_fix_count--;

		mutex_exit(&block->mutex);

#ifdef UNIV_SYNC_DEBUG
		rw_lock_s_unlock(&(block->debug_latch));
#endif

		return(FALSE);
	}

	mtr_memo_push(mtr, block, fix_type);

#ifdef UNIV_DEBUG
	buf_dbg_counter++;

	if (buf_dbg_counter % 5771 == 0) {
		ut_ad(buf_validate());
	}
#endif
	ut_ad(block->buf_fix_count > 0);
	ut_ad(block->state == BUF_BLOCK_FILE_PAGE);
#ifdef UNIV_DEBUG_FILE_ACCESSES
	ut_a(block->file_page_was_freed == FALSE);
#endif

#ifdef UNIV_IBUF_DEBUG
	ut_a((mode == BUF_KEEP_OLD)
	     || (ibuf_count_get(block->space, block->offset) == 0));
#endif
	buf_pool->n_page_gets++;

	return(TRUE);
}

/************************************************************************
Inits a page to the buffer buf_pool, for use in ibbackup --restore. */

void
buf_page_init_for_backup_restore(
/*=============================*/
	ulint		space,	/* in: space id */
	ulint		offset,	/* in: offset of the page within space
				in units of a page */
	buf_block_t*	block)	/* in: block to init */
{
	/* Set the state of the block */
	block->magic_n		= BUF_BLOCK_MAGIC_N;

	block->state		= BUF_BLOCK_FILE_PAGE;
	block->space		= space;
	block->offset		= offset;

	block->lock_hash_val	= 0;

	block->freed_page_clock = 0;

	block->newest_modification = ut_dulint_zero;
	block->oldest_modification = ut_dulint_zero;

	block->accessed		= FALSE;
	block->buf_fix_count	= 0;
	block->io_fix		= 0;

	block->n_hash_helps	= 0;
	block->is_hashed	= FALSE;
	block->n_fields		= 1;
	block->n_bytes		= 0;
	block->left_side	= TRUE;

	block->file_page_was_freed = FALSE;
}

/************************************************************************
Inits a page to the buffer buf_pool. */
static
void
buf_page_init(
/*==========*/
	ulint		space,	/* in: space id */
	ulint		offset,	/* in: offset of the page within space
				in units of a page */
	buf_block_t*	block)	/* in: block to init */
{

	ut_ad(mutex_own(&(buf_pool->mutex)));
	ut_ad(mutex_own(&(block->mutex)));
	ut_a(block->state != BUF_BLOCK_FILE_PAGE);

	/* Set the state of the block */
	block->magic_n		= BUF_BLOCK_MAGIC_N;

	block->state		= BUF_BLOCK_FILE_PAGE;
	block->space		= space;
	block->offset		= offset;

	block->check_index_page_at_flush = FALSE;
	block->index		= NULL;

	block->lock_hash_val	= lock_rec_hash(space, offset);

#ifdef UNIV_DEBUG_VALGRIND
	if (!space) {
		/* Silence valid Valgrind warnings about uninitialized
		data being written to data files.  There are some unused
		bytes on some pages that InnoDB does not initialize. */
		UNIV_MEM_VALID(block->frame, UNIV_PAGE_SIZE);
	}
#endif /* UNIV_DEBUG_VALGRIND */

	/* Insert into the hash table of file pages */

	if (buf_page_hash_get(space, offset)) {
		fprintf(stderr,
			"InnoDB: Error: page %lu %lu already found"
			" in the hash table\n",
			(ulong) space,
			(ulong) offset);
#ifdef UNIV_DEBUG
		buf_print();
		buf_LRU_print();
		buf_validate();
		buf_LRU_validate();
#endif /* UNIV_DEBUG */
		ut_a(0);
	}

	HASH_INSERT(buf_block_t, hash, buf_pool->page_hash,
		    buf_page_address_fold(space, offset), block);

	block->freed_page_clock = 0;

	block->newest_modification = ut_dulint_zero;
	block->oldest_modification = ut_dulint_zero;

	block->accessed		= FALSE;
	block->buf_fix_count	= 0;
	block->io_fix		= 0;

	block->n_hash_helps	= 0;
	block->is_hashed	= FALSE;
	block->n_fields		= 1;
	block->n_bytes		= 0;
	block->left_side	= TRUE;

	block->file_page_was_freed = FALSE;
}

/************************************************************************
Function which inits a page for read to the buffer buf_pool. If the page is
(1) already in buf_pool, or
(2) if we specify to read only ibuf pages and the page is not an ibuf page, or
(3) if the space is deleted or being deleted,
then this function does nothing.
Sets the io_fix flag to BUF_IO_READ and sets a non-recursive exclusive lock
on the buffer frame. The io-handler must take care that the flag is cleared
and the lock released later. This is one of the functions which perform the
state transition NOT_USED => FILE_PAGE to a block (the other is
buf_page_create). */

buf_block_t*
buf_page_init_for_read(
/*===================*/
				/* out: pointer to the block or NULL */
	ulint*		err,	/* out: DB_SUCCESS or DB_TABLESPACE_DELETED */
	ulint		mode,	/* in: BUF_READ_IBUF_PAGES_ONLY, ... */
	ulint		space,	/* in: space id */
	ib_longlong	tablespace_version,/* in: prevents reading from a wrong
				version of the tablespace in case we have done
				DISCARD + IMPORT */
	ulint		offset)	/* in: page number */
{
	buf_block_t*	block;
	mtr_t		mtr;

	ut_ad(buf_pool);

	*err = DB_SUCCESS;

	if (mode == BUF_READ_IBUF_PAGES_ONLY) {
		/* It is a read-ahead within an ibuf routine */

		ut_ad(!ibuf_bitmap_page(offset));
		ut_ad(ibuf_inside());

		mtr_start(&mtr);

		if (!ibuf_page_low(space, offset, &mtr)) {

			mtr_commit(&mtr);

			return(NULL);
		}
	} else {
		ut_ad(mode == BUF_READ_ANY_PAGE);
	}

	block = buf_block_alloc();

	ut_a(block);

	mutex_enter(&(buf_pool->mutex));
	mutex_enter(&block->mutex);

	if (fil_tablespace_deleted_or_being_deleted_in_mem(
		    space, tablespace_version)) {
		*err = DB_TABLESPACE_DELETED;
	}

	if (*err == DB_TABLESPACE_DELETED
	    || NULL != buf_page_hash_get(space, offset)) {

		/* The page belongs to a space which has been
		deleted or is being deleted, or the page is
		already in buf_pool, return */

		mutex_exit(&block->mutex);
		mutex_exit(&(buf_pool->mutex));

		buf_block_free(block);

		if (mode == BUF_READ_IBUF_PAGES_ONLY) {

			mtr_commit(&mtr);
		}

		return(NULL);
	}

	ut_ad(block);

	buf_page_init(space, offset, block);

	/* The block must be put to the LRU list, to the old blocks */

	buf_LRU_add_block(block, TRUE);		/* TRUE == to old blocks */

	block->io_fix = BUF_IO_READ;

	buf_pool->n_pend_reads++;

	/* We set a pass-type x-lock on the frame because then the same
	thread which called for the read operation (and is running now at
	this point of code) can wait for the read to complete by waiting
	for the x-lock on the frame; if the x-lock were recursive, the
	same thread would illegally get the x-lock before the page read
	is completed. The x-lock is cleared by the io-handler thread. */

	rw_lock_x_lock_gen(&(block->lock), BUF_IO_READ);

	mutex_exit(&block->mutex);
	mutex_exit(&(buf_pool->mutex));

	if (mode == BUF_READ_IBUF_PAGES_ONLY) {

		mtr_commit(&mtr);
	}

	return(block);
}

/************************************************************************
Initializes a page to the buffer buf_pool. The page is usually not read
from a file even if it cannot be found in the buffer buf_pool. This is one
of the functions which perform to a block a state transition NOT_USED =>
FILE_PAGE (the other is buf_page_init_for_read above). */

buf_frame_t*
buf_page_create(
/*============*/
			/* out: pointer to the frame, page bufferfixed */
	ulint	space,	/* in: space id */
	ulint	offset,	/* in: offset of the page within space in units of
			a page */
	mtr_t*	mtr)	/* in: mini-transaction handle */
{
	buf_frame_t*	frame;
	buf_block_t*	block;
	buf_block_t*	free_block	= NULL;

	ut_ad(mtr);

	free_block = buf_LRU_get_free_block();

	mutex_enter(&(buf_pool->mutex));

	block = buf_page_hash_get(space, offset);

	if (block != NULL) {
#ifdef UNIV_IBUF_DEBUG
		ut_a(ibuf_count_get(block->space, block->offset) == 0);
#endif
		block->file_page_was_freed = FALSE;

		/* Page can be found in buf_pool */
		mutex_exit(&(buf_pool->mutex));

		buf_block_free(free_block);

		frame = buf_page_get_with_no_latch(space, offset, mtr);

		return(frame);
	}

	/* If we get here, the page was not in buf_pool: init it there */

#ifdef UNIV_DEBUG
	if (buf_debug_prints) {
		fprintf(stderr, "Creating space %lu page %lu to buffer\n",
			(ulong) space, (ulong) offset);
	}
#endif /* UNIV_DEBUG */

	block = free_block;

	mutex_enter(&block->mutex);

	buf_page_init(space, offset, block);

	/* The block must be put to the LRU list */
	buf_LRU_add_block(block, FALSE);

#ifdef UNIV_SYNC_DEBUG
	buf_block_buf_fix_inc_debug(block, __FILE__, __LINE__);
#else
	buf_block_buf_fix_inc(block);
#endif
	buf_pool->n_pages_created++;

	mutex_exit(&(buf_pool->mutex));

	mtr_memo_push(mtr, block, MTR_MEMO_BUF_FIX);

	block->accessed = TRUE;

	mutex_exit(&block->mutex);

	/* Delete possible entries for the page from the insert buffer:
	such can exist if the page belonged to an index which was dropped */

	ibuf_merge_or_delete_for_page(NULL, space, offset, TRUE);

	/* Flush pages from the end of the LRU list if necessary */
	buf_flush_free_margin();

	frame = block->frame;

	memset(frame + FIL_PAGE_PREV, 0xff, 4);
	memset(frame + FIL_PAGE_NEXT, 0xff, 4);
	mach_write_to_2(frame + FIL_PAGE_TYPE, FIL_PAGE_TYPE_ALLOCATED);

	/* Reset to zero the file flush lsn field in the page; if the first
	page of an ibdata file is 'created' in this function into the buffer
	pool then we lose the original contents of the file flush lsn stamp.
	Then InnoDB could in a crash recovery print a big, false, corruption
	warning if the stamp contains an lsn bigger than the ib_logfile lsn. */

	memset(frame + FIL_PAGE_FILE_FLUSH_LSN, 0, 8);

#ifdef UNIV_DEBUG
	buf_dbg_counter++;

	if (buf_dbg_counter % 357 == 0) {
		ut_ad(buf_validate());
	}
#endif
#ifdef UNIV_IBUF_DEBUG
	ut_a(ibuf_count_get(block->space, block->offset) == 0);
#endif
	return(frame);
}

/************************************************************************
Completes an asynchronous read or write request of a file page to or from
the buffer pool. */

void
buf_page_io_complete(
/*=================*/
	buf_block_t*	block)	/* in: pointer to the block in question */
{
	ulint		io_type;

	ut_ad(block);

	ut_a(block->state == BUF_BLOCK_FILE_PAGE);

	/* We do not need protect block->io_fix here by block->mutex to read
	it because this is the only function where we can change the value
	from BUF_IO_READ or BUF_IO_WRITE to some other value, and our code
	ensures that this is the only thread that handles the i/o for this
	block. */

	io_type = block->io_fix;

	if (io_type == BUF_IO_READ) {
		/* If this page is not uninitialized and not in the
		doublewrite buffer, then the page number and space id
		should be the same as in block. */
		ulint	read_page_no = mach_read_from_4(
			block->frame + FIL_PAGE_OFFSET);
		ulint	read_space_id = mach_read_from_4(
			block->frame + FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID);

		if (!block->space
		    && trx_doublewrite_page_inside(block->offset)) {

			ut_print_timestamp(stderr);
			fprintf(stderr,
				"  InnoDB: Error: reading page %lu\n"
				"InnoDB: which is in the"
				" doublewrite buffer!\n",
				(ulong) block->offset);
		} else if (!read_space_id && !read_page_no) {
			/* This is likely an uninitialized page. */
		} else if ((block->space && block->space != read_space_id)
			   || block->offset != read_page_no) {
			/* We did not compare space_id to read_space_id
			if block->space == 0, because the field on the
			page may contain garbage in MySQL < 4.1.1,
			which only supported block->space == 0. */

			ut_print_timestamp(stderr);
			fprintf(stderr,
				"  InnoDB: Error: space id and page n:o"
				" stored in the page\n"
				"InnoDB: read in are %lu:%lu,"
				" should be %lu:%lu!\n",
				(ulong) read_space_id, (ulong) read_page_no,
				(ulong) block->space, (ulong) block->offset);
		}
		/* From version 3.23.38 up we store the page checksum
		to the 4 first bytes of the page end lsn field */

		if (buf_page_is_corrupted(block->frame)) {
			fprintf(stderr,
				"InnoDB: Database page corruption on disk"
				" or a failed\n"
				"InnoDB: file read of page %lu.\n",
				(ulong) block->offset);

			fputs("InnoDB: You may have to recover"
			      " from a backup.\n", stderr);

			buf_page_print(block->frame);

			fprintf(stderr,
				"InnoDB: Database page corruption on disk"
				" or a failed\n"
				"InnoDB: file read of page %lu.\n",
				(ulong) block->offset);
			fputs("InnoDB: You may have to recover"
			      " from a backup.\n", stderr);
			fputs("InnoDB: It is also possible that"
			      " your operating\n"
			      "InnoDB: system has corrupted its"
			      " own file cache\n"
			      "InnoDB: and rebooting your computer"
			      " removes the\n"
			      "InnoDB: error.\n"
			      "InnoDB: If the corrupt page is an index page\n"
			      "InnoDB: you can also try to"
			      " fix the corruption\n"
			      "InnoDB: by dumping, dropping,"
			      " and reimporting\n"
			      "InnoDB: the corrupt table."
			      " You can use CHECK\n"
			      "InnoDB: TABLE to scan your"
			      " table for corruption.\n"
			      "InnoDB: See also"
			      " http://dev.mysql.com/doc/refman/5.1/en/"
			      "forcing-recovery.html\n"
			      "InnoDB: about forcing recovery.\n", stderr);

			if (srv_force_recovery < SRV_FORCE_IGNORE_CORRUPT) {
				fputs("InnoDB: Ending processing because of"
				      " a corrupt database page.\n",
				      stderr);
				exit(1);
			}
		}

		if (recv_recovery_is_on()) {
			recv_recover_page(FALSE, TRUE, block->frame,
					  block->space, block->offset);
		}

		if (!recv_no_ibuf_operations) {
			ibuf_merge_or_delete_for_page(
				block->frame, block->space, block->offset,
				TRUE);
		}
	}

	mutex_enter(&(buf_pool->mutex));
	mutex_enter(&block->mutex);

#ifdef UNIV_IBUF_DEBUG
	ut_a(ibuf_count_get(block->space, block->offset) == 0);
#endif
	/* Because this thread which does the unlocking is not the same that
	did the locking, we use a pass value != 0 in unlock, which simply
	removes the newest lock debug record, without checking the thread
	id. */

	block->io_fix = 0;

	if (io_type == BUF_IO_READ) {
		/* NOTE that the call to ibuf may have moved the ownership of
		the x-latch to this OS thread: do not let this confuse you in
		debugging! */

		ut_ad(buf_pool->n_pend_reads > 0);
		buf_pool->n_pend_reads--;
		buf_pool->n_pages_read++;

		rw_lock_x_unlock_gen(&(block->lock), BUF_IO_READ);

#ifdef UNIV_DEBUG
		if (buf_debug_prints) {
			fputs("Has read ", stderr);
		}
#endif /* UNIV_DEBUG */
	} else {
		ut_ad(io_type == BUF_IO_WRITE);

		/* Write means a flush operation: call the completion
		routine in the flush system */

		buf_flush_write_complete(block);

		rw_lock_s_unlock_gen(&(block->lock), BUF_IO_WRITE);

		buf_pool->n_pages_written++;

#ifdef UNIV_DEBUG
		if (buf_debug_prints) {
			fputs("Has written ", stderr);
		}
#endif /* UNIV_DEBUG */
	}

	mutex_exit(&block->mutex);
	mutex_exit(&(buf_pool->mutex));

#ifdef UNIV_DEBUG
	if (buf_debug_prints) {
		fprintf(stderr, "page space %lu page no %lu\n",
			(ulong) block->space, (ulong) block->offset);
	}
#endif /* UNIV_DEBUG */
}

/*************************************************************************
Invalidates the file pages in the buffer pool when an archive recovery is
completed. All the file pages buffered must be in a replaceable state when
this function is called: not latched and not modified. */

void
buf_pool_invalidate(void)
/*=====================*/
{
	ibool	freed;

	ut_ad(buf_all_freed());

	freed = TRUE;

	while (freed) {
		freed = buf_LRU_search_and_free_block(100);
	}

	mutex_enter(&(buf_pool->mutex));

	ut_ad(UT_LIST_GET_LEN(buf_pool->LRU) == 0);

	mutex_exit(&(buf_pool->mutex));
}

#ifdef UNIV_DEBUG
/*************************************************************************
Validates the buffer buf_pool data structure. */

ibool
buf_validate(void)
/*==============*/
{
	buf_block_t*	block;
	ulint		i;
	ulint		n_single_flush	= 0;
	ulint		n_lru_flush	= 0;
	ulint		n_list_flush	= 0;
	ulint		n_lru		= 0;
	ulint		n_flush		= 0;
	ulint		n_free		= 0;
	ulint		n_page		= 0;

	ut_ad(buf_pool);

	mutex_enter(&(buf_pool->mutex));

	for (i = 0; i < buf_pool->curr_size; i++) {

		block = buf_pool_get_nth_block(buf_pool, i);

		mutex_enter(&block->mutex);

		if (block->state == BUF_BLOCK_FILE_PAGE) {

			ut_a(buf_page_hash_get(block->space,
					       block->offset) == block);
			n_page++;

#ifdef UNIV_IBUF_DEBUG
			ut_a((block->io_fix == BUF_IO_READ)
			     || ibuf_count_get(block->space, block->offset)
			     == 0);
#endif
			if (block->io_fix == BUF_IO_WRITE) {

				if (block->flush_type == BUF_FLUSH_LRU) {
					n_lru_flush++;
					ut_a(rw_lock_is_locked(
						     &block->lock,
						     RW_LOCK_SHARED));
				} else if (block->flush_type
					   == BUF_FLUSH_LIST) {
					n_list_flush++;
				} else if (block->flush_type
					   == BUF_FLUSH_SINGLE_PAGE) {
					n_single_flush++;
				} else {
					ut_error;
				}

			} else if (block->io_fix == BUF_IO_READ) {

				ut_a(rw_lock_is_locked(&(block->lock),
						       RW_LOCK_EX));
			}

			n_lru++;

			if (ut_dulint_cmp(block->oldest_modification,
					  ut_dulint_zero) > 0) {
				n_flush++;
			}

		} else if (block->state == BUF_BLOCK_NOT_USED) {
			n_free++;
		}

		mutex_exit(&block->mutex);
	}

	if (n_lru + n_free > buf_pool->curr_size) {
		fprintf(stderr, "n LRU %lu, n free %lu\n",
			(ulong) n_lru, (ulong) n_free);
		ut_error;
	}

	ut_a(UT_LIST_GET_LEN(buf_pool->LRU) == n_lru);
	if (UT_LIST_GET_LEN(buf_pool->free) != n_free) {
		fprintf(stderr, "Free list len %lu, free blocks %lu\n",
			(ulong) UT_LIST_GET_LEN(buf_pool->free),
			(ulong) n_free);
		ut_error;
	}
	ut_a(UT_LIST_GET_LEN(buf_pool->flush_list) == n_flush);

	ut_a(buf_pool->n_flush[BUF_FLUSH_SINGLE_PAGE] == n_single_flush);
	ut_a(buf_pool->n_flush[BUF_FLUSH_LIST] == n_list_flush);
	ut_a(buf_pool->n_flush[BUF_FLUSH_LRU] == n_lru_flush);

	mutex_exit(&(buf_pool->mutex));

	ut_a(buf_LRU_validate());
	ut_a(buf_flush_validate());

	return(TRUE);
}

/*************************************************************************
Prints info of the buffer buf_pool data structure. */

void
buf_print(void)
/*===========*/
{
	dulint*		index_ids;
	ulint*		counts;
	ulint		size;
	ulint		i;
	ulint		j;
	dulint		id;
	ulint		n_found;
	buf_frame_t*	frame;
	dict_index_t*	index;

	ut_ad(buf_pool);

	size = buf_pool->curr_size;

	index_ids = mem_alloc(sizeof(dulint) * size);
	counts = mem_alloc(sizeof(ulint) * size);

	mutex_enter(&(buf_pool->mutex));

	fprintf(stderr,
		"buf_pool size %lu\n"
		"database pages %lu\n"
		"free pages %lu\n"
		"modified database pages %lu\n"
		"n pending reads %lu\n"
		"n pending flush LRU %lu list %lu single page %lu\n"
		"pages read %lu, created %lu, written %lu\n",
		(ulong) size,
		(ulong) UT_LIST_GET_LEN(buf_pool->LRU),
		(ulong) UT_LIST_GET_LEN(buf_pool->free),
		(ulong) UT_LIST_GET_LEN(buf_pool->flush_list),
		(ulong) buf_pool->n_pend_reads,
		(ulong) buf_pool->n_flush[BUF_FLUSH_LRU],
		(ulong) buf_pool->n_flush[BUF_FLUSH_LIST],
		(ulong) buf_pool->n_flush[BUF_FLUSH_SINGLE_PAGE],
		(ulong) buf_pool->n_pages_read, buf_pool->n_pages_created,
		(ulong) buf_pool->n_pages_written);

	/* Count the number of blocks belonging to each index in the buffer */

	n_found = 0;

	for (i = 0; i < size; i++) {
		frame = buf_pool_get_nth_block(buf_pool, i)->frame;

		if (fil_page_get_type(frame) == FIL_PAGE_INDEX) {

			id = btr_page_get_index_id(frame);

			/* Look for the id in the index_ids array */
			j = 0;

			while (j < n_found) {

				if (ut_dulint_cmp(index_ids[j], id) == 0) {
					(counts[j])++;

					break;
				}
				j++;
			}

			if (j == n_found) {
				n_found++;
				index_ids[j] = id;
				counts[j] = 1;
			}
		}
	}

	mutex_exit(&(buf_pool->mutex));

	for (i = 0; i < n_found; i++) {
		index = dict_index_get_if_in_cache(index_ids[i]);

		fprintf(stderr,
			"Block count for index %lu in buffer is about %lu",
			(ulong) ut_dulint_get_low(index_ids[i]),
			(ulong) counts[i]);

		if (index) {
			putc(' ', stderr);
			dict_index_name_print(stderr, NULL, index);
		}

		putc('\n', stderr);
	}

	mem_free(index_ids);
	mem_free(counts);

	ut_a(buf_validate());
}
#endif /* UNIV_DEBUG */

/*************************************************************************
Returns the number of latched pages in the buffer pool. */

ulint
buf_get_latched_pages_number(void)
{
	buf_block_t*	block;
	ulint		i;
	ulint		fixed_pages_number = 0;

	mutex_enter(&(buf_pool->mutex));

	for (i = 0; i < buf_pool->curr_size; i++) {

		block = buf_pool_get_nth_block(buf_pool, i);

		if (block->magic_n == BUF_BLOCK_MAGIC_N) {
			mutex_enter(&block->mutex);

			if (block->buf_fix_count != 0 || block->io_fix != 0) {
				fixed_pages_number++;
			}

			mutex_exit(&block->mutex);
		}
	}

	mutex_exit(&(buf_pool->mutex));

	return(fixed_pages_number);
}

/*************************************************************************
Returns the number of pending buf pool ios. */

ulint
buf_get_n_pending_ios(void)
/*=======================*/
{
	return(buf_pool->n_pend_reads
	       + buf_pool->n_flush[BUF_FLUSH_LRU]
	       + buf_pool->n_flush[BUF_FLUSH_LIST]
	       + buf_pool->n_flush[BUF_FLUSH_SINGLE_PAGE]);
}

/*************************************************************************
Returns the ratio in percents of modified pages in the buffer pool /
database pages in the buffer pool. */

ulint
buf_get_modified_ratio_pct(void)
/*============================*/
{
	ulint	ratio;

	mutex_enter(&(buf_pool->mutex));

	ratio = (100 * UT_LIST_GET_LEN(buf_pool->flush_list))
		/ (1 + UT_LIST_GET_LEN(buf_pool->LRU)
		   + UT_LIST_GET_LEN(buf_pool->free));

	/* 1 + is there to avoid division by zero */

	mutex_exit(&(buf_pool->mutex));

	return(ratio);
}

/*************************************************************************
Prints info of the buffer i/o. */

void
buf_print_io(
/*=========*/
	FILE*	file)	/* in/out: buffer where to print */
{
	time_t	current_time;
	double	time_elapsed;
	ulint	size;

	ut_ad(buf_pool);
	size = buf_pool->curr_size;

	mutex_enter(&(buf_pool->mutex));

	if (srv_use_awe) {
		fprintf(stderr,
			"AWE: Buffer pool memory frames %lu\n",
			(ulong) buf_pool->n_frames);

		fprintf(stderr,
			"AWE: Database pages and free buffers"
			" mapped in frames %lu\n",
			(ulong)
			UT_LIST_GET_LEN(buf_pool->awe_LRU_free_mapped));
	}
	fprintf(file,
		"Buffer pool size   %lu\n"
		"Free buffers       %lu\n"
		"Database pages     %lu\n"
		"Modified db pages  %lu\n"
		"Pending reads %lu\n"
		"Pending writes: LRU %lu, flush list %lu, single page %lu\n",
		(ulong) size,
		(ulong) UT_LIST_GET_LEN(buf_pool->free),
		(ulong) UT_LIST_GET_LEN(buf_pool->LRU),
		(ulong) UT_LIST_GET_LEN(buf_pool->flush_list),
		(ulong) buf_pool->n_pend_reads,
		(ulong) buf_pool->n_flush[BUF_FLUSH_LRU]
		+ buf_pool->init_flush[BUF_FLUSH_LRU],
		(ulong) buf_pool->n_flush[BUF_FLUSH_LIST]
		+ buf_pool->init_flush[BUF_FLUSH_LIST],
		(ulong) buf_pool->n_flush[BUF_FLUSH_SINGLE_PAGE]);

	current_time = time(NULL);
	time_elapsed = 0.001 + difftime(current_time,
					buf_pool->last_printout_time);
	buf_pool->last_printout_time = current_time;

	fprintf(file,
		"Pages read %lu, created %lu, written %lu\n"
		"%.2f reads/s, %.2f creates/s, %.2f writes/s\n",
		(ulong) buf_pool->n_pages_read,
		(ulong) buf_pool->n_pages_created,
		(ulong) buf_pool->n_pages_written,
		(buf_pool->n_pages_read - buf_pool->n_pages_read_old)
		/ time_elapsed,
		(buf_pool->n_pages_created - buf_pool->n_pages_created_old)
		/ time_elapsed,
		(buf_pool->n_pages_written - buf_pool->n_pages_written_old)
		/ time_elapsed);

	if (srv_use_awe) {
		fprintf(file, "AWE: %.2f page remaps/s\n",
			(buf_pool->n_pages_awe_remapped
			 - buf_pool->n_pages_awe_remapped_old)
			/ time_elapsed);
	}

	if (buf_pool->n_page_gets > buf_pool->n_page_gets_old) {
		fprintf(file, "Buffer pool hit rate %lu / 1000\n",
			(ulong)
			(1000 - ((1000 * (buf_pool->n_pages_read
					  - buf_pool->n_pages_read_old))
				 / (buf_pool->n_page_gets
				    - buf_pool->n_page_gets_old))));
	} else {
		fputs("No buffer pool page gets since the last printout\n",
		      file);
	}

	buf_pool->n_page_gets_old = buf_pool->n_page_gets;
	buf_pool->n_pages_read_old = buf_pool->n_pages_read;
	buf_pool->n_pages_created_old = buf_pool->n_pages_created;
	buf_pool->n_pages_written_old = buf_pool->n_pages_written;
	buf_pool->n_pages_awe_remapped_old = buf_pool->n_pages_awe_remapped;

	mutex_exit(&(buf_pool->mutex));
}

/**************************************************************************
Refreshes the statistics used to print per-second averages. */

void
buf_refresh_io_stats(void)
/*======================*/
{
	buf_pool->last_printout_time = time(NULL);
	buf_pool->n_page_gets_old = buf_pool->n_page_gets;
	buf_pool->n_pages_read_old = buf_pool->n_pages_read;
	buf_pool->n_pages_created_old = buf_pool->n_pages_created;
	buf_pool->n_pages_written_old = buf_pool->n_pages_written;
	buf_pool->n_pages_awe_remapped_old = buf_pool->n_pages_awe_remapped;
}

/*************************************************************************
Checks that all file pages in the buffer are in a replaceable state. */

ibool
buf_all_freed(void)
/*===============*/
{
	buf_block_t*	block;
	ulint		i;

	ut_ad(buf_pool);

	mutex_enter(&(buf_pool->mutex));

	for (i = 0; i < buf_pool->curr_size; i++) {

		block = buf_pool_get_nth_block(buf_pool, i);

		mutex_enter(&block->mutex);

		if (block->state == BUF_BLOCK_FILE_PAGE) {

			if (!buf_flush_ready_for_replace(block)) {

				fprintf(stderr,
					"Page %lu %lu still fixed or dirty\n",
					(ulong) block->space,
					(ulong) block->offset);
				ut_error;
			}
		}

		mutex_exit(&block->mutex);
	}

	mutex_exit(&(buf_pool->mutex));

	return(TRUE);
}

/*************************************************************************
Checks that there currently are no pending i/o-operations for the buffer
pool. */

ibool
buf_pool_check_no_pending_io(void)
/*==============================*/
				/* out: TRUE if there is no pending i/o */
{
	ibool	ret;

	mutex_enter(&(buf_pool->mutex));

	if (buf_pool->n_pend_reads + buf_pool->n_flush[BUF_FLUSH_LRU]
	    + buf_pool->n_flush[BUF_FLUSH_LIST]
	    + buf_pool->n_flush[BUF_FLUSH_SINGLE_PAGE]) {
		ret = FALSE;
	} else {
		ret = TRUE;
	}

	mutex_exit(&(buf_pool->mutex));

	return(ret);
}

/*************************************************************************
Gets the current length of the free list of buffer blocks. */

ulint
buf_get_free_list_len(void)
/*=======================*/
{
	ulint	len;

	mutex_enter(&(buf_pool->mutex));

	len = UT_LIST_GET_LEN(buf_pool->free);

	mutex_exit(&(buf_pool->mutex));

	return(len);
}