summaryrefslogtreecommitdiff
path: root/storage/innodb_plugin/trx/trx0sys.c
blob: 2aadcca2dae3673fa4f605242c1aaf4da618e652 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
/*****************************************************************************

Copyright (c) 1996, 2010, Innobase Oy. All Rights Reserved.

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

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 along with
this program; if not, write to the Free Software Foundation, Inc., 59 Temple
Place, Suite 330, Boston, MA 02111-1307 USA

*****************************************************************************/

/**************************************************//**
@file trx/trx0sys.c
Transaction system

Created 3/26/1996 Heikki Tuuri
*******************************************************/

#include "trx0sys.h"

#ifdef UNIV_NONINL
#include "trx0sys.ic"
#endif

#ifndef UNIV_HOTBACKUP
#include "fsp0fsp.h"
#include "mtr0log.h"
#include "mtr0log.h"
#include "trx0trx.h"
#include "trx0rseg.h"
#include "trx0undo.h"
#include "srv0srv.h"
#include "srv0start.h"
#include "trx0purge.h"
#include "log0log.h"
#include "os0file.h"
#include "read0read.h"

/** The file format tag structure with id and name. */
struct file_format_struct {
	ulint		id;		/*!< id of the file format */
	const char*	name;		/*!< text representation of the
					file format */
	mutex_t		mutex;		/*!< covers changes to the above
					fields */
};

/** The file format tag */
typedef struct file_format_struct	file_format_t;

/** The transaction system */
UNIV_INTERN trx_sys_t*		trx_sys		= NULL;
/** The doublewrite buffer */
UNIV_INTERN trx_doublewrite_t*	trx_doublewrite = NULL;

/** The following is set to TRUE when we are upgrading from pre-4.1
format data files to the multiple tablespaces format data files */
UNIV_INTERN ibool	trx_doublewrite_must_reset_space_ids	= FALSE;
/** Set to TRUE when the doublewrite buffer is being created */
UNIV_INTERN ibool	trx_doublewrite_buf_is_being_created = FALSE;

/** The following is TRUE when we are using the database in the
post-4.1 format, i.e., we have successfully upgraded, or have created
a new database installation */
UNIV_INTERN ibool	trx_sys_multiple_tablespace_format	= FALSE;

/** In a MySQL replication slave, in crash recovery we store the master log
file name and position here. */
/* @{ */
/** Master binlog file name */
UNIV_INTERN char	trx_sys_mysql_master_log_name[TRX_SYS_MYSQL_LOG_NAME_LEN];
/** Master binlog file position.  We have successfully got the updates
up to this position.  -1 means that no crash recovery was needed, or
there was no master log position info inside InnoDB.*/
UNIV_INTERN ib_int64_t	trx_sys_mysql_master_log_pos	= -1;
/* @} */

/** If this MySQL server uses binary logging, after InnoDB has been inited
and if it has done a crash recovery, we store the binlog file name and position
here. */
/* @{ */
/** Binlog file name */
UNIV_INTERN char	trx_sys_mysql_bin_log_name[TRX_SYS_MYSQL_LOG_NAME_LEN];
/** Binlog file position, or -1 if unknown */
UNIV_INTERN ib_int64_t	trx_sys_mysql_bin_log_pos	= -1;
/* @} */
#endif /* !UNIV_HOTBACKUP */

/** List of animal names representing file format. */
static const char*	file_format_name_map[] = {
	"Antelope",
	"Barracuda",
	"Cheetah",
	"Dragon",
	"Elk",
	"Fox",
	"Gazelle",
	"Hornet",
	"Impala",
	"Jaguar",
	"Kangaroo",
	"Leopard",
	"Moose",
	"Nautilus",
	"Ocelot",
	"Porpoise",
	"Quail",
	"Rabbit",
	"Shark",
	"Tiger",
	"Urchin",
	"Viper",
	"Whale",
	"Xenops",
	"Yak",
	"Zebra"
};

/** The number of elements in the file format name array. */
static const ulint	FILE_FORMAT_NAME_N
	= sizeof(file_format_name_map) / sizeof(file_format_name_map[0]);

#ifndef UNIV_HOTBACKUP
/** This is used to track the maximum file format id known to InnoDB. It's
updated via SET GLOBAL innodb_file_format_check = 'x' or when we open
or create a table. */
static	file_format_t	file_format_max;

/****************************************************************//**
Determines if a page number is located inside the doublewrite buffer.
@return TRUE if the location is inside the two blocks of the
doublewrite buffer */
UNIV_INTERN
ibool
trx_doublewrite_page_inside(
/*========================*/
	ulint	page_no)	/*!< in: page number */
{
	if (trx_doublewrite == NULL) {

		return(FALSE);
	}

	if (page_no >= trx_doublewrite->block1
	    && page_no < trx_doublewrite->block1
	    + TRX_SYS_DOUBLEWRITE_BLOCK_SIZE) {
		return(TRUE);
	}

	if (page_no >= trx_doublewrite->block2
	    && page_no < trx_doublewrite->block2
	    + TRX_SYS_DOUBLEWRITE_BLOCK_SIZE) {
		return(TRUE);
	}

	return(FALSE);
}

/****************************************************************//**
Creates or initialializes the doublewrite buffer at a database start. */
static
void
trx_doublewrite_init(
/*=================*/
	byte*	doublewrite)	/*!< in: pointer to the doublewrite buf
				header on trx sys page */
{
	trx_doublewrite = mem_alloc(sizeof(trx_doublewrite_t));

	/* Since we now start to use the doublewrite buffer, no need to call
	fsync() after every write to a data file */
#ifdef UNIV_DO_FLUSH
	os_do_not_call_flush_at_each_write = TRUE;
#endif /* UNIV_DO_FLUSH */

	mutex_create(&trx_doublewrite->mutex, SYNC_DOUBLEWRITE);

	trx_doublewrite->first_free = 0;

	trx_doublewrite->block1 = mach_read_from_4(
		doublewrite + TRX_SYS_DOUBLEWRITE_BLOCK1);
	trx_doublewrite->block2 = mach_read_from_4(
		doublewrite + TRX_SYS_DOUBLEWRITE_BLOCK2);
	trx_doublewrite->write_buf_unaligned = ut_malloc(
		(1 + 2 * TRX_SYS_DOUBLEWRITE_BLOCK_SIZE) * UNIV_PAGE_SIZE);

	trx_doublewrite->write_buf = ut_align(
		trx_doublewrite->write_buf_unaligned, UNIV_PAGE_SIZE);
	trx_doublewrite->buf_block_arr = mem_alloc(
		2 * TRX_SYS_DOUBLEWRITE_BLOCK_SIZE * sizeof(void*));
}

/****************************************************************//**
Marks the trx sys header when we have successfully upgraded to the >= 4.1.x
multiple tablespace format. */
UNIV_INTERN
void
trx_sys_mark_upgraded_to_multiple_tablespaces(void)
/*===============================================*/
{
	buf_block_t*	block;
	byte*		doublewrite;
	mtr_t		mtr;

	/* We upgraded to 4.1.x and reset the space id fields in the
	doublewrite buffer. Let us mark to the trx_sys header that the upgrade
	has been done. */

	mtr_start(&mtr);

	block = buf_page_get(TRX_SYS_SPACE, 0, TRX_SYS_PAGE_NO,
			     RW_X_LATCH, &mtr);
	buf_block_dbg_add_level(block, SYNC_NO_ORDER_CHECK);

	doublewrite = buf_block_get_frame(block) + TRX_SYS_DOUBLEWRITE;

	mlog_write_ulint(doublewrite + TRX_SYS_DOUBLEWRITE_SPACE_ID_STORED,
			 TRX_SYS_DOUBLEWRITE_SPACE_ID_STORED_N,
			 MLOG_4BYTES, &mtr);
	mtr_commit(&mtr);

	/* Flush the modified pages to disk and make a checkpoint */
	log_make_checkpoint_at(IB_ULONGLONG_MAX, TRUE);

	trx_sys_multiple_tablespace_format = TRUE;
}

/****************************************************************//**
Creates the doublewrite buffer to a new InnoDB installation. The header of the
doublewrite buffer is placed on the trx system header page. */
UNIV_INTERN
void
trx_sys_create_doublewrite_buf(void)
/*================================*/
{
	buf_block_t*	block;
	buf_block_t*	block2;
#ifdef UNIV_SYNC_DEBUG
	buf_block_t*	new_block;
#endif /* UNIV_SYNC_DEBUG */
	byte*	doublewrite;
	byte*	fseg_header;
	ulint	page_no;
	ulint	prev_page_no;
	ulint	i;
	mtr_t	mtr;

	if (trx_doublewrite) {
		/* Already inited */

		return;
	}

start_again:
	mtr_start(&mtr);
	trx_doublewrite_buf_is_being_created = TRUE;

	block = buf_page_get(TRX_SYS_SPACE, 0, TRX_SYS_PAGE_NO,
			     RW_X_LATCH, &mtr);
	buf_block_dbg_add_level(block, SYNC_NO_ORDER_CHECK);

	doublewrite = buf_block_get_frame(block) + TRX_SYS_DOUBLEWRITE;

	if (mach_read_from_4(doublewrite + TRX_SYS_DOUBLEWRITE_MAGIC)
	    == TRX_SYS_DOUBLEWRITE_MAGIC_N) {
		/* The doublewrite buffer has already been created:
		just read in some numbers */

		trx_doublewrite_init(doublewrite);

		mtr_commit(&mtr);
		trx_doublewrite_buf_is_being_created = FALSE;
	} else {
		fprintf(stderr,
			"InnoDB: Doublewrite buffer not found:"
			" creating new\n");

		if (buf_pool_get_curr_size()
		    < ((2 * TRX_SYS_DOUBLEWRITE_BLOCK_SIZE
			+ FSP_EXTENT_SIZE / 2 + 100)
		       * UNIV_PAGE_SIZE)) {
			fprintf(stderr,
				"InnoDB: Cannot create doublewrite buffer:"
				" you must\n"
				"InnoDB: increase your buffer pool size.\n"
				"InnoDB: Cannot continue operation.\n");

			exit(1);
		}

		block2 = fseg_create(TRX_SYS_SPACE, TRX_SYS_PAGE_NO,
				     TRX_SYS_DOUBLEWRITE
				     + TRX_SYS_DOUBLEWRITE_FSEG, &mtr);

		/* fseg_create acquires a second latch on the page,
		therefore we must declare it: */

		buf_block_dbg_add_level(block2, SYNC_NO_ORDER_CHECK);

		if (block2 == NULL) {
			fprintf(stderr,
				"InnoDB: Cannot create doublewrite buffer:"
				" you must\n"
				"InnoDB: increase your tablespace size.\n"
				"InnoDB: Cannot continue operation.\n");

			/* We exit without committing the mtr to prevent
			its modifications to the database getting to disk */

			exit(1);
		}

		fseg_header = buf_block_get_frame(block)
			+ TRX_SYS_DOUBLEWRITE + TRX_SYS_DOUBLEWRITE_FSEG;
		prev_page_no = 0;

		for (i = 0; i < 2 * TRX_SYS_DOUBLEWRITE_BLOCK_SIZE
			     + FSP_EXTENT_SIZE / 2; i++) {
			page_no = fseg_alloc_free_page(fseg_header,
						       prev_page_no + 1,
						       FSP_UP, &mtr);
			if (page_no == FIL_NULL) {
				fprintf(stderr,
					"InnoDB: Cannot create doublewrite"
					" buffer: you must\n"
					"InnoDB: increase your"
					" tablespace size.\n"
					"InnoDB: Cannot continue operation.\n"
					);

				exit(1);
			}

			/* We read the allocated pages to the buffer pool;
			when they are written to disk in a flush, the space
			id and page number fields are also written to the
			pages. When we at database startup read pages
			from the doublewrite buffer, we know that if the
			space id and page number in them are the same as
			the page position in the tablespace, then the page
			has not been written to in doublewrite. */

#ifdef UNIV_SYNC_DEBUG
			new_block =
#endif /* UNIV_SYNC_DEBUG */
			buf_page_get(TRX_SYS_SPACE, 0, page_no,
				     RW_X_LATCH, &mtr);
			buf_block_dbg_add_level(new_block,
						SYNC_NO_ORDER_CHECK);

			if (i == FSP_EXTENT_SIZE / 2) {
				ut_a(page_no == FSP_EXTENT_SIZE);
				mlog_write_ulint(doublewrite
						 + TRX_SYS_DOUBLEWRITE_BLOCK1,
						 page_no, MLOG_4BYTES, &mtr);
				mlog_write_ulint(doublewrite
						 + TRX_SYS_DOUBLEWRITE_REPEAT
						 + TRX_SYS_DOUBLEWRITE_BLOCK1,
						 page_no, MLOG_4BYTES, &mtr);
			} else if (i == FSP_EXTENT_SIZE / 2
				   + TRX_SYS_DOUBLEWRITE_BLOCK_SIZE) {
				ut_a(page_no == 2 * FSP_EXTENT_SIZE);
				mlog_write_ulint(doublewrite
						 + TRX_SYS_DOUBLEWRITE_BLOCK2,
						 page_no, MLOG_4BYTES, &mtr);
				mlog_write_ulint(doublewrite
						 + TRX_SYS_DOUBLEWRITE_REPEAT
						 + TRX_SYS_DOUBLEWRITE_BLOCK2,
						 page_no, MLOG_4BYTES, &mtr);
			} else if (i > FSP_EXTENT_SIZE / 2) {
				ut_a(page_no == prev_page_no + 1);
			}

			prev_page_no = page_no;
		}

		mlog_write_ulint(doublewrite + TRX_SYS_DOUBLEWRITE_MAGIC,
				 TRX_SYS_DOUBLEWRITE_MAGIC_N,
				 MLOG_4BYTES, &mtr);
		mlog_write_ulint(doublewrite + TRX_SYS_DOUBLEWRITE_MAGIC
				 + TRX_SYS_DOUBLEWRITE_REPEAT,
				 TRX_SYS_DOUBLEWRITE_MAGIC_N,
				 MLOG_4BYTES, &mtr);

		mlog_write_ulint(doublewrite
				 + TRX_SYS_DOUBLEWRITE_SPACE_ID_STORED,
				 TRX_SYS_DOUBLEWRITE_SPACE_ID_STORED_N,
				 MLOG_4BYTES, &mtr);
		mtr_commit(&mtr);

		/* Flush the modified pages to disk and make a checkpoint */
		log_make_checkpoint_at(IB_ULONGLONG_MAX, TRUE);

		fprintf(stderr, "InnoDB: Doublewrite buffer created\n");

		trx_sys_multiple_tablespace_format = TRUE;

		goto start_again;
	}
}

/****************************************************************//**
At a database startup initializes the doublewrite buffer memory structure if
we already have a doublewrite buffer created in the data files. If we are
upgrading to an InnoDB version which supports multiple tablespaces, then this
function performs the necessary update operations. If we are in a crash
recovery, this function uses a possible doublewrite buffer to restore
half-written pages in the data files. */
UNIV_INTERN
void
trx_sys_doublewrite_init_or_restore_pages(
/*======================================*/
	ibool	restore_corrupt_pages)	/*!< in: TRUE=restore pages */
{
	byte*	buf;
	byte*	read_buf;
	byte*	unaligned_read_buf;
	ulint	block1;
	ulint	block2;
	ulint	source_page_no;
	byte*	page;
	byte*	doublewrite;
	ulint	space_id;
	ulint	page_no;
	ulint	i;

	/* We do the file i/o past the buffer pool */

	unaligned_read_buf = ut_malloc(2 * UNIV_PAGE_SIZE);
	read_buf = ut_align(unaligned_read_buf, UNIV_PAGE_SIZE);

	/* Read the trx sys header to check if we are using the doublewrite
	buffer */

	fil_io(OS_FILE_READ, TRUE, TRX_SYS_SPACE, 0, TRX_SYS_PAGE_NO, 0,
	       UNIV_PAGE_SIZE, read_buf, NULL);
	doublewrite = read_buf + TRX_SYS_DOUBLEWRITE;

	if (mach_read_from_4(doublewrite + TRX_SYS_DOUBLEWRITE_MAGIC)
	    == TRX_SYS_DOUBLEWRITE_MAGIC_N) {
		/* The doublewrite buffer has been created */

		trx_doublewrite_init(doublewrite);

		block1 = trx_doublewrite->block1;
		block2 = trx_doublewrite->block2;

		buf = trx_doublewrite->write_buf;
	} else {
		goto leave_func;
	}

	if (mach_read_from_4(doublewrite + TRX_SYS_DOUBLEWRITE_SPACE_ID_STORED)
	    != TRX_SYS_DOUBLEWRITE_SPACE_ID_STORED_N) {

		/* We are upgrading from a version < 4.1.x to a version where
		multiple tablespaces are supported. We must reset the space id
		field in the pages in the doublewrite buffer because starting
		from this version the space id is stored to
		FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID. */

		trx_doublewrite_must_reset_space_ids = TRUE;

		fprintf(stderr,
			"InnoDB: Resetting space id's in the"
			" doublewrite buffer\n");
	} else {
		trx_sys_multiple_tablespace_format = TRUE;
	}

	/* Read the pages from the doublewrite buffer to memory */

	fil_io(OS_FILE_READ, TRUE, TRX_SYS_SPACE, 0, block1, 0,
	       TRX_SYS_DOUBLEWRITE_BLOCK_SIZE * UNIV_PAGE_SIZE,
	       buf, NULL);
	fil_io(OS_FILE_READ, TRUE, TRX_SYS_SPACE, 0, block2, 0,
	       TRX_SYS_DOUBLEWRITE_BLOCK_SIZE * UNIV_PAGE_SIZE,
	       buf + TRX_SYS_DOUBLEWRITE_BLOCK_SIZE * UNIV_PAGE_SIZE,
	       NULL);
	/* Check if any of these pages is half-written in data files, in the
	intended position */

	page = buf;

	for (i = 0; i < TRX_SYS_DOUBLEWRITE_BLOCK_SIZE * 2; i++) {

		page_no = mach_read_from_4(page + FIL_PAGE_OFFSET);

		if (trx_doublewrite_must_reset_space_ids) {

			space_id = 0;
			mach_write_to_4(page
					+ FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID, 0);
			/* We do not need to calculate new checksums for the
			pages because the field .._SPACE_ID does not affect
			them. Write the page back to where we read it from. */

			if (i < TRX_SYS_DOUBLEWRITE_BLOCK_SIZE) {
				source_page_no = block1 + i;
			} else {
				source_page_no = block2
					+ i - TRX_SYS_DOUBLEWRITE_BLOCK_SIZE;
			}

			fil_io(OS_FILE_WRITE, TRUE, 0, 0, source_page_no, 0,
			       UNIV_PAGE_SIZE, page, NULL);
			/* printf("Resetting space id in page %lu\n",
			source_page_no); */
		} else {
			space_id = mach_read_from_4(
				page + FIL_PAGE_ARCH_LOG_NO_OR_SPACE_ID);
		}

		if (!restore_corrupt_pages) {
			/* The database was shut down gracefully: no need to
			restore pages */

		} else if (!fil_tablespace_exists_in_mem(space_id)) {
			/* Maybe we have dropped the single-table tablespace
			and this page once belonged to it: do nothing */

		} else if (!fil_check_adress_in_tablespace(space_id,
							   page_no)) {
			fprintf(stderr,
				"InnoDB: Warning: a page in the"
				" doublewrite buffer is not within space\n"
				"InnoDB: bounds; space id %lu"
				" page number %lu, page %lu in"
				" doublewrite buf.\n",
				(ulong) space_id, (ulong) page_no, (ulong) i);

		} else if (space_id == TRX_SYS_SPACE
			   && ((page_no >= block1
				&& page_no
				< block1 + TRX_SYS_DOUBLEWRITE_BLOCK_SIZE)
			       || (page_no >= block2
				   && page_no
				   < (block2
				      + TRX_SYS_DOUBLEWRITE_BLOCK_SIZE)))) {

			/* It is an unwritten doublewrite buffer page:
			do nothing */
		} else {
			ulint	zip_size = fil_space_get_zip_size(space_id);

			/* Read in the actual page from the file */
			fil_io(OS_FILE_READ, TRUE, space_id, zip_size,
			       page_no, 0,
			       zip_size ? zip_size : UNIV_PAGE_SIZE,
			       read_buf, NULL);

			/* Check if the page is corrupt */

			if (UNIV_UNLIKELY
			    (buf_page_is_corrupted(read_buf, zip_size))) {

				fprintf(stderr,
					"InnoDB: Warning: database page"
					" corruption or a failed\n"
					"InnoDB: file read of"
					" space %lu page %lu.\n"
					"InnoDB: Trying to recover it from"
					" the doublewrite buffer.\n",
					(ulong) space_id, (ulong) page_no);

				if (buf_page_is_corrupted(page, zip_size)) {
					fprintf(stderr,
						"InnoDB: Dump of the page:\n");
					buf_page_print(read_buf, zip_size);
					fprintf(stderr,
						"InnoDB: Dump of"
						" corresponding page"
						" in doublewrite buffer:\n");
					buf_page_print(page, zip_size);

					fprintf(stderr,
						"InnoDB: Also the page in the"
						" doublewrite buffer"
						" is corrupt.\n"
						"InnoDB: Cannot continue"
						" operation.\n"
						"InnoDB: You can try to"
						" recover the database"
						" with the my.cnf\n"
						"InnoDB: option:\n"
						"InnoDB:"
						" innodb_force_recovery=6\n");
					exit(1);
				}

				/* Write the good page from the
				doublewrite buffer to the intended
				position */

				fil_io(OS_FILE_WRITE, TRUE, space_id,
				       zip_size, page_no, 0,
				       zip_size ? zip_size : UNIV_PAGE_SIZE,
				       page, NULL);
				fprintf(stderr,
					"InnoDB: Recovered the page from"
					" the doublewrite buffer.\n");
			}
		}

		page += UNIV_PAGE_SIZE;
	}

	fil_flush_file_spaces(FIL_TABLESPACE);

leave_func:
	ut_free(unaligned_read_buf);
}

/****************************************************************//**
Checks that trx is in the trx list.
@return	TRUE if is in */
UNIV_INTERN
ibool
trx_in_trx_list(
/*============*/
	trx_t*	in_trx)	/*!< in: trx */
{
	trx_t*	trx;

	ut_ad(mutex_own(&(kernel_mutex)));

	trx = UT_LIST_GET_FIRST(trx_sys->trx_list);

	while (trx != NULL) {

		if (trx == in_trx) {

			return(TRUE);
		}

		trx = UT_LIST_GET_NEXT(trx_list, trx);
	}

	return(FALSE);
}

/*****************************************************************//**
Writes the value of max_trx_id to the file based trx system header. */
UNIV_INTERN
void
trx_sys_flush_max_trx_id(void)
/*==========================*/
{
	trx_sysf_t*	sys_header;
	mtr_t		mtr;

	ut_ad(mutex_own(&kernel_mutex));

	mtr_start(&mtr);

	sys_header = trx_sysf_get(&mtr);

	mlog_write_dulint(sys_header + TRX_SYS_TRX_ID_STORE,
			  trx_sys->max_trx_id, &mtr);
	mtr_commit(&mtr);
}

/*****************************************************************//**
Updates the offset information about the end of the MySQL binlog entry
which corresponds to the transaction just being committed. In a MySQL
replication slave updates the latest master binlog position up to which
replication has proceeded. */
UNIV_INTERN
void
trx_sys_update_mysql_binlog_offset(
/*===============================*/
	const char*	file_name,/*!< in: MySQL log file name */
	ib_int64_t	offset,	/*!< in: position in that log file */
	ulint		field,	/*!< in: offset of the MySQL log info field in
				the trx sys header */
	mtr_t*		mtr)	/*!< in: mtr */
{
	trx_sysf_t*	sys_header;

	if (ut_strlen(file_name) >= TRX_SYS_MYSQL_LOG_NAME_LEN) {

		/* We cannot fit the name to the 512 bytes we have reserved */

		return;
	}

	sys_header = trx_sysf_get(mtr);

	if (mach_read_from_4(sys_header + field
			     + TRX_SYS_MYSQL_LOG_MAGIC_N_FLD)
	    != TRX_SYS_MYSQL_LOG_MAGIC_N) {

		mlog_write_ulint(sys_header + field
				 + TRX_SYS_MYSQL_LOG_MAGIC_N_FLD,
				 TRX_SYS_MYSQL_LOG_MAGIC_N,
				 MLOG_4BYTES, mtr);
	}

	if (0 != strcmp((char*) (sys_header + field + TRX_SYS_MYSQL_LOG_NAME),
			file_name)) {

		mlog_write_string(sys_header + field
				  + TRX_SYS_MYSQL_LOG_NAME,
				  (byte*) file_name, 1 + ut_strlen(file_name),
				  mtr);
	}

	if (mach_read_from_4(sys_header + field
			     + TRX_SYS_MYSQL_LOG_OFFSET_HIGH) > 0
	    || (offset >> 32) > 0) {

		mlog_write_ulint(sys_header + field
				 + TRX_SYS_MYSQL_LOG_OFFSET_HIGH,
				 (ulint)(offset >> 32),
				 MLOG_4BYTES, mtr);
	}

	mlog_write_ulint(sys_header + field
			 + TRX_SYS_MYSQL_LOG_OFFSET_LOW,
			 (ulint)(offset & 0xFFFFFFFFUL),
			 MLOG_4BYTES, mtr);
}

/*****************************************************************//**
Stores the MySQL binlog offset info in the trx system header if
the magic number shows it valid, and print the info to stderr */
UNIV_INTERN
void
trx_sys_print_mysql_binlog_offset(void)
/*===================================*/
{
	trx_sysf_t*	sys_header;
	mtr_t		mtr;
	ulint		trx_sys_mysql_bin_log_pos_high;
	ulint		trx_sys_mysql_bin_log_pos_low;

	mtr_start(&mtr);

	sys_header = trx_sysf_get(&mtr);

	if (mach_read_from_4(sys_header + TRX_SYS_MYSQL_LOG_INFO
			     + TRX_SYS_MYSQL_LOG_MAGIC_N_FLD)
	    != TRX_SYS_MYSQL_LOG_MAGIC_N) {

		mtr_commit(&mtr);

		return;
	}

	trx_sys_mysql_bin_log_pos_high = mach_read_from_4(
		sys_header + TRX_SYS_MYSQL_LOG_INFO
		+ TRX_SYS_MYSQL_LOG_OFFSET_HIGH);
	trx_sys_mysql_bin_log_pos_low = mach_read_from_4(
		sys_header + TRX_SYS_MYSQL_LOG_INFO
		+ TRX_SYS_MYSQL_LOG_OFFSET_LOW);

	trx_sys_mysql_bin_log_pos
		= (((ib_int64_t)trx_sys_mysql_bin_log_pos_high) << 32)
		+ (ib_int64_t)trx_sys_mysql_bin_log_pos_low;

	ut_memcpy(trx_sys_mysql_bin_log_name,
		  sys_header + TRX_SYS_MYSQL_LOG_INFO
		  + TRX_SYS_MYSQL_LOG_NAME, TRX_SYS_MYSQL_LOG_NAME_LEN);

	fprintf(stderr,
		"InnoDB: Last MySQL binlog file position %lu %lu,"
		" file name %s\n",
		trx_sys_mysql_bin_log_pos_high, trx_sys_mysql_bin_log_pos_low,
		trx_sys_mysql_bin_log_name);

	mtr_commit(&mtr);
}

/*****************************************************************//**
Prints to stderr the MySQL master log offset info in the trx system header if
the magic number shows it valid. */
UNIV_INTERN
void
trx_sys_print_mysql_master_log_pos(void)
/*====================================*/
{
	trx_sysf_t*	sys_header;
	mtr_t		mtr;

	mtr_start(&mtr);

	sys_header = trx_sysf_get(&mtr);

	if (mach_read_from_4(sys_header + TRX_SYS_MYSQL_MASTER_LOG_INFO
			     + TRX_SYS_MYSQL_LOG_MAGIC_N_FLD)
	    != TRX_SYS_MYSQL_LOG_MAGIC_N) {

		mtr_commit(&mtr);

		return;
	}

	fprintf(stderr,
		"InnoDB: In a MySQL replication slave the last"
		" master binlog file\n"
		"InnoDB: position %lu %lu, file name %s\n",
		(ulong) mach_read_from_4(sys_header
					 + TRX_SYS_MYSQL_MASTER_LOG_INFO
					 + TRX_SYS_MYSQL_LOG_OFFSET_HIGH),
		(ulong) mach_read_from_4(sys_header
					 + TRX_SYS_MYSQL_MASTER_LOG_INFO
					 + TRX_SYS_MYSQL_LOG_OFFSET_LOW),
		sys_header + TRX_SYS_MYSQL_MASTER_LOG_INFO
		+ TRX_SYS_MYSQL_LOG_NAME);
	/* Copy the master log position info to global variables we can
	use in ha_innobase.cc to initialize glob_mi to right values */

	ut_memcpy(trx_sys_mysql_master_log_name,
		  sys_header + TRX_SYS_MYSQL_MASTER_LOG_INFO
		  + TRX_SYS_MYSQL_LOG_NAME,
		  TRX_SYS_MYSQL_LOG_NAME_LEN);

	trx_sys_mysql_master_log_pos
		= (((ib_int64_t) mach_read_from_4(
			    sys_header + TRX_SYS_MYSQL_MASTER_LOG_INFO
			    + TRX_SYS_MYSQL_LOG_OFFSET_HIGH)) << 32)
		+ ((ib_int64_t) mach_read_from_4(
			   sys_header + TRX_SYS_MYSQL_MASTER_LOG_INFO
			   + TRX_SYS_MYSQL_LOG_OFFSET_LOW));
	mtr_commit(&mtr);
}

/****************************************************************//**
Looks for a free slot for a rollback segment in the trx system file copy.
@return	slot index or ULINT_UNDEFINED if not found */
UNIV_INTERN
ulint
trx_sysf_rseg_find_free(
/*====================*/
	mtr_t*	mtr)	/*!< in: mtr */
{
	trx_sysf_t*	sys_header;
	ulint		page_no;
	ulint		i;

	ut_ad(mutex_own(&(kernel_mutex)));

	sys_header = trx_sysf_get(mtr);

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

		page_no = trx_sysf_rseg_get_page_no(sys_header, i, mtr);

		if (page_no == FIL_NULL) {

			return(i);
		}
	}

	return(ULINT_UNDEFINED);
}

/*****************************************************************//**
Creates the file page for the transaction system. This function is called only
at the database creation, before trx_sys_init. */
static
void
trx_sysf_create(
/*============*/
	mtr_t*	mtr)	/*!< in: mtr */
{
	trx_sysf_t*	sys_header;
	ulint		slot_no;
	buf_block_t*	block;
	page_t*		page;
	ulint		page_no;
	ulint		i;

	ut_ad(mtr);

	/* Note that below we first reserve the file space x-latch, and
	then enter the kernel: we must do it in this order to conform
	to the latching order rules. */

	mtr_x_lock(fil_space_get_latch(TRX_SYS_SPACE, NULL), mtr);
	mutex_enter(&kernel_mutex);

	/* Create the trx sys file block in a new allocated file segment */
	block = fseg_create(TRX_SYS_SPACE, 0, TRX_SYS + TRX_SYS_FSEG_HEADER,
			    mtr);
	buf_block_dbg_add_level(block, SYNC_TRX_SYS_HEADER);

	ut_a(buf_block_get_page_no(block) == TRX_SYS_PAGE_NO);

	page = buf_block_get_frame(block);

	mlog_write_ulint(page + FIL_PAGE_TYPE, FIL_PAGE_TYPE_TRX_SYS,
			 MLOG_2BYTES, mtr);

	/* Reset the doublewrite buffer magic number to zero so that we
	know that the doublewrite buffer has not yet been created (this
	suppresses a Valgrind warning) */

	mlog_write_ulint(page + TRX_SYS_DOUBLEWRITE
			 + TRX_SYS_DOUBLEWRITE_MAGIC, 0, MLOG_4BYTES, mtr);

	sys_header = trx_sysf_get(mtr);

	/* Start counting transaction ids from number 1 up */
	mlog_write_dulint(sys_header + TRX_SYS_TRX_ID_STORE,
			  ut_dulint_create(0, 1), mtr);

	/* Reset the rollback segment slots */
	for (i = 0; i < TRX_SYS_N_RSEGS; i++) {

		trx_sysf_rseg_set_space(sys_header, i, ULINT_UNDEFINED, mtr);
		trx_sysf_rseg_set_page_no(sys_header, i, FIL_NULL, mtr);
	}

	/* The remaining area (up to the page trailer) is uninitialized.
	Silence Valgrind warnings about it. */
	UNIV_MEM_VALID(sys_header + (TRX_SYS_RSEGS
				     + TRX_SYS_N_RSEGS * TRX_SYS_RSEG_SLOT_SIZE
				     + TRX_SYS_RSEG_SPACE),
		       (UNIV_PAGE_SIZE - FIL_PAGE_DATA_END
			- (TRX_SYS_RSEGS
			   + TRX_SYS_N_RSEGS * TRX_SYS_RSEG_SLOT_SIZE
			   + TRX_SYS_RSEG_SPACE))
		       + page - sys_header);

	/* Create the first rollback segment in the SYSTEM tablespace */
	page_no = trx_rseg_header_create(TRX_SYS_SPACE, 0, ULINT_MAX, &slot_no,
					 mtr);
	ut_a(slot_no == TRX_SYS_SYSTEM_RSEG_ID);
	ut_a(page_no != FIL_NULL);

	mutex_exit(&kernel_mutex);
}

/*****************************************************************//**
Creates and initializes the central memory structures for the transaction
system. This is called when the database is started. */
UNIV_INTERN
void
trx_sys_init_at_db_start(void)
/*==========================*/
{
	trx_sysf_t*	sys_header;
	ib_int64_t	rows_to_undo	= 0;
	const char*	unit		= "";
	trx_t*		trx;
	mtr_t		mtr;

	mtr_start(&mtr);

	ut_ad(trx_sys == NULL);

	mutex_enter(&kernel_mutex);

	trx_sys = mem_alloc(sizeof(trx_sys_t));

	sys_header = trx_sysf_get(&mtr);

	trx_rseg_list_and_array_init(sys_header, &mtr);

	trx_sys->latest_rseg = UT_LIST_GET_FIRST(trx_sys->rseg_list);

	/* VERY important: after the database is started, max_trx_id value is
	divisible by TRX_SYS_TRX_ID_WRITE_MARGIN, and the 'if' in
	trx_sys_get_new_trx_id will evaluate to TRUE when the function
	is first time called, and the value for trx id will be written
	to the disk-based header! Thus trx id values will not overlap when
	the database is repeatedly started! */

	trx_sys->max_trx_id = ut_dulint_add(
		ut_dulint_align_up(mtr_read_dulint(
					   sys_header
					   + TRX_SYS_TRX_ID_STORE, &mtr),
				   TRX_SYS_TRX_ID_WRITE_MARGIN),
		2 * TRX_SYS_TRX_ID_WRITE_MARGIN);

	UT_LIST_INIT(trx_sys->mysql_trx_list);
	trx_dummy_sess = sess_open();
	trx_lists_init_at_db_start();

	if (UT_LIST_GET_LEN(trx_sys->trx_list) > 0) {
		trx = UT_LIST_GET_FIRST(trx_sys->trx_list);

		for (;;) {

			if ( trx->conc_state != TRX_PREPARED) {
				rows_to_undo += ut_conv_dulint_to_longlong(
					trx->undo_no);
			}

			trx = UT_LIST_GET_NEXT(trx_list, trx);

			if (!trx) {
				break;
			}
		}

		if (rows_to_undo > 1000000000) {
			unit = "M";
			rows_to_undo = rows_to_undo / 1000000;
		}

		fprintf(stderr,
			"InnoDB: %lu transaction(s) which must be"
			" rolled back or cleaned up\n"
			"InnoDB: in total %lu%s row operations to undo\n",
			(ulong) UT_LIST_GET_LEN(trx_sys->trx_list),
			(ulong) rows_to_undo, unit);

		fprintf(stderr, "InnoDB: Trx id counter is " TRX_ID_FMT "\n",
			TRX_ID_PREP_PRINTF(trx_sys->max_trx_id));
	}

	UT_LIST_INIT(trx_sys->view_list);

	trx_purge_sys_create();

	mutex_exit(&kernel_mutex);

	mtr_commit(&mtr);
}

/*****************************************************************//**
Creates and initializes the transaction system at the database creation. */
UNIV_INTERN
void
trx_sys_create(void)
/*================*/
{
	mtr_t	mtr;

	mtr_start(&mtr);

	trx_sysf_create(&mtr);

	mtr_commit(&mtr);

	trx_sys_init_at_db_start();
}

/*****************************************************************//**
Update the file format tag.
@return	always TRUE */
static
ibool
trx_sys_file_format_max_write(
/*==========================*/
	ulint		format_id,	/*!< in: file format id */
	const char**	name)		/*!< out: max file format name, can
					be NULL */
{
	mtr_t		mtr;
	byte*		ptr;
	buf_block_t*	block;
	ulint		tag_value_low;

	mtr_start(&mtr);

	block = buf_page_get(
		TRX_SYS_SPACE, 0, TRX_SYS_PAGE_NO, RW_X_LATCH, &mtr);

	file_format_max.id = format_id;
	file_format_max.name = trx_sys_file_format_id_to_name(format_id);

	ptr = buf_block_get_frame(block) + TRX_SYS_FILE_FORMAT_TAG;
	tag_value_low = format_id + TRX_SYS_FILE_FORMAT_TAG_MAGIC_N_LOW;

	if (name) {
		*name = file_format_max.name;
	}

	mlog_write_dulint(
		ptr,
		ut_dulint_create(TRX_SYS_FILE_FORMAT_TAG_MAGIC_N_HIGH,
				 tag_value_low),
		&mtr);

	mtr_commit(&mtr);

	return(TRUE);
}

/*****************************************************************//**
Read the file format tag.
@return	the file format or ULINT_UNDEFINED if not set. */
static
ulint
trx_sys_file_format_max_read(void)
/*==============================*/
{
	mtr_t			mtr;
	const byte*		ptr;
	const buf_block_t*	block;
	ulint			format_id;
	dulint			file_format_id;

	/* Since this is called during the startup phase it's safe to
	read the value without a covering mutex. */
	mtr_start(&mtr);

	block = buf_page_get(
		TRX_SYS_SPACE, 0, TRX_SYS_PAGE_NO, RW_X_LATCH, &mtr);

	ptr = buf_block_get_frame(block) + TRX_SYS_FILE_FORMAT_TAG;
	file_format_id = mach_read_from_8(ptr);

	mtr_commit(&mtr);

	format_id = file_format_id.low - TRX_SYS_FILE_FORMAT_TAG_MAGIC_N_LOW;

	if (file_format_id.high != TRX_SYS_FILE_FORMAT_TAG_MAGIC_N_HIGH
	    || format_id >= FILE_FORMAT_NAME_N) {

		/* Either it has never been tagged, or garbage in it. */
		return(ULINT_UNDEFINED);
	}

	return(format_id);
}

/*****************************************************************//**
Get the name representation of the file format from its id.
@return	pointer to the name */
UNIV_INTERN
const char*
trx_sys_file_format_id_to_name(
/*===========================*/
	const ulint	id)	/*!< in: id of the file format */
{
	ut_a(id < FILE_FORMAT_NAME_N);

	return(file_format_name_map[id]);
}

/*****************************************************************//**
Check for the max file format tag stored on disk. Note: If max_format_id
is == DICT_TF_FORMAT_MAX + 1 then we only print a warning.
@return	DB_SUCCESS or error code */
UNIV_INTERN
ulint
trx_sys_file_format_max_check(
/*==========================*/
	ulint	max_format_id)	/*!< in: max format id to check */
{
	ulint	format_id;

	/* Check the file format in the tablespace. Do not try to
	recover if the file format is not supported by the engine
	unless forced by the user. */
	format_id = trx_sys_file_format_max_read();
	if (format_id == ULINT_UNDEFINED) {
		/* Format ID was not set. Set it to minimum possible
		value. */
		format_id = DICT_TF_FORMAT_51;
	}

	ut_print_timestamp(stderr);
	fprintf(stderr,
		"  InnoDB: highest supported file format is %s.\n",
		trx_sys_file_format_id_to_name(DICT_TF_FORMAT_MAX));

	if (format_id > DICT_TF_FORMAT_MAX) {

		ut_a(format_id < FILE_FORMAT_NAME_N);

		ut_print_timestamp(stderr);
		fprintf(stderr,
			"  InnoDB: %s: the system tablespace is in a file "
			"format that this version doesn't support - %s\n",
			((max_format_id <= DICT_TF_FORMAT_MAX)
				? "Error" : "Warning"),
			trx_sys_file_format_id_to_name(format_id));

		if (max_format_id <= DICT_TF_FORMAT_MAX) {
			return(DB_ERROR);
		}
	}

	format_id = (format_id > max_format_id) ? format_id : max_format_id;

	/* We don't need a mutex here, as this function should only
	be called once at start up. */
	file_format_max.id = format_id;
	file_format_max.name = trx_sys_file_format_id_to_name(format_id);

	return(DB_SUCCESS);
}

/*****************************************************************//**
Set the file format id unconditionally except if it's already the
same value.
@return	TRUE if value updated */
UNIV_INTERN
ibool
trx_sys_file_format_max_set(
/*========================*/
	ulint		format_id,	/*!< in: file format id */
	const char**	name)		/*!< out: max file format name or
					NULL if not needed. */
{
	ibool		ret = FALSE;

	ut_a(format_id <= DICT_TF_FORMAT_MAX);

	mutex_enter(&file_format_max.mutex);

	/* Only update if not already same value. */
	if (format_id != file_format_max.id) {

		ret = trx_sys_file_format_max_write(format_id, name);
	}

	mutex_exit(&file_format_max.mutex);

	return(ret);
}

/********************************************************************//**
Tags the system table space with minimum format id if it has not been
tagged yet.
WARNING: This function is only called during the startup and AFTER the
redo log application during recovery has finished. */
UNIV_INTERN
void
trx_sys_file_format_tag_init(void)
/*==============================*/
{
	ulint	format_id;

	format_id = trx_sys_file_format_max_read();

	/* If format_id is not set then set it to the minimum. */
	if (format_id == ULINT_UNDEFINED) {
		trx_sys_file_format_max_set(DICT_TF_FORMAT_51, NULL);
	}
}

/********************************************************************//**
Update the file format tag in the system tablespace only if the given
format id is greater than the known max id.
@return	TRUE if format_id was bigger than the known max id */
UNIV_INTERN
ibool
trx_sys_file_format_max_upgrade(
/*============================*/
	const char**	name,		/*!< out: max file format name */
	ulint		format_id)	/*!< in: file format identifier */
{
	ibool		ret = FALSE;

	ut_a(name);
	ut_a(file_format_max.name != NULL);
	ut_a(format_id <= DICT_TF_FORMAT_MAX);

	mutex_enter(&file_format_max.mutex);

	if (format_id > file_format_max.id) {

		ret = trx_sys_file_format_max_write(format_id, name);
	}

	mutex_exit(&file_format_max.mutex);

	return(ret);
}

/*****************************************************************//**
Get the name representation of the file format from its id.
@return	pointer to the max format name */
UNIV_INTERN
const char*
trx_sys_file_format_max_get(void)
/*=============================*/
{
	return(file_format_max.name);
}

/*****************************************************************//**
Initializes the tablespace tag system. */
UNIV_INTERN
void
trx_sys_file_format_init(void)
/*==========================*/
{
	mutex_create(&file_format_max.mutex, SYNC_FILE_FORMAT_TAG);

	/* We don't need a mutex here, as this function should only
	be called once at start up. */
	file_format_max.id = DICT_TF_FORMAT_51;

	file_format_max.name = trx_sys_file_format_id_to_name(
		file_format_max.id);
}

/*****************************************************************//**
Closes the tablespace tag system. */
UNIV_INTERN
void
trx_sys_file_format_close(void)
/*===========================*/
{
	/* Does nothing at the moment */
}
#else /* !UNIV_HOTBACKUP */
/*****************************************************************//**
Prints to stderr the MySQL binlog info in the system header if the
magic number shows it valid. */
UNIV_INTERN
void
trx_sys_print_mysql_binlog_offset_from_page(
/*========================================*/
	const byte*	page)	/*!< in: buffer containing the trx
				system header page, i.e., page number
				TRX_SYS_PAGE_NO in the tablespace */
{
	const trx_sysf_t*	sys_header;

	sys_header = page + TRX_SYS;

	if (mach_read_from_4(sys_header + TRX_SYS_MYSQL_LOG_INFO
			     + TRX_SYS_MYSQL_LOG_MAGIC_N_FLD)
	    == TRX_SYS_MYSQL_LOG_MAGIC_N) {

		fprintf(stderr,
			"ibbackup: Last MySQL binlog file position %lu %lu,"
			" file name %s\n",
			(ulong) mach_read_from_4(
				sys_header + TRX_SYS_MYSQL_LOG_INFO
				+ TRX_SYS_MYSQL_LOG_OFFSET_HIGH),
			(ulong) mach_read_from_4(
				sys_header + TRX_SYS_MYSQL_LOG_INFO
				+ TRX_SYS_MYSQL_LOG_OFFSET_LOW),
			sys_header + TRX_SYS_MYSQL_LOG_INFO
			+ TRX_SYS_MYSQL_LOG_NAME);
	}
}


/* THESE ARE COPIED FROM NON-HOTBACKUP PART OF THE INNODB SOURCE TREE
   (This code duplication should be fixed at some point!)
*/

#define	TRX_SYS_SPACE	0	/* the SYSTEM tablespace */
/* The offset of the file format tag on the trx system header page */
#define TRX_SYS_FILE_FORMAT_TAG		(UNIV_PAGE_SIZE - 16)
/* We use these random constants to reduce the probability of reading
garbage (from previous versions) that maps to an actual format id. We
use these as bit masks at the time of  reading and writing from/to disk. */
#define TRX_SYS_FILE_FORMAT_TAG_MAGIC_N_LOW	3645922177UL
#define TRX_SYS_FILE_FORMAT_TAG_MAGIC_N_HIGH	2745987765UL

/* END OF COPIED DEFINITIONS */


/*****************************************************************//**
Reads the file format id from the first system table space file.
Even if the call succeeds and returns TRUE, the returned format id
may be ULINT_UNDEFINED signalling that the format id was not present
in the data file.
@return TRUE if call succeeds */
UNIV_INTERN
ibool
trx_sys_read_file_format_id(
/*========================*/
	const char *pathname,  /*!< in: pathname of the first system
				        table space file */
	ulint *format_id)      /*!< out: file format of the system table
				         space */
{
	os_file_t	file;
	ibool		success;
	byte		buf[UNIV_PAGE_SIZE * 2];
	page_t*		page = ut_align(buf, UNIV_PAGE_SIZE);
	const byte*	ptr;
	dulint		file_format_id;

	*format_id = ULINT_UNDEFINED;
	
	file = os_file_create_simple_no_error_handling(
		pathname,
		OS_FILE_OPEN,
		OS_FILE_READ_ONLY,
		&success
	);
	if (!success) {
		/* The following call prints an error message */
		os_file_get_last_error(TRUE);
        
		ut_print_timestamp(stderr);
        
		fprintf(stderr,
"  ibbackup: Error: trying to read system tablespace file format,\n"
"  ibbackup: but could not open the tablespace file %s!\n",
			pathname
		);
		return(FALSE);
	}

	/* Read the page on which file format is stored */

	success = os_file_read_no_error_handling(
		file, page, TRX_SYS_PAGE_NO * UNIV_PAGE_SIZE, 0, UNIV_PAGE_SIZE
	);
	if (!success) {
		/* The following call prints an error message */
		os_file_get_last_error(TRUE);
        
		ut_print_timestamp(stderr);
        
		fprintf(stderr,
"  ibbackup: Error: trying to read system table space file format,\n"
"  ibbackup: but failed to read the tablespace file %s!\n",
			pathname
		);
		os_file_close(file);
		return(FALSE);
	}
	os_file_close(file);

	/* get the file format from the page */
	ptr = page + TRX_SYS_FILE_FORMAT_TAG;
	file_format_id = mach_read_from_8(ptr);

	*format_id = file_format_id.low - TRX_SYS_FILE_FORMAT_TAG_MAGIC_N_LOW;

	if (file_format_id.high != TRX_SYS_FILE_FORMAT_TAG_MAGIC_N_HIGH
	    || *format_id >= FILE_FORMAT_NAME_N) {

		/* Either it has never been tagged, or garbage in it. */
		*format_id = ULINT_UNDEFINED;
		return(TRUE);
	}
	
	return(TRUE);
}


/*****************************************************************//**
Reads the file format id from the given per-table data file.
@return TRUE if call succeeds */
UNIV_INTERN
ibool
trx_sys_read_pertable_file_format_id(
/*=================================*/
	const char *pathname,  /*!< in: pathname of a per-table
				        datafile */
	ulint *format_id)      /*!< out: file format of the per-table
				         data file */
{
	os_file_t	file;
	ibool		success;
	byte		buf[UNIV_PAGE_SIZE * 2];
	page_t*		page = ut_align(buf, UNIV_PAGE_SIZE);
	const byte*	ptr;
	ib_uint32_t	flags;

	*format_id = ULINT_UNDEFINED;
	
	file = os_file_create_simple_no_error_handling(
		pathname,
		OS_FILE_OPEN,
		OS_FILE_READ_ONLY,
		&success
	);
	if (!success) {
		/* The following call prints an error message */
		os_file_get_last_error(TRUE);
        
		ut_print_timestamp(stderr);
        
		fprintf(stderr,
"  ibbackup: Error: trying to read per-table tablespace format,\n"
"  ibbackup: but could not open the tablespace file %s!\n",
			pathname
		);
		return(FALSE);
	}

	/* Read the first page of the per-table datafile */

	success = os_file_read_no_error_handling(
		file, page, 0, 0, UNIV_PAGE_SIZE
	);
	if (!success) {
		/* The following call prints an error message */
		os_file_get_last_error(TRUE);
        
		ut_print_timestamp(stderr);
        
		fprintf(stderr,
"  ibbackup: Error: trying to per-table data file format,\n"
"  ibbackup: but failed to read the tablespace file %s!\n",
			pathname
		);
		os_file_close(file);
		return(FALSE);
	}
	os_file_close(file);

	/* get the file format from the page */
	ptr = page + 54;
	flags = mach_read_from_4(ptr);
	if (flags == 0) {
		/* file format is Antelope */
		*format_id = 0;
		return (TRUE);
	} else if (flags & 1) {
		/* tablespace flags are ok */
		*format_id = (flags / 32) % 128;
		return (TRUE);
	} else {
		/* bad tablespace flags */
		return(FALSE);
	}
}


/*****************************************************************//**
Get the name representation of the file format from its id.
@return	pointer to the name */
UNIV_INTERN
const char*
trx_sys_file_format_id_to_name(
/*===========================*/
	const ulint	id)	/*!< in: id of the file format */
{
	if (!(id < FILE_FORMAT_NAME_N)) {
		/* unknown id */
		return ("Unknown");
	}

	return(file_format_name_map[id]);
}

#endif /* !UNIV_HOTBACKUP */

#ifndef UNIV_HOTBACKUP
/*********************************************************************
Shutdown/Close the transaction system. */
UNIV_INTERN
void
trx_sys_close(void)
/*===============*/
{
	trx_t*		trx;
	trx_rseg_t*	rseg;
	read_view_t*	view;

	ut_ad(trx_sys != NULL);
	ut_ad(srv_shutdown_state == SRV_SHUTDOWN_EXIT_THREADS);

	/* Check that all read views are closed except read view owned
	by a purge. */

	if (UT_LIST_GET_LEN(trx_sys->view_list) > 1) {
		fprintf(stderr,
			"InnoDB: Error: all read views were not closed"
			" before shutdown:\n"
			"InnoDB: %lu read views open \n",
			UT_LIST_GET_LEN(trx_sys->view_list) - 1);
	}

	sess_close(trx_dummy_sess);
	trx_dummy_sess = NULL;

	trx_purge_sys_close();

	mutex_enter(&kernel_mutex);

	/* Free the double write data structures. */
	ut_a(trx_doublewrite != NULL);
	ut_free(trx_doublewrite->write_buf_unaligned);
	trx_doublewrite->write_buf_unaligned = NULL;

	mem_free(trx_doublewrite->buf_block_arr);
	trx_doublewrite->buf_block_arr = NULL;

	mutex_free(&trx_doublewrite->mutex);
	mem_free(trx_doublewrite);
	trx_doublewrite = NULL;

	/* Only prepared transactions may be left in the system. Free them. */
	ut_a(UT_LIST_GET_LEN(trx_sys->trx_list) == trx_n_prepared);

	while ((trx = UT_LIST_GET_FIRST(trx_sys->trx_list)) != NULL) {
		trx_free_prepared(trx);
	}

	/* There can't be any active transactions. */
	rseg = UT_LIST_GET_FIRST(trx_sys->rseg_list);

	while (rseg != NULL) {
		trx_rseg_t*	prev_rseg = rseg;

		rseg = UT_LIST_GET_NEXT(rseg_list, prev_rseg);
		UT_LIST_REMOVE(rseg_list, trx_sys->rseg_list, prev_rseg);

		trx_rseg_mem_free(prev_rseg);
	}

	view = UT_LIST_GET_FIRST(trx_sys->view_list);

	while (view != NULL) {
		read_view_t*	prev_view = view;

		view = UT_LIST_GET_NEXT(view_list, prev_view);

		/* Views are allocated from the trx_sys->global_read_view_heap.
		So, we simply remove the element here. */
		UT_LIST_REMOVE(view_list, trx_sys->view_list, prev_view);
	}

	ut_a(UT_LIST_GET_LEN(trx_sys->trx_list) == 0);
	ut_a(UT_LIST_GET_LEN(trx_sys->rseg_list) == 0);
	ut_a(UT_LIST_GET_LEN(trx_sys->view_list) == 0);
	ut_a(UT_LIST_GET_LEN(trx_sys->mysql_trx_list) == 0);

	mem_free(trx_sys);

	trx_sys = NULL;
	mutex_exit(&kernel_mutex);
}
#endif /* !UNIV_HOTBACKUP */