btreeInt.h 28 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650
  1. /*
  2. ** 2004 April 6
  3. **
  4. ** The author disclaims copyright to this source code. In place of
  5. ** a legal notice, here is a blessing:
  6. **
  7. ** May you do good and not evil.
  8. ** May you find forgiveness for yourself and forgive others.
  9. ** May you share freely, never taking more than you give.
  10. **
  11. *************************************************************************
  12. ** $Id: btreeInt.h,v 1.14 2007/12/07 18:55:28 drh Exp $
  13. **
  14. ** This file implements a external (disk-based) database using BTrees.
  15. ** For a detailed discussion of BTrees, refer to
  16. **
  17. ** Donald E. Knuth, THE ART OF COMPUTER PROGRAMMING, Volume 3:
  18. ** "Sorting And Searching", pages 473-480. Addison-Wesley
  19. ** Publishing Company, Reading, Massachusetts.
  20. **
  21. ** The basic idea is that each page of the file contains N database
  22. ** entries and N+1 pointers to subpages.
  23. **
  24. ** ----------------------------------------------------------------
  25. ** | Ptr(0) | Key(0) | Ptr(1) | Key(1) | ... | Key(N-1) | Ptr(N) |
  26. ** ----------------------------------------------------------------
  27. **
  28. ** All of the keys on the page that Ptr(0) points to have values less
  29. ** than Key(0). All of the keys on page Ptr(1) and its subpages have
  30. ** values greater than Key(0) and less than Key(1). All of the keys
  31. ** on Ptr(N) and its subpages have values greater than Key(N-1). And
  32. ** so forth.
  33. **
  34. ** Finding a particular key requires reading O(log(M)) pages from the
  35. ** disk where M is the number of entries in the tree.
  36. **
  37. ** In this implementation, a single file can hold one or more separate
  38. ** BTrees. Each BTree is identified by the index of its root page. The
  39. ** key and data for any entry are combined to form the "payload". A
  40. ** fixed amount of payload can be carried directly on the database
  41. ** page. If the payload is larger than the preset amount then surplus
  42. ** bytes are stored on overflow pages. The payload for an entry
  43. ** and the preceding pointer are combined to form a "Cell". Each
  44. ** page has a small header which contains the Ptr(N) pointer and other
  45. ** information such as the size of key and data.
  46. **
  47. ** FORMAT DETAILS
  48. **
  49. ** The file is divided into pages. The first page is called page 1,
  50. ** the second is page 2, and so forth. A page number of zero indicates
  51. ** "no such page". The page size can be anything between 512 and 65536.
  52. ** Each page can be either a btree page, a freelist page or an overflow
  53. ** page.
  54. **
  55. ** The first page is always a btree page. The first 100 bytes of the first
  56. ** page contain a special header (the "file header") that describes the file.
  57. ** The format of the file header is as follows:
  58. **
  59. ** OFFSET SIZE DESCRIPTION
  60. ** 0 16 Header string: "SQLite format 3\000"
  61. ** 16 2 Page size in bytes.
  62. ** 18 1 File format write version
  63. ** 19 1 File format read version
  64. ** 20 1 Bytes of unused space at the end of each page
  65. ** 21 1 Max embedded payload fraction
  66. ** 22 1 Min embedded payload fraction
  67. ** 23 1 Min leaf payload fraction
  68. ** 24 4 File change counter
  69. ** 28 4 Reserved for future use
  70. ** 32 4 First freelist page
  71. ** 36 4 Number of freelist pages in the file
  72. ** 40 60 15 4-byte meta values passed to higher layers
  73. **
  74. ** All of the integer values are big-endian (most significant byte first).
  75. **
  76. ** The file change counter is incremented when the database is changed
  77. ** This counter allows other processes to know when the file has changed
  78. ** and thus when they need to flush their cache.
  79. **
  80. ** The max embedded payload fraction is the amount of the total usable
  81. ** space in a page that can be consumed by a single cell for standard
  82. ** B-tree (non-LEAFDATA) tables. A value of 255 means 100%. The default
  83. ** is to limit the maximum cell size so that at least 4 cells will fit
  84. ** on one page. Thus the default max embedded payload fraction is 64.
  85. **
  86. ** If the payload for a cell is larger than the max payload, then extra
  87. ** payload is spilled to overflow pages. Once an overflow page is allocated,
  88. ** as many bytes as possible are moved into the overflow pages without letting
  89. ** the cell size drop below the min embedded payload fraction.
  90. **
  91. ** The min leaf payload fraction is like the min embedded payload fraction
  92. ** except that it applies to leaf nodes in a LEAFDATA tree. The maximum
  93. ** payload fraction for a LEAFDATA tree is always 100% (or 255) and it
  94. ** not specified in the header.
  95. **
  96. ** Each btree pages is divided into three sections: The header, the
  97. ** cell pointer array, and the cell content area. Page 1 also has a 100-byte
  98. ** file header that occurs before the page header.
  99. **
  100. ** |----------------|
  101. ** | file header | 100 bytes. Page 1 only.
  102. ** |----------------|
  103. ** | page header | 8 bytes for leaves. 12 bytes for interior nodes
  104. ** |----------------|
  105. ** | cell pointer | | 2 bytes per cell. Sorted order.
  106. ** | array | | Grows downward
  107. ** | | v
  108. ** |----------------|
  109. ** | unallocated |
  110. ** | space |
  111. ** |----------------| ^ Grows upwards
  112. ** | cell content | | Arbitrary order interspersed with freeblocks.
  113. ** | area | | and free space fragments.
  114. ** |----------------|
  115. **
  116. ** The page headers looks like this:
  117. **
  118. ** OFFSET SIZE DESCRIPTION
  119. ** 0 1 Flags. 1: intkey, 2: zerodata, 4: leafdata, 8: leaf
  120. ** 1 2 byte offset to the first freeblock
  121. ** 3 2 number of cells on this page
  122. ** 5 2 first byte of the cell content area
  123. ** 7 1 number of fragmented free bytes
  124. ** 8 4 Right child (the Ptr(N) value). Omitted on leaves.
  125. **
  126. ** The flags define the format of this btree page. The leaf flag means that
  127. ** this page has no children. The zerodata flag means that this page carries
  128. ** only keys and no data. The intkey flag means that the key is a integer
  129. ** which is stored in the key size entry of the cell header rather than in
  130. ** the payload area.
  131. **
  132. ** The cell pointer array begins on the first byte after the page header.
  133. ** The cell pointer array contains zero or more 2-byte numbers which are
  134. ** offsets from the beginning of the page to the cell content in the cell
  135. ** content area. The cell pointers occur in sorted order. The system strives
  136. ** to keep free space after the last cell pointer so that new cells can
  137. ** be easily added without having to defragment the page.
  138. **
  139. ** Cell content is stored at the very end of the page and grows toward the
  140. ** beginning of the page.
  141. **
  142. ** Unused space within the cell content area is collected into a linked list of
  143. ** freeblocks. Each freeblock is at least 4 bytes in size. The byte offset
  144. ** to the first freeblock is given in the header. Freeblocks occur in
  145. ** increasing order. Because a freeblock must be at least 4 bytes in size,
  146. ** any group of 3 or fewer unused bytes in the cell content area cannot
  147. ** exist on the freeblock chain. A group of 3 or fewer free bytes is called
  148. ** a fragment. The total number of bytes in all fragments is recorded.
  149. ** in the page header at offset 7.
  150. **
  151. ** SIZE DESCRIPTION
  152. ** 2 Byte offset of the next freeblock
  153. ** 2 Bytes in this freeblock
  154. **
  155. ** Cells are of variable length. Cells are stored in the cell content area at
  156. ** the end of the page. Pointers to the cells are in the cell pointer array
  157. ** that immediately follows the page header. Cells is not necessarily
  158. ** contiguous or in order, but cell pointers are contiguous and in order.
  159. **
  160. ** Cell content makes use of variable length integers. A variable
  161. ** length integer is 1 to 9 bytes where the lower 7 bits of each
  162. ** byte are used. The integer consists of all bytes that have bit 8 set and
  163. ** the first byte with bit 8 clear. The most significant byte of the integer
  164. ** appears first. A variable-length integer may not be more than 9 bytes long.
  165. ** As a special case, all 8 bytes of the 9th byte are used as data. This
  166. ** allows a 64-bit integer to be encoded in 9 bytes.
  167. **
  168. ** 0x00 becomes 0x00000000
  169. ** 0x7f becomes 0x0000007f
  170. ** 0x81 0x00 becomes 0x00000080
  171. ** 0x82 0x00 becomes 0x00000100
  172. ** 0x80 0x7f becomes 0x0000007f
  173. ** 0x8a 0x91 0xd1 0xac 0x78 becomes 0x12345678
  174. ** 0x81 0x81 0x81 0x81 0x01 becomes 0x10204081
  175. **
  176. ** Variable length integers are used for rowids and to hold the number of
  177. ** bytes of key and data in a btree cell.
  178. **
  179. ** The content of a cell looks like this:
  180. **
  181. ** SIZE DESCRIPTION
  182. ** 4 Page number of the left child. Omitted if leaf flag is set.
  183. ** var Number of bytes of data. Omitted if the zerodata flag is set.
  184. ** var Number of bytes of key. Or the key itself if intkey flag is set.
  185. ** * Payload
  186. ** 4 First page of the overflow chain. Omitted if no overflow
  187. **
  188. ** Overflow pages form a linked list. Each page except the last is completely
  189. ** filled with data (pagesize - 4 bytes). The last page can have as little
  190. ** as 1 byte of data.
  191. **
  192. ** SIZE DESCRIPTION
  193. ** 4 Page number of next overflow page
  194. ** * Data
  195. **
  196. ** Freelist pages come in two subtypes: trunk pages and leaf pages. The
  197. ** file header points to the first in a linked list of trunk page. Each trunk
  198. ** page points to multiple leaf pages. The content of a leaf page is
  199. ** unspecified. A trunk page looks like this:
  200. **
  201. ** SIZE DESCRIPTION
  202. ** 4 Page number of next trunk page
  203. ** 4 Number of leaf pointers on this page
  204. ** * zero or more pages numbers of leaves
  205. */
  206. #include "sqliteInt.h"
  207. #include "pager.h"
  208. #include "btree.h"
  209. #include "os.h"
  210. #include <assert.h>
  211. /* Round up a number to the next larger multiple of 8. This is used
  212. ** to force 8-byte alignment on 64-bit architectures.
  213. */
  214. #define ROUND8(x) ((x+7)&~7)
  215. /* The following value is the maximum cell size assuming a maximum page
  216. ** size give above.
  217. */
  218. #define MX_CELL_SIZE(pBt) (pBt->pageSize-8)
  219. /* The maximum number of cells on a single page of the database. This
  220. ** assumes a minimum cell size of 3 bytes. Such small cells will be
  221. ** exceedingly rare, but they are possible.
  222. */
  223. #define MX_CELL(pBt) ((pBt->pageSize-8)/3)
  224. /* Forward declarations */
  225. typedef struct MemPage MemPage;
  226. typedef struct BtLock BtLock;
  227. /*
  228. ** This is a magic string that appears at the beginning of every
  229. ** SQLite database in order to identify the file as a real database.
  230. **
  231. ** You can change this value at compile-time by specifying a
  232. ** -DSQLITE_FILE_HEADER="..." on the compiler command-line. The
  233. ** header must be exactly 16 bytes including the zero-terminator so
  234. ** the string itself should be 15 characters long. If you change
  235. ** the header, then your custom library will not be able to read
  236. ** databases generated by the standard tools and the standard tools
  237. ** will not be able to read databases created by your custom library.
  238. */
  239. #ifndef SQLITE_FILE_HEADER /* 123456789 123456 */
  240. # define SQLITE_FILE_HEADER "SQLite format 3"
  241. #endif
  242. /*
  243. ** Page type flags. An ORed combination of these flags appear as the
  244. ** first byte of on-disk image of every BTree page.
  245. */
  246. #define PTF_INTKEY 0x01
  247. #define PTF_ZERODATA 0x02
  248. #define PTF_LEAFDATA 0x04
  249. #define PTF_LEAF 0x08
  250. /*
  251. ** As each page of the file is loaded into memory, an instance of the following
  252. ** structure is appended and initialized to zero. This structure stores
  253. ** information about the page that is decoded from the raw file page.
  254. **
  255. ** The pParent field points back to the parent page. This allows us to
  256. ** walk up the BTree from any leaf to the root. Care must be taken to
  257. ** unref() the parent page pointer when this page is no longer referenced.
  258. ** The pageDestructor() routine handles that chore.
  259. **
  260. ** Access to all fields of this structure is controlled by the mutex
  261. ** stored in MemPage.pBt->mutex.
  262. */
  263. struct MemPage {
  264. u8 isInit; /* True if previously initialized. MUST BE FIRST! */
  265. u8 idxShift; /* True if Cell indices have changed */
  266. u8 nOverflow; /* Number of overflow cell bodies in aCell[] */
  267. u8 intKey; /* True if intkey flag is set */
  268. u8 leaf; /* True if leaf flag is set */
  269. u8 zeroData; /* True if table stores keys only */
  270. u8 leafData; /* True if tables stores data on leaves only */
  271. u8 hasData; /* True if this page stores data */
  272. u8 hdrOffset; /* 100 for page 1. 0 otherwise */
  273. u8 childPtrSize; /* 0 if leaf==1. 4 if leaf==0 */
  274. u16 maxLocal; /* Copy of BtShared.maxLocal or BtShared.maxLeaf */
  275. u16 minLocal; /* Copy of BtShared.minLocal or BtShared.minLeaf */
  276. u16 cellOffset; /* Index in aData of first cell pointer */
  277. u16 idxParent; /* Index in parent of this node */
  278. u16 nFree; /* Number of free bytes on the page */
  279. u16 nCell; /* Number of cells on this page, local and ovfl */
  280. struct _OvflCell { /* Cells that will not fit on aData[] */
  281. u8 *pCell; /* Pointers to the body of the overflow cell */
  282. u16 idx; /* Insert this cell before idx-th non-overflow cell */
  283. } aOvfl[5];
  284. BtShared *pBt; /* Pointer to BtShared that this page is part of */
  285. u8 *aData; /* Pointer to disk image of the page data */
  286. DbPage *pDbPage; /* Pager page handle */
  287. Pgno pgno; /* Page number for this page */
  288. MemPage *pParent; /* The parent of this page. NULL for root */
  289. };
  290. /*
  291. ** The in-memory image of a disk page has the auxiliary information appended
  292. ** to the end. EXTRA_SIZE is the number of bytes of space needed to hold
  293. ** that extra information.
  294. */
  295. #define EXTRA_SIZE sizeof(MemPage)
  296. /* A Btree handle
  297. **
  298. ** A database connection contains a pointer to an instance of
  299. ** this object for every database file that it has open. This structure
  300. ** is opaque to the database connection. The database connection cannot
  301. ** see the internals of this structure and only deals with pointers to
  302. ** this structure.
  303. **
  304. ** For some database files, the same underlying database cache might be
  305. ** shared between multiple connections. In that case, each contection
  306. ** has it own pointer to this object. But each instance of this object
  307. ** points to the same BtShared object. The database cache and the
  308. ** schema associated with the database file are all contained within
  309. ** the BtShared object.
  310. **
  311. ** All fields in this structure are accessed under sqlite3.mutex.
  312. ** The pBt pointer itself may not be changed while there exists cursors
  313. ** in the referenced BtShared that point back to this Btree since those
  314. ** cursors have to do go through this Btree to find their BtShared and
  315. ** they often do so without holding sqlite3.mutex.
  316. */
  317. struct Btree {
  318. sqlite3 *db; /* The database connection holding this btree */
  319. BtShared *pBt; /* Sharable content of this btree */
  320. u8 inTrans; /* TRANS_NONE, TRANS_READ or TRANS_WRITE */
  321. u8 sharable; /* True if we can share pBt with another db */
  322. u8 locked; /* True if db currently has pBt locked */
  323. int wantToLock; /* Number of nested calls to sqlite3BtreeEnter() */
  324. Btree *pNext; /* List of other sharable Btrees from the same db */
  325. Btree *pPrev; /* Back pointer of the same list */
  326. };
  327. /*
  328. ** Btree.inTrans may take one of the following values.
  329. **
  330. ** If the shared-data extension is enabled, there may be multiple users
  331. ** of the Btree structure. At most one of these may open a write transaction,
  332. ** but any number may have active read transactions.
  333. */
  334. #define TRANS_NONE 0
  335. #define TRANS_READ 1
  336. #define TRANS_WRITE 2
  337. /*
  338. ** An instance of this object represents a single database file.
  339. **
  340. ** A single database file can be in use as the same time by two
  341. ** or more database connections. When two or more connections are
  342. ** sharing the same database file, each connection has it own
  343. ** private Btree object for the file and each of those Btrees points
  344. ** to this one BtShared object. BtShared.nRef is the number of
  345. ** connections currently sharing this database file.
  346. **
  347. ** Fields in this structure are accessed under the BtShared.mutex
  348. ** mutex, except for nRef and pNext which are accessed under the
  349. ** global SQLITE_MUTEX_STATIC_MASTER mutex. The pPager field
  350. ** may not be modified once it is initially set as long as nRef>0.
  351. ** The pSchema field may be set once under BtShared.mutex and
  352. ** thereafter is unchanged as long as nRef>0.
  353. */
  354. struct BtShared {
  355. Pager *pPager; /* The page cache */
  356. sqlite3 *db; /* Database connection currently using this Btree */
  357. BtCursor *pCursor; /* A list of all open cursors */
  358. MemPage *pPage1; /* First page of the database */
  359. u8 inStmt; /* True if we are in a statement subtransaction */
  360. u8 readOnly; /* True if the underlying file is readonly */
  361. u8 maxEmbedFrac; /* Maximum payload as % of total page size */
  362. u8 minEmbedFrac; /* Minimum payload as % of total page size */
  363. u8 minLeafFrac; /* Minimum leaf payload as % of total page size */
  364. u8 pageSizeFixed; /* True if the page size can no longer be changed */
  365. #ifndef SQLITE_OMIT_AUTOVACUUM
  366. u8 autoVacuum; /* True if auto-vacuum is enabled */
  367. u8 incrVacuum; /* True if incr-vacuum is enabled */
  368. Pgno nTrunc; /* Non-zero if the db will be truncated (incr vacuum) */
  369. #endif
  370. u16 pageSize; /* Total number of bytes on a page */
  371. u16 usableSize; /* Number of usable bytes on each page */
  372. int maxLocal; /* Maximum local payload in non-LEAFDATA tables */
  373. int minLocal; /* Minimum local payload in non-LEAFDATA tables */
  374. int maxLeaf; /* Maximum local payload in a LEAFDATA table */
  375. int minLeaf; /* Minimum local payload in a LEAFDATA table */
  376. u8 inTransaction; /* Transaction state */
  377. int nTransaction; /* Number of open transactions (read + write) */
  378. void *pSchema; /* Pointer to space allocated by sqlite3BtreeSchema() */
  379. void (*xFreeSchema)(void*); /* Destructor for BtShared.pSchema */
  380. sqlite3_mutex *mutex; /* Non-recursive mutex required to access this struct */
  381. BusyHandler busyHdr; /* The busy handler for this btree */
  382. #ifndef SQLITE_OMIT_SHARED_CACHE
  383. int nRef; /* Number of references to this structure */
  384. BtShared *pNext; /* Next on a list of sharable BtShared structs */
  385. BtLock *pLock; /* List of locks held on this shared-btree struct */
  386. #endif
  387. };
  388. /*
  389. ** An instance of the following structure is used to hold information
  390. ** about a cell. The parseCellPtr() function fills in this structure
  391. ** based on information extract from the raw disk page.
  392. */
  393. typedef struct CellInfo CellInfo;
  394. struct CellInfo {
  395. u8 *pCell; /* Pointer to the start of cell content */
  396. i64 nKey; /* The key for INTKEY tables, or number of bytes in key */
  397. u32 nData; /* Number of bytes of data */
  398. u32 nPayload; /* Total amount of payload */
  399. u16 nHeader; /* Size of the cell content header in bytes */
  400. u16 nLocal; /* Amount of payload held locally */
  401. u16 iOverflow; /* Offset to overflow page number. Zero if no overflow */
  402. u16 nSize; /* Size of the cell content on the main b-tree page */
  403. };
  404. /*
  405. ** A cursor is a pointer to a particular entry within a particular
  406. ** b-tree within a database file.
  407. **
  408. ** The entry is identified by its MemPage and the index in
  409. ** MemPage.aCell[] of the entry.
  410. **
  411. ** When a single database file can shared by two more database connections,
  412. ** but cursors cannot be shared. Each cursor is associated with a
  413. ** particular database connection identified BtCursor.pBtree.db.
  414. **
  415. ** Fields in this structure are accessed under the BtShared.mutex
  416. ** found at self->pBt->mutex.
  417. */
  418. struct BtCursor {
  419. Btree *pBtree; /* The Btree to which this cursor belongs */
  420. BtShared *pBt; /* The BtShared this cursor points to */
  421. BtCursor *pNext, *pPrev; /* Forms a linked list of all cursors */
  422. int (*xCompare)(void*,int,const void*,int,const void*); /* Key comp func */
  423. void *pArg; /* First arg to xCompare() */
  424. Pgno pgnoRoot; /* The root page of this tree */
  425. MemPage *pPage; /* Page that contains the entry */
  426. int idx; /* Index of the entry in pPage->aCell[] */
  427. CellInfo info; /* A parse of the cell we are pointing at */
  428. u8 wrFlag; /* True if writable */
  429. u8 eState; /* One of the CURSOR_XXX constants (see below) */
  430. void *pKey; /* Saved key that was cursor's last known position */
  431. i64 nKey; /* Size of pKey, or last integer key */
  432. int skip; /* (skip<0) -> Prev() is a no-op. (skip>0) -> Next() is */
  433. #ifndef SQLITE_OMIT_INCRBLOB
  434. u8 isIncrblobHandle; /* True if this cursor is an incr. io handle */
  435. Pgno *aOverflow; /* Cache of overflow page locations */
  436. #endif
  437. };
  438. /*
  439. ** Potential values for BtCursor.eState.
  440. **
  441. ** CURSOR_VALID:
  442. ** Cursor points to a valid entry. getPayload() etc. may be called.
  443. **
  444. ** CURSOR_INVALID:
  445. ** Cursor does not point to a valid entry. This can happen (for example)
  446. ** because the table is empty or because BtreeCursorFirst() has not been
  447. ** called.
  448. **
  449. ** CURSOR_REQUIRESEEK:
  450. ** The table that this cursor was opened on still exists, but has been
  451. ** modified since the cursor was last used. The cursor position is saved
  452. ** in variables BtCursor.pKey and BtCursor.nKey. When a cursor is in
  453. ** this state, restoreOrClearCursorPosition() can be called to attempt to
  454. ** seek the cursor to the saved position.
  455. **
  456. ** CURSOR_FAULT:
  457. ** A unrecoverable error (an I/O error or a malloc failure) has occurred
  458. ** on a different connection that shares the BtShared cache with this
  459. ** cursor. The error has left the cache in an inconsistent state.
  460. ** Do nothing else with this cursor. Any attempt to use the cursor
  461. ** should return the error code stored in BtCursor.skip
  462. */
  463. #define CURSOR_INVALID 0
  464. #define CURSOR_VALID 1
  465. #define CURSOR_REQUIRESEEK 2
  466. #define CURSOR_FAULT 3
  467. /*
  468. ** The TRACE macro will print high-level status information about the
  469. ** btree operation when the global variable sqlite3_btree_trace is
  470. ** enabled.
  471. */
  472. #if SQLITE_TEST
  473. # define TRACE(X) if( sqlite3_btree_trace ){ printf X; fflush(stdout); }
  474. #else
  475. # define TRACE(X)
  476. #endif
  477. /*
  478. ** Routines to read and write variable-length integers. These used to
  479. ** be defined locally, but now we use the varint routines in the util.c
  480. ** file.
  481. */
  482. #define getVarint sqlite3GetVarint
  483. #define getVarint32(A,B) ((*B=*(A))<=0x7f?1:sqlite3GetVarint32(A,B))
  484. #define putVarint sqlite3PutVarint
  485. /* The database page the PENDING_BYTE occupies. This page is never used.
  486. ** TODO: This macro is very similary to PAGER_MJ_PGNO() in pager.c. They
  487. ** should possibly be consolidated (presumably in pager.h).
  488. **
  489. ** If disk I/O is omitted (meaning that the database is stored purely
  490. ** in memory) then there is no pending byte.
  491. */
  492. #ifdef SQLITE_OMIT_DISKIO
  493. # define PENDING_BYTE_PAGE(pBt) 0x7fffffff
  494. #else
  495. # define PENDING_BYTE_PAGE(pBt) ((PENDING_BYTE/(pBt)->pageSize)+1)
  496. #endif
  497. /*
  498. ** A linked list of the following structures is stored at BtShared.pLock.
  499. ** Locks are added (or upgraded from READ_LOCK to WRITE_LOCK) when a cursor
  500. ** is opened on the table with root page BtShared.iTable. Locks are removed
  501. ** from this list when a transaction is committed or rolled back, or when
  502. ** a btree handle is closed.
  503. */
  504. struct BtLock {
  505. Btree *pBtree; /* Btree handle holding this lock */
  506. Pgno iTable; /* Root page of table */
  507. u8 eLock; /* READ_LOCK or WRITE_LOCK */
  508. BtLock *pNext; /* Next in BtShared.pLock list */
  509. };
  510. /* Candidate values for BtLock.eLock */
  511. #define READ_LOCK 1
  512. #define WRITE_LOCK 2
  513. /*
  514. ** These macros define the location of the pointer-map entry for a
  515. ** database page. The first argument to each is the number of usable
  516. ** bytes on each page of the database (often 1024). The second is the
  517. ** page number to look up in the pointer map.
  518. **
  519. ** PTRMAP_PAGENO returns the database page number of the pointer-map
  520. ** page that stores the required pointer. PTRMAP_PTROFFSET returns
  521. ** the offset of the requested map entry.
  522. **
  523. ** If the pgno argument passed to PTRMAP_PAGENO is a pointer-map page,
  524. ** then pgno is returned. So (pgno==PTRMAP_PAGENO(pgsz, pgno)) can be
  525. ** used to test if pgno is a pointer-map page. PTRMAP_ISPAGE implements
  526. ** this test.
  527. */
  528. #define PTRMAP_PAGENO(pBt, pgno) ptrmapPageno(pBt, pgno)
  529. #define PTRMAP_PTROFFSET(pBt, pgno) (5*(pgno-ptrmapPageno(pBt, pgno)-1))
  530. #define PTRMAP_ISPAGE(pBt, pgno) (PTRMAP_PAGENO((pBt),(pgno))==(pgno))
  531. /*
  532. ** The pointer map is a lookup table that identifies the parent page for
  533. ** each child page in the database file. The parent page is the page that
  534. ** contains a pointer to the child. Every page in the database contains
  535. ** 0 or 1 parent pages. (In this context 'database page' refers
  536. ** to any page that is not part of the pointer map itself.) Each pointer map
  537. ** entry consists of a single byte 'type' and a 4 byte parent page number.
  538. ** The PTRMAP_XXX identifiers below are the valid types.
  539. **
  540. ** The purpose of the pointer map is to facility moving pages from one
  541. ** position in the file to another as part of autovacuum. When a page
  542. ** is moved, the pointer in its parent must be updated to point to the
  543. ** new location. The pointer map is used to locate the parent page quickly.
  544. **
  545. ** PTRMAP_ROOTPAGE: The database page is a root-page. The page-number is not
  546. ** used in this case.
  547. **
  548. ** PTRMAP_FREEPAGE: The database page is an unused (free) page. The page-number
  549. ** is not used in this case.
  550. **
  551. ** PTRMAP_OVERFLOW1: The database page is the first page in a list of
  552. ** overflow pages. The page number identifies the page that
  553. ** contains the cell with a pointer to this overflow page.
  554. **
  555. ** PTRMAP_OVERFLOW2: The database page is the second or later page in a list of
  556. ** overflow pages. The page-number identifies the previous
  557. ** page in the overflow page list.
  558. **
  559. ** PTRMAP_BTREE: The database page is a non-root btree page. The page number
  560. ** identifies the parent page in the btree.
  561. */
  562. #define PTRMAP_ROOTPAGE 1
  563. #define PTRMAP_FREEPAGE 2
  564. #define PTRMAP_OVERFLOW1 3
  565. #define PTRMAP_OVERFLOW2 4
  566. #define PTRMAP_BTREE 5
  567. /* A bunch of assert() statements to check the transaction state variables
  568. ** of handle p (type Btree*) are internally consistent.
  569. */
  570. #define btreeIntegrity(p) \
  571. assert( p->pBt->inTransaction!=TRANS_NONE || p->pBt->nTransaction==0 ); \
  572. assert( p->pBt->inTransaction>=p->inTrans );
  573. /*
  574. ** The ISAUTOVACUUM macro is used within balance_nonroot() to determine
  575. ** if the database supports auto-vacuum or not. Because it is used
  576. ** within an expression that is an argument to another macro
  577. ** (sqliteMallocRaw), it is not possible to use conditional compilation.
  578. ** So, this macro is defined instead.
  579. */
  580. #ifndef SQLITE_OMIT_AUTOVACUUM
  581. #define ISAUTOVACUUM (pBt->autoVacuum)
  582. #else
  583. #define ISAUTOVACUUM 0
  584. #endif
  585. /*
  586. ** This structure is passed around through all the sanity checking routines
  587. ** in order to keep track of some global state information.
  588. */
  589. typedef struct IntegrityCk IntegrityCk;
  590. struct IntegrityCk {
  591. BtShared *pBt; /* The tree being checked out */
  592. Pager *pPager; /* The associated pager. Also accessible by pBt->pPager */
  593. int nPage; /* Number of pages in the database */
  594. int *anRef; /* Number of times each page is referenced */
  595. int mxErr; /* Stop accumulating errors when this reaches zero */
  596. char *zErrMsg; /* An error message. NULL if no errors seen. */
  597. int nErr; /* Number of messages written to zErrMsg so far */
  598. };
  599. /*
  600. ** Read or write a two- and four-byte big-endian integer values.
  601. */
  602. #define get2byte(x) ((x)[0]<<8 | (x)[1])
  603. #define put2byte(p,v) ((p)[0] = (v)>>8, (p)[1] = (v))
  604. #define get4byte sqlite3Get4byte
  605. #define put4byte sqlite3Put4byte
  606. /*
  607. ** Internal routines that should be accessed by the btree layer only.
  608. */
  609. int sqlite3BtreeGetPage(BtShared*, Pgno, MemPage**, int);
  610. int sqlite3BtreeInitPage(MemPage *pPage, MemPage *pParent);
  611. void sqlite3BtreeParseCellPtr(MemPage*, u8*, CellInfo*);
  612. void sqlite3BtreeParseCell(MemPage*, int, CellInfo*);
  613. #ifdef SQLITE_TEST
  614. u8 *sqlite3BtreeFindCell(MemPage *pPage, int iCell);
  615. #endif
  616. int sqlite3BtreeRestoreOrClearCursorPosition(BtCursor *pCur);
  617. void sqlite3BtreeGetTempCursor(BtCursor *pCur, BtCursor *pTempCur);
  618. void sqlite3BtreeReleaseTempCursor(BtCursor *pCur);
  619. int sqlite3BtreeIsRootPage(MemPage *pPage);
  620. void sqlite3BtreeMoveToParent(BtCursor *pCur);