Many hyperlinks are disabled.
Use anonymous login
to enable hyperlinks.
Overview
Comment: | Combine various boolean variables in the BtShared structure into a single boolean vector. Also make performance improvement simplifications to sqlite3BtreeMovetoUnpacked(). |
---|---|
Downloads: | Tarball | ZIP archive |
Timelines: | family | ancestors | descendants | both | trunk |
Files: | files | file ages | folders |
SHA1: |
119493318e0ad4c2858fe1484b0d7166 |
User & Date: | drh 2012-01-05 23:32:06.822 |
Context
2012-01-06
| ||
13:58 | Add missing finish_test to the end of the zerodamage.test module. Disable the zerodamage module if virtual tables are omitted from the build. (check-in: d2a5685b5e user: drh tags: trunk) | |
2012-01-05
| ||
23:32 | Combine various boolean variables in the BtShared structure into a single boolean vector. Also make performance improvement simplifications to sqlite3BtreeMovetoUnpacked(). (check-in: 119493318e user: drh tags: trunk) | |
21:19 | Make sure the name of the shared memory file has two zero-terminators in the UNIX VFS, so that sqlite3_uri_parameter() will work correctly on that name. (check-in: 3d088ba5e3 user: drh tags: trunk) | |
Changes
Changes to src/backup.c.
︙ | ︙ | |||
701 702 703 704 705 706 707 | ** checks this assumption - (p->rc) should be set to either SQLITE_DONE ** or an error code. */ sqlite3_backup_step(&b, 0x7FFFFFFF); assert( b.rc!=SQLITE_OK ); rc = sqlite3_backup_finish(&b); if( rc==SQLITE_OK ){ | | | 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 | ** checks this assumption - (p->rc) should be set to either SQLITE_DONE ** or an error code. */ sqlite3_backup_step(&b, 0x7FFFFFFF); assert( b.rc!=SQLITE_OK ); rc = sqlite3_backup_finish(&b); if( rc==SQLITE_OK ){ pTo->pBt->btsFlags &= ~BTS_PAGESIZE_FIXED; }else{ sqlite3PagerClearCache(sqlite3BtreePager(b.pDest)); } assert( sqlite3BtreeIsInTrans(pTo)==0 ); sqlite3BtreeLeave(pFrom); sqlite3BtreeLeave(pTo); |
︙ | ︙ |
Changes to src/btree.c.
︙ | ︙ | |||
239 240 241 242 243 244 245 | if( !p->sharable ){ return SQLITE_OK; } /* If some other connection is holding an exclusive lock, the ** requested lock may not be obtained. */ | | | | 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 | if( !p->sharable ){ return SQLITE_OK; } /* If some other connection is holding an exclusive lock, the ** requested lock may not be obtained. */ if( pBt->pWriter!=p && (pBt->btsFlags & BTS_EXCLUSIVE)!=0 ){ sqlite3ConnectionBlocked(p->db, pBt->pWriter->db); return SQLITE_LOCKED_SHAREDCACHE; } for(pIter=pBt->pLock; pIter; pIter=pIter->pNext){ /* The condition (pIter->eLock!=eLock) in the following if(...) ** statement is a simplification of: ** ** (eLock==WRITE_LOCK || pIter->eLock==WRITE_LOCK) ** ** since we know that if eLock==WRITE_LOCK, then no other connection ** may hold a WRITE_LOCK on any table in this file (since there can ** only be a single writer). */ assert( pIter->eLock==READ_LOCK || pIter->eLock==WRITE_LOCK ); assert( eLock==READ_LOCK || pIter->pBtree==p || pIter->eLock==READ_LOCK); if( pIter->pBtree!=p && pIter->iTable==iTab && pIter->eLock!=eLock ){ sqlite3ConnectionBlocked(p->db, pIter->pBtree->db); if( eLock==WRITE_LOCK ){ assert( p==pBt->pWriter ); pBt->btsFlags |= BTS_PENDING; } return SQLITE_LOCKED_SHAREDCACHE; } } return SQLITE_OK; } #endif /* !SQLITE_OMIT_SHARED_CACHE */ |
︙ | ︙ | |||
348 349 350 351 352 353 354 | #ifndef SQLITE_OMIT_SHARED_CACHE /* ** Release all the table locks (locks obtained via calls to ** the setSharedCacheTableLock() procedure) held by Btree object p. ** ** This function assumes that Btree p has an open read or write | | | | | < | | | | < | 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 | #ifndef SQLITE_OMIT_SHARED_CACHE /* ** Release all the table locks (locks obtained via calls to ** the setSharedCacheTableLock() procedure) held by Btree object p. ** ** This function assumes that Btree p has an open read or write ** transaction. If it does not, then the BTS_PENDING flag ** may be incorrectly cleared. */ static void clearAllSharedCacheTableLocks(Btree *p){ BtShared *pBt = p->pBt; BtLock **ppIter = &pBt->pLock; assert( sqlite3BtreeHoldsMutex(p) ); assert( p->sharable || 0==*ppIter ); assert( p->inTrans>0 ); while( *ppIter ){ BtLock *pLock = *ppIter; assert( (pBt->btsFlags & BTS_EXCLUSIVE)==0 || pBt->pWriter==pLock->pBtree ); assert( pLock->pBtree->inTrans>=pLock->eLock ); if( pLock->pBtree==p ){ *ppIter = pLock->pNext; assert( pLock->iTable!=1 || pLock==&p->lock ); if( pLock->iTable!=1 ){ sqlite3_free(pLock); } }else{ ppIter = &pLock->pNext; } } assert( (pBt->btsFlags & BTS_PENDING)==0 || pBt->pWriter ); if( pBt->pWriter==p ){ pBt->pWriter = 0; pBt->btsFlags &= ~(BTS_EXCLUSIVE|BTS_PENDING); }else if( pBt->nTransaction==2 ){ /* This function is called when Btree p is concluding its ** transaction. If there currently exists a writer, and p is not ** that writer, then the number of locks held by connections other ** than the writer must be about to drop to zero. In this case ** set the BTS_PENDING flag to 0. ** ** If there is not currently a writer, then BTS_PENDING must ** be zero already. So this next line is harmless in that case. */ pBt->btsFlags &= ~BTS_PENDING; } } /* ** This function changes all write-locks held by Btree p into read-locks. */ static void downgradeAllSharedCacheTableLocks(Btree *p){ BtShared *pBt = p->pBt; if( pBt->pWriter==p ){ BtLock *pLock; pBt->pWriter = 0; pBt->btsFlags &= ~(BTS_EXCLUSIVE|BTS_PENDING); for(pLock=pBt->pLock; pLock; pLock=pLock->pNext){ assert( pLock->eLock==READ_LOCK || pLock->pBtree==p ); pLock->eLock = READ_LOCK; } } } |
︙ | ︙ | |||
1260 1261 1262 1263 1264 1265 1266 | assert( pPage->pBt!=0 ); assert( sqlite3PagerIswriteable(pPage->pDbPage) ); assert( start>=pPage->hdrOffset+6+pPage->childPtrSize ); assert( (start + size) <= (int)pPage->pBt->usableSize ); assert( sqlite3_mutex_held(pPage->pBt->mutex) ); assert( size>=0 ); /* Minimum cell size is 4 */ | | | 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 | assert( pPage->pBt!=0 ); assert( sqlite3PagerIswriteable(pPage->pDbPage) ); assert( start>=pPage->hdrOffset+6+pPage->childPtrSize ); assert( (start + size) <= (int)pPage->pBt->usableSize ); assert( sqlite3_mutex_held(pPage->pBt->mutex) ); assert( size>=0 ); /* Minimum cell size is 4 */ if( pPage->pBt->btsFlags & BTS_SECURE_DELETE ){ /* Overwrite deleted information with zeros when the secure_delete ** option is enabled */ memset(&data[start], 0, size); } /* Add the space back into the linked list of freeblocks. Note that ** even though the freeblock list was checked by btreeInitPage(), |
︙ | ︙ | |||
1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 | pPage->intKey = 0; pPage->hasData = 0; pPage->maxLocal = pBt->maxLocal; pPage->minLocal = pBt->minLocal; }else{ return SQLITE_CORRUPT_BKPT; } return SQLITE_OK; } /* ** Initialize the auxiliary information for a disk block. ** ** Return SQLITE_OK on success. If we see that the page does | > | 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 | pPage->intKey = 0; pPage->hasData = 0; pPage->maxLocal = pBt->maxLocal; pPage->minLocal = pBt->minLocal; }else{ return SQLITE_CORRUPT_BKPT; } pPage->max1bytePayload = pBt->max1bytePayload; return SQLITE_OK; } /* ** Initialize the auxiliary information for a disk block. ** ** Return SQLITE_OK on success. If we see that the page does |
︙ | ︙ | |||
1498 1499 1500 1501 1502 1503 1504 | u16 first; assert( sqlite3PagerPagenumber(pPage->pDbPage)==pPage->pgno ); assert( sqlite3PagerGetExtra(pPage->pDbPage) == (void*)pPage ); assert( sqlite3PagerGetData(pPage->pDbPage) == data ); assert( sqlite3PagerIswriteable(pPage->pDbPage) ); assert( sqlite3_mutex_held(pBt->mutex) ); | | | 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 | u16 first; assert( sqlite3PagerPagenumber(pPage->pDbPage)==pPage->pgno ); assert( sqlite3PagerGetExtra(pPage->pDbPage) == (void*)pPage ); assert( sqlite3PagerGetData(pPage->pDbPage) == data ); assert( sqlite3PagerIswriteable(pPage->pDbPage) ); assert( sqlite3_mutex_held(pBt->mutex) ); if( pBt->btsFlags & BTS_SECURE_DELETE ){ memset(&data[hdr], 0, pBt->usableSize - hdr); } data[hdr] = (char)flags; first = hdr + 8 + 4*((flags&PTF_LEAF)==0 ?1:0); memset(&data[hdr+1], 0, 4); data[hdr+7] = 0; put2byte(&data[hdr+5], pBt->usableSize); |
︙ | ︙ | |||
1851 1852 1853 1854 1855 1856 1857 | pBt->openFlags = (u8)flags; pBt->db = db; sqlite3PagerSetBusyhandler(pBt->pPager, btreeInvokeBusyHandler, pBt); p->pBt = pBt; pBt->pCursor = 0; pBt->pPage1 = 0; | | | | | 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 | pBt->openFlags = (u8)flags; pBt->db = db; sqlite3PagerSetBusyhandler(pBt->pPager, btreeInvokeBusyHandler, pBt); p->pBt = pBt; pBt->pCursor = 0; pBt->pPage1 = 0; if( sqlite3PagerIsreadonly(pBt->pPager) ) pBt->btsFlags |= BTS_READ_ONLY; #ifdef SQLITE_SECURE_DELETE pBt->btsFlags |= BTS_SECURE_DELETE; #endif pBt->pageSize = (zDbHeader[16]<<8) | (zDbHeader[17]<<16); if( pBt->pageSize<512 || pBt->pageSize>SQLITE_MAX_PAGE_SIZE || ((pBt->pageSize-1)&pBt->pageSize)!=0 ){ pBt->pageSize = 0; #ifndef SQLITE_OMIT_AUTOVACUUM /* If the magic name ":memory:" will create an in-memory database, then ** leave the autoVacuum mode at 0 (do not auto-vacuum), even if ** SQLITE_DEFAULT_AUTOVACUUM is true. On the other hand, if ** SQLITE_OMIT_MEMORYDB has been defined, then ":memory:" is just a ** regular file-name. In this case the auto-vacuum applies as per normal. */ if( zFilename && !isMemdb ){ pBt->autoVacuum = (SQLITE_DEFAULT_AUTOVACUUM ? 1 : 0); pBt->incrVacuum = (SQLITE_DEFAULT_AUTOVACUUM==2 ? 1 : 0); } #endif nReserve = 0; }else{ nReserve = zDbHeader[20]; pBt->btsFlags |= BTS_PAGESIZE_FIXED; #ifndef SQLITE_OMIT_AUTOVACUUM pBt->autoVacuum = (get4byte(&zDbHeader[36 + 4*4])?1:0); pBt->incrVacuum = (get4byte(&zDbHeader[36 + 7*4])?1:0); #endif } rc = sqlite3PagerSetPagesize(pBt->pPager, &pBt->pageSize, nReserve); if( rc ) goto btree_open_out; |
︙ | ︙ | |||
2162 2163 2164 2165 2166 2167 2168 | ** of the database file used for locking (beginning at PENDING_BYTE, ** the first byte past the 1GB boundary, 0x40000000) needs to occur ** at the beginning of a page. ** ** If parameter nReserve is less than zero, then the number of reserved ** bytes per page is left unchanged. ** | | | | | 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 | ** of the database file used for locking (beginning at PENDING_BYTE, ** the first byte past the 1GB boundary, 0x40000000) needs to occur ** at the beginning of a page. ** ** If parameter nReserve is less than zero, then the number of reserved ** bytes per page is left unchanged. ** ** If the iFix!=0 then the BTS_PAGESIZE_FIXED flag is set so that the page size ** and autovacuum mode can no longer be changed. */ int sqlite3BtreeSetPageSize(Btree *p, int pageSize, int nReserve, int iFix){ int rc = SQLITE_OK; BtShared *pBt = p->pBt; assert( nReserve>=-1 && nReserve<=255 ); sqlite3BtreeEnter(p); if( pBt->btsFlags & BTS_PAGESIZE_FIXED ){ sqlite3BtreeLeave(p); return SQLITE_READONLY; } if( nReserve<0 ){ nReserve = pBt->pageSize - pBt->usableSize; } assert( nReserve>=0 && nReserve<=255 ); if( pageSize>=512 && pageSize<=SQLITE_MAX_PAGE_SIZE && ((pageSize-1)&pageSize)==0 ){ assert( (pageSize & 7)==0 ); assert( !pBt->pPage1 && !pBt->pCursor ); pBt->pageSize = (u32)pageSize; freeTempSpace(pBt); } rc = sqlite3PagerSetPagesize(pBt->pPager, &pBt->pageSize, nReserve); pBt->usableSize = pBt->pageSize - (u16)nReserve; if( iFix ) pBt->btsFlags |= BTS_PAGESIZE_FIXED; sqlite3BtreeLeave(p); return rc; } /* ** Return the currently defined page size */ |
︙ | ︙ | |||
2227 2228 2229 2230 2231 2232 2233 | sqlite3BtreeEnter(p); n = sqlite3PagerMaxPageCount(p->pBt->pPager, mxPage); sqlite3BtreeLeave(p); return n; } /* | | | | > | | | 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 | sqlite3BtreeEnter(p); n = sqlite3PagerMaxPageCount(p->pBt->pPager, mxPage); sqlite3BtreeLeave(p); return n; } /* ** Set the BTS_SECURE_DELETE flag if newFlag is 0 or 1. If newFlag is -1, ** then make no changes. Always return the value of the BTS_SECURE_DELETE ** setting after the change. */ int sqlite3BtreeSecureDelete(Btree *p, int newFlag){ int b; if( p==0 ) return 0; sqlite3BtreeEnter(p); if( newFlag>=0 ){ p->pBt->btsFlags &= ~BTS_SECURE_DELETE; if( newFlag ) p->pBt->btsFlags |= BTS_SECURE_DELETE; } b = (p->pBt->btsFlags & BTS_SECURE_DELETE)!=0; sqlite3BtreeLeave(p); return b; } #endif /* !defined(SQLITE_OMIT_PAGER_PRAGMAS) || !defined(SQLITE_OMIT_VACUUM) */ /* ** Change the 'auto-vacuum' property of the database. If the 'autoVacuum' ** parameter is non-zero, then auto-vacuum mode is enabled. If zero, it ** is disabled. The default value for the auto-vacuum property is ** determined by the SQLITE_DEFAULT_AUTOVACUUM macro. */ int sqlite3BtreeSetAutoVacuum(Btree *p, int autoVacuum){ #ifdef SQLITE_OMIT_AUTOVACUUM return SQLITE_READONLY; #else BtShared *pBt = p->pBt; int rc = SQLITE_OK; u8 av = (u8)autoVacuum; sqlite3BtreeEnter(p); if( (pBt->btsFlags & BTS_PAGESIZE_FIXED)!=0 && (av ?1:0)!=pBt->autoVacuum ){ rc = SQLITE_READONLY; }else{ pBt->autoVacuum = av ?1:0; pBt->incrVacuum = av==2 ?1:0; } sqlite3BtreeLeave(p); return rc; |
︙ | ︙ | |||
2333 2334 2335 2336 2337 2338 2339 | rc = SQLITE_NOTADB; if( memcmp(page1, zMagicHeader, 16)!=0 ){ goto page1_init_failed; } #ifdef SQLITE_OMIT_WAL if( page1[18]>1 ){ | | | | | 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 | rc = SQLITE_NOTADB; if( memcmp(page1, zMagicHeader, 16)!=0 ){ goto page1_init_failed; } #ifdef SQLITE_OMIT_WAL if( page1[18]>1 ){ pBt->btsFlags |= BTS_READ_ONLY; } if( page1[19]>1 ){ goto page1_init_failed; } #else if( page1[18]>2 ){ pBt->btsFlags |= BTS_READ_ONLY; } if( page1[19]>2 ){ goto page1_init_failed; } /* If the write version is set to 2, this database should be accessed ** in WAL mode. If the log is not already open, open it now. Then ** return SQLITE_OK and return without populating BtShared.pPage1. ** The caller detects this and calls this function again. This is ** required as the version of page 1 currently in the page1 buffer ** may not be the latest version - there may be a newer one in the log ** file. */ if( page1[19]==2 && (pBt->btsFlags & BTS_NO_WAL)==0 ){ int isOpen = 0; rc = sqlite3PagerOpenWal(pBt->pPager, &isOpen); if( rc!=SQLITE_OK ){ goto page1_init_failed; }else if( isOpen==0 ){ releasePage(pPage1); return SQLITE_OK; |
︙ | ︙ | |||
2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 | ** 17 bytes long, 0 to N bytes of payload, and an optional 4 byte overflow ** page pointer. */ pBt->maxLocal = (u16)((pBt->usableSize-12)*64/255 - 23); pBt->minLocal = (u16)((pBt->usableSize-12)*32/255 - 23); pBt->maxLeaf = (u16)(pBt->usableSize - 35); pBt->minLeaf = (u16)((pBt->usableSize-12)*32/255 - 23); assert( pBt->maxLeaf + 23 <= MX_CELL_SIZE(pBt) ); pBt->pPage1 = pPage1; pBt->nPage = nPage; return SQLITE_OK; page1_init_failed: releasePage(pPage1); | > > > > > | 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 | ** 17 bytes long, 0 to N bytes of payload, and an optional 4 byte overflow ** page pointer. */ pBt->maxLocal = (u16)((pBt->usableSize-12)*64/255 - 23); pBt->minLocal = (u16)((pBt->usableSize-12)*32/255 - 23); pBt->maxLeaf = (u16)(pBt->usableSize - 35); pBt->minLeaf = (u16)((pBt->usableSize-12)*32/255 - 23); if( pBt->maxLocal>127 ){ pBt->max1bytePayload = 127; }else{ pBt->max1bytePayload = pBt->maxLocal; } assert( pBt->maxLeaf + 23 <= MX_CELL_SIZE(pBt) ); pBt->pPage1 = pPage1; pBt->nPage = nPage; return SQLITE_OK; page1_init_failed: releasePage(pPage1); |
︙ | ︙ | |||
2494 2495 2496 2497 2498 2499 2500 | assert( pBt->usableSize<=pBt->pageSize && pBt->usableSize+255>=pBt->pageSize); data[20] = (u8)(pBt->pageSize - pBt->usableSize); data[21] = 64; data[22] = 32; data[23] = 32; memset(&data[24], 0, 100-24); zeroPage(pP1, PTF_INTKEY|PTF_LEAF|PTF_LEAFDATA ); | | | 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 | assert( pBt->usableSize<=pBt->pageSize && pBt->usableSize+255>=pBt->pageSize); data[20] = (u8)(pBt->pageSize - pBt->usableSize); data[21] = 64; data[22] = 32; data[23] = 32; memset(&data[24], 0, 100-24); zeroPage(pP1, PTF_INTKEY|PTF_LEAF|PTF_LEAFDATA ); pBt->btsFlags |= BTS_PAGESIZE_FIXED; #ifndef SQLITE_OMIT_AUTOVACUUM assert( pBt->autoVacuum==1 || pBt->autoVacuum==0 ); assert( pBt->incrVacuum==1 || pBt->incrVacuum==0 ); put4byte(&data[36 + 4*4], pBt->autoVacuum); put4byte(&data[36 + 7*4], pBt->incrVacuum); #endif pBt->nPage = 1; |
︙ | ︙ | |||
2558 2559 2560 2561 2562 2563 2564 | ** is requested, this is a no-op. */ if( p->inTrans==TRANS_WRITE || (p->inTrans==TRANS_READ && !wrflag) ){ goto trans_begun; } /* Write transactions are not possible on a read-only database */ | | | > > | 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 | ** is requested, this is a no-op. */ if( p->inTrans==TRANS_WRITE || (p->inTrans==TRANS_READ && !wrflag) ){ goto trans_begun; } /* Write transactions are not possible on a read-only database */ if( (pBt->btsFlags & BTS_READ_ONLY)!=0 && wrflag ){ rc = SQLITE_READONLY; goto trans_begun; } #ifndef SQLITE_OMIT_SHARED_CACHE /* If another database handle has already opened a write transaction ** on this shared-btree structure and a second write transaction is ** requested, return SQLITE_LOCKED. */ if( (wrflag && pBt->inTransaction==TRANS_WRITE) || (pBt->btsFlags & BTS_PENDING)!=0 ){ pBlock = pBt->pWriter->db; }else if( wrflag>1 ){ BtLock *pIter; for(pIter=pBt->pLock; pIter; pIter=pIter->pNext){ if( pIter->pBtree!=p ){ pBlock = pIter->pBtree->db; break; |
︙ | ︙ | |||
2592 2593 2594 2595 2596 2597 2598 | /* Any read-only or read-write transaction implies a read-lock on ** page 1. So if some other shared-cache client already has a write-lock ** on page 1, the transaction cannot be opened. */ rc = querySharedCacheTableLock(p, MASTER_ROOT, READ_LOCK); if( SQLITE_OK!=rc ) goto trans_begun; | > | | | 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 | /* Any read-only or read-write transaction implies a read-lock on ** page 1. So if some other shared-cache client already has a write-lock ** on page 1, the transaction cannot be opened. */ rc = querySharedCacheTableLock(p, MASTER_ROOT, READ_LOCK); if( SQLITE_OK!=rc ) goto trans_begun; pBt->btsFlags &= ~BTS_INITIALLY_EMPTY; if( pBt->nPage==0 ) pBt->btsFlags |= BTS_INITIALLY_EMPTY; do { /* Call lockBtree() until either pBt->pPage1 is populated or ** lockBtree() returns something other than SQLITE_OK. lockBtree() ** may return SQLITE_OK but leave pBt->pPage1 set to 0 if after ** reading page 1 it discovers that the page-size of the database ** file is not pBt->pageSize. In this case lockBtree() will update ** pBt->pageSize to the page-size of the file on disk. */ while( pBt->pPage1==0 && SQLITE_OK==(rc = lockBtree(pBt)) ); if( rc==SQLITE_OK && wrflag ){ if( (pBt->btsFlags & BTS_READ_ONLY)!=0 ){ rc = SQLITE_READONLY; }else{ rc = sqlite3PagerBegin(pBt->pPager,wrflag>1,sqlite3TempInMemory(p->db)); if( rc==SQLITE_OK ){ rc = newDatabase(pBt); } } |
︙ | ︙ | |||
2641 2642 2643 2644 2645 2646 2647 | pBt->inTransaction = p->inTrans; } if( wrflag ){ MemPage *pPage1 = pBt->pPage1; #ifndef SQLITE_OMIT_SHARED_CACHE assert( !pBt->pWriter ); pBt->pWriter = p; | > | | 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 | pBt->inTransaction = p->inTrans; } if( wrflag ){ MemPage *pPage1 = pBt->pPage1; #ifndef SQLITE_OMIT_SHARED_CACHE assert( !pBt->pWriter ); pBt->pWriter = p; pBt->btsFlags &= ~BTS_EXCLUSIVE; if( wrflag>1 ) pBt->btsFlags |= BTS_EXCLUSIVE; #endif /* If the db-size header field is incorrect (as it may be if an old ** client has been writing the database file), update it now. Doing ** this sooner rather than later means the database size can safely ** re-read the database size from page 1 if a savepoint or transaction ** rollback occurs within the transaction. |
︙ | ︙ | |||
3370 3371 3372 3373 3374 3375 3376 | ** using the sqlite3BtreeSavepoint() function. */ int sqlite3BtreeBeginStmt(Btree *p, int iStatement){ int rc; BtShared *pBt = p->pBt; sqlite3BtreeEnter(p); assert( p->inTrans==TRANS_WRITE ); | | | 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 | ** using the sqlite3BtreeSavepoint() function. */ int sqlite3BtreeBeginStmt(Btree *p, int iStatement){ int rc; BtShared *pBt = p->pBt; sqlite3BtreeEnter(p); assert( p->inTrans==TRANS_WRITE ); assert( (pBt->btsFlags & BTS_READ_ONLY)==0 ); assert( iStatement>0 ); assert( iStatement>p->db->nSavepoint ); assert( pBt->inTransaction==TRANS_WRITE ); /* At the pager level, a statement transaction is a savepoint with ** an index greater than all savepoints created explicitly using ** SQL statements. It is illegal to open, release or rollback any ** such savepoints while the statement transaction savepoint is active. |
︙ | ︙ | |||
3405 3406 3407 3408 3409 3410 3411 | if( p && p->inTrans==TRANS_WRITE ){ BtShared *pBt = p->pBt; assert( op==SAVEPOINT_RELEASE || op==SAVEPOINT_ROLLBACK ); assert( iSavepoint>=0 || (iSavepoint==-1 && op==SAVEPOINT_ROLLBACK) ); sqlite3BtreeEnter(p); rc = sqlite3PagerSavepoint(pBt->pPager, op, iSavepoint); if( rc==SQLITE_OK ){ | > | > | 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 | if( p && p->inTrans==TRANS_WRITE ){ BtShared *pBt = p->pBt; assert( op==SAVEPOINT_RELEASE || op==SAVEPOINT_ROLLBACK ); assert( iSavepoint>=0 || (iSavepoint==-1 && op==SAVEPOINT_ROLLBACK) ); sqlite3BtreeEnter(p); rc = sqlite3PagerSavepoint(pBt->pPager, op, iSavepoint); if( rc==SQLITE_OK ){ if( iSavepoint<0 && (pBt->btsFlags & BTS_INITIALLY_EMPTY)!=0 ){ pBt->nPage = 0; } rc = newDatabase(pBt); pBt->nPage = get4byte(28 + pBt->pPage1->aData); /* The database size was written into the offset 28 of the header ** when the transaction started, so we know that the value at offset ** 28 is nonzero. */ assert( pBt->nPage>0 ); |
︙ | ︙ | |||
3475 3476 3477 3478 3479 3480 3481 | assert( wrFlag==0 || !hasReadConflicts(p, iTable) ); /* Assert that the caller has opened the required transaction. */ assert( p->inTrans>TRANS_NONE ); assert( wrFlag==0 || p->inTrans==TRANS_WRITE ); assert( pBt->pPage1 && pBt->pPage1->aData ); | | | 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 | assert( wrFlag==0 || !hasReadConflicts(p, iTable) ); /* Assert that the caller has opened the required transaction. */ assert( p->inTrans>TRANS_NONE ); assert( wrFlag==0 || p->inTrans==TRANS_WRITE ); assert( pBt->pPage1 && pBt->pPage1->aData ); if( NEVER(wrFlag && (pBt->btsFlags & BTS_READ_ONLY)!=0) ){ return SQLITE_READONLY; } if( iTable==1 && btreePagecount(pBt)==0 ){ assert( wrFlag==0 ); iTable = 0; } |
︙ | ︙ | |||
4555 4556 4557 4558 4559 4560 4561 | ** page is less than 16384 bytes and may be stored as a 2-byte ** varint. This information is used to attempt to avoid parsing ** the entire cell by checking for the cases where the record is ** stored entirely within the b-tree page by inspecting the first ** 2 bytes of the cell. */ int nCell = pCell[0]; | < | | | | 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 | ** page is less than 16384 bytes and may be stored as a 2-byte ** varint. This information is used to attempt to avoid parsing ** the entire cell by checking for the cases where the record is ** stored entirely within the b-tree page by inspecting the first ** 2 bytes of the cell. */ int nCell = pCell[0]; if( nCell<=pPage->max1bytePayload /* && (pCell+nCell)<pPage->aDataEnd */ ){ /* This branch runs if the record-size field of the cell is a ** single byte varint and the record fits entirely on the main ** b-tree page. */ testcase( pCell+nCell+1==pPage->aDataEnd ); c = sqlite3VdbeRecordCompare(nCell, (void*)&pCell[1], pIdxKey); }else if( !(pCell[1] & 0x80) && (nCell = ((nCell&0x7f)<<7) + pCell[1])<=pPage->maxLocal /* && (pCell+nCell+2)<=pPage->aDataEnd */ ){ /* The record-size field is a 2 byte varint and the record ** fits entirely on the main b-tree page. */ testcase( pCell+nCell+2==pPage->aDataEnd ); c = sqlite3VdbeRecordCompare(nCell, (void*)&pCell[2], pIdxKey); }else{ /* The record flows over onto one or more overflow pages. In |
︙ | ︙ | |||
5112 5113 5114 5115 5116 5117 5118 | /* Increment the free page count on pPage1 */ rc = sqlite3PagerWrite(pPage1->pDbPage); if( rc ) goto freepage_out; nFree = get4byte(&pPage1->aData[36]); put4byte(&pPage1->aData[36], nFree+1); | | | 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 | /* Increment the free page count on pPage1 */ rc = sqlite3PagerWrite(pPage1->pDbPage); if( rc ) goto freepage_out; nFree = get4byte(&pPage1->aData[36]); put4byte(&pPage1->aData[36], nFree+1); if( pBt->btsFlags & BTS_SECURE_DELETE ){ /* If the secure_delete option is enabled, then ** always fully overwrite deleted information with zeros. */ if( (!pPage && ((rc = btreeGetPage(pBt, iPage, &pPage, 0))!=0) ) || ((rc = sqlite3PagerWrite(pPage->pDbPage))!=0) ){ goto freepage_out; |
︙ | ︙ | |||
5173 5174 5175 5176 5177 5178 5179 | ** to 3.6.0 or later) we should consider fixing the conditional above ** to read "usableSize/4-2" instead of "usableSize/4-8". */ rc = sqlite3PagerWrite(pTrunk->pDbPage); if( rc==SQLITE_OK ){ put4byte(&pTrunk->aData[4], nLeaf+1); put4byte(&pTrunk->aData[8+nLeaf*4], iPage); | | | 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 | ** to 3.6.0 or later) we should consider fixing the conditional above ** to read "usableSize/4-2" instead of "usableSize/4-8". */ rc = sqlite3PagerWrite(pTrunk->pDbPage); if( rc==SQLITE_OK ){ put4byte(&pTrunk->aData[4], nLeaf+1); put4byte(&pTrunk->aData[8+nLeaf*4], iPage); if( pPage && (pBt->btsFlags & BTS_SECURE_DELETE)==0 ){ sqlite3PagerDontWrite(pPage->pDbPage); } rc = btreeSetHasContent(pBt, iPage); } TRACE(("FREE-PAGE: %d leaf on trunk page %d\n",pPage->pgno,pTrunk->pgno)); goto freepage_out; } |
︙ | ︙ | |||
6014 6015 6016 6017 6018 6019 6020 | ** later on. ** ** But not if we are in secure-delete mode. In secure-delete mode, ** the dropCell() routine will overwrite the entire cell with zeroes. ** In this case, temporarily copy the cell into the aOvflSpace[] ** buffer. It will be copied out again as soon as the aSpace[] buffer ** is allocated. */ | | | 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 | ** later on. ** ** But not if we are in secure-delete mode. In secure-delete mode, ** the dropCell() routine will overwrite the entire cell with zeroes. ** In this case, temporarily copy the cell into the aOvflSpace[] ** buffer. It will be copied out again as soon as the aSpace[] buffer ** is allocated. */ if( pBt->btsFlags & BTS_SECURE_DELETE ){ int iOff; iOff = SQLITE_PTR_TO_INT(apDiv[i]) - SQLITE_PTR_TO_INT(pParent->aData); if( (iOff+szNew[i])>(int)pBt->usableSize ){ rc = SQLITE_CORRUPT_BKPT; memset(apOld, 0, (i+1)*sizeof(MemPage*)); goto balance_cleanup; |
︙ | ︙ | |||
6756 6757 6758 6759 6760 6761 6762 | if( pCur->eState==CURSOR_FAULT ){ assert( pCur->skipNext!=SQLITE_OK ); return pCur->skipNext; } assert( cursorHoldsMutex(pCur) ); | | > | 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 | if( pCur->eState==CURSOR_FAULT ){ assert( pCur->skipNext!=SQLITE_OK ); return pCur->skipNext; } assert( cursorHoldsMutex(pCur) ); assert( pCur->wrFlag && pBt->inTransaction==TRANS_WRITE && (pBt->btsFlags & BTS_READ_ONLY)==0 ); assert( hasSharedCacheTableLock(p, pCur->pgnoRoot, pCur->pKeyInfo!=0, 2) ); /* Assert that the caller has been consistent. If this cursor was opened ** expecting an index b-tree, then the caller should be inserting blob ** keys with no associated data. If the cursor was opened expecting an ** intkey table, the caller should be inserting integer keys with a ** blob of associated data. */ |
︙ | ︙ | |||
6885 6886 6887 6888 6889 6890 6891 | MemPage *pPage; /* Page to delete cell from */ unsigned char *pCell; /* Pointer to cell to delete */ int iCellIdx; /* Index of cell to delete */ int iCellDepth; /* Depth of node containing pCell */ assert( cursorHoldsMutex(pCur) ); assert( pBt->inTransaction==TRANS_WRITE ); | | | 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 | MemPage *pPage; /* Page to delete cell from */ unsigned char *pCell; /* Pointer to cell to delete */ int iCellIdx; /* Index of cell to delete */ int iCellDepth; /* Depth of node containing pCell */ assert( cursorHoldsMutex(pCur) ); assert( pBt->inTransaction==TRANS_WRITE ); assert( (pBt->btsFlags & BTS_READ_ONLY)==0 ); assert( pCur->wrFlag ); assert( hasSharedCacheTableLock(p, pCur->pgnoRoot, pCur->pKeyInfo!=0, 2) ); assert( !hasReadConflicts(p, pCur->pgnoRoot) ); if( NEVER(pCur->aiIdx[pCur->iPage]>=pCur->apPage[pCur->iPage]->nCell) || NEVER(pCur->eState!=CURSOR_VALID) ){ |
︙ | ︙ | |||
7006 7007 7008 7009 7010 7011 7012 | MemPage *pRoot; Pgno pgnoRoot; int rc; int ptfFlags; /* Page-type flage for the root page of new table */ assert( sqlite3BtreeHoldsMutex(p) ); assert( pBt->inTransaction==TRANS_WRITE ); | | | 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 | MemPage *pRoot; Pgno pgnoRoot; int rc; int ptfFlags; /* Page-type flage for the root page of new table */ assert( sqlite3BtreeHoldsMutex(p) ); assert( pBt->inTransaction==TRANS_WRITE ); assert( (pBt->btsFlags & BTS_READ_ONLY)==0 ); #ifdef SQLITE_OMIT_AUTOVACUUM rc = allocateBtreePage(pBt, &pRoot, &pgnoRoot, 1, 0); if( rc ){ return rc; } #else |
︙ | ︙ | |||
7380 7381 7382 7383 7384 7385 7386 | assert( idx>=0 && idx<=15 ); *pMeta = get4byte(&pBt->pPage1->aData[36 + idx*4]); /* If auto-vacuum is disabled in this build and this is an auto-vacuum ** database, mark the database as read-only. */ #ifdef SQLITE_OMIT_AUTOVACUUM | | > > | 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 | assert( idx>=0 && idx<=15 ); *pMeta = get4byte(&pBt->pPage1->aData[36 + idx*4]); /* If auto-vacuum is disabled in this build and this is an auto-vacuum ** database, mark the database as read-only. */ #ifdef SQLITE_OMIT_AUTOVACUUM if( idx==BTREE_LARGEST_ROOT_PAGE && *pMeta>0 ){ pBt->btsFlags |= BTS_READ_ONLY; } #endif sqlite3BtreeLeave(p); } /* ** Write meta-information back into the database. Meta[0] is |
︙ | ︙ | |||
8180 8181 8182 8183 8184 8185 8186 | ** (c) the connection holds a write-lock on the table (if required), ** (d) there are no conflicting read-locks, and ** (e) the cursor points at a valid row of an intKey table. */ if( !pCsr->wrFlag ){ return SQLITE_READONLY; } | > | | 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 | ** (c) the connection holds a write-lock on the table (if required), ** (d) there are no conflicting read-locks, and ** (e) the cursor points at a valid row of an intKey table. */ if( !pCsr->wrFlag ){ return SQLITE_READONLY; } assert( (pCsr->pBt->btsFlags & BTS_READ_ONLY)==0 && pCsr->pBt->inTransaction==TRANS_WRITE ); assert( hasSharedCacheTableLock(pCsr->pBtree, pCsr->pgnoRoot, 0, 2) ); assert( !hasReadConflicts(pCsr->pBtree, pCsr->pgnoRoot) ); assert( pCsr->apPage[pCsr->iPage]->intKey ); return accessPayload(pCsr, offset, amt, (unsigned char *)z, 1); } |
︙ | ︙ | |||
8220 8221 8222 8223 8224 8225 8226 | int rc; /* Return code */ assert( iVersion==1 || iVersion==2 ); /* If setting the version fields to 1, do not automatically open the ** WAL connection, even if the version fields are currently set to 2. */ | > | | | 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 | int rc; /* Return code */ assert( iVersion==1 || iVersion==2 ); /* If setting the version fields to 1, do not automatically open the ** WAL connection, even if the version fields are currently set to 2. */ pBt->btsFlags &= ~BTS_NO_WAL; if( iVersion==1 ) pBt->btsFlags |= BTS_NO_WAL; rc = sqlite3BtreeBeginTrans(pBtree, 0); if( rc==SQLITE_OK ){ u8 *aData = pBt->pPage1->aData; if( aData[18]!=(u8)iVersion || aData[19]!=(u8)iVersion ){ rc = sqlite3BtreeBeginTrans(pBtree, 2); if( rc==SQLITE_OK ){ rc = sqlite3PagerWrite(pBt->pPage1->pDbPage); if( rc==SQLITE_OK ){ aData[18] = (u8)iVersion; aData[19] = (u8)iVersion; } } } } pBt->btsFlags &= ~BTS_NO_WAL; return rc; } |
Changes to src/btreeInt.h.
︙ | ︙ | |||
273 274 275 276 277 278 279 280 281 282 283 284 285 286 | u8 isInit; /* True if previously initialized. MUST BE FIRST! */ u8 nOverflow; /* Number of overflow cell bodies in aCell[] */ u8 intKey; /* True if intkey flag is set */ u8 leaf; /* True if leaf flag is set */ u8 hasData; /* True if this page stores data */ u8 hdrOffset; /* 100 for page 1. 0 otherwise */ u8 childPtrSize; /* 0 if leaf==1. 4 if leaf==0 */ u16 maxLocal; /* Copy of BtShared.maxLocal or BtShared.maxLeaf */ u16 minLocal; /* Copy of BtShared.minLocal or BtShared.minLeaf */ u16 cellOffset; /* Index in aData of first cell pointer */ u16 nFree; /* Number of free bytes on the page */ u16 nCell; /* Number of cells on this page, local and ovfl */ u16 maskPage; /* Mask for page offset */ struct _OvflCell { /* Cells that will not fit on aData[] */ | > | 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 | u8 isInit; /* True if previously initialized. MUST BE FIRST! */ u8 nOverflow; /* Number of overflow cell bodies in aCell[] */ u8 intKey; /* True if intkey flag is set */ u8 leaf; /* True if leaf flag is set */ u8 hasData; /* True if this page stores data */ u8 hdrOffset; /* 100 for page 1. 0 otherwise */ u8 childPtrSize; /* 0 if leaf==1. 4 if leaf==0 */ u8 max1bytePayload; /* min(maxLocal,127) */ u16 maxLocal; /* Copy of BtShared.maxLocal or BtShared.maxLeaf */ u16 minLocal; /* Copy of BtShared.minLocal or BtShared.minLeaf */ u16 cellOffset; /* Index in aData of first cell pointer */ u16 nFree; /* Number of free bytes on the page */ u16 nCell; /* Number of cells on this page, local and ovfl */ u16 maskPage; /* Mask for page offset */ struct _OvflCell { /* Cells that will not fit on aData[] */ |
︙ | ︙ | |||
403 404 405 406 407 408 409 | ** This feature is included to help prevent writer-starvation. */ struct BtShared { Pager *pPager; /* The page cache */ sqlite3 *db; /* Database connection currently using this Btree */ BtCursor *pCursor; /* A list of all open cursors */ MemPage *pPage1; /* First page of the database */ | < < < < > | < < > > > > > > > > > > > | 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 | ** This feature is included to help prevent writer-starvation. */ struct BtShared { Pager *pPager; /* The page cache */ sqlite3 *db; /* Database connection currently using this Btree */ BtCursor *pCursor; /* A list of all open cursors */ MemPage *pPage1; /* First page of the database */ u8 openFlags; /* Flags to sqlite3BtreeOpen() */ #ifndef SQLITE_OMIT_AUTOVACUUM u8 autoVacuum; /* True if auto-vacuum is enabled */ u8 incrVacuum; /* True if incr-vacuum is enabled */ #endif u8 inTransaction; /* Transaction state */ u8 max1bytePayload; /* Maximum first byte of cell for a 1-byte payload */ u16 btsFlags; /* Boolean parameters. See BTS_* macros below */ u16 maxLocal; /* Maximum local payload in non-LEAFDATA tables */ u16 minLocal; /* Minimum local payload in non-LEAFDATA tables */ u16 maxLeaf; /* Maximum local payload in a LEAFDATA table */ u16 minLeaf; /* Minimum local payload in a LEAFDATA table */ u32 pageSize; /* Total number of bytes on a page */ u32 usableSize; /* Number of usable bytes on each page */ int nTransaction; /* Number of open transactions (read + write) */ u32 nPage; /* Number of pages in the database */ void *pSchema; /* Pointer to space allocated by sqlite3BtreeSchema() */ void (*xFreeSchema)(void*); /* Destructor for BtShared.pSchema */ sqlite3_mutex *mutex; /* Non-recursive mutex required to access this object */ Bitvec *pHasContent; /* Set of pages moved to free-list this transaction */ #ifndef SQLITE_OMIT_SHARED_CACHE int nRef; /* Number of references to this structure */ BtShared *pNext; /* Next on a list of sharable BtShared structs */ BtLock *pLock; /* List of locks held on this shared-btree struct */ Btree *pWriter; /* Btree with currently open write transaction */ #endif u8 *pTmpSpace; /* BtShared.pageSize bytes of space for tmp use */ }; /* ** Allowed values for BtShared.btsFlags */ #define BTS_READ_ONLY 0x0001 /* Underlying file is readonly */ #define BTS_PAGESIZE_FIXED 0x0002 /* Page size can no longer be changed */ #define BTS_SECURE_DELETE 0x0004 /* PRAGMA secure_delete is enabled */ #define BTS_INITIALLY_EMPTY 0x0008 /* Database was empty at trans start */ #define BTS_NO_WAL 0x0010 /* Do not open write-ahead-log files */ #define BTS_EXCLUSIVE 0x0020 /* pWriter has an exclusive lock */ #define BTS_PENDING 0x0040 /* Waiting for read-locks to clear */ /* ** An instance of the following structure is used to hold information ** about a cell. The parseCellPtr() function fills in this structure ** based on information extract from the raw disk page. */ typedef struct CellInfo CellInfo; struct CellInfo { |
︙ | ︙ |