Many hyperlinks are disabled.
Use anonymous login
to enable hyperlinks.
Changes In Branch wal-trace-375 Excluding Merge-Ins
This is equivalent to a diff from e5ca59e6 to 1725aa75
2011-02-19
| ||
14:19 | Changes which attempt to address an obscure SQLITE_PROTOCOL error. (Leaf check-in: 1725aa75 user: drh tags: wal-trace-375) | |
2011-01-19
| ||
21:58 | Comment improvements in pcache1.c. No changes to code. (check-in: 9660a0a2 user: drh tags: trunk) | |
2011-01-18
| ||
17:34 | Pull over all the latest trunk changes. (check-in: ca86d04b user: drh tags: wal-trace-375) | |
17:03 | Do not use mutexes in the pcache implementation unless SQLITE_ENABLE_MEMORY_MANAGMENT is defined. This is a performance enhancement. A side effect is that pcaches will not steal pages from one another unless ENABLE_MEMORY_MANAGEMENT is set, or unless SQLITE_THREADSAFE=0. (check-in: e5ca59e6 user: drh tags: trunk) | |
16:13 | Get all test cases working with the mutex-free-pcache implementation. (Closed-Leaf check-in: 2dc98d29 user: drh tags: mutex-free-pcache) | |
2011-01-17
| ||
18:30 | Fix a typo in the documentation for sqlite3_stmt_readonly(). (check-in: 56417a33 user: drh tags: trunk) | |
Changes to src/wal.c.
︙ | ︙ | |||
248 249 250 251 252 253 254 255 256 257 258 259 260 261 | */ #if defined(SQLITE_TEST) && defined(SQLITE_DEBUG) int sqlite3WalTrace = 0; # define WALTRACE(X) if(sqlite3WalTrace) sqlite3DebugPrintf X #else # define WALTRACE(X) #endif /* ** The maximum (and only) versions of the wal and wal-index formats ** that may be interpreted by this version of SQLite. ** ** If a client begins recovering a WAL file and finds that (a) the checksum ** values in the wal-header are correct and (b) the version field is not | > > > > > > > > > > > > > > > | 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 | */ #if defined(SQLITE_TEST) && defined(SQLITE_DEBUG) int sqlite3WalTrace = 0; # define WALTRACE(X) if(sqlite3WalTrace) sqlite3DebugPrintf X #else # define WALTRACE(X) #endif /* ** WAL tracing logic added to search for an SQLITE_PROTOCOL error. */ static void walTrace(const char *zFormat, ...){ va_list ap; char zMsg[100]; va_start(ap, zFormat); sqlite3_vsnprintf(sizeof(zMsg), zMsg, zFormat, ap); va_end(ap); #ifdef SQLITE_WAL_TRACE fprintf(stdout, "WALTRACE: [%s]\n", zMsg); fflush(stdout); #endif sqlite3_log(99, "%s", zMsg); } /* ** The maximum (and only) versions of the wal and wal-index formats ** that may be interpreted by this version of SQLite. ** ** If a client begins recovering a WAL file and finds that (a) the checksum ** values in the wal-header are correct and (b) the version field is not |
︙ | ︙ | |||
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 | /* Enlarge the pWal->apWiData[] array if required */ if( pWal->nWiData<=iPage ){ int nByte = sizeof(u32*)*(iPage+1); volatile u32 **apNew; apNew = (volatile u32 **)sqlite3_realloc((void *)pWal->apWiData, nByte); if( !apNew ){ *ppPage = 0; return SQLITE_NOMEM; } memset((void*)&apNew[pWal->nWiData], 0, sizeof(u32*)*(iPage+1-pWal->nWiData)); pWal->apWiData = apNew; pWal->nWiData = iPage+1; } /* Request a pointer to the required page from the VFS */ if( pWal->apWiData[iPage]==0 ){ if( pWal->exclusiveMode==WAL_HEAPMEMORY_MODE ){ pWal->apWiData[iPage] = (u32 volatile *)sqlite3MallocZero(WALINDEX_PGSZ); if( !pWal->apWiData[iPage] ) rc = SQLITE_NOMEM; }else{ rc = sqlite3OsShmMap(pWal->pDbFd, iPage, WALINDEX_PGSZ, pWal->writeLock, (void volatile **)&pWal->apWiData[iPage] ); } } *ppPage = pWal->apWiData[iPage]; assert( iPage==0 || *ppPage || rc!=SQLITE_OK ); return rc; } | > > | 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 | /* Enlarge the pWal->apWiData[] array if required */ if( pWal->nWiData<=iPage ){ int nByte = sizeof(u32*)*(iPage+1); volatile u32 **apNew; apNew = (volatile u32 **)sqlite3_realloc((void *)pWal->apWiData, nByte); if( !apNew ){ *ppPage = 0; walTrace("realloc(%d) in walIndexPage()", nByte); return SQLITE_NOMEM; } memset((void*)&apNew[pWal->nWiData], 0, sizeof(u32*)*(iPage+1-pWal->nWiData)); pWal->apWiData = apNew; pWal->nWiData = iPage+1; } /* Request a pointer to the required page from the VFS */ if( pWal->apWiData[iPage]==0 ){ if( pWal->exclusiveMode==WAL_HEAPMEMORY_MODE ){ pWal->apWiData[iPage] = (u32 volatile *)sqlite3MallocZero(WALINDEX_PGSZ); if( !pWal->apWiData[iPage] ) rc = SQLITE_NOMEM; }else{ rc = sqlite3OsShmMap(pWal->pDbFd, iPage, WALINDEX_PGSZ, pWal->writeLock, (void volatile **)&pWal->apWiData[iPage] ); } if( rc ) walTrace("xShmMap():%d in walIndexPage(iPage=%d)",rc,iPage); } *ppPage = pWal->apWiData[iPage]; assert( iPage==0 || *ppPage || rc!=SQLITE_OK ); return rc; } |
︙ | ︙ | |||
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 | /* If the first attempt failed, it might have been due to a race ** with a writer. So get a WRITE lock and try again. */ assert( badHdr==0 || pWal->writeLock==0 ); if( badHdr && SQLITE_OK==(rc = walLockExclusive(pWal, WAL_WRITE_LOCK, 1)) ){ pWal->writeLock = 1; if( SQLITE_OK==(rc = walIndexPage(pWal, 0, &page0)) ){ badHdr = walIndexTryHdr(pWal, pChanged); if( badHdr ){ /* If the wal-index header is still malformed even while holding ** a WRITE lock, it can only mean that the header is corrupted and ** needs to be reconstructed. So run recovery to do exactly that. */ rc = walIndexRecover(pWal); *pChanged = 1; } } pWal->writeLock = 0; walUnlockExclusive(pWal, WAL_WRITE_LOCK, 1); } /* If the header is read successfully, check the version number to make ** sure the wal-index was not constructed with some future format that ** this version of SQLite cannot understand. */ if( badHdr==0 && pWal->hdr.iVersion!=WALINDEX_MAX_VERSION ){ rc = SQLITE_CANTOPEN_BKPT; | > > > > | 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 | /* If the first attempt failed, it might have been due to a race ** with a writer. So get a WRITE lock and try again. */ assert( badHdr==0 || pWal->writeLock==0 ); if( badHdr && SQLITE_OK==(rc = walLockExclusive(pWal, WAL_WRITE_LOCK, 1)) ){ pWal->writeLock = 1; walTrace("trying walIndexTryHdr w/lock"); if( SQLITE_OK==(rc = walIndexPage(pWal, 0, &page0)) ){ badHdr = walIndexTryHdr(pWal, pChanged); if( badHdr ){ /* If the wal-index header is still malformed even while holding ** a WRITE lock, it can only mean that the header is corrupted and ** needs to be reconstructed. So run recovery to do exactly that. */ walTrace("walIndexTryHdr() failed w/lock"); rc = walIndexRecover(pWal); if( rc ) walTrace("walIndexRecover():%d", rc); *pChanged = 1; } } pWal->writeLock = 0; walUnlockExclusive(pWal, WAL_WRITE_LOCK, 1); } else if(badHdr) walTrace("walLockExcl():%d in walIndexReadHdr()", rc); /* If the header is read successfully, check the version number to make ** sure the wal-index was not constructed with some future format that ** this version of SQLite cannot understand. */ if( badHdr==0 && pWal->hdr.iVersion!=WALINDEX_MAX_VERSION ){ rc = SQLITE_CANTOPEN_BKPT; |
︙ | ︙ | |||
1947 1948 1949 1950 1951 1952 1953 | u32 mxReadMark; /* Largest aReadMark[] value */ int mxI; /* Index of largest aReadMark[] value */ int i; /* Loop counter */ int rc = SQLITE_OK; /* Return code */ assert( pWal->readLock<0 ); /* Not currently locked */ | | > > > > > > > > > > > > > > > > > > > | | 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 | u32 mxReadMark; /* Largest aReadMark[] value */ int mxI; /* Index of largest aReadMark[] value */ int i; /* Loop counter */ int rc = SQLITE_OK; /* Return code */ assert( pWal->readLock<0 ); /* Not currently locked */ /* Take steps to avoid spinning forever if there is a protocol error. ** ** Circumstances that cause a RETRY should only last for the briefest ** instances of time. No I/O or other system calls are done while the ** locks are held, so the locks should not be held for very long. But ** if we are unlucky, another process that is holding a lock might get ** paged out or take a page-fault that is time-consuming to resolve, ** during the few nanoseconds that it is holding the lock. In that case, ** it might take longer than normal for the lock to free. ** ** After 5 RETRYs, we begin calling sqlite3OsSleep(). The first few ** calls to sqlite3OsSleep() have a delay of 1 microsecond. Really this ** is more of a scheduler yield than an actual delay. But on the 10th ** an subsequent retries, the delays start becoming longer and longer, ** so that on the 100th (and last) RETRY we delay for 21 milliseconds. ** The total delay time before giving up is less than 1 second. */ if( cnt>5 ){ int nDelay = 1; /* Pause time in microseconds */ walTrace("cnt=%d",cnt); if( cnt>100 ) return SQLITE_PROTOCOL; if( cnt>=10 ) nDelay = (cnt-9)*238; /* Max delay 21ms. Total delay 996ms */ sqlite3OsSleep(pWal->pVfs, nDelay); } if( !useWal ){ rc = walIndexReadHdr(pWal, pChanged); if( rc==SQLITE_BUSY ){ /* If there is not a recovery running in another thread or process ** then convert BUSY errors to WAL_RETRY. If recovery is known to |
︙ | ︙ | |||
2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 | ** ** However, if frames have been appended to the log (or if the log ** is wrapped and written for that matter) before the READ_LOCK(0) ** is obtained, that is not necessarily true. A checkpointer may ** have started to backfill the appended frames but crashed before ** it finished. Leaving a corrupt image in the database file. */ walUnlockShared(pWal, WAL_READ_LOCK(0)); return WAL_RETRY; } pWal->readLock = 0; return SQLITE_OK; }else if( rc!=SQLITE_BUSY ){ return rc; } } /* If we get this far, it means that the reader will want to use ** the WAL to get at content from recent commits. The job now is ** to select one of the aReadMark[] entries that is closest to ** but not exceeding pWal->hdr.mxFrame and lock that entry. */ mxReadMark = 0; mxI = 0; for(i=1; i<WAL_NREADER; i++){ u32 thisMark = pInfo->aReadMark[i]; if( mxReadMark<=thisMark && thisMark<=pWal->hdr.mxFrame ){ assert( thisMark!=READMARK_NOT_USED ); mxReadMark = thisMark; mxI = i; } } | > > | < < < < < < < < < < < < < < > | > > > > > > > | 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 | ** ** However, if frames have been appended to the log (or if the log ** is wrapped and written for that matter) before the READ_LOCK(0) ** is obtained, that is not necessarily true. A checkpointer may ** have started to backfill the appended frames but crashed before ** it finished. Leaving a corrupt image in the database file. */ walTrace("wal read/write race - writer won"); walUnlockShared(pWal, WAL_READ_LOCK(0)); return WAL_RETRY; } pWal->readLock = 0; return SQLITE_OK; }else if( rc!=SQLITE_BUSY ){ walTrace("walLockShared(0):%d in walTryBeginRead", rc); return rc; } } /* If we get this far, it means that the reader will want to use ** the WAL to get at content from recent commits. The job now is ** to select one of the aReadMark[] entries that is closest to ** but not exceeding pWal->hdr.mxFrame and lock that entry. */ mxReadMark = 0; mxI = 0; for(i=1; i<WAL_NREADER; i++){ u32 thisMark = pInfo->aReadMark[i]; if( mxReadMark<=thisMark && thisMark<=pWal->hdr.mxFrame ){ assert( thisMark!=READMARK_NOT_USED ); mxReadMark = thisMark; mxI = i; } } /* There was once an "if" here. The extra "{" is to preserve indentation. */ { if( mxReadMark < pWal->hdr.mxFrame || mxI==0 ){ for(i=1; i<WAL_NREADER; i++){ rc = walLockExclusive(pWal, WAL_READ_LOCK(i), 1); if( rc==SQLITE_OK ){ mxReadMark = pInfo->aReadMark[i] = pWal->hdr.mxFrame; mxI = i; walUnlockExclusive(pWal, WAL_READ_LOCK(i), 1); break; }else if( rc!=SQLITE_BUSY ){ walTrace("walLockExclusive(%d):%d", i, rc); return rc; } } } if( mxI==0 ){ assert( rc==SQLITE_BUSY ); walTrace("all readlocks busy: cannot set read mark"); return WAL_RETRY; } rc = walLockShared(pWal, WAL_READ_LOCK(mxI)); if( rc ){ walTrace("walLockShared(mxI=%d):%d", mxI, rc); return rc==SQLITE_BUSY ? WAL_RETRY : rc; } /* Now that the read-lock has been obtained, check that neither the ** value in the aReadMark[] array or the contents of the wal-index ** header have changed. ** ** It is necessary to check that the wal-index header did not change |
︙ | ︙ | |||
2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 | int rc = SQLITE_OK; int cnt; if( pWal->readLock==0 ){ volatile WalCkptInfo *pInfo = walCkptInfo(pWal); assert( pInfo->nBackfill==pWal->hdr.mxFrame ); if( pInfo->nBackfill>0 ){ rc = walLockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1); if( rc==SQLITE_OK ){ /* If all readers are using WAL_READ_LOCK(0) (in other words if no ** readers are currently using the WAL), then the transactions ** frames will overwrite the start of the existing log. Update the ** wal-index header to reflect this. ** ** In theory it would be Ok to update the cache of the header only ** at this point. But updating the actual wal-index header is also ** safe and means there is no special case for sqlite3WalUndo() ** to handle if this transaction is rolled back. */ int i; /* Loop counter */ u32 *aSalt = pWal->hdr.aSalt; /* Big-endian salt values */ pWal->nCkpt++; pWal->hdr.mxFrame = 0; sqlite3Put4byte((u8*)&aSalt[0], 1 + sqlite3Get4byte((u8*)&aSalt[0])); | > > | | 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 | int rc = SQLITE_OK; int cnt; if( pWal->readLock==0 ){ volatile WalCkptInfo *pInfo = walCkptInfo(pWal); assert( pInfo->nBackfill==pWal->hdr.mxFrame ); if( pInfo->nBackfill>0 ){ u32 salt1; sqlite3_randomness(4, &salt1); rc = walLockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1); if( rc==SQLITE_OK ){ /* If all readers are using WAL_READ_LOCK(0) (in other words if no ** readers are currently using the WAL), then the transactions ** frames will overwrite the start of the existing log. Update the ** wal-index header to reflect this. ** ** In theory it would be Ok to update the cache of the header only ** at this point. But updating the actual wal-index header is also ** safe and means there is no special case for sqlite3WalUndo() ** to handle if this transaction is rolled back. */ int i; /* Loop counter */ u32 *aSalt = pWal->hdr.aSalt; /* Big-endian salt values */ pWal->nCkpt++; pWal->hdr.mxFrame = 0; sqlite3Put4byte((u8*)&aSalt[0], 1 + sqlite3Get4byte((u8*)&aSalt[0])); aSalt[1] = salt1; walIndexWriteHdr(pWal); pInfo->nBackfill = 0; for(i=1; i<WAL_NREADER; i++) pInfo->aReadMark[i] = READMARK_NOT_USED; assert( pInfo->aReadMark[0]==0 ); walUnlockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1); }else if( rc!=SQLITE_BUSY ){ return rc; |
︙ | ︙ |