pager.c

来自「sqlite最新源码」· C语言 代码 · 共 1,620 行 · 第 1/5 页

/*
** Journal files begin with the following magic string.  The data
** was obtained from /dev/random.  It is used only as a sanity check.
**
** Since version 2.8.0, the journal format contains additional sanity
** checking information.  If the power fails while the journal is being
** written, semi-random garbage data might appear in the journal
** file after power is restored.  If an attempt is then made
** to roll the journal back, the database could be corrupted.  The additional
** sanity checking data is an attempt to discover the garbage in the
** journal and ignore it.
**
** The sanity checking information for the new journal format consists
** of a 32-bit checksum on each page of data.  The checksum covers both
** the page number and the pPager->pageSize bytes of data for the page.
** This cksum is initialized to a 32-bit random value that appears in the
** journal file right after the header.  The random initializer is important,
** because garbage data that appears at the end of a journal is likely
** data that was once in other files that have now been deleted.  If the
** garbage data came from an obsolete journal file, the checksums might
** be correct.  But by initializing the checksum to random value which
** is different for every journal, we minimize that risk.
*/
static const unsigned char aJournalMagic[] = {
  0xd9, 0xd5, 0x05, 0xf9, 0x20, 0xa1, 0x63, 0xd7,
};

/*
** The size of the of each page record in the journal is given by
** the following macro.
*/
#define JOURNAL_PG_SZ(pPager)  ((pPager->pageSize) + 8)

/*
** The journal header size for this pager. This is usually the same 
** size as a single disk sector. See also setSectorSize().
*/
#define JOURNAL_HDR_SZ(pPager) (pPager->sectorSize)

/*
** The macro MEMDB is true if we are dealing with an in-memory database.
** We do this as a macro so that if the SQLITE_OMIT_MEMORYDB macro is set,
** the value of MEMDB will be a constant and the compiler will optimize
** out code that would never execute.
*/
#ifdef SQLITE_OMIT_MEMORYDB
# define MEMDB 0
#else
# define MEMDB pPager->memDb
#endif

/*
** The maximum legal page number is (2^31 - 1).
*/
#define PAGER_MAX_PGNO 2147483647

#ifndef NDEBUG 
/*
** Usage:
**
**   assert( assert_pager_state(pPager) );
*/
static int assert_pager_state(Pager *pPager){

  /* A temp-file is always in PAGER_EXCLUSIVE or PAGER_SYNCED state. */
  assert( pPager->tempFile==0 || pPager->state>=PAGER_EXCLUSIVE );

  /* The changeCountDone flag is always set for temp-files */
  assert( pPager->tempFile==0 || pPager->changeCountDone );

  return 1;
}
#endif

/*
** Return true if it is necessary to write page *pPg into the sub-journal.
** A page needs to be written into the sub-journal if there exists one
** or more open savepoints for which:
**
**   * The page-number is less than or equal to PagerSavepoint.nOrig, and
**   * The bit corresponding to the page-number is not set in
**     PagerSavepoint.pInSavepoint.
*/
static int subjRequiresPage(PgHdr *pPg){
  Pgno pgno = pPg->pgno;
  Pager *pPager = pPg->pPager;
  int i;
  for(i=0; i<pPager->nSavepoint; i++){
    PagerSavepoint *p = &pPager->aSavepoint[i];
    if( p->nOrig>=pgno && 0==sqlite3BitvecTest(p->pInSavepoint, pgno) ){
      return 1;
    }
  }
  return 0;
}

/*
** Return true if the page is already in the journal file.
*/
static int pageInJournal(PgHdr *pPg){
  return sqlite3BitvecTest(pPg->pPager->pInJournal, pPg->pgno);
}

/*
** Read a 32-bit integer from the given file descriptor.  Store the integer
** that is read in *pRes.  Return SQLITE_OK if everything worked, or an
** error code is something goes wrong.
**
** All values are stored on disk as big-endian.
*/
static int read32bits(sqlite3_file *fd, i64 offset, u32 *pRes){
  unsigned char ac[4];
  int rc = sqlite3OsRead(fd, ac, sizeof(ac), offset);
  if( rc==SQLITE_OK ){
    *pRes = sqlite3Get4byte(ac);
  }
  return rc;
}

/*
** Write a 32-bit integer into a string buffer in big-endian byte order.
*/
#define put32bits(A,B)  sqlite3Put4byte((u8*)A,B)

/*
** Write a 32-bit integer into the given file descriptor.  Return SQLITE_OK
** on success or an error code is something goes wrong.
*/
static int write32bits(sqlite3_file *fd, i64 offset, u32 val){
  char ac[4];
  put32bits(ac, val);
  return sqlite3OsWrite(fd, ac, 4, offset);
}

/*
** The argument to this macro is a file descriptor (type sqlite3_file*).
** Return 0 if it is not open, or non-zero (but not 1) if it is.
**
** This is so that expressions can be written as:
**
**   if( isOpen(pPager->jfd) ){ ...
**
** instead of
**
**   if( pPager->jfd->pMethods ){ ...
*/
#define isOpen(pFd) ((pFd)->pMethods)

/*
** If file pFd is open, call sqlite3OsUnlock() on it.
*/
static int osUnlock(sqlite3_file *pFd, int eLock){
  if( !isOpen(pFd) ){
    return SQLITE_OK;
  }
  return sqlite3OsUnlock(pFd, eLock);
}

/*
** This function determines whether or not the atomic-write optimization
** can be used with this pager. The optimization can be used if:
**
**  (a) the value returned by OsDeviceCharacteristics() indicates that
**      a database page may be written atomically, and
**  (b) the value returned by OsSectorSize() is less than or equal
**      to the page size.
**
** The optimization is also always enabled for temporary files. It is
** an error to call this function if pPager is opened on an in-memory
** database.
**
** If the optimization cannot be used, 0 is returned. If it can be used,
** then the value returned is the size of the journal file when it
** contains rollback data for exactly one page.
*/
#ifdef SQLITE_ENABLE_ATOMIC_WRITE
static int jrnlBufferSize(Pager *pPager){
  assert( !MEMDB );
  if( !pPager->tempFile ){
    int dc;                           /* Device characteristics */
    int nSector;                      /* Sector size */
    int szPage;                       /* Page size */

    assert( isOpen(pPager->fd) );
    dc = sqlite3OsDeviceCharacteristics(pPager->fd);
    nSector = pPager->sectorSize;
    szPage = pPager->pageSize;

    assert(SQLITE_IOCAP_ATOMIC512==(512>>8));
    assert(SQLITE_IOCAP_ATOMIC64K==(65536>>8));
    if( 0==(dc&(SQLITE_IOCAP_ATOMIC|(szPage>>8)) || nSector>szPage) ){
      return 0;
    }
  }

  return JOURNAL_HDR_SZ(pPager) + JOURNAL_PG_SZ(pPager);
}
#endif

/*
** If SQLITE_CHECK_PAGES is defined then we do some sanity checking
** on the cache using a hash function.  This is used for testing
** and debugging only.
*/
#ifdef SQLITE_CHECK_PAGES
/*
** Return a 32-bit hash of the page data for pPage.
*/
static u32 pager_datahash(int nByte, unsigned char *pData){
  u32 hash = 0;
  int i;
  for(i=0; i<nByte; i++){
    hash = (hash*1039) + pData[i];
  }
  return hash;
}
static u32 pager_pagehash(PgHdr *pPage){
  return pager_datahash(pPage->pPager->pageSize, (unsigned char *)pPage->pData);
}
static void pager_set_pagehash(PgHdr *pPage){
  pPage->pageHash = pager_pagehash(pPage);
}

/*
** The CHECK_PAGE macro takes a PgHdr* as an argument. If SQLITE_CHECK_PAGES
** is defined, and NDEBUG is not defined, an assert() statement checks
** that the page is either dirty or still matches the calculated page-hash.
*/
#define CHECK_PAGE(x) checkPage(x)
static void checkPage(PgHdr *pPg){
  Pager *pPager = pPg->pPager;
  assert( !pPg->pageHash || pPager->errCode
      || (pPg->flags&PGHDR_DIRTY) || pPg->pageHash==pager_pagehash(pPg) );
}

#else
#define pager_datahash(X,Y)  0
#define pager_pagehash(X)  0
#define CHECK_PAGE(x)
#endif  /* SQLITE_CHECK_PAGES */

/*
** When this is called the journal file for pager pPager must be open.
** This function attempts to read a master journal file name from the 
** end of the file and, if successful, copies it into memory supplied 
** by the caller. See comments above writeMasterJournal() for the format
** used to store a master journal file name at the end of a journal file.
**
** zMaster must point to a buffer of at least nMaster bytes allocated by
** the caller. This should be sqlite3_vfs.mxPathname+1 (to ensure there is
** enough space to write the master journal name). If the master journal
** name in the journal is longer than nMaster bytes (including a
** nul-terminator), then this is handled as if no master journal name
** were present in the journal.
**
** If a master journal file name is present at the end of the journal
** file, then it is copied into the buffer pointed to by zMaster. A
** nul-terminator byte is appended to the buffer following the master
** journal file name.
**
** If it is determined that no master journal file name is present 
** zMaster[0] is set to 0 and SQLITE_OK returned.
**
** If an error occurs while reading from the journal file, an SQLite
** error code is returned.
*/
static int readMasterJournal(sqlite3_file *pJrnl, char *zMaster, u32 nMaster){
  int rc;                    /* Return code */
  u32 len;                   /* Length in bytes of master journal name */
  i64 szJ;                   /* Total size in bytes of journal file pJrnl */
  u32 cksum;                 /* MJ checksum value read from journal */
  u32 u;                     /* Unsigned loop counter */
  unsigned char aMagic[8];   /* A buffer to hold the magic header */
  zMaster[0] = '\0';

  if( SQLITE_OK!=(rc = sqlite3OsFileSize(pJrnl, &szJ))
   || szJ<16
   || SQLITE_OK!=(rc = read32bits(pJrnl, szJ-16, &len))
   || len>=nMaster 
   || SQLITE_OK!=(rc = read32bits(pJrnl, szJ-12, &cksum))
   || SQLITE_OK!=(rc = sqlite3OsRead(pJrnl, aMagic, 8, szJ-8))
   || memcmp(aMagic, aJournalMagic, 8)
   || SQLITE_OK!=(rc = sqlite3OsRead(pJrnl, zMaster, len, szJ-16-len))
  ){
    return rc;
  }

  /* See if the checksum matches the master journal name */
  for(u=0; u<len; u++){
    cksum -= zMaster[u];
  }
  if( cksum ){
    /* If the checksum doesn't add up, then one or more of the disk sectors
    ** containing the master journal filename is corrupted. This means
    ** definitely roll back, so just return SQLITE_OK and report a (nul)
    ** master-journal filename.
    */
    len = 0;
  }
  zMaster[len] = '\0';
   
  return SQLITE_OK;
}

/*
** Return the offset of the sector boundary at or immediately 
** following the value in pPager->journalOff, assuming a sector 
** size of pPager->sectorSize bytes.
**
** i.e for a sector size of 512:
**
**   Pager.journalOff          Return value
**   ---------------------------------------
**   0                         0
**   512                       512
**   100                       512
**   2000                      2048
** 
*/
static i64 journalHdrOffset(Pager *pPager){
  i64 offset = 0;