btree.c

sqlite最新源码

  int nCell;
  int cellOffset;
  unsigned char *data;
  
  data = pPage->aData;
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  assert( pPage->pBt );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  assert( nByte>=0 );  /* Minimum cell size is 4 */
  assert( pPage->nFree>=nByte );
  assert( pPage->nOverflow==0 );
  pPage->nFree -= (u16)nByte;
  hdr = pPage->hdrOffset;

  nFrag = data[hdr+7];
  if( nFrag<60 ){
    /* Search the freelist looking for a slot big enough to satisfy the
    ** space request. */
    addr = hdr+1;
    while( (pc = get2byte(&data[addr]))>0 ){
      size = get2byte(&data[pc+2]);
      if( size>=nByte ){
        int x = size - nByte;
        if( size<nByte+4 ){
          memcpy(&data[addr], &data[pc], 2);
          data[hdr+7] = (u8)(nFrag + x);
          return pc;
        }else{
          put2byte(&data[pc+2], x);
          return pc + x;
        }
      }
      addr = pc;
    }
  }

  /* Allocate memory from the gap in between the cell pointer array
  ** and the cell content area.
  */
  top = get2byte(&data[hdr+5]);
  nCell = get2byte(&data[hdr+3]);
  cellOffset = pPage->cellOffset;
  if( nFrag>=60 || cellOffset + 2*nCell > top - nByte ){
    defragmentPage(pPage);
    top = get2byte(&data[hdr+5]);
  }
  top -= nByte;
  assert( cellOffset + 2*nCell <= top );
  put2byte(&data[hdr+5], top);
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  return top;
}

/*
** Return a section of the pPage->aData to the freelist.
** The first byte of the new free block is pPage->aDisk[start]
** and the size of the block is "size" bytes.
**
** Most of the effort here is involved in coalesing adjacent
** free blocks into a single big free block.
*/
static int freeSpace(MemPage *pPage, int start, int size){
  int addr, pbegin, hdr;
  unsigned char *data = pPage->aData;

  assert( pPage->pBt!=0 );
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  assert( start>=pPage->hdrOffset+6+(pPage->leaf?0:4) );
  assert( (start + size)<=pPage->pBt->usableSize );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  assert( size>=0 );   /* Minimum cell size is 4 */

#ifdef SQLITE_SECURE_DELETE
  /* Overwrite deleted information with zeros when the SECURE_DELETE 
  ** option is enabled at compile-time */
  memset(&data[start], 0, size);
#endif

  /* Add the space back into the linked list of freeblocks */
  hdr = pPage->hdrOffset;
  addr = hdr + 1;
  while( (pbegin = get2byte(&data[addr]))<start && pbegin>0 ){
    assert( pbegin<=pPage->pBt->usableSize-4 );
    if( pbegin<=addr ) {
      return SQLITE_CORRUPT_BKPT;
    }
    addr = pbegin;
  }
  if ( pbegin>pPage->pBt->usableSize-4 ) {
    return SQLITE_CORRUPT_BKPT;
  }
  assert( pbegin>addr || pbegin==0 );
  put2byte(&data[addr], start);
  put2byte(&data[start], pbegin);
  put2byte(&data[start+2], size);
  pPage->nFree += (u16)size;

  /* Coalesce adjacent free blocks */
  addr = pPage->hdrOffset + 1;
  while( (pbegin = get2byte(&data[addr]))>0 ){
    int pnext, psize, x;
    assert( pbegin>addr );
    assert( pbegin<=pPage->pBt->usableSize-4 );
    pnext = get2byte(&data[pbegin]);
    psize = get2byte(&data[pbegin+2]);
    if( pbegin + psize + 3 >= pnext && pnext>0 ){
      int frag = pnext - (pbegin+psize);
      if( (frag<0) || (frag>(int)data[pPage->hdrOffset+7]) ){
        return SQLITE_CORRUPT_BKPT;
      }
      data[pPage->hdrOffset+7] -= (u8)frag;
      x = get2byte(&data[pnext]);
      put2byte(&data[pbegin], x);
      x = pnext + get2byte(&data[pnext+2]) - pbegin;
      put2byte(&data[pbegin+2], x);
    }else{
      addr = pbegin;
    }
  }

  /* If the cell content area begins with a freeblock, remove it. */
  if( data[hdr+1]==data[hdr+5] && data[hdr+2]==data[hdr+6] ){
    int top;
    pbegin = get2byte(&data[hdr+1]);
    memcpy(&data[hdr+1], &data[pbegin], 2);
    top = get2byte(&data[hdr+5]) + get2byte(&data[pbegin+2]);
    put2byte(&data[hdr+5], top);
  }
  assert( sqlite3PagerIswriteable(pPage->pDbPage) );
  return SQLITE_OK;
}

/*
** Decode the flags byte (the first byte of the header) for a page
** and initialize fields of the MemPage structure accordingly.
**
** Only the following combinations are supported.  Anything different
** indicates a corrupt database files:
**
**         PTF_ZERODATA
**         PTF_ZERODATA | PTF_LEAF
**         PTF_LEAFDATA | PTF_INTKEY
**         PTF_LEAFDATA | PTF_INTKEY | PTF_LEAF
*/
static int decodeFlags(MemPage *pPage, int flagByte){
  BtShared *pBt;     /* A copy of pPage->pBt */

  assert( pPage->hdrOffset==(pPage->pgno==1 ? 100 : 0) );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  pPage->leaf = (u8)(flagByte>>3);  assert( PTF_LEAF == 1<<3 );
  flagByte &= ~PTF_LEAF;
  pPage->childPtrSize = 4-4*pPage->leaf;
  pBt = pPage->pBt;
  if( flagByte==(PTF_LEAFDATA | PTF_INTKEY) ){
    pPage->intKey = 1;
    pPage->hasData = pPage->leaf;
    pPage->maxLocal = pBt->maxLeaf;
    pPage->minLocal = pBt->minLeaf;
  }else if( flagByte==PTF_ZERODATA ){
    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
** not contain a well-formed database page, then return 
** SQLITE_CORRUPT.  Note that a return of SQLITE_OK does not
** guarantee that the page is well-formed.  It only shows that
** we failed to detect any corruption.
*/
int sqlite3BtreeInitPage(MemPage *pPage){

  assert( pPage->pBt!=0 );
  assert( sqlite3_mutex_held(pPage->pBt->mutex) );
  assert( pPage->pgno==sqlite3PagerPagenumber(pPage->pDbPage) );
  assert( pPage == sqlite3PagerGetExtra(pPage->pDbPage) );
  assert( pPage->aData == sqlite3PagerGetData(pPage->pDbPage) );

  if( !pPage->isInit ){
    u16 pc;            /* Address of a freeblock within pPage->aData[] */
    u8 hdr;            /* Offset to beginning of page header */
    u8 *data;          /* Equal to pPage->aData */
    BtShared *pBt;        /* The main btree structure */
    u16 usableSize;    /* Amount of usable space on each page */
    u16 cellOffset;    /* Offset from start of page to first cell pointer */
    u16 nFree;         /* Number of unused bytes on the page */
    u16 top;           /* First byte of the cell content area */

    pBt = pPage->pBt;

    hdr = pPage->hdrOffset;
    data = pPage->aData;
    if( decodeFlags(pPage, data[hdr]) ) return SQLITE_CORRUPT_BKPT;
    assert( pBt->pageSize>=512 && pBt->pageSize<=32768 );
    pPage->maskPage = pBt->pageSize - 1;
    pPage->nOverflow = 0;
    usableSize = pBt->usableSize;
    pPage->cellOffset = cellOffset = hdr + 12 - 4*pPage->leaf;
    top = get2byte(&data[hdr+5]);
    pPage->nCell = get2byte(&data[hdr+3]);
    if( pPage->nCell>MX_CELL(pBt) ){
      /* To many cells for a single page.  The page must be corrupt */
      return SQLITE_CORRUPT_BKPT;
    }
  
    /* Compute the total free space on the page */
    pc = get2byte(&data[hdr+1]);
    nFree = data[hdr+7] + top - (cellOffset + 2*pPage->nCell);
    while( pc>0 ){
      u16 next, size;
      if( pc>usableSize-4 ){
        /* Free block is off the page */
        return SQLITE_CORRUPT_BKPT; 
      }
      next = get2byte(&data[pc]);
      size = get2byte(&data[pc+2]);
      if( next>0 && next<=pc+size+3 ){
        /* Free blocks must be in accending order */
        return SQLITE_CORRUPT_BKPT; 
      }
      nFree += size;
      pc = next;
    }
    pPage->nFree = (u16)nFree;
    if( nFree>=usableSize ){
      /* Free space cannot exceed total page size */
      return SQLITE_CORRUPT_BKPT; 
    }

#if 0
  /* Check that all the offsets in the cell offset array are within range. 
  ** 
  ** Omitting this consistency check and using the pPage->maskPage mask
  ** to prevent overrunning the page buffer in findCell() results in a
  ** 2.5% performance gain.
  */
  {
    u8 *pOff;        /* Iterator used to check all cell offsets are in range */
    u8 *pEnd;        /* Pointer to end of cell offset array */
    u8 mask;         /* Mask of bits that must be zero in MSB of cell offsets */
    mask = ~(((u8)(pBt->pageSize>>8))-1);
    pEnd = &data[cellOffset + pPage->nCell*2];
    for(pOff=&data[cellOffset]; pOff!=pEnd && !((*pOff)&mask); pOff+=2);
    if( pOff!=pEnd ){
      return SQLITE_CORRUPT_BKPT;
    }
  }
#endif

    pPage->isInit = 1;
  }
  return SQLITE_OK;
}

/*
** Set up a raw page so that it looks like a database page holding
** no entries.
*/
static void zeroPage(MemPage *pPage, int flags){
  unsigned char *data = pPage->aData;
  BtShared *pBt = pPage->pBt;
  u8 hdr = pPage->hdrOffset;
  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) );
  /*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);
  pPage->nFree = pBt->usableSize - first;
  decodeFlags(pPage, flags);
  pPage->hdrOffset = hdr;
  pPage->cellOffset = first;
  pPage->nOverflow = 0;
  assert( pBt->pageSize>=512 && pBt->pageSize<=32768 );
  pPage->maskPage = pBt->pageSize - 1;
  pPage->nCell = 0;
  pPage->isInit = 1;
}


/*
** Convert a DbPage obtained from the pager into a MemPage used by
** the btree layer.
*/
static MemPage *btreePageFromDbPage(DbPage *pDbPage, Pgno pgno, BtShared *pBt){
  MemPage *pPage = (MemPage*)sqlite3PagerGetExtra(pDbPage);
  pPage->aData = sqlite3PagerGetData(pDbPage);
  pPage->pDbPage = pDbPage;
  pPage->pBt = pBt;
  pPage->pgno = pgno;
  pPage->hdrOffset = pPage->pgno==1 ? 100 : 0;
  return pPage; 
}

/*
** Get a page from the pager.  Initialize the MemPage.pBt and
** MemPage.aData elements if needed.
**
** If the noContent flag is set, it means that we do not care about
** the content of the page at this time.  So do not go to the disk
** to fetch the content.  Just fill in the content with zeros for now.
** If in the future we call sqlite3PagerWrite() on this page, that
** means we have started to be concerned about content and the disk
** read should occur at that point.
*/
int sqlite3BtreeGetPage(
  BtShared *pBt,       /* The btree */
  Pgno pgno,           /* Number of the page to fetch */
  MemPage **ppPage,    /* Return the page in this parameter */
  int noContent        /* Do not load page content if true */
){
  int rc;
  DbPage *pDbPage;

  assert( sqlite3_mutex_held(pBt->mutex) );
  rc = sqlite3PagerAcquire(pBt->pPager, pgno, (DbPage**)&pDbPage, noContent);
  if( rc ) return rc;
  *ppPage = btreePageFromDbPage(pDbPage, pgno, pBt);
  return SQLITE_OK;
}

/*
** Retrieve a page from the pager cache. If the requested page is not
** already in the pager cache return NULL. Initialize the MemPage.pBt and
** MemPage.aData elements if needed.
*/
static MemPage *btreePageLookup(BtShared *pBt, Pgno pgno){
  DbPage *pDbPage;
  assert( sqlite3_mutex_held(pBt->mutex) );
  pDbPage = sqlite3PagerLookup(pBt->pPager, pgno);
  if( pDbPage ){
    return btreePageFromDbPage(pDbPage, pgno, pBt);
  }
  return 0;
}

/*
** Return the size of the database file in pages. If there is any kind of
** error, return ((unsigned int)-1).
*/
static Pgno pagerPagecount(BtShared *pBt){
  int nPage = -1;
  int rc;
  assert( pBt->pPage1 );
  rc = sqlite3PagerPagecount(pBt->pPager, &nPage);
  assert( rc==SQLITE_OK || nPage==-1 );
  return (Pgno)nPage;
}

/*
** Get a page from the pager and initialize it.  This routine
** is just a convenience wrapper around separate calls to
** sqlite3BtreeGetPage() and sqlite3BtreeInitPage().
*/
static int getAndInitPage(
  BtShared *pBt,          /* The database file */
  Pgno pgno,           /* Number of the page to get */
  MemPage **ppPage     /* Write the page pointer here */
){
  int rc;
  MemPage *pPage;

  assert( sqlite3_mutex_held(pBt->mutex) );
  if( pgno==0 ){
    return SQLITE_CORRUPT_BKPT; 
  }

  /* It is often the case that the page we want is already in cache.
  ** If so, get it directly.  This saves us from having to call
  ** pagerPagecount() to make sure pgno is within limits, which results
  ** in a measureable performance improvements.
  */
  *ppPage = pPage = btreePageLookup(pBt, pgno);
  if( pPage ){
    /* Page is already in cache */
    rc = SQLITE_OK;
  }else{
    /* Page not in cache.  Acquire it. */
    if( pgno>pagerPagecount(pBt) ){
      return SQLITE_CORRUPT_BKPT; 
    }
    rc = sqlite3BtreeGetPage(pBt, pgno, ppPage, 0);
    if( rc ) return rc;
    pPage = *ppPage;
  }
  if( !pPage->isInit ){
    rc = sqlite3BtreeInitPage(pPage);
  }
  if( rc!=SQLITE_OK ){
    releasePage(pPage);
    *ppPage = 0;
  }
  return rc;
}

/*
** Release a MemPage.  This should be called once for each prior
** call to sqlite3BtreeGetPage.
*/
static void releasePage(MemPage *pPage){
  if( pPage ){
    assert( pPage->nOverflow==0 || sqlite3PagerPageRefcount(pPage->pDbPage)>1 );
    assert( pPage->aData );
    assert( pPage->pBt );
    assert( sqlite3PagerGetExtra(pPage->pDbPage) == (void*)pPage );