btree.c

轻量级数据库软件,嵌入式设计可以考虑考虑,性能不错

** used to test if pgno is a pointer-map page. PTRMAP_ISPAGE implements
** this test.
*/
#define PTRMAP_PAGENO(pBt, pgno) ptrmapPageno(pBt, pgno)
#define PTRMAP_PTROFFSET(pBt, pgno) (5*(pgno-ptrmapPageno(pBt, pgno)-1))
#define PTRMAP_ISPAGE(pBt, pgno) (PTRMAP_PAGENO((pBt),(pgno))==(pgno))

static Pgno ptrmapPageno(BtShared *pBt, Pgno pgno){
  int nPagesPerMapPage = (pBt->usableSize/5)+1;
  int iPtrMap = (pgno-2)/nPagesPerMapPage;
  int ret = (iPtrMap*nPagesPerMapPage) + 2; 
  if( ret==PENDING_BYTE_PAGE(pBt) ){
    ret++;
  }
  return ret;
}

/*
** The pointer map is a lookup table that identifies the parent page for
** each child page in the database file.  The parent page is the page that
** contains a pointer to the child.  Every page in the database contains
** 0 or 1 parent pages.  (In this context 'database page' refers
** to any page that is not part of the pointer map itself.)  Each pointer map
** entry consists of a single byte 'type' and a 4 byte parent page number.
** The PTRMAP_XXX identifiers below are the valid types.
**
** The purpose of the pointer map is to facility moving pages from one
** position in the file to another as part of autovacuum.  When a page
** is moved, the pointer in its parent must be updated to point to the
** new location.  The pointer map is used to locate the parent page quickly.
**
** PTRMAP_ROOTPAGE: The database page is a root-page. The page-number is not
**                  used in this case.
**
** PTRMAP_FREEPAGE: The database page is an unused (free) page. The page-number 
**                  is not used in this case.
**
** PTRMAP_OVERFLOW1: The database page is the first page in a list of 
**                   overflow pages. The page number identifies the page that
**                   contains the cell with a pointer to this overflow page.
**
** PTRMAP_OVERFLOW2: The database page is the second or later page in a list of
**                   overflow pages. The page-number identifies the previous
**                   page in the overflow page list.
**
** PTRMAP_BTREE: The database page is a non-root btree page. The page number
**               identifies the parent page in the btree.
*/
#define PTRMAP_ROOTPAGE 1
#define PTRMAP_FREEPAGE 2
#define PTRMAP_OVERFLOW1 3
#define PTRMAP_OVERFLOW2 4
#define PTRMAP_BTREE 5

/*
** Write an entry into the pointer map.
**
** This routine updates the pointer map entry for page number 'key'
** so that it maps to type 'eType' and parent page number 'pgno'.
** An error code is returned if something goes wrong, otherwise SQLITE_OK.
*/
static int ptrmapPut(BtShared *pBt, Pgno key, u8 eType, Pgno parent){
  u8 *pPtrmap;    /* The pointer map page */
  Pgno iPtrmap;   /* The pointer map page number */
  int offset;     /* Offset in pointer map page */
  int rc;

  /* The master-journal page number must never be used as a pointer map page */
  assert( 0==PTRMAP_ISPAGE(pBt, PENDING_BYTE_PAGE(pBt)) );

  assert( pBt->autoVacuum );
  if( key==0 ){
    return SQLITE_CORRUPT_BKPT;
  }
  iPtrmap = PTRMAP_PAGENO(pBt, key);
  rc = sqlite3pager_get(pBt->pPager, iPtrmap, (void **)&pPtrmap);
  if( rc!=SQLITE_OK ){
    return rc;
  }
  offset = PTRMAP_PTROFFSET(pBt, key);

  if( eType!=pPtrmap[offset] || get4byte(&pPtrmap[offset+1])!=parent ){
    TRACE(("PTRMAP_UPDATE: %d->(%d,%d)\n", key, eType, parent));
    rc = sqlite3pager_write(pPtrmap);
    if( rc==SQLITE_OK ){
      pPtrmap[offset] = eType;
      put4byte(&pPtrmap[offset+1], parent);
    }
  }

  sqlite3pager_unref(pPtrmap);
  return rc;
}

/*
** Read an entry from the pointer map.
**
** This routine retrieves the pointer map entry for page 'key', writing
** the type and parent page number to *pEType and *pPgno respectively.
** An error code is returned if something goes wrong, otherwise SQLITE_OK.
*/
static int ptrmapGet(BtShared *pBt, Pgno key, u8 *pEType, Pgno *pPgno){
  int iPtrmap;       /* Pointer map page index */
  u8 *pPtrmap;       /* Pointer map page data */
  int offset;        /* Offset of entry in pointer map */
  int rc;

  iPtrmap = PTRMAP_PAGENO(pBt, key);
  rc = sqlite3pager_get(pBt->pPager, iPtrmap, (void **)&pPtrmap);
  if( rc!=0 ){
    return rc;
  }

  offset = PTRMAP_PTROFFSET(pBt, key);
  assert( pEType!=0 );
  *pEType = pPtrmap[offset];
  if( pPgno ) *pPgno = get4byte(&pPtrmap[offset+1]);

  sqlite3pager_unref(pPtrmap);
  if( *pEType<1 || *pEType>5 ) return SQLITE_CORRUPT_BKPT;
  return SQLITE_OK;
}

#endif /* SQLITE_OMIT_AUTOVACUUM */

/*
** Given a btree page and a cell index (0 means the first cell on
** the page, 1 means the second cell, and so forth) return a pointer
** to the cell content.
**
** This routine works only for pages that do not contain overflow cells.
*/
static u8 *findCell(MemPage *pPage, int iCell){
  u8 *data = pPage->aData;
  assert( iCell>=0 );
  assert( iCell<get2byte(&data[pPage->hdrOffset+3]) );
  return data + get2byte(&data[pPage->cellOffset+2*iCell]);
}

/*
** This a more complex version of findCell() that works for
** pages that do contain overflow cells.  See insert
*/
static u8 *findOverflowCell(MemPage *pPage, int iCell){
  int i;
  for(i=pPage->nOverflow-1; i>=0; i--){
    int k;
    struct _OvflCell *pOvfl;
    pOvfl = &pPage->aOvfl[i];
    k = pOvfl->idx;
    if( k<=iCell ){
      if( k==iCell ){
        return pOvfl->pCell;
      }
      iCell--;
    }
  }
  return findCell(pPage, iCell);
}

/*
** Parse a cell content block and fill in the CellInfo structure.  There
** are two versions of this function.  parseCell() takes a cell index
** as the second argument and parseCellPtr() takes a pointer to the
** body of the cell as its second argument.
*/
static void parseCellPtr(
  MemPage *pPage,         /* Page containing the cell */
  u8 *pCell,              /* Pointer to the cell text. */
  CellInfo *pInfo         /* Fill in this structure */
){
  int n;                  /* Number bytes in cell content header */
  u32 nPayload;           /* Number of bytes of cell payload */

  pInfo->pCell = pCell;
  assert( pPage->leaf==0 || pPage->leaf==1 );
  n = pPage->childPtrSize;
  assert( n==4-4*pPage->leaf );
  if( pPage->hasData ){
    n += getVarint32(&pCell[n], &nPayload);
  }else{
    nPayload = 0;
  }
  pInfo->nData = nPayload;
  if( pPage->intKey ){
    n += getVarint(&pCell[n], (u64 *)&pInfo->nKey);
  }else{
    u32 x;
    n += getVarint32(&pCell[n], &x);
    pInfo->nKey = x;
    nPayload += x;
  }
  pInfo->nHeader = n;
  if( nPayload<=pPage->maxLocal ){
    /* This is the (easy) common case where the entire payload fits
    ** on the local page.  No overflow is required.
    */
    int nSize;          /* Total size of cell content in bytes */
    pInfo->nLocal = nPayload;
    pInfo->iOverflow = 0;
    nSize = nPayload + n;
    if( nSize<4 ){
      nSize = 4;        /* Minimum cell size is 4 */
    }
    pInfo->nSize = nSize;
  }else{
    /* If the payload will not fit completely on the local page, we have
    ** to decide how much to store locally and how much to spill onto
    ** overflow pages.  The strategy is to minimize the amount of unused
    ** space on overflow pages while keeping the amount of local storage
    ** in between minLocal and maxLocal.
    **
    ** Warning:  changing the way overflow payload is distributed in any
    ** way will result in an incompatible file format.
    */
    int minLocal;  /* Minimum amount of payload held locally */
    int maxLocal;  /* Maximum amount of payload held locally */
    int surplus;   /* Overflow payload available for local storage */

    minLocal = pPage->minLocal;
    maxLocal = pPage->maxLocal;
    surplus = minLocal + (nPayload - minLocal)%(pPage->pBt->usableSize - 4);
    if( surplus <= maxLocal ){
      pInfo->nLocal = surplus;
    }else{
      pInfo->nLocal = minLocal;
    }
    pInfo->iOverflow = pInfo->nLocal + n;
    pInfo->nSize = pInfo->iOverflow + 4;
  }
}
static void parseCell(
  MemPage *pPage,         /* Page containing the cell */
  int iCell,              /* The cell index.  First cell is 0 */
  CellInfo *pInfo         /* Fill in this structure */
){
  parseCellPtr(pPage, findCell(pPage, iCell), pInfo);
}

/*
** Compute the total number of bytes that a Cell needs in the cell
** data area of the btree-page.  The return number includes the cell
** data header and the local payload, but not any overflow page or
** the space used by the cell pointer.
*/
#ifndef NDEBUG
static int cellSize(MemPage *pPage, int iCell){
  CellInfo info;
  parseCell(pPage, iCell, &info);
  return info.nSize;
}
#endif
static int cellSizePtr(MemPage *pPage, u8 *pCell){
  CellInfo info;
  parseCellPtr(pPage, pCell, &info);
  return info.nSize;
}

#ifndef SQLITE_OMIT_AUTOVACUUM
/*
** If the cell pCell, part of page pPage contains a pointer
** to an overflow page, insert an entry into the pointer-map
** for the overflow page.
*/
static int ptrmapPutOvflPtr(MemPage *pPage, u8 *pCell){
  if( pCell ){
    CellInfo info;
    parseCellPtr(pPage, pCell, &info);
    if( (info.nData+(pPage->intKey?0:info.nKey))>info.nLocal ){
      Pgno ovfl = get4byte(&pCell[info.iOverflow]);
      return ptrmapPut(pPage->pBt, ovfl, PTRMAP_OVERFLOW1, pPage->pgno);
    }
  }
  return SQLITE_OK;
}
/*
** If the cell with index iCell on page pPage contains a pointer
** to an overflow page, insert an entry into the pointer-map
** for the overflow page.
*/
static int ptrmapPutOvfl(MemPage *pPage, int iCell){
  u8 *pCell;
  pCell = findOverflowCell(pPage, iCell);
  return ptrmapPutOvflPtr(pPage, pCell);
}
#endif


/* A bunch of assert() statements to check the transaction state variables
** of handle p (type Btree*) are internally consistent.
*/
#define btreeIntegrity(p) \
  assert( p->inTrans!=TRANS_NONE || p->pBt->nTransaction<p->pBt->nRef ); \
  assert( p->pBt->nTransaction<=p->pBt->nRef ); \
  assert( p->pBt->inTransaction!=TRANS_NONE || p->pBt->nTransaction==0 ); \
  assert( p->pBt->inTransaction>=p->inTrans ); 

/*
** Defragment the page given.  All Cells are moved to the
** end of the page and all free space is collected into one
** big FreeBlk that occurs in between the header and cell
** pointer array and the cell content area.
*/
static int defragmentPage(MemPage *pPage){
  int i;                     /* Loop counter */
  int pc;                    /* Address of a i-th cell */
  int addr;                  /* Offset of first byte after cell pointer array */
  int hdr;                   /* Offset to the page header */
  int size;                  /* Size of a cell */
  int usableSize;            /* Number of usable bytes on a page */
  int cellOffset;            /* Offset to the cell pointer array */
  int brk;                   /* Offset to the cell content area */
  int nCell;                 /* Number of cells on the page */
  unsigned char *data;       /* The page data */
  unsigned char *temp;       /* Temp area for cell content */

  assert( sqlite3pager_iswriteable(pPage->aData) );
  assert( pPage->pBt!=0 );
  assert( pPage->pBt->usableSize <= SQLITE_MAX_PAGE_SIZE );
  assert( pPage->nOverflow==0 );
  temp = sqliteMalloc( pPage->pBt->pageSize );
  if( temp==0 ) return SQLITE_NOMEM;
  data = pPage->aData;
  hdr = pPage->hdrOffset;
  cellOffset = pPage->cellOffset;
  nCell = pPage->nCell;
  assert( nCell==get2byte(&data[hdr+3]) );
  usableSize = pPage->pBt->usableSize;
  brk = get2byte(&data[hdr+5]);
  memcpy(&temp[brk], &data[brk], usableSize - brk);
  brk = usableSize;
  for(i=0; i<nCell; i++){
    u8 *pAddr;     /* The i-th cell pointer */
    pAddr = &data[cellOffset + i*2];
    pc = get2byte(pAddr);
    assert( pc<pPage->pBt->usableSize );
    size = cellSizePtr(pPage, &temp[pc]);
    brk -= size;
    memcpy(&data[brk], &temp[pc], size);
    put2byte(pAddr, brk);
  }
  assert( brk>=cellOffset+2*nCell );
  put2byte(&data[hdr+5], brk);
  data[hdr+1] = 0;
  data[hdr+2] = 0;
  data[hdr+7] = 0;
  addr = cellOffset+2*nCell;
  memset(&data[addr], 0, brk-addr);
  sqliteFree(temp);
  return SQLITE_OK;
}

/*
** Allocate nByte bytes of space on a page.
**
** Return the index into pPage->aData[] of the first byte of
** the new allocation. Or return 0 if there is not enough free
** space on the page to satisfy the allocation request.
**
** If the page contains nBytes of free space but does not contain
** nBytes of contiguous free space, then this routine automatically
** calls defragementPage() to consolidate all free space before 
** allocating the new chunk.
*/
static int allocateSpace(MemPage *pPage, int nByte){
  int addr, pc, hdr;
  int size;
  int nFrag;
  int top;
  int nCell;
  int cellOffset;
  unsigned char *data;
  
  data = pPage->aData;
  assert( sqlite3pager_iswriteable(data) );
  assert( pPage->pBt );
  if( nByte<4 ) nByte = 4;