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

  if( pPage->nFree<nByte || pPage->nOverflow>0 ) return 0;
  pPage->nFree -= 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 ){
        if( size<nByte+4 ){
          memcpy(&data[addr], &data[pc], 2);
          data[hdr+7] = nFrag + size - nByte;
          return pc;
        }else{
          put2byte(&data[pc+2], size-nByte);
          return pc + size - nByte;
        }
      }
      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 ){
    if( defragmentPage(pPage) ) return 0;
    top = get2byte(&data[hdr+5]);
  }
  top -= nByte;
  assert( cellOffset + 2*nCell <= top );
  put2byte(&data[hdr+5], top);
  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 void freeSpace(MemPage *pPage, int start, int size){
  int addr, pbegin, hdr;
  unsigned char *data = pPage->aData;

  assert( pPage->pBt!=0 );
  assert( sqlite3pager_iswriteable(data) );
  assert( start>=pPage->hdrOffset+6+(pPage->leaf?0:4) );
  assert( (start + size)<=pPage->pBt->usableSize );
  if( size<4 ) size = 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 );
    assert( pbegin>addr );
    addr = pbegin;
  }
  assert( pbegin<=pPage->pBt->usableSize-4 );
  assert( pbegin>addr || pbegin==0 );
  put2byte(&data[addr], start);
  put2byte(&data[start], pbegin);
  put2byte(&data[start+2], size);
  pPage->nFree += size;

  /* Coalesce adjacent free blocks */
  addr = pPage->hdrOffset + 1;
  while( (pbegin = get2byte(&data[addr]))>0 ){
    int pnext, psize;
    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);
      assert( frag<=data[pPage->hdrOffset+7] );
      data[pPage->hdrOffset+7] -= frag;
      put2byte(&data[pbegin], get2byte(&data[pnext]));
      put2byte(&data[pbegin+2], pnext+get2byte(&data[pnext+2])-pbegin);
    }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]);
    put2byte(&data[hdr+5], top + get2byte(&data[pbegin+2]));
  }
}

/*
** Decode the flags byte (the first byte of the header) for a page
** and initialize fields of the MemPage structure accordingly.
*/
static void decodeFlags(MemPage *pPage, int flagByte){
  BtShared *pBt;     /* A copy of pPage->pBt */

  assert( pPage->hdrOffset==(pPage->pgno==1 ? 100 : 0) );
  pPage->intKey = (flagByte & (PTF_INTKEY|PTF_LEAFDATA))!=0;
  pPage->zeroData = (flagByte & PTF_ZERODATA)!=0;
  pPage->leaf = (flagByte & PTF_LEAF)!=0;
  pPage->childPtrSize = 4*(pPage->leaf==0);
  pBt = pPage->pBt;
  if( flagByte & PTF_LEAFDATA ){
    pPage->leafData = 1;
    pPage->maxLocal = pBt->maxLeaf;
    pPage->minLocal = pBt->minLeaf;
  }else{
    pPage->leafData = 0;
    pPage->maxLocal = pBt->maxLocal;
    pPage->minLocal = pBt->minLocal;
  }
  pPage->hasData = !(pPage->zeroData || (!pPage->leaf && pPage->leafData));
}

/*
** Initialize the auxiliary information for a disk block.
**
** The pParent parameter must be a pointer to the MemPage which
** is the parent of the page being initialized.  The root of a
** BTree has no parent and so for that page, pParent==NULL.
**
** 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.
*/
static int initPage(
  MemPage *pPage,        /* The page to be initialized */
  MemPage *pParent       /* The parent.  Might be NULL */
){
  int pc;            /* Address of a freeblock within pPage->aData[] */
  int hdr;           /* Offset to beginning of page header */
  u8 *data;          /* Equal to pPage->aData */
  BtShared *pBt;        /* The main btree structure */
  int usableSize;    /* Amount of usable space on each page */
  int cellOffset;    /* Offset from start of page to first cell pointer */
  int nFree;         /* Number of unused bytes on the page */
  int top;           /* First byte of the cell content area */

  pBt = pPage->pBt;
  assert( pBt!=0 );
  assert( pParent==0 || pParent->pBt==pBt );
  assert( pPage->pgno==sqlite3pager_pagenumber(pPage->aData) );
  assert( pPage->aData == &((unsigned char*)pPage)[-pBt->pageSize] );
  if( pPage->pParent!=pParent && (pPage->pParent!=0 || pPage->isInit) ){
    /* The parent page should never change unless the file is corrupt */
    return SQLITE_CORRUPT_BKPT;
  }
  if( pPage->isInit ) return SQLITE_OK;
  if( pPage->pParent==0 && pParent!=0 ){
    pPage->pParent = pParent;
    sqlite3pager_ref(pParent->aData);
  }
  hdr = pPage->hdrOffset;
  data = pPage->aData;
  decodeFlags(pPage, data[hdr]);
  pPage->nOverflow = 0;
  pPage->idxShift = 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;
  }
  if( pPage->nCell==0 && pParent!=0 && pParent->pgno!=1 ){
    /* All pages must have at least one cell, except for root pages */
    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 ){
    int 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 = nFree;
  if( nFree>=usableSize ){
    /* Free space cannot exceed total page size */
    return SQLITE_CORRUPT_BKPT; 
  }

  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;
  int hdr = pPage->hdrOffset;
  int first;

  assert( sqlite3pager_pagenumber(data)==pPage->pgno );
  assert( &data[pBt->pageSize] == (unsigned char*)pPage );
  assert( sqlite3pager_iswriteable(data) );
  memset(&data[hdr], 0, pBt->usableSize - hdr);
  data[hdr] = flags;
  first = hdr + 8 + 4*((flags&PTF_LEAF)==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;
  pPage->idxShift = 0;
  pPage->nCell = 0;
  pPage->isInit = 1;
}

/*
** Get a page from the pager.  Initialize the MemPage.pBt and
** MemPage.aData elements if needed.
*/
static int getPage(BtShared *pBt, Pgno pgno, MemPage **ppPage){
  int rc;
  unsigned char *aData;
  MemPage *pPage;
  rc = sqlite3pager_get(pBt->pPager, pgno, (void**)&aData);
  if( rc ) return rc;
  pPage = (MemPage*)&aData[pBt->pageSize];
  pPage->aData = aData;
  pPage->pBt = pBt;
  pPage->pgno = pgno;
  pPage->hdrOffset = pPage->pgno==1 ? 100 : 0;
  *ppPage = pPage;
  return SQLITE_OK;
}

/*
** Get a page from the pager and initialize it.  This routine
** is just a convenience wrapper around separate calls to
** getPage() and initPage().
*/
static int getAndInitPage(
  BtShared *pBt,          /* The database file */
  Pgno pgno,           /* Number of the page to get */
  MemPage **ppPage,    /* Write the page pointer here */
  MemPage *pParent     /* Parent of the page */
){
  int rc;
  if( pgno==0 ){
    return SQLITE_CORRUPT_BKPT; 
  }
  rc = getPage(pBt, pgno, ppPage);
  if( rc==SQLITE_OK && (*ppPage)->isInit==0 ){
    rc = initPage(*ppPage, pParent);
  }
  return rc;
}

/*
** Release a MemPage.  This should be called once for each prior
** call to getPage.
*/
static void releasePage(MemPage *pPage){
  if( pPage ){
    assert( pPage->aData );
    assert( pPage->pBt );
    assert( &pPage->aData[pPage->pBt->pageSize]==(unsigned char*)pPage );
    sqlite3pager_unref(pPage->aData);
  }
}

/*
** This routine is called when the reference count for a page
** reaches zero.  We need to unref the pParent pointer when that
** happens.
*/
static void pageDestructor(void *pData, int pageSize){
  MemPage *pPage;
  assert( (pageSize & 7)==0 );
  pPage = (MemPage*)&((char*)pData)[pageSize];
  if( pPage->pParent ){
    MemPage *pParent = pPage->pParent;
    pPage->pParent = 0;
    releasePage(pParent);
  }
  pPage->isInit = 0;
}

/*
** During a rollback, when the pager reloads information into the cache
** so that the cache is restored to its original state at the start of
** the transaction, for each page restored this routine is called.
**
** This routine needs to reset the extra data section at the end of the
** page to agree with the restored data.
*/
static void pageReinit(void *pData, int pageSize){
  MemPage *pPage;
  assert( (pageSize & 7)==0 );
  pPage = (MemPage*)&((char*)pData)[pageSize];
  if( pPage->isInit ){
    pPage->isInit = 0;
    initPage(pPage, pPage->pParent);
  }
}

/*
** Open a database file.
** 
** zFilename is the name of the database file.  If zFilename is NULL
** a new database with a random name is created.  This randomly named
** database file will be deleted when sqlite3BtreeClose() is called.
*/
int sqlite3BtreeOpen(
  const char *zFilename,  /* Name of the file containing the BTree database */
  sqlite3 *pSqlite,       /* Associated database handle */
  Btree **ppBtree,        /* Pointer to new Btree object written here */
  int flags               /* Options */
){
  BtShared *pBt;          /* Shared part of btree structure */
  Btree *p;               /* Handle to return */
  int rc;
  int nReserve;
  unsigned char zDbHeader[100];
#if !defined(SQLITE_OMIT_SHARED_CACHE) && !defined(SQLITE_OMIT_DISKIO)
  const ThreadData *pTsdro;
#endif

  /* Set the variable isMemdb to true for an in-memory database, or 
  ** false for a file-based database. This symbol is only required if
  ** either of the shared-data or autovacuum features are compiled 
  ** into the library.
  */
#if !defined(SQLITE_OMIT_SHARED_CACHE) || !defined(SQLITE_OMIT_AUTOVACUUM)
  #ifdef SQLITE_OMIT_MEMORYDB
    const int isMemdb = 0;
  #else
    const int isMemdb = zFilename && !strcmp(zFilename, ":memory:");
  #endif
#endif

  p = sqliteMalloc(sizeof(Btree));
  if( !p ){
    return SQLITE_NOMEM;
  }