btree.c

sqlite-3.4.1,嵌入式数据库.是一个功能强大的开源数据库,给学习和研发以及小型公司的发展带来了全所未有的好处.

** The maximum number of cache pages is set to the absolute
** value of mxPage.  If mxPage is negative, the pager will
** operate asynchronously - it will not stop to do fsync()s
** to insure data is written to the disk surface before
** continuing.  Transactions still work if synchronous is off,
** and the database cannot be corrupted if this program
** crashes.  But if the operating system crashes or there is
** an abrupt power failure when synchronous is off, the database
** could be left in an inconsistent and unrecoverable state.
** Synchronous is on by default so database corruption is not
** normally a worry.
*/
int sqlite3BtreeSetCacheSize(Btree *p, int mxPage){
  BtShared *pBt = p->pBt;
  sqlite3PagerSetCachesize(pBt->pPager, mxPage);
  return SQLITE_OK;
}

/*
** Change the way data is synced to disk in order to increase or decrease
** how well the database resists damage due to OS crashes and power
** failures.  Level 1 is the same as asynchronous (no syncs() occur and
** there is a high probability of damage)  Level 2 is the default.  There
** is a very low but non-zero probability of damage.  Level 3 reduces the
** probability of damage to near zero but with a write performance reduction.
*/
#ifndef SQLITE_OMIT_PAGER_PRAGMAS
int sqlite3BtreeSetSafetyLevel(Btree *p, int level, int fullSync){
  BtShared *pBt = p->pBt;
  sqlite3PagerSetSafetyLevel(pBt->pPager, level, fullSync);
  return SQLITE_OK;
}
#endif

/*
** Return TRUE if the given btree is set to safety level 1.  In other
** words, return TRUE if no sync() occurs on the disk files.
*/
int sqlite3BtreeSyncDisabled(Btree *p){
  BtShared *pBt = p->pBt;
  assert( pBt && pBt->pPager );
  return sqlite3PagerNosync(pBt->pPager);
}

#if !defined(SQLITE_OMIT_PAGER_PRAGMAS) || !defined(SQLITE_OMIT_VACUUM)
/*
** Change the default pages size and the number of reserved bytes per page.
**
** The page size must be a power of 2 between 512 and 65536.  If the page
** size supplied does not meet this constraint then the page size is not
** changed.
**
** Page sizes are constrained to be a power of two so that the region
** of the database file used for locking (beginning at PENDING_BYTE,
** the first byte past the 1GB boundary, 0x40000000) needs to occur
** at the beginning of a page.
**
** If parameter nReserve is less than zero, then the number of reserved
** bytes per page is left unchanged.
*/
int sqlite3BtreeSetPageSize(Btree *p, int pageSize, int nReserve){
  BtShared *pBt = p->pBt;
  if( pBt->pageSizeFixed ){
    return SQLITE_READONLY;
  }
  if( nReserve<0 ){
    nReserve = pBt->pageSize - pBt->usableSize;
  }
  if( pageSize>=512 && pageSize<=SQLITE_MAX_PAGE_SIZE &&
        ((pageSize-1)&pageSize)==0 ){
    assert( (pageSize & 7)==0 );
    assert( !pBt->pPage1 && !pBt->pCursor );
    pBt->pageSize = sqlite3PagerSetPagesize(pBt->pPager, pageSize);
  }
  pBt->usableSize = pBt->pageSize - nReserve;
  return SQLITE_OK;
}

/*
** Return the currently defined page size
*/
int sqlite3BtreeGetPageSize(Btree *p){
  return p->pBt->pageSize;
}
int sqlite3BtreeGetReserve(Btree *p){
  return p->pBt->pageSize - p->pBt->usableSize;
}

/*
** Set the maximum page count for a database if mxPage is positive.
** No changes are made if mxPage is 0 or negative.
** Regardless of the value of mxPage, return the maximum page count.
*/
int sqlite3BtreeMaxPageCount(Btree *p, int mxPage){
  return sqlite3PagerMaxPageCount(p->pBt->pPager, mxPage);
}
#endif /* !defined(SQLITE_OMIT_PAGER_PRAGMAS) || !defined(SQLITE_OMIT_VACUUM) */

/*
** Change the 'auto-vacuum' property of the database. If the 'autoVacuum'
** parameter is non-zero, then auto-vacuum mode is enabled. If zero, it
** is disabled. The default value for the auto-vacuum property is 
** determined by the SQLITE_DEFAULT_AUTOVACUUM macro.
*/
int sqlite3BtreeSetAutoVacuum(Btree *p, int autoVacuum){
#ifdef SQLITE_OMIT_AUTOVACUUM
  return SQLITE_READONLY;
#else
  BtShared *pBt = p->pBt;
  int av = (autoVacuum?1:0);
  if( pBt->pageSizeFixed && av!=pBt->autoVacuum ){
    return SQLITE_READONLY;
  }
  pBt->autoVacuum = av;
  return SQLITE_OK;
#endif
}

/*
** Return the value of the 'auto-vacuum' property. If auto-vacuum is 
** enabled 1 is returned. Otherwise 0.
*/
int sqlite3BtreeGetAutoVacuum(Btree *p){
#ifdef SQLITE_OMIT_AUTOVACUUM
  return BTREE_AUTOVACUUM_NONE;
#else
  return (
    (!p->pBt->autoVacuum)?BTREE_AUTOVACUUM_NONE:
    (!p->pBt->incrVacuum)?BTREE_AUTOVACUUM_FULL:
    BTREE_AUTOVACUUM_INCR
  );
#endif
}


/*
** Get a reference to pPage1 of the database file.  This will
** also acquire a readlock on that file.
**
** SQLITE_OK is returned on success.  If the file is not a
** well-formed database file, then SQLITE_CORRUPT is returned.
** SQLITE_BUSY is returned if the database is locked.  SQLITE_NOMEM
** is returned if we run out of memory. 
*/
static int lockBtree(BtShared *pBt){
  int rc, pageSize;
  MemPage *pPage1;
  if( pBt->pPage1 ) return SQLITE_OK;
  rc = sqlite3BtreeGetPage(pBt, 1, &pPage1, 0);
  if( rc!=SQLITE_OK ) return rc;
  

  /* Do some checking to help insure the file we opened really is
  ** a valid database file. 
  */
  rc = SQLITE_NOTADB;
  if( sqlite3PagerPagecount(pBt->pPager)>0 ){
    u8 *page1 = pPage1->aData;
    if( memcmp(page1, zMagicHeader, 16)!=0 ){
      goto page1_init_failed;
    }
    if( page1[18]>1 ){
      pBt->readOnly = 1;
    }
    if( page1[19]>1 ){
      goto page1_init_failed;
    }
    pageSize = get2byte(&page1[16]);
    if( ((pageSize-1)&pageSize)!=0 || pageSize<512 ){
      goto page1_init_failed;
    }
    assert( (pageSize & 7)==0 );
    pBt->pageSize = pageSize;
    pBt->usableSize = pageSize - page1[20];
    if( pBt->usableSize<500 ){
      goto page1_init_failed;
    }
    pBt->maxEmbedFrac = page1[21];
    pBt->minEmbedFrac = page1[22];
    pBt->minLeafFrac = page1[23];
#ifndef SQLITE_OMIT_AUTOVACUUM
    pBt->autoVacuum = (get4byte(&page1[36 + 4*4])?1:0);
    pBt->incrVacuum = (get4byte(&page1[36 + 7*4])?1:0);
#endif
  }

  /* maxLocal is the maximum amount of payload to store locally for
  ** a cell.  Make sure it is small enough so that at least minFanout
  ** cells can will fit on one page.  We assume a 10-byte page header.
  ** Besides the payload, the cell must store:
  **     2-byte pointer to the cell
  **     4-byte child pointer
  **     9-byte nKey value
  **     4-byte nData value
  **     4-byte overflow page pointer
  ** So a cell consists of a 2-byte poiner, a header which is as much as
  ** 17 bytes long, 0 to N bytes of payload, and an optional 4 byte overflow
  ** page pointer.
  */
  pBt->maxLocal = (pBt->usableSize-12)*pBt->maxEmbedFrac/255 - 23;
  pBt->minLocal = (pBt->usableSize-12)*pBt->minEmbedFrac/255 - 23;
  pBt->maxLeaf = pBt->usableSize - 35;
  pBt->minLeaf = (pBt->usableSize-12)*pBt->minLeafFrac/255 - 23;
  if( pBt->minLocal>pBt->maxLocal || pBt->maxLocal<0 ){
    goto page1_init_failed;
  }
  assert( pBt->maxLeaf + 23 <= MX_CELL_SIZE(pBt) );
  pBt->pPage1 = pPage1;
  return SQLITE_OK;

page1_init_failed:
  releasePage(pPage1);
  pBt->pPage1 = 0;
  return rc;
}

/*
** This routine works like lockBtree() except that it also invokes the
** busy callback if there is lock contention.
*/
static int lockBtreeWithRetry(Btree *pRef){
  int rc = SQLITE_OK;
  if( pRef->inTrans==TRANS_NONE ){
    u8 inTransaction = pRef->pBt->inTransaction;
    btreeIntegrity(pRef);
    rc = sqlite3BtreeBeginTrans(pRef, 0);
    pRef->pBt->inTransaction = inTransaction;
    pRef->inTrans = TRANS_NONE;
    if( rc==SQLITE_OK ){
      pRef->pBt->nTransaction--;
    }
    btreeIntegrity(pRef);
  }
  return rc;
}
       

/*
** If there are no outstanding cursors and we are not in the middle
** of a transaction but there is a read lock on the database, then
** this routine unrefs the first page of the database file which 
** has the effect of releasing the read lock.
**
** If there are any outstanding cursors, this routine is a no-op.
**
** If there is a transaction in progress, this routine is a no-op.
*/
static void unlockBtreeIfUnused(BtShared *pBt){
  if( pBt->inTransaction==TRANS_NONE && pBt->pCursor==0 && pBt->pPage1!=0 ){
    if( sqlite3PagerRefcount(pBt->pPager)>=1 ){
      if( pBt->pPage1->aData==0 ){
        MemPage *pPage = pBt->pPage1;
        pPage->aData = &((u8*)pPage)[-pBt->pageSize];
        pPage->pBt = pBt;
        pPage->pgno = 1;
      }
      releasePage(pBt->pPage1);
    }
    pBt->pPage1 = 0;
    pBt->inStmt = 0;
  }
}

/*
** Create a new database by initializing the first page of the
** file.
*/
static int newDatabase(BtShared *pBt){
  MemPage *pP1;
  unsigned char *data;
  int rc;
  if( sqlite3PagerPagecount(pBt->pPager)>0 ) return SQLITE_OK;
  pP1 = pBt->pPage1;
  assert( pP1!=0 );
  data = pP1->aData;
  rc = sqlite3PagerWrite(pP1->pDbPage);
  if( rc ) return rc;
  memcpy(data, zMagicHeader, sizeof(zMagicHeader));
  assert( sizeof(zMagicHeader)==16 );
  put2byte(&data[16], pBt->pageSize);
  data[18] = 1;
  data[19] = 1;
  data[20] = pBt->pageSize - pBt->usableSize;
  data[21] = pBt->maxEmbedFrac;
  data[22] = pBt->minEmbedFrac;
  data[23] = pBt->minLeafFrac;
  memset(&data[24], 0, 100-24);
  zeroPage(pP1, PTF_INTKEY|PTF_LEAF|PTF_LEAFDATA );
  pBt->pageSizeFixed = 1;
#ifndef SQLITE_OMIT_AUTOVACUUM
  assert( pBt->autoVacuum==1 || pBt->autoVacuum==0 );
  assert( pBt->incrVacuum==1 || pBt->incrVacuum==0 );
  put4byte(&data[36 + 4*4], pBt->autoVacuum);
  put4byte(&data[36 + 7*4], pBt->incrVacuum);
#endif
  return SQLITE_OK;
}

/*
** Attempt to start a new transaction. A write-transaction
** is started if the second argument is nonzero, otherwise a read-
** transaction.  If the second argument is 2 or more and exclusive
** transaction is started, meaning that no other process is allowed
** to access the database.  A preexisting transaction may not be
** upgraded to exclusive by calling this routine a second time - the
** exclusivity flag only works for a new transaction.
**
** A write-transaction must be started before attempting any 
** changes to the database.  None of the following routines 
** will work unless a transaction is started first:
**
**      sqlite3BtreeCreateTable()
**      sqlite3BtreeCreateIndex()
**      sqlite3BtreeClearTable()
**      sqlite3BtreeDropTable()
**      sqlite3BtreeInsert()
**      sqlite3BtreeDelete()
**      sqlite3BtreeUpdateMeta()
**
** If an initial attempt to acquire the lock fails because of lock contention
** and the database was previously unlocked, then invoke the busy handler
** if there is one.  But if there was previously a read-lock, do not
** invoke the busy handler - just return SQLITE_BUSY.  SQLITE_BUSY is 
** returned when there is already a read-lock in order to avoid a deadlock.
**
** Suppose there are two processes A and B.  A has a read lock and B has
** a reserved lock.  B tries to promote to exclusive but is blocked because
** of A's read lock.  A tries to promote to reserved but is blocked by B.
** One or the other of the two processes must give way or there can be
** no progress.  By returning SQLITE_BUSY and not invoking the busy callback
** when A already has a read lock, we encourage A to give up and let B
** proceed.
*/
int sqlite3BtreeBeginTrans(Btree *p, int wrflag){
  BtShared *pBt = p->pBt;
  int rc = SQLITE_OK;

  btreeIntegrity(p);

  /* If the btree is already in a write-transaction, or it
  ** is already in a read-transaction and a read-transaction
  ** is requested, this is a no-op.
  */
  if( p->inTrans==TRANS_WRITE || (p->inTrans==TRANS_READ && !wrflag) ){
    return SQLITE_OK;
  }

  /* Write transactions are not possible on a read-only database */
  if( pBt->readOnly && wrflag ){
    return SQLITE_READONLY;
  }

  /* If another database handle has already opened a write transaction 
  ** on this shared-btree structure and a second write transaction is
  ** requested, return SQLITE_BUSY.
  */
  if( pBt->inTransaction==TRANS_WRITE && wrflag ){
    return SQLITE_BUSY;
  }

  do {
    if( pBt->pPage1==0 ){
      rc = lockBtree(pBt);
    }

    if( rc==SQLITE_OK && wrflag ){
      if( pBt->readOnly ){
        rc = SQLITE_READONLY;
      }else{
        rc = sqlite3PagerBegin(pBt->pPage1->pDbPage, wrflag>1);
        if( rc==SQLITE_OK ){
          rc = newDatabase(pBt);
        }
      }
    }
  
    if( rc==SQLITE_OK ){
      if( wrflag ) pBt->inStmt = 0;
    }else{
      unlockBtreeIfUnused(pBt);
    }
  }while( rc==SQLITE_BUSY && pBt->inTransaction==TRANS_NONE &&
          sqlite3InvokeBusyHandler(pBt->pBusyHandler) );

  if( rc==SQLITE_OK ){
    if( p->inTrans==TRANS_NONE ){
      pBt->nTransaction++;
    }
    p->inTrans = (wrflag?TRANS_WRITE:TRANS_READ);
    if( p->inTrans>pBt->inTransaction ){
      pBt->inTransaction = p->inTrans;
    }
  }

  btreeIntegrity(p);
  return rc;
}

#ifndef SQLITE_OMIT_AUTOVACUUM

/*
** Set the pointer-map entries for all children of page pPage. Also, if
** pPage contains cells that point to overflow pages, set the pointer
** map entries for the overflow pages as well.
*/
static int setChildPtrmaps(MemPage *pPage){
  int i;                             /* Counter variable */
  int nCell;                         /* Number of cells in page pPage */
  int rc;                            /* Return code */
  BtShared *pBt = pPage->pBt;
  int isInitOrig = pPage->isInit;
  Pgno pgno = pPage->pgno;

  rc = sqlite3BtreeInitPage(pPage, pPage->pParent);
  if( rc!=SQLITE_OK ){
    goto set_child_ptrmaps_out;
  }
  nCell = pPage->nCell;