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

  p->inTrans = TRANS_NONE;
  p->pSqlite = pSqlite;

  /* Try to find an existing Btree structure opened on zFilename. */
#if !defined(SQLITE_OMIT_SHARED_CACHE) && !defined(SQLITE_OMIT_DISKIO)
  pTsdro = sqlite3ThreadDataReadOnly();
  if( pTsdro->useSharedData && zFilename && !isMemdb ){
    char *zFullPathname = sqlite3OsFullPathname(zFilename);
    if( !zFullPathname ){
      sqliteFree(p);
      return SQLITE_NOMEM;
    }
    for(pBt=pTsdro->pBtree; pBt; pBt=pBt->pNext){
      assert( pBt->nRef>0 );
      if( 0==strcmp(zFullPathname, sqlite3pager_filename(pBt->pPager)) ){
        p->pBt = pBt;
        *ppBtree = p;
        pBt->nRef++;
        sqliteFree(zFullPathname);
        return SQLITE_OK;
      }
    }
    sqliteFree(zFullPathname);
  }
#endif

  /*
  ** The following asserts make sure that structures used by the btree are
  ** the right size.  This is to guard against size changes that result
  ** when compiling on a different architecture.
  */
  assert( sizeof(i64)==8 || sizeof(i64)==4 );
  assert( sizeof(u64)==8 || sizeof(u64)==4 );
  assert( sizeof(u32)==4 );
  assert( sizeof(u16)==2 );
  assert( sizeof(Pgno)==4 );

  pBt = sqliteMalloc( sizeof(*pBt) );
  if( pBt==0 ){
    *ppBtree = 0;
    sqliteFree(p);
    return SQLITE_NOMEM;
  }
  rc = sqlite3pager_open(&pBt->pPager, zFilename, EXTRA_SIZE, flags);
  if( rc==SQLITE_OK ){
    rc = sqlite3pager_read_fileheader(pBt->pPager,sizeof(zDbHeader),zDbHeader);
  }
  if( rc!=SQLITE_OK ){
    if( pBt->pPager ){
      sqlite3pager_close(pBt->pPager);
    }
    sqliteFree(pBt);
    sqliteFree(p);
    *ppBtree = 0;
    return rc;
  }
  p->pBt = pBt;

  sqlite3pager_set_destructor(pBt->pPager, pageDestructor);
  sqlite3pager_set_reiniter(pBt->pPager, pageReinit);
  pBt->pCursor = 0;
  pBt->pPage1 = 0;
  pBt->readOnly = sqlite3pager_isreadonly(pBt->pPager);
  pBt->pageSize = get2byte(&zDbHeader[16]);
  if( pBt->pageSize<512 || pBt->pageSize>SQLITE_MAX_PAGE_SIZE
       || ((pBt->pageSize-1)&pBt->pageSize)!=0 ){
    pBt->pageSize = SQLITE_DEFAULT_PAGE_SIZE;
    pBt->maxEmbedFrac = 64;   /* 25% */
    pBt->minEmbedFrac = 32;   /* 12.5% */
    pBt->minLeafFrac = 32;    /* 12.5% */
#ifndef SQLITE_OMIT_AUTOVACUUM
    /* If the magic name ":memory:" will create an in-memory database, then
    ** do not set the auto-vacuum flag, even if SQLITE_DEFAULT_AUTOVACUUM
    ** is true. On the other hand, if SQLITE_OMIT_MEMORYDB has been defined,
    ** then ":memory:" is just a regular file-name. Respect the auto-vacuum
    ** default in this case.
    */
    if( zFilename && !isMemdb ){
      pBt->autoVacuum = SQLITE_DEFAULT_AUTOVACUUM;
    }
#endif
    nReserve = 0;
  }else{
    nReserve = zDbHeader[20];
    pBt->maxEmbedFrac = zDbHeader[21];
    pBt->minEmbedFrac = zDbHeader[22];
    pBt->minLeafFrac = zDbHeader[23];
    pBt->pageSizeFixed = 1;
#ifndef SQLITE_OMIT_AUTOVACUUM
    pBt->autoVacuum = (get4byte(&zDbHeader[36 + 4*4])?1:0);
#endif
  }
  pBt->usableSize = pBt->pageSize - nReserve;
  assert( (pBt->pageSize & 7)==0 );  /* 8-byte alignment of pageSize */
  sqlite3pager_set_pagesize(pBt->pPager, pBt->pageSize);

#if !defined(SQLITE_OMIT_SHARED_CACHE) && !defined(SQLITE_OMIT_DISKIO)
  /* Add the new btree to the linked list starting at ThreadData.pBtree.
  ** There is no chance that a malloc() may fail inside of the 
  ** sqlite3ThreadData() call, as the ThreadData structure must have already
  ** been allocated for pTsdro->useSharedData to be non-zero.
  */
  if( pTsdro->useSharedData && zFilename && !isMemdb ){
    pBt->pNext = pTsdro->pBtree;
    sqlite3ThreadData()->pBtree = pBt;
  }
#endif
  pBt->nRef = 1;
  *ppBtree = p;
  return SQLITE_OK;
}

/*
** Close an open database and invalidate all cursors.
*/
int sqlite3BtreeClose(Btree *p){
  BtShared *pBt = p->pBt;
  BtCursor *pCur;

#ifndef SQLITE_OMIT_SHARED_CACHE
  ThreadData *pTsd;
#endif

  /* Close all cursors opened via this handle.  */
  pCur = pBt->pCursor;
  while( pCur ){
    BtCursor *pTmp = pCur;
    pCur = pCur->pNext;
    if( pTmp->pBtree==p ){
      sqlite3BtreeCloseCursor(pTmp);
    }
  }

  /* Rollback any active transaction and free the handle structure.
  ** The call to sqlite3BtreeRollback() drops any table-locks held by
  ** this handle.
  */
  sqlite3BtreeRollback(p);
  sqliteFree(p);

#ifndef SQLITE_OMIT_SHARED_CACHE
  /* If there are still other outstanding references to the shared-btree
  ** structure, return now. The remainder of this procedure cleans 
  ** up the shared-btree.
  */
  assert( pBt->nRef>0 );
  pBt->nRef--;
  if( pBt->nRef ){
    return SQLITE_OK;
  }

  /* Remove the shared-btree from the thread wide list. Call 
  ** ThreadDataReadOnly() and then cast away the const property of the 
  ** pointer to avoid allocating thread data if it is not really required.
  */
  pTsd = (ThreadData *)sqlite3ThreadDataReadOnly();
  if( pTsd->pBtree==pBt ){
    assert( pTsd==sqlite3ThreadData() );
    pTsd->pBtree = pBt->pNext;
  }else{
    BtShared *pPrev;
    for(pPrev=pTsd->pBtree; pPrev && pPrev->pNext!=pBt; pPrev=pPrev->pNext){}
    if( pPrev ){
      assert( pTsd==sqlite3ThreadData() );
      pPrev->pNext = pBt->pNext;
    }
  }
#endif

  /* Close the pager and free the shared-btree structure */
  assert( !pBt->pCursor );
  sqlite3pager_close(pBt->pPager);
  if( pBt->xFreeSchema && pBt->pSchema ){
    pBt->xFreeSchema(pBt->pSchema);
  }
  sqliteFree(pBt->pSchema);
  sqliteFree(pBt);
  return SQLITE_OK;
}

/*
** Change the busy handler callback function.
*/
int sqlite3BtreeSetBusyHandler(Btree *p, BusyHandler *pHandler){
  BtShared *pBt = p->pBt;
  pBt->pBusyHandler = pHandler;
  sqlite3pager_set_busyhandler(pBt->pPager, pHandler);
  return SQLITE_OK;
}

/*
** Change the limit on the number of pages allowed in the cache.
**
** 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;
  sqlite3pager_set_cachesize(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;
  sqlite3pager_set_safety_level(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 sqlite3pager_nosync(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 = sqlite3pager_set_pagesize(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;
}
#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){
  BtShared *pBt = p->pBt;;
#ifdef SQLITE_OMIT_AUTOVACUUM
  return SQLITE_READONLY;
#else
  if( pBt->pageSizeFixed ){
    return SQLITE_READONLY;
  }
  pBt->autoVacuum = (autoVacuum?1:0);
  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 0;
#else
  return p->pBt->autoVacuum;
#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.  SQLITE_PROTOCOL is returned
** if there is a locking protocol violation.
*/
static int lockBtree(BtShared *pBt){
  int rc, pageSize;
  MemPage *pPage1;
  if( pBt->pPage1 ) return SQLITE_OK;
  rc = getPage(pBt, 1, &pPage1);
  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( sqlite3pager_pagecount(pBt->pPager)>0 ){
    u8 *page1 = pPage1->aData;
    if( memcmp(page1, zMagicHeader, 16)!=0 ){
      goto page1_init_failed;
    }
    if( page1[18]>1 || page1[19]>1 ){
      goto page1_init_failed;
    }
    pageSize = get2byte(&page1[16]);
    if( ((pageSize-1)&pageSize)!=0 ){
      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);
#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 ove