2021SC@SDUSC SQLite源码分析(三)————B树API与游标
2021SC@SDUSC SQLite源码分析(三)————B树与内存的页一、B-tree模块的API二、API功能分析三 、关于游标一、B-tree模块的APIB-tree模块有自己的API,它们是独立于sqlite外部API的。这些API主要是针对SQLite需求量身定做的,因此对于其他的数据库并不适用。要想更加了解SQLite内部机制,先了解这些API是很有必要的。B-tree的另一个优点是
2021SC@SDUSC SQLite源码分析(三)————B树API与游标
一、B-tree模块的API
B-tree模块有自己的API,它们是独立于sqlite外部API的。这些API主要是针对SQLite需求量身定做的,因此对于其他的数据库并不适用。要想更加了解SQLite内部机制,先了解这些API是很有必要的。B-tree的另一个优点是本身事务机制、pager处理事务、锁以及日志文件,并为B-tree模块提供支持。B-tree API根据目的大体划分成以下函数:存取及事务函数,表函数 ,游标函数 ,记录函数,配置管理函数 。
(C API负责域值,VDBE负责处理记录,B-tree负责处理键值和数据,pager负责处理页,操作系统接口负责处理二进制数据和原始数据存储。 每个模块负责维护自身在数据库中对应的数据部分,然后依靠底层提供所需信息的初始数据,并从中提取需要的内容。)
二、API功能分析
打开数据库文件和数据库文件加锁等相关的API:
数据库建表,删表相关的API:
遍历表格的游标相关API:
增删改查相关的API:
数据库参数配置相关的API:
图源:http://huili.github.io/B-treeImplementation/b-tree_api.html
sqlite3BtreeOpen函数:
/*
** Open a database file.
**
** zFilename is the name of the database file. If zFilename is NULL
** then an ephemeral database is created. The ephemeral database might
** be exclusively in memory, or it might use a disk-based memory cache.
** Either way, the ephemeral database will be automatically deleted
** when sqlite3BtreeClose() is called.
**
** If zFilename is ":memory:" then an in-memory database is created
** that is automatically destroyed when it is closed.
**
** The "flags" parameter is a bitmask that might contain bits like
** BTREE_OMIT_JOURNAL and/or BTREE_MEMORY.
**
** If the database is already opened in the same database connection
** and we are in shared cache mode, then the open will fail with an
** SQLITE_CONSTRAINT error. We cannot allow two or more BtShared
** objects in the same database connection since doing so will lead
** to problems with locking.
*/
int sqlite3BtreeOpen(
sqlite3_vfs *pVfs, /* VFS to use for this b-tree */
const char *zFilename, /* Name of the file containing the BTree database */
sqlite3 *db, /* Associated database handle */
Btree **ppBtree, /* Pointer to new Btree object written here */
int flags, /* Options */
int vfsFlags /* Flags passed through to sqlite3_vfs.xOpen() */
){
BtShared *pBt = 0; /* Shared part of btree structure */
Btree *p; /* Handle to return */
sqlite3_mutex *mutexOpen = 0; /* Prevents a race condition. Ticket #3537 */
int rc = SQLITE_OK; /* Result code from this function */
u8 nReserve; /* Byte of unused space on each page */
unsigned char zDbHeader[100]; /* Database header content */
/* True if opening an ephemeral, temporary database */
const int isTempDb = zFilename==0 || zFilename[0]==0;
/* Set the variable isMemdb to true for an in-memory database, or
** false for a file-based database.
*/
#ifdef SQLITE_OMIT_MEMORYDB
const int isMemdb = 0;
#else
const int isMemdb = (zFilename && strcmp(zFilename, ":memory:")==0)
|| (isTempDb && sqlite3TempInMemory(db))
|| (vfsFlags & SQLITE_OPEN_MEMORY)!=0;
#endif
assert( db!=0 );
assert( pVfs!=0 );
assert( sqlite3_mutex_held(db->mutex) );
assert( (flags&0xff)==flags ); /* flags fit in 8 bits */
/* Only a BTREE_SINGLE database can be BTREE_UNORDERED */
assert( (flags & BTREE_UNORDERED)==0 || (flags & BTREE_SINGLE)!=0 );
/* A BTREE_SINGLE database is always a temporary and/or ephemeral */
assert( (flags & BTREE_SINGLE)==0 || isTempDb );
if( isMemdb ){
flags |= BTREE_MEMORY;
}
if( (vfsFlags & SQLITE_OPEN_MAIN_DB)!=0 && (isMemdb || isTempDb) ){
vfsFlags = (vfsFlags & ~SQLITE_OPEN_MAIN_DB) | SQLITE_OPEN_TEMP_DB;
}
p = sqlite3MallocZero(sizeof(Btree));
if( !p ){
return SQLITE_NOMEM_BKPT;
}
p->inTrans = TRANS_NONE;
p->db = db;
#ifndef SQLITE_OMIT_SHARED_CACHE
p->lock.pBtree = p;
p->lock.iTable = 1;
#endif
#if !defined(SQLITE_OMIT_SHARED_CACHE) && !defined(SQLITE_OMIT_DISKIO)
/*
** If this Btree is a candidate for shared cache, try to find an
** existing BtShared object that we can share with
*/
if( isTempDb==0 && (isMemdb==0 || (vfsFlags&SQLITE_OPEN_URI)!=0) ){
if( vfsFlags & SQLITE_OPEN_SHAREDCACHE ){
int nFilename = sqlite3Strlen30(zFilename)+1;
int nFullPathname = pVfs->mxPathname+1;
char *zFullPathname = sqlite3Malloc(MAX(nFullPathname,nFilename));
MUTEX_LOGIC( sqlite3_mutex *mutexShared; )
p->sharable = 1;
if( !zFullPathname ){
sqlite3_free(p);
return SQLITE_NOMEM_BKPT;
}
if( isMemdb ){
memcpy(zFullPathname, zFilename, nFilename);
}else{
rc = sqlite3OsFullPathname(pVfs, zFilename,
nFullPathname, zFullPathname);
if( rc ){
if( rc==SQLITE_OK_SYMLINK ){
rc = SQLITE_OK;
}else{
sqlite3_free(zFullPathname);
sqlite3_free(p);
return rc;
}
}
}
#if SQLITE_THREADSAFE
mutexOpen = sqlite3MutexAlloc(SQLITE_MUTEX_STATIC_OPEN);
sqlite3_mutex_enter(mutexOpen);
mutexShared = sqlite3MutexAlloc(SQLITE_MUTEX_STATIC_MAIN);
sqlite3_mutex_enter(mutexShared);
#endif
for(pBt=GLOBAL(BtShared*,sqlite3SharedCacheList); pBt; pBt=pBt->pNext){
assert( pBt->nRef>0 );
if( 0==strcmp(zFullPathname, sqlite3PagerFilename(pBt->pPager, 0))
&& sqlite3PagerVfs(pBt->pPager)==pVfs ){
int iDb;
for(iDb=db->nDb-1; iDb>=0; iDb--){
Btree *pExisting = db->aDb[iDb].pBt;
if( pExisting && pExisting->pBt==pBt ){
sqlite3_mutex_leave(mutexShared);
sqlite3_mutex_leave(mutexOpen);
sqlite3_free(zFullPathname);
sqlite3_free(p);
return SQLITE_CONSTRAINT;
}
}
p->pBt = pBt;
pBt->nRef++;
break;
}
}
sqlite3_mutex_leave(mutexShared);
sqlite3_free(zFullPathname);
}
#ifdef SQLITE_DEBUG
else{
/* In debug mode, we mark all persistent databases as sharable
** even when they are not. This exercises the locking code and
** gives more opportunity for asserts(sqlite3_mutex_held())
** statements to find locking problems.
*/
p->sharable = 1;
}
#endif
}
#endif
if( pBt==0 ){
/*
** 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 );
assert( sizeof(u64)==8 );
assert( sizeof(u32)==4 );
assert( sizeof(u16)==2 );
assert( sizeof(Pgno)==4 );
pBt = sqlite3MallocZero( sizeof(*pBt) );
if( pBt==0 ){
rc = SQLITE_NOMEM_BKPT;
goto btree_open_out;
}
rc = sqlite3PagerOpen(pVfs, &pBt->pPager, zFilename,
sizeof(MemPage), flags, vfsFlags, pageReinit);
if( rc==SQLITE_OK ){
sqlite3PagerSetMmapLimit(pBt->pPager, db->szMmap);
rc = sqlite3PagerReadFileheader(pBt->pPager,sizeof(zDbHeader),zDbHeader);
}
if( rc!=SQLITE_OK ){
goto btree_open_out;
}
pBt->openFlags = (u8)flags;
pBt->db = db;
sqlite3PagerSetBusyHandler(pBt->pPager, btreeInvokeBusyHandler, pBt);
p->pBt = pBt;
pBt->pCursor = 0;
pBt->pPage1 = 0;
if( sqlite3PagerIsreadonly(pBt->pPager) ) pBt->btsFlags |= BTS_READ_ONLY;
#if defined(SQLITE_SECURE_DELETE)
pBt->btsFlags |= BTS_SECURE_DELETE;
#elif defined(SQLITE_FAST_SECURE_DELETE)
pBt->btsFlags |= BTS_OVERWRITE;
#endif
/* EVIDENCE-OF: R-51873-39618 The page size for a database file is
** determined by the 2-byte integer located at an offset of 16 bytes from
** the beginning of the database file. */
pBt->pageSize = (zDbHeader[16]<<8) | (zDbHeader[17]<<16);
if( pBt->pageSize<512 || pBt->pageSize>SQLITE_MAX_PAGE_SIZE
|| ((pBt->pageSize-1)&pBt->pageSize)!=0 ){
pBt->pageSize = 0;
#ifndef SQLITE_OMIT_AUTOVACUUM
/* If the magic name ":memory:" will create an in-memory database, then
** leave the autoVacuum mode at 0 (do not auto-vacuum), 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. In this case the auto-vacuum applies as per normal.
*/
if( zFilename && !isMemdb ){
pBt->autoVacuum = (SQLITE_DEFAULT_AUTOVACUUM ? 1 : 0);
pBt->incrVacuum = (SQLITE_DEFAULT_AUTOVACUUM==2 ? 1 : 0);
}
#endif
nReserve = 0;
}else{
/* EVIDENCE-OF: R-37497-42412 The size of the reserved region is
** determined by the one-byte unsigned integer found at an offset of 20
** into the database file header. */
nReserve = zDbHeader[20];
pBt->btsFlags |= BTS_PAGESIZE_FIXED;
#ifndef SQLITE_OMIT_AUTOVACUUM
pBt->autoVacuum = (get4byte(&zDbHeader[36 + 4*4])?1:0);
pBt->incrVacuum = (get4byte(&zDbHeader[36 + 7*4])?1:0);
#endif
}
rc = sqlite3PagerSetPagesize(pBt->pPager, &pBt->pageSize, nReserve);
if( rc ) goto btree_open_out;
pBt->usableSize = pBt->pageSize - nReserve;
assert( (pBt->pageSize & 7)==0 ); /* 8-byte alignment of pageSize */
#if !defined(SQLITE_OMIT_SHARED_CACHE) && !defined(SQLITE_OMIT_DISKIO)
/* Add the new BtShared object to the linked list sharable BtShareds.
*/
pBt->nRef = 1;
if( p->sharable ){
MUTEX_LOGIC( sqlite3_mutex *mutexShared; )
MUTEX_LOGIC( mutexShared = sqlite3MutexAlloc(SQLITE_MUTEX_STATIC_MAIN);)
if( SQLITE_THREADSAFE && sqlite3GlobalConfig.bCoreMutex ){
pBt->mutex = sqlite3MutexAlloc(SQLITE_MUTEX_FAST);
if( pBt->mutex==0 ){
rc = SQLITE_NOMEM_BKPT;
goto btree_open_out;
}
}
sqlite3_mutex_enter(mutexShared);
pBt->pNext = GLOBAL(BtShared*,sqlite3SharedCacheList);
GLOBAL(BtShared*,sqlite3SharedCacheList) = pBt;
sqlite3_mutex_leave(mutexShared);
}
#endif
}
#if !defined(SQLITE_OMIT_SHARED_CACHE) && !defined(SQLITE_OMIT_DISKIO)
/* If the new Btree uses a sharable pBtShared, then link the new
** Btree into the list of all sharable Btrees for the same connection.
** The list is kept in ascending order by pBt address.
*/
if( p->sharable ){
int i;
Btree *pSib;
for(i=0; i<db->nDb; i++){
if( (pSib = db->aDb[i].pBt)!=0 && pSib->sharable ){
while( pSib->pPrev ){ pSib = pSib->pPrev; }
if( (uptr)p->pBt<(uptr)pSib->pBt ){
p->pNext = pSib;
p->pPrev = 0;
pSib->pPrev = p;
}else{
while( pSib->pNext && (uptr)pSib->pNext->pBt<(uptr)p->pBt ){
pSib = pSib->pNext;
}
p->pNext = pSib->pNext;
p->pPrev = pSib;
if( p->pNext ){
p->pNext->pPrev = p;
}
pSib->pNext = p;
}
break;
}
}
}
#endif
*ppBtree = p;
btree_open_out:
if( rc!=SQLITE_OK ){
if( pBt && pBt->pPager ){
sqlite3PagerClose(pBt->pPager, 0);
}
sqlite3_free(pBt);
sqlite3_free(p);
*ppBtree = 0;
}else{
sqlite3_file *pFile;
/* If the B-Tree was successfully opened, set the pager-cache size to the
** default value. Except, when opening on an existing shared pager-cache,
** do not change the pager-cache size.
*/
if( sqlite3BtreeSchema(p, 0, 0)==0 ){
sqlite3BtreeSetCacheSize(p, SQLITE_DEFAULT_CACHE_SIZE);
}
pFile = sqlite3PagerFile(pBt->pPager);
if( pFile->pMethods ){
sqlite3OsFileControlHint(pFile, SQLITE_FCNTL_PDB, (void*)&pBt->db);
}
}
if( mutexOpen ){
assert( sqlite3_mutex_held(mutexOpen) );
sqlite3_mutex_leave(mutexOpen);
}
assert( rc!=SQ
三 、关于游标
btreeInt.h 中 游标 的定义:
/*
** A cursor is a pointer to a particular entry within a particular
** b-tree within a database file.
**
** The entry is identified by its MemPage and the index in
** MemPage.aCell[] of the entry.
**
** A single database file can be shared by two more database connections,
** but cursors cannot be shared. Each cursor is associated with a
** particular database connection identified BtCursor.pBtree.db.
**
** Fields in this structure are accessed under the BtShared.mutex
** found at self->pBt->mutex.
**
** skipNext meaning:
** The meaning of skipNext depends on the value of eState:
**
** eState Meaning of skipNext
** VALID skipNext is meaningless and is ignored
** INVALID skipNext is meaningless and is ignored
** SKIPNEXT sqlite3BtreeNext() is a no-op if skipNext>0 and
** sqlite3BtreePrevious() is no-op if skipNext<0.
** REQUIRESEEK restoreCursorPosition() restores the cursor to
** eState=SKIPNEXT if skipNext!=0
** FAULT skipNext holds the cursor fault error code.
*/
struct BtCursor {
u8 eState; /* One of the CURSOR_XXX constants (see below) */
u8 curFlags; /* zero or more BTCF_* flags defined below */
u8 curPagerFlags; /* Flags to send to sqlite3PagerGet() */
u8 hints; /* As configured by CursorSetHints() */
int skipNext; /* Prev() is noop if negative. Next() is noop if positive.
** Error code if eState==CURSOR_FAULT */
Btree *pBtree; /* The Btree to which this cursor belongs */
Pgno *aOverflow; /* Cache of overflow page locations */
void *pKey; /* Saved key that was cursor last known position */
/* All fields above are zeroed when the cursor is allocated. See
** sqlite3BtreeCursorZero(). Fields that follow must be manually
** initialized. */
#define BTCURSOR_FIRST_UNINIT pBt /* Name of first uninitialized field */
BtShared *pBt; /* The BtShared this cursor points to */
BtCursor *pNext; /* Forms a linked list of all cursors */
CellInfo info; /* A parse of the cell we are pointing at */
i64 nKey; /* Size of pKey, or last integer key */
Pgno pgnoRoot; /* The root page of this tree */
i8 iPage; /* Index of current page in apPage */
u8 curIntKey; /* Value of apPage[0]->intKey */
u16 ix; /* Current index for apPage[iPage] */
u16 aiIdx[BTCURSOR_MAX_DEPTH-1]; /* Current index in apPage[i] */
struct KeyInfo *pKeyInfo; /* Arg passed to comparison function */
MemPage *pPage; /* Current page */
MemPage *apPage[BTCURSOR_MAX_DEPTH-1]; /* Stack of parents of current page */
};
btree.c中的btreeCursor:
/*
** Create a new cursor for the BTree whose root is on the page
** iTable. If a read-only cursor is requested, it is assumed that
** the caller already has at least a read-only transaction open
** on the database already. If a write-cursor is requested, then
** the caller is assumed to have an open write transaction.
**
** If the BTREE_WRCSR bit of wrFlag is clear, then the cursor can only
** be used for reading. If the BTREE_WRCSR bit is set, then the cursor
** can be used for reading or for writing if other conditions for writing
** are also met. These are the conditions that must be met in order
** for writing to be allowed:
**
** 1: The cursor must have been opened with wrFlag containing BTREE_WRCSR
**
** 2: Other database connections that share the same pager cache
** but which are not in the READ_UNCOMMITTED state may not have
** cursors open with wrFlag==0 on the same table. Otherwise
** the changes made by this write cursor would be visible to
** the read cursors in the other database connection.
**
** 3: The database must be writable (not on read-only media)
**
** 4: There must be an active transaction.
**
** The BTREE_FORDELETE bit of wrFlag may optionally be set if BTREE_WRCSR
** is set. If FORDELETE is set, that is a hint to the implementation that
** this cursor will only be used to seek to and delete entries of an index
** as part of a larger DELETE statement. The FORDELETE hint is not used by
** this implementation. But in a hypothetical alternative storage engine
** in which index entries are automatically deleted when corresponding table
** rows are deleted, the FORDELETE flag is a hint that all SEEK and DELETE
** operations on this cursor can be no-ops and all READ operations can
** return a null row (2-bytes: 0x01 0x00).
**
** No checking is done to make sure that page iTable really is the
** root page of a b-tree. If it is not, then the cursor acquired
** will not work correctly.
**
** It is assumed that the sqlite3BtreeCursorZero() has been called
** on pCur to initialize the memory space prior to invoking this routine.
*/
static int btreeCursor(
Btree *p, /* The btree */
Pgno iTable, /* Root page of table to open */
int wrFlag, /* 1 to write. 0 read-only */
struct KeyInfo *pKeyInfo, /* First arg to comparison function */
BtCursor *pCur /* Space for new cursor */
){
BtShared *pBt = p->pBt; /* Shared b-tree handle */
BtCursor *pX; /* Looping over other all cursors */
assert( sqlite3BtreeHoldsMutex(p) );
assert( wrFlag==0
|| wrFlag==BTREE_WRCSR
|| wrFlag==(BTREE_WRCSR|BTREE_FORDELETE)
);
/* The following assert statements verify that if this is a sharable
** b-tree database, the connection is holding the required table locks,
** and that no other connection has any open cursor that conflicts with
** this lock. The iTable<1 term disables the check for corrupt schemas. */
assert( hasSharedCacheTableLock(p, iTable, pKeyInfo!=0, (wrFlag?2:1))
|| iTable<1 );
assert( wrFlag==0 || !hasReadConflicts(p, iTable) );
/* Assert that the caller has opened the required transaction. */
assert( p->inTrans>TRANS_NONE );
assert( wrFlag==0 || p->inTrans==TRANS_WRITE );
assert( pBt->pPage1 && pBt->pPage1->aData );
assert( wrFlag==0 || (pBt->btsFlags & BTS_READ_ONLY)==0 );
if( wrFlag ){
allocateTempSpace(pBt);
if( pBt->pTmpSpace==0 ) return SQLITE_NOMEM_BKPT;
}
if( iTable<=1 ){
if( iTable<1 ){
return SQLITE_CORRUPT_BKPT;
}else if( btreePagecount(pBt)==0 ){
assert( wrFlag==0 );
iTable = 0;
}
}
/* Now that no other errors can occur, finish filling in the BtCursor
** variables and link the cursor into the BtShared list. */
pCur->pgnoRoot = iTable;
pCur->iPage = -1;
pCur->pKeyInfo = pKeyInfo;
pCur->pBtree = p;
pCur->pBt = pBt;
pCur->curFlags = wrFlag ? BTCF_WriteFlag : 0;
pCur->curPagerFlags = wrFlag ? 0 : PAGER_GET_READONLY;
/* If there are two or more cursors on the same btree, then all such
** cursors *must* have the BTCF_Multiple flag set. */
for(pX=pBt->pCursor; pX; pX=pX->pNext){
if( pX->pgnoRoot==iTable ){
pX->curFlags |= BTCF_Multiple;
pCur->curFlags |= BTCF_Multiple;
}
}
pCur->pNext = pBt->pCursor;
pBt->pCursor = pCur;
pCur->eState = CURSOR_INVALID;
return SQLITE_OK;
}
游标是一种从表中检索数据并进行操作的灵活手段,游标主要用在服务器上,处理由客户端发送给服务端的sql语句,或是批处理、存储过程、触发器中的数据处理请求。
游标的优点在于它可以定位到结果集中的某一行,并可以对该行数据执行特定操作。一个完整的游标由5部分组成:
(1)声明游标 (2)打开游标 (3)从一个游标中查找信息 (4)关闭游标 (5)释放游标
2在性能上,游标会吃更多的内存,减少可用的并发,占用宽带,锁定资源还有更多的代码量。可是为什么学习游标呢?
1 现存系统有一些游标,我们查询必须通过游标来实现
2 作为一个备用方式,当我们穷尽了while循环,子查询,临时表,表变量,自建函数或其他方式仍然无法实现某些查询的时候用游标来实现。
使用Cursor对象执行select语句时,通过featchall()返回select的全部数据结果集。结果集是一个list,每个元素都是一个tuple,对应一行记录,按建表的字段顺序排列。fetchone()返回一条结果,是一个tuple,每个元素是一个字段值。
需要注意的是,SQLite游标是有状态的,只能遍历结果集一次,不能在结果集中返回移动,遍历结束返回空值。featchall()一次性返回全部结果,fetchone()依顺序每次返回一条结果,而且对fetchone()执行len()操作以获得所取得记录的条数后,相当于完成对结果集的一次遍历,结果集将被清空。因此,取得结果集后,如需对结果集进行进一步操作,可将结果集保存到变量中。
更多推荐
所有评论(0)