/library/Library/WP7/SQLiteDriver/sqlite/wal_c.cs
C# | 2751 lines | 1384 code | 225 blank | 1142 comment | 244 complexity | c71f94acbce0b78bc9e2a56f8e0c2e0a MD5 | raw file
- using System;
- using System.Diagnostics;
- using System.Text;
- using Bitmask = System.UInt64;
- using u32 = System.UInt32;
- namespace Community.CsharpSqlite
- {
- public partial class Sqlite3
- {
- /*
- ** 2010 February 1
- **
- ** The author disclaims copyright to this source code. In place of
- ** a legal notice, here is a blessing:
- **
- ** May you do good and not evil.
- ** May you find forgiveness for yourself and forgive others.
- ** May you share freely, never taking more than you give.
- **
- *************************************************************************
- **
- ** This file contains the implementation of a write-ahead log (WAL) used in
- ** "journal_mode=WAL" mode.
- **
- ** WRITE-AHEAD LOG (WAL) FILE FORMAT
- **
- ** A WAL file consists of a header followed by zero or more "frames".
- ** Each frame records the revised content of a single page from the
- ** database file. All changes to the database are recorded by writing
- ** frames into the WAL. Transactions commit when a frame is written that
- ** contains a commit marker. A single WAL can and usually does record
- ** multiple transactions. Periodically, the content of the WAL is
- ** transferred back into the database file in an operation called a
- ** "checkpoint".
- **
- ** A single WAL file can be used multiple times. In other words, the
- ** WAL can fill up with frames and then be checkpointed and then new
- ** frames can overwrite the old ones. A WAL always grows from beginning
- ** toward the end. Checksums and counters attached to each frame are
- ** used to determine which frames within the WAL are valid and which
- ** are leftovers from prior checkpoints.
- **
- ** The WAL header is 32 bytes in size and consists of the following eight
- ** big-endian 32-bit unsigned integer values:
- **
- ** 0: Magic number. 0x377f0682 or 0x377f0683
- ** 4: File format version. Currently 3007000
- ** 8: Database page size. Example: 1024
- ** 12: Checkpoint sequence number
- ** 16: Salt-1, random integer incremented with each checkpoint
- ** 20: Salt-2, a different random integer changing with each ckpt
- ** 24: Checksum-1 (first part of checksum for first 24 bytes of header).
- ** 28: Checksum-2 (second part of checksum for first 24 bytes of header).
- **
- ** Immediately following the wal-header are zero or more frames. Each
- ** frame consists of a 24-byte frame-header followed by a <page-size> bytes
- ** of page data. The frame-header is six big-endian 32-bit unsigned
- ** integer values, as follows:
- **
- ** 0: Page number.
- ** 4: For commit records, the size of the database image in pages
- ** after the commit. For all other records, zero.
- ** 8: Salt-1 (copied from the header)
- ** 12: Salt-2 (copied from the header)
- ** 16: Checksum-1.
- ** 20: Checksum-2.
- **
- ** A frame is considered valid if and only if the following conditions are
- ** true:
- **
- ** (1) The salt-1 and salt-2 values in the frame-header match
- ** salt values in the wal-header
- **
- ** (2) The checksum values in the final 8 bytes of the frame-header
- ** exactly match the checksum computed consecutively on the
- ** WAL header and the first 8 bytes and the content of all frames
- ** up to and including the current frame.
- **
- ** The checksum is computed using 32-bit big-endian integers if the
- ** magic number in the first 4 bytes of the WAL is 0x377f0683 and it
- ** is computed using little-endian if the magic number is 0x377f0682.
- ** The checksum values are always stored in the frame header in a
- ** big-endian format regardless of which byte order is used to compute
- ** the checksum. The checksum is computed by interpreting the input as
- ** an even number of unsigned 32-bit integers: x[0] through x[N]. The
- ** algorithm used for the checksum is as follows:
- **
- ** for i from 0 to n-1 step 2:
- ** s0 += x[i] + s1;
- ** s1 += x[i+1] + s0;
- ** endfor
- **
- ** Note that s0 and s1 are both weighted checksums using fibonacci weights
- ** in reverse order (the largest fibonacci weight occurs on the first element
- ** of the sequence being summed.) The s1 value spans all 32-bit
- ** terms of the sequence whereas s0 omits the final term.
- **
- ** On a checkpoint, the WAL is first VFS.xSync-ed, then valid content of the
- ** WAL is transferred into the database, then the database is VFS.xSync-ed.
- ** The VFS.xSync operations serve as write barriers - all writes launched
- ** before the xSync must complete before any write that launches after the
- ** xSync begins.
- **
- ** After each checkpoint, the salt-1 value is incremented and the salt-2
- ** value is randomized. This prevents old and new frames in the WAL from
- ** being considered valid at the same time and being checkpointing together
- ** following a crash.
- **
- ** READER ALGORITHM
- **
- ** To read a page from the database (call it page number P), a reader
- ** first checks the WAL to see if it contains page P. If so, then the
- ** last valid instance of page P that is a followed by a commit frame
- ** or is a commit frame itself becomes the value read. If the WAL
- ** contains no copies of page P that are valid and which are a commit
- ** frame or are followed by a commit frame, then page P is read from
- ** the database file.
- **
- ** To start a read transaction, the reader records the index of the last
- ** valid frame in the WAL. The reader uses this recorded "mxFrame" value
- ** for all subsequent read operations. New transactions can be appended
- ** to the WAL, but as long as the reader uses its original mxFrame value
- ** and ignores the newly appended content, it will see a consistent snapshot
- ** of the database from a single point in time. This technique allows
- ** multiple concurrent readers to view different versions of the database
- ** content simultaneously.
- **
- ** The reader algorithm in the previous paragraphs works correctly, but
- ** because frames for page P can appear anywhere within the WAL, the
- ** reader has to scan the entire WAL looking for page P frames. If the
- ** WAL is large (multiple megabytes is typical) that scan can be slow,
- ** and read performance suffers. To overcome this problem, a separate
- ** data structure called the wal-index is maintained to expedite the
- ** search for frames of a particular page.
- **
- ** WAL-INDEX FORMAT
- **
- ** Conceptually, the wal-index is shared memory, though VFS implementations
- ** might choose to implement the wal-index using a mmapped file. Because
- ** the wal-index is shared memory, SQLite does not support journal_mode=WAL
- ** on a network filesystem. All users of the database must be able to
- ** share memory.
- **
- ** The wal-index is transient. After a crash, the wal-index can (and should
- ** be) reconstructed from the original WAL file. In fact, the VFS is required
- ** to either truncate or zero the header of the wal-index when the last
- ** connection to it closes. Because the wal-index is transient, it can
- ** use an architecture-specific format; it does not have to be cross-platform.
- ** Hence, unlike the database and WAL file formats which store all values
- ** as big endian, the wal-index can store multi-byte values in the native
- ** byte order of the host computer.
- **
- ** The purpose of the wal-index is to answer this question quickly: Given
- ** a page number P, return the index of the last frame for page P in the WAL,
- ** or return NULL if there are no frames for page P in the WAL.
- **
- ** The wal-index consists of a header region, followed by an one or
- ** more index blocks.
- **
- ** The wal-index header contains the total number of frames within the WAL
- ** in the the mxFrame field.
- **
- ** Each index block except for the first contains information on
- ** HASHTABLE_NPAGE frames. The first index block contains information on
- ** HASHTABLE_NPAGE_ONE frames. The values of HASHTABLE_NPAGE_ONE and
- ** HASHTABLE_NPAGE are selected so that together the wal-index header and
- ** first index block are the same size as all other index blocks in the
- ** wal-index.
- **
- ** Each index block contains two sections, a page-mapping that contains the
- ** database page number associated with each wal frame, and a hash-table
- ** that allows readers to query an index block for a specific page number.
- ** The page-mapping is an array of HASHTABLE_NPAGE (or HASHTABLE_NPAGE_ONE
- ** for the first index block) 32-bit page numbers. The first entry in the
- ** first index-block contains the database page number corresponding to the
- ** first frame in the WAL file. The first entry in the second index block
- ** in the WAL file corresponds to the (HASHTABLE_NPAGE_ONE+1)th frame in
- ** the log, and so on.
- **
- ** The last index block in a wal-index usually contains less than the full
- ** complement of HASHTABLE_NPAGE (or HASHTABLE_NPAGE_ONE) page-numbers,
- ** depending on the contents of the WAL file. This does not change the
- ** allocated size of the page-mapping array - the page-mapping array merely
- ** contains unused entries.
- **
- ** Even without using the hash table, the last frame for page P
- ** can be found by scanning the page-mapping sections of each index block
- ** starting with the last index block and moving toward the first, and
- ** within each index block, starting at the end and moving toward the
- ** beginning. The first entry that equals P corresponds to the frame
- ** holding the content for that page.
- **
- ** The hash table consists of HASHTABLE_NSLOT 16-bit unsigned integers.
- ** HASHTABLE_NSLOT = 2*HASHTABLE_NPAGE, and there is one entry in the
- ** hash table for each page number in the mapping section, so the hash
- ** table is never more than half full. The expected number of collisions
- ** prior to finding a match is 1. Each entry of the hash table is an
- ** 1-based index of an entry in the mapping section of the same
- ** index block. Let K be the 1-based index of the largest entry in
- ** the mapping section. (For index blocks other than the last, K will
- ** always be exactly HASHTABLE_NPAGE (4096) and for the last index block
- ** K will be (mxFrame%HASHTABLE_NPAGE).) Unused slots of the hash table
- ** contain a value of 0.
- **
- ** To look for page P in the hash table, first compute a hash iKey on
- ** P as follows:
- **
- ** iKey = (P * 383) % HASHTABLE_NSLOT
- **
- ** Then start scanning entries of the hash table, starting with iKey
- ** (wrapping around to the beginning when the end of the hash table is
- ** reached) until an unused hash slot is found. Let the first unused slot
- ** be at index iUnused. (iUnused might be less than iKey if there was
- ** wrap-around.) Because the hash table is never more than half full,
- ** the search is guaranteed to eventually hit an unused entry. Let
- ** iMax be the value between iKey and iUnused, closest to iUnused,
- ** where aHash[iMax]==P. If there is no iMax entry (if there exists
- ** no hash slot such that aHash[i]==p) then page P is not in the
- ** current index block. Otherwise the iMax-th mapping entry of the
- ** current index block corresponds to the last entry that references
- ** page P.
- **
- ** A hash search begins with the last index block and moves toward the
- ** first index block, looking for entries corresponding to page P. On
- ** average, only two or three slots in each index block need to be
- ** examined in order to either find the last entry for page P, or to
- ** establish that no such entry exists in the block. Each index block
- ** holds over 4000 entries. So two or three index blocks are sufficient
- ** to cover a typical 10 megabyte WAL file, assuming 1K pages. 8 or 10
- ** comparisons (on average) suffice to either locate a frame in the
- ** WAL or to establish that the frame does not exist in the WAL. This
- ** is much faster than scanning the entire 10MB WAL.
- **
- ** Note that entries are added in order of increasing K. Hence, one
- ** reader might be using some value K0 and a second reader that started
- ** at a later time (after additional transactions were added to the WAL
- ** and to the wal-index) might be using a different value K1, where K1>K0.
- ** Both readers can use the same hash table and mapping section to get
- ** the correct result. There may be entries in the hash table with
- ** K>K0 but to the first reader, those entries will appear to be unused
- ** slots in the hash table and so the first reader will get an answer as
- ** if no values greater than K0 had ever been inserted into the hash table
- ** in the first place - which is what reader one wants. Meanwhile, the
- ** second reader using K1 will see additional values that were inserted
- ** later, which is exactly what reader two wants.
- **
- ** When a rollback occurs, the value of K is decreased. Hash table entries
- ** that correspond to frames greater than the new K value are removed
- ** from the hash table at this point.
- *************************************************************************
- ** Included in SQLite3 port to C#-SQLite; 2008 Noah B Hart
- ** C#-SQLite is an independent reimplementation of the SQLite software library
- **
- ** SQLITE_SOURCE_ID: 2010-12-07 20:14:09 a586a4deeb25330037a49df295b36aaf624d0f45
- **
- *************************************************************************
- */
- #if !SQLITE_OMIT_WAL
- //#include "wal.h"
- /*
- ** Trace output macros
- */
- #if (SQLITE_TEST) && (SQLITE_DEBUG)
- int sqlite3WalTrace = 0;
- //# define WALTRACE(X) if(sqlite3WalTrace) sqlite3DebugPrintf X
- static void WALTRACE(params object[] X)
- {
- if(sqlite3WalTrace) sqlite3DebugPrintf(X);
- }
- #else
- //# define WALTRACE(X)
- static void WALTRACE(params object[] X) {}
- #endif
- /*
- ** The maximum (and only) versions of the wal and wal-index formats
- ** that may be interpreted by this version of SQLite.
- **
- ** If a client begins recovering a WAL file and finds that (a) the checksum
- ** values in the wal-header are correct and (b) the version field is not
- ** WAL_MAX_VERSION, recovery fails and SQLite returns SQLITE_CANTOPEN.
- **
- ** Similarly, if a client successfully reads a wal-index header (i.e. the
- ** checksum test is successful) and finds that the version field is not
- ** WALINDEX_MAX_VERSION, then no read-transaction is opened and SQLite
- ** returns SQLITE_CANTOPEN.
- */
- //#define WAL_MAX_VERSION 3007000
- //#define WALINDEX_MAX_VERSION 3007000
- const int WAL_MAX_VERSION = 3007000;
- const int WALINDEX_MAX_VERSION = 3007000;
- /*
- ** Indices of various locking bytes. WAL_NREADER is the number
- ** of available reader locks and should be at least 3.
- */
- //#define WAL_WRITE_LOCK 0
- //#define WAL_ALL_BUT_WRITE 1
- //#define WAL_CKPT_LOCK 1
- //#define WAL_RECOVER_LOCK 2
- //#define WAL_READ_LOCK(I) (3+(I))
- //#define WAL_NREADER (SQLITE_SHM_NLOCK-3)
- const int WAL_WRITE_LOCK = 0;
- const int WAL_ALL_BUT_WRITE = 1;
- const int WAL_CKPT_LOCK = 1;
- const int WAL_RECOVER_LOCK = 2;
- const int WAL_READ_LOCK(I) = (3+(I));
- const int WAL_NREADER = (SQLITE_SHM_NLOCK-3);
- /* Object declarations */
- typedef struct WalIndexHdr WalIndexHdr;
- typedef struct WalIterator WalIterator;
- typedef struct WalCkptInfo WalCkptInfo;
- /*
- ** The following object holds a copy of the wal-index header content.
- **
- ** The actual header in the wal-index consists of two copies of this
- ** object.
- */
- struct WalIndexHdr {
- u32 iVersion; /* Wal-index version */
- u32 unused; /* Unused (padding) field */
- u32 iChange; /* Counter incremented each transaction */
- u8 isInit; /* 1 when initialized */
- u8 bigEndCksum; /* True if checksums in WAL are big-endian */
- u16 szPage; /* Database page size in bytes */
- u32 mxFrame; /* Index of last valid frame in the WAL */
- u32 nPage; /* Size of database in pages */
- u32 aFrameCksum[2]; /* Checksum of last frame in log */
- u32 aSalt[2]; /* Two salt values copied from WAL header */
- u32 aCksum[2]; /* Checksum over all prior fields */
- };
- /*
- ** A copy of the following object occurs in the wal-index immediately
- ** following the second copy of the WalIndexHdr. This object stores
- ** information used by checkpoint.
- **
- ** nBackfill is the number of frames in the WAL that have been written
- ** back into the database. (We call the act of moving content from WAL to
- ** database "backfilling".) The nBackfill number is never greater than
- ** WalIndexHdr.mxFrame. nBackfill can only be increased by threads
- ** holding the WAL_CKPT_LOCK lock (which includes a recovery thread).
- ** However, a WAL_WRITE_LOCK thread can move the value of nBackfill from
- ** mxFrame back to zero when the WAL is reset.
- **
- ** There is one entry in aReadMark[] for each reader lock. If a reader
- ** holds read-lock K, then the value in aReadMark[K] is no greater than
- ** the mxFrame for that reader. The value READMARK_NOT_USED (0xffffffff)
- ** for any aReadMark[] means that entry is unused. aReadMark[0] is
- ** a special case; its value is never used and it exists as a place-holder
- ** to avoid having to offset aReadMark[] indexs by one. Readers holding
- ** WAL_READ_LOCK(0) always ignore the entire WAL and read all content
- ** directly from the database.
- **
- ** The value of aReadMark[K] may only be changed by a thread that
- ** is holding an exclusive lock on WAL_READ_LOCK(K). Thus, the value of
- ** aReadMark[K] cannot changed while there is a reader is using that mark
- ** since the reader will be holding a shared lock on WAL_READ_LOCK(K).
- **
- ** The checkpointer may only transfer frames from WAL to database where
- ** the frame numbers are less than or equal to every aReadMark[] that is
- ** in use (that is, every aReadMark[j] for which there is a corresponding
- ** WAL_READ_LOCK(j)). New readers (usually) pick the aReadMark[] with the
- ** largest value and will increase an unused aReadMark[] to mxFrame if there
- ** is not already an aReadMark[] equal to mxFrame. The exception to the
- ** previous sentence is when nBackfill equals mxFrame (meaning that everything
- ** in the WAL has been backfilled into the database) then new readers
- ** will choose aReadMark[0] which has value 0 and hence such reader will
- ** get all their all content directly from the database file and ignore
- ** the WAL.
- **
- ** Writers normally append new frames to the end of the WAL. However,
- ** if nBackfill equals mxFrame (meaning that all WAL content has been
- ** written back into the database) and if no readers are using the WAL
- ** (in other words, if there are no WAL_READ_LOCK(i) where i>0) then
- ** the writer will first "reset" the WAL back to the beginning and start
- ** writing new content beginning at frame 1.
- **
- ** We assume that 32-bit loads are atomic and so no locks are needed in
- ** order to read from any aReadMark[] entries.
- */
- struct WalCkptInfo {
- u32 nBackfill; /* Number of WAL frames backfilled into DB */
- u32 aReadMark[WAL_NREADER]; /* Reader marks */
- };
- //#define READMARK_NOT_USED 0xffffffff
- const int READMARK_NOT_USED = 0xffffffff;
- /* A block of WALINDEX_LOCK_RESERVED bytes beginning at
- ** WALINDEX_LOCK_OFFSET is reserved for locks. Since some systems
- ** only support mandatory file-locks, we do not read or write data
- ** from the region of the file on which locks are applied.
- */
- //#define WALINDEX_LOCK_OFFSET (sizeof(WalIndexHdr)*2 + sizeof(WalCkptInfo))
- //#define WALINDEX_LOCK_RESERVED 16
- //#define WALINDEX_HDR_SIZE (WALINDEX_LOCK_OFFSET+WALINDEX_LOCK_RESERVED)
- const int WALINDEX_LOCK_OFFSET = (sizeof(WalIndexHdr)*2 + sizeof(WalCkptInfo));
- const int WALINDEX_LOCK_RESERVED= 16;
- const int WALINDEX_HDR_SIZE = (WALINDEX_LOCK_OFFSET+WALINDEX_LOCK_RESERVED);
- /* Size of header before each frame in wal */
- //#define WAL_FRAME_HDRSIZE 24
- const int WAL_FRAME_HDRSIZE =24;
- /* Size of write ahead log header, including checksum. */
- /* #define WAL_HDRSIZE 24 */
- //#define WAL_HDRSIZE 32
- const int WAL_HDRSIZE =32;
- /* WAL magic value. Either this value, or the same value with the least
- ** significant bit also set (WAL_MAGIC | 0x00000001) is stored in 32-bit
- ** big-endian format in the first 4 bytes of a WAL file.
- **
- ** If the LSB is set, then the checksums for each frame within the WAL
- ** file are calculated by treating all data as an array of 32-bit
- ** big-endian words. Otherwise, they are calculated by interpreting
- ** all data as 32-bit little-endian words.
- */
- //#define WAL_MAGIC 0x377f0682
- const int WAL_MAGIC = 0x377f0682;
- /*
- ** Return the offset of frame iFrame in the write-ahead log file,
- ** assuming a database page size of szPage bytes. The offset returned
- ** is to the start of the write-ahead log frame-header.
- */
- //#define walFrameOffset(iFrame, szPage) ( \
- // WAL_HDRSIZE + ((iFrame)-1)*(i64)((szPage)+WAL_FRAME_HDRSIZE) \
- //)
- static int walFrameOffset(iFrame, szPage) {
- return WAL_HDRSIZE + ((iFrame)-1)*(i64)((szPage)+WAL_FRAME_HDRSIZE);
- }
- /*
- ** An open write-ahead log file is represented by an instance of the
- ** following object.
- */
- struct Wal {
- sqlite3_vfs *pVfs; /* The VFS used to create pDbFd */
- sqlite3_file *pDbFd; /* File handle for the database file */
- sqlite3_file *pWalFd; /* File handle for WAL file */
- u32 iCallback; /* Value to pass to log callback (or 0) */
- int nWiData; /* Size of array apWiData */
- volatile u32 **apWiData; /* Pointer to wal-index content in memory */
- u16 szPage; /* Database page size */
- i16 readLock; /* Which read lock is being held. -1 for none */
- u8 exclusiveMode; /* Non-zero if connection is in exclusive mode */
- u8 writeLock; /* True if in a write transaction */
- u8 ckptLock; /* True if holding a checkpoint lock */
- u8 readOnly; /* True if the WAL file is open read-only */
- WalIndexHdr hdr; /* Wal-index header for current transaction */
- const char *zWalName; /* Name of WAL file */
- u32 nCkpt; /* Checkpoint sequence counter in the wal-header */
- #if SQLITE_DEBUG
- u8 lockError; /* True if a locking error has occurred */
- #endif
- };
- /*
- ** Each page of the wal-index mapping contains a hash-table made up of
- ** an array of HASHTABLE_NSLOT elements of the following type.
- */
- typedef u16 ht_slot;
- /*
- ** This structure is used to implement an iterator that loops through
- ** all frames in the WAL in database page order. Where two or more frames
- ** correspond to the same database page, the iterator visits only the
- ** frame most recently written to the WAL (in other words, the frame with
- ** the largest index).
- **
- ** The internals of this structure are only accessed by:
- **
- ** walIteratorInit() - Create a new iterator,
- ** walIteratorNext() - Step an iterator,
- ** walIteratorFree() - Free an iterator.
- **
- ** This functionality is used by the checkpoint code (see walCheckpoint()).
- */
- struct WalIterator {
- int iPrior; /* Last result returned from the iterator */
- int nSegment; /* Size of the aSegment[] array */
- struct WalSegment {
- int iNext; /* Next slot in aIndex[] not yet returned */
- ht_slot *aIndex; /* i0, i1, i2... such that aPgno[iN] ascend */
- u32 *aPgno; /* Array of page numbers. */
- int nEntry; /* Max size of aPgno[] and aIndex[] arrays */
- int iZero; /* Frame number associated with aPgno[0] */
- } aSegment[1]; /* One for every 32KB page in the WAL */
- };
- /*
- ** Define the parameters of the hash tables in the wal-index file. There
- ** is a hash-table following every HASHTABLE_NPAGE page numbers in the
- ** wal-index.
- **
- ** Changing any of these constants will alter the wal-index format and
- ** create incompatibilities.
- */
- //#define HASHTABLE_NPAGE 4096 /* Must be power of 2 */
- //#define HASHTABLE_HASH_1 383 /* Should be prime */
- //#define HASHTABLE_NSLOT (HASHTABLE_NPAGE*2) /* Must be a power of 2 */
- const int HASHTABLE_NPAGE = 4096 ;
- const int HASHTABLE_HASH_1 = 383 ;
- const int HASHTABLE_NSLOT = (HASHTABLE_NPAGE*2);
- /*
- ** The block of page numbers associated with the first hash-table in a
- ** wal-index is smaller than usual. This is so that there is a complete
- ** hash-table on each aligned 32KB page of the wal-index.
- */
- //#define HASHTABLE_NPAGE_ONE (HASHTABLE_NPAGE - (WALINDEX_HDR_SIZE/sizeof(u32)))
- const int HASHTABLE_NPAGE_ONE =(HASHTABLE_NPAGE - (WALINDEX_HDR_SIZE/sizeof(u32)));
- /* The wal-index is divided into pages of WALINDEX_PGSZ bytes each. */
- //#define WALINDEX_PGSZ ( \
- // sizeof(ht_slot)*HASHTABLE_NSLOT + HASHTABLE_NPAGE*sizeof(u32) \
- //)
- static int WALINDEX_PGSZ(){
- return sizeof(ht_slot)*HASHTABLE_NSLOT + HASHTABLE_NPAGE*sizeof(u32);
- }
- /*
- ** Obtain a pointer to the iPage'th page of the wal-index. The wal-index
- ** is broken into pages of WALINDEX_PGSZ bytes. Wal-index pages are
- ** numbered from zero.
- **
- ** If this call is successful, *ppPage is set to point to the wal-index
- ** page and SQLITE_OK is returned. If an error (an OOM or VFS error) occurs,
- ** then an SQLite error code is returned and *ppPage is set to 0.
- */
- static int walIndexPage(Wal *pWal, int iPage, volatile u32 **ppPage){
- int rc = SQLITE_OK;
- /* Enlarge the pWal.apWiData[] array if required */
- if( pWal.nWiData<=iPage ){
- int nByte = sizeof(u32*)*(iPage+1);
- volatile u32 **apNew;
- apNew = (volatile u32 **)sqlite3_realloc((void *)pWal.apWiData, nByte);
- if( !apNew ){
- *ppPage = 0;
- return SQLITE_NOMEM;
- }
- memset((void*)&apNew[pWal.nWiData], 0,
- sizeof(u32*)*(iPage+1-pWal.nWiData));
- pWal.apWiData = apNew;
- pWal.nWiData = iPage+1;
- }
- /* Request a pointer to the required page from the VFS */
- if( pWal.apWiData[iPage]==0 ){
- if( pWal.exclusiveMode==WAL_HEAPMEMORY_MODE ){
- pWal.apWiData[iPage] = (u32 volatile *)sqlite3MallocZero(WALINDEX_PGSZ);
- if( !pWal.apWiData[iPage] ) rc = SQLITE_NOMEM;
- }else{
- rc = sqlite3OsShmMap(pWal.pDbFd, iPage, WALINDEX_PGSZ,
- pWal.writeLock, (void volatile **)&pWal.apWiData[iPage]
- );
- }
- }
- *ppPage = pWal.apWiData[iPage];
- Debug.Assert( iPage==0 || *ppPage || rc!=SQLITE_OK );
- return rc;
- }
- /*
- ** Return a pointer to the WalCkptInfo structure in the wal-index.
- */
- static volatile WalCkptInfo *walCkptInfo(Wal *pWal){
- Debug.Assert( pWal.nWiData>0 && pWal.apWiData[0] );
- return (volatile WalCkptInfo*)&(pWal.apWiData[0][sizeof(WalIndexHdr)/2]);
- }
- /*
- ** Return a pointer to the WalIndexHdr structure in the wal-index.
- */
- static volatile WalIndexHdr *walIndexHdr(Wal *pWal){
- Debug.Assert( pWal.nWiData>0 && pWal.apWiData[0] );
- return (volatile WalIndexHdr*)pWal.apWiData[0];
- }
- /*
- ** The argument to this macro must be of type u32. On a little-endian
- ** architecture, it returns the u32 value that results from interpreting
- ** the 4 bytes as a big-endian value. On a big-endian architecture, it
- ** returns the value that would be produced by intepreting the 4 bytes
- ** of the input value as a little-endian integer.
- */
- //#define BYTESWAP32(x) ( \
- // (((x)&0x000000FF)<<24) + (((x)&0x0000FF00)<<8) \
- // + (((x)&0x00FF0000)>>8) + (((x)&0xFF000000)>>24) \
- //)
- static int BYTESWAP32(int x) { return
- (((x)&0x000000FF)<<24) + (((x)&0x0000FF00)<<8)
- + (((x)&0x00FF0000)>>8) + (((x)&0xFF000000)>>24) ;
- }
- /*
- ** Generate or extend an 8 byte checksum based on the data in
- ** array aByte[] and the initial values of aIn[0] and aIn[1] (or
- ** initial values of 0 and 0 if aIn==NULL).
- **
- ** The checksum is written back into aOut[] before returning.
- **
- ** nByte must be a positive multiple of 8.
- */
- static void walChecksumBytes(
- int nativeCksum, /* True for native byte-order, false for non-native */
- u8 *a, /* Content to be checksummed */
- int nByte, /* Bytes of content in a[]. Must be a multiple of 8. */
- const u32 *aIn, /* Initial checksum value input */
- u32 *aOut /* OUT: Final checksum value output */
- ){
- u32 s1, s2;
- u32 *aData = (u32 *)a;
- u32 *aEnd = (u32 *)&a[nByte];
- if( aIn ){
- s1 = aIn[0];
- s2 = aIn[1];
- }else{
- s1 = s2 = 0;
- }
- Debug.Assert( nByte>=8 );
- Debug.Assert( (nByte&0x00000007)==0 );
- if( nativeCksum ){
- do {
- s1 += *aData++ + s2;
- s2 += *aData++ + s1;
- }while( aData<aEnd );
- }else{
- do {
- s1 += BYTESWAP32(aData[0]) + s2;
- s2 += BYTESWAP32(aData[1]) + s1;
- aData += 2;
- }while( aData<aEnd );
- }
- aOut[0] = s1;
- aOut[1] = s2;
- }
- static void walShmBarrier(Wal *pWal){
- if( pWal.exclusiveMode!=WAL_HEAPMEMORY_MODE ){
- sqlite3OsShmBarrier(pWal.pDbFd);
- }
- }
- /*
- ** Write the header information in pWal.hdr into the wal-index.
- **
- ** The checksum on pWal.hdr is updated before it is written.
- */
- static void walIndexWriteHdr(Wal *pWal){
- volatile WalIndexHdr *aHdr = walIndexHdr(pWal);
- const int nCksum = offsetof(WalIndexHdr, aCksum);
- Debug.Assert( pWal.writeLock );
- pWal.hdr.isInit = 1;
- pWal.hdr.iVersion = WALINDEX_MAX_VERSION;
- walChecksumBytes(1, (u8*)&pWal.hdr, nCksum, 0, pWal.hdr.aCksum);
- memcpy((void *)&aHdr[1], (void *)&pWal.hdr, sizeof(WalIndexHdr));
- walShmBarrier(pWal);
- memcpy((void *)&aHdr[0], (void *)&pWal.hdr, sizeof(WalIndexHdr));
- }
- /*
- ** This function encodes a single frame header and writes it to a buffer
- ** supplied by the caller. A frame-header is made up of a series of
- ** 4-byte big-endian integers, as follows:
- **
- ** 0: Page number.
- ** 4: For commit records, the size of the database image in pages
- ** after the commit. For all other records, zero.
- ** 8: Salt-1 (copied from the wal-header)
- ** 12: Salt-2 (copied from the wal-header)
- ** 16: Checksum-1.
- ** 20: Checksum-2.
- */
- static void walEncodeFrame(
- Wal *pWal, /* The write-ahead log */
- u32 iPage, /* Database page number for frame */
- u32 nTruncate, /* New db size (or 0 for non-commit frames) */
- u8 *aData, /* Pointer to page data */
- u8 *aFrame /* OUT: Write encoded frame here */
- ){
- int nativeCksum; /* True for native byte-order checksums */
- u32 *aCksum = pWal.hdr.aFrameCksum;
- Debug.Assert( WAL_FRAME_HDRSIZE==24 );
- sqlite3Put4byte(&aFrame[0], iPage);
- sqlite3Put4byte(&aFrame[4], nTruncate);
- memcpy(&aFrame[8], pWal.hdr.aSalt, 8);
- nativeCksum = (pWal.hdr.bigEndCksum==SQLITE_BIGENDIAN);
- walChecksumBytes(nativeCksum, aFrame, 8, aCksum, aCksum);
- walChecksumBytes(nativeCksum, aData, pWal.szPage, aCksum, aCksum);
- sqlite3Put4byte(&aFrame[16], aCksum[0]);
- sqlite3Put4byte(&aFrame[20], aCksum[1]);
- }
- /*
- ** Check to see if the frame with header in aFrame[] and content
- ** in aData[] is valid. If it is a valid frame, fill *piPage and
- ** *pnTruncate and return true. Return if the frame is not valid.
- */
- static int walDecodeFrame(
- Wal *pWal, /* The write-ahead log */
- u32 *piPage, /* OUT: Database page number for frame */
- u32 *pnTruncate, /* OUT: New db size (or 0 if not commit) */
- u8 *aData, /* Pointer to page data (for checksum) */
- u8 *aFrame /* Frame data */
- ){
- int nativeCksum; /* True for native byte-order checksums */
- u32 *aCksum = pWal.hdr.aFrameCksum;
- u32 pgno; /* Page number of the frame */
- Debug.Assert( WAL_FRAME_HDRSIZE==24 );
- /* A frame is only valid if the salt values in the frame-header
- ** match the salt values in the wal-header.
- */
- if( memcmp(&pWal.hdr.aSalt, &aFrame[8], 8)!=0 ){
- return 0;
- }
- /* A frame is only valid if the page number is creater than zero.
- */
- pgno = sqlite3Get4byte(&aFrame[0]);
- if( pgno==0 ){
- return 0;
- }
- /* A frame is only valid if a checksum of the WAL header,
- ** all prior frams, the first 16 bytes of this frame-header,
- ** and the frame-data matches the checksum in the last 8
- ** bytes of this frame-header.
- */
- nativeCksum = (pWal.hdr.bigEndCksum==SQLITE_BIGENDIAN);
- walChecksumBytes(nativeCksum, aFrame, 8, aCksum, aCksum);
- walChecksumBytes(nativeCksum, aData, pWal.szPage, aCksum, aCksum);
- if( aCksum[0]!=sqlite3Get4byte(&aFrame[16])
- || aCksum[1]!=sqlite3Get4byte(&aFrame[20])
- ){
- /* Checksum failed. */
- return 0;
- }
- /* If we reach this point, the frame is valid. Return the page number
- ** and the new database size.
- */
- *piPage = pgno;
- *pnTruncate = sqlite3Get4byte(&aFrame[4]);
- return 1;
- }
- #if (SQLITE_TEST) && (SQLITE_DEBUG)
- /*
- ** Names of locks. This routine is used to provide debugging output and is not
- ** a part of an ordinary build.
- */
- static const char *walLockName(int lockIdx){
- if( lockIdx==WAL_WRITE_LOCK ){
- return "WRITE-LOCK";
- }else if( lockIdx==WAL_CKPT_LOCK ){
- return "CKPT-LOCK";
- }else if( lockIdx==WAL_RECOVER_LOCK ){
- return "RECOVER-LOCK";
- }else{
- static char zName[15];
- sqlite3_snprintf(sizeof(zName), zName, "READ-LOCK[%d]",
- lockIdx-WAL_READ_LOCK(0));
- return zName;
- }
- }
- #endif //*defined(SQLITE_TEST) || defined(SQLITE_DEBUG) */
-
- /*
- ** Set or release locks on the WAL. Locks are either shared or exclusive.
- ** A lock cannot be moved directly between shared and exclusive - it must go
- ** through the unlocked state first.
- **
- ** In locking_mode=EXCLUSIVE, all of these routines become no-ops.
- */
- static int walLockShared(Wal *pWal, int lockIdx){
- int rc;
- if( pWal.exclusiveMode ) return SQLITE_OK;
- rc = sqlite3OsShmLock(pWal.pDbFd, lockIdx, 1,
- SQLITE_SHM_LOCK | SQLITE_SHM_SHARED);
- WALTRACE(("WAL%p: acquire SHARED-%s %s\n", pWal,
- walLockName(lockIdx), rc ? "failed" : "ok"));
- VVA_ONLY( pWal.lockError = (u8)(rc!=SQLITE_OK && rc!=SQLITE_BUSY); )
- return rc;
- }
- static void walUnlockShared(Wal *pWal, int lockIdx){
- if( pWal.exclusiveMode ) return;
- (void)sqlite3OsShmLock(pWal.pDbFd, lockIdx, 1,
- SQLITE_SHM_UNLOCK | SQLITE_SHM_SHARED);
- WALTRACE(("WAL%p: release SHARED-%s\n", pWal, walLockName(lockIdx)));
- }
- static int walLockExclusive(Wal *pWal, int lockIdx, int n){
- int rc;
- if( pWal.exclusiveMode ) return SQLITE_OK;
- rc = sqlite3OsShmLock(pWal.pDbFd, lockIdx, n,
- SQLITE_SHM_LOCK | SQLITE_SHM_EXCLUSIVE);
- WALTRACE(("WAL%p: acquire EXCLUSIVE-%s cnt=%d %s\n", pWal,
- walLockName(lockIdx), n, rc ? "failed" : "ok"));
- VVA_ONLY( pWal.lockError = (u8)(rc!=SQLITE_OK && rc!=SQLITE_BUSY); )
- return rc;
- }
- static void walUnlockExclusive(Wal *pWal, int lockIdx, int n){
- if( pWal.exclusiveMode ) return;
- (void)sqlite3OsShmLock(pWal.pDbFd, lockIdx, n,
- SQLITE_SHM_UNLOCK | SQLITE_SHM_EXCLUSIVE);
- WALTRACE(("WAL%p: release EXCLUSIVE-%s cnt=%d\n", pWal,
- walLockName(lockIdx), n));
- }
- /*
- ** Compute a hash on a page number. The resulting hash value must land
- ** between 0 and (HASHTABLE_NSLOT-1). The walHashNext() function advances
- ** the hash to the next value in the event of a collision.
- */
- static int walHash(u32 iPage){
- Debug.Assert( iPage>0 );
- Debug.Assert( (HASHTABLE_NSLOT & (HASHTABLE_NSLOT-1))==0 );
- return (iPage*HASHTABLE_HASH_1) & (HASHTABLE_NSLOT-1);
- }
- static int walNextHash(int iPriorHash){
- return (iPriorHash+1)&(HASHTABLE_NSLOT-1);
- }
- /*
- ** Return pointers to the hash table and page number array stored on
- ** page iHash of the wal-index. The wal-index is broken into 32KB pages
- ** numbered starting from 0.
- **
- ** Set output variable *paHash to point to the start of the hash table
- ** in the wal-index file. Set *piZero to one less than the frame
- ** number of the first frame indexed by this hash table. If a
- ** slot in the hash table is set to N, it refers to frame number
- ** (*piZero+N) in the log.
- **
- ** Finally, set *paPgno so that *paPgno[1] is the page number of the
- ** first frame indexed by the hash table, frame (*piZero+1).
- */
- static int walHashGet(
- Wal *pWal, /* WAL handle */
- int iHash, /* Find the iHash'th table */
- volatile ht_slot **paHash, /* OUT: Pointer to hash index */
- volatile u32 **paPgno, /* OUT: Pointer to page number array */
- u32 *piZero /* OUT: Frame associated with *paPgno[0] */
- ){
- int rc; /* Return code */
- volatile u32 *aPgno;
- rc = walIndexPage(pWal, iHash, &aPgno);
- Debug.Assert( rc==SQLITE_OK || iHash>0 );
- if( rc==SQLITE_OK ){
- u32 iZero;
- volatile ht_slot *aHash;
- aHash = (volatile ht_slot *)&aPgno[HASHTABLE_NPAGE];
- if( iHash==0 ){
- aPgno = &aPgno[WALINDEX_HDR_SIZE/sizeof(u32)];
- iZero = 0;
- }else{
- iZero = HASHTABLE_NPAGE_ONE + (iHash-1)*HASHTABLE_NPAGE;
- }
-
- *paPgno = &aPgno[-1];
- *paHash = aHash;
- *piZero = iZero;
- }
- return rc;
- }
- /*
- ** Return the number of the wal-index page that contains the hash-table
- ** and page-number array that contain entries corresponding to WAL frame
- ** iFrame. The wal-index is broken up into 32KB pages. Wal-index pages
- ** are numbered starting from 0.
- */
- static int walFramePage(u32 iFrame){
- int iHash = (iFrame+HASHTABLE_NPAGE-HASHTABLE_NPAGE_ONE-1) / HASHTABLE_NPAGE;
- Debug.Assert( (iHash==0 || iFrame>HASHTABLE_NPAGE_ONE)
- && (iHash>=1 || iFrame<=HASHTABLE_NPAGE_ONE)
- && (iHash<=1 || iFrame>(HASHTABLE_NPAGE_ONE+HASHTABLE_NPAGE))
- && (iHash>=2 || iFrame<=HASHTABLE_NPAGE_ONE+HASHTABLE_NPAGE)
- && (iHash<=2 || iFrame>(HASHTABLE_NPAGE_ONE+2*HASHTABLE_NPAGE))
- );
- return iHash;
- }
- /*
- ** Return the page number associated with frame iFrame in this WAL.
- */
- static u32 walFramePgno(Wal *pWal, u32 iFrame){
- int iHash = walFramePage(iFrame);
- if( iHash==0 ){
- return pWal.apWiData[0][WALINDEX_HDR_SIZE/sizeof(u32) + iFrame - 1];
- }
- return pWal.apWiData[iHash][(iFrame-1-HASHTABLE_NPAGE_ONE)%HASHTABLE_NPAGE];
- }
- /*
- ** Remove entries from the hash table that point to WAL slots greater
- ** than pWal.hdr.mxFrame.
- **
- ** This function is called whenever pWal.hdr.mxFrame is decreased due
- ** to a rollback or savepoint.
- **
- ** At most only the hash table containing pWal.hdr.mxFrame needs to be
- ** updated. Any later hash tables will be automatically cleared when
- ** pWal.hdr.mxFrame advances to the point where those hash tables are
- ** actually needed.
- */
- static void walCleanupHash(Wal *pWal){
- volatile ht_slot *aHash = 0; /* Pointer to hash table to clear */
- volatile u32 *aPgno = 0; /* Page number array for hash table */
- u32 iZero = 0; /* frame == (aHash[x]+iZero) */
- int iLimit = 0; /* Zero values greater than this */
- int nByte; /* Number of bytes to zero in aPgno[] */
- int i; /* Used to iterate through aHash[] */
- Debug.Assert( pWal.writeLock );
- testcase( pWal.hdr.mxFrame==HASHTABLE_NPAGE_ONE-1 );
- testcase( pWal.hdr.mxFrame==HASHTABLE_NPAGE_ONE );
- testcase( pWal.hdr.mxFrame==HASHTABLE_NPAGE_ONE+1 );
- if( pWal.hdr.mxFrame==0 ) return;
- /* Obtain pointers to the hash-table and page-number array containing
- ** the entry that corresponds to frame pWal.hdr.mxFrame. It is guaranteed
- ** that the page said hash-table and array reside on is already mapped.
- */
- Debug.Assert( pWal.nWiData>walFramePage(pWal.hdr.mxFrame) );
- Debug.Assert( pWal.apWiData[walFramePage(pWal.hdr.mxFrame)] );
- walHashGet(pWal, walFramePage(pWal.hdr.mxFrame), &aHash, &aPgno, &iZero);
- /* Zero all hash-table entries that correspond to frame numbers greater
- ** than pWal.hdr.mxFrame.
- */
- iLimit = pWal.hdr.mxFrame - iZero;
- Debug.Assert( iLimit>0 );
- for(i=0; i<HASHTABLE_NSLOT; i++){
- if( aHash[i]>iLimit ){
- aHash[i] = 0;
- }
- }
-
- /* Zero the entries in the aPgno array that correspond to frames with
- ** frame numbers greater than pWal.hdr.mxFrame.
- */
- nByte = (int)((char *)aHash - (char *)&aPgno[iLimit+1]);
- memset((void *)&aPgno[iLimit+1], 0, nByte);
- #if SQLITE_ENABLE_EXPENSIVE_ASSERT
- /* Verify that the every entry in the mapping region is still reachable
- ** via the hash table even after the cleanup.
- */
- if( iLimit ){
- int i; /* Loop counter */
- int iKey; /* Hash key */
- for(i=1; i<=iLimit; i++){
- for(iKey=walHash(aPgno[i]); aHash[iKey]; iKey=walNextHash(iKey)){
- if( aHash[iKey]==i ) break;
- }
- Debug.Assert( aHash[iKey]==i );
- }
- }
- #endif //* SQLITE_ENABLE_EXPENSIVE_ASSERT */
- }
- /*
- ** Set an entry in the wal-index that will map database page number
- ** pPage into WAL frame iFrame.
- */
- static int walIndexAppend(Wal *pWal, u32 iFrame, u32 iPage){
- int rc; /* Return code */
- u32 iZero = 0; /* One less than frame number of aPgno[1] */
- volatile u32 *aPgno = 0; /* Page number array */
- volatile ht_slot *aHash = 0; /* Hash table */
- rc = walHashGet(pWal, walFramePage(iFrame), &aHash, &aPgno, &iZero);
- /* Assuming the wal-index file was successfully mapped, populate the
- ** page number array and hash table entry.
- */
- if( rc==SQLITE_OK ){
- int iKey; /* Hash table key */
- int idx; /* Value to write to hash-table slot */
- int nCollide; /* Number of hash collisions */
- idx = iFrame - iZero;
- Debug.Assert( idx <= HASHTABLE_NSLOT/2 + 1 );
-
- /* If this is the first entry to be added to this hash-table, zero the
- ** entire hash table and aPgno[] array before proceding.
- */
- if( idx==1 ){
- int nByte = (int)((u8 *)&aHash[HASHTABLE_NSLOT] - (u8 *)&aPgno[1]);
- memset((void*)&aPgno[1], 0, nByte);
- }
- /* If the entry in aPgno[] is already set, then the previous writer
- ** must have exited unexpectedly in the middle of a transaction (after
- ** writing one or more dirty pages to the WAL to free up memory).
- ** Remove the remnants of that writers uncommitted transaction from
- ** the hash-table before writing any new entries.
- */
- if( aPgno[idx] ){
- walCleanupHash(pWal);
- Debug.Assert( !aPgno[idx] );
- }
- /* Write the aPgno[] array entry and the hash-table slot. */
- nCollide = idx;
- for(iKey=walHash(iPage); aHash[iKey]; iKey=walNextHash(iKey)){
- if( (nCollide--)==0 ) return SQLITE_CORRUPT_BKPT;
- }
- aPgno[idx] = iPage;
- aHash[iKey] = (ht_slot)idx;
- #if SQLITE_ENABLE_EXPENSIVE_ASSERT
- /* Verify that the number of entries in the hash table exactly equals
- ** the number of entries in the mapping region.
- */
- {
- int i; /* Loop counter */
- int nEntry = 0; /* Number of entries in the hash table */
- for(i=0; i<HASHTABLE_NSLOT; i++){ if( aHash[i] ) nEntry++; }
- Debug.Assert( nEntry==idx );
- }
- /* Verify that the every entry in the mapping region is reachable
- ** via the hash table. This turns out to be a really, really expensive
- ** thing to check, so only do this occasionally - not on every
- ** iteration.
- */
- if( (idx&0x3ff)==0 ){
- int i; /* Loop counter */
- for(i=1; i<=idx; i++){
- for(iKey=walHash(aPgno[i]); aHash[iKey]; iKey=walNextHash(iKey)){
- if( aHash[iKey]==i ) break;
- }
- Debug.Assert( aHash[iKey]==i );
- }
- }
- #endif //* SQLITE_ENABLE_EXPENSIVE_ASSERT */
- }
- return rc;
- }
- /*
- ** Recover the wal-index by reading the write-ahead log file.
- **
- ** This routine first tries to establish an exclusive lock on the
- ** wal-index to prevent other threads/processes from doing anything
- ** with the WAL or wal-index while recovery is running. The
- ** WAL_RECOVER_LOCK is also held so that other threads will know
- ** that this thread is running recovery. If unable to establish
- ** the necessary locks, this routine returns SQLITE_BUSY.
- */
- static int walIndexRecover(Wal *pWal){
- int rc; /* Return Code */
- i64 nSize; /* Size of log file */
- u32 aFrameCksum[2] = {0, 0};
- int iLock; /* Lock offset to lock for checkpoint */
- int nLock; /* Number of locks to hold */
- /* Obtain an exclusive lock on all byte in the locking range not already
- ** locked by the caller. The caller is guaranteed to have locked the
- ** WAL_WRITE_LOCK byte, and may have also locked the WAL_CKPT_LOCK byte.
- ** If successful, the same bytes that are locked here are unlocked before
- ** this function returns.
- */
- Debug.Assert( pWal.ckptLock==1 || pWal.ckptLock==0 );
- Debug.Assert( WAL_ALL_BUT_WRITE==WAL_WRITE_LOCK+1 );
- Debug.Assert( WAL_CKPT_LOCK==WAL_ALL_BUT_WRITE );
- Debug.Assert( pWal.writeLock );
- iLock = WAL_ALL_BUT_WRITE + pWal.ckptLock;
- nLock = SQLITE_SHM_NLOCK - iLock;
- rc = walLockExclusive(pWal, iLock, nLock);
- if( rc ){
- return rc;
- }
- WALTRACE(("WAL%p: recovery begin...\n", pWal));
- memset(&pWal.hdr, 0, sizeof(WalIndexHdr));
- rc = sqlite3OsFileSize(pWal.pWalFd, &nSize);
- if( rc!=SQLITE_OK ){
- goto recovery_error;
- }
- if( nSize>WAL_HDRSIZE ){
- u8 aBuf[WAL_HDRSIZE]; /* Buffer to load WAL header into */
- u8 *aFrame = 0; /* Malloc'd buffer to load entire frame */
- int szFrame; /* Number of bytes in buffer aFrame[] */
- u8 *aData; /* Pointer to data part of aFrame buffer */
- int iFrame; /* Index of last frame read */
- i64 iOffset; /* Next offset to read from log file */
- int szPage; /* Page size according to the log */
- u32 magic; /* Magic value read from WAL header */
- u32 version; /* Magic value read from WAL header */
- /* Read in the WAL header. */
- rc = sqlite3OsRead(pWal.pWalFd, aBuf, WAL_HDRSIZE, 0);
- if( rc!=SQLITE_OK ){
- goto recovery_error;
- }
- /* If the database page size is not a power of two, or is greater than
- ** SQLITE_MAX_PAGE_SIZE, conclude that the WAL file contains no valid
- ** data. Similarly, if the 'magic' value is invalid, ignore the whole
- ** WAL file.
- */
- magic = sqlite3Get4byte(&aBuf[0]);
- szPage = sqlite3Get4byte(&aBuf[8]);
- if( (magic&0xFFFFFFFE)!=WAL_MAGIC
- || szPage&(szPage-1)
- || szPage>SQLITE_MAX_PAGE_SIZE
- || szPage<512
- ){
- goto finished;
- }
- pWal.hdr.bigEndCksum = (u8)(magic&0x00000001);
- pWal.szPage = (u16)szPage;
- pWal.nCkpt = sqlite3Get4byte(&aBuf[12]);
- memcpy(&pWal.hdr.aSalt, &aBuf[16], 8);
- /* Verify that the WAL header checksum is correct */
- walChecksumBytes(pWal.hdr.bigEndCksum==SQLITE_BIGENDIAN,
- aBuf, WAL_HDRSIZE-2*4, 0, pWal.hdr.aFrameCksum
- );
- if( pWal.hdr.aFrameCksum[0]!=sqlite3Get4byte(&aBuf[24])
- || pWal.hdr.aFrameCksum[1]!=sqlite3Get4byte(&aBuf[28])
- ){
- goto finished;
- }
- /* Verify that the version number on the WAL format is one that
- ** are able to understand */
- version = sqlite3Get4byte(&aBuf[4]);
- if( version!=WAL_MAX_VERSION ){
- rc = SQLITE_CANTOPEN_BKPT;
- goto finished;
- }
- /* Malloc a buffer to read frames into. */
- szFrame = szPage + WAL_FRAME_HDRSIZE;
- aFrame = (u8 *)sqlite3_malloc(szFrame);
- if( !aFrame ){
- rc = SQLITE_NOMEM;
- goto recovery_error;
- }
- aData = &aFrame[WAL_FRAME_HDRSIZE];
- /* Read all frames from the log file. */
- iFrame = 0;
- for(iOffset=WAL_HDRSIZE; (iOffset+szFrame)<=nSize; iOffset+=szFrame){
- u32 pgno; /* Database page number for frame */
- u32 nTruncate; /* dbsize field from frame header */
- int isValid; /* True if this frame is valid */
- /* Read and decode the next log frame. */
- rc = sqlite3OsRead(pWal.pWalFd, aFrame, szFrame, iOffset);
- if( rc!=SQLITE_OK ) break;
- isValid = walDecodeFrame(pWal, &pgno, &nTruncate, aData, aFrame);
- if( !isValid ) break;
- rc = walIndexAppend(pWal, ++iFrame, pgno);
- if( rc!=SQLITE_OK ) break;
- /* If nTruncate is non-zero, this is a commit record. */
- if( nTruncate ){
- pWal.hdr.mxFrame = iFrame;
- pWal.hdr.nPage = nTruncate;
- pWal.hdr.szPage = (u16)szPage;
- aFrameCksum[0] = pWal.hdr.aFrameCksum[0];
- aFrameCksum[1] = pWal.hdr.aFrameCksum[1];
- }
- }
- sqlite3_free(aFrame);
- }
- finished:
- if( rc==SQLITE_OK ){
- volatile WalCkptInfo *pInfo;
- int i;
- pWal.hdr.aFrameCksum[0] = aFrameCksum[0];
- pWal.hdr.aFrameCksum[1] = aFrameCksum[1];
- walIndexWriteHdr(pWal);
- /* Reset the checkpoint-header. This is safe because this thread is
- ** currently holding locks that exclude all other readers, writers and
- ** checkpointers.
- */
- pInfo = walCkptInfo(pWal);
- pInfo.nBackfill = 0;
- pInfo.aReadMark[0] = 0;
- for(i=1; i<WAL_NREADER; i++) pInfo.aReadMark[i] = READMARK_NOT_USED;
- }
- recovery_error:
- WALTRACE(("WAL%p: recovery %s\n", pWal, rc ? "failed" : "ok"));
- walUnlockExclusive(pWal, iLock, nLock);
- return rc;
- }
- /*
- ** Close an open wal-index.
- */
- static void walIndexClose(Wal *pWal, int isDelete){
- if( pWal.exclusiveMode==WAL_HEAPMEMORY_MODE ){
- int i;
- for(i=0; i<pWal.nWiData; i++){
- sqlite3_free((void *)pWal.apWiData[i]);
- pWal.apWiData[i] = 0;
- }
- }else{
- sqlite3OsShmUnmap(pWal.pDbFd, isDelete);
- }
- }
- /*
- ** Open a connection to the WAL file zWalName. The database file must
- ** already be opened on connection pDbFd. The buffer that zWalName points
- ** to must remain valid for the lifetime of the returned Wal* handle.
- **
- ** A SHARED lock should be held on the database file when this function
- ** is called. The purpose of this SHARED lock is to prevent any other
- ** client from unlinking the WAL or wal-index file. If another process
- ** were to do this just after this client opened one of these files, the
- ** system would be badly broken.
- **
- ** If the log file is successfully opened, SQLITE_OK is returned and
- ** *ppWal is set to point to a new WAL handle. If an error occurs,
- ** an SQLite error code is returned and *ppWal is left unmodified.
- */
- int sqlite3WalOpen(
- sqlite3_vfs *pVfs, /* vfs module to open wal and wal-index */
- sqlite3_file *pDbFd, /* The open database file */
- const char *zWalName, /* Name of the WAL file */
- int bNoShm, /* True to run in heap-memory mode */
- Wal **ppWal /* OUT: Allocated Wal handle */
- ){
- int rc; /* Return Code */
- Wal *pRet; /* Object to allocate and return */
- int flags; /* Flags passed to OsOpen() */
- Debug.Assert( zWalName && zWalName[0] );
- Debug.Assert( pDbFd );
- /* In the amalgamation, the os_unix.c and os_win.c source files come before
- ** this source file. Verify that the #defines of the locking byte offsets
- ** in os_unix.c and os_win.c agree with the WALINDEX_LOCK_OFFSET value.
- */
- #if WIN_SHM_BASE
- Debug.Assert( WIN_SHM_BASE==WALINDEX_LOCK_OFFSET );
- #endif
- #if UNIX_SHM_BASE
- Debug.Assert( UNIX_SHM_BASE==WALINDEX_LOCK_OFFSET );
- #endif
- /* Allocate an instance of struct Wal to return. */
- *ppWal = 0;
- pRet = (Wal*)sqlite3MallocZero(sizeof(Wal) + pVfs.szOsFile);
- if( !pRet ){
- return SQLITE_NOMEM;
- }
- pRet.pVfs = pVfs;
- pRet.pWalFd = (sqlite3_file *)&pRet[1];
- pRet.pDbFd = pDbFd;
- pRet.readLock = -1;
- pRet.zWalName = zWalName;
- pRet.exclusiveMode = (bNoShm ? WAL_HEAPMEMORY_MODE: WAL_NORMAL_MODE);
- /* Open file handle on the write-ahead log file. */
- flags = (SQLITE_OPEN_READWRITE|SQLITE_OPEN_CREATE|SQLITE_OPEN_WAL);
- rc = sqlite3OsOpen(pVfs, zWalName, pRet.pWalFd, flags, &flags);
- if( rc==SQLITE_OK && flags&SQLITE_OPEN_READONLY ){
- pRet.readOnly = 1;
- }
- if( rc!=SQLITE_OK ){
- walIndexClose(pRet, 0);
- sqlite3OsClose(pRet.pWalFd);
- sqlite3_free(pRet);
- }else{
- *ppWal = pRet;
- WALTRACE(("WAL%d: opened\n", pRet));
- }
- return rc;
- }
- /*
- ** Find the smallest page number out of all pages held in the WAL that
- ** has not been returned by any prior invocation of this method on the
- ** same WalIterator object. Write into *piFrame the frame index where
- ** that page was last written into the WAL. Write into *piPage the page
- ** number.
- **
- ** Return 0 on success. If there are no pages in the WAL with a page
- ** number larger than *piPage, then return 1.
- */
- static int walIteratorNext(
- WalIterator *p, /* Iterator */
- u32 *piPage, /* OUT: The page number of the next page */
- u32 *piFrame /* OUT: Wal frame index of next page */
- ){
- u32 iMin; /* Result pgno must be greater than iMin */
- u32 iRet = 0xFFFFFFFF; /* 0xffffffff is never a valid page number */
- int i; /* For looping through segments */
- iMin = p.iPrior;
- Debug.Assert( iMin<0xffffffff );
- for(i=p.nSegment-1; i>=0; i--){
- struct WalSegment *pSegment = &p.aSegment[i];
- while( pSegment.iNext<pSegment.nEntry ){
- u32 iPg = pSegment.aPgno[pSegment.aIndex[pSegment.iNext]];
- if( iPg>iMin ){
- if( iPg<iRet ){
- iRet = iPg;
- *piFrame = pSegment.iZero + pSegment.aIndex[pSegment.iNext];
- }
- break;
- }
- pSegment.iNext++;
- }
- }
- *piPage = p.iPrior = iRet;
- return (iRet==0xFFFFFFFF);
- }
- /*
- ** This function merges two sorted lists into a single sorted list.
- */
- static void walMerge(
- u32 *aContent, /* Pages in wal */
- ht_slot *aLeft, /* IN: Left hand input list */
- int nLeft, /* IN: Elements in array *paLeft */
- ht_slot **paRight, /* IN/OUT: Right hand input list */
- int *pnRight, /* IN/OUT: Elements in *paRight */
- ht_slot *aTmp /* Temporary buffer */
- ){
- int iLeft = 0; /* Current index in aLeft */
- int iRight = 0; /* Current index in aRight */
- int iOut = 0; /* Current index in output buffer */
- int nRight = *pnRight;
- ht_slot *aRight = *paRight;
- Debug.Assert( nLeft>0 && nRight>0 );
- while( iRight<nRight || iLeft<nLeft ){
- ht_slot logpage;
- Pgno dbpage;
- if( (iLeft<nLeft)
- && (iRight>=nRight || aContent[aLeft[iLeft]]<aContent[aRight[iRight]])
- ){
- logpage = aLeft[iLeft++];
- }else{
- logpage = aRight[iRight++];
- }
- dbpage = aContent[logpage];
- aTmp[iOut++] = logpage;
- if( iLeft<nLeft && aContent[aLeft[iLeft]]==dbpage ) iLeft++;
- Debug.Assert( iLeft>=nLeft || aContent[aLeft[iLeft]]>dbpage );
- Debug.Assert( iRight>=nRight || aContent[aRight[iRight]]>dbpage );
- }
- *paRight = aLeft;
- *pnRight = iOut;
- memcpy(aLeft, aTmp, sizeof(aTmp[0])*iOut);
- }
- /*
- ** Sort the elements in list aList, removing any duplicates.
- */
- static void walMergesort(
- u32 *aContent, /* Pages in wal */
- ht_slot *aBuffer, /* Buffer of at least *pnList items to use */
- ht_slot *aList, /* IN/OUT: List to sort */
- int *pnList /* IN/OUT: Number of elements in aList[] */
- ){
- struct Sublist {
- int nList; /* Number of elements in aList */
- ht_slot *aList; /* Pointer to sub-list content */
- };
- const int nList = *pnList; /* Size of input list */
- int nMerge = 0; /* Number of elements in list aMerge */
- ht_slot *aMerge = 0; /* List to be merged */
- int iList; /* Index into input list */
- int iSub = 0; /* Index into aSub array */
- struct Sublist aSub[13]; /* Array of sub-lists */
- memset(aSub, 0, sizeof(aSub));
- Debug.Assert( nList<=HASHTABLE_NPAGE && nList>0 );
- Debug.Assert( HASHTABLE_NPAGE==(1<<(ArraySize(aSub)-1)) );
- for(iList=0; iList<nList; iList++){
- nMerge = 1;
- aMerge = &aList[iList];
- for(iSub=0; iList & (1<<iSub); iSub++){
- struct Sublist *p = &aSub[iSub];
- Debug.Assert( p.aList && p.nList<=(1<<iSub) );
- Debug.Assert( p.aList==&aList[iList&~((2<<iSub)-1)] );
- walMerge(aContent, p.aList, p.nList, &aMerge, &nMerge, aBuffer);
- }
- aSub[iSub].aList = aMerge;
- aSub[iSub].nList = nMerge;
- }
- for(iSub++; iSub<ArraySize(aSub); iSub++){
- if( nList & (1<<iSub) ){
- struct Sublist *p = &aSub[iSub];
- Debug.Assert( p.nList<=(1<<iSub) );
- Debug.Assert( p.aList==&aList[nList&~((2<<iSub)-1)] );
- walMerge(aContent, p.aList, p.nList, &aMerge, &nMerge, aBuffer);
- }
- }
- Debug.Assert( aMerge==aList );
- *pnList = nMerge;
- #if SQLITE_DEBUG
- {
- int i;
- for(i=1; i<*pnList; i++){
- Debug.Assert( aContent[aList[i]] > aContent[aList[i-1]] );
- }
- }
- #endif
- }
- /*
- ** Free an iterator allocated by walIteratorInit().
- */
- static void walIteratorFree(WalIterator *p){
- sqlite3ScratchFree(p);
- }
- /*
- ** Construct a WalInterator object that can be used to loop over all
- ** pages in the WAL in ascending order. The caller must hold the checkpoint
- **
- ** On success, make *pp point to the newly allocated WalInterator object
- ** return SQLITE_OK. Otherwise, return an error code. If this routine
- ** returns an error, the value of *pp is undefined.
- **
- ** The calling routine should invoke walIteratorFree() to destroy the
- ** WalIterator object when it has finished with it.
- */
- static int walIteratorInit(Wal *pWal, WalIterator **pp){
- WalIterator *p; /* Return value */
- int nSegment; /* Number of segments to merge */
- u32 iLast; /* Last frame in log */
- int nByte; /* Number of bytes to allocate */
- int i; /* Iterator variable */
- ht_slot *aTmp; /* Temp space used by merge-sort */
- int rc = SQLITE_OK; /* Return Code */
- /* This routine only runs while holding the checkpoint lock. And
- ** it only runs if there is actually content in the log (mxFrame>0).
- */
- Debug.Assert( pWal.ckptLock && pWal.hdr.mxFrame>0 );
- iLast = pWal.hdr.mxFrame;
- /* Allocate space for the WalIterator object. */
- nSegment = walFramePage(iLast) + 1;
- nByte = sizeof(WalIterator)
- + (nSegment-1)*sizeof(struct WalSegment)
- + iLast*sizeof(ht_slot);
- p = (WalIterator *)sqlite3ScratchMalloc(nByte);
- if( !p ){
- return SQLITE_NOMEM;
- }
- memset(p, 0, nByte);
- p.nSegment = nSegment;
- /* Allocate temporary space used by the merge-sort routine. This block
- ** of memory will be freed before this function returns.
- */
- aTmp = (ht_slot *)sqlite3ScratchMalloc(
- sizeof(ht_slot) * (iLast>HASHTABLE_NPAGE?HASHTABLE_NPAGE:iLast)
- );
- if( !aTmp ){
- rc = SQLITE_NOMEM;
- }
- for(i=0; rc==SQLITE_OK && i<nSegment; i++){
- volatile ht_slot *aHash;
- u32 iZero;
- volatile u32 *aPgno;
- rc = walHashGet(pWal, i, &aHash, &aPgno, &iZero);
- if( rc==SQLITE_OK ){
- int j; /* Counter variable */
- int nEntry; /* Number of entries in this segment */
- ht_slot *aIndex; /* Sorted index for this segment */
- aPgno++;
- if( (i+1)==nSegment ){
- nEntry = (int)(iLast - iZero);
- }else{
- nEntry = (int)((u32*)aHash - (u32*)aPgno);
- }
- aIndex = &((ht_slot *)&p.aSegment[p.nSegment])[iZero];
- iZero++;
-
- for(j=0; j<nEntry; j++){
- aIndex[j] = (ht_slot)j;
- }
- walMergesort((u32 *)aPgno, aTmp, aIndex, &nEntry);
- p.aSegment[i].iZero = iZero;
- p.aSegment[i].nEntry = nEntry;
- p.aSegment[i].aIndex = aIndex;
- p.aSegment[i].aPgno = (u32 *)aPgno;
- }
- }
- sqlite3ScratchFree(aTmp);
- if( rc!=SQLITE_OK ){
- walIteratorFree(p);
- }
- *pp = p;
- return rc;
- }
- /*
- ** Copy as much content as we can from the WAL back into the database file
- ** in response to an sqlite3_wal_checkpoint() request or the equivalent.
- **
- ** The amount of information copies from WAL to database might be limited
- ** by active readers. This routine will never overwrite a database page
- ** that a concurrent reader might be using.
- **
- ** All I/O barrier operations (a.k.a fsyncs) occur in this routine when
- ** SQLite is in WAL-mode in synchronous=NORMAL. That means that if
- ** checkpoints are always run by a background thread or background
- ** process, foreground threads will never block on a lengthy fsync call.
- **
- ** Fsync is called on the WAL before writing content out of the WAL and
- ** into the database. This ensures that if the new content is persistent
- ** in the WAL and can be recovered following a power-loss or hard reset.
- **
- ** Fsync is also called on the database file if (and only if) the entire
- ** WAL content is copied into the database file. This second fsync makes
- ** it safe to delete the WAL since the new content will persist in the
- ** database file.
- **
- ** This routine uses and updates the nBackfill field of the wal-index header.
- ** This is the only routine tha will increase the value of nBackfill.
- ** (A WAL reset or recovery will revert nBackfill to zero, but not increase
- ** its value.)
- **
- ** The caller must be holding sufficient locks to ensure that no other
- ** checkpoint is running (in any other thread or process) at the same
- ** time.
- */
- static int walCheckpoint(
- Wal *pWal, /* Wal connection */
- int sync_flags, /* Flags for OsSync() (or 0) */
- int nBuf, /* Size of zBuf in bytes */
- u8 *zBuf /* Temporary buffer to use */
- ){
- int rc; /* Return code */
- int szPage = pWal.hdr.szPage; /* Database page-size */
- WalIterator *pIter = 0; /* Wal iterator context */
- u32 iDbpage = 0; /* Next database page to write */
- u32 iFrame = 0; /* Wal frame containing data for iDbpage */
- u32 mxSafeFrame; /* Max frame that can be backfilled */
- int i; /* Loop counter */
- volatile WalCkptInfo *pInfo; /* The checkpoint status information */
- if( pWal.hdr.mxFrame==0 ) return SQLITE_OK;
- /* Allocate the iterator */
- rc = walIteratorInit(pWal, &pIter);
- if( rc!=SQLITE_OK ){
- return rc;
- }
- Debug.Assert( pIter );
- /*** TODO: Move this test out to the caller. Make it an Debug.Assert() here ***/
- if( pWal.hdr.szPage!=nBuf ){
- rc = SQLITE_CORRUPT_BKPT;
- goto walcheckpoint_out;
- }
- /* Compute in mxSafeFrame the index of the last frame of the WAL that is
- ** safe to write into the database. Frames beyond mxSafeFrame might
- ** overwrite database pages that are in use by active readers and thus
- ** cannot be backfilled from the WAL.
- */
- mxSafeFrame = pWal.hdr.mxFrame;
- pInfo = walCkptInfo(pWal);
- for(i=1; i<WAL_NREADER; i++){
- u32 y = pInfo.aReadMark[i];
- if( mxSafeFrame>=y ){
- Debug.Assert( y<=pWal.hdr.mxFrame );
- rc = walLockExclusive(pWal, WAL_READ_LOCK(i), 1);
- if( rc==SQLITE_OK ){
- pInfo.aReadMark[i] = READMARK_NOT_USED;
- walUnlockExclusive(pWal, WAL_READ_LOCK(i), 1);
- }else if( rc==SQLITE_BUSY ){
- mxSafeFrame = y;
- }else{
- goto walcheckpoint_out;
- }
- }
- }
- if( pInfo.nBackfill<mxSafeFrame
- && (rc = walLockExclusive(pWal, WAL_READ_LOCK(0), 1))==SQLITE_OK
- ){
- u32 nBackfill = pInfo.nBackfill;
- /* Sync the WAL to disk */
- if( sync_flags ){
- rc = sqlite3OsSync(pWal.pWalFd, sync_flags);
- }
- /* Iterate through the contents of the WAL, copying data to the db file. */
- while( rc==SQLITE_OK && 0==walIteratorNext(pIter, &iDbpage, &iFrame) ){
- i64 iOffset;
- Debug.Assert( walFramePgno(pWal, iFrame)==iDbpage );
- if( iFrame<=nBackfill || iFrame>mxSafeFrame ) continue;
- iOffset = walFrameOffset(iFrame, szPage) + WAL_FRAME_HDRSIZE;
- /* testcase( IS_BIG_INT(iOffset) ); // requires a 4GiB WAL file */
- rc = sqlite3OsRead(pWal.pWalFd, zBuf, szPage, iOffset);
- if( rc!=SQLITE_OK ) break;
- iOffset = (iDbpage-1)*(i64)szPage;
- testcase( IS_BIG_INT(iOffset) );
- rc = sqlite3OsWrite(pWal.pDbFd, zBuf, szPage, iOffset);
- if( rc!=SQLITE_OK ) break;
- }
- /* If work was actually accomplished... */
- if( rc==SQLITE_OK ){
- if( mxSafeFrame==walIndexHdr(pWal).mxFrame ){
- i64 szDb = pWal.hdr.nPage*(i64)szPage;
- testcase( IS_BIG_INT(szDb) );
- rc = sqlite3OsTruncate(pWal.pDbFd, szDb);
- if( rc==SQLITE_OK && sync_flags ){
- rc = sqlite3OsSync(pWal.pDbFd, sync_flags);
- }
- }
- if( rc==SQLITE_OK ){
- pInfo.nBackfill = mxSafeFrame;
- }
- }
- /* Release the reader lock held while backfilling */
- walUnlockExclusive(pWal, WAL_READ_LOCK(0), 1);
- }else if( rc==SQLITE_BUSY ){
- /* Reset the return code so as not to report a checkpoint failure
- ** just because active readers prevent any backfill.
- */
- rc = SQLITE_OK;
- }
- walcheckpoint_out:
- walIteratorFree(pIter);
- return rc;
- }
- /*
- ** Close a connection to a log file.
- */
- int sqlite3WalClose(
- Wal *pWal, /* Wal to close */
- int sync_flags, /* Flags to pass to OsSync() (or 0) */
- int nBuf,
- u8 *zBuf /* Buffer of at least nBuf bytes */
- ){
- int rc = SQLITE_OK;
- if( pWal ){
- int isDelete = 0; /* True to unlink wal and wal-index files */
- /* If an EXCLUSIVE lock can be obtained on the database file (using the
- ** ordinary, rollback-mode locking methods, this guarantees that the
- ** connection associated with this log file is the only connection to
- ** the database. In this case checkpoint the database and unlink both
- ** the wal and wal-index files.
- **
- ** The EXCLUSIVE lock is not released before returning.
- */
- rc = sqlite3OsLock(pWal.pDbFd, SQLITE_LOCK_EXCLUSIVE);
- if( rc==SQLITE_OK ){
- if( pWal.exclusiveMode==WAL_NORMAL_MODE ){
- pWal.exclusiveMode = WAL_EXCLUSIVE_MODE;
- }
- rc = sqlite3WalCheckpoint(pWal, sync_flags, nBuf, zBuf);
- if( rc==SQLITE_OK ){
- isDelete = 1;
- }
- }
- walIndexClose(pWal, isDelete);
- sqlite3OsClose(pWal.pWalFd);
- if( isDelete ){
- sqlite3OsDelete(pWal.pVfs, pWal.zWalName, 0);
- }
- WALTRACE(("WAL%p: closed\n", pWal));
- sqlite3_free((void *)pWal.apWiData);
- sqlite3_free(pWal);
- }
- return rc;
- }
- /*
- ** Try to read the wal-index header. Return 0 on success and 1 if
- ** there is a problem.
- **
- ** The wal-index is in shared memory. Another thread or process might
- ** be writing the header at the same time this procedure is trying to
- ** read it, which might result in inconsistency. A dirty read is detected
- ** by verifying that both copies of the header are the same and also by
- ** a checksum on the header.
- **
- ** If and only if the read is consistent and the header is different from
- ** pWal.hdr, then pWal.hdr is updated to the content of the new header
- ** and *pChanged is set to 1.
- **
- ** If the checksum cannot be verified return non-zero. If the header
- ** is read successfully and the checksum verified, return zero.
- */
- static int walIndexTryHdr(Wal *pWal, int *pChanged){
- u32 aCksum[2]; /* Checksum on the header content */
- WalIndexHdr h1, h2; /* Two copies of the header content */
- WalIndexHdr volatile *aHdr; /* Header in shared memory */
- /* The first page of the wal-index must be mapped at this point. */
- Debug.Assert( pWal.nWiData>0 && pWal.apWiData[0] );
- /* Read the header. This might happen currently with a write to the
- ** same area of shared memory on a different CPU in a SMP,
- ** meaning it is possible that an inconsistent snapshot is read
- ** from the file. If this happens, return non-zero.
- **
- ** There are two copies of the header at the beginning of the wal-index.
- ** When reading, read [0] first then [1]. Writes are in the reverse order.
- ** Memory barriers are used to prevent the compiler or the hardware from
- ** reordering the reads and writes.
- */
- aHdr = walIndexHdr(pWal);
- memcpy(&h1, (void *)&aHdr[0], sizeof(h1));
- walShmBarrier(pWal);
- memcpy(&h2, (void *)&aHdr[1], sizeof(h2));
- if( memcmp(&h1, &h2, sizeof(h1))!=0 ){
- return 1; /* Dirty read */
- }
- if( h1.isInit==0 ){
- return 1; /* Malformed header - probably all zeros */
- }
- walChecksumBytes(1, (u8*)&h1, sizeof(h1)-sizeof(h1.aCksum), 0, aCksum);
- if( aCksum[0]!=h1.aCksum[0] || aCksum[1]!=h1.aCksum[1] ){
- return 1; /* Checksum does not match */
- }
- if( memcmp(&pWal.hdr, &h1, sizeof(WalIndexHdr)) ){
- *pChanged = 1;
- memcpy(&pWal.hdr, &h1, sizeof(WalIndexHdr));
- pWal.szPage = pWal.hdr.szPage;
- }
- /* The header was successfully read. Return zero. */
- return 0;
- }
- /*
- ** Read the wal-index header from the wal-index and into pWal.hdr.
- ** If the wal-header appears to be corrupt, try to reconstruct the
- ** wal-index from the WAL before returning.
- **
- ** Set *pChanged to 1 if the wal-index header value in pWal.hdr is
- ** changed by this opertion. If pWal.hdr is unchanged, set *pChanged
- ** to 0.
- **
- ** If the wal-index header is successfully read, return SQLITE_OK.
- ** Otherwise an SQLite error code.
- */
- static int walIndexReadHdr(Wal *pWal, int *pChanged){
- int rc; /* Return code */
- int badHdr; /* True if a header read failed */
- volatile u32 *page0; /* Chunk of wal-index containing header */
- /* Ensure that page 0 of the wal-index (the page that contains the
- ** wal-index header) is mapped. Return early if an error occurs here.
- */
- Debug.Assert( pChanged );
- rc = walIndexPage(pWal, 0, &page0);
- if( rc!=SQLITE_OK ){
- return rc;
- };
- Debug.Assert( page0 || pWal.writeLock==0 );
- /* If the first page of the wal-index has been mapped, try to read the
- ** wal-index header immediately, without holding any lock. This usually
- ** works, but may fail if the wal-index header is corrupt or currently
- ** being modified by another thread or process.
- */
- badHdr = (page0 ? walIndexTryHdr(pWal, pChanged) : 1);
- /* If the first attempt failed, it might have been due to a race
- ** with a writer. So get a WRITE lock and try again.
- */
- Debug.Assert( badHdr==0 || pWal.writeLock==0 );
- if( badHdr && SQLITE_OK==(rc = walLockExclusive(pWal, WAL_WRITE_LOCK, 1)) ){
- pWal.writeLock = 1;
- if( SQLITE_OK==(rc = walIndexPage(pWal, 0, &page0)) ){
- badHdr = walIndexTryHdr(pWal, pChanged);
- if( badHdr ){
- /* If the wal-index header is still malformed even while holding
- ** a WRITE lock, it can only mean that the header is corrupted and
- ** needs to be reconstructed. So run recovery to do exactly that.
- */
- rc = walIndexRecover(pWal);
- *pChanged = 1;
- }
- }
- pWal.writeLock = 0;
- walUnlockExclusive(pWal, WAL_WRITE_LOCK, 1);
- }
- /* If the header is read successfully, check the version number to make
- ** sure the wal-index was not constructed with some future format that
- ** this version of SQLite cannot understand.
- */
- if( badHdr==0 && pWal.hdr.iVersion!=WALINDEX_MAX_VERSION ){
- rc = SQLITE_CANTOPEN_BKPT;
- }
- return rc;
- }
- /*
- ** This is the value that walTryBeginRead returns when it needs to
- ** be retried.
- */
- //#define WAL_RETRY (-1)
- const int WAL_RETRY =(-1);
- /*
- ** Attempt to start a read transaction. This might fail due to a race or
- ** other transient condition. When that happens, it returns WAL_RETRY to
- ** indicate to the caller that it is safe to retry immediately.
- **
- ** On success return SQLITE_OK. On a permanent failure (such an
- ** I/O error or an SQLITE_BUSY because another process is running
- ** recovery) return a positive error code.
- **
- ** The useWal parameter is true to force the use of the WAL and disable
- ** the case where the WAL is bypassed because it has been completely
- ** checkpointed. If useWal==0 then this routine calls walIndexReadHdr()
- ** to make a copy of the wal-index header into pWal.hdr. If the
- ** wal-index header has changed, *pChanged is set to 1 (as an indication
- ** to the caller that the local paget cache is obsolete and needs to be
- ** flushed.) When useWal==1, the wal-index header is assumed to already
- ** be loaded and the pChanged parameter is unused.
- **
- ** The caller must set the cnt parameter to the number of prior calls to
- ** this routine during the current read attempt that returned WAL_RETRY.
- ** This routine will start taking more aggressive measures to clear the
- ** race conditions after multiple WAL_RETRY returns, and after an excessive
- ** number of errors will ultimately return SQLITE_PROTOCOL. The
- ** SQLITE_PROTOCOL return indicates that some other process has gone rogue
- ** and is not honoring the locking protocol. There is a vanishingly small
- ** chance that SQLITE_PROTOCOL could be returned because of a run of really
- ** bad luck when there is lots of contention for the wal-index, but that
- ** possibility is so small that it can be safely neglected, we believe.
- **
- ** On success, this routine obtains a read lock on
- ** WAL_READ_LOCK(pWal.readLock). The pWal.readLock integer is
- ** in the range 0 <= pWal.readLock < WAL_NREADER. If pWal.readLock==(-1)
- ** that means the Wal does not hold any read lock. The reader must not
- ** access any database page that is modified by a WAL frame up to and
- ** including frame number aReadMark[pWal.readLock]. The reader will
- ** use WAL frames up to and including pWal.hdr.mxFrame if pWal.readLock>0
- ** Or if pWal.readLock==0, then the reader will ignore the WAL
- ** completely and get all content directly from the database file.
- ** If the useWal parameter is 1 then the WAL will never be ignored and
- ** this routine will always set pWal.readLock>0 on success.
- ** When the read transaction is completed, the caller must release the
- ** lock on WAL_READ_LOCK(pWal.readLock) and set pWal.readLock to -1.
- **
- ** This routine uses the nBackfill and aReadMark[] fields of the header
- ** to select a particular WAL_READ_LOCK() that strives to let the
- ** checkpoint process do as much work as possible. This routine might
- ** update values of the aReadMark[] array in the header, but if it does
- ** so it takes care to hold an exclusive lock on the corresponding
- ** WAL_READ_LOCK() while changing values.
- */
- static int walTryBeginRead(Wal *pWal, int *pChanged, int useWal, int cnt){
- volatile WalCkptInfo *pInfo; /* Checkpoint information in wal-index */
- u32 mxReadMark; /* Largest aReadMark[] value */
- int mxI; /* Index of largest aReadMark[] value */
- int i; /* Loop counter */
- int rc = SQLITE_OK; /* Return code */
- Debug.Assert( pWal.readLock<0 ); /* Not currently locked */
- /* Take steps to avoid spinning forever if there is a protocol error. */
- if( cnt>5 ){
- if( cnt>100 ) return SQLITE_PROTOCOL;
- sqlite3OsSleep(pWal.pVfs, 1);
- }
- if( !useWal ){
- rc = walIndexReadHdr(pWal, pChanged);
- if( rc==SQLITE_BUSY ){
- /* If there is not a recovery running in another thread or process
- ** then convert BUSY errors to WAL_RETRY. If recovery is known to
- ** be running, convert BUSY to BUSY_RECOVERY. There is a race here
- ** which might cause WAL_RETRY to be returned even if BUSY_RECOVERY
- ** would be technically correct. But the race is benign since with
- ** WAL_RETRY this routine will be called again and will probably be
- ** right on the second iteration.
- */
- if( pWal.apWiData[0]==0 ){
- /* This branch is taken when the xShmMap() method returns SQLITE_BUSY.
- ** We assume this is a transient condition, so return WAL_RETRY. The
- ** xShmMap() implementation used by the default unix and win32 VFS
- ** modules may return SQLITE_BUSY due to a race condition in the
- ** code that determines whether or not the shared-memory region
- ** must be zeroed before the requested page is returned.
- */
- rc = WAL_RETRY;
- }else if( SQLITE_OK==(rc = walLockShared(pWal, WAL_RECOVER_LOCK)) ){
- walUnlockShared(pWal, WAL_RECOVER_LOCK);
- rc = WAL_RETRY;
- }else if( rc==SQLITE_BUSY ){
- rc = SQLITE_BUSY_RECOVERY;
- }
- }
- if( rc!=SQLITE_OK ){
- return rc;
- }
- }
- pInfo = walCkptInfo(pWal);
- if( !useWal && pInfo.nBackfill==pWal.hdr.mxFrame ){
- /* The WAL has been completely backfilled (or it is empty).
- ** and can be safely ignored.
- */
- rc = walLockShared(pWal, WAL_READ_LOCK(0));
- walShmBarrier(pWal);
- if( rc==SQLITE_OK ){
- if( memcmp((void *)walIndexHdr(pWal), &pWal.hdr, sizeof(WalIndexHdr)) ){
- /* It is not safe to allow the reader to continue here if frames
- ** may have been appended to the log before READ_LOCK(0) was obtained.
- ** When holding READ_LOCK(0), the reader ignores the entire log file,
- ** which implies that the database file contains a trustworthy
- ** snapshoT. Since holding READ_LOCK(0) prevents a checkpoint from
- ** happening, this is usually correct.
- **
- ** However, if frames have been appended to the log (or if the log
- ** is wrapped and written for that matter) before the READ_LOCK(0)
- ** is obtained, that is not necessarily true. A checkpointer may
- ** have started to backfill the appended frames but crashed before
- ** it finished. Leaving a corrupt image in the database file.
- */
- walUnlockShared(pWal, WAL_READ_LOCK(0));
- return WAL_RETRY;
- }
- pWal.readLock = 0;
- return SQLITE_OK;
- }else if( rc!=SQLITE_BUSY ){
- return rc;
- }
- }
- /* If we get this far, it means that the reader will want to use
- ** the WAL to get at content from recent commits. The job now is
- ** to select one of the aReadMark[] entries that is closest to
- ** but not exceeding pWal.hdr.mxFrame and lock that entry.
- */
- mxReadMark = 0;
- mxI = 0;
- for(i=1; i<WAL_NREADER; i++){
- u32 thisMark = pInfo.aReadMark[i];
- if( mxReadMark<=thisMark && thisMark<=pWal.hdr.mxFrame ){
- Debug.Assert( thisMark!=READMARK_NOT_USED );
- mxReadMark = thisMark;
- mxI = i;
- }
- }
- if( mxI==0 ){
- /* If we get here, it means that all of the aReadMark[] entries between
- ** 1 and WAL_NREADER-1 are zero. Try to initialize aReadMark[1] to
- ** be mxFrame, then retry.
- */
- rc = walLockExclusive(pWal, WAL_READ_LOCK(1), 1);
- if( rc==SQLITE_OK ){
- pInfo.aReadMark[1] = pWal.hdr.mxFrame;
- walUnlockExclusive(pWal, WAL_READ_LOCK(1), 1);
- rc = WAL_RETRY;
- }else if( rc==SQLITE_BUSY ){
- rc = WAL_RETRY;
- }
- return rc;
- }else{
- if( mxReadMark < pWal.hdr.mxFrame ){
- for(i=1; i<WAL_NREADER; i++){
- rc = walLockExclusive(pWal, WAL_READ_LOCK(i), 1);
- if( rc==SQLITE_OK ){
- mxReadMark = pInfo.aReadMark[i] = pWal.hdr.mxFrame;
- mxI = i;
- walUnlockExclusive(pWal, WAL_READ_LOCK(i), 1);
- break;
- }else if( rc!=SQLITE_BUSY ){
- return rc;
- }
- }
- }
- rc = walLockShared(pWal, WAL_READ_LOCK(mxI));
- if( rc ){
- return rc==SQLITE_BUSY ? WAL_RETRY : rc;
- }
- /* Now that the read-lock has been obtained, check that neither the
- ** value in the aReadMark[] array or the contents of the wal-index
- ** header have changed.
- **
- ** It is necessary to check that the wal-index header did not change
- ** between the time it was read and when the shared-lock was obtained
- ** on WAL_READ_LOCK(mxI) was obtained to account for the possibility
- ** that the log file may have been wrapped by a writer, or that frames
- ** that occur later in the log than pWal.hdr.mxFrame may have been
- ** copied into the database by a checkpointer. If either of these things
- ** happened, then reading the database with the current value of
- ** pWal.hdr.mxFrame risks reading a corrupted snapshot. So, retry
- ** instead.
- **
- ** This does not guarantee that the copy of the wal-index header is up to
- ** date before proceeding. That would not be possible without somehow
- ** blocking writers. It only guarantees that a dangerous checkpoint or
- ** log-wrap (either of which would require an exclusive lock on
- ** WAL_READ_LOCK(mxI)) has not occurred since the snapshot was valid.
- */
- walShmBarrier(pWal);
- if( pInfo.aReadMark[mxI]!=mxReadMark
- || memcmp((void *)walIndexHdr(pWal), &pWal.hdr, sizeof(WalIndexHdr))
- ){
- walUnlockShared(pWal, WAL_READ_LOCK(mxI));
- return WAL_RETRY;
- }else{
- Debug.Assert( mxReadMark<=pWal.hdr.mxFrame );
- pWal.readLock = (i16)mxI;
- }
- }
- return rc;
- }
- /*
- ** Begin a read transaction on the database.
- **
- ** This routine used to be called sqlite3OpenSnapshot() and with good reason:
- ** it takes a snapshot of the state of the WAL and wal-index for the current
- ** instant in time. The current thread will continue to use this snapshot.
- ** Other threads might append new content to the WAL and wal-index but
- ** that extra content is ignored by the current thread.
- **
- ** If the database contents have changes since the previous read
- ** transaction, then *pChanged is set to 1 before returning. The
- ** Pager layer will use this to know that is cache is stale and
- ** needs to be flushed.
- */
- int sqlite3WalBeginReadTransaction(Wal *pWal, int *pChanged){
- int rc; /* Return code */
- int cnt = 0; /* Number of TryBeginRead attempts */
- do{
- rc = walTryBeginRead(pWal, pChanged, 0, ++cnt);
- }while( rc==WAL_RETRY );
- return rc;
- }
- /*
- ** Finish with a read transaction. All this does is release the
- ** read-lock.
- */
- void sqlite3WalEndReadTransaction(Wal *pWal){
- if( pWal.readLock>=0 ){
- walUnlockShared(pWal, WAL_READ_LOCK(pWal.readLock));
- pWal.readLock = -1;
- }
- }
- /*
- ** Read a page from the WAL, if it is present in the WAL and if the
- ** current read transaction is configured to use the WAL.
- **
- ** The *pInWal is set to 1 if the requested page is in the WAL and
- ** has been loaded. Or *pInWal is set to 0 if the page was not in
- ** the WAL and needs to be read out of the database.
- */
- int sqlite3WalRead(
- Wal *pWal, /* WAL handle */
- Pgno pgno, /* Database page number to read data for */
- int *pInWal, /* OUT: True if data is read from WAL */
- int nOut, /* Size of buffer pOut in bytes */
- u8 *pOut /* Buffer to write page data to */
- ){
- u32 iRead = 0; /* If !=0, WAL frame to return data from */
- u32 iLast = pWal.hdr.mxFrame; /* Last page in WAL for this reader */
- int iHash; /* Used to loop through N hash tables */
- /* This routine is only be called from within a read transaction. */
- Debug.Assert( pWal.readLock>=0 || pWal.lockError );
- /* If the "last page" field of the wal-index header snapshot is 0, then
- ** no data will be read from the wal under any circumstances. Return early
- ** in this case as an optimization. Likewise, if pWal.readLock==0,
- ** then the WAL is ignored by the reader so return early, as if the
- ** WAL were empty.
- */
- if( iLast==0 || pWal.readLock==0 ){
- *pInWal = 0;
- return SQLITE_OK;
- }
- /* Search the hash table or tables for an entry matching page number
- ** pgno. Each iteration of the following for() loop searches one
- ** hash table (each hash table indexes up to HASHTABLE_NPAGE frames).
- **
- ** This code might run concurrently to the code in walIndexAppend()
- ** that adds entries to the wal-index (and possibly to this hash
- ** table). This means the value just read from the hash
- ** slot (aHash[iKey]) may have been added before or after the
- ** current read transaction was opened. Values added after the
- ** read transaction was opened may have been written incorrectly -
- ** i.e. these slots may contain garbage data. However, we assume
- ** that any slots written before the current read transaction was
- ** opened remain unmodified.
- **
- ** For the reasons above, the if(...) condition featured in the inner
- ** loop of the following block is more stringent that would be required
- ** if we had exclusive access to the hash-table:
- **
- ** (aPgno[iFrame]==pgno):
- ** This condition filters out normal hash-table collisions.
- **
- ** (iFrame<=iLast):
- ** This condition filters out entries that were added to the hash
- ** table after the current read-transaction had started.
- */
- for(iHash=walFramePage(iLast); iHash>=0 && iRead==0; iHash--){
- volatile ht_slot *aHash; /* Pointer to hash table */
- volatile u32 *aPgno; /* Pointer to array of page numbers */
- u32 iZero; /* Frame number corresponding to aPgno[0] */
- int iKey; /* Hash slot index */
- int nCollide; /* Number of hash collisions remaining */
- int rc; /* Error code */
- rc = walHashGet(pWal, iHash, &aHash, &aPgno, &iZero);
- if( rc!=SQLITE_OK ){
- return rc;
- }
- nCollide = HASHTABLE_NSLOT;
- for(iKey=walHash(pgno); aHash[iKey]; iKey=walNextHash(iKey)){
- u32 iFrame = aHash[iKey] + iZero;
- if( iFrame<=iLast && aPgno[aHash[iKey]]==pgno ){
- Debug.Assert( iFrame>iRead );
- iRead = iFrame;
- }
- if( (nCollide--)==0 ){
- return SQLITE_CORRUPT_BKPT;
- }
- }
- }
- #if SQLITE_ENABLE_EXPENSIVE_ASSERT
- /* If expensive Debug.Assert() statements are available, do a linear search
- ** of the wal-index file content. Make sure the results agree with the
- ** result obtained using the hash indexes above. */
- {
- u32 iRead2 = 0;
- u32 iTest;
- for(iTest=iLast; iTest>0; iTest--){
- if( walFramePgno(pWal, iTest)==pgno ){
- iRead2 = iTest;
- break;
- }
- }
- Debug.Assert( iRead==iRead2 );
- }
- #endif
- /* If iRead is non-zero, then it is the log frame number that contains the
- ** required page. Read and return data from the log file.
- */
- if( iRead ){
- i64 iOffset = walFrameOffset(iRead, pWal.hdr.szPage) + WAL_FRAME_HDRSIZE;
- *pInWal = 1;
- /* testcase( IS_BIG_INT(iOffset) ); // requires a 4GiB WAL */
- return sqlite3OsRead(pWal.pWalFd, pOut, nOut, iOffset);
- }
- *pInWal = 0;
- return SQLITE_OK;
- }
- /*
- ** Set *pPgno to the size of the database file (or zero, if unknown).
- */
- void sqlite3WalDbsize(Wal *pWal, Pgno *pPgno){
- Debug.Assert( pWal.readLock>=0 || pWal.lockError );
- *pPgno = pWal.hdr.nPage;
- }
- /*
- ** This function starts a write transaction on the WAL.
- **
- ** A read transaction must have already been started by a prior call
- ** to sqlite3WalBeginReadTransaction().
- **
- ** If another thread or process has written into the database since
- ** the read transaction was started, then it is not possible for this
- ** thread to write as doing so would cause a fork. So this routine
- ** returns SQLITE_BUSY in that case and no write transaction is started.
- **
- ** There can only be a single writer active at a time.
- */
- int sqlite3WalBeginWriteTransaction(Wal *pWal){
- int rc;
- /* Cannot start a write transaction without first holding a read
- ** transaction. */
- Debug.Assert( pWal.readLock>=0 );
- if( pWal.readOnly ){
- return SQLITE_READONLY;
- }
- /* Only one writer allowed at a time. Get the write lock. Return
- ** SQLITE_BUSY if unable.
- */
- rc = walLockExclusive(pWal, WAL_WRITE_LOCK, 1);
- if( rc ){
- return rc;
- }
- pWal.writeLock = 1;
- /* If another connection has written to the database file since the
- ** time the read transaction on this connection was started, then
- ** the write is disallowed.
- */
- if( memcmp(&pWal.hdr, (void *)walIndexHdr(pWal), sizeof(WalIndexHdr))!=0 ){
- walUnlockExclusive(pWal, WAL_WRITE_LOCK, 1);
- pWal.writeLock = 0;
- rc = SQLITE_BUSY;
- }
- return rc;
- }
- /*
- ** End a write transaction. The commit has already been done. This
- ** routine merely releases the lock.
- */
- int sqlite3WalEndWriteTransaction(Wal *pWal){
- if( pWal.writeLock ){
- walUnlockExclusive(pWal, WAL_WRITE_LOCK, 1);
- pWal.writeLock = 0;
- }
- return SQLITE_OK;
- }
- /*
- ** If any data has been written (but not committed) to the log file, this
- ** function moves the write-pointer back to the start of the transaction.
- **
- ** Additionally, the callback function is invoked for each frame written
- ** to the WAL since the start of the transaction. If the callback returns
- ** other than SQLITE_OK, it is not invoked again and the error code is
- ** returned to the caller.
- **
- ** Otherwise, if the callback function does not return an error, this
- ** function returns SQLITE_OK.
- */
- int sqlite3WalUndo(Wal *pWal, int (*xUndo)(void *, Pgno), void *pUndoCtx){
- int rc = SQLITE_OK;
- if( pWal.writeLock ){
- Pgno iMax = pWal.hdr.mxFrame;
- Pgno iFrame;
-
- /* Restore the clients cache of the wal-index header to the state it
- ** was in before the client began writing to the database.
- */
- memcpy(&pWal.hdr, (void *)walIndexHdr(pWal), sizeof(WalIndexHdr));
- for(iFrame=pWal.hdr.mxFrame+1;
- ALWAYS(rc==SQLITE_OK) && iFrame<=iMax;
- iFrame++
- ){
- /* This call cannot fail. Unless the page for which the page number
- ** is passed as the second argument is (a) in the cache and
- ** (b) has an outstanding reference, then xUndo is either a no-op
- ** (if (a) is false) or simply expels the page from the cache (if (b)
- ** is false).
- **
- ** If the upper layer is doing a rollback, it is guaranteed that there
- ** are no outstanding references to any page other than page 1. And
- ** page 1 is never written to the log until the transaction is
- ** committed. As a result, the call to xUndo may not fail.
- */
- Debug.Assert( walFramePgno(pWal, iFrame)!=1 );
- rc = xUndo(pUndoCtx, walFramePgno(pWal, iFrame));
- }
- walCleanupHash(pWal);
- }
- Debug.Assert( rc==SQLITE_OK );
- return rc;
- }
- /*
- ** Argument aWalData must point to an array of WAL_SAVEPOINT_NDATA u32
- ** values. This function populates the array with values required to
- ** "rollback" the write position of the WAL handle back to the current
- ** point in the event of a savepoint rollback (via WalSavepointUndo()).
- */
- void sqlite3WalSavepoint(Wal *pWal, u32 *aWalData){
- Debug.Assert( pWal.writeLock );
- aWalData[0] = pWal.hdr.mxFrame;
- aWalData[1] = pWal.hdr.aFrameCksum[0];
- aWalData[2] = pWal.hdr.aFrameCksum[1];
- aWalData[3] = pWal.nCkpt;
- }
- /*
- ** Move the write position of the WAL back to the point identified by
- ** the values in the aWalData[] array. aWalData must point to an array
- ** of WAL_SAVEPOINT_NDATA u32 values that has been previously populated
- ** by a call to WalSavepoint().
- */
- int sqlite3WalSavepointUndo(Wal *pWal, u32 *aWalData){
- int rc = SQLITE_OK;
- Debug.Assert( pWal.writeLock );
- Debug.Assert( aWalData[3]!=pWal.nCkpt || aWalData[0]<=pWal.hdr.mxFrame );
- if( aWalData[3]!=pWal.nCkpt ){
- /* This savepoint was opened immediately after the write-transaction
- ** was started. Right after that, the writer decided to wrap around
- ** to the start of the log. Update the savepoint values to match.
- */
- aWalData[0] = 0;
- aWalData[3] = pWal.nCkpt;
- }
- if( aWalData[0]<pWal.hdr.mxFrame ){
- pWal.hdr.mxFrame = aWalData[0];
- pWal.hdr.aFrameCksum[0] = aWalData[1];
- pWal.hdr.aFrameCksum[1] = aWalData[2];
- walCleanupHash(pWal);
- }
- return rc;
- }
- /*
- ** This function is called just before writing a set of frames to the log
- ** file (see sqlite3WalFrames()). It checks to see if, instead of appending
- ** to the current log file, it is possible to overwrite the start of the
- ** existing log file with the new frames (i.e. "reset" the log). If so,
- ** it sets pWal.hdr.mxFrame to 0. Otherwise, pWal.hdr.mxFrame is left
- ** unchanged.
- **
- ** SQLITE_OK is returned if no error is encountered (regardless of whether
- ** or not pWal.hdr.mxFrame is modified). An SQLite error code is returned
- ** if an error occurs.
- */
- static int walRestartLog(Wal *pWal){
- int rc = SQLITE_OK;
- int cnt;
- if( pWal.readLock==0 ){
- volatile WalCkptInfo *pInfo = walCkptInfo(pWal);
- Debug.Assert( pInfo.nBackfill==pWal.hdr.mxFrame );
- if( pInfo.nBackfill>0 ){
- rc = walLockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1);
- if( rc==SQLITE_OK ){
- /* If all readers are using WAL_READ_LOCK(0) (in other words if no
- ** readers are currently using the WAL), then the transactions
- ** frames will overwrite the start of the existing log. Update the
- ** wal-index header to reflect this.
- **
- ** In theory it would be Ok to update the cache of the header only
- ** at this point. But updating the actual wal-index header is also
- ** safe and means there is no special case for sqlite3WalUndo()
- ** to handle if this transaction is rolled back.
- */
- int i; /* Loop counter */
- u32 *aSalt = pWal.hdr.aSalt; /* Big-endian salt values */
- pWal.nCkpt++;
- pWal.hdr.mxFrame = 0;
- sqlite3Put4byte((u8*)&aSalt[0], 1 + sqlite3Get4byte((u8*)&aSalt[0]));
- sqlite3_randomness(4, &aSalt[1]);
- walIndexWriteHdr(pWal);
- pInfo.nBackfill = 0;
- for(i=1; i<WAL_NREADER; i++) pInfo.aReadMark[i] = READMARK_NOT_USED;
- Debug.Assert( pInfo.aReadMark[0]==0 );
- walUnlockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1);
- }else if( rc!=SQLITE_BUSY ){
- return rc;
- }
- }
- walUnlockShared(pWal, WAL_READ_LOCK(0));
- pWal.readLock = -1;
- cnt = 0;
- do{
- int notUsed;
- rc = walTryBeginRead(pWal, ¬Used, 1, ++cnt);
- }while( rc==WAL_RETRY );
- }
- return rc;
- }
- /*
- ** Write a set of frames to the log. The caller must hold the write-lock
- ** on the log file (obtained using sqlite3WalBeginWriteTransaction()).
- */
- int sqlite3WalFrames(
- Wal *pWal, /* Wal handle to write to */
- int szPage, /* Database page-size in bytes */
- PgHdr *pList, /* List of dirty pages to write */
- Pgno nTruncate, /* Database size after this commit */
- int isCommit, /* True if this is a commit */
- int sync_flags /* Flags to pass to OsSync() (or 0) */
- ){
- int rc; /* Used to catch return codes */
- u32 iFrame; /* Next frame address */
- u8 aFrame[WAL_FRAME_HDRSIZE]; /* Buffer to assemble frame-header in */
- PgHdr *p; /* Iterator to run through pList with. */
- PgHdr *pLast = 0; /* Last frame in list */
- int nLast = 0; /* Number of extra copies of last page */
- Debug.Assert( pList );
- Debug.Assert( pWal.writeLock );
- #if (SQLITE_TEST) && (SQLITE_DEBUG)
- { int cnt; for(cnt=0, p=pList; p; p=p.pDirty, cnt++){}
- WALTRACE(("WAL%p: frame write begin. %d frames. mxFrame=%d. %s\n",
- pWal, cnt, pWal.hdr.mxFrame, isCommit ? "Commit" : "Spill"));
- }
- #endif
- /* See if it is possible to write these frames into the start of the
- ** log file, instead of appending to it at pWal.hdr.mxFrame.
- */
- if( SQLITE_OK!=(rc = walRestartLog(pWal)) ){
- return rc;
- }
- /* If this is the first frame written into the log, write the WAL
- ** header to the start of the WAL file. See comments at the top of
- ** this source file for a description of the WAL header format.
- */
- iFrame = pWal.hdr.mxFrame;
- if( iFrame==0 ){
- u8 aWalHdr[WAL_HDRSIZE]; /* Buffer to assemble wal-header in */
- u32 aCksum[2]; /* Checksum for wal-header */
- sqlite3Put4byte(&aWalHdr[0], (WAL_MAGIC | SQLITE_BIGENDIAN));
- sqlite3Put4byte(&aWalHdr[4], WAL_MAX_VERSION);
- sqlite3Put4byte(&aWalHdr[8], szPage);
- sqlite3Put4byte(&aWalHdr[12], pWal.nCkpt);
- sqlite3_randomness(8, pWal.hdr.aSalt);
- memcpy(&aWalHdr[16], pWal.hdr.aSalt, 8);
- walChecksumBytes(1, aWalHdr, WAL_HDRSIZE-2*4, 0, aCksum);
- sqlite3Put4byte(&aWalHdr[24], aCksum[0]);
- sqlite3Put4byte(&aWalHdr[28], aCksum[1]);
-
- pWal.szPage = (u16)szPage;
- pWal.hdr.bigEndCksum = SQLITE_BIGENDIAN;
- pWal.hdr.aFrameCksum[0] = aCksum[0];
- pWal.hdr.aFrameCksum[1] = aCksum[1];
- rc = sqlite3OsWrite(pWal.pWalFd, aWalHdr, sizeof(aWalHdr), 0);
- WALTRACE(("WAL%p: wal-header write %s\n", pWal, rc ? "failed" : "ok"));
- if( rc!=SQLITE_OK ){
- return rc;
- }
- }
- Debug.Assert( (int)pWal.szPage==szPage );
- /* Write the log file. */
- for(p=pList; p; p=p.pDirty){
- u32 nDbsize; /* Db-size field for frame header */
- i64 iOffset; /* Write offset in log file */
- void *pData;
-
- iOffset = walFrameOffset(++iFrame, szPage);
- /* testcase( IS_BIG_INT(iOffset) ); // requires a 4GiB WAL */
-
- /* Populate and write the frame header */
- nDbsize = (isCommit && p.pDirty==0) ? nTruncate : 0;
- #if (SQLITE_HAS_CODEC)
- if( (pData = sqlite3PagerCodec(p))==0 ) return SQLITE_NOMEM;
- #else
- pData = p.pData;
- #endif
- walEncodeFrame(pWal, p.pgno, nDbsize, pData, aFrame);
- rc = sqlite3OsWrite(pWal.pWalFd, aFrame, sizeof(aFrame), iOffset);
- if( rc!=SQLITE_OK ){
- return rc;
- }
- /* Write the page data */
- rc = sqlite3OsWrite(pWal.pWalFd, pData, szPage, iOffset+sizeof(aFrame));
- if( rc!=SQLITE_OK ){
- return rc;
- }
- pLast = p;
- }
- /* Sync the log file if the 'isSync' flag was specified. */
- if( sync_flags ){
- i64 iSegment = sqlite3OsSectorSize(pWal.pWalFd);
- i64 iOffset = walFrameOffset(iFrame+1, szPage);
- Debug.Assert( isCommit );
- Debug.Assert( iSegment>0 );
- iSegment = (((iOffset+iSegment-1)/iSegment) * iSegment);
- while( iOffset<iSegment ){
- void *pData;
- #if (SQLITE_HAS_CODEC)
- if( (pData = sqlite3PagerCodec(pLast))==0 ) return SQLITE_NOMEM;
- #else
- pData = pLast.pData;
- #endif
- walEncodeFrame(pWal, pLast.pgno, nTruncate, pData, aFrame);
- /* testcase( IS_BIG_INT(iOffset) ); // requires a 4GiB WAL */
- rc = sqlite3OsWrite(pWal.pWalFd, aFrame, sizeof(aFrame), iOffset);
- if( rc!=SQLITE_OK ){
- return rc;
- }
- iOffset += WAL_FRAME_HDRSIZE;
- rc = sqlite3OsWrite(pWal.pWalFd, pData, szPage, iOffset);
- if( rc!=SQLITE_OK ){
- return rc;
- }
- nLast++;
- iOffset += szPage;
- }
- rc = sqlite3OsSync(pWal.pWalFd, sync_flags);
- }
- /* Append data to the wal-index. It is not necessary to lock the
- ** wal-index to do this as the SQLITE_SHM_WRITE lock held on the wal-index
- ** guarantees that there are no other writers, and no data that may
- ** be in use by existing readers is being overwritten.
- */
- iFrame = pWal.hdr.mxFrame;
- for(p=pList; p && rc==SQLITE_OK; p=p.pDirty){
- iFrame++;
- rc = walIndexAppend(pWal, iFrame, p.pgno);
- }
- while( nLast>0 && rc==SQLITE_OK ){
- iFrame++;
- nLast--;
- rc = walIndexAppend(pWal, iFrame, pLast.pgno);
- }
- if( rc==SQLITE_OK ){
- /* Update the private copy of the header. */
- pWal.hdr.szPage = (u16)szPage;
- pWal.hdr.mxFrame = iFrame;
- if( isCommit ){
- pWal.hdr.iChange++;
- pWal.hdr.nPage = nTruncate;
- }
- /* If this is a commit, update the wal-index header too. */
- if( isCommit ){
- walIndexWriteHdr(pWal);
- pWal.iCallback = iFrame;
- }
- }
- WALTRACE(("WAL%p: frame write %s\n", pWal, rc ? "failed" : "ok"));
- return rc;
- }
- /*
- ** This routine is called to implement sqlite3_wal_checkpoint() and
- ** related interfaces.
- **
- ** Obtain a CHECKPOINT lock and then backfill as much information as
- ** we can from WAL into the database.
- */
- int sqlite3WalCheckpoint(
- Wal *pWal, /* Wal connection */
- int sync_flags, /* Flags to sync db file with (or 0) */
- int nBuf, /* Size of temporary buffer */
- u8 *zBuf /* Temporary buffer to use */
- ){
- int rc; /* Return code */
- int isChanged = 0; /* True if a new wal-index header is loaded */
- Debug.Assert( pWal.ckptLock==0 );
- WALTRACE(("WAL%p: checkpoint begins\n", pWal));
- rc = walLockExclusive(pWal, WAL_CKPT_LOCK, 1);
- if( rc ){
- /* Usually this is SQLITE_BUSY meaning that another thread or process
- ** is already running a checkpoint, or maybe a recovery. But it might
- ** also be SQLITE_IOERR. */
- return rc;
- }
- pWal.ckptLock = 1;
- /* Copy data from the log to the database file. */
- rc = walIndexReadHdr(pWal, &isChanged);
- if( rc==SQLITE_OK ){
- rc = walCheckpoint(pWal, sync_flags, nBuf, zBuf);
- }
- if( isChanged ){
- /* If a new wal-index header was loaded before the checkpoint was
- ** performed, then the pager-cache associated with pWal is now
- ** out of date. So zero the cached wal-index header to ensure that
- ** next time the pager opens a snapshot on this database it knows that
- ** the cache needs to be reset.
- */
- memset(&pWal.hdr, 0, sizeof(WalIndexHdr));
- }
- /* Release the locks. */
- walUnlockExclusive(pWal, WAL_CKPT_LOCK, 1);
- pWal.ckptLock = 0;
- WALTRACE(("WAL%p: checkpoint %s\n", pWal, rc ? "failed" : "ok"));
- return rc;
- }
- /* Return the value to pass to a sqlite3_wal_hook callback, the
- ** number of frames in the WAL at the point of the last commit since
- ** sqlite3WalCallback() was called. If no commits have occurred since
- ** the last call, then return 0.
- */
- int sqlite3WalCallback(Wal *pWal){
- u32 ret = 0;
- if( pWal ){
- ret = pWal.iCallback;
- pWal.iCallback = 0;
- }
- return (int)ret;
- }
- /*
- ** This function is called to change the WAL subsystem into or out
- ** of locking_mode=EXCLUSIVE.
- **
- ** If op is zero, then attempt to change from locking_mode=EXCLUSIVE
- ** into locking_mode=NORMAL. This means that we must acquire a lock
- ** on the pWal.readLock byte. If the WAL is already in locking_mode=NORMAL
- ** or if the acquisition of the lock fails, then return 0. If the
- ** transition out of exclusive-mode is successful, return 1. This
- ** operation must occur while the pager is still holding the exclusive
- ** lock on the main database file.
- **
- ** If op is one, then change from locking_mode=NORMAL into
- ** locking_mode=EXCLUSIVE. This means that the pWal.readLock must
- ** be released. Return 1 if the transition is made and 0 if the
- ** WAL is already in exclusive-locking mode - meaning that this
- ** routine is a no-op. The pager must already hold the exclusive lock
- ** on the main database file before invoking this operation.
- **
- ** If op is negative, then do a dry-run of the op==1 case but do
- ** not actually change anything. The pager uses this to see if it
- ** should acquire the database exclusive lock prior to invoking
- ** the op==1 case.
- */
- int sqlite3WalExclusiveMode(Wal *pWal, int op){
- int rc;
- Debug.Assert( pWal.writeLock==0 );
- Debug.Assert( pWal.exclusiveMode!=WAL_HEAPMEMORY_MODE || op==-1 );
- /* pWal.readLock is usually set, but might be -1 if there was a
- ** prior error while attempting to acquire are read-lock. This cannot
- ** happen if the connection is actually in exclusive mode (as no xShmLock
- ** locks are taken in this case). Nor should the pager attempt to
- ** upgrade to exclusive-mode following such an error.
- */
- Debug.Assert( pWal.readLock>=0 || pWal.lockError );
- Debug.Assert( pWal.readLock>=0 || (op<=0 && pWal.exclusiveMode==0) );
- if( op==0 ){
- if( pWal.exclusiveMode ){
- pWal.exclusiveMode = 0;
- if( walLockShared(pWal, WAL_READ_LOCK(pWal.readLock))!=SQLITE_OK ){
- pWal.exclusiveMode = 1;
- }
- rc = pWal.exclusiveMode==0;
- }else{
- /* Already in locking_mode=NORMAL */
- rc = 0;
- }
- }else if( op>0 ){
- Debug.Assert( pWal.exclusiveMode==0 );
- Debug.Assert( pWal.readLock>=0 );
- walUnlockShared(pWal, WAL_READ_LOCK(pWal.readLock));
- pWal.exclusiveMode = 1;
- rc = 1;
- }else{
- rc = pWal.exclusiveMode==0;
- }
- return rc;
- }
- /*
- ** Return true if the argument is non-NULL and the WAL module is using
- ** heap-memory for the wal-index. Otherwise, if the argument is NULL or the
- ** WAL module is using shared-memory, return false.
- */
- int sqlite3WalHeapMemory(Wal *pWal){
- return (pWal && pWal.exclusiveMode==WAL_HEAPMEMORY_MODE );
- }
- #endif //* #if !SQLITE_OMIT_WAL */
- }
- }