SQLite

Check-in [e2fc5c814c]
Login

Many hyperlinks are disabled.
Use anonymous login to enable hyperlinks.

Overview
Comment:Add experimental mode that uses two wal files. Activated using "PRAGMA journal_mode = wal2".
Downloads: Tarball | ZIP archive
Timelines: family | ancestors | descendants | both | wal2
Files: files | file ages | folders
SHA3-256: e2fc5c814cf6862d536aacb9eca66ecd31ba7e3e3033fa4c5564d533f4a18dfc
User & Date: dan 2017-10-04 20:57:14.949
Context
2017-10-05
18:14
Fix test case failures on this branch. (check-in: 16decc13af user: dan tags: wal2)
2017-10-04
20:57
Add experimental mode that uses two wal files. Activated using "PRAGMA journal_mode = wal2". (check-in: e2fc5c814c user: dan tags: wal2)
18:26
Updates to requirements marks. (check-in: 40964a4ef7 user: drh tags: trunk)
Changes
Unified Diff Ignore Whitespace Patch
Changes to src/btree.c.
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
    if( page1[18]>1 ){
      pBt->btsFlags |= BTS_READ_ONLY;
    }
    if( page1[19]>1 ){
      goto page1_init_failed;
    }
#else
    if( page1[18]>2 ){
      pBt->btsFlags |= BTS_READ_ONLY;
    }
    if( page1[19]>2 ){
      goto page1_init_failed;
    }

    /* If the write version is set to 2, this database should be accessed
    ** in WAL mode. If the log is not already open, open it now. Then 
    ** return SQLITE_OK and return without populating BtShared.pPage1.
    ** The caller detects this and calls this function again. This is
    ** required as the version of page 1 currently in the page1 buffer
    ** may not be the latest version - there may be a newer one in the log
    ** file.
    */
    if( page1[19]==2 && (pBt->btsFlags & BTS_NO_WAL)==0 ){
      int isOpen = 0;
      rc = sqlite3PagerOpenWal(pBt->pPager, &isOpen);
      if( rc!=SQLITE_OK ){
        goto page1_init_failed;
      }else{
        setDefaultSyncFlag(pBt, SQLITE_DEFAULT_WAL_SYNCHRONOUS+1);
        if( isOpen==0 ){
          releasePageOne(pPage1);
          return SQLITE_OK;







|


|











|

|







2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
    if( page1[18]>1 ){
      pBt->btsFlags |= BTS_READ_ONLY;
    }
    if( page1[19]>1 ){
      goto page1_init_failed;
    }
#else
    if( page1[18]>3 ){
      pBt->btsFlags |= BTS_READ_ONLY;
    }
    if( page1[19]>3 ){
      goto page1_init_failed;
    }

    /* If the write version is set to 2, this database should be accessed
    ** in WAL mode. If the log is not already open, open it now. Then 
    ** return SQLITE_OK and return without populating BtShared.pPage1.
    ** The caller detects this and calls this function again. This is
    ** required as the version of page 1 currently in the page1 buffer
    ** may not be the latest version - there may be a newer one in the log
    ** file.
    */
    if( page1[19]>=2 && (pBt->btsFlags & BTS_NO_WAL)==0 ){
      int isOpen = 0;
      rc = sqlite3PagerOpenWal(pBt->pPager, (page1[19]==3), &isOpen);
      if( rc!=SQLITE_OK ){
        goto page1_init_failed;
      }else{
        setDefaultSyncFlag(pBt, SQLITE_DEFAULT_WAL_SYNCHRONOUS+1);
        if( isOpen==0 ){
          releasePageOne(pPage1);
          return SQLITE_OK;
9862
9863
9864
9865
9866
9867
9868
9869
9870
9871
9872
9873
9874
9875
9876
** "write version" (single byte at byte offset 19) fields in the database
** header to iVersion.
*/
int sqlite3BtreeSetVersion(Btree *pBtree, int iVersion){
  BtShared *pBt = pBtree->pBt;
  int rc;                         /* Return code */
 
  assert( iVersion==1 || iVersion==2 );

  /* If setting the version fields to 1, do not automatically open the
  ** WAL connection, even if the version fields are currently set to 2.
  */
  pBt->btsFlags &= ~BTS_NO_WAL;
  if( iVersion==1 ) pBt->btsFlags |= BTS_NO_WAL;








|







9862
9863
9864
9865
9866
9867
9868
9869
9870
9871
9872
9873
9874
9875
9876
** "write version" (single byte at byte offset 19) fields in the database
** header to iVersion.
*/
int sqlite3BtreeSetVersion(Btree *pBtree, int iVersion){
  BtShared *pBt = pBtree->pBt;
  int rc;                         /* Return code */
 
  assert( iVersion==1 || iVersion==2 || iVersion==3 );

  /* If setting the version fields to 1, do not automatically open the
  ** WAL connection, even if the version fields are currently set to 2.
  */
  pBt->btsFlags &= ~BTS_NO_WAL;
  if( iVersion==1 ) pBt->btsFlags |= BTS_NO_WAL;

Changes to src/os_unix.c.
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
  int rc = SQLITE_OK;    /* Result code form fcntl() */

  /* Access to the unixShmNode object is serialized by the caller */
  pShmNode = pFile->pInode->pShmNode;
  assert( sqlite3_mutex_held(pShmNode->mutex) || pShmNode->nRef==0 );

  /* Shared locks never span more than one byte */
  assert( n==1 || lockType!=F_RDLCK );

  /* Locks are within range */
  assert( n>=1 && n<=SQLITE_SHM_NLOCK );

  if( pShmNode->h>=0 ){
    /* Initialize the locking parameters */
    memset(&f, 0, sizeof(f));







|







4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
  int rc = SQLITE_OK;    /* Result code form fcntl() */

  /* Access to the unixShmNode object is serialized by the caller */
  pShmNode = pFile->pInode->pShmNode;
  assert( sqlite3_mutex_held(pShmNode->mutex) || pShmNode->nRef==0 );

  /* Shared locks never span more than one byte */
  /* assert( n==1 || lockType!=F_RDLCK ); */

  /* Locks are within range */
  assert( n>=1 && n<=SQLITE_SHM_NLOCK );

  if( pShmNode->h>=0 ){
    /* Initialize the locking parameters */
    memset(&f, 0, sizeof(f));
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
  assert( pShmNode->pInode==pDbFd->pInode );
  assert( ofst>=0 && ofst+n<=SQLITE_SHM_NLOCK );
  assert( n>=1 );
  assert( flags==(SQLITE_SHM_LOCK | SQLITE_SHM_SHARED)
       || flags==(SQLITE_SHM_LOCK | SQLITE_SHM_EXCLUSIVE)
       || flags==(SQLITE_SHM_UNLOCK | SQLITE_SHM_SHARED)
       || flags==(SQLITE_SHM_UNLOCK | SQLITE_SHM_EXCLUSIVE) );
  assert( n==1 || (flags & SQLITE_SHM_EXCLUSIVE)!=0 );
  assert( pShmNode->h>=0 || pDbFd->pInode->bProcessLock==1 );
  assert( pShmNode->h<0 || pDbFd->pInode->bProcessLock==0 );

  mask = (1<<(ofst+n)) - (1<<ofst);
  assert( n>1 || mask==(1<<ofst) );
  sqlite3_mutex_enter(pShmNode->mutex);
  if( flags & SQLITE_SHM_UNLOCK ){







|







4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
  assert( pShmNode->pInode==pDbFd->pInode );
  assert( ofst>=0 && ofst+n<=SQLITE_SHM_NLOCK );
  assert( n>=1 );
  assert( flags==(SQLITE_SHM_LOCK | SQLITE_SHM_SHARED)
       || flags==(SQLITE_SHM_LOCK | SQLITE_SHM_EXCLUSIVE)
       || flags==(SQLITE_SHM_UNLOCK | SQLITE_SHM_SHARED)
       || flags==(SQLITE_SHM_UNLOCK | SQLITE_SHM_EXCLUSIVE) );
  /* assert( n==1 || (flags & SQLITE_SHM_EXCLUSIVE)!=0 ); */
  assert( pShmNode->h>=0 || pDbFd->pInode->bProcessLock==1 );
  assert( pShmNode->h<0 || pDbFd->pInode->bProcessLock==0 );

  mask = (1<<(ofst+n)) - (1<<ofst);
  assert( n>1 || mask==(1<<ofst) );
  sqlite3_mutex_enter(pShmNode->mutex);
  if( flags & SQLITE_SHM_UNLOCK ){
Changes to src/pager.c.
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
#endif

/*
** The maximum legal page number is (2^31 - 1).
*/
#define PAGER_MAX_PGNO 2147483647

/*
** The argument to this macro is a file descriptor (type sqlite3_file*).
** Return 0 if it is not open, or non-zero (but not 1) if it is.
**
** This is so that expressions can be written as:
**
**   if( isOpen(pPager->jfd) ){ ...
**
** instead of
**
**   if( pPager->jfd->pMethods ){ ...
*/
#define isOpen(pFd) ((pFd)->pMethods!=0)

/*
** Return true if this pager uses a write-ahead log to read page pgno.
** Return false if the pager reads pgno directly from the database.
*/
#if !defined(SQLITE_OMIT_WAL) && defined(SQLITE_DIRECT_OVERFLOW_READ)
int sqlite3PagerUseWal(Pager *pPager, Pgno pgno){
  u32 iRead = 0;







<
<
<
<
<
<
<
<
<
<
<
<
<
<







806
807
808
809
810
811
812














813
814
815
816
817
818
819
#endif

/*
** The maximum legal page number is (2^31 - 1).
*/
#define PAGER_MAX_PGNO 2147483647















/*
** Return true if this pager uses a write-ahead log to read page pgno.
** Return false if the pager reads pgno directly from the database.
*/
#if !defined(SQLITE_OMIT_WAL) && defined(SQLITE_DIRECT_OVERFLOW_READ)
int sqlite3PagerUseWal(Pager *pPager, Pgno pgno){
  u32 iRead = 0;
940
941
942
943
944
945
946

947
948
949
950
951
952
953
954
955
956
957
958
959
960

961
962
963
964
965
966
967
968
969
970
971
972

973
974
975
976
977
978
979
        ** a rollback transaction that switches from journal_mode=off
        ** to journal_mode=wal.
        */
        assert( p->eLock>=RESERVED_LOCK );
        assert( isOpen(p->jfd) 
             || p->journalMode==PAGER_JOURNALMODE_OFF 
             || p->journalMode==PAGER_JOURNALMODE_WAL 

        );
      }
      assert( pPager->dbOrigSize==pPager->dbFileSize );
      assert( pPager->dbOrigSize==pPager->dbHintSize );
      break;

    case PAGER_WRITER_DBMOD:
      assert( p->eLock==EXCLUSIVE_LOCK );
      assert( pPager->errCode==SQLITE_OK );
      assert( !pagerUseWal(pPager) );
      assert( p->eLock>=EXCLUSIVE_LOCK );
      assert( isOpen(p->jfd) 
           || p->journalMode==PAGER_JOURNALMODE_OFF 
           || p->journalMode==PAGER_JOURNALMODE_WAL 

           || (sqlite3OsDeviceCharacteristics(p->fd)&SQLITE_IOCAP_BATCH_ATOMIC)
      );
      assert( pPager->dbOrigSize<=pPager->dbHintSize );
      break;

    case PAGER_WRITER_FINISHED:
      assert( p->eLock==EXCLUSIVE_LOCK );
      assert( pPager->errCode==SQLITE_OK );
      assert( !pagerUseWal(pPager) );
      assert( isOpen(p->jfd) 
           || p->journalMode==PAGER_JOURNALMODE_OFF 
           || p->journalMode==PAGER_JOURNALMODE_WAL 

           || (sqlite3OsDeviceCharacteristics(p->fd)&SQLITE_IOCAP_BATCH_ATOMIC)
      );
      break;

    case PAGER_ERROR:
      /* There must be at least one outstanding reference to the pager if
      ** in ERROR state. Otherwise the pager should have already dropped







>














>












>







926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
        ** a rollback transaction that switches from journal_mode=off
        ** to journal_mode=wal.
        */
        assert( p->eLock>=RESERVED_LOCK );
        assert( isOpen(p->jfd) 
             || p->journalMode==PAGER_JOURNALMODE_OFF 
             || p->journalMode==PAGER_JOURNALMODE_WAL 
             || p->journalMode==PAGER_JOURNALMODE_WAL2
        );
      }
      assert( pPager->dbOrigSize==pPager->dbFileSize );
      assert( pPager->dbOrigSize==pPager->dbHintSize );
      break;

    case PAGER_WRITER_DBMOD:
      assert( p->eLock==EXCLUSIVE_LOCK );
      assert( pPager->errCode==SQLITE_OK );
      assert( !pagerUseWal(pPager) );
      assert( p->eLock>=EXCLUSIVE_LOCK );
      assert( isOpen(p->jfd) 
           || p->journalMode==PAGER_JOURNALMODE_OFF 
           || p->journalMode==PAGER_JOURNALMODE_WAL 
           || p->journalMode==PAGER_JOURNALMODE_WAL2
           || (sqlite3OsDeviceCharacteristics(p->fd)&SQLITE_IOCAP_BATCH_ATOMIC)
      );
      assert( pPager->dbOrigSize<=pPager->dbHintSize );
      break;

    case PAGER_WRITER_FINISHED:
      assert( p->eLock==EXCLUSIVE_LOCK );
      assert( pPager->errCode==SQLITE_OK );
      assert( !pagerUseWal(pPager) );
      assert( isOpen(p->jfd) 
           || p->journalMode==PAGER_JOURNALMODE_OFF 
           || p->journalMode==PAGER_JOURNALMODE_WAL 
           || p->journalMode==PAGER_JOURNALMODE_WAL2
           || (sqlite3OsDeviceCharacteristics(p->fd)&SQLITE_IOCAP_BATCH_ATOMIC)
      );
      break;

    case PAGER_ERROR:
      /* There must be at least one outstanding reference to the pager if
      ** in ERROR state. Otherwise the pager should have already dropped
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080

2081
2082
2083
2084
2085
2086
2087
          ** https://bugzilla.mozilla.org/show_bug.cgi?id=1072773
          */
          rc = sqlite3OsSync(pPager->jfd, pPager->syncFlags);
        }
      }
      pPager->journalOff = 0;
    }else if( pPager->journalMode==PAGER_JOURNALMODE_PERSIST
      || (pPager->exclusiveMode && pPager->journalMode!=PAGER_JOURNALMODE_WAL)
    ){
      rc = zeroJournalHdr(pPager, hasMaster||pPager->tempFile);
      pPager->journalOff = 0;
    }else{
      /* This branch may be executed with Pager.journalMode==MEMORY if
      ** a hot-journal was just rolled back. In this case the journal
      ** file should be closed and deleted. If this connection writes to
      ** the database file, it will do so using an in-memory journal.
      */
      int bDelete = !pPager->tempFile;
      assert( sqlite3JournalIsInMemory(pPager->jfd)==0 );
      assert( pPager->journalMode==PAGER_JOURNALMODE_DELETE 
           || pPager->journalMode==PAGER_JOURNALMODE_MEMORY 
           || pPager->journalMode==PAGER_JOURNALMODE_WAL 

      );
      sqlite3OsClose(pPager->jfd);
      if( bDelete ){
        rc = sqlite3OsDelete(pPager->pVfs, pPager->zJournal, pPager->extraSync);
      }
    }
  }







|













|
>







2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
          ** https://bugzilla.mozilla.org/show_bug.cgi?id=1072773
          */
          rc = sqlite3OsSync(pPager->jfd, pPager->syncFlags);
        }
      }
      pPager->journalOff = 0;
    }else if( pPager->journalMode==PAGER_JOURNALMODE_PERSIST
      || (pPager->exclusiveMode && pPager->journalMode<PAGER_JOURNALMODE_WAL)
    ){
      rc = zeroJournalHdr(pPager, hasMaster||pPager->tempFile);
      pPager->journalOff = 0;
    }else{
      /* This branch may be executed with Pager.journalMode==MEMORY if
      ** a hot-journal was just rolled back. In this case the journal
      ** file should be closed and deleted. If this connection writes to
      ** the database file, it will do so using an in-memory journal.
      */
      int bDelete = !pPager->tempFile;
      assert( sqlite3JournalIsInMemory(pPager->jfd)==0 );
      assert( pPager->journalMode==PAGER_JOURNALMODE_DELETE 
           || pPager->journalMode==PAGER_JOURNALMODE_MEMORY 
           || pPager->journalMode==PAGER_JOURNALMODE_WAL
           || pPager->journalMode==PAGER_JOURNALMODE_WAL2
      );
      sqlite3OsClose(pPager->jfd);
      if( bDelete ){
        rc = sqlite3OsDelete(pPager->pVfs, pPager->zJournal, pPager->extraSync);
      }
    }
  }
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356

        rc = pagerPagecount(pPager, &nPage);
        if( rc ) return rc;
        if( nPage==0 ){
          rc = sqlite3OsDelete(pPager->pVfs, pPager->zWal, 0);
        }else{
          testcase( sqlite3PcachePagecount(pPager->pPCache)==0 );
          rc = sqlite3PagerOpenWal(pPager, 0);
        }
      }else if( pPager->journalMode==PAGER_JOURNALMODE_WAL ){
        pPager->journalMode = PAGER_JOURNALMODE_DELETE;
      }
    }
  }
  return rc;
}
#endif







|

|







3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346

        rc = pagerPagecount(pPager, &nPage);
        if( rc ) return rc;
        if( nPage==0 ){
          rc = sqlite3OsDelete(pPager->pVfs, pPager->zWal, 0);
        }else{
          testcase( sqlite3PcachePagecount(pPager->pPCache)==0 );
          rc = sqlite3PagerOpenWal(pPager, 0, 0);
        }
      }else if( pPager->journalMode>=PAGER_JOURNALMODE_WAL ){
        pPager->journalMode = PAGER_JOURNALMODE_DELETE;
      }
    }
  }
  return rc;
}
#endif
7241
7242
7243
7244
7245
7246
7247

7248
7249
7250
7251
7252
7253
7254

  /* The eMode parameter is always valid */
  assert(      eMode==PAGER_JOURNALMODE_DELETE
            || eMode==PAGER_JOURNALMODE_TRUNCATE
            || eMode==PAGER_JOURNALMODE_PERSIST
            || eMode==PAGER_JOURNALMODE_OFF 
            || eMode==PAGER_JOURNALMODE_WAL 

            || eMode==PAGER_JOURNALMODE_MEMORY );

  /* This routine is only called from the OP_JournalMode opcode, and
  ** the logic there will never allow a temporary file to be changed
  ** to WAL mode.
  */
  assert( pPager->tempFile==0 || eMode!=PAGER_JOURNALMODE_WAL );







>







7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245

  /* The eMode parameter is always valid */
  assert(      eMode==PAGER_JOURNALMODE_DELETE
            || eMode==PAGER_JOURNALMODE_TRUNCATE
            || eMode==PAGER_JOURNALMODE_PERSIST
            || eMode==PAGER_JOURNALMODE_OFF 
            || eMode==PAGER_JOURNALMODE_WAL 
            || eMode==PAGER_JOURNALMODE_WAL2
            || eMode==PAGER_JOURNALMODE_MEMORY );

  /* This routine is only called from the OP_JournalMode opcode, and
  ** the logic there will never allow a temporary file to be changed
  ** to WAL mode.
  */
  assert( pPager->tempFile==0 || eMode!=PAGER_JOURNALMODE_WAL );
7275
7276
7277
7278
7279
7280
7281

7282
7283
7284


7285
7286
7287
7288
7289
7290
7291
    */
    assert( (PAGER_JOURNALMODE_TRUNCATE & 5)==1 );
    assert( (PAGER_JOURNALMODE_PERSIST & 5)==1 );
    assert( (PAGER_JOURNALMODE_DELETE & 5)==0 );
    assert( (PAGER_JOURNALMODE_MEMORY & 5)==4 );
    assert( (PAGER_JOURNALMODE_OFF & 5)==0 );
    assert( (PAGER_JOURNALMODE_WAL & 5)==5 );


    assert( isOpen(pPager->fd) || pPager->exclusiveMode );
    if( !pPager->exclusiveMode && (eOld & 5)==1 && (eMode & 1)==0 ){



      /* In this case we would like to delete the journal file. If it is
      ** not possible, then that is not a problem. Deleting the journal file
      ** here is an optimization only.
      **
      ** Before deleting the journal file, obtain a RESERVED lock on the
      ** database file. This ensures that the journal file is not deleted







>


|
>
>







7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
    */
    assert( (PAGER_JOURNALMODE_TRUNCATE & 5)==1 );
    assert( (PAGER_JOURNALMODE_PERSIST & 5)==1 );
    assert( (PAGER_JOURNALMODE_DELETE & 5)==0 );
    assert( (PAGER_JOURNALMODE_MEMORY & 5)==4 );
    assert( (PAGER_JOURNALMODE_OFF & 5)==0 );
    assert( (PAGER_JOURNALMODE_WAL & 5)==5 );
    assert( (PAGER_JOURNALMODE_WAL2 & 5)==4 );

    assert( isOpen(pPager->fd) || pPager->exclusiveMode );
    if( !pPager->exclusiveMode && (eOld & 5)==1 && (eMode & 1)==0 
     && eMode!=PAGER_JOURNALMODE_WAL2       /* TODO: fix this if possible */
    ){

      /* In this case we would like to delete the journal file. If it is
      ** not possible, then that is not a problem. Deleting the journal file
      ** here is an optimization only.
      **
      ** Before deleting the journal file, obtain a RESERVED lock on the
      ** database file. This ensures that the journal file is not deleted
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474

/*
** Call sqlite3WalOpen() to open the WAL handle. If the pager is in 
** exclusive-locking mode when this function is called, take an EXCLUSIVE
** lock on the database file and use heap-memory to store the wal-index
** in. Otherwise, use the normal shared-memory.
*/
static int pagerOpenWal(Pager *pPager){
  int rc = SQLITE_OK;

  assert( pPager->pWal==0 && pPager->tempFile==0 );
  assert( pPager->eLock==SHARED_LOCK || pPager->eLock==EXCLUSIVE_LOCK );

  /* If the pager is already in exclusive-mode, the WAL module will use 
  ** heap-memory for the wal-index instead of the VFS shared-memory 
  ** implementation. Take the exclusive lock now, before opening the WAL
  ** file, to make sure this is safe.
  */
  if( pPager->exclusiveMode ){
    rc = pagerExclusiveLock(pPager);
  }

  /* Open the connection to the log file. If this operation fails, 
  ** (e.g. due to malloc() failure), return an error code.
  */
  if( rc==SQLITE_OK ){
    rc = sqlite3WalOpen(pPager->pVfs,
        pPager->fd, pPager->zWal, pPager->exclusiveMode,
        pPager->journalSizeLimit, &pPager->pWal
    );
  }
  pagerFixMaplimit(pPager);

  return rc;
}








|




















|







7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468

/*
** Call sqlite3WalOpen() to open the WAL handle. If the pager is in 
** exclusive-locking mode when this function is called, take an EXCLUSIVE
** lock on the database file and use heap-memory to store the wal-index
** in. Otherwise, use the normal shared-memory.
*/
static int pagerOpenWal(Pager *pPager, int bWal2){
  int rc = SQLITE_OK;

  assert( pPager->pWal==0 && pPager->tempFile==0 );
  assert( pPager->eLock==SHARED_LOCK || pPager->eLock==EXCLUSIVE_LOCK );

  /* If the pager is already in exclusive-mode, the WAL module will use 
  ** heap-memory for the wal-index instead of the VFS shared-memory 
  ** implementation. Take the exclusive lock now, before opening the WAL
  ** file, to make sure this is safe.
  */
  if( pPager->exclusiveMode ){
    rc = pagerExclusiveLock(pPager);
  }

  /* Open the connection to the log file. If this operation fails, 
  ** (e.g. due to malloc() failure), return an error code.
  */
  if( rc==SQLITE_OK ){
    rc = sqlite3WalOpen(pPager->pVfs,
        pPager->fd, pPager->zWal, pPager->exclusiveMode,
        pPager->journalSizeLimit, bWal2, &pPager->pWal
    );
  }
  pagerFixMaplimit(pPager);

  return rc;
}

7486
7487
7488
7489
7490
7491
7492

7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
**
** If the pager is open on a temp-file (or in-memory database), or if
** the WAL file is already open, set *pbOpen to 1 and return SQLITE_OK
** without doing anything.
*/
int sqlite3PagerOpenWal(
  Pager *pPager,                  /* Pager object */

  int *pbOpen                     /* OUT: Set to true if call is a no-op */
){
  int rc = SQLITE_OK;             /* Return code */

  assert( assert_pager_state(pPager) );
  assert( pPager->eState==PAGER_OPEN   || pbOpen );
  assert( pPager->eState==PAGER_READER || !pbOpen );
  assert( pbOpen==0 || *pbOpen==0 );
  assert( pbOpen!=0 || (!pPager->tempFile && !pPager->pWal) );

  if( !pPager->tempFile && !pPager->pWal ){
    if( !sqlite3PagerWalSupported(pPager) ) return SQLITE_CANTOPEN;

    /* Close any rollback journal previously open */
    sqlite3OsClose(pPager->jfd);

    rc = pagerOpenWal(pPager);
    if( rc==SQLITE_OK ){
      pPager->journalMode = PAGER_JOURNALMODE_WAL;
      pPager->eState = PAGER_OPEN;
    }
  }else{
    *pbOpen = 1;
  }

  return rc;







>
















|

|







7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
**
** If the pager is open on a temp-file (or in-memory database), or if
** the WAL file is already open, set *pbOpen to 1 and return SQLITE_OK
** without doing anything.
*/
int sqlite3PagerOpenWal(
  Pager *pPager,                  /* Pager object */
  int bWal2,                      /* Open in wal2 mode if not already open */
  int *pbOpen                     /* OUT: Set to true if call is a no-op */
){
  int rc = SQLITE_OK;             /* Return code */

  assert( assert_pager_state(pPager) );
  assert( pPager->eState==PAGER_OPEN   || pbOpen );
  assert( pPager->eState==PAGER_READER || !pbOpen );
  assert( pbOpen==0 || *pbOpen==0 );
  assert( pbOpen!=0 || (!pPager->tempFile && !pPager->pWal) );

  if( !pPager->tempFile && !pPager->pWal ){
    if( !sqlite3PagerWalSupported(pPager) ) return SQLITE_CANTOPEN;

    /* Close any rollback journal previously open */
    sqlite3OsClose(pPager->jfd);

    rc = pagerOpenWal(pPager, bWal2);
    if( rc==SQLITE_OK ){
      pPager->journalMode = bWal2?PAGER_JOURNALMODE_WAL2:PAGER_JOURNALMODE_WAL;
      pPager->eState = PAGER_OPEN;
    }
  }else{
    *pbOpen = 1;
  }

  return rc;
7526
7527
7528
7529
7530
7531
7532
7533


7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
** EXCLUSIVE lock on the database file. If this cannot be obtained, an
** error (SQLITE_BUSY) is returned and the log connection is not closed.
** If successful, the EXCLUSIVE lock is not released before returning.
*/
int sqlite3PagerCloseWal(Pager *pPager, sqlite3 *db){
  int rc = SQLITE_OK;

  assert( pPager->journalMode==PAGER_JOURNALMODE_WAL );



  /* If the log file is not already open, but does exist in the file-system,
  ** it may need to be checkpointed before the connection can switch to
  ** rollback mode. Open it now so this can happen.
  */
  if( !pPager->pWal ){
    int logexists = 0;
    rc = pagerLockDb(pPager, SHARED_LOCK);
    if( rc==SQLITE_OK ){
      rc = sqlite3OsAccess(
          pPager->pVfs, pPager->zWal, SQLITE_ACCESS_EXISTS, &logexists
      );
    }
    if( rc==SQLITE_OK && logexists ){
      rc = pagerOpenWal(pPager);
    }
  }
    
  /* Checkpoint and close the log. Because an EXCLUSIVE lock is held on
  ** the database file, the log and log-summary files will be deleted.
  */
  if( rc==SQLITE_OK && pPager->pWal ){







|
>
>














|







7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
** EXCLUSIVE lock on the database file. If this cannot be obtained, an
** error (SQLITE_BUSY) is returned and the log connection is not closed.
** If successful, the EXCLUSIVE lock is not released before returning.
*/
int sqlite3PagerCloseWal(Pager *pPager, sqlite3 *db){
  int rc = SQLITE_OK;

  assert( pPager->journalMode==PAGER_JOURNALMODE_WAL 
       || pPager->journalMode==PAGER_JOURNALMODE_WAL2
  );

  /* If the log file is not already open, but does exist in the file-system,
  ** it may need to be checkpointed before the connection can switch to
  ** rollback mode. Open it now so this can happen.
  */
  if( !pPager->pWal ){
    int logexists = 0;
    rc = pagerLockDb(pPager, SHARED_LOCK);
    if( rc==SQLITE_OK ){
      rc = sqlite3OsAccess(
          pPager->pVfs, pPager->zWal, SQLITE_ACCESS_EXISTS, &logexists
      );
    }
    if( rc==SQLITE_OK && logexists ){
      rc = pagerOpenWal(pPager, 0);
    }
  }
    
  /* Checkpoint and close the log. Because an EXCLUSIVE lock is held on
  ** the database file, the log and log-summary files will be deleted.
  */
  if( rc==SQLITE_OK && pPager->pWal ){
Changes to src/pager.h.
77
78
79
80
81
82
83

















84
85
86
87
88
89
90
#define PAGER_JOURNALMODE_QUERY     (-1)  /* Query the value of journalmode */
#define PAGER_JOURNALMODE_DELETE      0   /* Commit by deleting journal file */
#define PAGER_JOURNALMODE_PERSIST     1   /* Commit by zeroing journal header */
#define PAGER_JOURNALMODE_OFF         2   /* Journal omitted.  */
#define PAGER_JOURNALMODE_TRUNCATE    3   /* Commit by truncating journal */
#define PAGER_JOURNALMODE_MEMORY      4   /* In-memory journal file */
#define PAGER_JOURNALMODE_WAL         5   /* Use write-ahead logging */


















/*
** Flags that make up the mask passed to sqlite3PagerGet().
*/
#define PAGER_GET_NOCONTENT     0x01  /* Do not load data from disk */
#define PAGER_GET_READONLY      0x02  /* Read-only page is acceptable */








>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
#define PAGER_JOURNALMODE_QUERY     (-1)  /* Query the value of journalmode */
#define PAGER_JOURNALMODE_DELETE      0   /* Commit by deleting journal file */
#define PAGER_JOURNALMODE_PERSIST     1   /* Commit by zeroing journal header */
#define PAGER_JOURNALMODE_OFF         2   /* Journal omitted.  */
#define PAGER_JOURNALMODE_TRUNCATE    3   /* Commit by truncating journal */
#define PAGER_JOURNALMODE_MEMORY      4   /* In-memory journal file */
#define PAGER_JOURNALMODE_WAL         5   /* Use write-ahead logging */
#define PAGER_JOURNALMODE_WAL2        6   /* Use write-ahead logging mode 2 */

#define isWalMode(x) ((x)==PAGER_JOURNALMODE_WAL || (x)==PAGER_JOURNALMODE_WAL2)

/*
** The argument to this macro is a file descriptor (type sqlite3_file*).
** Return 0 if it is not open, or non-zero (but not 1) if it is.
**
** This is so that expressions can be written as:
**
**   if( isOpen(pPager->jfd) ){ ...
**
** instead of
**
**   if( pPager->jfd->pMethods ){ ...
*/
#define isOpen(pFd) ((pFd)->pMethods!=0)

/*
** Flags that make up the mask passed to sqlite3PagerGet().
*/
#define PAGER_GET_NOCONTENT     0x01  /* Do not load data from disk */
#define PAGER_GET_READONLY      0x02  /* Read-only page is acceptable */

173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
int sqlite3PagerSavepoint(Pager *pPager, int op, int iSavepoint);
int sqlite3PagerSharedLock(Pager *pPager);

#ifndef SQLITE_OMIT_WAL
  int sqlite3PagerCheckpoint(Pager *pPager, sqlite3*, int, int*, int*);
  int sqlite3PagerWalSupported(Pager *pPager);
  int sqlite3PagerWalCallback(Pager *pPager);
  int sqlite3PagerOpenWal(Pager *pPager, int *pisOpen);
  int sqlite3PagerCloseWal(Pager *pPager, sqlite3*);
# ifdef SQLITE_DIRECT_OVERFLOW_READ
  int sqlite3PagerUseWal(Pager *pPager, Pgno);
# endif
# ifdef SQLITE_ENABLE_SNAPSHOT
  int sqlite3PagerSnapshotGet(Pager *pPager, sqlite3_snapshot **ppSnapshot);
  int sqlite3PagerSnapshotOpen(Pager *pPager, sqlite3_snapshot *pSnapshot);







|







190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
int sqlite3PagerSavepoint(Pager *pPager, int op, int iSavepoint);
int sqlite3PagerSharedLock(Pager *pPager);

#ifndef SQLITE_OMIT_WAL
  int sqlite3PagerCheckpoint(Pager *pPager, sqlite3*, int, int*, int*);
  int sqlite3PagerWalSupported(Pager *pPager);
  int sqlite3PagerWalCallback(Pager *pPager);
  int sqlite3PagerOpenWal(Pager *pPager, int, int *pisOpen);
  int sqlite3PagerCloseWal(Pager *pPager, sqlite3*);
# ifdef SQLITE_DIRECT_OVERFLOW_READ
  int sqlite3PagerUseWal(Pager *pPager, Pgno);
# endif
# ifdef SQLITE_ENABLE_SNAPSHOT
  int sqlite3PagerSnapshotGet(Pager *pPager, sqlite3_snapshot **ppSnapshot);
  int sqlite3PagerSnapshotOpen(Pager *pPager, sqlite3_snapshot *pSnapshot);
Changes to src/pragma.c.
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271

272
273
274
275
276
277
278
** defined in pager.h. This function returns the associated lowercase
** journal-mode name.
*/
const char *sqlite3JournalModename(int eMode){
  static char * const azModeName[] = {
    "delete", "persist", "off", "truncate", "memory"
#ifndef SQLITE_OMIT_WAL
     , "wal"
#endif
  };
  assert( PAGER_JOURNALMODE_DELETE==0 );
  assert( PAGER_JOURNALMODE_PERSIST==1 );
  assert( PAGER_JOURNALMODE_OFF==2 );
  assert( PAGER_JOURNALMODE_TRUNCATE==3 );
  assert( PAGER_JOURNALMODE_MEMORY==4 );
  assert( PAGER_JOURNALMODE_WAL==5 );

  assert( eMode>=0 && eMode<=ArraySize(azModeName) );

  if( eMode==ArraySize(azModeName) ) return 0;
  return azModeName[eMode];
}

/*







|








>







256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
** defined in pager.h. This function returns the associated lowercase
** journal-mode name.
*/
const char *sqlite3JournalModename(int eMode){
  static char * const azModeName[] = {
    "delete", "persist", "off", "truncate", "memory"
#ifndef SQLITE_OMIT_WAL
     , "wal", "wal2"
#endif
  };
  assert( PAGER_JOURNALMODE_DELETE==0 );
  assert( PAGER_JOURNALMODE_PERSIST==1 );
  assert( PAGER_JOURNALMODE_OFF==2 );
  assert( PAGER_JOURNALMODE_TRUNCATE==3 );
  assert( PAGER_JOURNALMODE_MEMORY==4 );
  assert( PAGER_JOURNALMODE_WAL==5 );
  assert( PAGER_JOURNALMODE_WAL2==6 );
  assert( eMode>=0 && eMode<=ArraySize(azModeName) );

  if( eMode==ArraySize(azModeName) ) return 0;
  return azModeName[eMode];
}

/*
Changes to src/vdbe.c.
6321
6322
6323
6324
6325
6326
6327

6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353





6354




6355
6356
6357
6358
6359
6360
6361
6362
6363
6364

6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384

6385
6386


6387
6388
6389
6390
6391
6392
6393
  eNew = pOp->p3;
  assert( eNew==PAGER_JOURNALMODE_DELETE 
       || eNew==PAGER_JOURNALMODE_TRUNCATE 
       || eNew==PAGER_JOURNALMODE_PERSIST 
       || eNew==PAGER_JOURNALMODE_OFF
       || eNew==PAGER_JOURNALMODE_MEMORY
       || eNew==PAGER_JOURNALMODE_WAL

       || eNew==PAGER_JOURNALMODE_QUERY
  );
  assert( pOp->p1>=0 && pOp->p1<db->nDb );
  assert( p->readOnly==0 );

  pBt = db->aDb[pOp->p1].pBt;
  pPager = sqlite3BtreePager(pBt);
  eOld = sqlite3PagerGetJournalMode(pPager);
  if( eNew==PAGER_JOURNALMODE_QUERY ) eNew = eOld;
  if( !sqlite3PagerOkToChangeJournalMode(pPager) ) eNew = eOld;

#ifndef SQLITE_OMIT_WAL
  zFilename = sqlite3PagerFilename(pPager, 1);

  /* Do not allow a transition to journal_mode=WAL for a database
  ** in temporary storage or if the VFS does not support shared memory 
  */
  if( eNew==PAGER_JOURNALMODE_WAL
   && (sqlite3Strlen30(zFilename)==0           /* Temp file */
       || !sqlite3PagerWalSupported(pPager))   /* No shared-memory support */
  ){
    eNew = eOld;
  }

  if( (eNew!=eOld)
   && (eOld==PAGER_JOURNALMODE_WAL || eNew==PAGER_JOURNALMODE_WAL)





  ){




    if( !db->autoCommit || db->nVdbeRead>1 ){
      rc = SQLITE_ERROR;
      sqlite3VdbeError(p,
          "cannot change %s wal mode from within a transaction",
          (eNew==PAGER_JOURNALMODE_WAL ? "into" : "out of")
      );
      goto abort_due_to_error;
    }else{
 
      if( eOld==PAGER_JOURNALMODE_WAL ){

        /* If leaving WAL mode, close the log file. If successful, the call
        ** to PagerCloseWal() checkpoints and deletes the write-ahead-log 
        ** file. An EXCLUSIVE lock may still be held on the database file 
        ** after a successful return. 
        */
        rc = sqlite3PagerCloseWal(pPager, db);
        if( rc==SQLITE_OK ){
          sqlite3PagerSetJournalMode(pPager, eNew);
        }
      }else if( eOld==PAGER_JOURNALMODE_MEMORY ){
        /* Cannot transition directly from MEMORY to WAL.  Use mode OFF
        ** as an intermediate */
        sqlite3PagerSetJournalMode(pPager, PAGER_JOURNALMODE_OFF);
      }
  
      /* Open a transaction on the database file. Regardless of the journal
      ** mode, this transaction always uses a rollback journal.
      */
      assert( sqlite3BtreeIsInTrans(pBt)==0 );
      if( rc==SQLITE_OK ){

        rc = sqlite3BtreeSetVersion(pBt, (eNew==PAGER_JOURNALMODE_WAL ? 2 : 1));
      }


    }
  }
#endif /* ifndef SQLITE_OMIT_WAL */

  if( rc ) eNew = eOld;
  eNew = sqlite3PagerSetJournalMode(pPager, eNew);








>

















|






|
|
>
>
>
>
>
|
>
>
>
>







<
|
|
>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
>
|
<
>
>







6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371

6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396

6397
6398
6399
6400
6401
6402
6403
6404
6405
  eNew = pOp->p3;
  assert( eNew==PAGER_JOURNALMODE_DELETE 
       || eNew==PAGER_JOURNALMODE_TRUNCATE 
       || eNew==PAGER_JOURNALMODE_PERSIST 
       || eNew==PAGER_JOURNALMODE_OFF
       || eNew==PAGER_JOURNALMODE_MEMORY
       || eNew==PAGER_JOURNALMODE_WAL
       || eNew==PAGER_JOURNALMODE_WAL2
       || eNew==PAGER_JOURNALMODE_QUERY
  );
  assert( pOp->p1>=0 && pOp->p1<db->nDb );
  assert( p->readOnly==0 );

  pBt = db->aDb[pOp->p1].pBt;
  pPager = sqlite3BtreePager(pBt);
  eOld = sqlite3PagerGetJournalMode(pPager);
  if( eNew==PAGER_JOURNALMODE_QUERY ) eNew = eOld;
  if( !sqlite3PagerOkToChangeJournalMode(pPager) ) eNew = eOld;

#ifndef SQLITE_OMIT_WAL
  zFilename = sqlite3PagerFilename(pPager, 1);

  /* Do not allow a transition to journal_mode=WAL for a database
  ** in temporary storage or if the VFS does not support shared memory 
  */
  if( isWalMode(eNew)
   && (sqlite3Strlen30(zFilename)==0           /* Temp file */
       || !sqlite3PagerWalSupported(pPager))   /* No shared-memory support */
  ){
    eNew = eOld;
  }

  if( eNew!=eOld && (isWalMode(eNew) || isWalMode(eOld)) ){

    /* Prevent changing directly to wal2 from wal mode. And vice versa. */
    if( isWalMode(eNew) && isWalMode(eOld) ){
      rc = SQLITE_ERROR;
      sqlite3VdbeError(p, "cannot change from %s to %s mode",
          sqlite3JournalModename(eOld), sqlite3JournalModename(eNew)
      );
      goto abort_due_to_error;
    }

    /* Prevent switching into or out of wal/wal2 mode mid-transaction */
    if( !db->autoCommit || db->nVdbeRead>1 ){
      rc = SQLITE_ERROR;
      sqlite3VdbeError(p,
          "cannot change %s wal mode from within a transaction",
          (eNew==PAGER_JOURNALMODE_WAL ? "into" : "out of")
      );
      goto abort_due_to_error;

    }
 
    if( isWalMode(eOld) ){
      /* If leaving WAL mode, close the log file. If successful, the call
      ** to PagerCloseWal() checkpoints and deletes the write-ahead-log 
      ** file. An EXCLUSIVE lock may still be held on the database file 
      ** after a successful return. 
      */
      rc = sqlite3PagerCloseWal(pPager, db);
      if( rc==SQLITE_OK ){
        sqlite3PagerSetJournalMode(pPager, eNew);
      }
    }else if( eOld==PAGER_JOURNALMODE_MEMORY ){
      /* Cannot transition directly from MEMORY to WAL.  Use mode OFF
      ** as an intermediate */
      sqlite3PagerSetJournalMode(pPager, PAGER_JOURNALMODE_OFF);
    }

    /* Open a transaction on the database file. Regardless of the journal
    ** mode, this transaction always uses a rollback journal.
    */
    assert( sqlite3BtreeIsInTrans(pBt)==0 );
    if( rc==SQLITE_OK ){
      /* 1==rollback, 2==wal, 3==wal2 */
      rc = sqlite3BtreeSetVersion(pBt, 

          1 + isWalMode(eNew) + (eNew==PAGER_JOURNALMODE_WAL2)
      );
    }
  }
#endif /* ifndef SQLITE_OMIT_WAL */

  if( rc ) eNew = eOld;
  eNew = sqlite3PagerSetJournalMode(pPager, eNew);

Changes to src/wal.c.
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284





























285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303






304
305
306
307
308
309
310
311
312
313
314
315
316
317
318





































319
320
321
322
323
324
325
int sqlite3WalTrace = 0;
# define WALTRACE(X)  if(sqlite3WalTrace) sqlite3DebugPrintf X
#else
# define WALTRACE(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

/*
** Indices of various locking bytes.   WAL_NREADER is the number
** of available reader locks and should be at least 3.  The default
** is SQLITE_SHM_NLOCK==8 and  WAL_NREADER==5.
*/
#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)































/* 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 followed by one instance of the WalCkptInfo object.
** For all versions of SQLite through 3.10.0 and probably beyond,
** the locking bytes (WalCkptInfo.aLock) start at offset 120 and
** the total header size is 136 bytes.
**
** The szPage value can be any power of 2 between 512 and 32768, inclusive.
** Or it can be 1 to represent a 65536-byte page.  The latter case was
** added in 3.7.1 when support for 64K pages was added.  






*/
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. 1==64K */
  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







|
|
|
|
|
|

|
|
<
|

|
|













>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>



















>
>
>
>
>
>



|




|






>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266

267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
int sqlite3WalTrace = 0;
# define WALTRACE(X)  if(sqlite3WalTrace) sqlite3DebugPrintf X
#else
# define WALTRACE(X)
#endif

/*
** Both the wal-file and the wal-index contain version fields 
** indicating the current version of the system. If a client
** reads the header of a wal file (as part of recovery), or the
** wal-index (as part of opening a read transaction) and (a) the
** header checksum is correct but (b) the version field is not
** recognized, the operation fails with SQLITE_CANTOPEN.
**
** Currently, clients support both version-1 ("journal_mode=wal") and
** version-2 ("journal_mode=wal2"). Legacy clients may support version-1

** only.
*/
#define WAL_VERSION1 3007000      /* For "journal_mode=wal" */
#define WAL_VERSION2 3021000      /* For "journal_mode=wal2" */

/*
** Indices of various locking bytes.   WAL_NREADER is the number
** of available reader locks and should be at least 3.  The default
** is SQLITE_SHM_NLOCK==8 and  WAL_NREADER==5.
*/
#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)

/*
** Values that may be stored in Wal.readLock in wal2 mode.
**
** In wal mode, the Wal.readLock member is set to -1 when no read-lock
** is held, or else is the index of the read-mark on which a lock is
** held.
**
** In wal2 mode, Wal.readLock must be set to one of the following values.
** A value of -1 still indicates that no read-lock is held, but the other
** values are symbolic. See the implementation of walLockReader() for
** details of how the symbols map to OS level locks.
*/
#define WAL_LOCK_NONE        -1
#define WAL_LOCK_PART1        1
#define WAL_LOCK_PART1_FULL2  2
#define WAL_LOCK_PART2        3
#define WAL_LOCK_PART2_FULL1  4

/* 
** This constant is used in wal2 mode only.
**
** In wal2 mode, when committing a transaction, if the current wal file 
** is sufficiently large and there are no conflicting locks held, the
** writer writes the new transaction into the start of the other wal
** file. Usually, "sufficiently large" is defined by the value configured
** using "PRAGMA journal_size_limit". However, if no such value has been
** configured, sufficiently large defaults to WAL_DEFAULT_WALSIZE frames.
*/
#define WAL_DEFAULT_WALSIZE 1000

/* 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 followed by one instance of the WalCkptInfo object.
** For all versions of SQLite through 3.10.0 and probably beyond,
** the locking bytes (WalCkptInfo.aLock) start at offset 120 and
** the total header size is 136 bytes.
**
** The szPage value can be any power of 2 between 512 and 32768, inclusive.
** Or it can be 1 to represent a 65536-byte page.  The latter case was
** added in 3.7.1 when support for 64K pages was added.  
**
** WAL2 mode notes: Member variable mxFrame2 is only used in wal2 mode
** (when iVersion is set to WAL_VERSION2). The lower 31 bits store
** the maximum frame number in file *-wal2. The most significant bit
** is a flag - set if clients are currently appending to *-wal2, clear
** otherwise.
*/
struct WalIndexHdr {
  u32 iVersion;                   /* Wal-index version */
  u32 mxFrame2;                   /* See "WAL2 mode notes" above */
  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. 1==64K */
  u32 mxFrame;                    /* Index of last valid frame in each 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 */
};

/*
** The following macros and functions are get/set methods for the maximum
** frame numbers and current wal file values stored in the WalIndexHdr
** structure. These are helpful because of the unorthodox way in which
** the values are stored in wal2 mode (see above). They are equivalent
** to functions with the following signatures.
**
**   u32  walidxGetMxFrame(WalIndexHdr*, int iWal);          // get mxFrame
**   void walidxSetMxFrame(WalIndexHdr*, int iWal, u32 val); // set mxFrame
**   int  walidxGetFile(WalIndexHdr*)                        // get file
**   void walidxSetFile(WalIndexHdr*, int val);              // set file
*/
#define walidxGetMxFrame(pHdr, iWal) \
  ((iWal) ? ((pHdr)->mxFrame2 & 0x7FFFFFF) : (pHdr)->mxFrame)

static void walidxSetMxFrame(WalIndexHdr *pHdr, int iWal, u32 mxFrame){
  if( iWal ){
    pHdr->mxFrame2 = (pHdr->mxFrame2 & 0x80000000) | mxFrame;
  }else{
    pHdr->mxFrame = mxFrame;
  }
  assert( walidxGetMxFrame(pHdr, iWal)==mxFrame );
}

#define walidxGetFile(pHdr) ((pHdr)->mxFrame2 >> 31)

#define walidxSetFile(pHdr, iWal) (                                   \
    (pHdr)->mxFrame2 = ((pHdr)->mxFrame2 & 0x7FFFFFFF) | ((iWal)<<31) \
)

/*
** Argument is a pointer to a Wal structure. Return true if the current
** cache of the wal-index header indicates "journal_mode=wal2" mode, or
** false otherwise.
*/
#define isWalMode2(pWal) ((pWal)->hdr.iVersion==WAL_VERSION2)

/*
** 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
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449

450
451
452
453
454
455
456

457
458
459
460
461
462
463
/*
** 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) */
  i64 mxWalSize;             /* Truncate WAL to this size upon reset */
  int nWiData;               /* Size of array apWiData */
  int szFirstBlock;          /* Size of first block written to WAL file */
  volatile u32 **apWiData;   /* Pointer to wal-index content in memory */
  u32 szPage;                /* Database page size */
  i16 readLock;              /* Which read lock is being held.  -1 for none */
  u8 syncFlags;              /* Flags to use to sync header writes */
  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;               /* WAL_RDWR, WAL_RDONLY, or WAL_SHM_RDONLY */
  u8 truncateOnCommit;       /* True to truncate WAL file on commit */
  u8 syncHeader;             /* Fsync the WAL header if true */
  u8 padToSectorBoundary;    /* Pad transactions out to the next sector */
  WalIndexHdr hdr;           /* Wal-index header for current transaction */
  u32 minFrame;              /* Ignore wal frames before this one */
  u32 iReCksum;              /* On commit, recalculate checksums from here */
  const char *zWalName;      /* Name of WAL file */

  u32 nCkpt;                 /* Checkpoint sequence counter in the wal-header */
#ifdef SQLITE_DEBUG
  u8 lockError;              /* True if a locking error has occurred */
#endif
#ifdef SQLITE_ENABLE_SNAPSHOT
  WalIndexHdr *pSnapshot;    /* Start transaction here if not NULL */
#endif

};

/*
** Candidate values for Wal.exclusiveMode.
*/
#define WAL_NORMAL_MODE     0
#define WAL_EXCLUSIVE_MODE  1     







|



















>







>







494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
/*
** 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 *apWalFd[2];  /* File handle for "*-wal" and "*-wal2" */
  u32 iCallback;             /* Value to pass to log callback (or 0) */
  i64 mxWalSize;             /* Truncate WAL to this size upon reset */
  int nWiData;               /* Size of array apWiData */
  int szFirstBlock;          /* Size of first block written to WAL file */
  volatile u32 **apWiData;   /* Pointer to wal-index content in memory */
  u32 szPage;                /* Database page size */
  i16 readLock;              /* Which read lock is being held.  -1 for none */
  u8 syncFlags;              /* Flags to use to sync header writes */
  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;               /* WAL_RDWR, WAL_RDONLY, or WAL_SHM_RDONLY */
  u8 truncateOnCommit;       /* True to truncate WAL file on commit */
  u8 syncHeader;             /* Fsync the WAL header if true */
  u8 padToSectorBoundary;    /* Pad transactions out to the next sector */
  WalIndexHdr hdr;           /* Wal-index header for current transaction */
  u32 minFrame;              /* Ignore wal frames before this one */
  u32 iReCksum;              /* On commit, recalculate checksums from here */
  const char *zWalName;      /* Name of WAL file */
  char *zWalName2;           /* Name of second WAL file */
  u32 nCkpt;                 /* Checkpoint sequence counter in the wal-header */
#ifdef SQLITE_DEBUG
  u8 lockError;              /* True if a locking error has occurred */
#endif
#ifdef SQLITE_ENABLE_SNAPSHOT
  WalIndexHdr *pSnapshot;    /* Start transaction here if not NULL */
#endif
  int bWal2;                 /* bWal2 flag passed to WalOpen() */
};

/*
** Candidate values for Wal.exclusiveMode.
*/
#define WAL_NORMAL_MODE     0
#define WAL_EXCLUSIVE_MODE  1     
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
*/
static void walIndexWriteHdr(Wal *pWal){
  volatile WalIndexHdr *aHdr = walIndexHdr(pWal);
  const int nCksum = offsetof(WalIndexHdr, aCksum);

  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], (const void*)&pWal->hdr, sizeof(WalIndexHdr));
  walShmBarrier(pWal);
  memcpy((void*)&aHdr[0], (const void*)&pWal->hdr, sizeof(WalIndexHdr));
}

/*







|







736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
*/
static void walIndexWriteHdr(Wal *pWal){
  volatile WalIndexHdr *aHdr = walIndexHdr(pWal);
  const int nCksum = offsetof(WalIndexHdr, aCksum);

  assert( pWal->writeLock );
  pWal->hdr.isInit = 1;
  assert( pWal->hdr.iVersion==WAL_VERSION1||pWal->hdr.iVersion==WAL_VERSION2 );
  walChecksumBytes(1, (u8*)&pWal->hdr, nCksum, 0, pWal->hdr.aCksum);
  memcpy((void*)&aHdr[1], (const void*)&pWal->hdr, sizeof(WalIndexHdr));
  walShmBarrier(pWal);
  memcpy((void*)&aHdr[0], (const void*)&pWal->hdr, sizeof(WalIndexHdr));
}

/*
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
  */
  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]) 







|







814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
  */
  pgno = sqlite3Get4byte(&aFrame[0]);
  if( pgno==0 ){
    return 0;
  }

  /* A frame is only valid if a checksum of the WAL header,
  ** all prior frames, 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]) 
826
827
828
829
830
831
832






























833
834
835
836
837
838
839
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){







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
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));
}

/*
** This function is used to take and release read-locks in wal2 mode.
**
** Use of WAL_READ_LOCK(x) slots for (1<=x<=4).
**
** 1) Partial read of *-wal-1   (blocks checkpointer from checkpointing)
** 2) Full read of *-wal-2      (blocks writer from writing)
** 3) Partial read of *-wal-2   (blocks checkpointer from checkpointing)
** 4) Full read of *-wal-1      (blocks writer from writing)
*/
static int walLockReader(Wal *pWal, int eLock, int bLock){
  int i;                          /* Index of first readmark to lock */
  int n;                          /* Number of readmarks to lock */

  assert( pWal->hdr.iVersion==WAL_VERSION2 );
  if( pWal->exclusiveMode ) return SQLITE_OK;

  switch( eLock ){
    case WAL_LOCK_PART1      : i = 1; n = 1; break; 
    case WAL_LOCK_PART1_FULL2: i = 1; n = 2; break; 
    case WAL_LOCK_PART2      : i = 3; n = 1; break; 
    case WAL_LOCK_PART2_FULL1: i = 3; n = 2; break; 
    default: assert( !"cannot happen" );
  }

  return sqlite3OsShmLock(pWal->pDbFd, WAL_READ_LOCK(i), n,
      SQLITE_SHM_SHARED | (bLock ? SQLITE_SHM_LOCK : SQLITE_SHM_UNLOCK) 
  );
}

/*
** 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){
886
887
888
889
890
891
892





































893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
















910
911
912
913
914
915
916
917
918
919
920




921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940


941








942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000

1001







1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
  
    *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;
  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[] */











  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.
  */
  assert( pWal->nWiData>walFramePage(pWal->hdr.mxFrame) );
  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;
  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);

#ifdef 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 j;           /* Loop counter */
    int iKey;        /* Hash key */
    for(j=1; j<=iLimit; j++){
      for(iKey=walHash(aPgno[j]); aHash[iKey]; iKey=walNextHash(iKey)){
        if( aHash[iKey]==j ) break;
      }
      assert( aHash[iKey]==j );
    }
  }
#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;
    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 proceeding. 
    */
    if( idx==1 ){
      int nByte = (int)((u8 *)&aHash[HASHTABLE_NSLOT] - (u8 *)&aPgno[1]);







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>

















>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>











>
>
>
>




















>
>

>
>
>
>
>
>
>
>

|
|
|

|





|
|
|




|








|
<




















<




|




>
|
>
>
>
>
>
>
>
|









|







989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139

1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159

1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
  
    *paPgno = &aPgno[-1];
    *paHash = aHash;
    *piZero = iZero;
  }
  return rc;
}

static u32 walExternalEncode(int iWal, u32 iFrame){
  u32 iRet;
  if( iWal ){
    iRet = HASHTABLE_NPAGE_ONE + iFrame;
    iRet += ((iFrame-1) / HASHTABLE_NPAGE) * HASHTABLE_NPAGE;
  }else{
    iRet = iFrame;
    iFrame += HASHTABLE_NPAGE - HASHTABLE_NPAGE_ONE;
    iRet += ((iFrame-1) / HASHTABLE_NPAGE) * HASHTABLE_NPAGE;
  }
  return iRet;
}

/*
** Parameter iExternal is an external frame identifier. This function
** transforms it to a wal file number (0 or 1) and frame number within
** this wal file (reported via output parameter *piRead).
*/
static int walExternalDecode(u32 iExternal, u32 *piRead){
  int iHash = (iExternal+HASHTABLE_NPAGE-HASHTABLE_NPAGE_ONE-1)/HASHTABLE_NPAGE;

  if( 0==(iHash & 0x01) ){
    /* A frame in wal file 0 */
    *piRead = (iExternal <= HASHTABLE_NPAGE_ONE) ? iExternal :
      iExternal - (iHash/2) * HASHTABLE_NPAGE;
    return 0;
  }
  if( iHash==0 ){
    *piRead = iExternal;
    return 0;
  }else{
    *piRead = iExternal - HASHTABLE_NPAGE_ONE - ((iHash-1)/2) * HASHTABLE_NPAGE;
  }

  return (iHash % 2);
}

/*
** 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;
  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 index of the hash-table corresponding to frame iFrame of wal
** file iWal.
*/
static int walFramePage2(int iWal, u32 iFrame){
  int iRet;
  assert( iWal==0 || iWal==1 );
  assert( iFrame>0 );
  if( iWal==0 ){
    iRet = 2*((iFrame+HASHTABLE_NPAGE-HASHTABLE_NPAGE_ONE-1)/HASHTABLE_NPAGE);
  }else{
    iRet = 1 + 2 * ((iFrame-1) / HASHTABLE_NPAGE);
  }
  return iRet;
}

/*
** 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];
}

static u32 walFramePgno2(Wal *pWal, int iWal, u32 iFrame){
  return walFramePgno(pWal, walExternalEncode(iWal, iFrame));
}

/*
** 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[] */
  int iWal = walidxGetFile(&pWal->hdr);
  u32 mxFrame = walidxGetMxFrame(&pWal->hdr, iWal);

  u32 iExternal;
  if( isWalMode2(pWal) ){
    iExternal = walExternalEncode(iWal, mxFrame);
  }else{
    assert( iWal==0 );
    iExternal = mxFrame;
  }

  assert( pWal->writeLock );
  testcase( mxFrame==HASHTABLE_NPAGE_ONE-1 );
  testcase( mxFrame==HASHTABLE_NPAGE_ONE );
  testcase( mxFrame==HASHTABLE_NPAGE_ONE+1 );

  if( 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.
  */
  assert( pWal->nWiData>walFramePage(iExternal) );
  assert( pWal->apWiData[walFramePage(iExternal)] );
  walHashGet(pWal, walFramePage(iExternal), &aHash, &aPgno, &iZero);

  /* Zero all hash-table entries that correspond to frame numbers greater
  ** than pWal->hdr.mxFrame.
  */
  iLimit = iExternal - iZero;
  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);

#ifdef 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 j;           /* Loop counter */
    int iKey;        /* Hash key */
    for(j=1; j<=iLimit; j++){
      for(iKey=walHash(aPgno[j]); aHash[iKey]; iKey=walNextHash(iKey)){
        if( aHash[iKey]==j ) break;
      }
      assert( aHash[iKey]==j );
    }
  }
#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, int iWal, 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 */
  u32 iExternal;
  
  if( isWalMode2(pWal) ){
    iExternal = walExternalEncode(iWal, iFrame);
  }else{
    assert( iWal==0 );
    iExternal = iFrame;
  }

  rc = walHashGet(pWal, walFramePage(iExternal), &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 = iExternal - iZero;
    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 proceeding. 
    */
    if( idx==1 ){
      int nByte = (int)((u8 *)&aHash[HASHTABLE_NSLOT] - (u8 *)&aPgno[1]);
1067
1068
1069
1070
1071
1072
1073































































































































1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090




1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112

1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124



1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214










1215






1216

















1217
1218
1219
1220
1221
1222
1223
1224


1225
1226
1227
1228

1229
1230
1231
1232
1233
1234
1235
1236
1237

1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261


1262
1263
1264
1265
1266
1267
1268
#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.
  */
  assert( pWal->ckptLock==1 || pWal->ckptLock==0 );
  assert( WAL_ALL_BUT_WRITE==WAL_WRITE_LOCK+1 );
  assert( WAL_CKPT_LOCK==WAL_ALL_BUT_WRITE );
  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 */
    int isValid;                  /* True if this frame is valid */

    /* 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 = 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_malloc64(szFrame);
    if( !aFrame ){
      rc = SQLITE_NOMEM_BKPT;
      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 */

      /* Read and decode the next log frame. */
      iFrame++;
      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&0xff00) | (szPage>>16));
        testcase( szPage<=32768 );
        testcase( szPage>=65536 );
        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->nBackfillAttempted = pWal->hdr.mxFrame;
    pInfo->aReadMark[0] = 0;
    for(i=1; i<WAL_NREADER; i++) pInfo->aReadMark[i] = READMARK_NOT_USED;
    if( pWal->hdr.mxFrame ) pInfo->aReadMark[1] = pWal->hdr.mxFrame;


    /* If more than one frame was recovered from the log file, report an
    ** event via sqlite3_log(). This is to help with identifying performance
    ** problems caused by applications routinely shutting down without
    ** checkpointing the log file.
    */
    if( pWal->hdr.nPage ){
      sqlite3_log(SQLITE_NOTICE_RECOVER_WAL,
          "recovered %d frames from WAL file %s",

          pWal->hdr.mxFrame, pWal->zWalName
      );
    }
  }

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.
**







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>













<
<


>
>
>
>



















|
|
<
>
|
|
<
|
<
<
<
|
<
<
<
<
>
>
>
|
|
<
|
<
<
<
<
<
|
<
<
|
|
|
<
<
<
<
<
<
<
<
<
<
<
<
<
|
<
<
<
<
<
<
<
<
<
|
|
|
|
|
<
<
<
|
<
<
|
|
<
<
<
<
|
<
<
<
<
<
|
<
<
<
|
<
<
|
|
<
<
<
|
|
<
<
<
<
<


|
<
|
<
<


|
>
>
>
>
>
>
>
>
>
>
|
>
>
>
>
>
>
|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>




|
<

|
>
>
|
|
|
|
>




|
<


|
>
|




<






|











>
>







1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389


1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416

1417
1418
1419

1420



1421




1422
1423
1424
1425
1426

1427





1428


1429
1430
1431













1432









1433
1434
1435
1436
1437



1438


1439
1440




1441





1442



1443


1444
1445



1446
1447





1448
1449
1450

1451


1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494

1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508

1509
1510
1511
1512
1513
1514
1515
1516
1517

1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
#endif /* SQLITE_ENABLE_EXPENSIVE_ASSERT */
  }


  return rc;
}

/*
** Recover a single wal file - *-wal if iWal==0, or *-wal2 if iWal==1.
*/
static int walIndexRecoverOne(Wal *pWal, int iWal, u32 *pnCkpt, int *pbZero){
  i64 nSize;                      /* Size of log file */
  u32 aFrameCksum[2] = {0, 0};
  int rc;
  sqlite3_file *pWalFd = pWal->apWalFd[iWal];

  assert( iWal==0 || iWal==1 );

  memset(&pWal->hdr, 0, sizeof(WalIndexHdr));
  sqlite3_randomness(8, pWal->hdr.aSalt);

  rc = sqlite3OsFileSize(pWalFd, &nSize);
  if( rc==SQLITE_OK ){
    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 */
      int isValid;                  /* True if this frame is valid */
  
      /* Read in the WAL header. */
      rc = sqlite3OsRead(pWalFd, aBuf, WAL_HDRSIZE, 0);
      if( rc!=SQLITE_OK ){
        return rc;
      }
  
      /* 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 
      ){
        return SQLITE_OK;
      }
      pWal->hdr.bigEndCksum = (u8)(magic&0x00000001);
      pWal->szPage = szPage;
  
      /* 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])
      ){
        return SQLITE_OK;
      }
  
      memcpy(&pWal->hdr.aSalt, &aBuf[16], 8);
      *pnCkpt = sqlite3Get4byte(&aBuf[12]);
  
      /* Verify that the version number on the WAL format is one that
      ** are able to understand */
      version = sqlite3Get4byte(&aBuf[4]);
      if( version!=WAL_VERSION1 && version!=WAL_VERSION2 ){
        return SQLITE_CANTOPEN_BKPT;
      }
      pWal->hdr.iVersion = version;
  
      /* Malloc a buffer to read frames into. */
      szFrame = szPage + WAL_FRAME_HDRSIZE;
      aFrame = (u8 *)sqlite3_malloc64(szFrame);
      if( !aFrame ){
        return SQLITE_NOMEM_BKPT;
      }
      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 */
  
        /* Read and decode the next log frame. */
        iFrame++;
        rc = sqlite3OsRead(pWalFd, aFrame, szFrame, iOffset);
        if( rc!=SQLITE_OK ) break;
        isValid = walDecodeFrame(pWal, &pgno, &nTruncate, aData, aFrame);
        if( !isValid ) break;
        rc = walIndexAppend(pWal, iWal, 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&0xff00) | (szPage>>16));
          testcase( szPage<=32768 );
          testcase( szPage>=65536 );
          aFrameCksum[0] = pWal->hdr.aFrameCksum[0];
          aFrameCksum[1] = pWal->hdr.aFrameCksum[1];
        }
      }
  
      sqlite3_free(aFrame);
    }else if( pbZero && nSize==0 ){
      *pbZero = 1;
    }
  }

  pWal->hdr.aFrameCksum[0] = aFrameCksum[0];
  pWal->hdr.aFrameCksum[1] = aFrameCksum[1];

  return rc;
}

static int walOpenWal2(Wal *pWal){
  int rc = SQLITE_OK;
  if( !isOpen(pWal->apWalFd[1]) ){
    int f = (SQLITE_OPEN_READWRITE|SQLITE_OPEN_CREATE|SQLITE_OPEN_WAL);
    rc = sqlite3OsOpen(pWal->pVfs, pWal->zWalName2, pWal->apWalFd[1], f, &f);
  }
  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 */


  int iLock;                      /* Lock offset to lock for checkpoint */
  int nLock;                      /* Number of locks to hold */
  u32 nCkpt1 = 0xFFFFFFFF;
  u32 nCkpt2 = 0xFFFFFFFF;
  int bZero = 0;
  WalIndexHdr hdr;

  /* 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.
  */
  assert( pWal->ckptLock==1 || pWal->ckptLock==0 );
  assert( WAL_ALL_BUT_WRITE==WAL_WRITE_LOCK+1 );
  assert( WAL_CKPT_LOCK==WAL_ALL_BUT_WRITE );
  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));

  /* Recover the *-wal file. If a valid version-1 header is recovered
  ** from it, do not open the *-wal2 file. Even if it exists.

  **
  ** Otherwise, if the *-wal2 file exists or if the "wal2" flag was 
  ** specified when sqlite3WalOpen() was called, open and recover

  ** the *-wal2 file. Except, if the *-wal file was zero bytes in size,



  ** truncate the *-wal2 to zero bytes in size.




  **
  ** After this block has run, if the *-wal2 file is open the system
  ** starts up in VERSION2 mode. In this case pWal->hdr contains the 
  ** wal-index header considering only *-wal2. Stack variable hdr
  ** contains the wal-index header considering only *-wal. The hash 

  ** tables are populated for both.  





  **


  ** Or, if the *-wal2 file is not open, start up in VERSION1 mode.
  ** pWal->hdr is already populated.
  */













  rc = walIndexRecoverOne(pWal, 0, &nCkpt1, &bZero);









  assert( pWal->hdr.iVersion==0 
      || pWal->hdr.iVersion==WAL_VERSION1 
      || pWal->hdr.iVersion==WAL_VERSION2 
  );
  if( rc==SQLITE_OK && pWal->hdr.iVersion!=WAL_VERSION1 ){



    int bOpen = 1;


    sqlite3_vfs *pVfs = pWal->pVfs;
    if( pWal->hdr.iVersion==0 && pWal->bWal2==0 ){




      rc = sqlite3OsAccess(pVfs, pWal->zWalName2, SQLITE_ACCESS_EXISTS, &bOpen);





    }



    if( rc==SQLITE_OK && bOpen ){


      rc = walOpenWal2(pWal);
      if( rc==SQLITE_OK ){



        hdr = pWal->hdr;
        rc = walIndexRecoverOne(pWal, 1, &nCkpt2, 0);





      }
    }
  }




  if( rc==SQLITE_OK ){
    volatile WalCkptInfo *pInfo;

    if( isOpen(pWal->apWalFd[1]) ){
      /* The case where *-wal2 may follow *-wal */
      if( nCkpt2<=0x0F && nCkpt2==nCkpt1+1 ){
        if( sqlite3Get4byte((u8*)(&pWal->hdr.aSalt[0]))==hdr.aFrameCksum[0]
            && sqlite3Get4byte((u8*)(&pWal->hdr.aSalt[1]))==hdr.aFrameCksum[1]
          ){
          walidxSetFile(&pWal->hdr, 1);
          walidxSetMxFrame(&pWal->hdr, 1, pWal->hdr.mxFrame);
          walidxSetMxFrame(&pWal->hdr, 0, hdr.mxFrame);
        }else{
          pWal->hdr = hdr;
        }
      }else

      /* When *-wal may follow *-wal2 */
      if( (nCkpt2==0x0F && nCkpt1==0) || (nCkpt2<0x0F && nCkpt2==nCkpt1-1) ){
        if( sqlite3Get4byte((u8*)(&hdr.aSalt[0]))==pWal->hdr.aFrameCksum[0]
         && sqlite3Get4byte((u8*)(&hdr.aSalt[1]))==pWal->hdr.aFrameCksum[1]
        ){
          SWAP(WalIndexHdr, pWal->hdr, hdr);
          walidxSetMxFrame(&pWal->hdr, 1, hdr.mxFrame);
        }
      }else

      /* Fallback */
      if( nCkpt1<=nCkpt2 ){
        pWal->hdr = hdr;
      }else{
        walidxSetFile(&pWal->hdr, 1);
      }
      pWal->hdr.iVersion = WAL_VERSION2;
    }else{
      pWal->hdr.iVersion = WAL_VERSION1;
    }

    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);
    memset((void*)pInfo, 0, sizeof(WalCkptInfo));
    if( 0==isWalMode2(pWal) ){
      int i;
      pInfo->nBackfillAttempted = pWal->hdr.mxFrame;
      pInfo->aReadMark[0] = 0;
      for(i=1; i<WAL_NREADER; i++) pInfo->aReadMark[i] = READMARK_NOT_USED;
      if( pWal->hdr.mxFrame ) pInfo->aReadMark[1] = pWal->hdr.mxFrame;
    }

    /* If more than one frame was recovered from the log file, report an
    ** event via sqlite3_log(). This is to help with identifying performance
    ** problems caused by applications routinely shutting down without
    ** checkpointing the log file.  */

    if( pWal->hdr.nPage ){
      sqlite3_log(SQLITE_NOTICE_RECOVER_WAL,
          "recovered (%d,%d) frames from WAL files %s[2] (%s mode)",
          walidxGetMxFrame(&pWal->hdr, 0), walidxGetMxFrame(&pWal->hdr, 1), 
          pWal->zWalName, isWalMode2(pWal) ? "wal2" : "wal"
      );
    }
  }


  WALTRACE(("WAL%p: recovery %s\n", pWal, rc ? "failed" : "ok"));
  walUnlockExclusive(pWal, iLock, nLock);
  return rc;
}

/*
** Close an open wal-index and wal files.
*/
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);
  }
  sqlite3OsClose(pWal->apWalFd[0]);
  sqlite3OsClose(pWal->apWalFd[1]);
}

/* 
** 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.
**
1278
1279
1280
1281
1282
1283
1284

1285
1286
1287
1288
1289


1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308


1309
1310
1311
1312
1313
1314
1315
1316
1317
1318

1319
1320
1321
1322
1323
1324
1325

1326





1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
*/
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 */
  i64 mxWalSize,                  /* Truncate WAL to this size on reset */

  Wal **ppWal                     /* OUT: Allocated Wal handle */
){
  int rc;                         /* Return Code */
  Wal *pRet;                      /* Object to allocate and return */
  int flags;                      /* Flags passed to OsOpen() */



  assert( zWalName && zWalName[0] );
  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.
  ** For that matter, if the lock offset ever changes from its initial design
  ** value of 120, we need to know that so there is an assert() to check it.
  */
  assert( 120==WALINDEX_LOCK_OFFSET );
  assert( 136==WALINDEX_HDR_SIZE );
#ifdef WIN_SHM_BASE
  assert( WIN_SHM_BASE==WALINDEX_LOCK_OFFSET );
#endif
#ifdef UNIX_SHM_BASE
  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_BKPT;
  }

  pRet->pVfs = pVfs;
  pRet->pWalFd = (sqlite3_file *)&pRet[1];

  pRet->pDbFd = pDbFd;
  pRet->readLock = -1;
  pRet->mxWalSize = mxWalSize;
  pRet->zWalName = zWalName;
  pRet->syncHeader = 1;
  pRet->padToSectorBoundary = 1;
  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 = WAL_RDONLY;
  }

  if( rc!=SQLITE_OK ){
    walIndexClose(pRet, 0);
    sqlite3OsClose(pRet->pWalFd);
    sqlite3_free(pRet);
  }else{
    int iDC = sqlite3OsDeviceCharacteristics(pDbFd);
    if( iDC & SQLITE_IOCAP_SEQUENTIAL ){ pRet->syncHeader = 0; }
    if( iDC & SQLITE_IOCAP_POWERSAFE_OVERWRITE ){
      pRet->padToSectorBoundary = 0;
    }







>





>
>



















>
>



|





|
>

|





>

>
>
>
>
>
|

|






<







1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623

1624
1625
1626
1627
1628
1629
1630
*/
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 */
  i64 mxWalSize,                  /* Truncate WAL to this size on reset */
  int bWal2,                      /* True to open in wal2 mode */
  Wal **ppWal                     /* OUT: Allocated Wal handle */
){
  int rc;                         /* Return Code */
  Wal *pRet;                      /* Object to allocate and return */
  int flags;                      /* Flags passed to OsOpen() */
  int nWalName;                   /* Length of zWalName in bytes */
  int nByte;                      /* Bytes of space to allocate */

  assert( zWalName && zWalName[0] );
  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.
  ** For that matter, if the lock offset ever changes from its initial design
  ** value of 120, we need to know that so there is an assert() to check it.
  */
  assert( 120==WALINDEX_LOCK_OFFSET );
  assert( 136==WALINDEX_HDR_SIZE );
#ifdef WIN_SHM_BASE
  assert( WIN_SHM_BASE==WALINDEX_LOCK_OFFSET );
#endif
#ifdef UNIX_SHM_BASE
  assert( UNIX_SHM_BASE==WALINDEX_LOCK_OFFSET );
#endif

  nWalName = sqlite3Strlen30(zWalName);
  nByte = sizeof(Wal) + pVfs->szOsFile*2 + nWalName+2;

  /* Allocate an instance of struct Wal to return. */
  *ppWal = 0;
  pRet = (Wal*)sqlite3MallocZero(nByte);
  if( !pRet ){
    return SQLITE_NOMEM_BKPT;
  }

  pRet->pVfs = pVfs;
  pRet->apWalFd[0] = (sqlite3_file*)((char*)pRet+sizeof(Wal));
  pRet->apWalFd[1] = (sqlite3_file*)((char*)pRet+sizeof(Wal)+pVfs->szOsFile);
  pRet->pDbFd = pDbFd;
  pRet->readLock = WAL_LOCK_NONE;
  pRet->mxWalSize = mxWalSize;
  pRet->zWalName = zWalName;
  pRet->syncHeader = 1;
  pRet->padToSectorBoundary = 1;
  pRet->exclusiveMode = (bNoShm ? WAL_HEAPMEMORY_MODE: WAL_NORMAL_MODE);
  pRet->bWal2 = bWal2;

  pRet->zWalName2 = (char*)pRet + sizeof(Wal) + 2*pVfs->szOsFile;
  memcpy(pRet->zWalName2, zWalName, nWalName);
  pRet->zWalName2[nWalName] = '2';
  pRet->zWalName2[nWalName+1] = '\0';

  /* Open a file handle on the first write-ahead log file. */
  flags = (SQLITE_OPEN_READWRITE|SQLITE_OPEN_CREATE|SQLITE_OPEN_WAL);
  rc = sqlite3OsOpen(pVfs, zWalName, pRet->apWalFd[0], flags, &flags);
  if( rc==SQLITE_OK && flags&SQLITE_OPEN_READONLY ){
    pRet->readOnly = WAL_RDONLY;
  }

  if( rc!=SQLITE_OK ){
    walIndexClose(pRet, 0);

    sqlite3_free(pRet);
  }else{
    int iDC = sqlite3OsDeviceCharacteristics(pDbFd);
    if( iDC & SQLITE_IOCAP_SEQUENTIAL ){ pRet->syncHeader = 0; }
    if( iDC & SQLITE_IOCAP_POWERSAFE_OVERWRITE ){
      pRet->padToSectorBoundary = 0;
    }
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561

1562
1563



1564
1565
1566
1567

1568
1569




1570


1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602

1603








1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
}

/*
** 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
** lock.
**
** 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).
  */

  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 *)sqlite3_malloc64(nByte);
  if( !p ){
    return SQLITE_NOMEM_BKPT;
  }
  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 *)sqlite3_malloc64(
      sizeof(ht_slot) * (iLast>HASHTABLE_NPAGE?HASHTABLE_NPAGE:iLast)
  );
  if( !aTmp ){
    rc = SQLITE_NOMEM_BKPT;
  }

  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;
    }
  }
  sqlite3_free(aTmp);

  if( rc!=SQLITE_OK ){
    walIteratorFree(p);
  }







|
|
|




|





>


>
>
>




>
|
|
>
>
>
>
|
>
>

<




















|

|


|




>

>
>
>
>
>
>
>
>

|











|
|
|
|







1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869

1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
}

/*
** 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
** lock.
**
** On success, make *pp point to the newly allocated WalIterator object
** and return SQLITE_OK. Otherwise, return an error code. If this routine
** returns an error, the final 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, int iWal, 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 */
  int iLastSeg;                   /* Last hash table to iterate though */
  ht_slot *aTmp;                  /* Temp space used by merge-sort */
  int rc = SQLITE_OK;             /* Return Code */
  int iMode = isWalMode2(pWal) ? 2 : 1;

  assert( isWalMode2(pWal) || iWal==0 );

  /* This routine only runs while holding the checkpoint lock. And
  ** it only runs if there is actually content in the log (mxFrame>0).
  */
  iLast = walidxGetMxFrame(&pWal->hdr, iWal);
  assert( pWal->ckptLock && iLast>0 );

  if( iMode==2 ){
    iLastSeg = walFramePage2(iWal, iLast);
  }else{
    iLastSeg = walFramePage(iLast);
  }
  nSegment = 1 + (iLastSeg/iMode);

  /* Allocate space for the WalIterator object. */

  nByte = sizeof(WalIterator) 
        + (nSegment-1)*sizeof(struct WalSegment)
        + iLast*sizeof(ht_slot);
  p = (WalIterator *)sqlite3_malloc64(nByte);
  if( !p ){
    return SQLITE_NOMEM_BKPT;
  }
  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 *)sqlite3_malloc64(
      sizeof(ht_slot) * (iLast>HASHTABLE_NPAGE?HASHTABLE_NPAGE:iLast)
  );
  if( !aTmp ){
    rc = SQLITE_NOMEM_BKPT;
  }

  for(i=iWal; rc==SQLITE_OK && i<=iLastSeg; i+=iMode){
    volatile ht_slot *aHash;
    u32 iExtZero;
    volatile u32 *aPgno;

    rc = walHashGet(pWal, i, &aHash, &aPgno, &iExtZero);
    if( rc==SQLITE_OK ){
      int j;                      /* Counter variable */
      int nEntry;                 /* Number of entries in this segment */
      ht_slot *aIndex;            /* Sorted index for this segment */
      u32 iZero;

      if( iMode==2 ){
        walExternalDecode(iExtZero+1, &iZero);
        iZero--;
        assert( iZero==0 || i>=2 );
      }else{
        iZero = iExtZero;
      }

      aPgno++;
      if( i==iLastSeg ){
        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/iMode].iZero = iZero;
      p->aSegment[i/iMode].nEntry = nEntry;
      p->aSegment[i/iMode].aIndex = aIndex;
      p->aSegment[i/iMode].aPgno = (u32 *)aPgno;
    }
  }
  sqlite3_free(aTmp);

  if( rc!=SQLITE_OK ){
    walIteratorFree(p);
  }
1674
1675
1676
1677
1678
1679
1680

1681
1682
1683
1684
1685
1686
1687
** new wal-index header. It should be passed a pseudo-random value (i.e. 
** one obtained from sqlite3_randomness()).
*/
static void walRestartHdr(Wal *pWal, u32 salt1){
  volatile WalCkptInfo *pInfo = walCkptInfo(pWal);
  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]));
  memcpy(&pWal->hdr.aSalt[1], &salt1, 4);
  walIndexWriteHdr(pWal);
  pInfo->nBackfill = 0;
  pInfo->nBackfillAttempted = 0;







>







1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
** new wal-index header. It should be passed a pseudo-random value (i.e. 
** one obtained from sqlite3_randomness()).
*/
static void walRestartHdr(Wal *pWal, u32 salt1){
  volatile WalCkptInfo *pInfo = walCkptInfo(pWal);
  int i;                          /* Loop counter */
  u32 *aSalt = pWal->hdr.aSalt;   /* Big-endian salt values */
  assert( isWalMode2(pWal)==0 );
  pWal->nCkpt++;
  pWal->hdr.mxFrame = 0;
  sqlite3Put4byte((u8*)&aSalt[0], 1 + sqlite3Get4byte((u8*)&aSalt[0]));
  memcpy(&pWal->hdr.aSalt[1], &salt1, 4);
  walIndexWriteHdr(pWal);
  pInfo->nBackfill = 0;
  pInfo->nBackfillAttempted = 0;
1735
1736
1737
1738
1739
1740
1741


1742

1743
1744
1745
1746

1747



1748








1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759

1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791

1792
1793
1794
1795
1796
1797

1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817

1818


1819
1820
1821
1822
1823

1824
1825
1826



1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841

1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
  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 */
  u32 mxPage;                     /* Max database page to write */
  int i;                          /* Loop counter */
  volatile WalCkptInfo *pInfo;    /* The checkpoint status information */




  szPage = walPagesize(pWal);
  testcase( szPage<=32768 );
  testcase( szPage>=65536 );
  pInfo = walCkptInfo(pWal);

  if( pInfo->nBackfill<pWal->hdr.mxFrame ){












    /* Allocate the iterator */
    rc = walIteratorInit(pWal, &pIter);
    if( rc!=SQLITE_OK ){
      return rc;
    }
    assert( pIter );

    /* EVIDENCE-OF: R-62920-47450 The busy-handler callback is never invoked
    ** in the SQLITE_CHECKPOINT_PASSIVE mode. */
    assert( eMode!=SQLITE_CHECKPOINT_PASSIVE || xBusy==0 );


    /* 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;
    mxPage = pWal->hdr.nPage;
    for(i=1; i<WAL_NREADER; i++){
      /* Thread-sanitizer reports that the following is an unsafe read,
      ** as some other thread may be in the process of updating the value
      ** of the aReadMark[] slot. The assumption here is that if that is
      ** happening, the other client may only be increasing the value,
      ** not decreasing it. So assuming either that either the "old" or
      ** "new" version of the value is read, and not some arbitrary value
      ** that would never be written by a real client, things are still 
      ** safe.  */
      u32 y = pInfo->aReadMark[i];
      if( mxSafeFrame>y ){
        assert( y<=pWal->hdr.mxFrame );
        rc = walBusyLock(pWal, xBusy, pBusyArg, WAL_READ_LOCK(i), 1);
        if( rc==SQLITE_OK ){
          pInfo->aReadMark[i] = (i==1 ? mxSafeFrame : READMARK_NOT_USED);
          walUnlockExclusive(pWal, WAL_READ_LOCK(i), 1);
        }else if( rc==SQLITE_BUSY ){
          mxSafeFrame = y;
          xBusy = 0;
        }else{
          goto walcheckpoint_out;
        }
      }
    }


    if( pInfo->nBackfill<mxSafeFrame
     && (rc = walBusyLock(pWal, xBusy, pBusyArg, WAL_READ_LOCK(0),1))==SQLITE_OK
    ){
      i64 nSize;                    /* Current size of database file */
      u32 nBackfill = pInfo->nBackfill;


      pInfo->nBackfillAttempted = mxSafeFrame;

      /* Sync the WAL to disk */
      rc = sqlite3OsSync(pWal->pWalFd, CKPT_SYNC_FLAGS(sync_flags));

      /* If the database may grow as a result of this checkpoint, hint
      ** about the eventual size of the db file to the VFS layer.
      */
      if( rc==SQLITE_OK ){
        i64 nReq = ((i64)mxPage * szPage);
        rc = sqlite3OsFileSize(pWal->pDbFd, &nSize);
        if( rc==SQLITE_OK && nSize<nReq ){
          sqlite3OsFileControlHint(pWal->pDbFd, SQLITE_FCNTL_SIZE_HINT, &nReq);
        }
      }


      /* Iterate through the contents of the WAL, copying data to the db file */
      while( rc==SQLITE_OK && 0==walIteratorNext(pIter, &iDbpage, &iFrame) ){
        i64 iOffset;

        assert( walFramePgno(pWal, iFrame)==iDbpage );


        if( db->u1.isInterrupted ){
          rc = db->mallocFailed ? SQLITE_NOMEM_BKPT : SQLITE_INTERRUPT;
          break;
        }
        if( iFrame<=nBackfill || iFrame>mxSafeFrame || iDbpage>mxPage ){

          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 ){
            rc = sqlite3OsSync(pWal->pDbFd, CKPT_SYNC_FLAGS(sync_flags));
          }
        }
        if( rc==SQLITE_OK ){
          pInfo->nBackfill = mxSafeFrame;
        }
      }

      /* Release the reader lock held while backfilling */
      walUnlockExclusive(pWal, WAL_READ_LOCK(0), 1);
    }

    if( rc==SQLITE_BUSY ){
      /* Reset the return code so as not to report a checkpoint failure
      ** just because there are active readers.  */
      rc = SQLITE_OK;
    }
  }

  /* If this is an SQLITE_CHECKPOINT_RESTART or TRUNCATE operation, and the
  ** entire wal file has been copied into the database file, then block 
  ** until all readers have finished using the wal file. This ensures that 
  ** the next process to write to the database restarts the wal file.
  */
  if( rc==SQLITE_OK && eMode!=SQLITE_CHECKPOINT_PASSIVE ){
    assert( pWal->writeLock );
    if( pInfo->nBackfill<pWal->hdr.mxFrame ){
      rc = SQLITE_BUSY;
    }else if( eMode>=SQLITE_CHECKPOINT_RESTART ){
      u32 salt1;
      sqlite3_randomness(4, &salt1);
      assert( pInfo->nBackfill==pWal->hdr.mxFrame );







>
>

>




>
|
>
>
>

>
>
>
>
>
>
>
>

|









>
|
|
|
|

<
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
>
|

|



>


|
|


|
<








<



>
|
>
>





>



>
>
>

|







|
|
|
|
|
|
>
|
|
|
<
|
|
|
|
<

|














|







2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087

2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128

2129
2130
2131
2132
2133
2134
2135
2136

2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174

2175
2176
2177
2178

2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
  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 */
  u32 mxPage;                     /* Max database page to write */
  int i;                          /* Loop counter */
  volatile WalCkptInfo *pInfo;    /* The checkpoint status information */
  int bWal2 = isWalMode2(pWal);   /* True for wal2 connections */
  int iCkpt = bWal2 ? !walidxGetFile(&pWal->hdr) : 0;

  mxSafeFrame = walidxGetMxFrame(&pWal->hdr, iCkpt);
  szPage = walPagesize(pWal);
  testcase( szPage<=32768 );
  testcase( szPage>=65536 );
  pInfo = walCkptInfo(pWal);
  if( (bWal2==1 && pInfo->nBackfill==0 && mxSafeFrame) 
   || (bWal2==0 && pInfo->nBackfill<mxSafeFrame) 
  ){
    sqlite3_file *pWalFd = pWal->apWalFd[iCkpt];
    mxPage = pWal->hdr.nPage;

    /* If this is a wal2 system, check for a reader holding a lock 
    ** preventing this checkpoint operation. If one is found, return
    ** early.  */
    if( bWal2 ){
      rc = walLockExclusive(pWal, WAL_READ_LOCK(1 + iCkpt*2), 1);
      if( rc!=SQLITE_OK ) return rc;
    }

    /* Allocate the iterator */
    rc = walIteratorInit(pWal, iCkpt, &pIter);
    if( rc!=SQLITE_OK ){
      return rc;
    }
    assert( pIter );

    /* EVIDENCE-OF: R-62920-47450 The busy-handler callback is never invoked
    ** in the SQLITE_CHECKPOINT_PASSIVE mode. */
    assert( eMode!=SQLITE_CHECKPOINT_PASSIVE || xBusy==0 );


    /* If this is a wal system (not wal2), 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.
    */

    if( bWal2==0 ){
      for(i=1; i<WAL_NREADER; i++){
        /* Thread-sanitizer reports that the following is an unsafe read,
        ** as some other thread may be in the process of updating the value
        ** of the aReadMark[] slot. The assumption here is that if that is
        ** happening, the other client may only be increasing the value,
        ** not decreasing it. So assuming either that either the "old" or
        ** "new" version of the value is read, and not some arbitrary value
        ** that would never be written by a real client, things are still 
        ** safe.  */
        u32 y = pInfo->aReadMark[i];
        if( mxSafeFrame>y ){
          assert( y<=pWal->hdr.mxFrame );
          rc = walBusyLock(pWal, xBusy, pBusyArg, WAL_READ_LOCK(i), 1);
          if( rc==SQLITE_OK ){
            pInfo->aReadMark[i] = (i==1 ? mxSafeFrame : READMARK_NOT_USED);
            walUnlockExclusive(pWal, WAL_READ_LOCK(i), 1);
          }else if( rc==SQLITE_BUSY ){
            mxSafeFrame = y;
            xBusy = 0;
          }else{
            goto walcheckpoint_out;
          }
        }
      }
    }

    if( bWal2 || (pInfo->nBackfill<mxSafeFrame
     && (rc = walBusyLock(pWal, xBusy, pBusyArg, WAL_READ_LOCK(0),1))==SQLITE_OK
    )){
      i64 nSize;                    /* Current size of database file */
      u32 nBackfill = pInfo->nBackfill;

      assert( bWal2==0 || nBackfill==0 );
      pInfo->nBackfillAttempted = mxSafeFrame;

      /* Sync the wal file being checkpointed to disk */
      rc = sqlite3OsSync(pWalFd, CKPT_SYNC_FLAGS(sync_flags));

      /* If the database may grow as a result of this checkpoint, hint
      ** about the eventual size of the db file to the VFS layer.  */

      if( rc==SQLITE_OK ){
        i64 nReq = ((i64)mxPage * szPage);
        rc = sqlite3OsFileSize(pWal->pDbFd, &nSize);
        if( rc==SQLITE_OK && nSize<nReq ){
          sqlite3OsFileControlHint(pWal->pDbFd, SQLITE_FCNTL_SIZE_HINT, &nReq);
        }
      }


      /* Iterate through the contents of the WAL, copying data to the db file */
      while( rc==SQLITE_OK && 0==walIteratorNext(pIter, &iDbpage, &iFrame) ){
        i64 iOffset;

        assert( bWal2==1 || walFramePgno(pWal, iFrame)==iDbpage );
        assert( bWal2==0 || walFramePgno2(pWal, iCkpt, iFrame)==iDbpage );

        if( db->u1.isInterrupted ){
          rc = db->mallocFailed ? SQLITE_NOMEM_BKPT : SQLITE_INTERRUPT;
          break;
        }
        if( iFrame<=nBackfill || iFrame>mxSafeFrame || iDbpage>mxPage ){
          assert( bWal2==0 || iDbpage>mxPage );
          continue;
        }
        iOffset = walFrameOffset(iFrame, szPage) + WAL_FRAME_HDRSIZE;
        WALTRACE(("WAL%p: checkpoint frame %d of wal %d to db page %d\n",
              pWal, (int)iFrame, iCkpt, (int)iDbpage
        ));
        /* testcase( IS_BIG_INT(iOffset) ); // requires a 4GiB WAL file */
        rc = sqlite3OsRead(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;
      }

      /* Truncate the db file, sync the wal file and set the WalCkptInfo
      ** flag to indicate that it has been checkpointed. */
      if( !bWal2 && rc==SQLITE_OK && 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 ){
        rc = sqlite3OsSync(pWal->pDbFd, CKPT_SYNC_FLAGS(sync_flags));
      }

      if( rc==SQLITE_OK ){
        pInfo->nBackfill = bWal2 ? 1 : mxSafeFrame;
      }


      /* Release the reader lock held while backfilling */
      walUnlockExclusive(pWal, WAL_READ_LOCK(bWal2 ? 1 + iCkpt*2 : 0), 1);
    }

    if( rc==SQLITE_BUSY ){
      /* Reset the return code so as not to report a checkpoint failure
      ** just because there are active readers.  */
      rc = SQLITE_OK;
    }
  }

  /* If this is an SQLITE_CHECKPOINT_RESTART or TRUNCATE operation, and the
  ** entire wal file has been copied into the database file, then block 
  ** until all readers have finished using the wal file. This ensures that 
  ** the next process to write to the database restarts the wal file.
  */
  if( bWal2==0 && rc==SQLITE_OK && eMode!=SQLITE_CHECKPOINT_PASSIVE ){
    assert( pWal->writeLock );
    if( pInfo->nBackfill<pWal->hdr.mxFrame ){
      rc = SQLITE_BUSY;
    }else if( eMode>=SQLITE_CHECKPOINT_RESTART ){
      u32 salt1;
      sqlite3_randomness(4, &salt1);
      assert( pInfo->nBackfill==pWal->hdr.mxFrame );
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908

1909
1910
1911
1912
1913
1914
1915
1916
1917
1918

1919
1920
1921
1922
1923
1924
1925
          ** writer clients should see that the entire log file has been
          ** checkpointed and behave accordingly. This seems unsafe though,
          ** as it would leave the system in a state where the contents of
          ** the wal-index header do not match the contents of the 
          ** file-system. To avoid this, update the wal-index header to
          ** indicate that the log file contains zero valid frames.  */
          walRestartHdr(pWal, salt1);
          rc = sqlite3OsTruncate(pWal->pWalFd, 0);
        }
        walUnlockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1);
      }
    }
  }

 walcheckpoint_out:
  walIteratorFree(pIter);
  return rc;
}

/*
** If the WAL file is currently larger than nMax bytes in size, truncate
** it to exactly nMax bytes. If an error occurs while doing so, ignore it.
*/
static void walLimitSize(Wal *pWal, i64 nMax){

  i64 sz;
  int rx;
  sqlite3BeginBenignMalloc();
  rx = sqlite3OsFileSize(pWal->pWalFd, &sz);
  if( rx==SQLITE_OK && (sz > nMax ) ){
    rx = sqlite3OsTruncate(pWal->pWalFd, nMax);
  }
  sqlite3EndBenignMalloc();
  if( rx ){
    sqlite3_log(rx, "cannot limit WAL size: %s", pWal->zWalName);

  }
}

/*
** Close a connection to a log file.
*/
int sqlite3WalClose(







|
















>
|
|
|
|
|
|
|
|
|
|
>







2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
          ** writer clients should see that the entire log file has been
          ** checkpointed and behave accordingly. This seems unsafe though,
          ** as it would leave the system in a state where the contents of
          ** the wal-index header do not match the contents of the 
          ** file-system. To avoid this, update the wal-index header to
          ** indicate that the log file contains zero valid frames.  */
          walRestartHdr(pWal, salt1);
          rc = sqlite3OsTruncate(pWal->apWalFd[0], 0);
        }
        walUnlockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1);
      }
    }
  }

 walcheckpoint_out:
  walIteratorFree(pIter);
  return rc;
}

/*
** If the WAL file is currently larger than nMax bytes in size, truncate
** it to exactly nMax bytes. If an error occurs while doing so, ignore it.
*/
static void walLimitSize(Wal *pWal, i64 nMax){
  if( isWalMode2(pWal)==0 ){
    i64 sz;
    int rx;
    sqlite3BeginBenignMalloc();
    rx = sqlite3OsFileSize(pWal->apWalFd[0], &sz);
    if( rx==SQLITE_OK && (sz > nMax ) ){
      rx = sqlite3OsTruncate(pWal->apWalFd[0], nMax);
    }
    sqlite3EndBenignMalloc();
    if( rx ){
      sqlite3_log(rx, "cannot limit WAL size: %s", pWal->zWalName);
    }
  }
}

/*
** Close a connection to a log file.
*/
int sqlite3WalClose(
1940
1941
1942
1943
1944
1945
1946

1947
1948
1949

1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973

1974








1975
1976
1977
1978
1979

1980
1981
1982
1983
1984
1985
1986
    ** the wal and wal-index files.
    **
    ** The EXCLUSIVE lock is not released before returning.
    */
    if( zBuf!=0
     && SQLITE_OK==(rc = sqlite3OsLock(pWal->pDbFd, SQLITE_LOCK_EXCLUSIVE))
    ){

      if( pWal->exclusiveMode==WAL_NORMAL_MODE ){
        pWal->exclusiveMode = WAL_EXCLUSIVE_MODE;
      }

      rc = sqlite3WalCheckpoint(pWal, db, 
          SQLITE_CHECKPOINT_PASSIVE, 0, 0, sync_flags, nBuf, zBuf, 0, 0
      );
      if( rc==SQLITE_OK ){
        int bPersist = -1;
        sqlite3OsFileControlHint(
            pWal->pDbFd, SQLITE_FCNTL_PERSIST_WAL, &bPersist
        );
        if( bPersist!=1 ){
          /* Try to delete the WAL file if the checkpoint completed and
          ** fsyned (rc==SQLITE_OK) and if we are not in persistent-wal
          ** mode (!bPersist) */
          isDelete = 1;
        }else if( pWal->mxWalSize>=0 ){
          /* Try to truncate the WAL file to zero bytes if the checkpoint
          ** completed and fsynced (rc==SQLITE_OK) and we are in persistent
          ** WAL mode (bPersist) and if the PRAGMA journal_size_limit is a
          ** non-negative value (pWal->mxWalSize>=0).  Note that we truncate
          ** to zero bytes as truncating to the journal_size_limit might
          ** leave a corrupt WAL file on disk. */
          walLimitSize(pWal, 0);
        }
      }
    }










    walIndexClose(pWal, isDelete);
    sqlite3OsClose(pWal->pWalFd);
    if( isDelete ){
      sqlite3BeginBenignMalloc();
      sqlite3OsDelete(pWal->pVfs, pWal->zWalName, 0);

      sqlite3EndBenignMalloc();
    }
    WALTRACE(("WAL%p: closed\n", pWal));
    sqlite3_free((void *)pWal->apWiData);
    sqlite3_free(pWal);
  }
  return rc;







>



>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
>

>
>
>
>
>
>
>
>

<



>







2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316

2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
    ** the wal and wal-index files.
    **
    ** The EXCLUSIVE lock is not released before returning.
    */
    if( zBuf!=0
     && SQLITE_OK==(rc = sqlite3OsLock(pWal->pDbFd, SQLITE_LOCK_EXCLUSIVE))
    ){
      int i;
      if( pWal->exclusiveMode==WAL_NORMAL_MODE ){
        pWal->exclusiveMode = WAL_EXCLUSIVE_MODE;
      }
      for(i=0; rc==SQLITE_OK && i<2; i++){
        rc = sqlite3WalCheckpoint(pWal, db, 
            SQLITE_CHECKPOINT_PASSIVE, 0, 0, sync_flags, nBuf, zBuf, 0, 0
        );
        if( rc==SQLITE_OK ){
          int bPersist = -1;
          sqlite3OsFileControlHint(
              pWal->pDbFd, SQLITE_FCNTL_PERSIST_WAL, &bPersist
          );
          if( bPersist!=1 ){
            /* Try to delete the WAL file if the checkpoint completed and
            ** fsyned (rc==SQLITE_OK) and if we are not in persistent-wal
            ** mode (!bPersist) */
            isDelete = 1;
          }else if( pWal->mxWalSize>=0 ){
            /* Try to truncate the WAL file to zero bytes if the checkpoint
            ** completed and fsynced (rc==SQLITE_OK) and we are in persistent
            ** WAL mode (bPersist) and if the PRAGMA journal_size_limit is a
            ** non-negative value (pWal->mxWalSize>=0).  Note that we truncate
            ** to zero bytes as truncating to the journal_size_limit might
            ** leave a corrupt WAL file on disk. */
            walLimitSize(pWal, 0);
          }
        }

        if( isWalMode2(pWal)==0 ) break;

        walCkptInfo(pWal)->nBackfill = 0;
        walidxSetFile(&pWal->hdr, !walidxGetFile(&pWal->hdr));
        pWal->writeLock = 1;
        walIndexWriteHdr(pWal);
        pWal->writeLock = 0;
      }
    }

    walIndexClose(pWal, isDelete);

    if( isDelete ){
      sqlite3BeginBenignMalloc();
      sqlite3OsDelete(pWal->pVfs, pWal->zWalName, 0);
      sqlite3OsDelete(pWal->pVfs, pWal->zWalName2, 0);
      sqlite3EndBenignMalloc();
    }
    WALTRACE(("WAL%p: closed\n", pWal));
    sqlite3_free((void *)pWal->apWiData);
    sqlite3_free(pWal);
  }
  return rc;
2111
2112
2113
2114
2115
2116
2117
2118


2119
2120
2121
2122
2123
2124
2125
    }
  }

  /* 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;
}

/*







|
>
>







2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
    }
  }

  /* 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!=WAL_VERSION1 && pWal->hdr.iVersion!=WAL_VERSION2
  ){
    rc = SQLITE_CANTOPEN_BKPT;
  }

  return rc;
}

/*
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
** 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  */
  u32 mxFrame;                    /* Wal frame to lock to */

  assert( pWal->readLock<0 );     /* Not currently locked */

  /* Take steps to avoid spinning forever if there is a protocol error.
  **
  ** Circumstances that cause a RETRY should only last for the briefest
  ** instances of time.  No I/O or other system calls are done while the
  ** locks are held, so the locks should not be held for very long. But 
  ** if we are unlucky, another process that is holding a lock might get







<
<
<

<

|







2519
2520
2521
2522
2523
2524
2525



2526

2527
2528
2529
2530
2531
2532
2533
2534
2535
** 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 */



  int rc = SQLITE_OK;             /* Return code  */


  assert( pWal->readLock==WAL_LOCK_NONE );     /* Not currently locked */

  /* Take steps to avoid spinning forever if there is a protocol error.
  **
  ** Circumstances that cause a RETRY should only last for the briefest
  ** instances of time.  No I/O or other system calls are done while the
  ** locks are held, so the locks should not be held for very long. But 
  ** if we are unlucky, another process that is holding a lock might get
2244
2245
2246
2247
2248
2249
2250
























2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375

2376
2377
2378
2379
2380
2381
2382
    }
    if( rc!=SQLITE_OK ){
      return rc;
    }
  }

  pInfo = walCkptInfo(pWal);
























  if( !useWal && pInfo->nBackfill==pWal->hdr.mxFrame 
#ifdef SQLITE_ENABLE_SNAPSHOT
   && (pWal->pSnapshot==0 || pWal->hdr.mxFrame==0
     || 0==memcmp(&pWal->hdr, pWal->pSnapshot, sizeof(WalIndexHdr)))
#endif
  ){
    /* 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;
  mxFrame = pWal->hdr.mxFrame;
#ifdef SQLITE_ENABLE_SNAPSHOT
  if( pWal->pSnapshot && pWal->pSnapshot->mxFrame<mxFrame ){
    mxFrame = pWal->pSnapshot->mxFrame;
  }
#endif
  for(i=1; i<WAL_NREADER; i++){
    u32 thisMark = pInfo->aReadMark[i];
    if( mxReadMark<=thisMark && thisMark<=mxFrame ){
      assert( thisMark!=READMARK_NOT_USED );
      mxReadMark = thisMark;
      mxI = i;
    }
  }
  if( (pWal->readOnly & WAL_SHM_RDONLY)==0
   && (mxReadMark<mxFrame || mxI==0)
  ){
    for(i=1; i<WAL_NREADER; i++){
      rc = walLockExclusive(pWal, WAL_READ_LOCK(i), 1);
      if( rc==SQLITE_OK ){
        mxReadMark = pInfo->aReadMark[i] = mxFrame;
        mxI = i;
        walUnlockExclusive(pWal, WAL_READ_LOCK(i), 1);
        break;
      }else if( rc!=SQLITE_BUSY ){
        return rc;
      }
    }
  }
  if( mxI==0 ){
    assert( rc==SQLITE_BUSY || (pWal->readOnly & WAL_SHM_RDONLY)!=0 );
    return rc==SQLITE_BUSY ? WAL_RETRY : SQLITE_READONLY_CANTLOCK;
  }

  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.
  **
  ** Before checking that the live wal-index header has not changed
  ** since it was read, set Wal.minFrame to the first frame in the wal
  ** file that has not yet been checkpointed. This client will not need
  ** to read any frames earlier than minFrame from the wal file - they
  ** can be safely read directly from the database file.
  **
  ** Because a ShmBarrier() call is made between taking the copy of 
  ** nBackfill and checking that the wal-header in shared-memory still
  ** matches the one cached in pWal->hdr, it is guaranteed that the 
  ** checkpointer that set nBackfill was not working with a wal-index
  ** header newer than that cached in pWal->hdr. If it were, that could
  ** cause a problem. The checkpointer could omit to checkpoint
  ** a version of page X that lies before pWal->minFrame (call that version
  ** A) on the basis that there is a newer version (version B) of the same
  ** page later in the wal file. But if version B happens to like past
  ** frame pWal->hdr.mxFrame - then the client would incorrectly assume
  ** that it can read version A from the database file. However, since
  ** we can guarantee that the checkpointer that set nBackfill could not
  ** see any pages past pWal->hdr.mxFrame, this problem does not come up.
  */
  pWal->minFrame = pInfo->nBackfill+1;
  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{
    assert( mxReadMark<=pWal->hdr.mxFrame );
    pWal->readLock = (i16)mxI;

  }
  return rc;
}

#ifdef SQLITE_ENABLE_SNAPSHOT
/*
** Attempt to reduce the value of the WalCkptInfo.nBackfillAttempted 







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|

|
|

|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|

|
|
|
|
|
|
|
|

|
|
|

|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|

|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
>







2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
    }
    if( rc!=SQLITE_OK ){
      return rc;
    }
  }

  pInfo = walCkptInfo(pWal);
  if( isWalMode2(pWal) ){
    int eLock = 1 + (walidxGetFile(&pWal->hdr)*2);
    if( pInfo->nBackfill==0 ){
      eLock += walidxGetMxFrame(&pWal->hdr, !walidxGetFile(&pWal->hdr))>0;
    }
    rc = walLockReader(pWal, eLock, 1);
    if( rc!=SQLITE_OK ){
      return rc;
    }

    walShmBarrier(pWal);
    if( memcmp((void *)walIndexHdr(pWal), &pWal->hdr, sizeof(WalIndexHdr)) ){
      walLockReader(pWal, eLock, 0);
      return WAL_RETRY;
    }else{
      pWal->readLock = eLock;
    }
    assert( pWal->minFrame==0 && walFramePage(pWal->minFrame)==0 );
  }else{
    u32 mxReadMark;               /* Largest aReadMark[] value */
    int mxI;                      /* Index of largest aReadMark[] value */
    int i;                        /* Loop counter */
    u32 mxFrame;                  /* Wal frame to lock to */

    if( !useWal && pInfo->nBackfill==pWal->hdr.mxFrame 
#ifdef SQLITE_ENABLE_SNAPSHOT
     && (pWal->pSnapshot==0 || pWal->hdr.mxFrame==0
       || 0==memcmp(&pWal->hdr, pWal->pSnapshot, sizeof(WalIndexHdr)))
#endif
      ){
      /* 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;
    mxFrame = pWal->hdr.mxFrame;
#ifdef SQLITE_ENABLE_SNAPSHOT
    if( pWal->pSnapshot && pWal->pSnapshot->mxFrame<mxFrame ){
      mxFrame = pWal->pSnapshot->mxFrame;
    }
#endif
    for(i=1; i<WAL_NREADER; i++){
      u32 thisMark = pInfo->aReadMark[i];
      if( mxReadMark<=thisMark && thisMark<=mxFrame ){
        assert( thisMark!=READMARK_NOT_USED );
        mxReadMark = thisMark;
        mxI = i;
      }
    }
    if( (pWal->readOnly & WAL_SHM_RDONLY)==0
        && (mxReadMark<mxFrame || mxI==0)
      ){
      for(i=1; i<WAL_NREADER; i++){
        rc = walLockExclusive(pWal, WAL_READ_LOCK(i), 1);
        if( rc==SQLITE_OK ){
          mxReadMark = pInfo->aReadMark[i] = mxFrame;
          mxI = i;
          walUnlockExclusive(pWal, WAL_READ_LOCK(i), 1);
          break;
        }else if( rc!=SQLITE_BUSY ){
          return rc;
        }
      }
    }
    if( mxI==0 ){
      assert( rc==SQLITE_BUSY || (pWal->readOnly & WAL_SHM_RDONLY)!=0 );
      return rc==SQLITE_BUSY ? WAL_RETRY : SQLITE_READONLY_CANTLOCK;
    }

    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.
    **
    ** Before checking that the live wal-index header has not changed
    ** since it was read, set Wal.minFrame to the first frame in the wal
    ** file that has not yet been checkpointed. This client will not need
    ** to read any frames earlier than minFrame from the wal file - they
    ** can be safely read directly from the database file.
    **
    ** Because a ShmBarrier() call is made between taking the copy of 
    ** nBackfill and checking that the wal-header in shared-memory still
    ** matches the one cached in pWal->hdr, it is guaranteed that the 
    ** checkpointer that set nBackfill was not working with a wal-index
    ** header newer than that cached in pWal->hdr. If it were, that could
    ** cause a problem. The checkpointer could omit to checkpoint
    ** a version of page X that lies before pWal->minFrame (call that version
    ** A) on the basis that there is a newer version (version B) of the same
    ** page later in the wal file. But if version B happens to like past
    ** frame pWal->hdr.mxFrame - then the client would incorrectly assume
    ** that it can read version A from the database file. However, since
    ** we can guarantee that the checkpointer that set nBackfill could not
    ** see any pages past pWal->hdr.mxFrame, this problem does not come up.
    */
    pWal->minFrame = pInfo->nBackfill+1;
    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{
      assert( mxReadMark<=pWal->hdr.mxFrame );
      pWal->readLock = (i16)mxI;
    }
  }
  return rc;
}

#ifdef SQLITE_ENABLE_SNAPSHOT
/*
** Attempt to reduce the value of the WalCkptInfo.nBackfillAttempted 
2484
2485
2486
2487
2488
2489
2490




2491
2492
2493
2494
2495
2496
2497
  do{
    rc = walTryBeginRead(pWal, pChanged, 0, ++cnt);
  }while( rc==WAL_RETRY );
  testcase( (rc&0xff)==SQLITE_BUSY );
  testcase( (rc&0xff)==SQLITE_IOERR );
  testcase( rc==SQLITE_PROTOCOL );
  testcase( rc==SQLITE_OK );





#ifdef SQLITE_ENABLE_SNAPSHOT
  if( rc==SQLITE_OK ){
    if( pSnapshot && memcmp(pSnapshot, &pWal->hdr, sizeof(WalIndexHdr))!=0 ){
      /* At this point the client has a lock on an aReadMark[] slot holding
      ** a value equal to or smaller than pSnapshot->mxFrame, but pWal->hdr
      ** is populated with the wal-index header corresponding to the head







>
>
>
>







2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
  do{
    rc = walTryBeginRead(pWal, pChanged, 0, ++cnt);
  }while( rc==WAL_RETRY );
  testcase( (rc&0xff)==SQLITE_BUSY );
  testcase( (rc&0xff)==SQLITE_IOERR );
  testcase( rc==SQLITE_PROTOCOL );
  testcase( rc==SQLITE_OK );
  
  if( rc==SQLITE_OK && pWal->hdr.iVersion==WAL_VERSION2 ){
    rc = walOpenWal2(pWal);
  }

#ifdef SQLITE_ENABLE_SNAPSHOT
  if( rc==SQLITE_OK ){
    if( pSnapshot && memcmp(pSnapshot, &pWal->hdr, sizeof(WalIndexHdr))!=0 ){
      /* At this point the client has a lock on an aReadMark[] slot holding
      ** a value equal to or smaller than pSnapshot->mxFrame, but pWal->hdr
      ** is populated with the wal-index header corresponding to the head
2557
2558
2559
2560
2561
2562
2563
2564



2565

2566
2567
2568



























































2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582



2583
2584
2585
2586
2587
2588
2589
2590
2591
2592

2593





2594
2595
2596


2597



2598



2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621

2622





2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650







2651

2652
2653
2654
2655
2656



2657
2658
2659
2660
2661
2662
2663

/*
** Finish with a read transaction.  All this does is release the
** read-lock.
*/
void sqlite3WalEndReadTransaction(Wal *pWal){
  sqlite3WalEndWriteTransaction(pWal);
  if( pWal->readLock>=0 ){



    walUnlockShared(pWal, WAL_READ_LOCK(pWal->readLock));

    pWal->readLock = -1;
  }
}




























































/*
** Search the wal file for page pgno. If found, set *piRead to the frame that
** contains the page. Otherwise, if pgno is not in the wal file, set *piRead
** to zero.
**
** Return SQLITE_OK if successful, or an error code if an error occurs. If an
** error does occur, the final value of *piRead is undefined.
*/
int sqlite3WalFindFrame(
  Wal *pWal,                      /* WAL handle */
  Pgno pgno,                      /* Database page number to read data for */
  u32 *piRead                     /* OUT: Frame number (or zero) */
){



  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 */
  int iMinHash;

  /* This routine is only be called from within a read transaction. */
  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 ){



    *piRead = 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.
  */
  iMinHash = walFramePage(pWal->minFrame);
  for(iHash=walFramePage(iLast); iHash>=iMinHash && 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 && iFrame>=pWal->minFrame && aPgno[aHash[iKey]]==pgno ){
        assert( iFrame>iRead || CORRUPT_DB );
        iRead = iFrame;
      }
      if( (nCollide--)==0 ){
        return SQLITE_CORRUPT_BKPT;
      }
    }







  }


#ifdef SQLITE_ENABLE_EXPENSIVE_ASSERT
  /* If expensive 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;
    assert( pWal->minFrame>0 );
    for(iTest=iLast; iTest>=pWal->minFrame; iTest--){
      if( walFramePgno(pWal, iTest)==pgno ){
        iRead2 = iTest;







|
>
>
>
|
>
|


>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>














>
>
>

|

<


|

|
|
>
|
>
>
>
>
>
|
<
<
>
>
|
>
>
>
|
>
>
>
|
|
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|
|
>
|
>
>
>
>
>
|
<
<
<
|
|
<
<
<
<
<
<
|
<
|
<
|
<
<
<
<
<
<
|
<
<
|
|
>
>
>
>
>
>
>

>




|
>
>
>







2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019

3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033


3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046


















3047
3048
3049
3050
3051
3052
3053
3054
3055
3056



3057
3058






3059

3060

3061






3062


3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088

/*
** Finish with a read transaction.  All this does is release the
** read-lock.
*/
void sqlite3WalEndReadTransaction(Wal *pWal){
  sqlite3WalEndWriteTransaction(pWal);
  if( pWal->readLock!=WAL_LOCK_NONE ){
    if( isWalMode2(pWal) ){
      (void)walLockReader(pWal, pWal->readLock, 0);
    }else{
      walUnlockShared(pWal, WAL_READ_LOCK(pWal->readLock));
    }
    pWal->readLock = WAL_LOCK_NONE;
  }
}

/* Search hash table iHash for an entry matching page number
** pgno. Each call to this function searches a single 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.
*/
static int walSearchHash(
  Wal *pWal, 
  u32 iLast,
  int iHash, 
  Pgno pgno, 
  u32 *piRead
){
  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 && iFrame>=pWal->minFrame && aPgno[aHash[iKey]]==pgno ){
      assert( iFrame>*piRead || CORRUPT_DB );
      *piRead = iFrame;
    }
    if( (nCollide--)==0 ){
      return SQLITE_CORRUPT_BKPT;
    }
  }

  return SQLITE_OK;
}


/*
** Search the wal file for page pgno. If found, set *piRead to the frame that
** contains the page. Otherwise, if pgno is not in the wal file, set *piRead
** to zero.
**
** Return SQLITE_OK if successful, or an error code if an error occurs. If an
** error does occur, the final value of *piRead is undefined.
*/
int sqlite3WalFindFrame(
  Wal *pWal,                      /* WAL handle */
  Pgno pgno,                      /* Database page number to read data for */
  u32 *piRead                     /* OUT: Frame number (or zero) */
){
  int bWal2 = isWalMode2(pWal);
  int iApp = walidxGetFile(&pWal->hdr);
  int rc = SQLITE_OK;
  u32 iRead = 0;                  /* If !=0, WAL frame to return data from */
  u32 iLast;                      /* Last frame in wal file */
  int iHash;                      /* Used to loop through N hash tables */


  /* This routine is only be called from within a read transaction. */
  assert( pWal->readLock!=WAL_LOCK_NONE );

  /* If this is a wal2 system, the client must have a partial-wal lock 
  ** on wal file iApp. Or if it is a wal system, iApp==0 must be true.  */
  assert( bWal2==0 || iApp==1
       || pWal->readLock==WAL_LOCK_PART1 || pWal->readLock==WAL_LOCK_PART1_FULL2
  );
  assert( bWal2==0 || iApp==0
       || pWal->readLock==WAL_LOCK_PART2 || pWal->readLock==WAL_LOCK_PART2_FULL1
  );
  assert( bWal2 || iApp==0 );



  /* Search the wal file that the client holds a partial lock on first */
  iLast = walidxGetMxFrame(&pWal->hdr, iApp);
  if( iLast ){
    u32 iExternal = bWal2 ? walExternalEncode(iApp, iLast) : iLast;
    int iMinHash = walFramePage(pWal->minFrame);
    for(iHash=walFramePage(iExternal); 
        iHash>=iMinHash && iRead==0; 
        iHash-=(1+bWal2)
    ){
      rc = walSearchHash(pWal, iExternal, iHash, pgno, &iRead);
      if( rc!=SQLITE_OK ) break;
    }
  }



















  /* If the requested page was not found, no error has occured, and 
  ** the client holds a full-wal lock on the other wal file, search it
  ** too.  */
  if( rc==SQLITE_OK && bWal2 && iRead==0 && (
        pWal->readLock==WAL_LOCK_PART1_FULL2 
     || pWal->readLock==WAL_LOCK_PART2_FULL1
  )){
    iLast = walidxGetMxFrame(&pWal->hdr, !iApp);
    if( iLast ){



      u32 iExternal = walExternalEncode(!iApp, iLast);
      for(iHash=walFramePage2(!iApp, iLast); iHash>=0 && iRead==0; iHash -= 2){






        rc = walSearchHash(pWal, iExternal, iHash, pgno, &iRead);

        if( rc!=SQLITE_OK ) break;

      }






    }


  }

#if defined(SQLITE_TEST) && defined(SQLITE_DEBUG)
  if( iRead ){ 
    u32 iFrame;
    int iWal = walExternalDecode(iRead, &iFrame);
    WALTRACE(("WAL%p: page %d @ frame %d wal %d\n",pWal,(int)pgno,iFrame,iWal));
  }else{
    WALTRACE(("WAL%p: page %d not found\n", pWal, (int)pgno));
  }
#endif

#ifdef SQLITE_ENABLE_EXPENSIVE_ASSERT
  /* If expensive 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.  
  **
  ** TODO: This is broken for wal2.
  */
  {
    u32 iRead2 = 0;
    u32 iTest;
    assert( pWal->minFrame>0 );
    for(iTest=iLast; iTest>=pWal->minFrame; iTest--){
      if( walFramePgno(pWal, iTest)==pgno ){
        iRead2 = iTest;
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686


2687


2688
2689
2690
2691










2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
/*
** Read the contents of frame iRead from the wal file into buffer pOut
** (which is nOut bytes in size). Return SQLITE_OK if successful, or an
** error code otherwise.
*/
int sqlite3WalReadFrame(
  Wal *pWal,                      /* WAL handle */
  u32 iRead,                      /* Frame to read */
  int nOut,                       /* Size of buffer pOut in bytes */
  u8 *pOut                        /* Buffer to write page data to */
){
  int sz;


  i64 iOffset;


  sz = pWal->hdr.szPage;
  sz = (sz&0xfe00) + ((sz&0x0001)<<16);
  testcase( sz<=32768 );
  testcase( sz>=65536 );










  iOffset = walFrameOffset(iRead, sz) + WAL_FRAME_HDRSIZE;
  /* testcase( IS_BIG_INT(iOffset) ); // requires a 4GiB WAL */
  return sqlite3OsRead(pWal->pWalFd, pOut, (nOut>sz ? sz : nOut), iOffset);
}

/* 
** Return the size of the database in pages (or zero, if unknown).
*/
Pgno sqlite3WalDbsize(Wal *pWal){
  if( pWal && ALWAYS(pWal->readLock>=0) ){
    return pWal->hdr.nPage;
  }
  return 0;
}


/* 







|




>
>

>
>




>
>
>
>
>
>
>
>
>
>


|






|







3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
/*
** Read the contents of frame iRead from the wal file into buffer pOut
** (which is nOut bytes in size). Return SQLITE_OK if successful, or an
** error code otherwise.
*/
int sqlite3WalReadFrame(
  Wal *pWal,                      /* WAL handle */
  u32 iExternal,                  /* Frame to read */
  int nOut,                       /* Size of buffer pOut in bytes */
  u8 *pOut                        /* Buffer to write page data to */
){
  int sz;
  int iWal = 0;
  u32 iRead;
  i64 iOffset;

  /* Figure out the page size */
  sz = pWal->hdr.szPage;
  sz = (sz&0xfe00) + ((sz&0x0001)<<16);
  testcase( sz<=32768 );
  testcase( sz>=65536 );

  if( isWalMode2(pWal) ){
    /* Figure out which of the two wal files, and the frame within, that 
    ** iExternal refers to.  */
    iWal = walExternalDecode(iExternal, &iRead);
  }else{
    iRead = iExternal;
  }

  WALTRACE(("WAL%p: reading frame %d wal %d\n", pWal, iRead, iWal));
  iOffset = walFrameOffset(iRead, sz) + WAL_FRAME_HDRSIZE;
  /* testcase( IS_BIG_INT(iOffset) ); // requires a 4GiB WAL */
  return sqlite3OsRead(pWal->apWalFd[iWal], pOut, (nOut>sz?sz:nOut), iOffset);
}

/* 
** Return the size of the database in pages (or zero, if unknown).
*/
Pgno sqlite3WalDbsize(Wal *pWal){
  if( pWal && ALWAYS(pWal->readLock!=WAL_LOCK_NONE) ){
    return pWal->hdr.nPage;
  }
  return 0;
}


/* 
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
** 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. */
  assert( pWal->readLock>=0 );
  assert( pWal->writeLock==0 && pWal->iReCksum==0 );

  if( pWal->readOnly ){
    return SQLITE_READONLY;
  }

  /* Only one writer allowed at a time.  Get the write lock.  Return







|







3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
** 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. */
  assert( pWal->readLock!=WAL_LOCK_NONE );
  assert( pWal->writeLock==0 && pWal->iReCksum==0 );

  if( pWal->readOnly ){
    return SQLITE_READONLY;
  }

  /* Only one writer allowed at a time.  Get the write lock.  Return
2777
2778
2779
2780
2781
2782
2783


2784
2785
2786


2787
2788
2789
2790


2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806




2807


2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821

2822

2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836


2837
2838

2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860



























2861
2862
2863
2864
2865

2866
2867
2868
2869
2870
2871
2872
2873
2874







2875






















2876

2877
2878
2879
2880
2881
2882
2883
**
** 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( ALWAYS(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.
      */




      assert( walFramePgno(pWal, iFrame)!=1 );


      rc = xUndo(pUndoCtx, walFramePgno(pWal, iFrame));
    }
    if( iMax!=pWal->hdr.mxFrame ) walCleanupHash(pWal);
  }
  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){

  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;



  assert( pWal->writeLock );

  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);
    assert( pInfo->nBackfill==pWal->hdr.mxFrame );
    if( pInfo->nBackfill>0 ){
      u32 salt1;
      sqlite3_randomness(4, &salt1);
      rc = walLockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1);
      if( rc==SQLITE_OK ){







>
>
|

|
>
>




>
>

<
|
<
<











>
>
>
>
|
>
>
|

|











>

>
|


|










>
>


>
|

|





|


|
|









>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>


|
|
<
>
|


|




|
>
>
>
>
>
>
>
|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
>







3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236

3237


3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344

3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
**
** 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( ALWAYS(pWal->writeLock) ){
    int iWal = walidxGetFile(&pWal->hdr);
    Pgno iMax = walidxGetMxFrame(&pWal->hdr, iWal);
    Pgno iNew;
    Pgno iFrame;

    assert( isWalMode2(pWal) || iWal==0 );

    /* 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));
    assert( walidxGetFile(&pWal->hdr)==iWal );
    iNew = walidxGetMxFrame(&pWal->hdr, walidxGetFile(&pWal->hdr));


    for(iFrame=iNew+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.
      */
      Pgno pgno;
      if( isWalMode2(pWal) ){
        pgno = walFramePgno2(pWal, iWal, iFrame);
      }else{
        pgno = walFramePgno(pWal, iFrame);
      }
      assert( pgno!=1 );
      rc = xUndo(pUndoCtx, pgno);
    }
    if( iMax!=iNew ) walCleanupHash(pWal);
  }
  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){
  int iWal = walidxGetFile(&pWal->hdr);
  assert( pWal->writeLock );
  assert( isWalMode2(pWal) || iWal==0 );
  aWalData[0] = walidxGetMxFrame(&pWal->hdr, iWal);
  aWalData[1] = pWal->hdr.aFrameCksum[0];
  aWalData[2] = pWal->hdr.aFrameCksum[1];
  aWalData[3] = isWalMode2(pWal) ? iWal : 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;
  int iWal = walidxGetFile(&pWal->hdr);
  int iCmp = isWalMode2(pWal) ? iWal : pWal->nCkpt;

  assert( pWal->writeLock );
  assert( isWalMode2(pWal) || iWal==0 );
  assert( aWalData[3]!=iCmp || aWalData[0]<=walidxGetMxFrame(&pWal->hdr,iWal) );

  if( aWalData[3]!=iCmp ){
    /* 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] = iCmp;
  }

  if( aWalData[0]<walidxGetMxFrame(&pWal->hdr, iWal) ){
    walidxSetMxFrame(&pWal->hdr, iWal, aWalData[0]);
    pWal->hdr.aFrameCksum[0] = aWalData[1];
    pWal->hdr.aFrameCksum[1] = aWalData[2];
    walCleanupHash(pWal);
  }

  return rc;
}

/*
** This function is used in wal2 mode.
**
** This function is called when writer pWal is just about to start 
** writing out frames. The "other" wal file (wal file !pWal->hdr.iAppend)
** has been fully checkpointed. This function returns SQLITE_OK if there
** are no readers preventing the writer from switching to the other wal
** file. Or SQLITE_BUSY if there are.
*/
static int walRestartOk(Wal *pWal){
  int rc;                                        /* Return code */
  int iApp = walidxGetFile(&pWal->hdr);          /* Current WAL file */

  /* No reader can be doing a "partial" read of wal file !iApp - in that
  ** case it would not have been possible to checkpoint the file. So
  ** it is only necessary to test for "full" readers. See the comment
  ** above walLockReader() function for exactly what this means in terms
  ** of locks.  */
  int i = (iApp==0) ? 2 : 4;

  rc = walLockExclusive(pWal, WAL_READ_LOCK(i), 1);
  if( rc==SQLITE_OK ){
    walUnlockExclusive(pWal, WAL_READ_LOCK(i), 1);
  }
  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 and desirable to switch to the
** other log file and write the new transaction to the start of it.

** If so, the wal-index header is updated accordingly - both in heap memory
** and in the *-shm file.
**
** SQLITE_OK is returned if no error is encountered (regardless of whether
** or not the wal-index header is modified). An SQLite error code is returned
** if an error occurs.
*/
static int walRestartLog(Wal *pWal){
  int rc = SQLITE_OK;

  if( isWalMode2(pWal) ){
    int iApp = walidxGetFile(&pWal->hdr);
    int nWalSize = WAL_DEFAULT_WALSIZE;
    if( pWal->mxWalSize>0 ){
      nWalSize = (pWal->mxWalSize-WAL_HDRSIZE+pWal->szPage+WAL_FRAME_HDRSIZE-1) 
        / (pWal->szPage+WAL_FRAME_HDRSIZE);
      nWalSize = MAX(nWalSize, 1);
    }

    if( walidxGetMxFrame(&pWal->hdr, iApp)>=nWalSize ){
      volatile WalCkptInfo *pInfo = walCkptInfo(pWal);
      if( walidxGetMxFrame(&pWal->hdr, !iApp)==0 || pInfo->nBackfill ){
        rc = walRestartOk(pWal);
        if( rc==SQLITE_OK ){
          iApp = !iApp;
          pWal->nCkpt++;
          walidxSetFile(&pWal->hdr, iApp);
          walidxSetMxFrame(&pWal->hdr, iApp, 0);
          sqlite3Put4byte((u8*)&pWal->hdr.aSalt[0], pWal->hdr.aFrameCksum[0]);
          sqlite3Put4byte((u8*)&pWal->hdr.aSalt[1], pWal->hdr.aFrameCksum[1]);
          walIndexWriteHdr(pWal);
          pInfo->nBackfill = 0;
          walLockReader(pWal, pWal->readLock, 0);
          pWal->readLock = iApp ? WAL_LOCK_PART2_FULL1 : WAL_LOCK_PART1_FULL2;
          rc = walLockReader(pWal, pWal->readLock, 1);
        }else if( rc==SQLITE_BUSY ){
          rc = SQLITE_OK;
        }
      }
    }
  }else if( pWal->readLock==0 ){
    int cnt;
    volatile WalCkptInfo *pInfo = walCkptInfo(pWal);
    assert( pInfo->nBackfill==pWal->hdr.mxFrame );
    if( pInfo->nBackfill>0 ){
      u32 salt1;
      sqlite3_randomness(4, &salt1);
      rc = walLockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1);
      if( rc==SQLITE_OK ){
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910

2911
2912
2913
2914
2915
2916
2917
        walRestartHdr(pWal, salt1);
        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, &notUsed, 1, ++cnt);
    }while( rc==WAL_RETRY );
    assert( (rc&0xff)!=SQLITE_BUSY ); /* BUSY not possible when useWal==1 */
    testcase( (rc&0xff)==SQLITE_IOERR );
    testcase( rc==SQLITE_PROTOCOL );
    testcase( rc==SQLITE_OK );
  }

  return rc;
}

/*
** Information about the current state of the WAL file and where
** the next fsync should occur - passed from sqlite3WalFrames() into
** walWriteToLog().







|










>







3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
        walRestartHdr(pWal, salt1);
        walUnlockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1);
      }else if( rc!=SQLITE_BUSY ){
        return rc;
      }
    }
    walUnlockShared(pWal, WAL_READ_LOCK(0));
    pWal->readLock = WAL_LOCK_NONE;
    cnt = 0;
    do{
      int notUsed;
      rc = walTryBeginRead(pWal, &notUsed, 1, ++cnt);
    }while( rc==WAL_RETRY );
    assert( (rc&0xff)!=SQLITE_BUSY ); /* BUSY not possible when useWal==1 */
    testcase( (rc&0xff)==SQLITE_IOERR );
    testcase( rc==SQLITE_PROTOCOL );
    testcase( rc==SQLITE_OK );
  }

  return rc;
}

/*
** Information about the current state of the WAL file and where
** the next fsync should occur - passed from sqlite3WalFrames() into
** walWriteToLog().
2962
2963
2964
2965
2966
2967
2968












2969
2970
2971
2972
2973
2974
2975
  PgHdr *pPage,               /* The page of the frame to be written */
  int nTruncate,              /* The commit flag.  Usually 0.  >0 for commit */
  sqlite3_int64 iOffset       /* Byte offset at which to write */
){
  int rc;                         /* Result code from subfunctions */
  void *pData;                    /* Data actually written */
  u8 aFrame[WAL_FRAME_HDRSIZE];   /* Buffer to assemble frame-header in */












#if defined(SQLITE_HAS_CODEC)
  if( (pData = sqlite3PagerCodec(pPage))==0 ) return SQLITE_NOMEM_BKPT;
#else
  pData = pPage->pData;
#endif
  walEncodeFrame(p->pWal, pPage->pgno, nTruncate, pData, aFrame);
  rc = walWriteToLog(p, aFrame, sizeof(aFrame), iOffset);







>
>
>
>
>
>
>
>
>
>
>
>







3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
  PgHdr *pPage,               /* The page of the frame to be written */
  int nTruncate,              /* The commit flag.  Usually 0.  >0 for commit */
  sqlite3_int64 iOffset       /* Byte offset at which to write */
){
  int rc;                         /* Result code from subfunctions */
  void *pData;                    /* Data actually written */
  u8 aFrame[WAL_FRAME_HDRSIZE];   /* Buffer to assemble frame-header in */

#if defined(SQLITE_TEST) && defined(SQLITE_DEBUG)
  { 
    int iWal = walidxGetFile(&p->pWal->hdr);
    int iFrame = 1 + (iOffset / (WAL_FRAME_HDRSIZE + p->pWal->szPage));
    assert( p->pWal->apWalFd[iWal]==p->pFd );
    WALTRACE(("WAL%p: page %d written to frame %d of wal %d\n",
          p->pWal, (int)pPage->pgno, iFrame, iWal
    ));
  }
#endif

#if defined(SQLITE_HAS_CODEC)
  if( (pData = sqlite3PagerCodec(pPage))==0 ) return SQLITE_NOMEM_BKPT;
#else
  pData = pPage->pData;
#endif
  walEncodeFrame(p->pWal, pPage->pgno, nTruncate, pData, aFrame);
  rc = walWriteToLog(p, aFrame, sizeof(aFrame), iOffset);
2984
2985
2986
2987
2988
2989
2990
2991
2992

2993
2994
2995
2996


2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
** one or more frames have been overwritten. It updates the checksums for
** all frames written to the wal file by the current transaction starting
** with the earliest to have been overwritten.
**
** SQLITE_OK is returned if successful, or an SQLite error code otherwise.
*/
static int walRewriteChecksums(Wal *pWal, u32 iLast){
  const int szPage = pWal->szPage;/* Database page size */
  int rc = SQLITE_OK;             /* Return code */

  u8 *aBuf;                       /* Buffer to load data from wal file into */
  u8 aFrame[WAL_FRAME_HDRSIZE];   /* Buffer to assemble frame-headers in */
  u32 iRead;                      /* Next frame to read from wal file */
  i64 iCksumOff;



  aBuf = sqlite3_malloc(szPage + WAL_FRAME_HDRSIZE);
  if( aBuf==0 ) return SQLITE_NOMEM_BKPT;

  /* Find the checksum values to use as input for the recalculating the
  ** first checksum. If the first frame is frame 1 (implying that the current
  ** transaction restarted the wal file), these values must be read from the
  ** wal-file header. Otherwise, read them from the frame header of the
  ** previous frame.  */
  assert( pWal->iReCksum>0 );
  if( pWal->iReCksum==1 ){
    iCksumOff = 24;
  }else{
    iCksumOff = walFrameOffset(pWal->iReCksum-1, szPage) + 16;
  }
  rc = sqlite3OsRead(pWal->pWalFd, aBuf, sizeof(u32)*2, iCksumOff);
  pWal->hdr.aFrameCksum[0] = sqlite3Get4byte(aBuf);
  pWal->hdr.aFrameCksum[1] = sqlite3Get4byte(&aBuf[sizeof(u32)]);

  iRead = pWal->iReCksum;
  pWal->iReCksum = 0;
  for(; rc==SQLITE_OK && iRead<=iLast; iRead++){
    i64 iOff = walFrameOffset(iRead, szPage);
    rc = sqlite3OsRead(pWal->pWalFd, aBuf, szPage+WAL_FRAME_HDRSIZE, iOff);
    if( rc==SQLITE_OK ){
      u32 iPgno, nDbSize;
      iPgno = sqlite3Get4byte(aBuf);
      nDbSize = sqlite3Get4byte(&aBuf[4]);

      walEncodeFrame(pWal, iPgno, nDbSize, &aBuf[WAL_FRAME_HDRSIZE], aFrame);
      rc = sqlite3OsWrite(pWal->pWalFd, aFrame, sizeof(aFrame), iOff);
    }
  }

  sqlite3_free(aBuf);
  return rc;
}








<

>




>
>















|







|






|







3507
3508
3509
3510
3511
3512
3513

3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
** one or more frames have been overwritten. It updates the checksums for
** all frames written to the wal file by the current transaction starting
** with the earliest to have been overwritten.
**
** SQLITE_OK is returned if successful, or an SQLite error code otherwise.
*/
static int walRewriteChecksums(Wal *pWal, u32 iLast){

  int rc = SQLITE_OK;             /* Return code */
  const int szPage = pWal->szPage;/* Database page size */
  u8 *aBuf;                       /* Buffer to load data from wal file into */
  u8 aFrame[WAL_FRAME_HDRSIZE];   /* Buffer to assemble frame-headers in */
  u32 iRead;                      /* Next frame to read from wal file */
  i64 iCksumOff;

  assert( isWalMode2(pWal)==0 );

  aBuf = sqlite3_malloc(szPage + WAL_FRAME_HDRSIZE);
  if( aBuf==0 ) return SQLITE_NOMEM_BKPT;

  /* Find the checksum values to use as input for the recalculating the
  ** first checksum. If the first frame is frame 1 (implying that the current
  ** transaction restarted the wal file), these values must be read from the
  ** wal-file header. Otherwise, read them from the frame header of the
  ** previous frame.  */
  assert( pWal->iReCksum>0 );
  if( pWal->iReCksum==1 ){
    iCksumOff = 24;
  }else{
    iCksumOff = walFrameOffset(pWal->iReCksum-1, szPage) + 16;
  }
  rc = sqlite3OsRead(pWal->apWalFd[0], aBuf, sizeof(u32)*2, iCksumOff);
  pWal->hdr.aFrameCksum[0] = sqlite3Get4byte(aBuf);
  pWal->hdr.aFrameCksum[1] = sqlite3Get4byte(&aBuf[sizeof(u32)]);

  iRead = pWal->iReCksum;
  pWal->iReCksum = 0;
  for(; rc==SQLITE_OK && iRead<=iLast; iRead++){
    i64 iOff = walFrameOffset(iRead, szPage);
    rc = sqlite3OsRead(pWal->apWalFd[0], aBuf, szPage+WAL_FRAME_HDRSIZE, iOff);
    if( rc==SQLITE_OK ){
      u32 iPgno, nDbSize;
      iPgno = sqlite3Get4byte(aBuf);
      nDbSize = sqlite3Get4byte(&aBuf[4]);

      walEncodeFrame(pWal, iPgno, nDbSize, &aBuf[WAL_FRAME_HDRSIZE], aFrame);
      rc = sqlite3OsWrite(pWal->apWalFd[0], aFrame, sizeof(aFrame), iOff);
    }
  }

  sqlite3_free(aBuf);
  return rc;
}

3050
3051
3052
3053
3054
3055
3056

3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073

3074

3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087



3088







3089

3090
3091
3092
3093
3094
3095












3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
  PgHdr *pLast = 0;               /* Last frame in list */
  int nExtra = 0;                 /* Number of extra copies of last page */
  int szFrame;                    /* The size of a single frame */
  i64 iOffset;                    /* Next byte to write in WAL file */
  WalWriter w;                    /* The writer */
  u32 iFirst = 0;                 /* First frame that may be overwritten */
  WalIndexHdr *pLive;             /* Pointer to shared header */


  assert( pList );
  assert( pWal->writeLock );

  /* If this frame set completes a transaction, then nTruncate>0.  If
  ** nTruncate==0 then this frame set does not complete the transaction. */
  assert( (isCommit!=0)==(nTruncate!=0) );

#if defined(SQLITE_TEST) && defined(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

  pLive = (WalIndexHdr*)walIndexHdr(pWal);
  if( memcmp(&pWal->hdr, (void *)pLive, sizeof(WalIndexHdr))!=0 ){

    iFirst = pLive->mxFrame+1;

  }

  /* 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);
    if( pWal->nCkpt==0 ) 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 = szPage;
    pWal->hdr.bigEndCksum = SQLITE_BIGENDIAN;
    pWal->hdr.aFrameCksum[0] = aCksum[0];
    pWal->hdr.aFrameCksum[1] = aCksum[1];
    pWal->truncateOnCommit = 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;
    }

    /* Sync the header (unless SQLITE_IOCAP_SEQUENTIAL is true or unless
    ** all syncing is turned off by PRAGMA synchronous=OFF).  Otherwise
    ** an out-of-order write following a WAL restart could result in
    ** database corruption.  See the ticket:
    **
    **     https://sqlite.org/src/info/ff5be73dee
    */
    if( pWal->syncHeader ){
      rc = sqlite3OsSync(pWal->pWalFd, CKPT_SYNC_FLAGS(sync_flags));
      if( rc ) return rc;
    }
  }
  assert( (int)pWal->szPage==szPage );

  /* Setup information needed to write frames into the WAL */
  w.pWal = pWal;
  w.pFd = pWal->pWalFd;
  w.iSyncPoint = 0;
  w.syncFlags = sync_flags;
  w.szPage = szPage;
  iOffset = walFrameOffset(iFrame+1, szPage);
  szFrame = szPage + WAL_FRAME_HDRSIZE;

  /* Write all frames into the log file exactly once */







>








<
<
<
<
<
<
<


>
|
>





|







>
>
>
|
>
>
>
>
>
>
>

>




|

>
>
>
>
>
>
>
>
>
>
>
>
|
<




|






|













|







|







3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590







3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640

3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
  PgHdr *pLast = 0;               /* Last frame in list */
  int nExtra = 0;                 /* Number of extra copies of last page */
  int szFrame;                    /* The size of a single frame */
  i64 iOffset;                    /* Next byte to write in WAL file */
  WalWriter w;                    /* The writer */
  u32 iFirst = 0;                 /* First frame that may be overwritten */
  WalIndexHdr *pLive;             /* Pointer to shared header */
  int iApp;

  assert( pList );
  assert( pWal->writeLock );

  /* If this frame set completes a transaction, then nTruncate>0.  If
  ** nTruncate==0 then this frame set does not complete the transaction. */
  assert( (isCommit!=0)==(nTruncate!=0) );








  pLive = (WalIndexHdr*)walIndexHdr(pWal);
  if( memcmp(&pWal->hdr, (void *)pLive, sizeof(WalIndexHdr))!=0 ){
    if( isWalMode2(pWal)==0 ){
      iFirst = pLive->mxFrame+1;
    }
  }

  /* 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.
  */
  else 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.
  */
  iApp = walidxGetFile(&pWal->hdr);
  iFrame = walidxGetMxFrame(&pWal->hdr, iApp);
  assert( iApp==0 || isWalMode2(pWal) );

#if defined(SQLITE_TEST) && defined(SQLITE_DEBUG)
  { int cnt; for(cnt=0, p=pList; p; p=p->pDirty, cnt++){}
    WALTRACE(("WAL%p: frame write begin. %d frames. iWal=%d. mxFrame=%d. %s\n",
              pWal, cnt, iApp, iFrame, isCommit ? "Commit" : "Spill"));
  }
#endif

  if( iFrame==0 ){
    u32 iCkpt = 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], pWal->hdr.iVersion);
    sqlite3Put4byte(&aWalHdr[8], szPage);
    if( isWalMode2(pWal) ){
      if( walidxGetMxFrame(&pWal->hdr, !iApp)>0 ){
        u8 aPrev[4];
        rc = sqlite3OsRead(pWal->apWalFd[!iApp], aPrev, 4, 12);
        if( rc!=SQLITE_OK ){
          return rc;
        }
        iCkpt = (sqlite3Get4byte(aPrev) + 1) & 0x0F;
      }
    }else{
      iCkpt = pWal->nCkpt;
    }
    sqlite3Put4byte(&aWalHdr[12], iCkpt);

    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 = szPage;
    pWal->hdr.bigEndCksum = SQLITE_BIGENDIAN;
    pWal->hdr.aFrameCksum[0] = aCksum[0];
    pWal->hdr.aFrameCksum[1] = aCksum[1];
    pWal->truncateOnCommit = 1;

    rc = sqlite3OsWrite(pWal->apWalFd[iApp], aWalHdr, sizeof(aWalHdr), 0);
    WALTRACE(("WAL%p: wal-header write %s\n", pWal, rc ? "failed" : "ok"));
    if( rc!=SQLITE_OK ){
      return rc;
    }

    /* Sync the header (unless SQLITE_IOCAP_SEQUENTIAL is true or unless
    ** all syncing is turned off by PRAGMA synchronous=OFF).  Otherwise
    ** an out-of-order write following a WAL restart could result in
    ** database corruption.  See the ticket:
    **
    **     https://sqlite.org/src/info/ff5be73dee
    */
    if( pWal->syncHeader ){
      rc = sqlite3OsSync(pWal->apWalFd[iApp], CKPT_SYNC_FLAGS(sync_flags));
      if( rc ) return rc;
    }
  }
  assert( (int)pWal->szPage==szPage );

  /* Setup information needed to write frames into the WAL */
  w.pWal = pWal;
  w.pFd = pWal->apWalFd[iApp];
  w.iSyncPoint = 0;
  w.syncFlags = sync_flags;
  w.szPage = szPage;
  iOffset = walFrameOffset(iFrame+1, szPage);
  szFrame = szPage + WAL_FRAME_HDRSIZE;

  /* Write all frames into the log file exactly once */
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
          pWal->iReCksum = iWrite;
        }
#if defined(SQLITE_HAS_CODEC)
        if( (pData = sqlite3PagerCodec(p))==0 ) return SQLITE_NOMEM;
#else
        pData = p->pData;
#endif
        rc = sqlite3OsWrite(pWal->pWalFd, pData, szPage, iOff);
        if( rc ) return rc;
        p->flags &= ~PGHDR_WAL_APPEND;
        continue;
      }
    }

    iFrame++;







|







3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
          pWal->iReCksum = iWrite;
        }
#if defined(SQLITE_HAS_CODEC)
        if( (pData = sqlite3PagerCodec(p))==0 ) return SQLITE_NOMEM;
#else
        pData = p->pData;
#endif
        rc = sqlite3OsWrite(pWal->apWalFd[iApp], pData, szPage, iOff);
        if( rc ) return rc;
        p->flags &= ~PGHDR_WAL_APPEND;
        continue;
      }
    }

    iFrame++;
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
  ** boundary is crossed.  Only the part of the WAL prior to the last
  ** sector boundary is synced; the part of the last frame that extends
  ** past the sector boundary is written after the sync.
  */
  if( isCommit && WAL_SYNC_FLAGS(sync_flags)!=0 ){
    int bSync = 1;
    if( pWal->padToSectorBoundary ){
      int sectorSize = sqlite3SectorSize(pWal->pWalFd);
      w.iSyncPoint = ((iOffset+sectorSize-1)/sectorSize)*sectorSize;
      bSync = (w.iSyncPoint==iOffset);
      testcase( bSync );
      while( iOffset<w.iSyncPoint ){
        rc = walWriteOneFrame(&w, pLast, nTruncate, iOffset);
        if( rc ) return rc;
        iOffset += szFrame;







|







3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
  ** boundary is crossed.  Only the part of the WAL prior to the last
  ** sector boundary is synced; the part of the last frame that extends
  ** past the sector boundary is written after the sync.
  */
  if( isCommit && WAL_SYNC_FLAGS(sync_flags)!=0 ){
    int bSync = 1;
    if( pWal->padToSectorBoundary ){
      int sectorSize = sqlite3SectorSize(w.pFd);
      w.iSyncPoint = ((iOffset+sectorSize-1)/sectorSize)*sectorSize;
      bSync = (w.iSyncPoint==iOffset);
      testcase( bSync );
      while( iOffset<w.iSyncPoint ){
        rc = walWriteOneFrame(&w, pLast, nTruncate, iOffset);
        if( rc ) return rc;
        iOffset += szFrame;
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260









3261

3262
3263
3264
3265
3266
3267
3268
  }

  /* 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){
    if( (p->flags & PGHDR_WAL_APPEND)==0 ) continue;
    iFrame++;
    rc = walIndexAppend(pWal, iFrame, p->pgno);
  }
  while( rc==SQLITE_OK && nExtra>0 ){
    iFrame++;
    nExtra--;
    rc = walIndexAppend(pWal, iFrame, pLast->pgno);
  }

  if( rc==SQLITE_OK ){
    /* Update the private copy of the header. */
    pWal->hdr.szPage = (u16)((szPage&0xff00) | (szPage>>16));
    testcase( szPage<=32768 );
    testcase( szPage>=65536 );
    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;
}








|



|




|







|







>
>
>
>
>
>
>
>
>
|
>







3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
  }

  /* 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 = walidxGetMxFrame(&pWal->hdr, iApp);
  for(p=pList; p && rc==SQLITE_OK; p=p->pDirty){
    if( (p->flags & PGHDR_WAL_APPEND)==0 ) continue;
    iFrame++;
    rc = walIndexAppend(pWal, iApp, iFrame, p->pgno);
  }
  while( rc==SQLITE_OK && nExtra>0 ){
    iFrame++;
    nExtra--;
    rc = walIndexAppend(pWal, iApp, iFrame, pLast->pgno);
  }

  if( rc==SQLITE_OK ){
    /* Update the private copy of the header. */
    pWal->hdr.szPage = (u16)((szPage&0xff00) | (szPage>>16));
    testcase( szPage<=32768 );
    testcase( szPage>=65536 );
    walidxSetMxFrame(&pWal->hdr, iApp, 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);
      if( isWalMode2(pWal) ){
        int iOther = !walidxGetFile(&pWal->hdr);
        if( walidxGetMxFrame(&pWal->hdr, iOther) 
            && !walCkptInfo(pWal)->nBackfill 
        ){
          pWal->iCallback = walidxGetMxFrame(&pWal->hdr, 0);
          pWal->iCallback += walidxGetMxFrame(&pWal->hdr, 1);
        }
      }else{
        pWal->iCallback = iFrame;
      }
    }
  }

  WALTRACE(("WAL%p: frame write %s\n", pWal, rc ? "failed" : "ok"));
  return rc;
}

3346
3347
3348
3349
3350
3351
3352
3353


3354
3355
3356
3357
3358
3359
3360
3361




3362








3363
3364
3365
3366
3367
3368
3369
      sqlite3OsUnfetch(pWal->pDbFd, 0, 0);
    }
  }

  /* Copy data from the log to the database file. */
  if( rc==SQLITE_OK ){

    if( pWal->hdr.mxFrame && walPagesize(pWal)!=nBuf ){


      rc = SQLITE_CORRUPT_BKPT;
    }else{
      rc = walCheckpoint(pWal, db, eMode2, xBusy2, pBusyArg, sync_flags, zBuf);
    }

    /* If no error occurred, set the output variables. */
    if( rc==SQLITE_OK || rc==SQLITE_BUSY ){
      if( pnLog ) *pnLog = (int)pWal->hdr.mxFrame;




      if( pnCkpt ) *pnCkpt = (int)(walCkptInfo(pWal)->nBackfill);








    }
  }

  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







|
>
>







|
>
>
>
>
|
>
>
>
>
>
>
>
>







3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
      sqlite3OsUnfetch(pWal->pDbFd, 0, 0);
    }
  }

  /* Copy data from the log to the database file. */
  if( rc==SQLITE_OK ){

    if( (walPagesize(pWal)!=nBuf) 
     && (walidxGetMxFrame(&pWal->hdr, 0) || walidxGetMxFrame(&pWal->hdr, 1))
    ){
      rc = SQLITE_CORRUPT_BKPT;
    }else{
      rc = walCheckpoint(pWal, db, eMode2, xBusy2, pBusyArg, sync_flags, zBuf);
    }

    /* If no error occurred, set the output variables. */
    if( rc==SQLITE_OK || rc==SQLITE_BUSY ){
      if( pnLog ){
        *pnLog = walidxGetMxFrame(&pWal->hdr,0)+walidxGetMxFrame(&pWal->hdr,1);
      }
      if( pnCkpt ){
        if( isWalMode2(pWal) ){
          if( (int)(walCkptInfo(pWal)->nBackfill) ){
            *pnCkpt = walidxGetMxFrame(&pWal->hdr, !walidxGetFile(&pWal->hdr));
          }else{
            *pnCkpt = 0;
          }
        }else{
          *pnCkpt = walCkptInfo(pWal)->nBackfill;
        }
      }
    }
  }

  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
3417
3418
3419
3420
3421
3422
3423

3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438



3439


3440
3441
3442
3443
3444
3445
3446
3447
3448
3449



3450

3451
3452
3453
3454
3455
3456
3457
** 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;

  assert( pWal->writeLock==0 );
  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.
  */
  assert( pWal->readLock>=0 || pWal->lockError );
  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 ){
    assert( pWal->exclusiveMode==0 );
    assert( pWal->readLock>=0 );



    walUnlockShared(pWal, WAL_READ_LOCK(pWal->readLock));

    pWal->exclusiveMode = 1;
    rc = 1;
  }else{
    rc = pWal->exclusiveMode==0;
  }
  return rc;
}







>









|
|




>
>
>
|
>
>










>
>
>
|
>







3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
** 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;

  assert( pWal->writeLock==0 );
  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.
  */
  assert( pWal->readLock!=WAL_LOCK_NONE || pWal->lockError );
  assert( pWal->readLock!=WAL_LOCK_NONE || (op<=0 && pWal->exclusiveMode==0) );

  if( op==0 ){
    if( pWal->exclusiveMode ){
      pWal->exclusiveMode = 0;
      if( isWalMode2(pWal) ){
        rc = walLockReader(pWal, pWal->readLock, 1);
      }else{
        rc = walLockShared(pWal, WAL_READ_LOCK(pWal->readLock));
      }
      if( rc==SQLITE_OK ){
        pWal->exclusiveMode = 1;
      }
      rc = pWal->exclusiveMode==0;
    }else{
      /* Already in locking_mode=NORMAL */
      rc = 0;
    }
  }else if( op>0 ){
    assert( pWal->exclusiveMode==0 );
    assert( pWal->readLock>=0 );
    if( isWalMode2(pWal) ){
      walLockReader(pWal, pWal->readLock, 0);
    }else{
      walUnlockShared(pWal, WAL_READ_LOCK(pWal->readLock));
    }
    pWal->exclusiveMode = 1;
    rc = 1;
  }else{
    rc = pWal->exclusiveMode==0;
  }
  return rc;
}
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
  return (pWal ? pWal->szPage : 0);
}
#endif

/* Return the sqlite3_file object for the WAL file
*/
sqlite3_file *sqlite3WalFile(Wal *pWal){
  return pWal->pWalFd;
}

#endif /* #ifndef SQLITE_OMIT_WAL */







|



4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
  return (pWal ? pWal->szPage : 0);
}
#endif

/* Return the sqlite3_file object for the WAL file
*/
sqlite3_file *sqlite3WalFile(Wal *pWal){
  return pWal->apWalFd[0];
}

#endif /* #ifndef SQLITE_OMIT_WAL */
Changes to src/wal.h.
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
/* Macros for extracting appropriate sync flags for either transaction
** commits (WAL_SYNC_FLAGS(X)) or for checkpoint ops (CKPT_SYNC_FLAGS(X)):
*/
#define WAL_SYNC_FLAGS(X)   ((X)&0x03)
#define CKPT_SYNC_FLAGS(X)  (((X)>>2)&0x03)

#ifdef SQLITE_OMIT_WAL
# define sqlite3WalOpen(x,y,z)                   0
# define sqlite3WalLimit(x,y)
# define sqlite3WalClose(v,w,x,y,z)              0
# define sqlite3WalBeginReadTransaction(y,z)     0
# define sqlite3WalEndReadTransaction(z)
# define sqlite3WalDbsize(y)                     0
# define sqlite3WalBeginWriteTransaction(y)      0
# define sqlite3WalEndWriteTransaction(x)        0







|







22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
/* Macros for extracting appropriate sync flags for either transaction
** commits (WAL_SYNC_FLAGS(X)) or for checkpoint ops (CKPT_SYNC_FLAGS(X)):
*/
#define WAL_SYNC_FLAGS(X)   ((X)&0x03)
#define CKPT_SYNC_FLAGS(X)  (((X)>>2)&0x03)

#ifdef SQLITE_OMIT_WAL
# define sqlite3WalOpen(w,x,y,z)                 0
# define sqlite3WalLimit(x,y)
# define sqlite3WalClose(v,w,x,y,z)              0
# define sqlite3WalBeginReadTransaction(y,z)     0
# define sqlite3WalEndReadTransaction(z)
# define sqlite3WalDbsize(y)                     0
# define sqlite3WalBeginWriteTransaction(y)      0
# define sqlite3WalEndWriteTransaction(x)        0
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65

/* Connection to a write-ahead log (WAL) file. 
** There is one object of this type for each pager. 
*/
typedef struct Wal Wal;

/* Open and close a connection to a write-ahead log. */
int sqlite3WalOpen(sqlite3_vfs*, sqlite3_file*, const char *, int, i64, Wal**);
int sqlite3WalClose(Wal *pWal, sqlite3*, int sync_flags, int, u8 *);

/* Set the limiting size of a WAL file. */
void sqlite3WalLimit(Wal*, i64);

/* Used by readers to open (lock) and close (unlock) a snapshot.  A 
** snapshot is like a read-transaction.  It is the state of the database







|







51
52
53
54
55
56
57
58
59
60
61
62
63
64
65

/* Connection to a write-ahead log (WAL) file. 
** There is one object of this type for each pager. 
*/
typedef struct Wal Wal;

/* Open and close a connection to a write-ahead log. */
int sqlite3WalOpen(sqlite3_vfs*, sqlite3_file*, const char *,int,i64,int,Wal**);
int sqlite3WalClose(Wal *pWal, sqlite3*, int sync_flags, int, u8 *);

/* Set the limiting size of a WAL file. */
void sqlite3WalLimit(Wal*, i64);

/* Used by readers to open (lock) and close (unlock) a snapshot.  A 
** snapshot is like a read-transaction.  It is the state of the database
Changes to test/permutations.test.
1000
1001
1002
1003
1004
1005
1006

















1007
1008
1009
1010
1011
1012
1013
    insert.test   insert2.test  insert3.test rollback.test 
    select1.test  select2.test  select3.test
  }
}

test_suite "wal" -description {
  Run tests with journal_mode=WAL

















} -initialize {
  set ::G(savepoint6_iterations) 100
} -shutdown {
  unset -nocomplain ::G(savepoint6_iterations)
} -files {
  savepoint.test     savepoint2.test     savepoint6.test
  trans.test         avtrans.test







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>







1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
    insert.test   insert2.test  insert3.test rollback.test 
    select1.test  select2.test  select3.test
  }
}

test_suite "wal" -description {
  Run tests with journal_mode=WAL
} -initialize {
  set ::G(savepoint6_iterations) 100
} -shutdown {
  unset -nocomplain ::G(savepoint6_iterations)
} -files {
  savepoint.test     savepoint2.test     savepoint6.test
  trans.test         avtrans.test

  fts3aa.test  fts3ab.test  fts3ac.test  fts3ad.test
  fts3ae.test  fts3af.test  fts3ag.test  fts3ah.test
  fts3ai.test  fts3aj.test  fts3ak.test  fts3al.test
  fts3am.test  fts3an.test  fts3ao.test  fts3b.test
  fts3c.test   fts3d.test   fts3e.test   fts3query.test 
}

test_suite "wal2" -description {
  Run tests with journal_mode=WAL2
} -initialize {
  set ::G(savepoint6_iterations) 100
} -shutdown {
  unset -nocomplain ::G(savepoint6_iterations)
} -files {
  savepoint.test     savepoint2.test     savepoint6.test
  trans.test         avtrans.test
Changes to test/savepoint.test.
24
25
26
27
28
29
30

31
32
33
34
35
36
37
do_test savepoint-1.1 {
  wal_set_journal_mode
  execsql {
    SAVEPOINT sp1;
    RELEASE sp1;
  }
} {}

do_test savepoint-1.2 {
  execsql {
    SAVEPOINT sp1;
    ROLLBACK TO sp1;
  }
} {}
do_test savepoint-1.3 {







>







24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
do_test savepoint-1.1 {
  wal_set_journal_mode
  execsql {
    SAVEPOINT sp1;
    RELEASE sp1;
  }
} {}
wal_check_journal_mode savepoint-1.1
do_test savepoint-1.2 {
  execsql {
    SAVEPOINT sp1;
    ROLLBACK TO sp1;
  }
} {}
do_test savepoint-1.3 {
Changes to test/savepoint6.test.
11
12
13
14
15
16
17




18
19
20
21
22
23
24
#
# $Id: savepoint6.test,v 1.4 2009/06/05 17:09:12 drh Exp $

set testdir [file dirname $argv0]
source $testdir/tester.tcl

proc sql {zSql} {




  uplevel db eval [list $zSql]
  #puts stderr "$zSql ;"
}

set DATABASE_SCHEMA {
    PRAGMA auto_vacuum = incremental;
    CREATE TABLE t1(x, y);







>
>
>
>







11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
#
# $Id: savepoint6.test,v 1.4 2009/06/05 17:09:12 drh Exp $

set testdir [file dirname $argv0]
source $testdir/tester.tcl

proc sql {zSql} {
  if {0 && $::debug_op} {
    puts stderr "$zSql ;"
    flush stderr
  }
  uplevel db eval [list $zSql]
  #puts stderr "$zSql ;"
}

set DATABASE_SCHEMA {
    PRAGMA auto_vacuum = incremental;
    CREATE TABLE t1(x, y);
63
64
65
66
67
68
69

70
71
72
73
74

75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91

92
93
94
95
96
97
98
99
100
101
102
103
104
105
106

107
108
109
110
111
112
113
114
115
116
117
118

119
120
121
122
123
124
125
#   rollback  NAME
#   release   NAME
#
#   insert_rows XVALUES
#   delete_rows XVALUES
#
proc savepoint {zName} {

  catch { sql "SAVEPOINT $zName" }
  lappend ::lSavepoint [list $zName [array get ::aEntry]]
}

proc rollback {zName} {

  catch { sql "ROLLBACK TO $zName" }
  for {set i [expr {[llength $::lSavepoint]-1}]} {$i>=0} {incr i -1} {
    set zSavepoint [lindex $::lSavepoint $i 0]
    if {$zSavepoint eq $zName} {
      unset -nocomplain ::aEntry
      array set ::aEntry [lindex $::lSavepoint $i 1]


      if {$i+1 < [llength $::lSavepoint]} {
        set ::lSavepoint [lreplace $::lSavepoint [expr $i+1] end]
      }
      break
    }
  }
}

proc release {zName} {

  catch { sql "RELEASE $zName" }
  for {set i [expr {[llength $::lSavepoint]-1}]} {$i>=0} {incr i -1} {
    set zSavepoint [lindex $::lSavepoint $i 0]
    if {$zSavepoint eq $zName} {
      set ::lSavepoint [lreplace $::lSavepoint $i end]
      break
    }
  }

  if {[llength $::lSavepoint] == 0} {
    #puts stderr "-- End of transaction!!!!!!!!!!!!!"
  }
}

proc insert_rows {lX} {

  foreach x $lX {
    set y [x_to_y $x]

    # Update database [db]
    sql "INSERT OR REPLACE INTO t1 VALUES($x, '$y')"

    # Update the Tcl database.
    set ::aEntry($x) $y
  }
}

proc delete_rows {lX} {

  foreach x $lX {
    # Update database [db]
    sql "DELETE FROM t1 WHERE x = $x"

    # Update the Tcl database.
    unset -nocomplain ::aEntry($x)
  }







>





>

















>















>












>







67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
#   rollback  NAME
#   release   NAME
#
#   insert_rows XVALUES
#   delete_rows XVALUES
#
proc savepoint {zName} {
  if {$::debug_op} { puts stderr "savepoint $zName" ; flush stderr }
  catch { sql "SAVEPOINT $zName" }
  lappend ::lSavepoint [list $zName [array get ::aEntry]]
}

proc rollback {zName} {
  if {$::debug_op} { puts stderr "rollback $zName" ; flush stderr }
  catch { sql "ROLLBACK TO $zName" }
  for {set i [expr {[llength $::lSavepoint]-1}]} {$i>=0} {incr i -1} {
    set zSavepoint [lindex $::lSavepoint $i 0]
    if {$zSavepoint eq $zName} {
      unset -nocomplain ::aEntry
      array set ::aEntry [lindex $::lSavepoint $i 1]


      if {$i+1 < [llength $::lSavepoint]} {
        set ::lSavepoint [lreplace $::lSavepoint [expr $i+1] end]
      }
      break
    }
  }
}

proc release {zName} {
  if {$::debug_op} { puts stderr "release $zName" ; flush stderr }
  catch { sql "RELEASE $zName" }
  for {set i [expr {[llength $::lSavepoint]-1}]} {$i>=0} {incr i -1} {
    set zSavepoint [lindex $::lSavepoint $i 0]
    if {$zSavepoint eq $zName} {
      set ::lSavepoint [lreplace $::lSavepoint $i end]
      break
    }
  }

  if {[llength $::lSavepoint] == 0} {
    #puts stderr "-- End of transaction!!!!!!!!!!!!!"
  }
}

proc insert_rows {lX} {
  if {$::debug_op} { puts stderr "insert_rows $lX" ; flush stderr }
  foreach x $lX {
    set y [x_to_y $x]

    # Update database [db]
    sql "INSERT OR REPLACE INTO t1 VALUES($x, '$y')"

    # Update the Tcl database.
    set ::aEntry($x) $y
  }
}

proc delete_rows {lX} {
  if {$::debug_op} { puts stderr "delete_rows $lX" ; flush stderr }
  foreach x $lX {
    # Update database [db]
    sql "DELETE FROM t1 WHERE x = $x"

    # Update the Tcl database.
    unset -nocomplain ::aEntry($x)
  }
159
160
161
162
163
164
165





166
167
168
169
170
171
172
  set ret [list]
  for {set i 0} {$i<$nRes} {incr i} {
    lappend ret [expr int(rand()*$nRange)]
  }
  return $ret
} 
#-------------------------------------------------------------------------






proc database_op {} {
  set i [expr int(rand()*2)] 
  if {$i==0} {
    insert_rows [random_integers 100 1000]
  }
  if {$i==1} {







>
>
>
>
>







168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
  set ret [list]
  for {set i 0} {$i<$nRes} {incr i} {
    lappend ret [expr int(rand()*$nRange)]
  }
  return $ret
} 
#-------------------------------------------------------------------------

set ::debug_op 0
proc debug_ops {} {
  set ::debug_op 1
}

proc database_op {} {
  set i [expr int(rand()*2)] 
  if {$i==0} {
    insert_rows [random_integers 100 1000]
  }
  if {$i==1} {
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
proc savepoint_op {} {
  set names {one two three four five}
  set cmds  {savepoint savepoint savepoint savepoint release rollback}

  set C [lindex $cmds [expr int(rand()*6)]]
  set N [lindex $names [expr int(rand()*5)]]

  #puts stderr "   $C $N ;  "
  #flush stderr

  $C $N
  return ok
}

expr srand(0)

############################################################################







<
<
<







195
196
197
198
199
200
201



202
203
204
205
206
207
208
proc savepoint_op {} {
  set names {one two three four five}
  set cmds  {savepoint savepoint savepoint savepoint release rollback}

  set C [lindex $cmds [expr int(rand()*6)]]
  set N [lindex $names [expr int(rand()*5)]]




  $C $N
  return ok
}

expr srand(0)

############################################################################
Changes to test/tester.tcl.
582
583
584
585
586
587
588

589
590
591
592
593
594
595
# Create a test database
#
proc reset_db {} {
  catch {db close}
  forcedelete test.db
  forcedelete test.db-journal
  forcedelete test.db-wal

  sqlite3 db ./test.db
  set ::DB [sqlite3_connection_pointer db]
  if {[info exists ::SETUP_SQL]} {
    db eval $::SETUP_SQL
  }
}
reset_db







>







582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
# Create a test database
#
proc reset_db {} {
  catch {db close}
  forcedelete test.db
  forcedelete test.db-journal
  forcedelete test.db-wal
  forcedelete test.db-wal2
  sqlite3 db ./test.db
  set ::DB [sqlite3_connection_pointer db]
  if {[info exists ::SETUP_SQL]} {
    db eval $::SETUP_SQL
  }
}
reset_db
2049
2050
2051
2052
2053
2054
2055
2056


2057
2058
2059




2060





2061
2062
2063
2064
2065




2066
2067
2068
2069
2070
2071
2072
2073
#     Otherwise (if not running a WAL permutation) this is a no-op.
#
#   wal_is_wal_mode
#
#     Returns true if this test should be run in WAL mode. False otherwise.
#
proc wal_is_wal_mode {} {
  expr {[permutation] eq "wal"}


}
proc wal_set_journal_mode {{db db}} {
  if { [wal_is_wal_mode] } {




    $db eval "PRAGMA journal_mode = WAL"





  }
}
proc wal_check_journal_mode {testname {db db}} {
  if { [wal_is_wal_mode] } {
    $db eval { SELECT * FROM sqlite_master }




    do_test $testname [list $db eval "PRAGMA main.journal_mode"] {wal}
  }
}

proc wal_is_capable {} {
  ifcapable !wal { return 0 }
  if {[permutation]=="journaltest"} { return 0 }
  return 1







|
>
>


|
>
>
>
>
|
>
>
>
>
>





>
>
>
>
|







2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
#     Otherwise (if not running a WAL permutation) this is a no-op.
#
#   wal_is_wal_mode
#
#     Returns true if this test should be run in WAL mode. False otherwise.
#
proc wal_is_wal_mode {} {
  if {[permutation] eq "wal"} { return 1 }
  if {[permutation] eq "wal2"} { return 2 }
  return 0
}
proc wal_set_journal_mode {{db db}} {
  switch -- [wal_is_wal_mode] {
    0 {
    }

    1 {
      $db eval "PRAGMA journal_mode = WAL"
    }

    2 {
      $db eval "PRAGMA journal_mode = WAL2"
    }
  }
}
proc wal_check_journal_mode {testname {db db}} {
  if { [wal_is_wal_mode] } {
    $db eval { SELECT * FROM sqlite_master }
    set expected "wal"
    if {[wal_is_wal_mode]==2} {
      set expected "wal2"
    }
    do_test $testname [list $db eval "PRAGMA main.journal_mode"] $expected
  }
}

proc wal_is_capable {} {
  ifcapable !wal { return 0 }
  if {[permutation]=="journaltest"} { return 0 }
  return 1
Added test/waltwo2.test.






























































































































































































































































>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
# 2017 September 19
#
# 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 implements regression tests for SQLite library.  The
# focus of this file is testing the operation of the library in
# "PRAGMA journal_mode=WAL2" mode.
#

set testdir [file dirname $argv0]
source $testdir/tester.tcl
source $testdir/lock_common.tcl
source $testdir/malloc_common.tcl
source $testdir/wal_common.tcl

set testprefix walsimple
ifcapable !wal {finish_test ; return }

db close
foreach f [glob -nocomplain test.db*] { forcedelete $f }
sqlite3 db test.db

do_execsql_test 1.0 {
  CREATE TABLE t1(x, y);
  PRAGMA journal_mode = wal2;
} {wal2}

do_execsql_test 1.1 {
  SELECT * FROM t1;
} {}

do_execsql_test 1.2 {
  INSERT INTO t1 VALUES(1, 2);
} {}

do_execsql_test 1.3 {
  SELECT * FROM t1;
} {1 2}

do_test 1.4 {
  sqlite3 db2 test.db
  execsql { SELECT * FROM t1 } db2
} {1 2}

do_test 1.5 {
  lsort [glob test.db*]
} {test.db test.db-shm test.db-wal test.db-wal2}

do_test 1.6 {
  db close
  db2 close
  sqlite3 db test.db
  execsql { SELECT * FROM t1 }
} {1 2}

do_execsql_test 1.7 {
  PRAGMA journal_size_limit = 4000;
  INSERT INTO t1 VALUES(3, 4);
  INSERT INTO t1 VALUES(5, 6);
  INSERT INTO t1 VALUES(7, 8);
  INSERT INTO t1 VALUES(9, 10);
  INSERT INTO t1 VALUES(11, 12);
  INSERT INTO t1 VALUES(13, 14);
  INSERT INTO t1 VALUES(15, 16);
  INSERT INTO t1 VALUES(17, 18);
  SELECT * FROM t1;
} {4000 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18}

do_test 1.8 {
  sqlite3 db2 test.db
  execsql { SELECT * FROM t1 } db2
} {1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18}

do_test 1.9 {
  db close
  db2 close
  lsort [glob test.db*]
} {test.db}

#-------------------------------------------------------------------------
reset_db
do_execsql_test 2.0 {
  CREATE TABLE t1(a INTEGER PRIMARY KEY, b, c);
  CREATE INDEX i1 ON t1(b, c);
  PRAGMA journal_mode = wal2;
  PRAGMA journal_size_limit = 4000;
} {wal2 4000}

proc wal_hook {DB nm nFrame} {
  $DB eval { PRAGMA wal_checkpoint }
}
db wal_hook [list wal_hook db]


foreach js {4000 8000 12000} {
  foreach NROW [list 100 200 300 400 500 600 1000] {
    do_test 2.$js.$NROW.1 {
      db eval "DELETE FROM t1"
      db eval "PRAGMA journal_size_limit = $js"
      set nTotal 0
      for {set i 0} {$i < $NROW} {incr i} {
        db eval { INSERT INTO t1 VALUES($i, $i, randomblob(abs(random()%50))) }
        incr nTotal $i
      }
      set {} {}
    } {}

    do_test 2.$js.$NROW.2 {
      sqlite3 db2 test.db
      db2 eval { 
        PRAGMA integrity_check;
        SELECT count(*), sum(b) FROM t1;
      }
    } [list ok $NROW $nTotal]

    db2 close
  }
}

finish_test