SQLite4  Check-in [53de55a6f4]

#define LSM_LOCK_READER(i)    ((i) + LSM_LOCK_CHECKPOINTER + 1)

/*
** Hard limit on the number of free-list entries that may be stored in 
** a checkpoint (the remainder are stored as a system record in the LSM).
** See also LSM_CONFIG_MAX_FREELIST.
*/
#define LSM_MAX_FREELIST_ENTRIES 24

#define LSM_ATTEMPTS_BEFORE_PROTOCOL 10000


/*
** Each entry stored in the LSM (or in-memory tree structure) has an
** associated mask of the following flags.

  Database *pDatabase;            /* Database this snapshot belongs to */
  Level *pLevel;                  /* Pointer to level 0 of snapshot (or NULL) */
  i64 iId;                        /* Snapshot id */
  i64 iLogOff;                    /* Log file offset */

  /* Used by worker snapshots only */
  int nBlock;                     /* Number of blocks in database file */
  Pgno aiAppend[LSM_APPLIST_SZ];  /* Append point list */
  Freelist freelist;              /* Free block list */
  int nFreelistOvfl;              /* Number of extra free-list entries in LSM */
  u32 nWrite;                     /* Total number of pages written to disk */
};
#define LSM_INITIAL_SNAPSHOT_ID 11

/*

**
**     4 integers. See ckptExportAppendlist().
**
**   For each level in the database, a level record. Formatted as follows:
**
**     0. Age of the level.
**     1. The number of right-hand segments (nRight, possibly 0),
**     2. Segment record for left-hand segment (8 integers defined below),
**     3. Segment record for each right-hand segment (8 integers defined below),
**     4. If nRight>0, The number of segments involved in the merge
**     5. if nRight>0, Current nSkip value (see Merge structure defn.),
**     6. For each segment in the merge:
**        5a. Page number of next cell to read during merge (this field
**            is 64-bits - 2 integers)
**        5b. Cell number of next cell to read during merge
**     7. Page containing current split-key (64-bits - 2 integers).
**     8. Cell within page containing current split-key.
**     9. Current pointer value (64-bits - 2 integers).
**
**   The freelist. 
**
**     1. Number of free-list entries stored in checkpoint header.
**     2. For each entry:
**        2a. Block number of free block.
**        2b. MSW of associated checkpoint id.
**        2c. LSW of associated checkpoint id.
**
**   If the overflow flag is set, then extra free-list entries may be stored
**   in the FREELIST record. The FREELIST record contains 3 32-bit integers
**   per entry, in the same format as above (without the "number of entries"
**   field).
**
**   The checksum:
**
**     1. Checksum value 1.
**     2. Checksum value 2.
**
** In the above, a segment record consists of the following four 64-bit 
** fields (converted to 2 * u32 by storing the MSW followed by LSW):
**
**     1. First page of array,
**     2. Last page of array,
**     3. Root page of array (or 0),
**     4. Size of array in pages.
*/

** follows:
**
**   * For each level in the database not undergoing a merge, add 1.
**
**   * For each level in the database that is undergoing a merge, add 
**     the number of segments on the rhs of the level.
**
** A level record not undergoing a merge is 10 integers. A level record 
** with nRhs rhs segments and (nRhs+1) input segments (i.e. including the 
** separators from the next level) is (11*nRhs+20) integers. The maximum
** per right-hand-side level is therefore 21 integers. So the maximum
** size of all level records in a checkpoint is 21*40=820 integers.
**
** TODO: Before pointer values were changed from 32 to 64 bits, the above
** used to come to 420 bytes - leaving significant space for a free-list
** prefix. No more. To fix this, reduce the size of the level records in
** a db snapshot, and improve management of the free-list tail in 
** lsm_sorted.c. 
*/
#define LSM_MAX_RHS_SEGMENTS 40

/*
** LARGE NUMBERS OF FREELIST ENTRIES:
**
** There is also a limit (LSM_MAX_FREELIST_ENTRIES - defined in lsmInt.h)

static const int one = 1;
#define LSM_LITTLE_ENDIAN (*(u8 *)(&one))

/* Sizes, in integers, of various parts of the checkpoint. */
#define CKPT_HDR_SIZE         9
#define CKPT_LOGPTR_SIZE      4


#define CKPT_APPENDLIST_SIZE  (LSM_APPLIST_SZ * 2)

/* A #define to describe each integer in the checkpoint header. */
#define CKPT_HDR_ID_MSW   0
#define CKPT_HDR_ID_LSW   1
#define CKPT_HDR_NCKPT    2
#define CKPT_HDR_NBLOCK   3
#define CKPT_HDR_BLKSZ    4

  if( *pRc==LSM_OK ){
    u32 aCksum[2] = {0, 0};
    ckptChecksum(p->aCkpt, nCkpt+2, &aCksum[0], &aCksum[1]);
    ckptSetValue(p, nCkpt, aCksum[0], pRc);
    ckptSetValue(p, nCkpt+1, aCksum[1], pRc);
  }
}

static void ckptAppend64(CkptBuffer *p, int *piOut, i64 iVal, int *pRc){
  int iOut = *piOut;
  ckptSetValue(p, iOut++, (iVal >> 32) & 0xFFFFFFFF, pRc);
  ckptSetValue(p, iOut++, (iVal & 0xFFFFFFFF), pRc);
  *piOut = iOut;
}

static i64 ckptRead64(u32 *a){
  return (((i64)a[0]) << 32) + (i64)a[1];
}

static i64 ckptGobble64(u32 *a, int *piIn){
  int iIn = *piIn;
  *piIn += 2;
  return ckptRead64(&a[iIn]);
}


/*
** Append a 6-value segment record corresponding to pSeg to the checkpoint 
** buffer passed as the third argument.
*/
static void ckptExportSegment(
  Segment *pSeg, 
  CkptBuffer *p, 
  int *piOut, 
  int *pRc
){


  ckptAppend64(p, piOut, pSeg->iFirst, pRc);
  ckptAppend64(p, piOut, pSeg->iLastPg, pRc);
  ckptAppend64(p, piOut, pSeg->iRoot, pRc);
  ckptAppend64(p, piOut, pSeg->nSize, pRc);


}

static void ckptExportLevel(
  Level *pLevel,                  /* Level object to serialize */
  CkptBuffer *p,                  /* Append new level record to this ckpt */
  int *piOut,                     /* IN/OUT: Size of checkpoint so far */
  int *pRc                        /* IN/OUT: Error code */

    }
    assert( pMerge->nInput==pLevel->nRight 
         || pMerge->nInput==pLevel->nRight+1 
    );
    ckptSetValue(p, iOut++, pMerge->nInput, pRc);
    ckptSetValue(p, iOut++, pMerge->nSkip, pRc);
    for(i=0; i<pMerge->nInput; i++){
      ckptAppend64(p, &iOut, pMerge->aInput[i].iPg, pRc);
      ckptSetValue(p, iOut++, pMerge->aInput[i].iCell, pRc);
    }
    ckptAppend64(p, &iOut, pMerge->splitkey.iPg, pRc);
    ckptSetValue(p, iOut++, pMerge->splitkey.iCell, pRc);
    ckptAppend64(p, &iOut, pMerge->iCurrentPtr, pRc);
  }

  *piOut = iOut;
}

/*
** Populate the log offset fields of the checkpoint buffer. 4 values.

){
  int iOut = *piOut;

  assert( iOut==CKPT_HDR_LO_MSW );

  if( bFlush ){
    i64 iOff = pDb->treehdr.iOldLog;

    ckptAppend64(p, &iOut, iOff, pRc);
    ckptSetValue(p, iOut++, pDb->treehdr.oldcksum0, pRc);
    ckptSetValue(p, iOut++, pDb->treehdr.oldcksum1, pRc);
  }else{
    for(; iOut<=CKPT_HDR_LO_CKSUM2; iOut++){
      ckptSetValue(p, iOut, pDb->pShmhdr->aSnap2[iOut], pRc);
    }
  }

  *piOut = iOut;
}

static void ckptExportAppendlist(
  lsm_db *db,                     /* Database connection */
  CkptBuffer *p,                  /* Checkpoint buffer to write to */
  int *piOut,                     /* IN/OUT: Offset within checkpoint buffer */
  int *pRc                        /* IN/OUT: Error code */
){
  int i;

  Pgno *aiAppend = db->pWorker->aiAppend;

  for(i=0; i<LSM_APPLIST_SZ; i++){
    ckptAppend64(p, piOut, aiAppend[i], pRc);
  }

};

static int ckptExportSnapshot( 
  lsm_db *pDb,                    /* Connection handle */
  int nOvfl,                      /* Number of free-list entries in LSM */
  int bLog,                       /* True to update log-offset fields */
  i64 iId,                        /* Checkpoint id */

** Helper function for ckptImport().
*/
static void ckptNewSegment(
  u32 *aIn,
  int *piIn,
  Segment *pSegment               /* Populate this structure */
){


  assert( pSegment->iFirst==0 && pSegment->iLastPg==0 );
  assert( pSegment->nSize==0 && pSegment->iRoot==0 );
  pSegment->iFirst = ckptGobble64(aIn, piIn);
  pSegment->iLastPg = ckptGobble64(aIn, piIn);
  pSegment->iRoot = ckptGobble64(aIn, piIn);
  pSegment->nSize = ckptGobble64(aIn, piIn);
  assert( pSegment->iFirst );

}

static int ckptSetupMerge(lsm_db *pDb, u32 *aInt, int *piIn, Level *pLevel){
  Merge *pMerge;                  /* Allocated Merge object */
  int nInput;                     /* Number of input segments in merge */
  int iIn = *piIn;                /* Next value to read from aInt[] */
  int i;                          /* Iterator variable */

  /* Populate the Merge object. */
  pMerge->aInput = (MergeInput *)&pMerge[1];
  pMerge->nInput = nInput;
  pMerge->iOutputOff = -1;
  pMerge->nSkip = (int)aInt[iIn++];
  for(i=0; i<nInput; i++){
    pMerge->aInput[i].iPg = ckptGobble64(aInt, &iIn);
    pMerge->aInput[i].iCell = (int)aInt[iIn++];
  }
  pMerge->splitkey.iPg = ckptGobble64(aInt, &iIn);
  pMerge->splitkey.iCell = (int)aInt[iIn++];
  pMerge->iCurrentPtr = ckptGobble64(aInt, &iIn);

  /* Set *piIn and return LSM_OK. */
  *piIn = iIn;
  return LSM_OK;
}

){
  int rc = LSM_OK;
  Snapshot *pNew;

  pNew = (Snapshot *)lsmMallocZeroRc(pDb->pEnv, sizeof(Snapshot), &rc);
  if( rc==LSM_OK ){
    int nFree;
    int i;
    int nLevel = (int)aCkpt[CKPT_HDR_NLEVEL];
    int iIn = CKPT_HDR_SIZE + CKPT_APPENDLIST_SIZE + CKPT_LOGPTR_SIZE;

    pNew->iId = lsmCheckpointId(aCkpt, 0);
    pNew->nBlock = aCkpt[CKPT_HDR_NBLOCK];
    pNew->nWrite = aCkpt[CKPT_HDR_NWRITE];
    rc = ckptLoadLevels(pDb, aCkpt, &iIn, nLevel, &pNew->pLevel);
    pNew->iLogOff = lsmCheckpointLogOffset(aCkpt);

    /* Make a copy of the append-list */
    for(i=0; i<LSM_APPLIST_SZ; i++){
      u32 *a = &aCkpt[CKPT_HDR_SIZE + CKPT_LOGPTR_SIZE + i*2];
      pNew->aiAppend[i] = ckptRead64(a);
    }

    /* Copy the free-list */
    if( bInclFreelist ){
      pNew->nFreelistOvfl = aCkpt[CKPT_HDR_OVFL];
      nFree = aCkpt[iIn++];
      if( nFree ){
        pNew->freelist.aEntry = (FreelistEntry *)lsmMallocZeroRc(

  int rc = LSM_OK;                /* Return code */
  int iFirst;                     /* First page on block iBlk */
  int iLast;                      /* Last page on block iBlk */
  Level *pLevel;                  /* Used to iterate through levels */

  int iIn;                        /* Used to iterate through append points */
  int iOut = 0;                   /* Used to output append points */
  Pgno *aApp = pSnapshot->aiAppend;

  iFirst = fsFirstPageOnBlock(pFS, iBlk);
  iLast = fsLastPageOnBlock(pFS, iBlk);

  /* Check if any other run in the snapshot has a start or end page 
  ** within this block. If there is such a run, return early. */
  for(pLevel=lsmDbSnapshotLevel(pSnapshot); pLevel; pLevel=pLevel->pNext){

  }

  return fsPageGet(pFS, iPg, 0, ppNext);
}

static Pgno findAppendPoint(FileSystem *pFS){
  int i;
  Pgno *aiAppend = pFS->pDb->pWorker->aiAppend;
  u32 iRet = 0;

  for(i=LSM_APPLIST_SZ-1; iRet==0 && i>=0; i--){
    if( (iRet = aiAppend[i]) ) aiAppend[i] = 0;
  }
  return iRet;
}

    **
    ** Otherwise, add the first free page in the last block used by the run
    ** to the lAppend list.
    */
    iBlk = fsPageToBlock(pFS, p->iLastPg);
    if( fsLastPageOnBlock(pFS, fsPageToBlock(pFS, p->iLastPg) )!=p->iLastPg ){
      int i;
      Pgno *aiAppend = pFS->pDb->pWorker->aiAppend;
      for(i=0; i<LSM_APPLIST_SZ; i++){
        if( aiAppend[i]==0 ){
          aiAppend[i] = p->iLastPg+1;
          break;
        }
      }
    }else if( pFS->pCompress==0 ){