int iReader;                    /* Read lock held (-1 == unlocked) */
  MultiCursor *pCsr;              /* List of all open cursors */
  LogWriter *pLogWriter;          /* Context for writing to the log file */
  int nTransOpen;                 /* Number of opened write transactions */
  int nTransAlloc;                /* Allocated size of aTrans[] array */
  TransMark *aTrans;              /* Array of marks for transaction rollback */
  IntArray rollback;              /* List of tree-nodes to roll back */


  /* Worker context */
  Snapshot *pWorker;              /* Worker snapshot (or NULL) */
  Freelist *pFreelist;            /* See sortedNewToplevel() */
  int bUseFreelist;               /* True to use pFreelist */
  int bIncrMerge;                 /* True if currently doing a merge */

  int iReader;                    /* Read lock held (-1 == unlocked) */
  MultiCursor *pCsr;              /* List of all open cursors */
  LogWriter *pLogWriter;          /* Context for writing to the log file */
  int nTransOpen;                 /* Number of opened write transactions */
  int nTransAlloc;                /* Allocated size of aTrans[] array */
  TransMark *aTrans;              /* Array of marks for transaction rollback */
  IntArray rollback;              /* List of tree-nodes to roll back */
  int bDiscardOld;                /* True if lsmTreeDiscardOld() was called */

  /* Worker context */
  Snapshot *pWorker;              /* Worker snapshot (or NULL) */
  Freelist *pFreelist;            /* See sortedNewToplevel() */
  int bUseFreelist;               /* True to use pFreelist */
  int bIncrMerge;                 /* True if currently doing a merge */

** but then not used. This function is used to push the block back onto
** the freelist. Refreeing a block is different from freeing is, as a refreed
** block may be reused immediately. Whereas a freed block can not be reused 
** until (at least) after the next checkpoint.
*/
int lsmBlockRefree(lsm_db *pDb, int iBlk){
  int rc = LSM_OK;                /* Return code */
  Snapshot *p = pDb->pWorker;

#ifdef LSM_LOG_FREELIST
  lsmLogMessage(pDb, LSM_OK, "lsmBlockRefree(): Refree block %d", iBlk);
#endif

  rc = freelistAppend(pDb, iBlk, 0);
  return rc;
................................................................................
/*
** Argument bFlush is true if the contents of the in-memory tree has just
** been flushed to disk. The significance of this is that once the snapshot
** created to hold the updated state of the database is synced to disk, log
** file space can be recycled.
*/
void lsmFinishWork(lsm_db *pDb, int bFlush, int *pRc){

  assert( *pRc!=0 || pDb->pWorker );
  if( pDb->pWorker ){
    /* If no error has occurred, serialize the worker snapshot and write
    ** it to shared memory.  */
    if( *pRc==LSM_OK ){
      *pRc = lsmSaveWorker(pDb, bFlush);
    }













    lsmFreeSnapshot(pDb->pEnv, pDb->pWorker);
    pDb->pWorker = 0;
  }

  lsmShmLock(pDb, LSM_LOCK_WORKER, LSM_LOCK_UNLOCK, 0);

}

/*
** Called when recovery is finished.
*/
int lsmFinishRecovery(lsm_db *pDb){
  lsmTreeEndTransaction(pDb, 1);
................................................................................
** Open a write transaction.
*/
int lsmBeginWriteTrans(lsm_db *pDb){
  int rc;                         /* Return code */
  ShmHeader *pShm = pDb->pShmhdr; /* Shared memory header */

  assert( pDb->nTransOpen==0 );


  /* If there is no read-transaction open, open one now. */
  rc = lsmBeginReadTrans(pDb);

  /* Attempt to take the WRITER lock */
  if( rc==LSM_OK ){
    rc = lsmShmLock(pDb, LSM_LOCK_WRITER, LSM_LOCK_EXCL, 0);
................................................................................
  ** WRITER lock and return an error code.  */
  if( rc==LSM_OK ){
    TreeHeader *p = &pDb->treehdr;
    pShm->bWriter = 1;
    p->root.iTransId++;
    if( lsmTreeHasOld(pDb) && p->iOldLog==pDb->pClient->iLogOff ){
      lsmTreeDiscardOld(pDb);

    }
  }else{
    lsmShmLock(pDb, LSM_LOCK_WRITER, LSM_LOCK_UNLOCK, 0);
    if( pDb->pCsr==0 ) lsmFinishReadTrans(pDb);
  }
  return rc;
}
................................................................................
  lsmLogEnd(pDb, bCommit);
  if( rc==LSM_OK && bCommit && lsmTreeSize(pDb)>pDb->nTreeLimit ){
    bFlush = 1;
    lsmTreeMakeOld(pDb);
  }
  lsmTreeEndTransaction(pDb, bCommit);


  if( rc==LSM_OK && bFlush && pDb->bAutowork ){
    rc = lsmSortedAutoWork(pDb, 1);


  }


  lsmShmLock(pDb, LSM_LOCK_WRITER, LSM_LOCK_UNLOCK, 0);

  if( bFlush && pDb->bAutowork==0 && pDb->xWork ){
    pDb->xWork(pDb, pDb->pWorkCtx);
  }
  return rc;
}


................................................................................
static int slotIsUsable(ShmReader *p, i64 iLsm, u32 iShmMin, u32 iShmMax){
  return( 
      p->iLsmId && p->iLsmId<=iLsm 
      && shm_sequence_ge(iShmMax, p->iTreeId)
      && shm_sequence_ge(p->iTreeId, iShmMin)
  );
}
















































/*
** Obtain a read-lock on database version identified by the combination
** of snapshot iLsm and tree iTree. Return LSM_OK if successful, or
** an LSM error code otherwise.
*/
int lsmReadlock(lsm_db *db, i64 iLsm, u32 iShmMin, u32 iShmMax){
................................................................................
** Ensure that database connection db has cached pointers to at least the 
** first nChunk chunks of shared memory.
*/
int lsmShmCacheChunks(lsm_db *db, int nChunk){
  int rc = LSM_OK;
  if( nChunk>db->nShm ){
    static const int NINCR = 16;
    void *pRet = 0;
    Database *p = db->pDatabase;
    lsm_env *pEnv = db->pEnv;
    int nAlloc;
    int i;

    /* Ensure that the db->apShm[] array is large enough. If an attempt to
    ** allocate memory fails, return LSM_NOMEM immediately. The apShm[] array

** but then not used. This function is used to push the block back onto
** the freelist. Refreeing a block is different from freeing is, as a refreed
** block may be reused immediately. Whereas a freed block can not be reused 
** until (at least) after the next checkpoint.
*/
int lsmBlockRefree(lsm_db *pDb, int iBlk){
  int rc = LSM_OK;                /* Return code */


#ifdef LSM_LOG_FREELIST
  lsmLogMessage(pDb, LSM_OK, "lsmBlockRefree(): Refree block %d", iBlk);
#endif

  rc = freelistAppend(pDb, iBlk, 0);
  return rc;
................................................................................
/*
** Argument bFlush is true if the contents of the in-memory tree has just
** been flushed to disk. The significance of this is that once the snapshot
** created to hold the updated state of the database is synced to disk, log
** file space can be recycled.
*/
void lsmFinishWork(lsm_db *pDb, int bFlush, int *pRc){
  int rc = *pRc;
  assert( rc!=0 || pDb->pWorker );
  if( pDb->pWorker ){
    /* If no error has occurred, serialize the worker snapshot and write
    ** it to shared memory.  */
    if( rc==LSM_OK ){
      rc = lsmSaveWorker(pDb, bFlush);
    }

    /* Assuming no error has occurred, update a read lock slot with the
    ** new snapshot id (see comments above function lsmSetReadLock()).  */
    if( rc==LSM_OK ){
      if( pDb->iReader<0 ){
        rc = lsmTreeLoadHeader(pDb, 0);
      }
      if( rc==LSM_OK ){
        rc = lsmSetReadLock(pDb, pDb->pWorker->iId, pDb->treehdr.iUsedShmid);
      }
    }

    /* Free the snapshot object. */
    lsmFreeSnapshot(pDb->pEnv, pDb->pWorker);
    pDb->pWorker = 0;
  }

  lsmShmLock(pDb, LSM_LOCK_WORKER, LSM_LOCK_UNLOCK, 0);
  *pRc = rc;
}

/*
** Called when recovery is finished.
*/
int lsmFinishRecovery(lsm_db *pDb){
  lsmTreeEndTransaction(pDb, 1);
................................................................................
** Open a write transaction.
*/
int lsmBeginWriteTrans(lsm_db *pDb){
  int rc;                         /* Return code */
  ShmHeader *pShm = pDb->pShmhdr; /* Shared memory header */

  assert( pDb->nTransOpen==0 );
  assert( pDb->bDiscardOld==0 );

  /* If there is no read-transaction open, open one now. */
  rc = lsmBeginReadTrans(pDb);

  /* Attempt to take the WRITER lock */
  if( rc==LSM_OK ){
    rc = lsmShmLock(pDb, LSM_LOCK_WRITER, LSM_LOCK_EXCL, 0);
................................................................................
  ** WRITER lock and return an error code.  */
  if( rc==LSM_OK ){
    TreeHeader *p = &pDb->treehdr;
    pShm->bWriter = 1;
    p->root.iTransId++;
    if( lsmTreeHasOld(pDb) && p->iOldLog==pDb->pClient->iLogOff ){
      lsmTreeDiscardOld(pDb);
      pDb->bDiscardOld = 1;
    }
  }else{
    lsmShmLock(pDb, LSM_LOCK_WRITER, LSM_LOCK_UNLOCK, 0);
    if( pDb->pCsr==0 ) lsmFinishReadTrans(pDb);
  }
  return rc;
}
................................................................................
  lsmLogEnd(pDb, bCommit);
  if( rc==LSM_OK && bCommit && lsmTreeSize(pDb)>pDb->nTreeLimit ){
    bFlush = 1;
    lsmTreeMakeOld(pDb);
  }
  lsmTreeEndTransaction(pDb, bCommit);

  if( rc==LSM_OK ){
    if( bFlush && pDb->bAutowork ){
      rc = lsmSortedAutoWork(pDb, 1);
    }else if( bCommit && pDb->bDiscardOld ){
      rc = lsmSetReadLock(pDb, pDb->pClient->iId, pDb->treehdr.iUsedShmid);
    }
  }
  pDb->bDiscardOld = 0;
  lsmShmLock(pDb, LSM_LOCK_WRITER, LSM_LOCK_UNLOCK, 0);

  if( bFlush && pDb->bAutowork==0 && pDb->xWork ){
    pDb->xWork(pDb, pDb->pWorkCtx);
  }
  return rc;
}


................................................................................
static int slotIsUsable(ShmReader *p, i64 iLsm, u32 iShmMin, u32 iShmMax){
  return( 
      p->iLsmId && p->iLsmId<=iLsm 
      && shm_sequence_ge(iShmMax, p->iTreeId)
      && shm_sequence_ge(p->iTreeId, iShmMin)
  );
}

/*
** Attempt to populate one of the read-lock slots to contain lock values
** iLsm/iShm. Or, if such a slot exists already, this function is a no-op.
**
** It is not an error if no slot can be populated because the write-lock
** cannot be obtained. If any other error occurs, return an LSM error code.
** Otherwise, LSM_OK.
**
** This function is called at various points to try to ensure that there
** always exists at least one read-lock slot that can be used by a read-only
** client. And so that, in the usual case, there is an "exact match" available
** whenever a read transaction is opened by any client. At present this
** function is called when:
**
**    * A write transaction that called lsmTreeDiscardOld() is committed, and
**    * Whenever the working snapshot is updated (i.e. lsmFinishWork()).
*/
int lsmSetReadLock(lsm_db *db, i64 iLsm, u32 iShm){
  int rc = LSM_OK;
  ShmHeader *pShm = db->pShmhdr;
  int i;

  /* Check if there is already a slot containing the required values. */
  for(i=0; i<LSM_LOCK_NREADER; i++){
    ShmReader *p = &pShm->aReader[i];
    if( p->iLsmId==iLsm && p->iTreeId==iShm ) return LSM_OK;
  }

  /* Iterate through all read-lock slots, attempting to take a write-lock
  ** on each of them. If a write-lock succeeds, populate the locked slot
  ** with the required values and break out of the loop.  */
  for(i=0; rc==LSM_OK && i<LSM_LOCK_NREADER; i++){
    rc = lsmShmLock(db, LSM_LOCK_READER(i), LSM_LOCK_EXCL, 0);
    if( rc==LSM_BUSY ){
      rc = LSM_OK;
    }else{
      ShmReader *p = &pShm->aReader[i];
      p->iLsmId = iLsm;
      p->iTreeId = iShm;
      lsmShmLock(db, LSM_LOCK_READER(i), LSM_LOCK_UNLOCK, 0);
      break;
    }
  }

  return rc;
}

/*
** Obtain a read-lock on database version identified by the combination
** of snapshot iLsm and tree iTree. Return LSM_OK if successful, or
** an LSM error code otherwise.
*/
int lsmReadlock(lsm_db *db, i64 iLsm, u32 iShmMin, u32 iShmMax){
................................................................................
** Ensure that database connection db has cached pointers to at least the 
** first nChunk chunks of shared memory.
*/
int lsmShmCacheChunks(lsm_db *db, int nChunk){
  int rc = LSM_OK;
  if( nChunk>db->nShm ){
    static const int NINCR = 16;

    Database *p = db->pDatabase;
    lsm_env *pEnv = db->pEnv;
    int nAlloc;
    int i;

    /* Ensure that the db->apShm[] array is large enough. If an attempt to
    ** allocate memory fails, return LSM_NOMEM immediately. The apShm[] array

<ol>
  <li> <p>Load the current tree-header from shared-memory.

  <li> <p>Load the current snapshot from shared-memory.
<p>Steps 1 and 2 are similar. In both cases, there are two copies
of the data structure being read in shared memory. No lock is held to prevent
another client updating them while the read is taking place using the following
pattern:

<ol type=i>
  <li> Update copy 2.
  <li> Invoke xShmBarrier().
  <li> Update copy 1.
</ol>

<ol>
  <li> <p>Load the current tree-header from shared-memory.

  <li> <p>Load the current snapshot from shared-memory.
<p>Steps 1 and 2 are similar. In both cases, there are two copies
of the data structure being read in shared memory. No lock is held to prevent
another client updating them while the read is taking place. Updaters use the
following pattern:

<ol type=i>
  <li> Update copy 2.
  <li> Invoke xShmBarrier().
  <li> Update copy 1.
</ol>