SQLite

** The pager is used to access a database disk file.  It implements
** atomic commit and rollback through the use of a journal file that
** is separate from the database file.  The pager also implements file
** locking to prevent two processes from writing the same database
** file simultaneously, or one process from reading the database while
** another is writing.
**
** @(#) $Id: pager.c,v 1.205 2005/05/21 02:48:09 drh Exp $
*/
#ifndef SQLITE_OMIT_DISKIO
#include "sqliteInt.h"
#include "os.h"
#include "pager.h"
#include <assert.h>
#include <string.h>

*/
#define pager_hash(PN)  ((PN)&(N_PG_HASH-1))

/*
** A open page cache is an instance of the following structure.
*/
struct Pager {

















  u8 journalOpen;             /* True if journal file descriptors is valid */
  u8 journalStarted;          /* True if header of journal is synced */
  u8 useJournal;              /* Use a rollback journal on this file */
  u8 noReadlock;              /* Do not bother to obtain readlocks */
  u8 stmtOpen;                /* True if the statement subjournal is open */
  u8 stmtInUse;               /* True we are in a statement subtransaction */
  u8 stmtAutoopen;            /* Open stmt journal when main journal is opened*/
  u8 noSync;                  /* Do not sync the journal if true */
  u8 fullSync;                /* Do extra syncs of the journal for robustness */
  u8 state;                   /* PAGER_UNLOCK, _SHARED, _RESERVED, etc. */
  u8 errMask;                 /* One of several kinds of errors */
  u8 tempFile;                /* zFilename is a temporary file */
  u8 readOnly;                /* True for a read-only database */
  u8 needSync;                /* True if an fsync() is needed on the journal */
  u8 dirtyCache;              /* True if cached pages have changed */
  u8 alwaysRollback;          /* Disable dont_rollback() for all pages */
  u8 memDb;                   /* True to inhibit all file I/O */
  u8 setMaster;               /* True if a m-j name has been written to jrnl */
  int dbSize;                 /* Number of pages in the file */
  int origDbSize;             /* dbSize before the current change */
  int stmtSize;               /* Size of database (in pages) at stmt_begin() */
  int nRec;                   /* Number of pages written to the journal */
  u32 cksumInit;              /* Quasi-random value added to every checksum */
  int stmtNRec;               /* Number of records in stmt subjournal */
  int nExtra;                 /* Add this many bytes to each in-memory page */
  int pageSize;               /* Number of bytes in a page */
  int nPage;                  /* Total number of in-memory pages */
  int nMaxPage;               /* High water mark of nPage */
  int nRef;                   /* Number of in-memory pages with PgHdr.nRef>0 */
  int mxPage;                 /* Maximum number of pages to hold in cache */
  u8 *aInJournal;             /* One bit for each page in the database file */
  u8 *aInStmt;                /* One bit for each page in the database */
  char *zFilename;            /* Name of the database file */
  char *zJournal;             /* Name of the journal file */
  char *zDirectory;           /* Directory hold database and journal files */
  OsFile fd, jfd;             /* File descriptors for database and journal */
  OsFile stfd;                /* File descriptor for the statement subjournal*/
  BusyHandler *pBusyHandler;  /* Pointer to sqlite.busyHandler */
  PgHdr *pFirst, *pLast;      /* List of free pages */
  PgHdr *pFirstSynced;        /* First free page with PgHdr.needSync==0 */
  PgHdr *pAll;                /* List of all pages */
  PgHdr *pStmt;               /* List of pages in the statement subjournal */
  i64 journalOff;             /* Current byte offset in the journal file */
  i64 journalHdr;             /* Byte offset to previous journal header */
  i64 stmtHdrOff;             /* First journal header written this statement */
  i64 stmtCksum;              /* cksumInit when statement was started */
  i64 stmtJSize;              /* Size of journal at stmt_begin() */
  int sectorSize;             /* Assumed sector size during rollback */
#ifdef SQLITE_TEST
  int nHit, nMiss, nOvfl;     /* Cache hits, missing, and LRU overflows */
  int nRead,nWrite;           /* Database pages read/written */
#endif
  void (*xDestructor)(void*,int); /* Call this routine when freeing pages */
  void (*xReiniter)(void*,int);   /* Call this routine when reloading pages */
  void (*xCodec)(void*,void*,Pgno,int); /* Routine for en/decoding data */
  void *pCodecArg;            /* First argument to xCodec() */
  PgHdr *aHash[N_PG_HASH];    /* Hash table to map page number to PgHdr */
};

/*
** If SQLITE_TEST is defined then increment the variable given in
** the argument
*/
#ifdef SQLITE_TEST
# define TEST_INCR(x)  x++
#else
# define TEST_INCR(x)
#endif

/*
** These are bits that can be set in Pager.errMask.
*/
#define PAGER_ERR_FULL     0x01  /* a write() failed */
#define PAGER_ERR_MEM      0x02  /* malloc() failed */
#define PAGER_ERR_LOCK     0x04  /* error in the locking protocol */
#define PAGER_ERR_CORRUPT  0x08  /* database or journal corruption */

    ** any such pages to the file.
    */
    if( pList->pgno<=pPager->dbSize ){
      CODEC(pPager, PGHDR_TO_DATA(pList), pList->pgno, 6);
      TRACE3("STORE %d page %d\n", PAGERID(pPager), pList->pgno);
      rc = sqlite3OsWrite(&pPager->fd, PGHDR_TO_DATA(pList), pPager->pageSize);
      CODEC(pPager, PGHDR_TO_DATA(pList), pList->pgno, 0);
      TEST_INCR(pPager->nWrite);
    }
#ifndef NDEBUG
    else{
      TRACE3("NOSTORE %d page %d\n", PAGERID(pPager), pList->pgno);
    }
#endif
    if( rc ) return rc;

    if( MEMDB && pPager->state==PAGER_UNLOCK ){
      pPager->state = PAGER_SHARED;
    }
  }
  if( pPg==0 ){
    /* The requested page is not in the page cache. */
    int h;
    TEST_INCR(pPager->nMiss);
    if( pPager->nPage<pPager->mxPage || pPager->pFirst==0 || MEMDB ){
      /* Create a new page */
      pPg = sqliteMallocRaw( sizeof(*pPg) + pPager->pageSize
                              + sizeof(u32) + pPager->nExtra
                              + MEMDB*sizeof(PgHistory) );
      if( pPg==0 ){
        pPager->errMask |= PAGER_ERR_MEM;

      if( pPg->alwaysRollback ){
        pPager->alwaysRollback = 1;
      }

      /* Unlink the old page from the free list and the hash table
      */
      unlinkPage(pPg);
      TEST_INCR(pPager->nOvfl);
    }
    pPg->pgno = pgno;
    if( pPager->aInJournal && (int)pgno<=pPager->origDbSize ){
      sqlite3CheckMemory(pPager->aInJournal, pgno/8);
      assert( pPager->journalOpen );
      pPg->inJournal = (pPager->aInJournal[pgno/8] & (1<<(pgno&7)))!=0;
      pPg->needSync = 0;

               || fileSize>=pgno*pPager->pageSize ){
          sqlite3pager_unref(PGHDR_TO_DATA(pPg));
          return rc;
        }else{
          memset(PGHDR_TO_DATA(pPg), 0, pPager->pageSize);
        }
      }else{
        TEST_INCR(pPager->nRead);
      }
    }
#ifdef SQLITE_CHECK_PAGES
    pPg->pageHash = pager_pagehash(pPg);
#endif
  }else{
    /* The requested page is in the page cache. */
    TEST_INCR(pPager->nHit);
    page_ref(pPg);
  }
  *ppPage = PGHDR_TO_DATA(pPg);
  return SQLITE_OK;
}

/*

  static int a[11];
  a[0] = pPager->nRef;
  a[1] = pPager->nPage;
  a[2] = pPager->mxPage;
  a[3] = pPager->dbSize;
  a[4] = pPager->state;
  a[5] = pPager->errMask;
#ifdef SQLITE_TEST
  a[6] = pPager->nHit;
  a[7] = pPager->nMiss;
  a[8] = pPager->nOvfl;
  a[9] = pPager->nRead;
  a[10] = pPager->nWrite;
#endif
  return a;
}

/*
** Set the statement rollback point.
**
** This routine should be called with the transaction journal already

/*
** 2001 September 15
**
** 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.
**
*************************************************************************
** Internal interface definitions for SQLite.
**
** @(#) $Id: sqliteInt.h,v 1.379 2005/05/21 02:48:09 drh Exp $
*/
#ifndef _SQLITEINT_H_
#define _SQLITEINT_H_

/*
** These #defines should enable >2GB file support on Posix if the
** underlying operating system supports it.  If the OS lacks

** store the most recent error code and, if applicable, string. The
** internal function sqlite3Error() is used to set these variables
** consistently.
*/
struct sqlite3 {
  int nDb;                      /* Number of backends currently in use */
  Db *aDb;                      /* All backends */

  int flags;                    /* Miscellanous flags. See below */
  int errCode;                  /* Most recent error code (SQLITE_*) */
  u8 enc;                       /* Text encoding for this database. */
  u8 autoCommit;                /* The auto-commit flag. */
  u8 file_format;               /* What file format version is this database? */
  u8 temp_store;                /* 1: file 2: memory 0: default */
  int nTable;                   /* Number of tables in the database */





  CollSeq *pDfltColl;           /* The default collating sequence (BINARY) */
  i64 lastRowid;                /* ROWID of most recent insert (see above) */
  i64 priorNewRowid;            /* Last randomly generated ROWID */
  int magic;                    /* Magic number for detect library misuse */
  int nChange;                  /* Value returned by sqlite3_changes() */
  int nTotalChange;             /* Value returned by sqlite3_total_changes() */
  struct sqlite3InitInfo {      /* Information used during initialization */
    int iDb;                    /* When back is being initialized */
    int newTnum;                /* Rootpage of table being initialized */
    u8 busy;                    /* TRUE if currently initializing */
  } init;
  struct Vdbe *pVdbe;           /* List of active virtual machines */
  int activeVdbeCnt;            /* Number of vdbes currently executing */
  void (*xTrace)(void*,const char*);     /* Trace function */
  void *pTraceArg;                       /* Argument to the trace function */
  void *pCommitArg;             /* Argument to xCommitCallback() */   
  int (*xCommitCallback)(void*);/* Invoked at every commit. */
  void(*xCollNeeded)(void*,sqlite3*,int eTextRep,const char*);
  void(*xCollNeeded16)(void*,sqlite3*,int eTextRep,const void*);
  void *pCollNeededArg;
  sqlite3_value *pValue;        /* Value used for transient conversions */
  sqlite3_value *pErr;          /* Most recent error message */
  char *zErrMsg;                /* Most recent error message (UTF-8 encoded) */
  char *zErrMsg16;              /* Most recent error message (UTF-16 encoded) */
#ifndef SQLITE_OMIT_AUTHORIZATION
  int (*xAuth)(void*,int,const char*,const char*,const char*,const char*);
                                /* Access authorization function */
  void *pAuthArg;               /* 1st argument to the access auth function */
#endif
#ifndef SQLITE_OMIT_PROGRESS_CALLBACK
  int (*xProgress)(void *);     /* The progress callback */
  void *pProgressArg;           /* Argument to the progress callback */
  int nProgressOps;             /* Number of opcodes for progress callback */
#endif










#ifndef SQLITE_OMIT_GLOBALRECOVER
  sqlite3 *pNext;               /* Linked list of open db handles. */
#endif
  Hash aFunc;                   /* All functions that can be in SQL exprs */
  Hash aCollSeq;                /* All collating sequences */
  BusyHandler busyHandler;      /* Busy callback */
  Db aDbStatic[2];              /* Static space for the 2 default backends */
};

/*
** Possible values for the sqlite.flags and or Db.flags fields.
**
** On sqlite.flags, the SQLITE_InTrans value means that we have
** executed a BEGIN.  On Db.flags, SQLITE_InTrans means a statement

  int rc;              /* Return code from execution */
  char *zErrMsg;       /* An error message */
  Vdbe *pVdbe;         /* An engine for executing database bytecode */
  u8 colNamesSet;      /* TRUE after OP_ColumnName has been issued to pVdbe */
  u8 nameClash;        /* A permanent table name clashes with temp table name */
  u8 checkSchema;      /* Causes schema cookie check after an error */
  u8 nested;           /* Number of nested calls to the parser/code generator */
  u8 fillAgg;          /* If true, ignore the Expr.iAgg field. Normally false */
  int nErr;            /* Number of errors seen */
  int nTab;            /* Number of previously allocated VDBE cursors */
  int nMem;            /* Number of memory cells used so far */
  int nSet;            /* Number of sets used so far */
  u32 writeMask;       /* Start a write transaction on these databases */
  u32 cookieMask;      /* Bitmask of schema verified databases */

  int cookieGoto;      /* Address of OP_Goto to cookie verifier subroutine */
  int cookieValue[MAX_ATTACHED+2];  /* Values of cookies to verify */


  /* Above is constant between recursions.  Below is reset before and after
  ** each recursion */

  int nVar;            /* Number of '?' variables seen in the SQL so far */
  int nVarExpr;        /* Number of used slots in apVarExpr[] */
  int nVarExprAlloc;   /* Number of allocated slots in apVarExpr[] */