SQLite

Check-in [2e6a462ceb]
Login

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

Overview
Comment:Make sure the wal-index reader detects an incorrect version number even if it had to hold a lock in order to read the wal-index. Also, expand and enhance various comments in wal.c.
Downloads: Tarball | ZIP archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: 2e6a462cebc05bfd4648d26dd5ae70b68844aa5f
User & Date: drh 2010-06-24 02:46:49.000
Context
2010-06-24
10:50
Add coverage tests. Remove a NEVER macro from pager.c, as the condition can now be true in wal mode. (check-in: 7aac9ad6dd user: dan tags: trunk)
02:46
Make sure the wal-index reader detects an incorrect version number even if it had to hold a lock in order to read the wal-index. Also, expand and enhance various comments in wal.c. (check-in: 2e6a462ceb user: drh tags: trunk)
2010-06-23
22:00
Fix and/or improve comments in wal.c. No code changes. (check-in: ee9991be08 user: drh tags: trunk)
Changes
Unified Diff Ignore Whitespace Patch
Changes to src/wal.c.
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712

  /* The header was successfully read. Return zero. */
  return 0;
}

/*
** Read the wal-index header from the wal-index and into pWal->hdr.
** If the wal-header appears to be corrupt, try to recover the log
** before returning.
**
** Set *pChanged to 1 if the wal-index header value in pWal->hdr is
** changed by this opertion.  If pWal->hdr is unchanged, set *pChanged
** to 0.
**
** This routine also maps the wal-index content into memory and assigns
** ownership of that mapping to the current thread.  In some implementations,
** only one thread at a time can hold a mapping of the wal-index.  Hence,
** the caller should strive to invoke walIndexUnmap() as soon as possible
** after this routine returns.
**
** If the wal-index header is successfully read, return SQLITE_OK. 
** Otherwise an SQLite error code.
*/
static int walIndexReadHdr(Wal *pWal, int *pChanged){
  int rc;                         /* Return code */
  int badHdr;                     /* True if a header read failed */
  volatile u32 *page0;

  /* Ensure that page 0 of the wal-index (the page that contains the 
  ** wal-index header) is mapped. Return early if an error occurs here.
  */
  assert( pChanged );
  rc = walIndexPage(pWal, 0, &page0);
  if( rc!=SQLITE_OK ){
    return rc;
  };
  assert( page0 || pWal->writeLock==0 );

  /* If the first page of the wal-index has been mapped, try to read the
  ** wal-index header immediately, without holding any lock. This usually
  ** works, but may fail if the wal-index header is corrupt or currently 
  ** being modified by another user.
  */
  badHdr = (page0 ? walIndexTryHdr(pWal, pChanged) : 1);
  if( badHdr==0 && pWal->hdr.iVersion!=WALINDEX_MAX_VERSION ){
    rc = SQLITE_CANTOPEN_BKPT;
  }

  /* If the first attempt failed, it might have been due to a race
  ** with a writer.  So get a WRITE lock and try again.
  */
  assert( badHdr==0 || pWal->writeLock==0 );
  if( badHdr && SQLITE_OK==(rc = walLockExclusive(pWal, WAL_WRITE_LOCK, 1)) ){
    pWal->writeLock = 1;







|
|





<
<
<
<
<
<






|














|


<
<
<







1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672






1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696



1697
1698
1699
1700
1701
1702
1703

  /* The header was successfully read. Return zero. */
  return 0;
}

/*
** Read the wal-index header from the wal-index and into pWal->hdr.
** If the wal-header appears to be corrupt, try to reconstruct the
** wal-index from the WAL before returning.
**
** Set *pChanged to 1 if the wal-index header value in pWal->hdr is
** changed by this opertion.  If pWal->hdr is unchanged, set *pChanged
** to 0.
**






** If the wal-index header is successfully read, return SQLITE_OK. 
** Otherwise an SQLite error code.
*/
static int walIndexReadHdr(Wal *pWal, int *pChanged){
  int rc;                         /* Return code */
  int badHdr;                     /* True if a header read failed */
  volatile u32 *page0;            /* Chunk of wal-index containing header */

  /* Ensure that page 0 of the wal-index (the page that contains the 
  ** wal-index header) is mapped. Return early if an error occurs here.
  */
  assert( pChanged );
  rc = walIndexPage(pWal, 0, &page0);
  if( rc!=SQLITE_OK ){
    return rc;
  };
  assert( page0 || pWal->writeLock==0 );

  /* If the first page of the wal-index has been mapped, try to read the
  ** wal-index header immediately, without holding any lock. This usually
  ** works, but may fail if the wal-index header is corrupt or currently 
  ** being modified by another thread or process.
  */
  badHdr = (page0 ? walIndexTryHdr(pWal, pChanged) : 1);




  /* If the first attempt failed, it might have been due to a race
  ** with a writer.  So get a WRITE lock and try again.
  */
  assert( badHdr==0 || pWal->writeLock==0 );
  if( badHdr && SQLITE_OK==(rc = walLockExclusive(pWal, WAL_WRITE_LOCK, 1)) ){
    pWal->writeLock = 1;
1720
1721
1722
1723
1724
1725
1726








1727
1728
1729
1730
1731
1732
1733
1734
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
        rc = walIndexRecover(pWal);
        *pChanged = 1;
      }
    }
    pWal->writeLock = 0;
    walUnlockExclusive(pWal, WAL_WRITE_LOCK, 1);
  }









  return rc;
}

/*
** This is the value that walTryBeginRead returns when it needs to
** be retried.
*/
#define WAL_RETRY  (-1)

/*
** Attempt to start a read transaction.  This might fail due to a race or
** other transient condition.  When that happens, it returns WAL_RETRY to
** indicate to the caller that it is safe to retry immediately.
**
** On success return SQLITE_OK.  On a permantent failure (such an
** I/O error or an SQLITE_BUSY because another process is running
** recovery) return a positive error code.




















**
** On success, this routine obtains a read lock on 
** WAL_READ_LOCK(pWal->readLock).  The pWal->readLock integer is
** in the range 0 <= pWal->readLock < WAL_NREADER.  If pWal->readLock==(-1)
** that means the Wal does not hold any read lock.  The reader must not
** access any database page that is modified by a WAL frame up to and
** including frame number aReadMark[pWal->readLock].  The reader will
** use WAL frames up to and including pWal->hdr.mxFrame if pWal->readLock>0
** Or if pWal->readLock==0, then the reader will ignore the WAL
** completely and get all content directly from the database file.


** When the read transaction is completed, the caller must release the
** lock on WAL_READ_LOCK(pWal->readLock) and set pWal->readLock to -1.
**
** This routine uses the nBackfill and aReadMark[] fields of the header
** to select a particular WAL_READ_LOCK() that strives to let the
** checkpoint process do as much work as possible.  This routine might
** update values of the aReadMark[] array in the header, but if it does







>
>
>
>
>
>
>
>















|


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










>
>







1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
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
        rc = walIndexRecover(pWal);
        *pChanged = 1;
      }
    }
    pWal->writeLock = 0;
    walUnlockExclusive(pWal, WAL_WRITE_LOCK, 1);
  }

  /* If the header is read successfully, check the version number to make
  ** sure the wal-index was not constructed with some future format that
  ** this version of SQLite cannot understand.
  */
  if( badHdr==0 && pWal->hdr.iVersion!=WALINDEX_MAX_VERSION ){
    rc = SQLITE_CANTOPEN_BKPT;
  }

  return rc;
}

/*
** This is the value that walTryBeginRead returns when it needs to
** be retried.
*/
#define WAL_RETRY  (-1)

/*
** Attempt to start a read transaction.  This might fail due to a race or
** other transient condition.  When that happens, it returns WAL_RETRY to
** indicate to the caller that it is safe to retry immediately.
**
** On success return SQLITE_OK.  On a permanent failure (such an
** I/O error or an SQLITE_BUSY because another process is running
** recovery) return a positive error code.
**
** The useWal parameter is true to force the use of the WAL and disable
** the case where the WAL is bypassed because it has been completely
** checkpointed.  If useWal==0 then this routine calls walIndexReadHdr() 
** to make a copy of the wal-index header into pWal->hdr.  If the 
** wal-index header has changed, *pChanged is set to 1 (as an indication 
** to the caller that the local paget cache is obsolete and needs to be 
** flushed.)  When useWal==1, the wal-index header is assumed to already
** be loaded and the pChanged parameter is unused.
**
** The caller must set the cnt parameter to the number of prior calls to
** this routine during the current read attempt that returned WAL_RETRY.
** This routine will start taking more aggressive measures to clear the
** race conditions after multiple WAL_RETRY returns, and after an excessive
** number of errors will ultimately return SQLITE_PROTOCOL.  The
** SQLITE_PROTOCOL return indicates that some other process has gone rogue
** and is not honoring the locking protocol.  There is a vanishingly small
** chance that SQLITE_PROTOCOL could be returned because of a run of really
** bad luck when there is lots of contention for the wal-index, but that
** possibility is so small that it can be safely neglected, we believe.
**
** On success, this routine obtains a read lock on 
** WAL_READ_LOCK(pWal->readLock).  The pWal->readLock integer is
** in the range 0 <= pWal->readLock < WAL_NREADER.  If pWal->readLock==(-1)
** that means the Wal does not hold any read lock.  The reader must not
** access any database page that is modified by a WAL frame up to and
** including frame number aReadMark[pWal->readLock].  The reader will
** use WAL frames up to and including pWal->hdr.mxFrame if pWal->readLock>0
** Or if pWal->readLock==0, then the reader will ignore the WAL
** completely and get all content directly from the database file.
** If the useWal parameter is 1 then the WAL will never be ignored and
** this routine will always set pWal->readLock>0 on success.
** When the read transaction is completed, the caller must release the
** lock on WAL_READ_LOCK(pWal->readLock) and set pWal->readLock to -1.
**
** This routine uses the nBackfill and aReadMark[] fields of the header
** to select a particular WAL_READ_LOCK() that strives to let the
** checkpoint process do as much work as possible.  This routine might
** update values of the aReadMark[] array in the header, but if it does
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801

1802
1803
1804
1805
1806
1807
1808
      if( rc==SQLITE_OK ){
        walUnlockShared(pWal, WAL_RECOVER_LOCK);
        rc = WAL_RETRY;
      }else if( rc==SQLITE_BUSY ){
        rc = SQLITE_BUSY_RECOVERY;
      }
    }
  }
  if( rc!=SQLITE_OK ){
    return rc;

  }

  pInfo = walCkptInfo(pWal);
  if( !useWal && pInfo->nBackfill==pWal->hdr.mxFrame ){
    /* The WAL has been completely backfilled (or it is empty).
    ** and can be safely ignored.
    */







<
|
|
>







1813
1814
1815
1816
1817
1818
1819

1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
      if( rc==SQLITE_OK ){
        walUnlockShared(pWal, WAL_RECOVER_LOCK);
        rc = WAL_RETRY;
      }else if( rc==SQLITE_BUSY ){
        rc = SQLITE_BUSY_RECOVERY;
      }
    }

    if( rc!=SQLITE_OK ){
      return rc;
    }
  }

  pInfo = walCkptInfo(pWal);
  if( !useWal && pInfo->nBackfill==pWal->hdr.mxFrame ){
    /* The WAL has been completely backfilled (or it is empty).
    ** and can be safely ignored.
    */
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
  int iHash;                      /* Used to loop through N hash tables */

  /* 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 to avoid the walIndexMap/Unmap overhead.  Likewise, if
  ** pWal->readLock==0, then the WAL is ignored by the reader so
  ** return early, as if the WAL were empty.
  */
  if( iLast==0 || pWal->readLock==0 ){
    *pInWal = 0;
    return SQLITE_OK;
  }

  /* Search the hash table or tables for an entry matching page number
  ** pgno. Each iteration of the following for() loop searches one
  ** hash table (each hash table indexes up to HASHTABLE_NPAGE frames).
  **
  ** This code may 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







|
|
|










|







1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
  int iHash;                      /* Used to loop through N hash tables */

  /* 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 ){
    *pInWal = 0;
    return SQLITE_OK;
  }

  /* Search the hash table or tables for an entry matching page number
  ** pgno. Each iteration of the following for() loop searches one
  ** hash table (each hash table indexes up to HASHTABLE_NPAGE frames).
  **
  ** This code might run concurrently to the code in walIndexAppend()
  ** that adds entries to the wal-index (and possibly to this hash 
  ** table). This means the value just read from the hash 
  ** slot (aHash[iKey]) may have been added before or after the 
  ** current read transaction was opened. Values added after the
  ** read transaction was opened may have been written incorrectly -
  ** i.e. these slots may contain garbage data. However, we assume
  ** that any slots written before the current read transaction was