/ Check-in [fd578a32]
Login

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

Overview
Comment:Changes to make WAL more robust against SQLITE_PROTOCOL errors.
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: fd578a32f8e9f04957359e73f244a60f02afe08c
User & Date: drh 2011-02-19 15:22:14
Context
2011-02-19
16:51
Add testcase macros to verify that all return values from walTryBeginRead() are tested. check-in: 262b6fca user: drh tags: trunk
15:22
Changes to make WAL more robust against SQLITE_PROTOCOL errors. check-in: fd578a32 user: drh tags: trunk
2011-02-18
17:23
Fix the sqlite3ValueFromExpr() routine so that it returns SQLITE_NOMEM on an OOM when trying to extract a NULL. check-in: 1061e94f user: drh tags: trunk
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to src/wal.c.

1997
1998
1999
2000
2001
2002
2003
2004
















2005

2006

2007
2008
2009
2010
2011
2012
2013
2014
....
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
....
2487
2488
2489
2490
2491
2492
2493


2494
2495
2496
2497
2498
2499
2500
....
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
  u32 mxReadMark;                 /* Largest aReadMark[] value */
  int mxI;                        /* Index of largest aReadMark[] value */
  int i;                          /* Loop counter */
  int rc = SQLITE_OK;             /* Return code  */

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

  /* Take steps to avoid spinning forever if there is a protocol error. */
















  if( cnt>5 ){

    if( cnt>100 ) return SQLITE_PROTOCOL;

    sqlite3OsSleep(pWal->pVfs, 1);
  }

  if( !useWal ){
    rc = walIndexReadHdr(pWal, pChanged);
    if( rc==SQLITE_BUSY ){
      /* If there is not a recovery running in another thread or process
      ** then convert BUSY errors to WAL_RETRY.  If recovery is known to
................................................................................
    u32 thisMark = pInfo->aReadMark[i];
    if( mxReadMark<=thisMark && thisMark<=pWal->hdr.mxFrame ){
      assert( thisMark!=READMARK_NOT_USED );
      mxReadMark = thisMark;
      mxI = i;
    }
  }
  if( mxI==0 ){
    /* If we get here, it means that all of the aReadMark[] entries between
    ** 1 and WAL_NREADER-1 are zero.  Try to initialize aReadMark[1] to
    ** be mxFrame, then retry.
    */
    rc = walLockExclusive(pWal, WAL_READ_LOCK(1), 1);
    if( rc==SQLITE_OK ){
      pInfo->aReadMark[1] = pWal->hdr.mxFrame;
      walUnlockExclusive(pWal, WAL_READ_LOCK(1), 1);
      rc = WAL_RETRY;
    }else if( rc==SQLITE_BUSY ){
      rc = WAL_RETRY;
    }
    return rc;
  }else{

    if( mxReadMark < pWal->hdr.mxFrame ){
      for(i=1; i<WAL_NREADER; i++){
        rc = walLockExclusive(pWal, WAL_READ_LOCK(i), 1);
        if( rc==SQLITE_OK ){
          mxReadMark = pInfo->aReadMark[i] = pWal->hdr.mxFrame;
          mxI = i;
          walUnlockExclusive(pWal, WAL_READ_LOCK(i), 1);
          break;
        }else if( rc!=SQLITE_BUSY ){
          return rc;
        }
      }
    }





    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
................................................................................
  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 ){


      rc = walLockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1);
      if( rc==SQLITE_OK ){
        /* If all readers are using WAL_READ_LOCK(0) (in other words if no
        ** readers are currently using the WAL), then the transactions
        ** frames will overwrite the start of the existing log. Update the
        ** wal-index header to reflect this.
        **
................................................................................
        ** to handle if this transaction is rolled back.
        */
        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]));
        sqlite3_randomness(4, &aSalt[1]);
        walIndexWriteHdr(pWal);
        pInfo->nBackfill = 0;
        for(i=1; i<WAL_NREADER; i++) pInfo->aReadMark[i] = READMARK_NOT_USED;
        assert( pInfo->aReadMark[0]==0 );
        walUnlockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1);
      }else if( rc!=SQLITE_BUSY ){
        return rc;







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

>

>
|







 







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












>
>
>
>







 







>
>







 







|







1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
....
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
....
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
....
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
  u32 mxReadMark;                 /* Largest aReadMark[] value */
  int mxI;                        /* Index of largest aReadMark[] value */
  int i;                          /* Loop counter */
  int rc = SQLITE_OK;             /* Return code  */

  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
  ** paged out or take a page-fault that is time-consuming to resolve, 
  ** during the few nanoseconds that it is holding the lock.  In that case,
  ** it might take longer than normal for the lock to free.
  **
  ** After 5 RETRYs, we begin calling sqlite3OsSleep().  The first few
  ** calls to sqlite3OsSleep() have a delay of 1 microsecond.  Really this
  ** is more of a scheduler yield than an actual delay.  But on the 10th
  ** an subsequent retries, the delays start becoming longer and longer, 
  ** so that on the 100th (and last) RETRY we delay for 21 milliseconds.
  ** The total delay time before giving up is less than 1 second.
  */
  if( cnt>5 ){
    int nDelay = 1;                      /* Pause time in microseconds */
    if( cnt>100 ) return SQLITE_PROTOCOL;
    if( cnt>=10 ) nDelay = (cnt-9)*238;  /* Max delay 21ms. Total delay 996ms */
    sqlite3OsSleep(pWal->pVfs, nDelay);
  }

  if( !useWal ){
    rc = walIndexReadHdr(pWal, pChanged);
    if( rc==SQLITE_BUSY ){
      /* If there is not a recovery running in another thread or process
      ** then convert BUSY errors to WAL_RETRY.  If recovery is known to
................................................................................
    u32 thisMark = pInfo->aReadMark[i];
    if( mxReadMark<=thisMark && thisMark<=pWal->hdr.mxFrame ){
      assert( thisMark!=READMARK_NOT_USED );
      mxReadMark = thisMark;
      mxI = i;
    }
  }
  /* There was once an "if" here. The extra "{" is to preserve indentation. */














  {
    if( mxReadMark < pWal->hdr.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] = pWal->hdr.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 );
      return WAL_RETRY;
    }

    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
................................................................................
  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 ){
        /* If all readers are using WAL_READ_LOCK(0) (in other words if no
        ** readers are currently using the WAL), then the transactions
        ** frames will overwrite the start of the existing log. Update the
        ** wal-index header to reflect this.
        **
................................................................................
        ** to handle if this transaction is rolled back.
        */
        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]));
        aSalt[1] = salt1;
        walIndexWriteHdr(pWal);
        pInfo->nBackfill = 0;
        for(i=1; i<WAL_NREADER; i++) pInfo->aReadMark[i] = READMARK_NOT_USED;
        assert( pInfo->aReadMark[0]==0 );
        walUnlockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1);
      }else if( rc!=SQLITE_BUSY ){
        return rc;