SQLite

Check-in [1725aa7501]
Login

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

Overview
Comment:Changes which attempt to address an obscure SQLITE_PROTOCOL error.
Downloads: Tarball | ZIP archive
Timelines: family | ancestors | wal-trace-375
Files: files | file ages | folders
SHA1: 1725aa7501fa97283a397d4c7cf206f35c6e6bb5
User & Date: drh 2011-02-19 14:19:17.314
Context
2011-02-19
14:19
Changes which attempt to address an obscure SQLITE_PROTOCOL error. (Leaf check-in: 1725aa7501 user: drh tags: wal-trace-375)
2011-01-18
17:34
Pull over all the latest trunk changes. (check-in: ca86d04be1 user: drh tags: wal-trace-375)
Changes
Unified Diff Ignore Whitespace Patch
Changes to src/wal.c.
1968
1969
1970
1971
1972
1973
1974
1975
















1976

1977
1978

1979
1980
1981
1982
1983
1984
1985
1986
  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 ){

    walTrace("cnt=%d",cnt);
    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







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

>


>
|







1968
1969
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
1998
1999
2000
2001
2002
2003
2004
  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 */
    walTrace("cnt=%d",cnt);
    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
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079

2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093





2094
2095
2096
2097
2098
2099
2100
    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;
      walTrace("aReadMark[1] <- %d", pWal->hdr.mxFrame);
    }else if( rc==SQLITE_BUSY ){
      rc = WAL_RETRY;
      walTrace("aReadMark[1] is busy");
    }
    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 ){
          walTrace("walLockExclusive(%d):%d", i, rc);
          return rc;
        }
      }
    }






    rc = walLockShared(pWal, WAL_READ_LOCK(mxI));
    if( rc ){
      walTrace("walLockShared(mxI=%d):%d", mxI, rc);
      return rc==SQLITE_BUSY ? WAL_RETRY : rc;
    }
    /* Now that the read-lock has been obtained, check that neither the







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













>
>
>
>
>







2074
2075
2076
2077
2078
2079
2080
2081
















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
    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 ){
          walTrace("walLockExclusive(%d):%d", i, rc);
          return rc;
        }
      }
    }
    if( mxI==0 ){
      assert( rc==SQLITE_BUSY );
      walTrace("all readlocks busy: cannot set read mark");
      return WAL_RETRY;
    }

    rc = walLockShared(pWal, WAL_READ_LOCK(mxI));
    if( rc ){
      walTrace("walLockShared(mxI=%d):%d", mxI, rc);
      return rc==SQLITE_BUSY ? WAL_RETRY : rc;
    }
    /* Now that the read-lock has been obtained, check that neither the
2465
2466
2467
2468
2469
2470
2471


2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
  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.
        **
        ** In theory it would be Ok to update the cache of the header only
        ** at this point. But updating the actual wal-index header is also
        ** safe and means there is no special case for sqlite3WalUndo()
        ** 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;







>
>

















|







2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
  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.
        **
        ** In theory it would be Ok to update the cache of the header only
        ** at this point. But updating the actual wal-index header is also
        ** safe and means there is no special case for sqlite3WalUndo()
        ** 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;