sqlite wal 分析

 /* 只在非SQLITE_CHECKPOINT_PASSIVE模式时设置xBusyHandler
  * 即SQLITE_CHECKPOINT_PASSIVE时如果获取不到锁，立即返回，不进行等待并retry
  */
 if( pPager->pWal ){
    rc = sqlite3WalCheckpoint(pPager->pWal, db, eMode,
        (eMode==SQLITE_CHECKPOINT_PASSIVE ? 0 : pPager->xBusyHandler),
        pPager->pBusyHandlerArg,
        pPager->walSyncFlags, pPager->pageSize, (u8 *)pPager->pTmpSpace,
        pnLog, pnCkpt
    );
  }

int sqlite3WalCheckpoint(
  Wal *pWal,                      /* Wal connection */
  int eMode,                      /* PASSIVE, FULL, RESTART, or TRUNCATE */
  int (*xBusy)(void*),            /* Function to call when busy */
  void *pBusyArg,                 /* Context argument for xBusyHandler */
  int sync_flags,                 /* Flags to sync db file with (or 0) */
  int nBuf,                       /* Size of temporary buffer */
  u8 *zBuf,                       /* Temporary buffer to use */
  int *pnLog,                     /* OUT: Number of frames in WAL */
  int *pnCkpt                     /* OUT: Number of backfilled frames in WAL */
){
  int rc;                         /* Return code */
  int isChanged = 0;              /* True if a new wal-index header is loaded */
  int eMode2 = eMode;             /* Mode to pass to walCheckpoint() */
  int (*xBusy2)(void*) = xBusy;   /* Busy handler for eMode2 */
  assert( pWal->ckptLock==0 );
  assert( pWal->writeLock==0 );
  /* EVIDENCE-OF: R-62920-47450 The busy-handler callback is never invoked
  ** in the SQLITE_CHECKPOINT_PASSIVE mode. */
  assert( eMode!=SQLITE_CHECKPOINT_PASSIVE || xBusy==0 );
  if( pWal->readOnly ) return SQLITE_READONLY;
  WALTRACE(("WAL%p: checkpoint begins\n", pWal));

  /* IMPLEMENTATION-OF: R-62028-47212 All calls obtain an exclusive 
  ** "checkpoint" lock on the database file. */
  // 独占获取WAL_CKPT_LOCK锁
  rc = walLockExclusive(pWal, WAL_CKPT_LOCK, 1);
  if( rc ){
    /* EVIDENCE-OF: R-10421-19736 If any other process is running a
    ** checkpoint operation at the same time, the lock cannot be obtained and
    ** SQLITE_BUSY is returned.
    ** EVIDENCE-OF: R-53820-33897 Even if there is a busy-handler configured,
    ** it will not be invoked in this case.
    */
    testcase( rc==SQLITE_BUSY );
    testcase( xBusy!=0 );
    return rc;
  }
  pWal->ckptLock = 1;
  /* IMPLEMENTATION-OF: R-59782-36818 The SQLITE_CHECKPOINT_FULL, RESTART and
  ** TRUNCATE modes also obtain the exclusive "writer" lock on the database
  ** file.
  **
  ** EVIDENCE-OF: R-60642-04082 If the writer lock cannot be obtained
  ** immediately, and a busy-handler is configured, it is invoked and the
  ** writer lock retried until either the busy-handler returns 0 or the
  ** lock is successfully obtained.
  */
  // 非SQLITE_CHECKPOINT_PASSIVE时，独占获取WAL_WRITE_LOCK锁，并进行busy retry
  if( eMode!=SQLITE_CHECKPOINT_PASSIVE ){
    rc = walBusyLock(pWal, xBusy, pBusyArg, WAL_WRITE_LOCK, 1);
    if( rc==SQLITE_OK ){
      pWal->writeLock = 1;
    }else if( rc==SQLITE_BUSY ){
      eMode2 = SQLITE_CHECKPOINT_PASSIVE;
      xBusy2 = 0;
      rc = SQLITE_OK;
    }
  }
  //如果wal-index显示db有变化，unfetch db文件，和主线逻辑关系不大
  /* Read the wal-index header. */
  if( rc==SQLITE_OK ){
    rc = walIndexReadHdr(pWal, &isChanged);
    if( isChanged && pWal->pDbFd->pMethods->iVersion>=3 ){
      sqlite3OsUnfetch(pWal->pDbFd, 0, 0);
    }
  }
  /* Copy data from the log to the database file. */
  if( rc==SQLITE_OK ){

    if( pWal->hdr.mxFrame && walPagesize(pWal)!=nBuf ){
      rc = SQLITE_CORRUPT_BKPT;
    }else{
      // checkpoint
      rc = walCheckpoint(pWal, eMode2, xBusy2, pBusyArg, sync_flags, zBuf);
    }
    /* If no error occurred, set the output variables. */
    if( rc==SQLITE_OK || rc==SQLITE_BUSY ){
      if( pnLog ) *pnLog = (int)pWal->hdr.mxFrame;
      if( pnCkpt ) *pnCkpt = (int)(walCkptInfo(pWal)->nBackfill);
    }
  }
  // release wal index，非主线逻辑
  if( isChanged ){
    /* If a new wal-index header was loaded before the checkpoint was 
    ** performed, then the pager-cache associated with pWal is now
    ** out of date. So zero the cached wal-index header to ensure that
    ** next time the pager opens a snapshot on this database it knows that
    ** the cache needs to be reset.
    */
    memset(&pWal->hdr, 0, sizeof(WalIndexHdr));
  }
// 释放锁，返回
  /* Release the locks. */
  sqlite3WalEndWriteTransaction(pWal);
  walUnlockExclusive(pWal, WAL_CKPT_LOCK, 1);
  pWal->ckptLock = 0;
  WALTRACE(("WAL%p: checkpoint %s\n", pWal, rc ? "failed" : "ok"));
  return (rc==SQLITE_OK && eMode!=eMode2 ? SQLITE_BUSY : rc);
}

static int walCheckpoint(
  Wal *pWal,                      /* Wal connection */
  int eMode,                      /* One of PASSIVE, FULL or RESTART */
  int (*xBusy)(void*),            /* Function to call when busy */
  void *pBusyArg,                 /* Context argument for xBusyHandler */
  int sync_flags,                 /* Flags for OsSync() (or 0) */
  u8 *zBuf                        /* Temporary buffer to use */
){
  int rc = SQLITE_OK;             /* Return code */
  int szPage;                     /* Database page-size */
  WalIterator *pIter = 0;         /* Wal iterator context */
  u32 iDbpage = 0;                /* Next database page to write */
  u32 iFrame = 0;                 /* Wal frame containing data for iDbpage */
  u32 mxSafeFrame;                /* Max frame that can be backfilled */
  u32 mxPage;                     /* Max database page to write */
  int i;                          /* Loop counter */
  volatile WalCkptInfo *pInfo;    /* The checkpoint status information */
  szPage = walPagesize(pWal);
  testcase( szPage<=32768 );
  testcase( szPage>=65536 );
  pInfo = walCkptInfo(pWal);
  if( pInfo->nBackfill<pWal->hdr.mxFrame ){
    /* Allocate the iterator */
    rc = walIteratorInit(pWal, &pIter);
    if( rc!=SQLITE_OK ){
      return rc;
    }
    assert( pIter );
    /* EVIDENCE-OF: R-62920-47450 The busy-handler callback is never invoked
    ** in the SQLITE_CHECKPOINT_PASSIVE mode. */
    assert( eMode!=SQLITE_CHECKPOINT_PASSIVE || xBusy==0 );
    /* Compute in mxSafeFrame the index of the last frame of the WAL that is
    ** safe to write into the database.  Frames beyond mxSafeFrame might
    ** overwrite database pages that are in use by active readers and thus
    ** cannot be backfilled from the WAL.
    */
    mxSafeFrame = pWal->hdr.mxFrame;
    mxPage = pWal->hdr.nPage;
    /* 计算mxSafeFrame
     * 会尝试独占的获取aReadMark锁，如果获取到，则代表原先持有对应aReadMark锁的事务已经结束。
     * 会不断的用busy rerty逻辑等待对应的读锁释放。
     * 如果对应事物一直没有释放aReadMark锁，最终的 mxSafeFrame = MIN（unfinished_aReadMarks）
     */
    for(i=1; i<WAL_NREADER; i++){
      /* Thread-sanitizer reports that the following is an unsafe read,
      ** as some other thread may be in the process of updating the value
      ** of the aReadMark[] slot. The assumption here is that if that is
      ** happening, the other client may only be increasing the value,
      ** not decreasing it. So assuming either that either the "old" or
      ** "new" version of the value is read, and not some arbitrary value
      ** that would never be written by a real client, things are still 
      ** safe.  */
      u32 y = pInfo->aReadMark[i];
      if( mxSafeFrame>y ){
        assert( y<=pWal->hdr.mxFrame );
     // 尝试获取 WAL_READ_LOCK(i)锁，并进行忙等待
        rc = walBusyLock(pWal, xBusy, pBusyArg, WAL_READ_LOCK(i), 1);
        if( rc==SQLITE_OK ){
        // 成功获取 WAL_READ_LOCK(i)锁，设置为READMARK_NOT_USED；i==1，是个treak，不影响主流程
          pInfo->aReadMark[i] = (i==1 ? mxSafeFrame : READMARK_NOT_USED);
          walUnlockExclusive(pWal, WAL_READ_LOCK(i), 1);
        }else if( rc==SQLITE_BUSY ){
        // 一直没有获取对应WAL_READ_LOCK(i)锁，设置mxSafeFrame为y
          mxSafeFrame = y;
          xBusy = 0;
        }else{
          goto walcheckpoint_out;
        }
      }
    }
    // 开始从wal文件写回db文件，此时独占的持有WAL_READ_LOCK(0)
    if( pInfo->nBackfill<mxSafeFrame
     && (rc = walBusyLock(pWal, xBusy, pBusyArg, WAL_READ_LOCK(0),1))==SQLITE_OK
    ){
      i64 nSize;                    /* Current size of database file */
      u32 nBackfill = pInfo->nBackfill;
      pInfo->nBackfillAttempted = mxSafeFrame;
      /* Sync the WAL to disk */
      if( sync_flags ){
        rc = sqlite3OsSync(pWal->pWalFd, sync_flags);
      }
      /* If the database may grow as a result of this checkpoint, hint
      ** about the eventual size of the db file to the VFS layer.
      */
      if( rc==SQLITE_OK ){
        i64 nReq = ((i64)mxPage * szPage);
        rc = sqlite3OsFileSize(pWal->pDbFd, &nSize);
        if( rc==SQLITE_OK && nSize<nReq ){
          sqlite3OsFileControlHint(pWal->pDbFd, SQLITE_FCNTL_SIZE_HINT, &nReq);
        }
      }
     // 逻辑比较简单，遍历并回写
      /* Iterate through the contents of the WAL, copying data to the db file */
      while( rc==SQLITE_OK && 0==walIteratorNext(pIter, &iDbpage, &iFrame) ){
        i64 iOffset;
        assert( walFramePgno(pWal, iFrame)==iDbpage );
        if( iFrame<=nBackfill || iFrame>mxSafeFrame || iDbpage>mxPage ){
          continue;
        }
        iOffset = walFrameOffset(iFrame, szPage) + WAL_FRAME_HDRSIZE;
        /* testcase( IS_BIG_INT(iOffset) ); // requires a 4GiB WAL file */
        rc = sqlite3OsRead(pWal->pWalFd, zBuf, szPage, iOffset);
        if( rc!=SQLITE_OK ) break;
        iOffset = (iDbpage-1)*(i64)szPage;
        testcase( IS_BIG_INT(iOffset) );
        rc = sqlite3OsWrite(pWal->pDbFd, zBuf, szPage, iOffset);
        if( rc!=SQLITE_OK ) break;
      }
      /* If work was actually accomplished... */
      if( rc==SQLITE_OK ){
        if( mxSafeFrame==walIndexHdr(pWal)->mxFrame ){
          i64 szDb = pWal->hdr.nPage*(i64)szPage;
          testcase( IS_BIG_INT(szDb) );
          rc = sqlite3OsTruncate(pWal->pDbFd, szDb);
          if( rc==SQLITE_OK && sync_flags ){
            rc = sqlite3OsSync(pWal->pDbFd, sync_flags);
          }
        }
        if( rc==SQLITE_OK ){
         /* 更新nBackfill为已经checkpoint的部分
           * nBackfill记录当前已经checkpoint的部分
           */
          pInfo->nBackfill = mxSafeFrame;
        }
      }
      /* Release the reader lock held while backfilling */
     // 释放 WAL_READ_LOCK(0)
      walUnlockExclusive(pWal, WAL_READ_LOCK(0), 1);
    }

    if( rc==SQLITE_BUSY ){
      /* Reset the return code so as not to report a checkpoint failure
      ** just because there are active readers.  */
      rc = SQLITE_OK;
    }
  }
  /* If this is an SQLITE_CHECKPOINT_RESTART or TRUNCATE operation, and the
  ** entire wal file has been copied into the database file, then block 
  ** until all readers have finished using the wal file. This ensures that 
  ** the next process to write to the database restarts the wal file.
  */
  // 非passive的checkpoint的区别都在这里
  if( rc==SQLITE_OK && eMode!=SQLITE_CHECKPOINT_PASSIVE ){
    assert( pWal->writeLock );
    if( pInfo->nBackfill<pWal->hdr.mxFrame ){
    // 没有全部checkpoint
      rc = SQLITE_BUSY;
    }else if( eMode>=SQLITE_CHECKPOINT_RESTART ){
    // RESTART or TRUNCATE
      u32 salt1;
      sqlite3_randomness(4, &salt1);
      assert( pInfo->nBackfill==pWal->hdr.mxFrame );
      // 获取所有读锁， 保证下一个事物能够重新开始restart，即循环利用wal文件
      rc = walBusyLock(pWal, xBusy, pBusyArg, WAL_READ_LOCK(1), WAL_NREADER-1);
      if( rc==SQLITE_OK ){
        if( eMode==SQLITE_CHECKPOINT_TRUNCATE ){
          /* IMPLEMENTATION-OF: R-44699-57140 This mode works the same way as
          ** SQLITE_CHECKPOINT_RESTART with the addition that it also
          ** truncates the log file to zero bytes just prior to a
          ** successful return.
          **
          ** In theory, it might be safe to do this without updating the
          ** wal-index header in shared memory, as all subsequent reader or
          ** writer clients should see that the entire log file has been
          ** checkpointed and behave accordingly. This seems unsafe though,
          ** as it would leave the system in a state where the contents of
          ** the wal-index header do not match the contents of the 
          ** file-system. To avoid this, update the wal-index header to
          ** indicate that the log file contains zero valid frames.  */
          walRestartHdr(pWal, salt1);
         // Truncate wal文件
          rc = sqlite3OsTruncate(pWal->pWalFd, 0);
        }
        walUnlockExclusive(pWal, WAL_READ_LOCK(1), WAL_NREADER-1);
      }
    }
  }
 walcheckpoint_out:
  walIteratorFree(pIter);
  return rc;
}