Merge pull request #170 from benbjohnson/remove-sync-lock-2

Remove SQLite write lock during WAL sync

db.go

@@ -751,27 +751,6 @@ func (db *DB) Sync(ctx context.Context) (err error) {
 		return fmt.Errorf("ensure wal exists: %w", err)
 	}
 
-	// Start a transaction. This will be promoted immediately after.
-	tx, err := db.db.Begin()
-	if err != nil {
-		return fmt.Errorf("begin: %w", err)
-	}
-
-	// Ensure write transaction rolls back before returning.
-	defer func() {
-		if e := rollback(tx); e != nil && err == nil {
-			err = e
-		}
-	}()
-
-	// Insert into the lock table to promote to a write tx. The lock table
-	// insert will never actually occur because our tx will be rolled back,
-	// however, it will ensure our tx grabs the write lock. Unfortunately,
-	// we can't call "BEGIN IMMEDIATE" as we are already in a transaction.
-	if _, err := tx.ExecContext(ctx, `INSERT INTO _litestream_lock (id) VALUES (1);`); err != nil {
-		return fmt.Errorf("_litestream_lock: %w", err)
-	}
-
 	// Verify our last sync matches the current state of the WAL.
 	// This ensures that we have an existing generation & that the last sync
 	// position of the real WAL hasn't been overwritten by another process.
@@ -818,11 +797,6 @@ func (db *DB) Sync(ctx context.Context) (err error) {
 		checkpoint = true
 	}
 
-	// Release write lock before checkpointing & exiting.
-	if err := tx.Rollback(); err != nil {
-		return fmt.Errorf("rollback write tx: %w", err)
-	}
-
 	// Issue the checkpoint.
 	if checkpoint {
 		changed = true

replica.go

@@ -607,6 +607,11 @@ func (r *FileReplica) snapshot(ctx context.Context, generation string, index int
 	r.muf.Lock()
 	defer r.muf.Unlock()
 
+	// Issue a passive checkpoint to flush any pages to disk before snapshotting.
+	if _, err := r.db.db.ExecContext(ctx, `PRAGMA wal_checkpoint(PASSIVE);`); err != nil {
+		return fmt.Errorf("pre-snapshot checkpoint: %w", err)
+	}
+
 	// Acquire a read lock on the database during snapshot to prevent checkpoints.
 	tx, err := r.db.db.Begin()
 	if err != nil {

s3/s3.go

@@ -649,6 +649,11 @@ func (r *Replica) snapshot(ctx context.Context, generation string, index int) er
 	r.muf.Lock()
 	defer r.muf.Unlock()
 
+	// Issue a passive checkpoint to flush any pages to disk before snapshotting.
+	if _, err := r.db.SQLDB().ExecContext(ctx, `PRAGMA wal_checkpoint(PASSIVE);`); err != nil {
+		return fmt.Errorf("pre-snapshot checkpoint: %w", err)
+	}
+
 	// Acquire a read lock on the database during snapshot to prevent checkpoints.
 	tx, err := r.db.SQLDB().Begin()
 	if err != nil {