filer: delete a copied rename's old object only after the commit

Review follow-ups:

- The old key of a copied remote-only entry, and the old directory of a
  rename that copied one, are now deleted once the rename has committed.
  A rename that fails after the copy leaves the source entry and its
  object in place, plus an extra object at the new key.
- Every part of a multipart copy is conditioned on the ETag the copy
  started from, so an object overwritten mid-copy fails the copy
  instead of mixing versions.
- Both copy paths keep the source's server-side encryption settings.
- filer.remote.sync no longer deletes a key that a remote-only entry
  holds by the time the delete event is processed: a file deleted and
  then replaced by a remote-only rename has its content only there.

weed/command/filer_remote_sync_dir.go

@@ -195,7 +195,7 @@ func (option *RemoteSyncOptions) makeEventProcessor(remoteStorage *remote_pb.Rem
 			return updateLocalEntry(option, message.NewParentPath, message.NewEntry, remoteEntry)
 		}
 		if filer_pb.IsDelete(resp) {
-			return processDeleteEvent(client, mountedDir, remoteStorageMountLocation, resp)
+			return processDeleteEvent(filerSource, client, mountedDir, remoteStorageMountLocation, resp)
 		}
 		if message.OldEntry != nil && message.NewEntry != nil {
 			return processUpdateEvent(option, filerSource, *option.storageClass, client, mountedDir, remoteStorageMountLocation, resp)
@@ -212,8 +212,11 @@ func (option *RemoteSyncOptions) makeEventProcessor(remoteStorage *remote_pb.Rem
 // event the inline delete already handled), and GCS reports that case as
 // ErrRemoteObjectNotFound where S3 and Azure answer an idempotent success.
 // Returning the error would pin the sync offset on an event that has nothing
-// left to do.
+// left to do. A file whose path a remote-only entry has taken since keeps its
+// object: a rename copied that entry's content to this key, and it exists
+// nowhere else.
 func processDeleteEvent(
+	filerSource filer_pb.FilerClient,
 	client remote_storage.RemoteStorageClient,
 	mountedDir string,
 	remoteStorageMountLocation *remote_pb.RemoteStorageLocation,
@@ -232,6 +235,16 @@ func processDeleteEvent(
 	}
 	glog.V(2).Infof("delete: %+v", resp)
 	dest := toRemoteStorageLocation(util.FullPath(mountedDir), util.NewFullPath(resp.Directory, message.OldEntry.Name), remoteStorageMountLocation)
+	if !message.OldEntry.IsDirectory {
+		current, err := currentEntry(filerSource, resp.Directory, message.OldEntry.Name)
+		if err != nil {
+			return err
+		}
+		if isRemoteOnly(current) {
+			glog.V(0).Infof("keep %s: a remote-only entry has taken its path since", remote_storage.FormatLocation(dest))
+			return nil
+		}
+	}
 	if message.OldEntry.IsDirectory {
 		glog.V(0).Infof("rmdir  %s", remote_storage.FormatLocation(dest))
 		return client.RemoveDirectory(dest)

weed/command/filer_remote_sync_dir_test.go

@@ -999,7 +999,7 @@ func TestDeleteEventAbsentRemoteObjectIsSuccess(t *testing.T) {
 
 	t.Run("absent object", func(t *testing.T) {
 		remote := &recordingRemote{deleteErr: remote_storage.ErrRemoteObjectNotFound}
-		if err := processDeleteEvent(remote, mountedDir, mountLoc, resp); err != nil {
+		if err := processDeleteEvent(&stubFilerClient{}, remote, mountedDir, mountLoc, resp); err != nil {
 			t.Fatalf("err = %v, want nil: deleting an absent object is complete", err)
 		}
 		if len(remote.deletes) != 1 || !proto.Equal(remote.deletes[0], wantDelete) {
@@ -1011,7 +1011,7 @@ func TestDeleteEventAbsentRemoteObjectIsSuccess(t *testing.T) {
 		marked := proto.Clone(resp).(*filer_pb.SubscribeMetadataResponse)
 		marked.EventNotification.OldEntry.Extended = map[string][]byte{filer.ExtKeepRemoteObjectKey: []byte("true")}
 		remote := &recordingRemote{}
-		if err := processDeleteEvent(remote, mountedDir, mountLoc, marked); err != nil {
+		if err := processDeleteEvent(&stubFilerClient{}, remote, mountedDir, mountLoc, marked); err != nil {
 			t.Fatalf("err = %v", err)
 		}
 		if len(remote.deletes) != 0 {
@@ -1019,9 +1019,41 @@ func TestDeleteEventAbsentRemoteObjectIsSuccess(t *testing.T) {
 		}
 	})
 
+	t.Run("a remote-only entry that took the path keeps the object", func(t *testing.T) {
+		// deleted, then a remote-only file renamed onto the path: the rename
+		// copied its content to this key before the sync got to the delete
+		remote := &recordingRemote{}
+		filerClient := &stubFilerClient{entry: &filer_pb.Entry{
+			Name:        "state.db.tmp",
+			Attributes:  &filer_pb.FuseAttributes{FileSize: 10},
+			RemoteEntry: &filer_pb.RemoteEntry{RemoteSize: 10},
+		}}
+		if err := processDeleteEvent(filerClient, remote, mountedDir, mountLoc, resp); err != nil {
+			t.Fatalf("err = %v", err)
+		}
+		if len(remote.deletes) != 0 {
+			t.Errorf("deletes = %+v, want none", remote.deletes)
+		}
+	})
+
+	t.Run("an entry with local data at the path does not stop the delete", func(t *testing.T) {
+		remote := &recordingRemote{}
+		filerClient := &stubFilerClient{entry: &filer_pb.Entry{
+			Name:        "state.db.tmp",
+			Content:     []byte("local"),
+			RemoteEntry: &filer_pb.RemoteEntry{RemoteSize: 10},
+		}}
+		if err := processDeleteEvent(filerClient, remote, mountedDir, mountLoc, resp); err != nil {
+			t.Fatalf("err = %v", err)
+		}
+		if len(remote.deletes) != 1 {
+			t.Errorf("deletes = %+v, want one", remote.deletes)
+		}
+	})
+
 	t.Run("other failure still fails", func(t *testing.T) {
 		remote := &recordingRemote{deleteErr: errors.New("AccessDenied: Access Denied")}
-		if err := processDeleteEvent(remote, mountedDir, mountLoc, resp); err == nil {
+		if err := processDeleteEvent(&stubFilerClient{}, remote, mountedDir, mountLoc, resp); err == nil {
 			t.Fatal("err = nil, want the delete failure")
 		}
 	})