[ws-daemon] start backup even pod still report the container is running after 5 minutes

Author: iQQBot

components/ws-daemon/pkg/controller/workspace_controller.go

@@ -349,9 +349,15 @@ func (wsc *WorkspaceController) doWorkspaceContentBackup(ctx context.Context, sp
 
 	if ws.IsConditionTrue(workspacev1.WorkspaceConditionContainerRunning) {
 		// Container is still running, we need to wait for it to stop.
-		// We should get an event when the condition changes, but requeue
-		// anyways to make sure we act on it in time.
-		return ctrl.Result{RequeueAfter: 500 * time.Millisecond}, nil
+		// We will wait for this situation for up to 5 minutes.
+		// If the container is still in a running state after that,
+		// there may be an issue with state synchronization.
+		// We should start backup anyway to avoid data loss.
+		if !(ws.DeletionTimestamp != nil && time.Since(ws.DeletionTimestamp.Time) > 5*time.Minute) {
+			// We should get an event when the condition changes, but requeue
+			// anyways to make sure we act on it in time.
+			return ctrl.Result{RequeueAfter: 500 * time.Millisecond}, nil
+		}
 	}
 
 	if wsc.latestWorkspace(ctx, ws) != nil {