Distributed transactional memory (DTM) is a powerful concurrency control model for distributed systems sparing the programmer from the complexity of manual implementation of lock-based distributed synchronization. We consider Herlihy and Sun’s dataflow DTM model, where objects are migrated to invoking transactions, and the open nesting model of managing inner (distributed) transactions. In this paper we present DATS, a dependency-aware transactional scheduler, that is able to boost the throughput of open-nested transactions reducing the overhead of running expensive compensating actions and abstract locks in the case of outer transaction aborts. The contribution of the paper is twofold: (A) DATS allows the commutable outer transactions to be validated concurrently and (B) allows the non-commutable outer transactions, depending on their inner transactions, to commit be committed before others without dependencies.