The primary-backup replication model is one of the commonly adopted approaches to providing fault tolerant data services. Its extension to the real-time environment, however, imposes the additional constraint of timing predictability, which requires a bounded overhead for managing redundancy. This paper discusses the trade-o between reducing system overhead and increasing temporal consistency between the primary and backup, and explores ways to optimize such a system to minimize either the inconsistency or the system overhead while maintaining the temporal consistency guarantees of the system. An implementation built on top of the existing RTPB model 20 was developed within the x-kernel architecture on the Mach OSF platform running MK 7.2. Results of an experimental evaluation of the proposed optimization techniques are discussed.