Component Replication based on Failover Units

Although component middleware is increasingly used to develop distributed, real-time and embedded (DRE) sys-tems, it poses new fault tolerance challenges, such as the need for efficient synchronization of internal component state, failure correlation across groups of components, and configuration of fault-tolerance properties at the compo-nent granularity level. This paper makes two contribu-tions to R&D on component-based fault-tolerance. First, we present the structure and functionality of our COmpo-nent Replication based on Failover Units (CORFU) middle-ware, which provides fail-stop behavior and fault correla-tion across groups of components in DRE systems. Second, we empirically evaluate CORFU and compare/contrast it with existing object-oriented fault-tolerance methods. Our results show that component middleware (1) has acceptable fault-tolerance performance for DRE systems and (2) eases the burden of application development by providing middle-ware support for fault-tolerance at the component level.