Skip to Main Content
Distributed hash tables (DHTs) build on structured peer-to-peer overlays because of their inherent high scalability and resilience against node failures. Combined with additional replication strategies such systems promise high availability for published data resources. However, regarding the support for atomic data operations replication comes at the cost of maintaining consistency. Thus, most DHT like systems either focus on immutable data resources or if supported at all they reinvent the wheel for their storage needs strictly focussing on mutable data and their own narrow application domain. What lacks is a generic but efficient solution to enable flexible consistent data operations for replicated data trimmed for highly concurrent and fluctuating environments. In this paper we introduce DhtFlex, a fault-tolerant distributed algorithm tailored for the needs of a DHT and optimized for the consistent management of replicated data resources in such environments. DhtFlex is supposed to serve as a generic building block to any underlying structured peer-to-peer overlay. It imposes an annotated resource concept to typify replicated data. DhtFlex enables efficient support for immutable as well as for optimized atomic operations on mutable data resources.