Optimistic Causal Consistency for Geo-Replicated Key-Value Stores

Causal consistency (CC) is an attractive model for geo-replicated data stores because it hits a sweet spot in the ease-of-programming versus performance trade-off. We present new approach implementing CC stores, which we call Optimistic Consistency (OCC). OCC's main design goal to maximize freshness. The optimism our lies fact that updates replicated remote center are made visible immediately, without checking if their causal dependencies have been received. Servers perform dependency check needed enforce only upon serving client operation, rather than on receipt of item as existing systems. OCC offers significant gain freshness, crucial importance various types applications, such real-time potentially blocking behavior makes vulnerable network partitions. therefore propose recovery mechanism allows system fall back pessimistic protocol continue operating during implement POCC, first causally consistent multi-master key-value store designed show POCC improves while offering comparable or better its counterparts.