Fast Algorithms for Maintaining Replica Consistency in Lazy Master Replicated Databases

Esther Pacitti , Pascale Minet (1) , Eric Simon (2)

1 REFLECS - Distributed Real-Time Fault-Tolerant Computing Systems
2 RODIN - Database Systems

In a lazy master replicated database, a transaction can commit after updating one replica copy (primary copy) at some master node. After the transaction commits, the updates are propagated towards the other replicas (secondary copies), which are updated in separate refresh transactions. A central problem is the design of algorithms that maintain replica's consistency while at the same time minimizing the performance degradation due to the synchronization of refresh transactions. In this paper, we propose a simple and general refreshment algorithm that solves this problem and we prove its correctness. The principle of the algorithm is to let refresh transactions wait for a certain «deliver time» before being executed at a node having secondary copies. We then present two main optimizations to this algorithm. One is based on specific properties of the topology of replica distribution across nodes. In particular, we characterize the nodes for which the deliver time can be null. The other improves the refreshment algorithm by using an immediate update propagation strategy. Our performance evaluation demonstrate the effectiveness of this optimization.

Mots clés: REPLICATED DATABASES; LAZY MASTER; REPLICA CONSISTENCY; REFRESHMENT ALGORITHM; DATA MART; DATA WAREHOUSE

Domaines: Autre [cs.OH]

Esther Pacitti, Pascale Minet, Eric Simon. Fast Algorithms for Maintaining Replica Consistency in Lazy Master Replicated Databases. [Research Report] RR-3654, INRIA. 1999. ⟨inria-00077204⟩