RAIDb: Redundant Array of Inexpensive Databases

Overview & Synopsis

Clusters of workstations become more and more popular to power data server applications such as large scale Web sites or e-Commerce applications. There has been much research on scaling the front tiers (web servers and application servers) using clusters, but databases usually remain on large dedicated SMP machines. In this paper, we address database performance scalability and high availability using clusters of commodity hardware. Our approach consists of studying different replication and partitioning strategies to achieve various degree of performance and fault tolerance. We propose the concept of Redundant Array of Inexpensive Databases (RAIDb). RAIDb is to databases what RAID is to disks. RAIDb aims at providing better performance and fault tolerance than a single database, at low cost, by combining multiple database instances into an array of databases. Like RAID, we define different RAIDb levels that provide various cost/performance/fault tolerance tradeoffs. RAIDb-0 features full partitioning, RAIDb-1 offers full replication and RAIDb-2 introduces an intermediate solution called partial replication, in which the user can define the degree of replication of each database table. We present a Java implementation of RAIDb called Clustered JDBC or C-JDBC. C-JDBC achieves both database performance scalability and high availability at the middleware level without changing existing applications. We show, using the TPC-W benchmark, that RAIDb-2 can offer better performance scalability (up to 25%) than traditional approaches by allowing fine-grain control on replication. Distributing and restricting the replication of frequently written tables to a small set of backends reduces I/O usage and improves CPU utilization of each cluster node.