FATES: Automatically-tuned Database Storage Management

Anastassia Ailamaki
Carnegie Mellon University

This talk describes Fates, a dynamic, robust, and automated system for database storage management. Borrowing from the Greek mythology, Fates includes three components that establish proper abstractions in the database storage system: Clotho decouples in-memory data layout from on-disk storage layout, providing the opportunity to design efficient data placement at each storage level separately. Lachesis provides device-specific hints and automatically specializes the system to extracted device characteristics. Finally, Atropos provides logical-to-physical volume mapping and arranges storage to offer robust performance across workloads. The talk will describe the Fates system design and implementation, and will demonstrate its efficiency through experimental results with application benchmarks.