🤖 AI Summary
Existing benchmarks for geographically distributed OLTP databases commonly overlook critical challenges such as network instability, lack of data and client locality, cross-region communication costs, and limited distribution patterns. To address this gap, this work proposes Gaia, a benchmarking framework that systematically evaluates the trade-offs among performance, fault tolerance, and cost through multi-cloud regional deployments, dynamic network emulation, and diverse geographic data distributions. Gaia reveals, for the first time, that mainstream systems exhibit high sensitivity to network fluctuations, that cross-region communication dominates cloud expenditure, and that multi-region fault-tolerance mechanisms introduce substantial—yet often overlooked—overheads along critical execution paths. This framework provides an empirical foundation for the design and optimization of geographically distributed databases.
📝 Abstract
Geo-distributed OLTP databases are widely deployed across cloud regions, yet current evaluation practices do not cover the challenges of this aspect. Existing benchmarks assume stable network conditions; they lack explicit settings for data and client locality, and they largely ignore data transfer costs across regions. In addition, most evaluations rely on a limited set of geo-distribution patterns. In this paper, we propose Gaia, a comprehensive evaluation framework that addresses these gaps. We use Gaia to perform a comprehensive evaluation of existing geo-distributed OLTP systems. We deploy them across multiple cloud regions, using different geo-distribution patterns and variable cross-region network conditions. Among other interesting findings, our framework reveals that: i) most systems are sensitive to network instabilities, ii) network costs dominate cloud deployment expenses iii) multi-region fault-tolerance mechanisms incur measurable critical-path overhead that is often overlooked in prior evaluations. We argue that for the design of future geo-distributed databases, we must rethink the trade-offs between performance, fault-tolerance, and cost.