OMBench: Taming Data Management Requirements in Cloud-Native Applications
TL;DR
This work presents OMBench through a decision-and-evaluation toolkit with rich visualization features so that users can navigate a set of candidate platforms to meet data management requirements and make informed decisions about their guarantees and resource implications.
Abstract
Function-as-a-Service, actor runtimes, and microservice frameworks have emerged as popular platforms for scalable cloud applications. However, understanding the data management trade-offs of these solutions, not to mention their programming abstractions and architectural design, can be cumbersome for practitioners and researchers. Furthermore, existing benchmarks fail to capture the data management requirements sought after by practitioners. Our recently developed Online Marketplace Benchmark (OMBench) fills these gaps by addressing key data management challenges developers face, including distributed transaction processing, consistent data querying and replication, event processing, and data integrity constraint enforcement. We present OMBench through a decision-and-evaluation toolkit with rich visualization features. Users can navigate a set of candidate platforms to meet data management requirements and make informed decisions about their guarantees and resource implications. Users can easily use the toolkit to evaluate performance across competing candidates to pinpoint the trade-offs of cloud programming platforms.