We describe how multi-national retailer ADEO successfully employed database virtualization to migrate all workloads of a complex Enterprise Data Warehouse (EDW) from a legacy Teradata system to Google BigQuery. We demonstrate the generality of the technology and the approach.

Performing a detailed workload analysis is a crucial step in determining the feasibility, timeline and cost of a major data warehouse replatforming project, i.e., migration from one platform to another. A large company's data warehouse applications may include millions of queries, some of which will use features that are unsupported or have different semantics in the new warehouse, or may have poor performance there.

Cloud service providers started with Infrastructure as a Service (IaaS) offerings and over time expanded into Platform as a Service (PaaS) and Software as a Service (SaaS). Even though each provider has a rich product offering, there are many scenarios where a multi-cloud strategy is desirable: utilizing economic dynamics, preventing data lock-in with one vendor, circumventing geographic restrictions, complying with local regulations, or combining on-premise and public-cloud resources. The challenge from a consumer perspective with multi-cloud deployments is the lack of a common abstraction for the offered products and a standardized way to express all of the application requirements for the resulting deployments. In this paper, we contribute by making yet another case for multi-cloud deployments and by predicting the emergence of a new generation of application-level resource managers which will natively support multi-cloud for enterprise applications. We identify three main components of the feedback loop controlled application-level resource managers: the software life-cycle manager, the data storage and access manager, and the service execution manager.