Abstract: Architecture that includes a service which ensures that a server database engine handles different types of workload in an optimized manner. The handling includes penalizing (e.g., delaying or rejecting) query requests from a network which would otherwise bring the database engine outside of the limits for which the engine can reliably and consistently handle workloads, and for which the engine is certified. The service provides engine throttling that adapts dynamically to the workload based on the workload type and resource consumption limits. The service can also exclude system critical workloads from throttling and selectively penalize requests based on the request source to provide optimized division of resources between the workloads. The level of throttling can be adjusted according to feedback received from previously-applied actions. The architecture also includes a configuration component external to the engine for the configuration of resource consumption limits and other parameters.