Abstract: A system for generating recommended computing resource configurations for machine learning services is described. The system includes computing resources to host a machine learning model. The system includes a machine learning recommendation service to receive, from a client via an interface, a request to monitor the computing resources. The recommendation service monitors the machine learning model, including recording utilization metrics of the computing resources, recording the different inference requests, and recording the respective inferences. The recommendation service generates a recommended computing resource configuration for the machine learning model based on the utilization metrics and an optimization objective for utilizing computing resources. The recommendation service determines to provide the recommended computing resource configuration based on an accuracy analysis performed for the machine learning model deployed on the recommended computing resource configuration.

Abstract: Disclosed techniques generate a data structure including data representing a configuration of a data storage system. A parameter can be obtained that is usable to configure the data storage system. Data representing the configuration of the data storage system can be modified based on the parameter. The data storage system can be configured, using the parameter, based on the modified data representing the configuration of the data storage system and predetermined configuration data for the data storage system.

Abstract: Operating settings for a benchmarking operation may be determined, based at least in part, on one or more benchmarking task parameters. The operating settings may be used to establish a set of worker resources to send requests against a target until a stop condition is valid. Data may be collected from the target and used to train one or more machine learning systems in order to provide improved operating setting recommendations for subsequent benchmarking tasks.