Amazon Compute Optimizer

Recommends optimal Amazon Web Services resources to reduce costs and improve performance for your workloads

Amazon Compute Optimizer recommends optimal Amazon Web Services resources for your workloads to reduce costs and improve performance by using machine learning to analyze historical utilization metrics. Over-provisioning resources can lead to unnecessary infrastructure cost, and under-provisioning resources can lead to poor application performance. Compute Optimizer helps you choose optimal configurations for three types of Amazon Web Services resources: Amazon EC2 instances, Amazon EBS volumes, and Amazon Lambda functions, based on your utilization data.

By applying the knowledge drawn from Amazon’s own experience running diverse workloads in the cloud, Compute Optimizer identifies workload patterns and recommends optimal Amazon Web Services resources. Compute Optimizer analyzes the configuration and resource utilization of your workload to identify dozens of defining characteristics, for example, if a workload is CPU-intensive, if it exhibits a daily pattern, or if a workload accesses local storage frequently. The service processes these characteristics and identifies the hardware resource required by the workload. Compute Optimizer infers how the workload would have performed on various hardware platforms (e.g. Amazon EC2 instances types) or using different configurations (e.g. Amazon EBS volume IOPS settings, and Amazon Lambda function memory sizes) to offer recommendations.

Compute Optimizer is available to you at no additional charge. To get started, you can opt in to the service in the Compute Optimizer Console.

Benefits

Lower costs by up to 25%

You can take advantage of the recommendations in Compute Optimizer to reduce costs by up to 25%. Compute Optimizer analyzes the configuration and resource utilization of a workload to identify Amazon Web Services resources, such as Amazon EC2 instances, Amazon EBS volumes, and Amazon Lambda functions, that might be under-provisioned or over-provisioned. Compute Optimizer then recommends you to right-size your Amazon Web Services resources and switch to a different instance size or instance type to save costs.

Optimize performance with actionable recommendations

Compute Optimizer recommends up to 3 options from 140+ EC2 instance types, as well as a wide range of EBS volume and Lambda function configuration options, to right size your workloads. Compute Optimizer also projects what the CPU utilization, memory utilization, and run time of your workload would have been on recommended Amazon Web Services resource options. This helps you understand how your workload would have performed on the recommended options before implementing the recommendations.

Get started quickly

With just four simple clicks from the Amazon Web Services Console, Compute Optimizer automatically generates recommendations. These recommendations are based on your current resource utilization data from Amazon CloudWatch metrics and Amazon Web Services resource metadata. You don’t need to invest substantial time and money to set up rules-based thresholds.

How it works

How-it-works-diagram-compute-optimizer-cn