AWS pushes compute efficiency measures as demand continues to grow

Amazon Web Services, the cloud computing giant that powers a startling chunk of the internet, is asking its engineers to practice efficiency measures to conserve CPU compute, including turning off computers they’re not using, according to a report from The Information.

AWS also suggests customers follow the same best practices for resource management.

The guidance follows internal meetings in May that emphasized maximizing existing infrastructure before new hardware arrives. Engineers have been asked to identify and reduce idle EC2 resources.

The optimization playbook focuses on rightsizing instances to match actual workload needs and stopping idle or unused resources.

In a statement, AWS said demand for its services, including EC2, remains exceptionally strong and continues to grow. The company said it works with internal teams to use compute resources efficiently through measures such as reclaiming idle instances, rightsizing and adjusting capacity as workloads change.

“Even with this heavy demand, we continue to satisfy the overwhelming majority of compute needs for both our internal and external customers,” an AWS spokesperson stated. “These efficiencies help manage capacity for internal and external customers alike, and any suggestion that these long-standing efforts reflect new capacity constraints is simply wrong.”