Amazon Web Services (AWS) operates a global network of leading-edge server rack technologies across its data centers. Despite being some of the most advanced servers in the world, eventually, like all hardware, they must be replaced. To extend the useful life of data center hardware, AWS sends all functional, sanitized, retired server racks and components to its reverse logistics hubs. There, server racks are securely demanufactured, and components are repaired and tested for reuse in our data centers.
The program supports AWS’s path to reaching net-zero carbon by 2040, as part of The Climate Pledge. AWS is embracing three circular economy principles for our server racks by designing for reusability, keeping equipment operating efficiently, and recovering value from securely decommissioned equipment through reuse, repair, and recycling. This allows AWS to keep resources at their highest value for as long as possible, avoiding waste generation from our global operations and reducing the use of raw materials and carbon emissions across our supply chain.
Here's a step-by-step look at the AWS reverse logistics program’s processes that make component reuse possible.
Step 1Decommissioned server racks are sanitized of customer data
Prior to being demanufactured at an AWS reverse logistics hub, all data-storing media is sanitized to ensure customer data is securely removed. Server racks are then decommissioned and tested for functionality.
Step 2Reverse logistics hubs take in decommissioned server racks and hardware components
AWS currently has reverse logistics hubs in major regions around the world that process hardware from local data centers. Each hub consists of an information technology (IT) asset disposition center that receives server racks and individual components from data centers and a failure analysis lab (FA lab) that tests and repairs used components. Throughout every stage of the reverse logistics process, security remains a top priority.
“We apply the same high level of care and security as we do when the hardware is active in production in our data centers,” said Lisa Anderson, AWS operations senior manager for reverse logistics in North America.
Step 3Server racks are carefully demanufactured into individual components
During the demanufacturing process, server racks are taken apart into individual components. AWS technicians then process and evaluate each component to determine the highest reuse potential. AWS Nitro Cards, power supply units (PSUs), graphics processing units (GPUs), switches, dual in-line memory modules (DIMMs), and fiber optics are among the components prioritized for reuse.
Step 4Individual components are sent to the FA lab for repairs and testing
The FA lab is the nucleus of an AWS reverse logistics hub. It’s made up of two parts: repair lab and testing lab. In the FA lab, technicians inspect components for physical damage.
Julie Scudder, manager of the AWS FA lab in North America, explained, “The technicians look for any defects that would prevent a component’s reuse in a data center.”
After inspection, the technicians make minor repairs when needed and clean components before sending them for testing.
Step 5Failure analysis testing ensures component functionality
In the FA lab, several server racks run throughout the day as technicians evaluate different aspects of performance. At the fiber optics station, AWS technicians run tests that measure data delivery to ensure their connection remains strong. Other tests simulate data center operational stresses or use software scripts to determine the functionality of components.
Step 6Nitro Cards are put in testing rigs that simulate the environment of a data center server
AWS Nitro Cards and their testing rigs are manufactured by Amazon’s Annapurna Labs. Once a card is placed in a testing rig, an FA lab technician runs a series of software scripts to ensure the card will perform with the same high-quality standards as a newly manufactured card. Nitro Cards are part of the AWS Nitro System that provides enhanced security, confidentiality, and performance, enabling the delivery of innovative technologies at a rapid pace to Amazon Elastic Compute Cloud (Amazon EC2) customers.
Step 7Test results are sent to AWS's hardware engineering teams, where they can be analyzed and used to improve future designs
The data collected from Nitro Card testing is sent directly to Amazon’s Annapurna Labs. This process helps identify hardware or software modifications to improve new product development and to further extend the lifespan of existing cards.
Step 8Functional components are returned to inventory for reuse in an AWS data center
As a final step, functional components are processed and shipped back to data centers.
“We have a lot of pride in the work that we do, knowing there's still a lot of useful life in the products that we touch,” said Anderson. “The components we repair are small, but they have the potential to make a big impact for our company, our customers, and our planet.”AWS docuseries shares stories of local people in eastern Oregon whose lives are being changed for the better by the cloud—in unexpected ways.