Amazon Technologies, Inc.

Benjamin Van Der Merwe

James Alfred Gordon Greenfield

Christopher Richard Jacques De Kadt

Jean-Paul Bauer

Adi Meyers

Roland Alexander Paterson-Jones

Mathew Daniel

Ross Bevan Engers

Sebastian Martin Biemueller

Thomas Friebel

Jaco Hermanus Gabriel Le Roux

David Daniel De Bruyn

Natu Lauchande

Christo Pierre Langenhoven

Oliver Nigel Nightingale

Techniques are described for providing a file system interface for use with network-accessible computing resources (e.g., located in a data center). A client computing device of a user may display information regarding at least some such computing resources to the user using a visual representation of a hierarchical file system (e.g., with the computing resources organized hierarchically), and allow standard file system commands to manipulate the computing resources, despite them not actually being part of a file system. Particular combinations of a file system command and a type of computing resource may be mapped to associated operations, which implement actions for computing resources of that type corresponding to functionality of that file system command. In some situations, the computing resources are provided by an online service, such as a configurable network service providing virtual computer networks to clients.

Providing a file system interface to network-accessible computing resources

Remote computing resource service providers allow customers to execute virtual computer systems in a virtual environment on hardware provided by the computing resource service provider. The hardware may be distributed between various geographic locations connected by a network. The distributed environment may increase latency of various operations of the virtual computer systems executed by the customer. To reduce latency of various operations predictive modeling is used to predict the occurrence of various operations and initiate the operations before they may occur, thereby reducing the amount of latency perceived by the customer.

Predictive instance suspension and resumption

A ranking service can retrieve metrics from a metrics data store and use the metrics to determine a priority order in which to power down resources in a data center. Metrics from the data store can include a number of instances running on a host, a length of time that an instance has been operational, a type of instance, an amount of CPU use on a host, etc. The ranking service can also obtain other parameters from other sources. The parameters can include whether redundant or failover instances exist, the importance of the instances, whether the customer itself is considered important, other generic parameters from the customer account, a customer provided ranking of instances, etc.

Mitigating an impact of a datacenter thermal event

Growing community of inventors

Cape Town, South Africa

Benjamin Van Der Merwe