Method, system and apparatus for providing pay-per-use distributed computing resources

摘要

Method, system, apparatus, and computer program and computer program product provide on-demand, scalable computational resources to application providers over a distributed network and system. Resources are made available based on demand for applications. Application providers are charged fees based on the amount of resources utilized to satisfy the needs of the application. In providing compute resources, method and apparatus is capable of rapidly activating a plurality of instances of the applications as demand increases and to halt instances as demand drops. Application providers are charged based on metered amount of computational resources utilized in processing their applications. Application providers access the network to distribute applications onto network to utilize distributed compute resources for processing of the applications. Application providers are further capable of monitoring, updating and replacing distributed applications. Apparatus and system includes plurality of computing resources distributed across a network capable of restoring and snapshotting provisioned applications based on demand.

主权项

1. A method for providing distributed application processing on a network for an end user, wherein the network includes geographically distributed compute resources, the method comprising:
receiving, at a first computer system and from an application provider, a request for execution of a first application, the first application configured to be used by the end user; identifying, by the first computer system, a first set of compute resources on one or more servers of the network that are geographically proximate to said end user; determining, by the first computer system, whether the first set of compute resources are available to execute the first application; if the first set of compute resources are not available to execute the first application, determining if the first set of compute resources can be made available by snapshotting a second application executing on the first set of compute resources; snapshotting the second application so as to free up a portion of the first set of compute resources that were associated with the second application; and if the first set of compute resources are available to execute the first application, executing at least a portion of said first application using the first set of compute resources.