On-Demand Access to Compute Resources

摘要

Disclosed are systems, methods and computer-readable media for controlling and managing the identification and provisioning of resources within an on-demand center as well as the transfer of workload to the provisioned resources. One aspect involves creating a virtual private cluster within the on-demand center for the particular workload from a local environment. A method of managing resources between a local compute environment and an on-demand environment includes detecting an event associated with a local compute environment and based on the detected event, identifying information about the local environment, establishing communication with an on-demand compute environment and transmitting the information about the local environment to the on-demand compute environment, provisioning resources within the on-demand compute environment to substantially duplicate the local environment and transferring workload from the local-environment to the on-demand compute environment. The event can be a threshold or a triggering event within or outside of the local environment.

主权项

1. A method comprising:
based on a detected event associated with a local compute environment, wherein the local compute environment is separate from a remote compute environment, receiving information about the local compute environment at the remote compute environment; receiving a request for resources in the remote compute environment, wherein a specification of resources is associated with the request, the specification of resources being one of fully explicit, partially explicit, fully implicit based on workload, and based on a virtual private cluster package concept where the virtual private cluster package can include aspects of provisioning a support environment and adjustments to resource request timeframes including pre-allocation, allocation duration, and post-allocation timeframe adjustments; based on the information and the specification of resources, reserving compute resources in the remote compute environment for a specific workload, to yield reserved compute resources, and wherein the reserved compute resources comprise at least one processor; provisioning the reserved compute resources within the remote compute environment such that a configuration of the remote compute environment substantially duplicates a configuration of the local compute environment; and receiving the specific workload from the local compute environment to the reserved compute resources in the remote compute environment such that the specific workload consumes the reserved compute resources.