摘要 |
<p>A system and method co-allocating resources within a compute environment are disclosed. The method embodiment of the invention comprises receiving a first request to reserve a first type of resource in a compute environment comprising a plurality of networked computing devices, analyzing first constraints, first service level agreement guarantees, and a first flex flag associated with the first request and related to use of the compute environment, identifying a first group of resources that meet the first request, receiving a second request to reserve a second type of resource in the compute environment, analyzing second constraints, second service level agreement guarantees, and a second flex flag associated with the second request and related to use of the compute environment, wherein the first type of resource and second type of resource span at least one computing device of the plurality of networked computing devices, wherein each computing device of the plurality of networked computing devices has a homogeneous processor architecture, identifying a second group of resources that meet the second request, and generating a co-allocation map between the first group of resources and the second group of resources, wherein the co-allocation map comprises at least one of (1) intersecting time frames in which both the first request and the second request can be simultaneously satisfied, and (2) all time frames where available resources exist that satisfy the first request and the second request.</p> |