摘要 |
Embodiments of the present invention provide an approach for determining distributions of virtual machine (VM) patterns across pools of VM instances based upon historical data (e.g., to achieve faster provisioning times). In a typical embodiment, a total pool size for a pool of VM instances is determined (e.g., based on historical data). Then, a distribution of a set of VM instance patterns across the pool is determined (e.g., also based upon historical data). Once the distribution has been determined, the pool of VM instances may be provisioned according to the distribution. In one embodiment, the VM patterns may be evenly distributed across the pool. In another embodiment, the VM patterns may be distributed according to percentages with which the VM patterns were previously requested. In yet another embodiment, the VM patterns may be grouped into two or more groups that are associated with particular user/customer level(s) (e.g., privilege and/or permission level, a service level purchased and/or specified by the consumer, etc). |