Predictive virtual server scheduling and optimization of dynamic consumable resources to achieve priority-based workload performance objectives

A computer-implemented method for predictive virtual server scheduling and optimization of dynamic consumable resources to achieve performance objectives, the method comprising:

• determining an initial allocation of a virtual server to a hypervisor associated with an importance level by:
• calculating a capacity requirement for each virtual server based on an administrator defined performance objective for each virtual server;
• calculating an available CPU capacity for each importance level based on the calculated capacity requirement for each virtual server, wherein each importance level is associated with one or more hypervisors, wherein each importance level indicates a priority over one or more hypervisors of other importance levels of which resources can be taken;
• sending the calculated capacity requirement for each virtual server and the calculated available CPU capacity to a scheduler;
• selecting, by a scheduler, a target hypervisor based on the calculated capacity requirement of each virtual server and the calculated available CPU capacity at each importance level of each hypervisor, wherein the selecting the target hypervisor selects a hypervisor associated with a lowest importance level, having a most available CPU capacity;
• performing the initial allocation by allocating the virtual server to the selected target hypervisor;
• determining one or more non-performing virtual servers and an associated importance level of the one or more non-performing virtual servers, wherein the non-performing virtual servers are virtual servers that were initially allocated and are not meeting a performance goal;
• if one or more non-performing virtual servers are determined, determining a total needed capacity required by the non-performing virtual servers at the importance level to meet the performance objective;
• comparing the total needed capacity with an available capacity of a lower importance level;
• redistributing the available capacity from the lower importance level to the importance level of the non-performing virtual servers;
• comparing the total needed capacity to an updated available capacity of the importance level of the one or more non-performing virtual servers;
• determining the one or more non-performing virtual servers as candidates for migration based on the comparison of the total needed capacity to the updated available capacity;
• and
• ranking the non-performing virtual server candidates for migration;
• performing the selecting of a new target hypervisor for the ranked candidates;
• and
• allocating the ranked candidates to the selected new target hypervisor.