In accordance with disclosed embodiments, there are provided systems, methods, and apparatuses for implementing a scheduler with preemptive termination of existing workloads to free resources for high priority items. For instance, according to one embodiment, there is disclosed a system to implement a scheduling service, wherein the system includes: a processor and a memory to execute instructions at the system; a compute resource discovery engine to identify a plurality of computing resources currently executing scheduled workload tasks; a workload discovery engine to identify one or more pending workload tasks to be scheduled for execution; in which each of the computing resources lack current available capacity to execute additional scheduled workload tasks; a policy engine to define a Service Level Target (SLT) for each of the scheduled workload tasks currently executing via the plurality of computing resources and for each of the one or more pending workload tasks to be scheduled for execution; an analysis engine to further terminate one of the scheduled workload tasks currently executing via the plurality of computing resources based on the defined SLTs for the respective workload tasks; and a scheduler to schedule one of the pending workload tasks into capacity within the plurality of computing resources freed up by the terminated workload task. Other related embodiments are disclosed.