Enables the support for Workload-aware preemption. This feature gate was removed in 1.37 and merged together with the GenericWorkload feature gate.
When enabled, if a PodGroup fails to schedule, the scheduler will use a workload-aware preemption algorithm to select victims to preempt instead of the default pod preemption algorithm.
来源:Kubernetes 文档贡献者 · 作者与贡献记录 · CC BY 4.0。离线整理了版式、链接和媒体显示。
