monitoring, by a processor set, a resource utilization of an operating system (OS) with applications utilizing larger pages;

training, by the processor set, a machine learning (ML) model to determine a larger pages allocation based on applications features that are set for the applications during a runtime operation for the larger pages;

determining, by the processor set, the monitored resource utilization is greater than a threshold resource utilization based on the trained ML model determining that a runtime log history for the application indicates that less memory resources are accessed during the runtime operation in comparison to previous runtime operations and a storage utilization is below a predetermined utilization, and the storage utilization is different from the monitored resource utilization;

in response to the determining the monitored resource utilization is greater than a threshold resource utilization, determining, by the processor set, a respective larger pages index value for each of the applications utilizing larger pages; and

turning off, by the processor set, larger pages utilization of a subset of the applications utilizing larger pages, wherein the subset comprises a predefined number of the applications utilizing larger pages that have highest determined larger pages index values.