Abstract: When the hardware needs to perform a disruptive hardware action, such as a stop of one or more central processors, the hardware provides advance notification to all affected operating systems. The advance notification includes the time that the proposed disruptive action is intended to be initiated and its projected duration. In one instance, the hardware does not proceed with the disruptive action until it receives return acknowledgment from the operating systems that the disruptive action can be performed. The operating systems may respond back to the hardware to proceed as planned with the disruptive action or to reinitiate it only after a specified delay. This allows the operating systems time to prepare for any consequences of the disruptive action.