Abstract: A technique includes receiving, by a cluster management controller, data representing results of a plurality of performance tests that are conducted on a plurality of processors that are associated with the plurality of computing nodes of a cluster. The technique includes, based on the data representing the results, selecting a lead processor of the plurality of processors; and communicating, by the cluster management controller, with the plurality of computing nodes to regulate core and un-core operating frequencies of the plurality of processors. Communicating with the plurality of computer nodes includes communicating data representing a core operating frequency of the lead processor and an un-core operating frequency of the lead processor.

Abstract: A technique includes receiving, by a cluster management controller, data representing results of a plurality of performance tests that are conducted on a plurality of processors that are associated with the plurality of computing nodes of a cluster. The technique includes, pursuant to block, based on the data representing the results, selecting a lead processor of the plurality of processors; and communicating, by the cluster management controller, with the plurality of computing nodes to regulate core and un-core operating frequencies of the plurality of processors. Communicating with the plurality of computer nodes includes communicating data representing a core operating frequency of the lead processor and an un-core operating frequency of the lead processor.

Abstract: An SMP computing system has a RAID controller and an interconnect bus system for communication processors and the RAID controller. There are in host memory a plurality of reply queues, at least one of which is associated with each processor of the SMP computing system. Replies associated with commands originating from a first processor are buffered by the RAID controller in a first reply queue, and replies associated with commands originating from a second processor are buffered in a second reply queue.

Abstract: A nonintrusive monitoring system is used to determine the onset and duration times of an electrical power outage-caused down condition of a computer without requiring a pre-power outage polling of a running component of the computer and thereby degrading computer system performance. In response to a supply power outage the monitoring system switches on a battery-powered counter device, representatively a digital counter or a real time clock, and then switches the counter device back off in response to resumption of power supply to the computer. A software portion of the monitoring system then detects the count value of the counter device, and utilizes the count value to compute the onset and duration times of the previous power outage.