Abstract: A method for managing power consumption of multiple computer servers is disclosed. The number of computer servers required to meet a current workload demand is initially determined. Next, a thermally optimized configuration of powered-on computer servers to meet the current workload demand is determined. At least one computer server is powered on or powered off, based on the thermally optimized configuration.

Abstract: A method (and system) of improving performance of a multiprocessor system, includes proactively flushing and locking an arbitrarily-sized region of memory out of caches of the multiprocessor system.

Abstract: In a method for automatically rejuvenating a component of a distributed data processing environment while minimizing the disruptive effects of the rejuvenation, a usage history for a distributed data processing environment is stored. The usage history describes multiple levels of overall usage of the distributed data processing environment over time. Also, health data relating to at least one component of the distributed data processing environment is received, and, in response, the health data is automatically utilized to determine a failure time within which that component is likely to require rejuvenation. In response to determining the failure time, the usage history is automatically utilized to identify an optimum rejuvenation time. In response to identifying the optimum rejuvenation time, that component is automatically rejuvenated according to the optimum rejuvenation time.

Abstract: A method for managing power consumption of multiple computer servers is disclosed. The current workload information and the current capacity information of a group of computer servers within a computer server pool are determined. A short term history and a long term history of the workload information are then built based on the determined workload information. Next, the information regarding short-term variations in workload is determined. Similarly, the information regarding long-term variations in workload is determined. Based on a combination of the above-mentioned determined short-term and long-term information, at least one of the computer servers is powered on or powered off.

Abstract: A method (and system) monitoring a bus with pair-wise participants, includes detecting a problem during a transaction between first and second participants on the bus, and determining which participant is at fault for the problem or whether the problem includes a systemic bus problem.

Abstract: Power and redundancy management policies are applied individually to the tiers of redundant servers of an application service such that power is reduced while maintaining a high level of system availability. Servers which are determined to be relatively inactive are moved to a free pool. Certain servers of the free pool are maintained in a hot standby state, while others are powered-off or set to operate in a low power mode. During times of high load, the servers in the hot standby state can be provisioned quickly into the application service.

Abstract: A method (and system) of improving performance of a multiprocessor system, includes proactively flushing and locking an arbitrarily-sized region of memory out of caches of the multiprocessor system.

Abstract: A method (and system) for increased software dependability, includes learning how to predict an outage of a software system running on a computer, and, based on the learning, predicting an imminent outage, and avoiding the outage.

Abstract: A method for managing power consumption of multiple computer servers is disclosed. The current workload information and the current capacity information of a group of computer servers within a computer server pool are determined. A short term history and a long term history of the workload information are then built based on the determined workload information. Next, the information regarding short-term variations in workload is determined. Similarly, the information regarding long-term variations in workload is determined. Based on a combination of the above-mentioned determined short-term and long-term information, at least one of the computer servers is powered on or powered off.

Abstract: A method for managing power consumption of multiple computer servers is disclosed. The number of computer servers required to meet a current workload demand is initially determined. Next, a thermally optimized configuration of powered-on computer servers to meet the current workload demand is determined. At least one computer server is powered on or powered off, based on the thermally optimized configuration.

Abstract: A method of enhancing software dependability, includes measuring an elapsed time in a software system running on a computer, determining whether the elapsed time matches a threshold, and when the elapsed time matches the threshold, rejuvenating at least a portion of the software system to reduce the likelihood of an outage and without modifying an application running in the software system.

Abstract: A method (and system) of reducing a time for a computer system to recover from a degradation of performance in a hardware or a software in at least one first node of the computer system, includes monitoring a state of the at least one first node, and based on the monitoring, transferring a state of the at least one first node to a second node prior to the degradation in performance of the hardware or the software of the at least one first node.

Abstract: A method (and system) of reducing warranty costs includes discriminating between hardware- and software-induced problems or outages in a computer system.

Abstract: A method of operating a node of a computer network which uses a plurality of servers, by determining that one of the servers has degraded health due to software aging, assigning tasks to the other servers while reducing workload at the first server, rejuvenating the first server once its workload has terminated and, after rejuvenation, assigning tasks to the first server. The servers are clustered to provide service based on a single server address (TCP/IP). The node may include a gateway interface which receives the server requests and passes them on to a dispatcher at the node. Tasks are assigned in response to health-related messages sent by the servers and received by a workload monitor agent of the dispatcher.

Abstract: In a method for automatically rejuvenating a component of a distributed data processing environment while minimizing the disruptive effects of the rejuvenation, a usage history for a distributed data processing environment is stored. The usage history describes multiple levels of overall usage of the distributed data processing environment over time. Also, health data relating to at least one component of the distributed data processing environment is received, and, in response, the health data is automatically utilized to determine a failure time within which that component is likely to require rejuvenation. In response to determining the failure time, the usage history is automatically utilized to identify an optimum rejuvenation time. In response to identifying the optimum rejuvenation time, that component is automatically rejuvenated according to the optimum rejuvenation time.