Abstract: Systems, apparatuses, methods, and software that implement power budget allocation optimization algorithms in multi-processor systems, such as server farms. The algorithms are derived from a queuing theoretic model that minimizes the mean response time of the system to the jobs in the workload while accounting for a variety of factors. These factors include, but are not necessarily limited to, the type of power (frequency) scaling mechanism(s) available within the processors in the system, the power-to-frequency relationship(s) of the processors for the scaling mechanism(s) available, whether or not the system is an open or closed loop system, the arrival rate of jobs incoming into the system, the number of jobs within the system, and the type of workload being processed.

Abstract: A dynamic capacity management policy for multi-paralleled computing resources (e.g., application servers, virtual application servers, etc.) that includes one or more of a state-change component, a load-balancing component, and a robustness-control component. The state-change component delays the release (e.g., powering down of a physical server, removal from a virtual-server lease, etc.) of each computing resource for a set amount of time. The load-balancing component can work in conjunction with the state-change component to reduce the number of idle computing resources by distributing incoming requests in a manner that keeps the already-processing computing resources as full of requests as possible. The robustness-control component scales capacity as a function of the current number of requests within the system of computing resources to account for variations other than request rate, such as request size, reduced processor frequency, network slowdowns, etc., that affect processing capacity.

Abstract: Processor-management techniques that purposely alternate a processor between an operating state and a non-operating state while the processor is executing the workload. The techniques leverage the “ultra-low-power” non-operating states of many processors to provide predictable power and/or frequency control of the processor. These techniques can provide better performance than known clock-throttling and dynamic voltage and frequency scaling schemes for controlling processors.

Abstract: In distributed networks of cooperating nodes, it is useful to perform resource discovery in a manner that is efficient but that also minimizes communication complexity. A system and method in which nodes in a network efficiently are provided with information about the presence of, and other information about, other nodes in the network provides tangible benefits. In general, in one aspect, a system and method according to the invention features a distributed method for communicating information among a plurality of nodes. The method includes communicating from the first node to the second node information about the first node and nodes that the first node is aware of. The method further includes adding or merging, by the second node, the information about the first node and nodes that the first node is aware of with information about nodes that the second node is aware of.

Abstract: A dynamic capacity management policy for multi-paralleled computing resources (e.g., application servers, virtual application servers, etc.) that includes one or more of a state-change component, a load-balancing component, and a robustness-control component. The state-change component delays the release (e.g., powering down of a physical server, removal from a virtual-server lease, etc.) of each computing resource for a set amount of time. The load-balancing component can work in conjunction with the state-change component to reduce the number of idle computing resources by distributing incoming requests in a manner that keeps the already-processing computing resources as full of requests as possible. The robustness-control component scales capacity as a function of the current number of requests within the system of computing resources to account for variations other than request rate, such as request size, reduced processor frequency, network slowdowns, etc., that affect processing capacity.

Abstract: Systems, apparatuses, methods, and software that implement power budget allocation optimization algorithms in multi-processor systems, such as server farms. The algorithms are derived from a queuing theoretic model that minimizes the mean response time of the system to the jobs in the workload while accounting for a variety of factors. These factors include, but are not necessarily limited to, the type of power (frequency) scaling mechanism(s) available within the processors in the system, the power-to-frequency relationship(s) of the processors for the scaling mechanism(s) available, whether or not the system is an open or closed loop system, the arrival rate of jobs incoming into the system, the number of jobs within the system, and the type of workload being processed.

Abstract: In distributed networks of cooperating nodes, it is useful to perform resource discovery in a manner that is efficient but that also minimizes communication complexity. A system and method in which nodes in a network efficiently are provided with information about the presence of, and other information about, other nodes in the network provides tangible benefits. In general, in one aspect, a system and method according to the invention features a distributed method for communicating information among a plurality of nodes. The method includes choosing, by a first node, one second node from information about nodes that the first node is aware of. The method further includes communicating from the first node to the second node information about the first node and nodes that the first node is aware of. The method further includes adding or merging, by the second node, the information about the first node and nodes that the first node is aware of with information about nodes that the second node is aware of.

Abstract: Processor-management techniques that purposely alternate a processor between an operating state and a non-operating state while the processor is executing the workload. The techniques leverage the “ultra-low-power” non-operating states of many processors to provide predictable power and/or frequency control of the processor. These techniques can provide better performance than known clock-throttling and dynamic voltage and frequency scaling schemes for controlling processors.

Abstract: In distributed networks of cooperating nodes, it is useful to perform resource discovery in a manner that is efficient but that also minimizes communication complexity. A system and method in which nodes in a network efficiently are provided with information about the presence of, and other information about, other nodes in the network provides tangible benefits. In general, in one aspect, a system and method according to the invention features a distributed method for communicating information among a plurality of nodes. The method includes choosing, by a first node, one second node from information about nodes that the first node is aware of. The method further includes communicating from the first node to the second node information about the first node and nodes that the first node is aware of. The method further includes adding or merging, by the second node, the information about the first node and nodes that the first node is aware of with information about nodes that the second node is aware of.

Abstract: In distributed networks of cooperating nodes, it is useful to perform resource discovery in a manner that is efficient but that also minimizes communication complexity. A system and method in which nodes in a network efficiently are provided with information about the presence of, and other information about, other nodes in the network provides tangible benefits. In general, in one aspect, a system and method according to the invention features a distributed method for communicating information among a plurality of nodes. The method includes choosing, by a first node, one second node from information about nodes that the first node is aware of. The method further includes communicating from the first node to the second node information about the first node and nodes that the first node is aware of. The method further includes adding or merging, by the second node, the information about the first node and nodes that the first node is aware of with information about nodes that the second node is aware of.

Abstract: In distributed networks of cooperating nodes, it is useful to perform resource discovery in a manner that is efficient but that also minimizes communication complexity. A system and method in which nodes in a network efficiently are provided with information about the presence of, and other information about, other nodes in the network provides tangible benefits. In general, in one aspect, a system and method according to the invention features a distributed method for communicating information among a plurality of nodes. The method includes communicating from the first node to the second node information about the first node and nodes that the first node is aware of. The method further includes adding or merging, by the second node, the information about the first node and nodes that the first node is aware of with information about nodes that the second node is aware of.

Abstract: A distributed server system is disclosed which includes a load balancer and a plurality of host processors. The load balancer receives requests for service and distributes task assignments among the plurality of processors based upon the amount of work associated with the respective requests for service. More specifically, each host processor services requests for service within a predefined task size interval and the load balancer assigns to each host processor only those requests for service which involve task sizes within the particular task size interval associated with the respective processor. In the foregoing manner, the variability of the task sizes assigned to any given host processor is minimized and performance of the distributed server system is improved.