Abstract: Disclosed are systems and methods of performing a power cap processing in a compute environment. The method includes determining of one of committed resources and dedicated resources in a compute environment exceed a threshold value for a job. If a determination is yes that the threshold value is exceeded, then the method includes preempting processing of the job in the compute environment by performing one of migrating the job to a new compute resources and performing a power reduction action associated with the job, such as slowing down a processor associated with a job or cancelling the job. When such a power state reduction action is taken, reservations associated with other jobs may also be adjusted.

Abstract: A systems, method and computer-readable media are disclosed for providing a dynamic roll-back reservation mask in a compute environment. The method of managing compute resources within a compute environment includes, based on an agreement between a compute resource provider and a customer, creating a roll-back reservation mask for compute resources which slides ahead of current time by a period of time. Within the roll-back reservation mask, the method specifies a subset of consumers and compute resource requests which can access compute resources associated with the roll-back reservation mask and, based on received data, the method dynamically modifies at least one of (1) the period of time the roll-back reservation mask slides ahead of current time and (2) the compute resources associated with the roll-back reservation mask.

Abstract: Disclosed are a system, method and computer-readable medium relating to managing resources within a compute environment having a group of nodes or computing devices. The method comprises, for each node in the compute environment: traversing a list jobs having a fixed time relationship, wherein for each job in the list, the following steps occur: obtaining a range list of available timeframes for each job, converting each availability timeframe to a start range, shifting the resulting start range in time by a job offset, for a first job, copying the resulting start range into a node range, and for all subsequent jobs, logically AND'ing the start range with the node range. Next, the method comprises logically OR'ing the node range with a global range, generating a list of acceptable resources on which to start and the timeframe at which to start and creating reservations according to the list of acceptable resources for the resources in the group of computing devices and associated job offsets.

Abstract: Disclosed is an on-demand system and method for managing resources in an on-demand compute environment from a local compute environment. The method includes receiving information at a local resource broker that is associated with resources within an on-demand compute environment, based on the information, communicating instructions from the local resource broker to the on-demand compute environment and modifying resources associated with the on-demand compute environment based on the instructions.

Abstract: Disclosed herein are systems, methods, and computer-readable media for dynamically managing data-centric searches. The method includes identifying an event related to domain-specific searches to a database, identifying data at a first memory location in the database, duplicating the data to a new memory location, and distributing processing more domain-specific searches amongst an expanded search space including the new memory location and the first memory location. The expanded search space can be reduced or collapsed in response to a reduction event by removing duplicate data from the first memory location or the new memory location and adjusting the distribution of processing amongst the remaining memory location. The method can optionally include organizing multiple events by network segment, identifying a network segment associated with domain-specific searches, and duplicating the data to a new memory location in close proximity to the identified network segment.

Abstract: Disclosed are methods for estimating a time associated with shifting a first workload from a first compute environment to a second compute environment, separate from the first compute environment, estimating a likelihood of success associated with a likelihood that the first workload could successfully be shifted to the second compute environment, dividing or using the likelihood of success by the time to yield or produce a risk-adjusted shift time and, when a comparison of the shift time is longer than a maximum acceptable wait time, proceeding with a first operation associated with how to preempt the first workload by the second workload.

Abstract: A systems, method and computer-readable media are disclosed for providing a dynamic roll-back reservation mask in a compute environment. The method of managing compute resources within a compute environment includes, based on an agreement between a compute resource provider and a customer, creating a roll-back reservation mask for compute resources which slides ahead of current time by a period of time. Within the roll-back reservation mask, the method specifies a subset of consumers and compute resource requests which can access compute resources associated with the roll-back reservation mask and, based on received data, the method dynamically modifies at least one of (1) the period of time the roll-back reservation mask slides ahead of current time and (2) the compute resources associated with the roll-back reservation mask.

Abstract: A system and method for reducing power consumption in clusters, grids, on-demand centers, etc. These principles can reduce both direct and indirect power consumption while maintaining either full cluster performance or adequate SLA based cluster performance. The method includes receiving at least one state data point regarding power consumption or temperature of at least one resource within the compute environment. Using intelligent policies to control power consumption, the method implements and interfaces with power managements facilities within the cluster, grid or on-demand center to implement policies, make dynamic changes, make predictions or actions, etc., to reduce the direct or indirect power consumption associated with a compute environment. Methods can include analysis of current workload and/or future workload in taking energy saving actions, and also involve reporting state information and updating algorithms based on historical experience or outside sources of information.

Abstract: Co-allocating resources within a compute environment includes. Receiving a request for a reservation for a first type of resource, analyzing constraints and guarantees associated with the first type of resource, identifying a first group of resources that meet the request for the first type of resource and storing in a first list, receiving a request for a reservation for a second type of resource, analyzing constraints and guarantees associated with the second type of resource, identifying a second group of resources that meet the request for the second type of resource and storing in a second list, calculating a co-allocation parameter between the first group of resources and the second group of resources and reserving resources according to the calculated co-allocation parameter of the first group of resources and the second group of resources. The request may also request exclusivity of the reservation.

Abstract: Disclosed herein are systems, methods, and computer readable-media for dynamically managing data-centric searches. The method includes receiving information associated with an event related to domain-specific searches to a database, identifying data at a first memory location in the database, the data being data identified in response to the domain-specific searches, duplicating the data at least once to at least one new memory location, and distributing processing more domain-specific searches amongst the at least one of the new memory location and the first memory location. The system can distribute the processing for more or additional domain-specific searches randomly, serially or using any other approach.

Abstract: An on-demand compute environment comprises a plurality of nodes within an on-demand compute environment available for provisioning and a slave management module operating on a dedicated node within the on-demand compute environment, wherein upon instructions from a master management module at a local compute environment, the slave management module modifies at least one node of the plurality of nodes.

Abstract: The invention relates to systems, methods and computer-readable media for controlling access to compute resources in a compute environment such as a cluster or a grid. The method of providing conditional access to a compute environment comprises associating a required service level threshold with a compute environment, associating a service level with a requestor, receiving a request for access to the compute environment from the requestor; and, if the service level of the requestor meets the specified service level threshold, then allowing access to the compute resources. The threshold-based access may be enforced by reservations, policies or some other method.

Abstract: The invention relates to systems, methods and computer-readable media for using system jobs for performing actions outside the constraints of batch compute jobs submitted to a compute environment such as a cluster or a grid. The method for modifying a compute environment from a system job comprises associating a system job to a queuable object, triggering the system job based on an event and performing arbitrary actions on resources outside of compute nodes in the compute environment. The queuable objects include objects such as batch compute jobs or job reservations. The events that trigger the system job may be time driven, such as ten minutes prior to completion of the batch compute job, or dependent on other actions associated with other system jobs. The system jobs may be utilized also to perform rolling maintenance on a node by node basis.

Abstract: A system and method of co-allocating resources within a compute environment are disclosed. The method embodiment of the invention comprises receiving a request for a reservation for a first type of resource, analyzing constraints and guarantees associated with the first type of resource, identifying a first group of resources that meet the request for the first type of resource and storing in a first list, receiving a request for a reservation for a second type of resource, analyzing constraints and guarantees associated with the second type of resource, identifying a second group of resources that meet the request for the second type of resource and storing in a second list, calculating a co-allocation parameter between the first group of resources and the second group of resources and reserving resources according to the calculated co-allocation parameter of the first group of resources and the second group of resources. The request may also request exclusivity of the reservation.

Abstract: A system and method for reserving resources within a compute environment such as a cluster or grid are disclosed. The method aspect of the disclosure includes receiving a request for resource availability in a compute environment from a requestor, associating a transaction identification with the request and resources within the compute environment that can meet the request and presenting the transaction identification to the requestor. The transaction ID can also be associated with a time frame in which resources are available and can also be associated with modifications to the resources and supersets of resources that could be drawn upon to meet the request. The transaction ID can also be associated with metrics that identify how well the resource fit with the request and modifications that can make the resources better match the workload which would be submitted under the request.

Abstract: A system and method of dynamically controlling a reservation of resources within a cluster environment to maximize a response time are disclosed. The method embodiment of the invention comprises receiving from a requester a request for a reservation of resources in the cluster environment, reserving a first group of resources, evaluating resources within the cluster environment to determine if the response time can be improved and if the response time can be improved, then canceling the reservation for the first group of resources and reserving a second group of resources to process the request at the improved response time.

Abstract: An on-demand compute environment comprises a plurality of nodes within an on-demand compute environment available for provisioning and a slave management module operating on a dedicated node within the on-demand compute environment, wherein upon instructions from a master management module at a local compute environment, the slave management module modifies at least one node of the plurality of nodes.

Abstract: The invention relates to systems, methods and computer-readable media for controlling access to compute resources in a compute environment such as a cluster or a grid. The method of providing conditional access to a compute environment comprises associating a required service level threshold with a compute environment, associating a service level with a requestor, receiving a request for access to the compute environment from the requestor; and, if the service level of the requestor meets the specified service level threshold, then allowing access to the compute resources. The threshold-based access may be enforced by reservations, policies or some other method.

Abstract: A system and method for reducing power consumption in clusters, grids, on-demand centers, etc. These principles can reduce both direct and indirect power consumption while maintaining either full cluster performance or adequate SLA based cluster performance. The method includes receiving at least one state data point regarding power consumption or temperature of at least one resource within the compute environment. Using intelligent policies to control power consumption, the method implements and interfaces with power managements facilities within the cluster, grid or on-demand center to implement policies, make dynamic changes, make predictions or actions, etc., to reduce the direct or indirect power consumption associated with a compute environment. Methods can include analysis of current workload and/or future workload in taking energy saving actions, and also involve reporting state information and updating algorithms based on historical experience or outside sources of information.

Abstract: Disclosed are a system, method and computer-readable medium relating to managing resources within a compute environment having a group of nodes or computing devices. The method comprises, for each node in the compute environment: traversing a list jobs having a fixed time relationship, wherein for each job in the list, the following steps occur: obtaining a range list of available timeframes for each job, converting each availability timeframe to a start range, shifting the resulting start range in time by a job offset, for a first job, copying the resulting start range into a node range, and for all subsequent jobs, logically AND'ing the start range with the node range. Next, the method comprises logically OR'ing the node range with a global range, generating a list of acceptable resources on which to start and the timeframe at which to start and creating reservations according to the list of acceptable resources for the resources in the group of computing devices and associated job offsets.