Abstract: An approach is provided for determining availabilities of servers in multiple tiers of a workload. A Monte Carlo approach is performed on a non-linear program resulting from availability and resource constraints being added to an optimization problem which includes a workload availability requirement, resource requirements for redundancy groups (RGs) in the workload, sets of server sizes, and sets of availability categories. Feasible solutions to the optimization problem are generated and each includes a cloud site hosting the workload, a number of servers in an RG, server sizes of the servers in the RG, categories of availability of the servers in the RG, and a number of servers in the RG that are required to be active for the RG to be available. A cost of achieving the requirement of the availability of the workload is minimized by performing a Pareto analysis of the feasible solutions.

Abstract: An approach is provided for determining availabilities of servers in multiple tiers of a workload. Based on (1) a required availability of the workload, (2) resource requirements for redundancy groups (RGs) in the workload, (3) sets of server sizes, and (4) sets of availability categories, numbers of server(s) included in respective RGs are determined, allocations to the server(s) of one or more server sizes from a selected set of server sizes are determined, and allocations to the server(s) of one or more categories of availability from a selected set of categories is determined, so that a cost of achieving the required availability of the workload is minimized.

Abstract: A method and system for optimizing power consumption of a data center by dynamic workload adjustment. Workload of the data center is dynamically adjusted from a current workload distribution to an optimal workload solution. The optimal workload solution is a candidate workload solution of at least one candidate workload solution having a lowest sum of a respective power cost and a respective migration cost. Each candidate workload solution represents a respective application map that specifies a respective workload distribution among application programs of the data center. Dynamically adjusting the workload of the data center includes: estimating a respective overall cost of each candidate workload solution, selecting the optimal workload solution that has a lowest overall cost as determined from the estimating, and transferring the optimal workload solution to devices of a computer system for deployment.

Abstract: A method and associated system for continuously optimizing data archive management scheduling. A flow network is modeled, which creates vertexes organized in multiple levels and creating multiple edges sequentially connecting the vertexes of the multiple levels. The multiple levels consist of N+1 levels denoted as LEVEL0, LEVEL1, . . . , LEVELN, wherein N is at least 2, wherein LEVEL0 includes a source vertex, wherein LEVEL1 includes at least one task vertex associated with at least one archive management task, wherein EDGEK is directed from the vertex of LEVELK?1 to the vertex of LEVELK for K=1, . . . , N, wherein EDGE1 indicates that a first task associated with a first task vertex of LEVEL1 is scheduled by a job scheduler, and wherein EDGE1 has a first weight equal to a time unit to perform the first task.

Abstract: The present invention proactively identifies hotspots in a cloud computing environment through cloud resource usage models that use workload parameters as inputs. In some embodiments the cloud resource usage models are based upon performance data from cloud resources and time series based workload trend models. Hotspots may occur and can be detected at any layer of the cloud computing environment, including the server, storage, and network level. In a typical embodiment, parameters for a workload are identified in the cloud computing environment and inputted into a cloud resource usage model. The model is run with the inputted workload parameters to identify potential hotspots, and resources are then provisioned for the workload so as to avoid these hotspots.

Abstract: Embodiments of the present invention provide an approach for adapting an information extraction middleware for a clustered computing environment (e.g., a cloud environment) by creating and managing a set of statistical models generated from performance statistics of operating devices within the clustered computing environment. This approach takes into account the required accuracy in modeling, including computation cost of modeling, to pick the best modeling solution at a given point in time. When higher accuracy is desired (e.g., nearing workload saturation), the approach adapts to use an appropriate modeling algorithm. Adapting statistical models to the data characteristics ensures optimal accuracy with minimal computation time and resources for modeling. This approach provides intelligent selective refinement of models using accuracy-based and operating probability-based triggers to optimize the clustered computing environment, i.e., maximize accuracy and minimize computation time.

Abstract: An approach is provided for determining availabilities of servers in multiple tiers of a workload. Based on (1) a required availability of the workload, (2) resource requirements for redundancy groups (RGs) in the workload, (3) sets of server sizes, and (4) sets of availability categories, numbers of server(s) included in respective RGs are determined, allocations to the server(s) of one or more server sizes from a selected set of server sizes are determined, and allocations to the server(s) of one or more categories of availability from a selected set of categories is determined, so that a cost of achieving the required availability of the workload is minimized.

Abstract: A method is implemented in a computer infrastructure having computer executable code tangibly embodied on a computer readable storage medium having programming instructions. The programming instructions are operable to determine one or more optimal mappings between a server layer and a storage layer through a network layer based on performance metrics of one or more ports of at least one of the server layer, the storage layer and the network layer.

Abstract: A method and system for optimizing power consumption of a data center by dynamic workload adjustment. Workload of the data center is dynamically adjusted from a current workload distribution to an optimal workload solution. The optimal workload solution is a candidate workload solution of at least one candidate workload solution having a lowest sum of a respective power cost and a respective migration cost. Each candidate workload solution represents a respective application map that specifies a respective workload distribution among application programs of the data center. Dynamically adjusting the workload of the data center includes: estimating a respective overall cost of each candidate workload solution, selecting the optimal workload solution that has a lowest overall cost as determined from the estimating, and transferring the optimal workload solution to devices of a computer system for deployment.

Abstract: A method and system for optimizing power consumption of a data center by dynamic workload adjustment. At least one candidate workload solution for the data center is generated. Each candidate workload solution represents a respective application map that specifies a respective workload distribution among application programs of the data center. Workload of the data center is dynamically adjusted from a current workload distribution to an optimal workload solution. The optimal workload solution is a candidate workload solution of the at least one candidate workload solution having a lowest sum of a respective power cost and a respective migration cost. Dynamically adjusting the workload of the data center includes: estimating a respective overall cost of each candidate workload solution, selecting the optimal workload solution that has a lowest overall cost as determined from the estimating, and transferring the optimal workload solution to devices of a computer system for deployment.

Abstract: Embodiments of the present invention provide performance isolation for storage clouds. Under one embodiment, workloads across a storage cloud architecture are grouped into clusters based on administrator or system input. A performance isolation domain is then created for each of the clusters, with each of the performance isolation domains comprising a set of data stores associated with a set of storage subsystems and a set of data paths that connect the set of data stores to a set of clients. Thereafter, performance isolation is provided among a set of layers of the performance isolation domains.

Abstract: The present invention proactively identifies hotspots in a cloud computing environment through cloud resource usage models that use workload parameters as inputs. In some embodiments the cloud resource usage models are based upon performance data from cloud resources and time series based workload trend models. Hotspots may occur and can be detected at any layer of the cloud computing environment, including the server, storage, and network level. In a typical embodiment, parameters for a workload are identified in the cloud computing environment and inputted into a cloud resource usage model. The model is run with the inputted workload parameters to identify potential hotspots, and resources are then provisioned for the workload so as to avoid these hotspots.

Abstract: The present invention proactively identifies hotspots in a cloud computing environment through cloud resource usage models that use workload parameters as inputs. In some embodiments the cloud resource usage models are based upon performance data from cloud resources and time series based workload trend models. Hotspots may occur and can be detected at any layer of the cloud computing environment, including the server, storage, and network level. In a typical embodiment, parameters for a workload are identified in the cloud computing environment and inputted into a cloud resource usage model. The model is run with the inputted workload parameters to identify potential hotspots, and resources are then provisioned for the workload so as to avoid these hotspots.

Abstract: In general, embodiments of present invention provide an approach for calibrating a cloud computing environment. Specifically, embodiments of the present invention provide an empirical approach for obtaining end-to-end performance characteristics for workloads in the cloud computing environment (hereinafter the “environment”). In a typical embodiment, different combinations of cloud server(s) and cloud storage unit(s) are determined. Then, a virtual machine is deployed to one or more of the servers within the cloud computing environment. The virtual machine is used to generate a desired workload on a set of servers within the environment. Thereafter, performance measurements for each of the different combinations under the desired workload will be taken. Among other things, the performance measurements indicate a connection quality between the set of servers and the set of storage units, and are used in calibrating the cloud computing environment to determine future workload placement.

Abstract: A method and associated system for continuously optimizing data archive management scheduling. A flow network is modeled, which creates vertexes organized in multiple levels and creating multiple edges sequentially connecting the vertexes of the multiple levels. The multiple levels consist of N+1 levels denoted as LEVEL0, LEVEL1, . . . , LEVELN, wherein N is at least 2, wherein LEVEL0 includes a source vertex, wherein LEVEL1 includes at least one task vertex associated with at least one archive management task, wherein EDGEK is directed from the vertex of LEVELK-1 to the vertex of LEVELK for K=1, . . . , N, wherein EDGE1 indicates that a first task associated with a first task vertex of LEVEL1 is scheduled by a job scheduler, and wherein EDGE1 has a first weight equal to a time unit to perform the first task.

Abstract: A method, system and program product for transmitting configuration item data by a network object within a network. The steps include the network object detecting a change; the network object detecting an amount of traffic within the network; the network object transmitting configuration item data to the network at a level based on the amount of traffic present within the network. If all of the configuration item data was not sent and the network object detects that the amount of network traffic within the network is below a determined amount, the network object transmits remaining configuration item data to the network; and if all configuration item data was sent, returns to the step of the network object detecting a change.

Abstract: A method and associated system for continuously optimizing data archive management scheduling. A flow network is modeled. The flow network represents data content, software programs, physical devices, and communication capacity of the archive management system in various levels of vertices such that an optimal path in the flow network from a task of at least one archive management task to a worker program of the archive management system represents an optimal initial schedule for the worker program to perform the task.

Abstract: Embodiments of the present invention provide an integrated host and subsystem port selection methodology that uses performance measurements combined with information about active data paths. This technique also helps in resilient fabric planning by selecting ports from redundant fabrics. In a typical embodiment, host port to storage port pairs that create a path between a host and a storage device will be identified. From these pairs, a set of host port to storage port candidates for communicate data from the host to the storage device will be identified based on a set of resiliency constraints. Then, a specific host port to storage port pair will be selected from the set based on a lowest joint workload measurement. A path will then be created between the specific host port and storage port, and data will be communicated from the host to the storage device via the path.

Abstract: Embodiments of the present invention provide an approach for intelligent storage planning and planning within a clustered computing environment (e.g., a cloud computing environment). Specifically, embodiments of the present invention will first determine/identify a set of storage area network volume controllers (SVCs) that is accessible from a host that has submitted a request for access to storage. Thereafter, a set of managed disk (mdisk) groups (i.e., corresponding to the set of SVCs) that are candidates for satisfying the request will be determined. This set of mdisk groups will then be filtered based on available space therein, a set of user/requester preferences, and optionally, a set of performance characteristics. Then, a particular mdisk group will be selected from the set of mdisk groups based on the filtering.

Abstract: A method is implemented in a computer infrastructure having computer executable code tangibly embodied on a computer readable storage medium having programming instructions. The programming instructions are operable to determine one or more optimal mappings between a server layer and a storage layer through a network layer based on performance metrics of one or more ports of at least one of the server layer, the storage layer and the network layer.