Abstract: Embodiments of the present invention provide an approach for analyzing operating costs (e.g., metered cost effects) for deployment patterns (and changes thereto) in a networked computing environment. In a typical embodiment, a deployment pattern for the networked computing environment is identified. The deployment pattern may comprise a set of components arranged in a network topology. Moreover, the set of components may be associated with a set of policies (e.g., stored in a computer memory medium and/or computer storage device). A cost analysis algorithm(s) may then be selected for the deployment pattern. The selected algorithm(s) may then be applied (e.g., to the deployment pattern and/or network computing environment) to analyze the operating costs of the deployment pattern.

Abstract: Embodiments of the present invention provide an approach for validating deployment patterns/topologies (e.g., prior to being deployed) against existing patterns that have already been determined to be compliant (e.g., against a set of policies/standards). In a typical embodiment, individual components of a proposed deployment pattern are identified and then evaluated against previously approved deployment patterns (e.g., based on standards and/or policies). Components of the proposed deployment patterns that are deemed non-compliant are identified, and corrective action(s) may be determined to address any non-compliance (e.g., to put the non-compliant components into compliance, to remove the non-compliant components, etc.).

Abstract: Embodiments of the present invention relate to an approach for resolving and/or implementing policies based on layers of a network stack (e.g., cloud computing stack). Specifically, for a given policy that is being resolved, the system first evaluates the applicability of the policy to each layer in the network stack. For a given policy, the system then evaluates the relative effectiveness of applying the policy to achieve the overall goal of the policy. Based on the best fit evaluation of the relative comparison, the system then decides how and where the policy is enacted (e.g., determines a protocol for implementing the policy).

Abstract: A first device transfers a running application to a second device. A first device sends a request to transfer a running application to a second device. The second device determines whether the application is presently installed on the second device. The second device determines whether the application is an application designed to run on a platform of the second device. The second device then receives state information for the application from the first device. In response to receiving the state information, the second device executes a counterpart application utilizing the state information received from the first device.

Abstract: A first device transfers a running application to a second device. A first device sends a request to transfer a running application to a second device. The second device determines whether the application is presently installed on the second device. The second device determines whether the application is an application designed to run on a platform of the second device. The second device then receives state information for the application from the first device. In response to receiving the state information, the second device executes a counterpart application utilizing the state information received from the first device.

Abstract: Embodiments of the present invention provide an approach for optimizing a configuration of virtual machine (VM) instances. In a typical embodiment, such optimization comprises either the splitting of a single VM instance into multiple VM instances or the consolidation of multiple VM instances into fewer (e.g., a single) VM instance. Along these lines, it will first be determined which VM instances would be good candidates for reconfiguration. Under one approach, VM instances that are candidates for reconfiguration are identified based upon an analysis of applicable/associated service level agreement (SLA) terms versus the performance of the VM instances. For example, VM instances can be reconfigured if such reconfiguration will maximize a benefit provided by the applicable SLA terms (e.g., if the splitting of a single VM instance into multiple VM instances would cause a workload to be processed more efficiently, resulting in a more favorable cost/benefit ratio).

Abstract: Embodiments of the present invention provide a self-updating node controller (e.g., for an endpoint/node such as a cloud node). In general, the node controller will autonomously and automatically obtain program code (e.g., scripts) from a central repository. Among other things, the program code enables the node controller to: receive a request message from a cloud node queue associated with the endpoint; process a request corresponding to the request message; automatically update the program code as needed (e.g., when requests cannot be processed/fulfilled); place a state message indicating a state of fulfillment of the request in a cloud manager queue associated with a cloud manager from which the request message was received; update an audit database to reflect the state of fulfillment; and/or place a failure message in a triage queue if the request cannot be processed by the node controller.

Abstract: Embodiments of the present invention provide an intelligent node controller (e.g., for an endpoint/node such as a cloud node) to process requests. Specifically, (among other things) the node controller will read a request message from a cloud node queue that is associated with the endpoint. The request message typically includes details related to a request for cloud resources and/or services received from a consumer. The node controller executes program code in an attempt to process the request. As the request is being processed, the node controller can place state messages indicating a state of fulfillment of the request on a cloud manager queue that is associated with a cloud manager from which the request message was received. In addition, the node controller can update an audit via an audit queue with the state messages. When a request cannot be processed, the node controller can place a failure message in a triage queue or the like.

Abstract: Embodiments of the present invention provide a distributed approach to request processing. Specifically, in a typical embodiment, a request is received via a cloud dispatcher, which generates and places a corresponding message in a cloud manager queue associated with a set (at least one) of cloud managers. The message is then placed in a cloud node queue associated with a set of cloud nodes that process the message and provide state information related to request processing in an audit queue associated with an audit database. In addition, cloud manager state information is placed in a dispatcher queue associated with the cloud dispatcher. This state information is used by the cloud dispatcher to determine where to place incoming requests. Under these embodiments, each cloud resource runs self-contained management code and performs actions by receiving instructions from a queue.