Abstract: Under the present invention, the performance of a set of system resources is monitored in response to incoming request traffic. When a system resource is approaching an overload condition, a corrective action is identified and implemented. Overload thresholds for each system resource and appropriate corrective actions are contained within a management policy. Based on a performance history of the corrective actions, the management policy can be changed/revised.

Abstract: Under the present invention, the performance of a set of system resources is monitored in response to incoming request traffic. When a system resource is approaching an overload condition, a corrective action is identified and implemented. Overload thresholds for each system resource and appropriate corrective actions are contained within a management policy. Based on a performance history of the corrective actions, the management policy can be changed/revised.

Abstract: Under the present invention, the performance of a set of system resources is monitored in response to incoming request traffic. When a system resource is approaching an overload condition, a corrective action is identified and implemented. Overload thresholds for each system resource and appropriate corrective actions are contained within a management policy. Based on a performance history of the corrective actions, the management policy can be changed/revised.

Abstract: Under the present invention, the performance of a set of system resources is monitored in response to incoming request traffic. When a system resource is approaching an overload condition, a corrective action is identified and implemented. Overload thresholds for each system resource and appropriate corrective actions are contained within a management policy. Based on a performance history of the corrective actions, the management policy can be changed/revised.

Abstract: Under the present invention, the performance of a set of system resources is monitored in response to incoming request traffic. When a system resource is approaching an overload condition, a corrective action is identified and implemented. Overload thresholds for each system resource and appropriate corrective actions are contained within a management policy. Based on a performance history of the corrective actions, the management policy can be changed/revised.

Abstract: Techniques are disclosed for programmatically allocating memory among competing services in a distributed computing environment. Characteristics of web request streams and formulas for cache hit rates and client response times are used to create an objective function for memory allocation, such that maximum benefit can be realized from the memory allocations. When a particular service is allocated more memory, it can store more of its objects in cache, which improves client response time. Optionally, information from service level agreements may be used as input to the memory allocation computations.

Abstract: A method for managing multi-tier SLA relationships. The method can include first computing costs of utilizing edge server resources in a CDN, costs of dedicating content host resources in a content host in lieu of the utilization, and prospective revenues which can be generated by the content host providing services based on the resources to content consumers. Minimum QoS levels can be identified which must be maintained when providing the services to the content consumers according to QoS terms in established SLAs between the content host and individual ones of the content consumers. Finally, a new SLA can be established between the content host and the CDN. Importantly, the new SLA can include QoS terms for selectively allocating resources in the CDN. Moreover, the QoS terms can optimize revenues generated by the content host providing services based on the selective allocation of resources and the computed costs.

Abstract: A method for enforcing a service discrimination policy in a storage system. The service discrimination policy enforcement method can include monitoring load metrics for physical resources required to access content stored within the storage system. A request to access the content stored within the storage system can be received. A corresponding guaranteed service level can be identified from the request. In consequence, a particular one of the physical resources can be selected to service the request based upon a determination that the selected physical resource can service the request while satisfying the guaranteed service level at a load indicated by the monitored load metrics.

Abstract: Under the present invention, the performance of a set of system resources is monitored in response to incoming request traffic. When a system resource is approaching an overload condition, a corrective action is identified and implemented. Overload thresholds for each system resource and appropriate corrective actions are contained within a management policy. Based on a performance history of the corrective actions, the management policy can be changed/revised.

Abstract: Techniques are disclosed for programmatically allocating memory among competing services in a distributed computing environment. Characteristics of web request streams and formulas for cache hit rates and client response times are used to create an objective function for memory allocation, such that maximum benefit can be realized from the memory allocations. When a particular service is allocated more memory, it can store more of its objects in cache, which improves client response time. Optionally, information from service level agreements may be used as input to the memory allocation computations.

Abstract: A method for enforcing a service discrimination policy in a storage system. The service discrimination policy enforcement method can include monitoring load metrics for physical resources required to access content stored within the storage system. A request to access the content stored within the storage system can be received. A corresponding guaranteed service level can be identified from the request. In consequence, a particular one of the physical resources can be selected to service the request based upon a determination that the selected physical resource can service the request while satisfying the guaranteed service level at a load indicated by the monitored load metrics.

Abstract: A method for managing multi-tier SLA relationships. The method can include first computing costs of utilizing edge server resources in a CDN, costs of dedicating content host resources in a content host in lieu of the utilization, and prospective revenues which can be generated by the content host providing services based on the resources to content consumers. Minimum QoS levels can be identified which must be maintained when providing the services to the content consumers according to QoS terms in established SLAs between the content host and individual ones of the content consumers. Finally, a new SLA can be established between the content host and the CDN. Importantly, the new SLA can include QoS terms for selectively allocating resources in the CDN. Moreover, the QoS terms can optimize revenues generated by the content host providing services based on the selective allocation of resources and the computed costs.

Abstract: A system and method termed adaptive message pipelining in which two or more data paths are joined by a data movement device. The data movement device has a data path controller for each incoming and outgoing data path. Adaptive message pipelining is a dynamic policy which adjusts between a store and forward data delivery method and a cut through delivery of data based upon network and I/O bus contention in order to decrease latency and maximize system throughput.