Abstract: Performance predictions in a computing cluster can be provided by sampling and storing historic workload request data of the computing cluster as time-stamped workload values, forecasting an expected total number of workload requests for a defined time interval in the future based on a time-series analysis of the time-stamped workload values, where the time-series analysis detects cyclic and repeating events in the time-stamped workload values. In response to a result of the time-series analysis, training a workload prediction model by using additional data about acyclic events in expected workload requests, where the training applies a statistical regression technique for predicting a future workload demand for the computing cluster, and in response to exceeding a predefined threshold value of the predicted future workload demand, reassigning resources of the computing cluster.

Abstract: Memory management is provided which includes a page replacement process managed by a storage manager and a workload manager. The page replacement process swaps out the content associated with a frame of physical memory to an auxiliary storage in order to provide a free frame. The memory management process includes: determining that the physical memory runs out of free frames; providing priority information from the workload manager to the storage manager, the priority information indicating the priority or business relevance of a certain process; selecting one or more pages to be swapped to the auxiliary storage based on the priority information; and swapping out the contents of the one or more selected pages to the auxiliary storage.

Abstract: Systems and methods for tracking computing resources are provided. Aspects include receiving, by a workload manager, a workload, wherein the workload is executable on a customer machine, and wherein the customer machine comprises a plurality of computing resources. The workload is analyzed to determine a workload profile. A token associated with the workload is received and associated with the workload profile. The token is authenticated and the workload is executed based at least in part on authentication of the token.

Abstract: Performance predictions in a computing cluster can be provided by sampling and storing historic workload request data of the computing cluster as time-stamped workload values, forecasting an expected total number of workload requests for a defined time interval in the future based on a time-series analysis of the time-stamped workload values, where the time-series analysis detects cyclic and repeating events in the time-stamped workload values. In response to a result of the time-series analysis, training a workload prediction model by using additional data about acyclic events in expected workload requests, where the training applies a statistical regression technique for predicting a future workload demand for the computing cluster, and in response to exceeding a predefined threshold value of the predicted future workload demand, reassigning resources of the computing cluster.

Abstract: Systems and methods for tracking computing resources are provided. Aspects include receiving, by a workload manager, a workload, wherein the workload is executable on a customer machine, and wherein the customer machine comprises a plurality of computing resources. The workload is analyzed to determine a workload profile. A token associated with the workload is received and associated with the workload profile. The token is authenticated and the workload is executed based at least in part on authentication of the token.

Abstract: Memory management is provided which includes a page replacement process managed by a storage manager and a workload manager. The page replacement process swaps out the content associated with a frame of physical memory to an auxiliary storage in order to provide a free frame. The memory management process includes: determining that the physical memory runs out of free frames; providing priority information from the workload manager to the storage manager, the priority information indicating the priority or business relevance of a certain process; selecting one or more pages to be swapped to the auxiliary storage based on the priority information; and swapping out the contents of the one or more selected pages to the auxiliary storage.

Abstract: A method of autonomous provisioning of resources of a computer system, wherein: performance-critical workload of the computer system is monitored; workload suffering is detected based on comparing the performance-critical workload with defined values of performance-critical workload goals; types of missing resources are determined; additional resources available for activation are determined; the additional resources are activated, and a notification of the activation is generated for being sent to a system provider for automated billing of the added capacity, and a computer device, data processing program, computer program product, and computer data signal therefor.

Abstract: A method for automatically adding capacity to a computer for a workload is provided. Metric information is received, defined in a policy, about a workload running on a computer. Capacity information for the computer is retrieved and is serialized in a serialized list in accordance with the policy. A demand for the workload is received and is a request for additional capacity of the computer. The demand for the workload is analyzed to determine whether the demand is characterized as a speed or a general purpose demand. Speed demand includes an increase in a speed level for the computer, and general purpose demand includes an increase in a speed level and/or a number of processors for the computer. An appropriate capacity is determined, from the serialized list, to add to the computer for the workload based on the analysis. The appropriate capacity of the computer is activated for the workload.

Abstract: A method for automatically adding capacity to a computer for a workload is provided. Metric information is received, defined in a policy, about a workload running on a computer. Capacity information for the computer is retrieved and is serialized in a serialized list in accordance with the policy. A demand for the workload is received and is a request for additional capacity of the computer. The demand for the workload is analyzed to determine whether the demand is characterized as a speed or a general purpose demand. Speed demand includes an increase in a speed level for the computer, and general purpose demand includes an increase in a speed level and/or a number of processors for the computer. An appropriate capacity is determined, from the serialized list, to add to the computer for the workload based on the analysis. The appropriate capacity of the computer is activated for the workload.

Abstract: A method of autonomous provisioning of resources of a computer system, wherein: performance-critical workload of the computer system is monitored; workload suffering is detected based on comparing the performance-critical workload with defined values of performance-critical workload goals; types of missing resources are determined; additional resources available for activation are determined; the additional resources are activated, and a notification of the activation is generated for being sent to a system provider for automated billing of the added capacity, and a computer device, data processing program, computer program product, and computer data signal therefor.