Patent attributes
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying a plurality of software components deployed on a cluster of computing nodes, each component operating on one or more respective nodes within the cluster to process a workload, each component utilizing at least the following resources of the one or more respective nodes: storage, processing power, memory, and disk and network input and output operations; determining, for each identified component, current and historical usages of the resources of the one or more respective nodes by the component when processing the workload; receiving data specifying a future workload; and calculating, from the current and historical usages of each component, an estimated capacity required for the cluster to process the future workload, where the estimated capacity specifies, at least, how many nodes should be in the cluster to process the future workload.
