System and method for managing a virtualized computing environment
AssigneeVMware, Inc.
InventorsAnne Marie Holler, Ganesha Shanmuganathan, Chirag Bhatt, Irfan Ahmad
Life of this patent
Estimating the term…
Abstract
A technique for predictive distributed resource scheduling and distributed power management includes analyzing patterns in the workload, predicting future workloads, and making recommendations for changes to the virtual computing environment. In addition, a cost-benefit analysis can be performed to determine whether the recommended change would likely result in improved performance.
Claims23
A method for managing distributed computing resources in a virtual computing environment, comprising:
- receiving resource usage data of one or more virtual machines executing on a host computer;
- comparing the resource usage data to previously collected resource usage data of the one or more virtual machines;
- generating a prediction of future workload based on said comparing;
- and
- generating a resource allocation recommendation based on the prediction;
- wherein generating a prediction of future workload based on said comparing further comprises:
- assuming a step pattern in the resource usage data;
- finding inter peak distances in the step pattern of the resource usage data;
- finding how long peaks in the step pattern of the resource data last;
- and
- predicting future workloads based on the inter peak distances in the step pattern of the resource usage data and based on how long the peaks in the step pattern of the resource usage data last.
A non-transitory computer-readable storage medium comprising instructions that, when executed in a computing device, causes the computing device to carry out the steps of:
- receiving resource usage data of one or more virtual machines executing on a host computer;
- comparing the resource usage data to previously collected resource usage data of the one or more virtual machines;
- generating a prediction of future workload based on said comparing;
- and
- generating a resource allocation recommendation based on the prediction;
- wherein generating a prediction of future workload based on said comparing further comprises:
- assuming a step pattern in the resource usage data;
- finding inter peak distances in the step pattern of the resource usage data;
- finding how long peaks in the step pattern of the resource data last;
- and
- predicting future workloads based on the inter peak distances in the step pattern of the resource usage data and based on how long the peaks in the step pattern of the resource usage data last.
A computer system, comprising:
- one or more host computers;
- and
- a virtual management computer, configured to:
- receive resource usage data of one or more virtual machines executing on the one or more host computers,
- compare the resource usage data to previously collected resource usage data of the one or more virtual machines,
- generate a prediction of future workload based on said comparing, and
- generate a resource allocation recommendation based on the prediction;
- wherein generating a prediction of future workload based on said comparing further comprises:
- assuming a step pattern in the resource usage data;
- finding inter peak distances in the step pattern of the resource usage data;
- finding how long peaks in the step pattern of the resource data last;
- and
- predicting future workloads based on the inter peak distances in the step pattern of the resource usage data and based on how long the peaks in the step pattern of the resource usage data last.
Dependencies are inferred from the claim text.