Automated capacity provisioning method using historical performance data
The method may include collecting performance data relating to processing nodes of a computer system which provide services via one or more applications, analyzing the performance data to generate an operational profile characterizing resource usage of the processing nodes, receiving a set of attributes characterizing expected performance goals in which the services are expected to be provided, and generating at least one provisioning policy based on an analysis of the operational profile in conjunction with the set of attributes. The at least one provisioning policy may specify a condition for re-allocating resources associated with at least one processing node in a manner that satisfies the performance goals of the set of attributes. The method may further include re-allocating, during runtime, the resources associated with the at least one processing node when the condition of the at least one provisioning policy is determined as satisfied.
1. A method for automatically scaling cloud computer resources, the method comprising: receiving a provisioning strategy; obtaining historical performance data characterizing a computer system over a first period of time, the computer system implementing computer resources with fluctuating demand over time; programmatically executing a trending analysis using the historical performance data over the first period of time to predict one or more resource usage patterns for a second period of time after the first period of time; automatically generating one or more auto-scaling policies based on results of the trending analysis and the provisioning strategy, the one or more auto-scaling policies including at least one of a first auto-scaling policy that correlates arrival rate and required servers, a second auto-scaling policy that correlates time-dependent information and required servers, a third auto- scaling policy that correlates utilization and required servers, or a fourth auto-scaling policy that correlates response time and required servers; monitoring current performance data characterizing the computer system during the second period of time, including monitoring the fluctuating demand; implementing the one or more auto-scaling policies, based on the monitoring and in reaction to the fluctuating demand, to allocate a quantity of the required servers to maintain the arrival rate within a defined range during the second period of time and one or more of the time-dependent information, the utilization, and the response time within the defined range during the second period of time; and provisioning the computer resources based on the one or more auto-scaling policies during the second period of time.
2. The method of claim 1 , wherein the provisioning strategy indicates a total average computer processing unit (CPU) utilization.
3. The method of claim 1 , wherein the execution of the trending analysis detects changes in daily or weekly resource usage patterns.
4. The method of claim 1 , further comprising:
obtaining historical performance data over the second period of time; and
programmatically re-executing the trending analysis using the historical performance data over the second period of time to predict one or more resource usage patterns for a third period of time after the second period of time.
5. The method of claim 1 , wherein the receiving step, the obtaining step, the programmatically executing step, the automatically generating step, and the provisioning step are sequentially executed without any manual intervention.
6. The method of claim 1 , wherein the one or more auto-scaling policies include a plurality of auto-scaling policies, the plurality of auto-scaling policies including the first auto-scaling policy, the second auto-scaling policy, the third auto-scaling policy, and the fourth auto-scaling policy.
7. A non-transitory computer-readable medium storing instructions, when executed by at least one processor, are configured to cause the at least one processor to execute the following operations: receive a provisioning strategy; obtain historical performance data characterizing a computer system over a first period of time, the computer system implementing computing resources with fluctuating demand over time; programmatically execute a trending analysis using the historical performance data over the first period of time to predict one or more resource usage patterns for a second period of time after the first period of time; automatically generate a plurality of auto-scaling policies based on results of the trending analysis and the provisioning strategy, the plurality of auto-scaling policies including a first auto-scaling policy that correlates time-dependent information and required servers, and a second auto-scaling policy that correlates utilization and required servers; monitor current performance data characterizing the computer system during the second period of time, including monitoring the fluctuating demand; implement the one or more auto-scaling policies, based on the monitoring and in reaction to the fluctuating demand, to allocate a quantity of the required servers to maintain the arrival rate within a defined range during the second period of time and one or more of the time-dependent information, the utilization, and the response time within the defined range during the second period of time; and provision cloud computer resources based on the plurality of the auto-scaling policies during the second period of time.
8. The non-transitory computer-readable medium of claim 7 , wherein the provisioning strategy indicates a total average computer processing unit (CPU) utilization.
9. The non-transitory computer-readable medium of claim 7 , wherein the execution of the trending analysis detects changes in daily or weekly resource usage patterns.
10. The non-transitory computer-readable medium of claim 7 , further comprising:
obtain historical performance data over the second period of time; and
programmatically re-execute the trending analysis using the historical performance data over the second period of time to predict one or more resource usage patterns for a third period of time after the second period of time.
11. The non-transitory computer-readable medium of claim 7 , wherein the receive operation, the obtain operation, the programmatically execute operation, the automatically generating operation, and the provisioning operation are sequentially executed without any manual intervention.
12. A capacity planning system for automatically scaling cloud computer resources in a computer system, the capacity planning system comprising: at least one processor; a non-transitory computer-readable medium storing executing instructions that when executed by the at least one processor are configured to cause the at least one processor to: receive a provisioning strategy; obtain historical performance data characterizing the computer system over a first period of time, the computer system implementing computing resources with fluctuating demand over time; programmatically execute a trending analysis using the historical performance data over the first period of time to predict one or more resource usage patterns for a second period of time after the first period of time; automatically generate a plurality of auto-scaling policies based on results of the trending analysis and the provisioning strategy, the plurality of auto-scaling policies including a first auto-scaling policy that correlates response time and required servers, and a second auto-scaling policy that correlates arrival rate and required servers; monitor current performance data characterizing the computer system during the second period of time, including monitoring the fluctuating demand; implement the one or more auto-scaling policies, based on the monitoring and in reaction to the fluctuating demand, to allocate a quantity of the required servers to maintain the arrival rate within a defined range during the second period of time and one or more of the time-dependent information, the utilization, and the response time within the defined range during the second period of time; and provision the cloud computer resources based on the plurality of the auto-scaling policies during the second period of time.
13. The capacity planning system of claim 12 , wherein the provisioning strategy indicates a total average computer processing unit (CPU) utilization.
14. The capacity planning system of claim 12 , wherein the execution of the trending analysis detects changes in daily or weekly resource usage patterns.
15. The capacity planning system of claim 12 , further comprising:
obtain historical performance data over the second period of time; and
programmatically re-execute the trending analysis using the historical performance data over the second period of time to predict one or more resource usage patterns for a third period of time after the second period of time.
16. The capacity planning system of claim 12 , wherein the receiving step, the obtaining step, the programmatically executing step, the automatically generating step, and the provisioning step are sequentially executed without any manual intervention.