PREDICTIVE AUTO SCALING ENGINE

摘要

Techniques for predictively scaling a distributed application are described. Embodiments could monitor performance of an application within a cloud computing environment over a first window of time to collect historical performance data. Here, the application comprises a plurality of application instances. A workload of the application could be monitored over a second window of time to collect historical workload data. Embodiments could analyze both the historical performance data and the historical workload data to determine one or more scaling patterns for the application. Upon determining a present state of the application matches one of the one or more scaling patterns, a plan for predictively scaling the application could be determined. Embodiments could then predictively scale the plurality of application instances, based on the determined plan.

主权项

1. A method, comprising:
monitoring performance of an application within a cloud computing environment over a first window of time to collect historical performance data, wherein the application comprises a plurality of application instances; monitoring a workload of the application over a second window of time to collect historical workload data; analyzing both the historical performance data and the historical workload data to determine one or more scaling patterns for the application; upon determining a present state of the application matches one of the one or more scaling patterns, determining a plan for predictively scaling the application; predictively scaling the plurality of application instances, based on the determined plan; and monitoring the performance of the application with the scaled plurality of application instances over a second window of time to collect at least one of additional performance data and additional workload data, wherein the at least one of additional performance data and additional workload data is used to influence future scaling events.