Dynamic model-based analysis of data centers

摘要

Techniques for model-based analysis of a data center. A method includes creating a metamodel based on domain knowledge to represent a type of object and/or relationship of a data center, using static and dynamic configuration and data analysis techniques to discover topology of elements of the data center and represent the topology as a model that is an instance of the metamodel, using the model to perform analysis of the data center in connection with a specified task, leveraging domain knowledge represented in nodes of the metamodel to guide the analysis in terms of determining guidelines to apply to each node and determining relationships to traverse to continue the analysis, extending the domain knowledge by updating the metamodel upon discovery of additional knowledge for use in improving analysis tasks, and extending the model on-demand using dynamic analysis techniques upon detection of multiple analysis failures.

主权项

1. A method for model-based analysis of a data center, the method comprising:
creating a metamodel based on domain knowledge to represent at least one type of object and/or relationship of a data center; using static and dynamic configuration and data analysis techniques to discover topology of one or more elements of the data center and represent the topology as a model that is an instance of the metamodel; extending the metamodel during dynamic topology discovery via network flow analysis by identifying one or more new types of services corresponding to one or more newly discovered topology nodes, based on counting one or more connections initiated by versus one or more connections initiated to such nodes by one or more other network endpoints in the data center; using the model to perform analysis of the data center in connection with a specified task; leveraging domain knowledge represented in one or more nodes of the extended metamodel to guide the analysis in terms of determining one or more guidelines to apply to each node and determining one or more relationships to traverse to continue the analysis; extending the domain knowledge by updating the extended metamodel upon discovery of additional knowledge for use in improving one or more analysis tasks; and extending the model on-demand using one or more dynamic analysis techniques upon detection of multiple analysis failures; wherein at least one of the steps is carried out by a computer device.