Method and system for analyzing root causes of relating performance issues among virtual machines to physical machines

摘要

According to one exemplary embodiment, a method for analyzing root causes applies an application-level dependency discovery and anomaly detection to find application-level dependencies in one or more virtual machines (VMs), and generate an application-level topology with anomaly, and then transfers the application-level topology with anomaly to a VM-level dependency, and transfers the VM-level dependency to a physical machine level (PM-level) dependency via a physical and virtual resource mapping, and eventually generates a group of event sets. A prioritized event list is generated by prioritizing the group of event sets.

主权项

1. A method for analyzing root causes of relating performance issues among virtual machines (VMs) to physical machines (PMs), in a physical data center configured to perform the method comprising:
providing communications between at least two VMs such that applications running on the at least two VMs communicate with each other; applying an application-level dependency discovery and anomaly detection to find an application-level dependency in one or more VMs running on a plurality of PMs in the physical data center, and generate an application-level topology with anomaly; transferring the application-level topology with anomaly to a VM-level dependency; transferring the VM-level dependency to a PM-level dependency via a physical and virtual resource mapping, and generating a group of event sets; and generating a prioritized event list by prioritizing the group of event sets, wherein a number of event sets in the group of event sets is equal to a number of links in the PM-level dependency.