An administrator has been alerted that the database VMs in the environment are not responsive.
During the investigation, the administrator discovered that the unresponsive VMs were migrated to different nodes in the cluster and have tasks in Prism Central with the following name: ADS: Remove Resource Contention.
What caused these VM migrations?
ADS (Acropolis Dynamic Scheduling) detected that the host CPU was running over 85% for 10 minutes. ADS monitors VM CPU utilization and storage CPU utilization to ensure that resources are allocated efficiently and to avoid contention. If the CPU usage on a host remains high, ADS will initiate VM migrations to redistribute the load and mitigate performance issues.
ADS monitors VM CPU utilization that includes the total CPU usage of each guest VM and storage CPU utilization that includes the storage controller (Stargate) CPU usage per VM or iSCSI target for the last 10 minutes. Based on the last 10 minutes of data, ADS estimates whether a CPU hotspot exists or is going to exist on a node. ADS does not monitor the network usage, and memory when memory overcommit is not enabled.
ADS monitors the following resources: VM CPU Utilization: Total CPU usage of each guest VM. Storage CPU Utilization: Storage controller (Stargate) CPU usage per VM or iSCSI target ADS does not monitor memory and networking usage. https://portal.nutanix.com/page/documents/details?targetId=AHV-Admin-Guide-v6_7:ahv-dynamic-scheduling-c.html