The ESXi Contention dashboard is the primary dashboard for managing ESXi host performance. The VMware administrator or architect can use it to monitor and troubleshoot any performance issue. If you determine that there is a performance issue, use the ESXI Utilization dashboard to see if the cause for the contention is high utilization.

Design Consideration

The ESXi Contention dashboard complements the Cluster Contention Dashboard, and shares the same design consideration.

This dashboard is used as part of your Standard Operating Procedure (SOP). It is designed to be used daily, hence the views are set to show data in the last 24 hours. The dashboard provides performance metrics for virtual machines in the selected data center.

To view the common design considerations among all performance management dashboards, see the Performance Dashboards.

How to Use the Dashboard

  • ESXi CPU Performance and ESXI Memory Performance.
    • Review the two distribution charts for an overview of all the ESXi host's utilization and memory performance.
    • Both charts are using the percentage of VM facing performance counter and not the worst performance among VM counter because you are looking at the ESXi performance and not at the single VM performance. See how it handles all the VMs.
    • The bar chart is color coded. Keep the percentage of the VM population not being served under 10%.
  • ESXi Hosts Performance.
    • The ESXi hosts performance table lists all the ESXi hosts, sorted by the worst performance in the last 24 hours. If the table is displays the green color, then there is no need to analyze further. The reason 24 hours is selected instead of one week is that the performance greater than 24 hours are likely to be irrelevant.
    • You can change the time period to the period of your interest. The maximum number is reflected accordingly.
  • Select an ESXi host from the table.
    • All the health charts show the KPI of the selected cluster.
    • For performance, it is important to show both depth and breadth of a performance problem. A problem that impacts one or two VMs require a different troubleshooting than a problem that impacts all VMs in the cluster.
    • Worst CPU overlap among VMs in the host is included as it indicates a lot of interruptions. A running VM might get interrupted because the VMkernel needs the physical core to run something else. High and frequent numbers of interruptions are not healthy and can impact the VM performance.
    • Expect the network error to be 1% and dropped packet to be 0 most of the times, if not always. If it is not zero, analyze it to see if there are any patterns across all ESXi hosts, and bring it up with your network team.

Points to Note

  • Consider adding a third distribution chart and display the CPU co-stop counter in this third chart, as it complements the CPU ready counter. If your environment has relatively slow network and storage IO, you can add IO wait too.
  • Unlike the Cluster Performance dashboard, there is no average ESXi hosts performance (%) at the vSphere World level. The reason is most ESXi hosts are part of a cluster and monitoring should be done at the cluster level.
  • Certain settings such as power management and hyper threading can impact the performance. Consider adding a property widget to show relevant properties of a selected ESXi host.