The Cluster Performance dashboard combines the functionality of the Cluster Contention, Cluster Utilization, ESXi Contention, and ESXi Utilization dashboards.

How to Use the Dashboard

The Cluster Performance dashboard is organized into sections for ease of use.
  • Overall Analysis

    The Average Cluster Performance health chart is green when all the clusters are performing well. If the clusters are unable to serve the VMs well, all the clusters are no longer green, with a few occurrences of red.

    As the chart displays all the clusters, it uses the vSphere World object. This object is the parent of the vCenter Server object, and so it displays all the clusters from all the vCenter Servers.

    The metric used is Performance \ Clusters Performance (%) and is the primary KPI for your entire IaaS. It plots how your IaaS is performing every five minutes, giving you the trend view of overall performance.

  • Multi-Cloud Analysis

    If the health chart is not green, and you want to find out which clusters are not performing, use the vSphere Clusters widget. The table lists all the clusters, starting with the cluster with the lowest performance. By default, the data displayed is from the last 24 hours. The Worst Performance column displays the lowest number in the time period. By default, vRealize Operations collects data every 5 minutes, so this is the lowest point among 288 datapoints (12 x 24 = 288).

    The Worst Performance column displays the lowest performance in the last period, specified under Time Settings.

  • Per-Cluster Analysis

    Select a cluster from the vSphere Clusters widget to see the trend over time. After you determine the cluster you want to investigate, review the five scoreboards: CPU, memory, disk, network, and others.

  • VM Shares

    A common root cause for uneven performance problems is uneven shares. Each slice in the pie chart must correspond to a class of service. If the entire cluster is serving one class, then you should see a simple circle with no slices.

  • Resource Pool Analysis

    Resource pool is another common reason behind uneven VM performances. A cluster with too many resource pools makes performance management difficult.

    The Resource Pools in the cluster provides a table listing all the resource pools.

  • ESXi Analysis

    A cluster is a collection of ESXi hosts and the performance can be affected by uneven performance among the member hosts. You can drill down from a cluster to the ESXi hosts. The ESXi Hosts in the Selected Cluster widget lists all the ESXi hosts in the cluster, sorted by the worst performance in the last 24 hours. If the table displays values in green, you do not have to analyze further.

    You can change the time period to the period of your interest. The maximum number will be reflected accordingly.

    The table helps you quickly compare the performance of each ESXi. You can also see the performance over time, to see a trend.

    Certain settings such as power management and hyper threading can impact performance. The ESXi Hosts in the Selected Cluster widget displays the relevant property of a selected ESXi Host.

  • VM Analysis

    When you select a cluster or ESXi from the Running VMs in the selected Cluster or ESXi widget the VMs that are running are automatically listed. Use this table to verify if the cluster or host performance problems were caused by VM configuration and usage. It is possible that the VM was not on the same host at the time of problem, due to vMotion.

    To drill down into a particular VM, select it and click the double arrow before the widget title.
  • Datastore Analysis

    Use the Shared datastores in the Cluster widget to see a list of shared datastores accessible by hosts in the cluster. You can also drill down to the selected datastore.