Use the Datastore Performance dashboard to view performance problems related to storage such as high latency, high outstanding IO, and low utilization. This dashboard is designed for both the VMware administrator and the Storage administrator, to foster a closer collaboration between the two teams. Local datastores are treated separately.

Design Considerations

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

How to Use the Dashboard

The Datastore Capacity dashboard is layered, gradually providing details as you work top-down in the dashboard.

  • Overall Analysis

    Select a data center from the Datacenters table. The three bar charts which are, VM Performance, Read Performance, and Write Performance provide an overall analysis of the datastore performance in a given vCenter Server data center or vSphere World. They work together to provide better insight. Just like other performance charts, the value displayed is the worst value during the time period. After you select a data center, if the Worst VM Disk Latency displays No data to display, it means that you have no observed latency issues for VM disk performance.

    The VM Performance chart displays the kind of latency and how many VMs experience that kind of latency. The VM Performance chart is your primary chart as it measures latency at the VM level. The Read Performance and Write Performance charts measure latency at the datastore level, which means they are the normalized average of all VMs in that datastore. Expect the VM Performance chart to be higher than the Read Performance and Write Performance charts. Read and write latency are displayed separately for better insight.

  • Datastore Analysis

    The Datastores Performance table automatically lists all the shared datastores in the data center or vSphere World. Both the worst (peak) performance and the 95th percentile are displayed. If the latter is close to the peak and it is also high, then it is a sustained problem. If the latter is low, then the problem is for a short duration. The table is color coded. Select a datastore that you want to troubleshoot. The relevant metrics and configuration are displayed.

  • VM Analysis

    The list of VMs running in the selected datastore is displayed, with the relevant contention and utilization counters. Select the VM that you want to troubleshoot. The contention and utilization of the VM are automatically displayed. The number is at the VM level. If you suspect one of the virtual disks has high latency, use the counter Peak Virtual Disk Read Latency (ms) and Peak Virtual Disk Write Latency (ms).

  • Relationship

    From the Related Clusters and Hosts to selected Datastores widget, select either an ESXi host, a vSphere cluster, or a vSAN cluster. The relevant contention and utilization counters are displayed.