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 Network administrator, to foster a closer collaboration between the two teams.

Design Considerations

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

How to Use the Dashboard

  • Select a data center from the data centers table.
    • The list of shared datastores in the data center is shown with their KPI.
      Note: Datastores that are unavailable are not shown.
  • Datastore Performance.
    • Read and Write latency are shown separately in the datastore performance table for a better insight. The nature of read and write problems might not be the same so it is useful to see the difference.
    • Both the worst (peak) performance and 95th percentile are shown. If the latter is close to the peak and high, then it is a sustained problem. If the latter is low, then it is a short duration.
    • The table is color-coded. If your operations require a different threshold, edit the widget to adjust it accordingly.
  • Select a datastore you want to troubleshoot.
    • Its read latency, write latency and outstanding IO is automatically shown.
      Note: The latency is the normalized average of all VMs in the datastore.
    • Its IOPS and throughput are also displayed. These line charts are not color-coded as it varies per customer. Edit the widget and add your expected threshold. It makes it easier for the Operations team.
    • The list of VMs is displayed.
  • Select a VM you want to troubleshoot.
    • Its read latency and write latency are shown.
      Note: The number is at the VM level. If you suspect one of the virtual disks has a high latency, use the counter Peak Virtual Disk Read Latency (ms) and Peak Virtual Disk Write Latency (ms).

Points to Note

  • The vSphere storage is represented as a datastore. The underlying storage protocol can be files (NFS) or blocks (VMFS). vSAN uses VMFS as its consumption layer as it is unique to vSAN, and has its own monitoring need. Latency can happen when IOPS and throughput are not high. When latency occurs, troubleshooting can take much time.
  • You can look at the logs and queue in the various storage stacks (for example, driver) and monitor their performance.
  • Datastores that share the same underlying physical array can experience problem at the same time. The underlying array can experience a hot spot on its own, as it is made of independent magnetic disks or SSD.
  • The dashboard does not have datastore clusters. If your environment uses it, add a View List to list them, and use this view list to drive the Datastore Performance view list.