You can use disk metrics to observe your disks' performance and debugperformance problems. This page lists the metrics available for Google Cloud Hyperdiskand Persistent Disk volumes.

Disk metrics can help you answer questions such as the following:

• What's the average read IOPS for a virtual machine (VM) instance's disks?
• On average, what's the latency for read or write operations?
• What's the averagequeue depthfor a specific disk?

Review your disk's metrics to ensure its performance is sufficient for yourworkload. In addition, you should also do the following:

• Review the disk optimization guidelines. For more information,seeOptimize Google Cloud HyperdiskandOptimize Persistent Disk.

• Check the disk's health. For detailed information about disk health, seeMonitor disk health.

This document discusses the disk metrics Compute Engine automatically collectsfrom each VM and how to view them inCloud Monitoring,which is Google Cloud's monitoring solution.

Available disk metrics

You can view metrics in Cloud Monitoring, or programmatically retrievemetrics using theREST API,client libraries,andPromethus Query Language (PromQL).

The following table lists the disk-specific metrics available for every disk.You can collect additional metrics if you install theOps Agent on your VM.

For a full list of Compute Engine metrics, seeCompute Engine metrics.

Each metric type in this table must be prefixed withcompute.googleapis.com/,which has been omitted from the table for readability.

Visualize disk performance on a chart

You can visualize your disk's performance by plotting any ofthe metrics listed in the preceding section with Metrics Explorer.Metrics Explorer is part of Cloud Monitoring.

Example: Visualize average latency for the disks attached to a VM

To visualize the averagelatency for a VM's disks on a chart, follow these instructions.You can follow the same procedure for the other metrics.

1. In the Google Cloud console, go to theleaderboard Metrics explorer page:

   Go toMetrics explorer

   If you use the search bar to find this page, then select the result whose subheading isMonitoring.

2. In the toolbar of the Google Cloud console, select your Google Cloud project. ForApp Hub configurations, select the App Hub host project or the app-enabled folder's management project.
3. In theMetric element, expand theSelect a metric menu, enterVM Instance in the filter bar, and then use the submenus to select a specific resource type and metric:
   1. In theActive resources menu, selectVM Instance.
   2. In theActive metric categories menu, selectInstance.
   3. In theActive metrics menu, selectDisk average latency.
   4. ClickApply.
   The fully qualified name for this metric iscompute.googleapis.com/instance/disk/average_io_latency.

4. To add filters, which remove time series from the query results, use theFilter element.

5. Configure how the data is viewed. To display only the metrics for each disk attachedto a specific instance, follow these steps:
   • In theFilter element, clickAdd filter, and then selectinstance_name. For the value, select a specific instance name.
   • In theAggregation entry, set the first menu toMean and the second menu todevice_name.

   For more information about configuring a chart, seeSelect metrics when using Metrics Explorer.

What's next

• Learn how tooptimize Persistent Disk performance.
• Learn more aboutcreating charts with Metric Explorer.
• Learn more aboutCloud Monitoring.
• Enable theMonitoring API.
• View all theavailable metrics for Compute Engine.