How to Measure Windows Server Disk Latency and IOPS
Applies to: Windows Server 2019, 2022 and 2025.
Disk response time affects databases, profiles, updates and file services. Storage capacity alone does not describe performance.
Monitoring should collect enough evidence to diagnose trends without overwhelming storage or exposing sensitive logs. Visit networkmanager.info.
Prerequisites
- Map physical and virtual disks.
- Know workload windows.
- Collect during representative activity.
- Check host metrics when virtualized.
Procedure
Step 1: Map disks
Capture device and volume layout.
Get-Disk
Get-Partition
Get-VolumeStep 2: Sample latency
Measure read, write and transfers.
Get-Counter '\PhysicalDisk(_Total)\Avg. Disk sec/Read','\PhysicalDisk(_Total)\Avg. Disk sec/Write','\PhysicalDisk(_Total)\Disk Transfers/sec' -SampleInterval 2 -MaxSamples 20Step 3: Check queue
Add current and average disk queue counters in Performance Monitor.
Step 4: Identify processes
Use Resource Monitor or application telemetry.
Step 5: Check events
Review disk, storage and NTFS warnings.
Step 6: Compare baseline
Evaluate by workload and storage SLA.
Verification
Correlate sustained latency with storage events.
Get-WinEvent -LogName System -MaxEvents 300 | Where ProviderName -Match 'disk|stor|ntfs'Rollback
Diagnostics are read-only. Storage migration or controller changes require a separate rollback plan.
Operational notes
Guest latency can originate from the hypervisor or shared storage.
Official references
Explore Netcloud24 Canada.
