The ESXi host experiencing latency and intermittent APDs on NFS datastores.

Products

• VMware vSphere ESXi
• VMware vSphere ESX 8.x
• VMware vSphere ESX 7.x

Issue/Introduction

Symptoms:

• The VM's may go into a hung state/unresponsive.
• The VMs running on the ESXi hosts experience slowness and unable to migrate to any host.
• Performance has deteriorated messages for the NFS datastores observed in the /var/log/vmkernel.log file of the ESXi host:

<Date>T<Time> cpu1:1000211299)WARNING: NFS: NFSVolumeLatencyUpdate:4879: NFS volume <NFS Volume name> performance has deteriorated. I/O latency increased from average value of 16857(us) to 68722(us). Exceeded threshold 10000(us)

 

• Intermittent APD events reported for the NFS datastore in the /var/log/vmkernel.log file of the ESXi host:

2025-08-10T12:31:59.601Z cpu11:2097622)StorageApdHandlerEv: 110: Device or filesystem with identifier [########-########] has entered the All Paths Down state.

• Running esxtop on the ESXi through CLI reports High DAVG value indicating latency from the storage device (LUN):

 

 

 

Environment

VMware vSphere ESXi 7.x
VMware vSphere ESXi 8.x

 

Cause

A temporary network or NFS server availability issue disrupted connectivity between the ESXi host and the NFS server

Resolution

• Verify the driver and firmware versions of the vmnics used for NFS traffic to ensure they are compatible and up to date.

• Reboot all ESXi hosts to clear any residual references for the affected datastores following an APD (All Paths Down).

• For more information on how to troubleshoot NFS datastore connectivity issue refer to this article :Troubleshooting NFS datastore connectivity issues

• If  no issues observed from the ESXi host , engage the switch vendor to investigate and identify the root cause of the APD incidents.

• Engage both the storage and switch vendors for further investigation related to latency issues.

Additional Information

Please refer the below KB articles for NFS datastore's APD issues.

cancel ESXi hosts reports sudden NFS APD events where the host enters and exists an APD without any interaction.

Permanent Device Loss (PDL) and All-Paths-Down (APD) on host

Wolken View Helper Settings

SLO Due reminder(minutes):
NAD to reminder(hours):
Auto Refresh Interval (seconds):
Auto Refresh:
Auto Check-In:
Check-In Time:
Check-Out Time:
Save

▶

Refer the KB article Troubleshooting NFS datastore connectivity issues for latency on NFS datastore.