1/4
VM running slow on your HCI cluster? Try this 4-step diagnostic flow before opening a ticket
  

George Fady Lv2  Posted 2026-Oct-27 01:15

Last edited by George Fady 2026-Oct-27 01:20.

Hey everyone! One of the most common tickets I see on aSV/HCI clusters is "my VM feels slow," even though nothing in the manager looks obviously broken. Here is the order I actually check things in:

1. Cluster alerts & node health - Console > Cluster > Alarms. A node quietly sitting in a degraded state will drag down every VM running on it.
2. vSAN/local-disk latency & IOPS - check the datastore performance view. If latency on a pool is high, check whether dedup/compression overhead is the real bottleneck before blaming the network.
3. Network - uplink saturation or packet loss on the storage network can look exactly like a disk problem from the VM's point of view.
4. CPU ready time & memory ballooning on the VM itself - sometimes it is not the cluster at all, it is a noisy-neighbor VM or an under-provisioned one.

I attached the flow I personally run through below - feel free to save it for your own runbook.

Question for the community: which of these four turns out to be the most common root cause in your environment - storage, network, or just VM sizing? Share your war stories in the comments!

Like this topic? Like it or reward the author.

Creating a topic earns you 5 coins. A featured or excellent topic earns you more coins. What is Coin?

Enter your mobile phone number and company name for better service. Go