All cluster-nodes are hanging after nightly backup

[hape]

Hello all,

last night our cluster of 7 nodes is hanging on the proxmox-admin-interface (on port 8006). At the time the Proxmox-cluster-management does not work the VMs on it are all runng fine. I had to restart the whole node via SSH-Console to get the node working again.




We have the current version of PVE running -> "Virtual Environment 4.4-13/7ea56165"

Is this a known problem or is it unique on our installation?

Are here additional informations and/or logs necessary to clarify this problem?

Hans-Peter Straub

 

[hape]

I saw this message on one of the hosts console:

 

[joshin]

What does your network topology look like? And did any of your storage hang?

 

[hape]

It looks that this problem is the result of too less memory with the newer 4.4 version of PVE. After upgrading it on all nodes, the cluster is running normal. I'm now looking if this problem will appear again in the future.