load average: 384.00, 383.34, 380.60

[Fathi]

Hi,
One of my cluster nodes is hanging repetitively and i have no other choice than to hard reset it.
When i execute the uptime command i get the following result:
08:42:42 up 2 days, 19:03, 1 user, load average: 384.00, 383.34, 380.60
This node is running latest pve 7.1 updated with the no-subscription apt repo to the freshest packages.
I can't do any investigation on that node, as it stops responding to any cli command, to know what's "eating" all these resources.
Have anyone faced similar situation ?
TIA.
Fathi B.N.

 

[mira]

Any chance you could access the syslogs (/var/log/syslog.*) for that node? By booting a Live ISO or something like that?
Most likely the logs will contain some information on the issue.