We see the error message even if the vSAN performance service is on and running.

From /var/run/log copy the vsanmgmtd.log so that we have pre-existing collected data on each host.

Restart the vSAN performance service on each ESXi host from the vSAN enabled cluster.

You can reach the section to do this via the vSphere Web Client by going to the appropriate vCenter and cluster, then click the Monitor tab > Virtual SAN > Health