Shared Storage Recommendation for Proxmox Cluster

[Testani]

root@pve03:~# netstat -s | egrep -i "retrans|loss|time"
198 segments retransmitted
536 TCP sockets finished time wait in fast timer
10122 packets rejected in established connections because of timestamp
Quick ack mode was activated 54423 times
3 times recovered from packet loss due to fast retransmit
Detected reordering 22 times using SACK
Detected reordering 24 times using reno fast retransmit
36 fast retransmits
TCPTimeouts: 14
TCPLossProbes: 136
TCPSynRetrans: 12
TcpTimeoutRehash: 14
root@pve03:~# uname -a
Linux pve03 6.8.8-



Thank you for your time, really.
The output with millions of retransmitted packets was caused by a massive test window with detach and attach interfaces. Above you have the output of the "stopped" situation. I have already tried everything and ended up having 1 dry path on which to instantiate a single cable without success.
I continue with the modification of the kernels and tests in that direction but I repeat that on the same hardware, same switch and same conf I have other servers and hypervisors that are working without problems. The same server with HV change works, even grafting an installation.

 

[floh8]

We need the VMs to be highly available. That's the reason looking for a reliable storage solution that can be shared between hosts. For the VMs, storage capacity planned is 12 TB.

I did initial research and I found that iSCSI doesn't support snapshots. Requires the advice from experts who is running small proxmox clusters with budget friendly hardware but without losing reliability.

Maybe u Wanne go with NFS. A workaround for snapshots with iscsi is to use backups.