The log shows the disk mirror starts over NBD via SSH, progresses for minutes, then the channel fails (“open failed … Broken pipe”). That’s classic of a transport drop under sustained load.
Some of the things you can check -
Are MTUs identical...
Hi, it seems like its a symptom of a mis-configured or stale network state. I’d start to check with the host’s interface setup and check whether ARP entries are aging out too aggressively on the switch side.
Hi, it seems like your host’s vmbr0 only shows link-local (fe80::…) — no global IPv6. That suggests the host bridge isn’t getting or relaying a global IPv6, so containers won’t have an upstream path.
Can you check vmbr0 has a proper global IPv6...
Hi y’all,
I’ve released a Proxmox hardening guide (PVE 8 / PBS 3) that extends the CIS Debian 12 benchmark with Proxmox specific tasks.
Repo: https://github.com/HomeSecExplorer/Proxmox-Hardening-Guide
A few controls are not yet validated and are...
@silke
You’re correct: Proxmox (and corosync) recommend a dedicated NIC for the cluster to avoid heartbeat issues during congestion.
A workable compromise:
Node1 & Node2: connect a dedicated NIC each to your spare switch ports, use this as the...
Yes, you can run a 5‑node Ceph cluster with just DAC cables (Max number of nodes recommended for this setup will be 3 nodes) —if you treat the SFP+ links as a routed L3 ring or mesh, not a Layer‑2 loop. Proxmox has a documented method for this...