×
Single node, clusters, HA & support – incl. Private Networks & vSwitch network setup
The combination of Proxmox VE and Hetzner offers enterprise virtualization without vendor lock-in – at a fraction of the cost of VMware or cloud VMs.
Proxmox is open source. Hetzner dedicated from ~€40/month. No per-socket licenses like VMware.
Hetzner data centers in Germany and Finland. Your data stays in the EU.
Root access, custom network configuration, no dependency on cloud provider APIs.
Dedicated hardware = consistent performance. No noisy neighbors, no throttling.
The cleaner your prechecks, the fewer mysterious cluster problems later – especially with Corosync and storage.
Single node (backup/DR) or HA cluster (failover)?
Don't change later – clusters don't like that.
Plan management, Corosync/cluster, storage separately.
Strict IP/MAC binding; consider virtual MACs for bridging.
Web GUI (8006), SSH (22) – via allowlist/VPN/jump host.
Automatically configured via DHCP/hc-utils on standard images.
Different installation paths for Hetzner Dedicated Servers – we choose the right one for your setup.
Boot rescue, install Debian (e.g. via installimage), then upgrade to Proxmox.
When useful:
Maximum control over partitioning/RAID
Boot official Proxmox ISO from rescue system via QEMU + VNC. ZFS-friendly.
Important:
Set interface names correctly before reboot
Automated installation for Hetzner Dedicated, incl. network configuration and ZFS RAID-1. Ideal for quick start and development – for production, adaptations are necessary.
Best practice: Corosync/cluster traffic should be separated, as other traffic causes latency/jitter and Corosync then "loses" nodes.
Must be set before cluster creation.
Dedicated link/network (vSwitch/Private Network).
Storage traffic must not disturb Corosync.
# Node 1: Create cluster
pvecm create pve-cluster-1
# Node 2: Join the cluster
pvecm add <IP-of-Node1>
# Check status
pvecm status
pvecm nodesWeb GUI/SSH (strictly limited, ideally via VPN/jump host)
Exclusive, quiet link (Private Network / vSwitch / dedicated NIC)
Separated (Ceph/NFS/iSCSI), not on Corosync link
Hetzner uses strict IP/MAC binding. Depending on setup, routed setups are required; for bridging you need virtual MACs – otherwise packets may end up as "abuse".
For bridged (vmbr0 directly on physical NIC): Set vMACs in Robot Panel, otherwise Hetzner routing discards your frames. For routed: Consider IP forwarding.
Hetzner-specific problems and their solutions
Cause: Wrong interface name/config after ISO install via rescue/QEMU
Solution: Set interface names correctly before reboot (follow Hetzner documentation)
Cause: Bridged setup without proper (virtual) MAC binding
Solution: Set vMACs in Robot Panel or switch to routed setup
Cause: Corosync running on overloaded network (storage/backup/migration)
Solution: Set up separate Corosync network (Private Network/vSwitch)
Cause: Hetzner Cloud Networks are private but not automatically encrypted
Solution: Use application TLS or VPN/WireGuard
Proxmox works as single node or as cluster. For many SMB setups, a properly operated single-node system is sufficient – what matters is backups, monitoring and documented updates.
Budget focus, simpler management, manageable workloads
Professionally operated with backups, restore tests and monitoring
Can be expanded to cluster anytime when requirements grow
Which architecture fits your requirements? We help with the decision.
One dedicated server for smaller workloads or cost focus. Full performance, simple setup, clear responsibility.
3+ nodes for true high availability. Automatic failover, live migration, maximum resilience.
Management/bastion in Hetzner Cloud, workloads on dedicated servers. vSwitch connects both worlds.
Hetzner offers flexible network options – we configure them optimally for your Proxmox cluster.
Private IPs, not internet-routed, L3 links. Ideal for cluster communication and management traffic.
Connects dedicated servers with cloud private networks. Layer-2 connection for seamless communication.
Best practice: Management, cluster/Corosync and storage on separate networks for security and performance.
Web GUI, SSH, API access
Heartbeat, quorum, cluster sync
Ceph, NFS, iSCSI traffic
Proxmox Cluster Manager and HA Manager enable automatic failover on node failures. We configure this for you.
pvecm, naming concept, network requirements
Automatic failover of VMs and containers
3-node recommendation, QDevice for 2-node setups
Fast, simple, ideal for local storage. But: HA/live migration requires shared storage.
Recommended for simple setupsShared storage, HA-friendly, self-healing. More complex, requires dedicated network.
Recommended for HA clustersProfessional operations mean: automation, monitoring, documented processes.
How we work – transparent and structured.
Analysis of existing workloads, network, storage and requirements
Planning the optimal configuration for your requirements
Setup of cluster, network, storage and backup systems
Failover tests, restore tests, live migration validation
Cutover of existing workloads with minimal downtime
Ongoing maintenance, monitoring and support as needed
We set up your Proxmox cluster, document everything and hand over to your team.
Your team handles daily operations, we support with updates, troubleshooting and expansions.
We handle complete operations: monitoring, updates, backups, support – you focus on your business.
12.12.2025
This post covers a fast, reproducible installation of Proxmox VE on a Hetzner Dedicated Server as a single node with ZFS Mirror (RAID1) – without...
09.12.2025
When a Proxmox cluster acts up, it's surprisingly often not Proxmox itself – it's the network: Corosync running over public IPs, storage or VM traffic...
16.06.2025
To protect against data loss, it is important to create regular backups of your Proxmox environment. A cost-effective and secure way to do this is...
Proxmox on Hetzner – Answers to Your Questions
Yes – for many SMB setups, a properly operated single node is absolutely sensible. What matters is backup concept, restore tests, monitoring, and an update process (instead of "HA at all costs").
Single node resolves failures via backup/restore (disaster recovery). An HA cluster offers failover and maintenance without downtime, but requires proper network/storage architecture.
For true quorum-based HA, a 3-node design is standard. 2-node setups are possible but need an additional quorum component/design decision (otherwise split-brain risk).
For dev/test and smaller setups, it can work. For stable performance, local NVMe and predictable latencies, Dedicated is often the better foundation.
Use a stable Proxmox release that matches the Debian base; the Proxmox ISO includes a complete Debian system with Proxmox packages.
Common paths are: Install Debian via rescue and then set up Proxmox – or boot the Proxmox ISO from the rescue system via QEMU/VNC. Hetzner documents both methods.
Yes – e.g., via rescue + QEMU/VNC or automated via script. The repo ariadata/proxmox-hetzner targets exactly "without console access".
Hostname and IP should be final before cluster creation; later changes in cluster context are very unpleasant or not supported.
Proxmox uses the Linux network stack; configuration is possible via GUI or via /etc/network/interfaces. For guests, you typically need Linux bridges (vmbrX).
The web GUI is accessible by default via https://<IP>:8006. For remote admin, also plan SSH (22) and control access ideally via allowlist/VPN.
Don't just expose it to the internet: IP allowlist, VPN/jump host, Proxmox firewall or upstream firewall. Proxmox notes that for remote admin you need rules for GUI (8006) and often SSH (22).
With subscription, the Enterprise Repository is the recommended, stable path. Without subscription, you use public repos; important is that repos are set correctly so updates work.
Yes: A single node on Dedicated (NVMe), clean network basics, immediate PBS/backup target, monitoring + documented update process. That gives you a "minimum viable setup" that can grow to a cluster later.
Private Networks are Layer-3 private links between cloud servers via separate interfaces – ideal for internal traffic like cluster communication or private services.
According to Hetzner docs, the Networks feature is free and traffic on private interfaces is not charged.
No – traffic is private/isolated but not automatically encrypted. For sensitive data: plan TLS or VPN/WireGuard.
Hetzner describes Networks as an L3 feature with IPv4 addressing (and notes limitations). Plan IPv6 separately via other mechanisms.
With standard images, the private network interface is automatically configured via DHCP (hc-utils).
Yes – Hetzner describes coupling a Robot vSwitch with a Cloud Network (subnet with "vSwitch connection").
A vSwitch is (depending on use) the foundation for private L2 connectivity and/or coupling between Dedicated and Cloud Networks. For Proxmox, this is relevant for keeping cluster/storage traffic private and controlled.
Corosync is latency-sensitive; other traffic can cause jitter and affect cluster stability. Best practice is a separate Corosync network; storage traffic should not run on the same network.
On Hetzner, you must take IP/MAC binding seriously; in some scenarios only routed works cleanly. For bridged setups, you may need virtual MACs – otherwise problems up to abuse/block can occur.
We check cluster status, Corosync bindings, and whether traffic really goes through the planned private network (not via public IP). We also validate failover/quorum under load.
Corosync on an overloaded network (storage/backup/migration), MTU mismatch, "accidentally" public traffic for cluster, or Hetzner-specific MAC/IP misconfiguration.
For single node, ZFS is often the sweet spot: fast, stable, simple. For HA clusters, Ceph is interesting because it provides distributed storage – but requires more planning (network, disks, sizing).
Rule of thumb: plan for 2-3x your current VM data needs plus backup buffer and growth. With Ceph, replication adds up (more raw capacity needed).
Yes – typically as "setup", "co-managed" or "fully managed": updates, monitoring, backup control, troubleshooting, and extensions (e.g., cluster growth, storage, network hardening).
CTO, EVA Real Estate, UAE
"I recently worked with Timo and the WZ-IT team, and honestly, it turned out to be one of the best tech decisions I have made for my business. Right from the start, Timo took the time to walk me through every step in a simple and calm way. No matter how many questions I had, he never rushed me. The results speak for themselves. With WZ-IT, we reduced our monthly expenses from $1,300 down to $250. This was a huge win for us."
Data Manager, ARGE, Germany
"With Timo and Robin, you're not only on the safe side technically - you also get the best human support! Whether it's quick help in everyday life or complex IT solutions: the guys from WZ-IT think along with you, act quickly and speak a language you understand. The collaboration is uncomplicated, reliable and always on an equal footing. That makes IT fun - and above all: it works! Big thank you to the team! (translated) "
CEO, Aphy B.V., Netherlands
"WZ-IT manages our Proxmox cluster reliably and professionally. The team handles continuous monitoring and regular updates for us and responds very quickly to any issues or inquiries. They also configure new nodes, systems, and applications that we need to add to our cluster. With WZ-IT's proactive support, our cluster and the business-critical applications running on it remain stable, and high availability is consistently ensured. We value the professional collaboration and the noticeable relief it brings to our daily operations."
CEO, Odiseo Solutions, Spain
"Counting on WZ-IT team was crucial, their expertise and solutions gave us the pace to deploy in production our services, even suggesting and performing improvements over our configuration and setup. We expect to keep counting on them for continuous maintenance of our services and implementation of new solutions."
Timo and Robin from WZ-IT set up a RocketChat server for us - and I couldn't be more satisfied! From the initial consultation to the final implementation, everything was absolutely professional, efficient, and to my complete satisfaction. I particularly appreciate the clear communication, transparent pricing, and the comprehensive expertise that both bring to the table. Even after the setup, they take care of the maintenance, which frees up my time enormously and allows me to focus on other important areas of my business - with the good feeling that our IT is in the best hands. I can recommend WZ-IT without reservation and look forward to continuing our collaboration! (translated)
We have had very good experiences with Mr. Wevelsiep and WZ-IT. The consultation was professional, clearly understandable, and at fair prices. The team not only implemented our requirements but also thought along and proactively. Instead of just processing individual tasks, they provided us with well-founded explanations that strengthened our own understanding. WZ-IT took a lot of pressure off us with their structured approach - that was exactly what we needed and is the reason why we keep coming back. (translated)
Robin and Timo provided excellent support during our migration from AWS to Hetzner! We received truly competent advice and will gladly return to their services in the future. (translated)
WZ-IT set up our Jitsi Meet Server anew - professional, fast, and reliable. (translated)
Our Proxmox Label
OutaCloud offers professional Proxmox support and proactive monitoring for your Hetzner infrastructure.
Whether a specific IT challenge or just an idea – we look forward to the exchange. In a brief conversation, we'll evaluate together if and how your project fits with WZ-IT.
Trusted by leading companies
Timo Wevelsiep & Robin Zins
CEOs of WZ-IT
