I Built a 5-Node Proxmox & Ceph Mini Rack with 17TB NVMe

VirtualizationHowto · Beginner ·📄 Research Papers Explained ·2mo ago
I rebuilt my home lab into a 5-node Proxmox and Ceph cluster using a compact 10-inch mini rack. It has 17TB of all-NVMe storage and dual 10Gb LACP networking. In this video I walk through the full hardware setup, erasure coding design, Ceph networking lessons, VLAN and firewall issues, Talos Kubernetes integration, and why this Proxmox HCI build replaced VMware for my production workloads. Read the full blog post here (and benchmarks!): https://www.virtualizationhowto.com/2026/02/i-built-a-5-node-proxmox-and-ceph-home-lab-with-17tb-and-dual-10gb-lacp/ Get a barebones Minisforum MS-01 (that I built my cluster using): https://geni.us/TtgM Check out the VHT forums to get your questions answered: https://www.virtualizationhowto.com/community/ ★ Skool Community https://www.skool.com/homelabexplorers/about?ref=25f64c297b724689ae81c7dd30ba2c21 ★ Substack URL: bleevht.substack.com ★ Subscribe to the channel: https://www.youtube.com/channel/UCrxcWtpd1IGHG9RbD_9380A?sub_confirmation=1 ★ My blog: https://www.virtualizationhowto.com ★ Twitter: https://twitter.com/vspinmaster ★ LinkedIn: https://www.linkedin.com/in/brandon-lee-vht/ ★ Github: https://github.com/brandonleegit ★ Facebook: https://www.facebook.com/people/VirtualizationHowto/100092747277326/ ★ Discord: https://discord.gg/Zb46NV6mB3 ★ Pinterest: https://www.pinterest.com/brandonleevht/ ⏱ Chapters 00:00 Introduction – 5-Node Proxmox & Ceph Mini Rack 01:07 Shrinking the Lab and Leaving VMware 02:59 Why I Standardized on 5 Uniform MS-01 Nodes 04:49 NVMe Storage Layout and OSD Design 05:41 Migrating Drives to New Hardware 06:31 Bonding, LACP, VLANs, and Network Layout 07:58 Ceph Erasure Coding (3+2 Explained) 09:02 Accidentally Wiping the Wrong NVMe (OSD Recovery) 09:40 10Gb Upgrade Plan and LACP Rollout 10:26 Jumbo Frame Troubleshooting 11:18 VLAN Tagging + Firewall + LACP Issues 13:26 CephFS and Shared Storage 14:11 Running Talos Kubernetes on Proxmox 15:00 Why Five Nodes Was the Right Number 15:35 17TB in a Mini
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

⚡
The ABCs of reading medical research and review papers these days
Learn to critically evaluate medical research papers by accepting nothing at face value, believing no one blindly, and checking everything
Medium · LLM
 ⚡
#1 DevLog Meta-research: I Got Tired of Tab Chaos While Reading Research Papers.
Learn to manage research paper tabs efficiently and apply meta-research techniques to improve productivity
Dev.to AI
 ⚡
How to Set Up a Karpathy-Style Wiki for Your Research Field
Learn to set up a Karpathy-style wiki for your research field to organize and share knowledge effectively
Medium · AI
 ⚡
The Non-Optimality of Scientific Knowledge: Path Dependence, Lock-In, and The Local Minimum Trap
Scientific knowledge may be stuck in a local minimum, hindering optimal progress, and understanding this concept is crucial for advancing research
ArXiv cs.AI

Chapters (15)

Introduction – 5-Node Proxmox & Ceph Mini Rack
1:07 Shrinking the Lab and Leaving VMware
2:59 Why I Standardized on 5 Uniform MS-01 Nodes
4:49 NVMe Storage Layout and OSD Design
5:41 Migrating Drives to New Hardware
6:31 Bonding, LACP, VLANs, and Network Layout
7:58 Ceph Erasure Coding (3+2 Explained)
9:02 Accidentally Wiping the Wrong NVMe (OSD Recovery)
9:40 10Gb Upgrade Plan and LACP Rollout
10:26 Jumbo Frame Troubleshooting
11:18 VLAN Tagging + Firewall + LACP Issues
13:26 CephFS and Shared Storage
14:11 Running Talos Kubernetes on Proxmox
15:00 Why Five Nodes Was the Right Number
15:35 17TB in a Mini
Up next
Microsoft Research Forum | Season 2, Episode 4
Microsoft Research
Watch →