McGarrah Technical Blog

Posts in category "proxmox"

Measuring the WAL vs DB Performance Gap on Ceph USB OSDs

Nine of my fifteen Ceph OSDs use WAL-only acceleration while six use DB. I set out to measure the performance gap and discovered the real story isn't WAL vs DB — it's the USB 3.0 hardware ceiling that dominates everything. The matched-hardware comparison shows DB is 5-15% faster on reads, not the 32% that naive cross-node testing suggested.

SSH Key-Based Access to a Proxmox Cluster

Typing passwords every time you SSH into a Proxmox node gets old fast — especially with a six-node cluster. Here's how to set up SSH key authentication and an SSH config so you can just type 'ssh harlan' and be in.

Hybrid Ceph Storage: SSD WAL/DB Acceleration with USB Drive Data

Running Ceph on USB drives sounds crazy until you put the WAL and DB on an SSD. Here's how separating metadata onto a Crucial MX500 transformed my 15-OSD homelab cluster from sluggish to surprisingly capable — at a fraction of all-SSD costs.

Monitoring ZFS Boot Mirror Health in Proxmox 8 Clusters

Automated SMART monitoring and cost planning for ZFS boot mirrors across a six-node Proxmox homelab cluster with mixed SSD/HDD hardware. Track drive health, plan replacements, and manage homelab storage costs effectively.

USB Drive SMART Updates: Fast-Track to the GRUB Solution

New USB drives arrived for my Ceph cluster, and they’re not reporting SMART data. Again. After solving this problem in my October 2025 article, I need to update the configuration with new device IDs and share the lessons learned from running this solution across my entire cluster.

The bottom line: This was absolutely the right decision. SMART monitoring has already caught failing drives before they damaged data, and the performance trade-off is negligible compared to the stability benefits.