Ivo Marino
Contact

Notes from running production.

I'm Ivo, a platform engineer and SRE. I write down what broke, what fixed it, and the numbers.

Read the latestAbout me
storage-node, from ZFS + NFS as Kubernetes Storage: Point-in-Time Recovery Without the Cost
# app bug corrupted the database files, noticed 30 minutes later
$ zfs rollback zroot/k8s-data@2026-04-15-09-00
# cluster hardware gone: clone this morning's offsite snapshot
$ zfs clone remote/k8s-data@2026-04-15 zroot/recovery

Writing

Out-of-Band SSH Tunnel Failover: Why Stability Beats Speed 30 s stable recovery. Kubernetes Pod Autoscaling with KEDA: Queue Depth Beats CPU Every Time 5 to 15 min processing latency. Production Security Updates Without Downtime: Debian, FreeBSD, and OpenBSD Security patches can't wait, but unplanned reboots break production. The update runbook for Debian, FreeBSD, … From Data Science to Production: MLOps CI/CD Pipeline with Real-time Accuracy Monitoring Production machine learning requires more than training good models. This guide covers building a complete … ZFS + NFS as Kubernetes Storage: Point-in-Time Recovery Without the Cost 1 h snapshot interval for every volume. OpenBSD CARP Firewalls in Front of a Private Kubernetes Cluster < 1 s firewall failover, state kept. Scaling MySQL Beyond Kubernetes: When Backups Become The Blocker We ran MySQL in Kubernetes for years until the data scaled from GB to TB. Kubernetes wasn't the … 2026 Relaunch: Infrastructure Lessons from 10+ Years Running Production Relaunching with a focus on pragmatic infrastructure: backup strategies, Kubernetes autoscaling, and lessons …