Blog
Notes, write-ups, and things I found interesting.
2026-11-01
Failover-Testing a Two-Node UFM HA Cluster: Soft Failover, Service Kill, and a Heartbeat Partition
2026-10-29
A Power Cut at the Rack: An OpenStack Start/Stop Runbook Built from the Aftermath
2026-10-27
Packing an Agent into a Container: Hermes in Docker
2026-10-27
NVIDIA DRA on a Mixed Cluster: Hard Memory Slices with MPS, Time-Slicing on a GB10
2026-10-14
When Calico Reads a Different Object Than the One You Edited
2026-10-14
Making a GPU Visible to Kubernetes: GPU Operator, DCGM, and Two Wrong Values
2026-09-23
Self-Service Persistent Storage on Kubernetes with Cinder CSI
2026-09-14
Stress-Testing Kubernetes on OpenStack: It Was the Storage All Along
2026-09-10
Unblocking a Rancher Cluster Stuck in 'Deleting'
2026-09-10
Provisioning RKE2 from Rancher? Prepare OpenStack First
2026-08-28
Bare-Metal Ceph as the RBD Backend for OpenStack
2026-08-27
Rancher on 3-Node RKE2 Inside OpenStack: Eight Things That Broke
2026-08-26
Benchmarking a Small Cloud: Where 1G Ethernet and HDDs Actually Cap Out
2026-08-13
Membina Lustre Lab di Rocky Linux 9: Dua Server, Tiga Client
2026-08-13
Building a 3-Node OpenStack Cloud with Kolla-Ansible
2026-08-12
Provision Server Bare-Metal dari Jauh dengan MAAS: PXE dan IPMI Tanpa Konsol
2026-08-12
AI Gateway: Satu Bastion Host untuk Semua API Key LLM
2026-08-11
When a Kubernetes Controller Silently Stops Watching One Resource Type
2026-08-11
Membina Mini HPC Cluster dengan Slurm, NFS dan OpenMPI di Proxmox
2026-08-10
Rancher Says 'Cluster Agent Is Not Connected': A Four-Step Fix That Needs No Re-Import
2026-08-07
Public SSH to Kubernetes GPU Pods Through Pangolin: Three Attempts and a Controller Patch
2026-08-07
Does Memory Plus Skills Close the Gap for a Small LLM? A Live Mini-Test
2026-08-05
Pod GPU Crash dengan Exit 127: Bina Image Jupyter + SSH yang Tahan Override
2026-08-04
LLM for Reasoning, Scripts for Execution: What an 8B Model on a CPU Taught Me
2026-08-03
Running a Local LLM on CPU: llama.cpp, Qwen3, and Open WebUI
2026-08-03
Mixture-of-Agents (MOA): Beberapa Model, Satu Jawapan Terbaik
2026-06-19
Troubleshooting NVIDIA UFM HA Single-Node Recovery
2024-02-05
Expanding System Disks and LVM Volumes on RHEL 9 Without Downtime
2022-08-26
Email Approvals with Google Forms, Sheets, and Two Add-ons
2022-08-25
Email Approvals with Microsoft Forms and Power Automate
2018-02-19
Automating Real-Time Security Alerts with Fail2ban and Telegram