Practical articles on AI, DevOps, Cloud, Linux, and infrastructure engineering.
When a service is slow and every dashboard looks green, bpftrace lets you watch the kernel directly. These one-liners found our tail latency.
We had long-lived AWS keys sitting in a datacenter we don't own. IAM Roles Anywhere let us delete every one of them. Here's the real setup.
How we cut auth redirect latency to single-digit milliseconds and ran A/B tests without a flash of wrong content, using Vercel Edge Middleware.
A 900GB events table where every query scanned four years to read one day. Range partitioning by month cut our dashboard queries from 8s to under 200ms.
A cron job silently stopped running for three weeks and nobody knew until the backups were missing. systemd timers give you the logging and status cron never did.
Pure vector search kept missing exact matches like error codes and CLI flags. Adding BM25 back and fusing the two lifted our retrieval recall by 11 points.
After running both in production across a dozen clusters, here's where Flux and Argo CD actually differ and which one we'd reach for now.
A bad deploy used to mean a pager at 2am and a manual rollback. Now Argo Rollouts watches the error rate and aborts the canary itself before anyone wakes up.
Both put SQLite near your users, but they solve replication and write latency very differently. We ran the same schema on both for a month and picked one.
Our support bot kept citing half a sentence and missing the answer that sat two lines below. The culprit wasn't the model, it was how we split the docs.
A 40GB index on a 6GB table was the first sign. Queries were fine until they weren't. Here's how we found the bloat and cleared it with zero downtime.
We moved a rewrite-heavy request path off Lambda@Edge to Workers and cut p95 from 340ms to 41ms. Here's when that swap pays off and when it doesn't.
