Halved

I run 19 instances of a C program that fetches RSS feeds on a 1vCPU VPS. Each run is short, but over time, the CPU profile felt off – spiky, higher than it should’ve been.

Turns out, the fetch loop was subtly blocking. No threads, just enough delay to cause churn. I rewrote it to run on an event loop – non-blocking I/O, no busy waits. After the change, CPU usage dropped by half. No infra changes, no concurrency hacks. Just better rhythm.

This wasn’t a benchmark stunt. This was about fixing something that felt wrong and watching the machine breathe easier.

Around the same time, I checked crisp’s page payloads. 2.8KB, uncompressed.

That’s one-fifth of a TCP packet1.

Not gzip tricks. Not minification games. Just clean markup, minimal styling, no JS. The whole page fits in a single TCP packet – with room to spare.

These aren’t just engineering wins. They’re reminders of a mindset:

Don’t waste cycles.

Don’t waste packets.

Don’t waste the reader’s attention.

There’s a kind of joy in building software that doesn’t get in the way. It doesn’t call attention to itself. It just runs – fast and quiet.

That’s what I’m chasing with crisp. Every line, every byte – intentional.