Post

😮

I always wondered: why bother assigning multiple cores to a pod only to then do clustering inside? Why not just assign a single core and do all clustering at the k8s layer?

Here's what Booking.com shipped, from their own writeup: → 30% fewer pods → 20% less memory per remaining pod → Up to 10% off latency at p75 and p99 And they got there without touching a single line of their rendering code.

The big move was swapping the process manager. They were on pm2 (Node's cluster module). A supervisor process accepts every connection and hands it off. That's an extra hop per request, plus a full duplicate of everything V8 builds at startup.

Wattpm runs your workers as worker threads and lets the kernel hand out connections with SO_REUSEPORT. No supervisor, no IPC pass-through. Each worker accepts straight from the kernel.