2 min lesson
Scale on SLO-relevant signals
Use "Scale on SLO-relevant signals" to tell the cases apart, then choose a response for each one.
Step 1 of 2
Scale on SLO-relevant signalsnot just CPU
CPU is a proxy and often a bad one. A request queue can be backing up while CPU sits at 40%, because the work is I/O-bound or waiting on a model backend. Scale on the thing your users actually feel: p99 latency, queue depth or in-flight request concurrency.
Interactive diagram. Tab through its regions; each focused region shows its detail in the panel below.
diagram: signal-bars
Ranked by how faithfully each tracks user-felt pain at 1M+ DAU scale.